Agent trace

Script completed
Wall time 0.1 seconds
Output:

/app
/task/requirements.txt
/task/current_model/two_tower_model.py
/task/current_model/train_current_model.py
/task/current_model/two_tower_model.py
/task/current_model/train_current_model.py
/task/evaluate_public.py
/task/ranking_evaluation.py
/task/data/validation_preference_state.parquet
/task/data/test_eligible_candidates.npz
/task/data/val_dislikes.parquet
/task/data/val_unlikes.parquet
/task/data/train_dislikes.parquet
/task/data/validation_eligible_candidates.npz
/task/data/train_listens.parquet
/task/data/train_likes.parquet
/task/data/train_undislikes.parquet
/task/data/val_undislikes.parquet
/task/data/val_listens.parquet
/task/data/val_likes.parquet
/task/data/train_unlikes.parquet
/task/data/candidate_catalog.parquet
/task/data/test_preference_state.parquet
/task/data/target_users.parquet
340M	/task/data
100K	/task/current_model
#!/usr/bin/env python3
"""Train the Yambda windowed two-tower baseline.

Every catalog listen with at least 50 percent completion is a sequence token.
Within each selected chronological window, every adjacent target contributes a
loss.  The fast default retains each user's most recent 128 training targets and
16 held-out validation targets; passing zero for either cap restores the
uncapped behavior for that side of the split.  A 100-step truncated-BPTT block
computes all of its timestep losses and carries the detached GRU hidden state
into the next block.

The model is a pure two-tower retriever: no user-ID embedding, no output
normalization, raw dot-product retrieval, sample-weighted binary cross entropy,
and 24 uniform plus eight propensity-corrected unique in-batch negatives. Every
selected adjacent target retains a nonzero weight. Only files under the supplied
public directory are read.
"""
from __future__ import annotations

import argparse
import json
import random
import sys
import time
from dataclasses import asdict, dataclass
from pathlib import Path

import numpy as np
import pandas as pd
import torch
from torch import nn
from torch.nn import functional as F

import two_tower_model as base


CACHE_VERSION = 2


@dataclass(frozen=True)
class Config:
    bptt_steps: int = 100
    user_batch_size: int = 64
    embedding_dim: int = 192
    hidden_dim: int = 192
    user_hidden_1: int = 512
    user_hidden_2: int = 256
    item_hidden_1: int = 512
    item_hidden_2: int = 256
    dropout: float = 0.05
    epochs: int = 1
    learning_rate: float = 1.0e-3
    weight_decay: float = 1.0e-5
    gradient_clip: float = 2.0
    loss_microbatch_size: int = 65_536
    uniform_negatives: int = 24
    inbatch_negatives: int = 8
    inbatch_correction_power: float = 0.5
    inbatch_correction_min: float = 0.25
    inbatch_correction_max: float = 4.0
    negative_filter_scope: str = "full-training-history"
    target_weighting: str = "organic-strong"
    ordinary_target_weight: float = 0.25
    organic_strong_target_weight: float = 1.0
    organic_like_target_weight: float = 3.0
    discovery_horizon_days: int = 7
    validation_fraction: float = 0.10
    max_train_targets_per_user: int = 128
    max_validation_targets_per_user: int = 16
    early_stopping_patience: int = 1
    early_stopping_min_delta: float = 1.0e-4
    seed: int = 29


@dataclass(frozen=True)
class CandidateSet:
    uids: np.ndarray
    item_ids: np.ndarray
    packed: np.ndarray

    @classmethod
    def read(cls, path: Path) -> "CandidateSet":
        with np.load(path, allow_pickle=False) as artifact:
            result = cls(
                uids=artifact["uids"].astype(np.int64, copy=True),
                item_ids=artifact["item_ids"].astype(np.int64, copy=True),
                packed=artifact["packed_eligible"].astype(np.uint8, copy=True),
            )
        expected = (len(result.uids), (len(result.item_ids) + 7) // 8)
        if result.packed.shape != expected:
            raise ValueError(
                f"invalid candidate artifact shape {result.packed.shape}; "
                f"expected {expected}"
            )
        return result


@dataclass(frozen=True)
class SequenceData:
    item_ids: np.ndarray
    item_features: np.ndarray
    user_ids: np.ndarray
    offsets: np.ndarray
    sequence_timestamps: np.ndarray
    sequence_items: np.ndarray
    event_features: np.ndarray
    activity_features: np.ndarray
    state_ids: np.ndarray
    liked_states: np.ndarray
    disliked_states: np.ndarray
    state_counts: np.ndarray
    inference_user_rows: np.ndarray
    inference_liked_items: np.ndarray
    inference_disliked_items: np.ndarray
    inference_user_features: np.ndarray

    @property
    def lengths(self) -> np.ndarray:
        return np.diff(self.offsets)

    @property
    def target_count(self) -> int:
        return int(np.maximum(self.lengths - 1, 0).sum())


@dataclass(frozen=True)
class TargetPartition:
    """A contiguous recent target window and its chronological BCE split."""

    window_starts: np.ndarray
    training_counts: np.ndarray
    validation_counts: np.ndarray
    history_training_counts: np.ndarray

    @property
    def selected_count(self) -> int:
        return int(self.training_counts.sum() + self.validation_counts.sum())


def log(message: str) -> None:
    print(message, file=sys.stderr, flush=True)


def seed_everything(seed: int) -> None:
    random.seed(seed)
    np.random.seed(seed)
    torch.manual_seed(seed)


def model_config(config: Config) -> base.TowerConfig:
    """Map the dense trainer configuration onto the unchanged tower."""
    return base.TowerConfig(
        sequence_length=config.bptt_steps,
        embedding_dim=config.embedding_dim,
        hidden_dim=config.hidden_dim,
        user_hidden_1=config.user_hidden_1,
        user_hidden_2=config.user_hidden_2,
        item_hidden_1=config.item_hidden_1,
        item_hidden_2=config.item_hidden_2,
        dropout=config.dropout,
        epochs=config.epochs,
        learning_rate=config.learning_rate,
        weight_decay=config.weight_decay,
        gradient_clip=config.gradient_clip,
        uniform_negatives=config.uniform_negatives,
        inbatch_negatives=config.inbatch_negatives,
        inbatch_correction_power=config.inbatch_correction_power,
        inbatch_correction_min=config.inbatch_correction_min,
        inbatch_correction_max=config.inbatch_correction_max,
        seed=config.seed,
    )


def append_state_snapshot(
    active_likes: dict[int, int],
    active_dislikes: dict[int, int],
    n_items: int,
    liked_states: list[np.ndarray],
    disliked_states: list[np.ndarray],
    state_counts: list[tuple[int, int]],
) -> int:
    liked_states.append(base.pack_active_items(active_likes, base.LIKE_ITEMS, n_items))
    disliked_states.append(
        base.pack_active_items(active_dislikes, base.DISLIKE_ITEMS, n_items)
    )
    state_counts.append((len(active_likes), len(active_dislikes)))
    return len(liked_states) - 1


def causal_activity_features(
    timestamps: np.ndarray,
    items: np.ndarray,
    organic: np.ndarray,
    completion: np.ndarray,
) -> np.ndarray:
    """Compute the first four reviewed user features at every event cutoff."""
    length = len(items)
    result = np.zeros((length, 4), dtype=np.float16)
    if not length:
        return result
    left_rows = np.searchsorted(
        timestamps,
        timestamps - base.PROFILE_LOOKBACK_DAYS * base.DAY,
        side="left",
    )
    rows = np.arange(length, dtype=np.int64)
    counts = rows - left_rows + 1
    organic_sum = np.cumsum(organic.astype(np.float64))
    completion_sum = np.cumsum(np.minimum(completion, 100).astype(np.float64))
    before_organic = np.where(
        left_rows > 0, organic_sum[np.maximum(left_rows - 1, 0)], 0.0
    )
    before_completion = np.where(
        left_rows > 0, completion_sum[np.maximum(left_rows - 1, 0)], 0.0
    )

    unique_counts = np.empty(length, dtype=np.int32)
    frequencies: dict[int, int] = {}
    left = 0
    for right, raw_item in enumerate(items):
        item = int(raw_item)
        frequencies[item] = frequencies.get(item, 0) + 1
        required_left = int(left_rows[right])
        while left < required_left:
            old_item = int(items[left])
            remaining = frequencies[old_item] - 1
            if remaining:
                frequencies[old_item] = remaining
            else:
                del frequencies[old_item]
            left += 1
        unique_counts[right] = len(frequencies)

    result[:, 0] = (np.log1p(counts) / 8.0).astype(np.float16)
    result[:, 1] = (np.log1p(unique_counts) / 6.0).astype(np.float16)
    result[:, 2] = (
        (organic_sum - before_organic) / np.maximum(counts, 1)
    ).astype(np.float16)
    result[:, 3] = (
        (completion_sum - before_completion)
        / np.maximum(counts, 1)
        / 100.0
    ).astype(np.float16)
    return result


def build_sequence_parts(
    listens: base.ListenEvents,
    explicit: base.ExplicitEvents,
    n_items: int,
    liked_states: list[np.ndarray],
    disliked_states: list[np.ndarray],
    state_counts: list[tuple[int, int]],
) -> tuple[np.ndarray, np.ndarray, np.ndarray, np.ndarray, np.ndarray] | None:
    qualifying = listens.completion_pct >= base.LISTEN_POSITIVE_THRESHOLD
    timestamps = listens.timestamps[qualifying].astype(np.int64, copy=False)
    items = listens.items[qualifying].astype(np.uint16, copy=False)
    organic = listens.organic[qualifying].astype(np.float32, copy=False)
    completion = listens.completion_pct[qualifying].astype(np.float32, copy=False)
    if not len(items):
"""Shared public-data primitives for the Yambda two-tower baseline."""
from __future__ import annotations

import sys
from dataclasses import dataclass
from pathlib import Path
from typing import Iterator

import numpy as np
import pandas as pd
import pyarrow.parquet as pq
import torch
from torch import nn


DAY = 86_400
TRAIN_END = 24_786_800
VALIDATION_END = 25_393_400
LISTEN_POSITIVE_THRESHOLD = 50
PROFILE_LOOKBACK_DAYS = 120
LIKE_ITEMS = 48
DISLIKE_ITEMS = 24
TOP_N = 100


@dataclass(frozen=True)
class TowerConfig:
    sequence_length: int = 100
    embedding_dim: int = 192
    hidden_dim: int = 192
    user_hidden_1: int = 512
    user_hidden_2: int = 256
    item_hidden_1: int = 512
    item_hidden_2: int = 256
    dropout: float = 0.05
    epochs: int = 1
    learning_rate: float = 1.0e-3
    weight_decay: float = 1.0e-5
    gradient_clip: float = 2.0
    uniform_negatives: int = 24
    inbatch_negatives: int = 8
    inbatch_correction_power: float = 0.5
    inbatch_correction_min: float = 0.25
    inbatch_correction_max: float = 4.0
    seed: int = 29


@dataclass(frozen=True)
class ListenEvents:
    timestamps: np.ndarray
    items: np.ndarray
    organic: np.ndarray
    completion_pct: np.ndarray


@dataclass(frozen=True)
class ExplicitEvents:
    timestamps: np.ndarray
    items: np.ndarray
    channel: np.ndarray
    active: np.ndarray
    organic_like: np.ndarray


def log(message: str) -> None:
    print(message, file=sys.stderr, flush=True)


def build_item_features(catalog: pd.DataFrame) -> np.ndarray:
    """Return four standardized features built only from the public catalog."""
    positives = catalog.positive_listens.to_numpy(dtype=np.float64, copy=False)
    organic = catalog.organic_positive_listens.to_numpy(dtype=np.float64, copy=False)
    popularity_rank = catalog.popularity_rank.to_numpy(dtype=np.float64, copy=False)
    features = np.column_stack(
        [
            np.log1p(positives),
            np.log1p(organic),
            organic / np.maximum(positives, 1.0),
            1.0 - (popularity_rank - 1.0) / max(len(catalog) - 1, 1),
        ]
    )
    means = features.mean(axis=0, keepdims=True)
    scales = np.maximum(features.std(axis=0, keepdims=True), 1.0e-6)
    standardized = ((features - means) / scales).astype(np.float32)
    if not np.isfinite(standardized).all():
        raise RuntimeError("catalog features contain non-finite values")
    return standardized


def _combine_listen_chunks(parts: list[ListenEvents]) -> ListenEvents:
    if len(parts) == 1:
        return parts[0]
    timestamps = np.concatenate([part.timestamps for part in parts])
    items = np.concatenate([part.items for part in parts])
    organic = np.concatenate([part.organic for part in parts])
    completion = np.concatenate([part.completion_pct for part in parts])
    order = np.argsort(timestamps, kind="stable")
    return ListenEvents(
        timestamps=timestamps[order],
        items=items[order],
        organic=organic[order],
        completion_pct=completion[order],
    )


def iter_listen_users(
    path: Path, item_index: pd.Index
) -> Iterator[tuple[int, ListenEvents]]:
    """Stream one uid-sorted public listen file one user at a time."""
    parquet = pq.ParquetFile(path)
    pending_uid: int | None = None
    pending: list[ListenEvents] = []
    previous_uid = -1
    for batch in parquet.iter_batches(
        batch_size=750_000,
        columns=["uid", "timestamp", "item_id", "is_organic", "played_ratio_pct"],
    ):
        frame = batch.to_pandas()
        mapped = item_index.get_indexer(frame.item_id.to_numpy(dtype=np.int64))
        keep = mapped >= 0
        if not np.any(keep):
            continue
        uids = frame.uid.to_numpy(dtype=np.int64, copy=False)[keep]
        timestamps = frame.timestamp.to_numpy(dtype=np.int64, copy=False)[keep]
        items = mapped[keep].astype(np.int32, copy=False)
        organic = frame.is_organic.to_numpy(dtype=np.uint8, copy=False)[keep]
        completion = frame.played_ratio_pct.to_numpy(dtype=np.uint16, copy=False)[keep]
        if np.any(uids[1:] < uids[:-1]):
            raise RuntimeError(f"{path.name} is not sorted by uid")
        boundaries = np.r_[
            0,
            np.flatnonzero(uids[1:] != uids[:-1]) + 1,
            len(uids),
        ]
        for start, end in zip(boundaries[:-1], boundaries[1:]):
            uid = int(uids[start])
            part = ListenEvents(
                timestamps[start:end].copy(),
                items[start:end].copy(),
                organic[start:end].copy(),
                completion[start:end].copy(),
            )
            if pending_uid is None:
                pending_uid = uid
            elif uid != pending_uid:
                if pending_uid < previous_uid:
                    raise RuntimeError(f"{path.name} user order regressed")
                yield pending_uid, _combine_listen_chunks(pending)
                previous_uid = pending_uid
                pending_uid = uid
                pending = []
            pending.append(part)
    if pending_uid is not None:
        yield pending_uid, _combine_listen_chunks(pending)


def merge_listen_streams(
    paths: list[Path], item_index: pd.Index
) -> Iterator[tuple[int, ListenEvents]]:
    """Merge uid-sorted public listen files without materializing them."""
    streams = [iter(iter_listen_users(path, item_index)) for path in paths]
    heads: list[tuple[int, ListenEvents] | None] = [
        next(stream, None) for stream in streams
    ]
    while any(head is not None for head in heads):
        uid = min(head[0] for head in heads if head is not None)
        parts: list[ListenEvents] = []
        for position, head in enumerate(heads):
            if head is not None and head[0] == uid:
                parts.append(head[1])
                heads[position] = next(streams[position], None)
        yield uid, _combine_listen_chunks(parts)


def load_explicit_events(
    data: Path,
    prefixes: tuple[str, ...],
    item_index: pd.Index,
) -> dict[int, ExplicitEvents]:
    """Load public explicit actions as chronological state changes."""
    specifications = (
        ("likes", 0, 1, 0),
        ("unlikes", 0, 0, 1),
        ("dislikes", 1, 1, 0),
        ("undislikes", 1, 0, 1),
    )
    parts: list[pd.DataFrame] = []
    for family, channel, active, tie_priority in specifications:
        for prefix in prefixes:
            frame = pd.read_parquet(
                data / f"{prefix}_{family}.parquet",
                columns=["uid", "timestamp", "item_id", "is_organic"],
            )
            mapped = item_index.get_indexer(
                frame.item_id.to_numpy(dtype=np.int64, copy=False)
            )
            keep = mapped >= 0
            if not np.any(keep):
                continue
            retained = frame.loc[keep, ["uid", "timestamp", "is_organic"]].copy()
            retained["item"] = mapped[keep].astype(np.int32, copy=False)
            retained["channel"] = np.int8(channel)
            retained["active"] = np.int8(active)
            retained["tie_priority"] = np.int8(tie_priority)
            retained["organic_like"] = np.int8(
                family == "likes"
            ) * retained.is_organic.astype(np.int8)
            parts.append(retained.drop(columns="is_organic"))
    if not parts:
        return {}
    events = pd.concat(parts, ignore_index=True)
    events = events.sort_values(
        ["uid", "timestamp", "tie_priority"], kind="mergesort"
    ).reset_index(drop=True)
    result: dict[int, ExplicitEvents] = {}
    for uid, rows in events.groupby("uid", sort=False):
        result[int(uid)] = ExplicitEvents(
            timestamps=rows.timestamp.to_numpy(dtype=np.int64, copy=True),
            items=rows.item.to_numpy(dtype=np.int32, copy=True),
            channel=rows.channel.to_numpy(dtype=np.int8, copy=True),
            active=rows.active.to_numpy(dtype=np.int8, copy=True),
            organic_like=rows.organic_like.to_numpy(dtype=np.int8, copy=True),
        )
    log(f"loaded explicit events: rows={len(events):,} users={len(result):,}")
    return result


def empty_explicit_events() -> ExplicitEvents:
    return ExplicitEvents(
        timestamps=np.empty(0, dtype=np.int64),
        items=np.empty(0, dtype=np.int32),
        channel=np.empty(0, dtype=np.int8),
        active=np.empty(0, dtype=np.int8),
        organic_like=np.empty(0, dtype=np.int8),
    )


def pack_active_items(
    active: dict[int, int], width: int, padding_item: int
) -> np.ndarray:
    packed = np.full(width, padding_item, dtype=np.uint16)
    if not active:
        return packed
    ordered = sorted(active.items(), key=lambda pair: (-pair[1], pair[0]))[:width]
    packed[: len(ordered)] = np.fromiter(
        (item for item, _ in ordered), dtype=np.uint16, count=len(ordered)
    )
    return packed


def load_inference_state(
    path: Path,
    item_index: pd.Index,
    uids: np.ndarray,
    n_items: int,
) -> tuple[np.ndarray, np.ndarray, np.ndarray, np.ndarray]:
    """Pack the task-provided active explicit state."""
    state = pd.read_parquet(path, columns=["uid", "item_id", "state"])
    mapped = item_index.get_indexer(state.item_id.to_numpy(dtype=np.int64))
    keep = mapped >= 0

Script completed
Wall time 0.1 seconds
Output:

Warning: truncated output (original token count: 16499)
Total output lines: 1441

/task/current_model/two_tower_model.py:40:    uniform_negatives: int = 24
/task/current_model/two_tower_model.py:41:    inbatch_negatives: int = 8
/task/current_model/two_tower_model.py:73:    popularity_rank = catalog.popularity_rank.to_numpy(dtype=np.float64, copy=False)
/task/current_model/two_tower_model.py:79:            1.0 - (popularity_rank - 1.0) / max(len(catalog) - 1, 1),
/task/current_model/two_tower_model.py:346:def invalid_negative_mask(
/task/current_model/two_tower_model.py:347:    negatives: torch.Tensor,
/task/current_model/two_tower_model.py:353:    invalid = negatives.eq(targets[:, None])
/task/current_model/two_tower_model.py:354:    invalid |= negatives[:, :, None].eq(context_items[:, None, :]).any(dim=2)
/task/current_model/two_tower_model.py:355:    invalid |= negatives[:, :, None].eq(liked_items[:, None, :]).any(dim=2)
/task/current_model/two_tower_model.py:356:    for column in range(1, negatives.shape[1]):
/task/current_model/two_tower_model.py:357:        invalid[:, column] |= negatives[:, column, None].eq(
/task/current_model/two_tower_model.py:358:            negatives[:, :column]
/task/current_model/two_tower_model.py:363:def draw_filtered_mixed_negatives(
/task/current_model/two_tower_model.py:374:    """Draw uniform and unique-target in-batch negatives."""
/task/current_model/two_tower_model.py:406:    negatives_cpu = torch.cat([uniform, inbatch], dim=1)
/task/current_model/two_tower_model.py:407:    correction_cpu = torch.ones_like(negatives_cpu, dtype=torch.float32)
/task/current_model/two_tower_model.py:412:    negatives = negatives_cpu.to(device)
/task/current_model/two_tower_model.py:415:        invalid = invalid_negative_mask(
/task/current_model/two_tower_model.py:416:            negatives, targets, context_items, liked_items
/task/current_model/two_tower_model.py:419:            return negatives, correction
/task/current_model/two_tower_model.py:426:        negatives[invalid] = replacements
/task/current_model/two_tower_model.py:428:    invalid = invalid_negative_mask(
/task/current_model/two_tower_model.py:429:        negatives, targets, context_items, liked_items
/task/current_model/two_tower_model.py:432:        raise RuntimeError("mixed negative resampling failed false-negative filter")
/task/current_model/two_tower_model.py:433:    return negatives, correction
/task/current_model/train_current_model.py:6:loss.  The fast default retains each user's most recent 128 training targets and
/task/current_model/train_current_model.py:9:computes all of its timestep losses and carries the detached GRU hidden state
/task/current_model/train_current_model.py:13:normalization, raw dot-product retrieval, sample-weighted binary cross entropy,
/task/current_model/train_current_model.py:14:and 24 uniform plus eight propensity-corrected unique in-batch negatives. Every
/task/current_model/train_current_model.py:55:    loss_microbatch_size: int = 65_536
/task/current_model/train_current_model.py:56:    uniform_negatives: int = 24
/task/current_model/train_current_model.py:57:    inbatch_negatives: int = 8
/task/current_model/train_current_model.py:61:    negative_filter_scope: str = "full-training-history"
/task/current_model/train_current_model.py:127:class TargetPartition:
/task/current_model/train_current_model.py:165:        uniform_negatives=config.uniform_negatives,
/task/current_model/train_current_model.py:166:        inbatch_negatives=config.inbatch_negatives,
/task/current_model/train_current_model.py:342:    public: Path, stage: str, config: Config
/task/current_model/train_current_model.py:346:        "popularity_rank"
/task/current_model/train_current_model.py:354:    if stage == "validation":
/task/current_model/train_current_model.py:463:        f"prepared stage={stage} sequence_users={len(prepared.user_ids):,} "
/task/current_model/train_current_model.py:471:def cache_metadata(stage: str, config: Config) -> dict[str, object]:
/task/current_model/train_current_model.py:474:        "stage": stage,
/task/current_model/train_current_model.py:477:        "event_time_feature": "exp-negative-gap-over-60-days",
/task/current_model/train_current_model.py:482:    path: Path, prepared: SequenceData, stage: str, config: Config
/task/current_model/train_current_model.py:487:        metadata=np.asarray(json.dumps(cache_metadata(stage, config), sort_keys=True)),
/task/current_model/train_current_model.py:493:def load_cache(path: Path, stage: str, config: Config) -> SequenceData:
/task/current_model/train_current_model.py:496:        expected = cache_metadata(stage, config)
/task/current_model/train_current_model.py:513:    stage: str,
/task/current_model/train_current_model.py:519:        if stage == "validation"
/task/current_model/train_current_model.py:524:        prepared = load_cache(cache, stage, config)
/task/current_model/train_current_model.py:528:    prepared, built_eligibility = prepare_data(public, stage, config)
/task/current_model/train_current_model.py:530:        save_cache(cache, prepared, stage, config)
/task/current_model/train_current_model.py:603:        f"full-history false-negative filter: users={len(prepared.user_ids):,} "
/task/current_model/train_current_model.py:609:def invalid_full_history_negatives(
/task/current_model/train_current_model.py:610:    negatives: np.ndarray,
/task/current_model/train_current_model.py:616:    """Return row-level invalid negatives using the complete training prefix."""
/task/current_model/train_current_model.py:617:    byte_columns = negatives >> 3
/task/current_model/train_current_model.py:618:    bit_columns = negatives & 7
/task/current_model/train_current_model.py:621:    invalid |= negatives == targets[:, None]
/task/current_model/train_current_model.py:622:    invalid |= (negatives[:, :, None] == liked_items[:, None, :]).any(axis=2)
/task/current_model/train_current_model.py:623:    for column in range(1, negatives.shape[1]):
/task/current_model/train_current_model.py:625:            negatives[:, column, None] == negatives[:, :column]
/task/current_model/train_current_model.py:630:def draw_full_history_filtered_negatives(
/task/current_model/train_current_model.py:641:    """Draw mixed negatives and reject all known public-training positives."""
/task/current_model/train_current_model.py:647:        (batch_size, config.uniform_negatives),
/task/current_model/train_current_model.py:653:    if config.inbatch_negatives:
/task/current_model/train_current_model.py:656:            config.inbatch_negatives, max(len(unique_targets) - 1, 0)
/task/current_model/train_current_model.py:672:        if corrected_count < config.inbatch_negatives:
/task/current_model/train_current_model.py:675:                (batch_size, config.inbatch_negatives - corrected_count),
/task/current_model/train_current_model.py:681:    negatives = torch.cat([uniform, inbatch], dim=1).numpy()
/task/current_model/train_current_model.py:682:    correction = np.ones_like(negatives, dtype=np.float32)
/task/current_model/train_current_model.py:685:            :, config.uniform_negatives : config.uniform_negatives + corrected_count
/task/current_model/train_current_model.py:688:        invalid = invalid_full_history_negatives(
/task/current_model/train_current_model.py:689:            negatives,
/task/current_model/train_current_model.py:697:                torch.from_numpy(negatives).to(device),
/task/current_model/train_current_model.py:706:        negatives[invalid] = replacements
/task/current_model/train_current_model.py:709:    invalid = invalid_full_history_negatives(
/task/current_model/train_current_model.py:710:        negatives,
/task/current_model/train_current_model.py:717:        raise RuntimeError("full-history negative resampling failed")
/task/current_model/train_current_model.py:719:        torch.from_numpy(negatives).to(device),
/task/current_model/train_current_model.py:724:def draw_training_negatives(
/task/current_model/train_current_model.py:736:    if config.negative_filter_scope == "full-training-history":
/task/current_model/train_current_model.py:738:            raise RuntimeError("full-history negative filter was not built")
/task/current_model/train_current_model.py:739:        return draw_full_history_filtered_negatives(
/task/current_model/train_current_model.py:750:    return base.draw_filtered_mixed_negatives(
/task/current_model/train_current_model.py:755:        config.uniform_negatives,
/task/current_model/train_current_model.py:756:        config.inbatch_negatives,
/task/current_model/train_current_model.py:816:    negatives: torch.Tensor,
/task/current_model/train_current_model.py:818:    all_items = torch.cat([positives, negatives.reshape(-1)])
/task/current_model/train_current_model.py:822:    negative_vectors = encoded[inverse[len(positives) :]].reshape(
/task/current_model/train_current_model.py:823:        len(positives), negatives.shape[1], -1
/task/current_model/train_current_model.py:825:    return positive_vectors, negative_vectors
/task/current_model/train_current_model.py:845:def corrected_negative_loss(
/task/current_model/train_current_model.py:851:    total = config.uniform_negatives + config.inbatch_negatives
/task/current_model/train_current_model.py:853:    if config.uniform_negatives:
/task/current_model/train_current_model.py:854:        result += config.uniform_negatives * raw[
/task/current_model/train_current_model.py:855:            :, : config.uniform_negatives
/task/current_model/train_current_model.py:857:    if config.inbatch_negatives:
/task/current_model/train_current_model.py:858:        selected = slice(config.uniform_negatives, total)
/task/current_model/train_current_model.py:860:        result += config.inbatch_negatives * (
/task/current_model/train_current_model.py:880:        raise RuntimeError("chronological target partition produced negative counts")
/task/current_model/train_current_model.py:893:) -> TargetPartition:
/task/current_model/train_current_model.py:906:    return TargetPartition(
/task/current_model/train_current_model.py:915:    public: Path, stage: str, item_ids: np.ndarray
/task/current_model/train_current_model.py:918:    prefixes = ("train",) if stage == "validation" else ("train", "val")
/task/current_model/train_current_model.py:957:    stage: str,
/task/current_model/train_current_model.py:978:                public, stage, prepared.item_ids
/task/current_model/train_current_model.py:981:                base.TRAIN_END if stage == "validation" else base.VALIDATION_END
/task/current_model/train_current_model.py:1119:    negatives: torch.Tensor,
/task/current_model/train_current_model.py:1120:    negative_weights: torch.Tensor,
/task/current_model/train_current_model.py:1121:    sample_weights: np.ndarray,
/task/current_model/train_current_model.py:1127:    total_weight = float(sample_weights.sum())
/task/current_model/train_current_model.py:1129:        raise RuntimeError("target block has no positive sample weight")
/task/current_model/train_current_model.py:1132:        "loss_sum": 0.0,
/task/current_model/train_current_model.py:1134:        "negative_sum": 0.0,
/task/current_model/train_current_model.py:1138:    for begin in range(0, target_count, config.loss_microbatch_size):
/task/current_model/train_current_model.py:1139:        end = min(begin + config.loss_microbatch_size, target_count)
/task/current_model/train_current_model.py:1162:        positive_vectors, negative_vectors = candidate_vectors(
/task/current_model/train_current_model.py:1165:            negatives[begin:end],
/task/current_model/train_current_model.py:1168:        negative_logits = torch.einsum(
/task/current_model/train_current_model.py:1169:            "bd,bkd->bk", query_vectors, negative_vectors
/task/current_model/train_current_model.py:1171:        positive_loss = F.softplus(-positive_logits)
/task/current_model/train_current_model.py:1172:        negative_loss = corrected_negative_loss(
/task/current_model/train_current_model.py:1173:            negative_logits, negative_weights[begin:end], config
/task/current_model/train_current_model.py:1176:            sample_weights[begin:end].astype(np.float32, copy=False)
/task/current_model/train_current_model.py:1178:        loss_sum = (
/task/current_model/train_current_model.py:1179:            selected_weights * (positive_loss + negative_loss) / 2.0
/task/current_model/train_current_model.py:1181:        if not bool(torch.isfinite(loss_sum)):
/task/current_model/train_current_model.py:1182:            raise RuntimeError("dense next-item training produced non-finite loss")
/task/current_model/train_current_model.py:1184:            (loss_sum / total_weight).backward()
/task/current_model/train_current_model.py:1188:        statistics["loss_sum"] += float(loss_sum.detach().cpu())
/task/current_model/train_current_model.py:1190:        statistics["negative_sum"] += float(negative_logits.detach().sum().cpu())
/task/current_model/train_current_model.py:1192:            (positive_logits.detach()[:, None] > negative_logits.detach()).sum().cpu()
/task/current_model/train_current_model.py:1227:    negative_count = config.uniform_negatives + config.inbatch_negatives
/task/current_model/train_current_model.py:1228:    total_loss = 0.0
/task/current_model/train_current_model.py:1232:    total_negative = 0.0
/task/current_model/train_current_model.py:1293:            negatives, negative_weights = draw_training_negatives(
/task/current_model/train_current_model.py:1314:                negatives,
/task/current_model/train_current_model.py:1315:                negative_weights,
/task/current_model/train_current_model.py:1327:            total_loss += statistics["loss_sum"]
/task/current_model/train_current_model.py:1331:            total_negative += statistics["negative_sum"]
/task/current_model/train_current_model.py:1337:                batch_bce = statistics["loss_sum"] / max(
/task/current_model/train_current_model.py:1340:                running_bce = total_loss / max(total_weight, 1.0e-12)
/task/current_model/train_current_model.py:1351:        "loss": total_loss / max(total_weight, 1.0e-12),
/task/current_model/train_current_model.py:1353:        "negative_logit": total_negative / max(total_targets * negative_count, 1),
/task/current_model/train_current_model.py:1355:        / max(total_targets * negative_count, 1),
/task/current_model/train_current_model.py:1388:    total_loss = 0.0
/task/current_model/train_current_model.py:1449:            negatives, negative_weights = draw_training_negatives(
/task/current_model/train_current_model.py:1469:                negatives,
/task/current_model/train_current_model.py:1470:                negative_weights,
/task/current_model/train_current_model.py:1475:            total_loss += statistics["loss_sum"]
/task/current_model/train_current_model.py:1481:        "validation_loss": total_loss / max(total_weight, 1.0e-12),
/task/current_model/train_current_model.py:1521:def train_model(
/task/current_model/train_current_model.py:1523:    stage: str,
/task/current_model/train_current_model.py:1560:        stage,
/task/current_model/train_current_model.py:1567:        if config.negative_filter_scope == "full-training-history"
/task/current_model/train_current_model.py:1571:    best_loss = float("inf")
/task/current_model/train_current_model.py:1601:            "negative_filter_scope", "last-100"
/task/current_model/train_current_model.py:1629:            stored_filter_scope != config.negative_filter_scope
/task/current_model/train_current_model.py:1657:            prior.pop("validation_loss", None)
/task/current_model/train_current_model.py:1660:                f"{stored_filter_scope}->{config.negative_filter_scope}, "
/task/current_model/train_current_model.py:1666:        if "validation_loss" not in prior:
/task/current_model/train_current_model.py:1682:        best_loss = float(prior["validation_loss"])
/task/current_model/train_current_model.py:1687:            f"loss={best_loss:.6f}"
/task/current_model/train_current_model.py:1731:            diagnostics["validation_loss"]
/task/current_model/train_current_model.py:1732:            < best_loss - config.early_stopping_min_delta
/task/current_model/train_current_model.py:1735:            best_loss = diagnostics["validation_loss"]
/task/current_model/train_current_model.py:1754:            f"epoch={epoch}/{config.epochs} train_loss={diagnostics['loss']:.5f} "
/task/current_model/train_current_model.py:1755:            f"validation_loss={diagnostics['validation_loss']:.5f} "
/task/current_model/train_current_model.py:1766:                f"best_epoch={best_epoch} best_validation_loss={best_loss:.6f}"
/task/current_model/train_current_model.py:1776:        f"loss={best_loss:.6f}"
/task/current_model/train_current_model.py:1861:def rank_candidates(
/task/current_model/train_current_model.py:1867:    ranking_batch_size: int,
/task/current_model/train_current_model.py:1882:    for start in range(0, len(eligibility.uids), ranking_batch_size):
/task/current_model/train_current_model.py:1883:        end = min(start + ranking_batch_size, len(eligibility.uids))
/task/current_model/train_current_model.py:1896:                (uid, int(prepared.item_ids[column]), rank)
/task/current_model/train_current_model.py:1897:                for rank, column in enumerate(columns, start=1)
/task/current_model/train_current_model.py:1900:            log(f"ranked users={end:,}/{len(eligibility.uids):,}")
/task/current_model/train_current_model.py:1909:    return pd.DataFrame(rows, columns=["uid", "item_id", "rank"]), diagnostics
/task/current_model/train_current_model.py:1912:def write_ranking(frame: pd.DataFrame, output: Path) -> None:
/task/current_model/train_current_model.py:1922:def main() -> int:
/task/current_model/train_current_model.py:1923:    parser = argparse.ArgumentParser(description=__doc__)
/task/current_model/train_current_model.py:1925:        "--stage", choices=("validation", "submission"), default="validation"
/task/current_model/train_current_model.py:1939:        "--loss-microbatch-size",
/task/current_model/train_current_model.py:1941:        default=Config.loss_microbatch_size,
/task/current_model/train_current_model.py:1944:        "--negative-filter-scope",
/task/current_model/train_current_model.py:1946:        default=Config.negative_filter_scope,
/task/current_model/train_current_model.py:2003:    parser.add_argument("--ranking-batch-size", type=int, default=64)
/task/current_model/train_current_model.py:2012:        or args.loss_microbatch_size < 1
/task/current_model/train_current_model.py:2033:        loss_microbatch_size=args.loss_microbatch_size,
/task/current_model/train_current_model.py:2034:        negative_filter_scope=args.negative_filter_scope,
/task/current_model/train_current_model.py:2057:        args.stage,
/task/current_model/train_current_model.py:2071:                    "stage": args.stage,
/task/current_model/train_current_model.py:2095:        args.stage,
/task/current_model/train_current_model.py:2102:    ranking, embedding_diagnostics = rank_candidates(
/task/current_model/train_current_model.py:2108:        args.ranking_batch_size,
/task/current_model/train_current_model.py:2110:    write_ranking(ranking, args.output.resolve())
/task/current_model/train_current_model.py:2115:                "stage": args.stage,
/task/current_model/train_current_model.py:2117:                "rows": len(ranking),
/task/current_model/train_current_model.py:2118:                "users": int(ranking.uid.nunique()),
/task/current_model/train_current_model.py:2126:                    "sequence_encoder": "one-layer-GRU-dense-timestep-loss",
/task/current_model/train_current_model.py:2129:                    "loss_execution": "gradient-accumulated-microbatches",
/task/current_model/train_current_model.py:2135:                    "objective": "sample-weighted-BCE-at-every-timestep",
/task/current_model/train_current_model.py:2136:                    "negative_sampl…6499 tokens truncated… == "validation" else base.VALIDATION_END
            )
            horizon = config.discovery_horizon_days * base.DAY
            grade_three = 0
            for user_row, uid in enumerate(prepared.user_ids):
                start = int(prepared.offsets[user_row])
                end = int(prepared.offsets[user_row + 1])
                if end - start < 2:
                    continue
                last_training_target = start + int(training_counts[user_row])
                first_validation_target = last_training_target + 1
                split_timestamp = (
                    int(prepared.sequence_timestamps[first_validation_target])
                    if first_validation_target < end
                    else history_end
                )
                user_likes = like_outcomes.get(int(uid), {})
                seen = {int(prepared.sequence_items[start])}
                for position in range(start + 1, end):
                    item = int(prepared.sequence_items[position])
                    novel = item not in seen
                    seen.add(item)
                    if not novel:
                        # Repeats remain training examples, but they cannot be
                        # eligible discovery outcomes at the corresponding
                        # cutoff and therefore keep only the ordinary weight.
                        weights[position] = config.ordinary_target_weight
                        continue
                    timestamps = user_likes.get(item)
                    if timestamps is None:
                        continue
                    timestamp = int(prepared.sequence_timestamps[position])
                    upper = min(
                        timestamp + horizon,
                        split_timestamp
                        if position <= last_training_target
                        else history_end,
                    )
                    outcome = int(np.searchsorted(timestamps, timestamp, side="left"))
                    if outcome < len(timestamps) and int(timestamps[outcome]) < upper:
                        weights[position] = config.organic_like_target_weight
                        grade_three += 1
            log(
                f"grade-3 first-encounter targets={grade_three:,} "
                f"horizon_days={config.discovery_horizon_days}"
            )
    log(
        f"target weighting={config.target_weighting} "
        f"min={weights.min():.3f} mean={weights.mean():.3f} "
        f"max={weights.max():.3f}"
    )
    return weights


def build_dense_block(
    prepared: SequenceData,
    target_weights: np.ndarray,
    users: np.ndarray,
    window_starts: np.ndarray,
    process_counts: np.ndarray,
    score_starts: np.ndarray,
    start: int,
    steps: int,
    config: Config,
) -> tuple[np.ndarray, ...]:
    """Build one causal sequence block and mark the target rows to score."""
    batch_size = len(users)
    padding_item = len(prepared.item_ids)
    input_items = np.full((batch_size, steps), padding_item, dtype=np.uint16)
    event_features = np.zeros((batch_size, steps, 3), dtype=np.float16)
    activity_features = np.zeros((batch_size, steps, 4), dtype=np.float16)
    state_ids = np.zeros((batch_size, steps), dtype=np.uint32)
    targets = np.zeros((batch_size, steps), dtype=np.uint16)
    weights = np.ones((batch_size, steps), dtype=np.float32)
    scored = np.zeros((batch_size, steps), dtype=bool)
    histories = np.full(
        (batch_size, steps, config.bptt_steps),
        padding_item,
        dtype=np.uint16,
    )
    processed = np.zeros(batch_size, dtype=np.int32)

    lengths = prepared.lengths
    for row, user_row in enumerate(users):
        count = min(steps, max(int(process_counts[row]) - start, 0))
        if not count:
            continue
        offset = int(prepared.offsets[user_row])
        window_start = int(window_starts[row])
        absolute_start = window_start + start
        positions = slice(
            offset + absolute_start,
            offset + absolute_start + count,
        )
        target_positions = slice(
            offset + absolute_start + 1,
            offset + absolute_start + count + 1,
        )
        input_items[row, :count] = prepared.sequence_items[positions]
        event_features[row, :count] = prepared.event_features[positions]
        activity_features[row, :count] = prepared.activity_features[positions]
        state_ids[row, :count] = prepared.state_ids[positions]
        targets[row, :count] = prepared.sequence_items[target_positions]
        weights[row, :count] = target_weights[target_positions]
        score_from = min(count, max(int(score_starts[row]) - start, 0))
        scored[row, score_from:count] = True
        processed[row] = count
        user_sequence = prepared.sequence_items[
            offset : offset + int(lengths[user_row])
        ]
        histories[row, :count] = history_windows(
            user_sequence,
            absolute_start,
            count,
            config.bptt_steps,
            padding_item,
        )
    return (
        input_items,
        event_features,
        activity_features,
        state_ids,
        targets,
        scored,
        histories,
        processed,
        weights,
    )


def score_target_microbatches(
    model: base.SequentialTwoTower,
    prepared: SequenceData,
    config: Config,
    sequence_vectors: torch.Tensor,
    flat_states: np.ndarray,
    flat_activity: np.ndarray,
    positive_items: torch.Tensor,
    negatives: torch.Tensor,
    negative_weights: torch.Tensor,
    sample_weights: np.ndarray,
    device: torch.device,
    backward: bool,
) -> tuple[dict[str, float], torch.Tensor | None]:
    """Compute one logical block's exact BCE in bounded-memory slices."""
    target_count = len(positive_items)
    total_weight = float(sample_weights.sum())
    if total_weight <= 0:
        raise RuntimeError("target block has no positive sample weight")
    sequence_gradient = torch.zeros_like(sequence_vectors) if backward else None
    statistics = {
        "loss_sum": 0.0,
        "positive_sum": 0.0,
        "negative_sum": 0.0,
        "pair_correct": 0.0,
        "weight_sum": 0.0,
    }
    for begin in range(0, target_count, config.loss_microbatch_size):
        end = min(begin + config.loss_microbatch_size, target_count)
        selected_states = flat_states[begin:end]
        if backward:
            sequence_input = (
                sequence_vectors[begin:end].detach().requires_grad_(True)
            )
        else:
            sequence_input = sequence_vectors[begin:end]
        liked_vectors, disliked_vectors, _ = pool_explicit_states(
            model, prepared, selected_states, device
        )
        counts = prepared.state_counts[selected_states]
        numeric = np.zeros((end - begin, 6), dtype=np.float32)
        numeric[:, :4] = flat_activity[begin:end]
        numeric[:, 4] = np.log1p(counts[:, 0]) / 6.0
        numeric[:, 5] = np.log1p(counts[:, 1]) / 4.0
        query_vectors = user_queries(
            model,
            sequence_input,
            liked_vectors,
            disliked_vectors,
            torch.from_numpy(numeric).to(device),
        )
        positive_vectors, negative_vectors = candidate_vectors(
            model,
            positive_items[begin:end],
            negatives[begin:end],
        )
        positive_logits = (query_vectors * positive_vectors).sum(dim=1)
        negative_logits = torch.einsum(
            "bd,bkd->bk", query_vectors, negative_vectors
        )
        positive_loss = F.softplus(-positive_logits)
        negative_loss = corrected_negative_loss(
            negative_logits, negative_weights[begin:end], config
        )
        selected_weights = torch.from_numpy(
            sample_weights[begin:end].astype(np.float32, copy=False)
        ).to(device)
        loss_sum = (
            selected_weights * (positive_loss + negative_loss) / 2.0
        ).sum()
        if not bool(torch.isfinite(loss_sum)):
            raise RuntimeError("dense next-item training produced non-finite loss")
        if backward:
            (loss_sum / total_weight).backward()
            if sequence_input.grad is None:
                raise RuntimeError("sequence microbatch did not produce a gradient")
            sequence_gradient[begin:end] = sequence_input.grad
        statistics["loss_sum"] += float(loss_sum.detach().cpu())
        statistics["positive_sum"] += float(positive_logits.detach().sum().cpu())
        statistics["negative_sum"] += float(negative_logits.detach().sum().cpu())
        statistics["pair_correct"] += float(
            (positive_logits.detach()[:, None] > negative_logits.detach()).sum().cpu()
        )
        statistics["weight_sum"] += float(selected_weights.sum().detach().cpu())
    return statistics, sequence_gradient


def release_accelerator_cache(device: torch.device) -> None:
    if device.type == "mps":
        torch.mps.empty_cache()


def run_training_epoch(
    model: base.SequentialTwoTower,
    optimizer: torch.optim.Optimizer,
    prepared: SequenceData,
    config: Config,
    target_weights: np.ndarray,
    window_starts: np.ndarray,
    target_counts: np.ndarray,
    item_correction: torch.Tensor,
    known_positive_packed: np.ndarray | None,
    generator: torch.Generator,
    device: torch.device,
    epoch: int,
) -> dict[str, float]:
    model.train()
    train_users = np.flatnonzero(target_counts > 0)
    sorted_users = train_users[
        np.argsort(target_counts[train_users], kind="stable")
    ]
    groups = [
        sorted_users[start : start + config.user_batch_size]
        for start in range(0, len(sorted_users), config.user_batch_size)
    ]
    group_order = torch.randperm(len(groups), generator=generator).numpy()
    negative_count = config.uniform_negatives + config.inbatch_negatives
    total_loss = 0.0
    total_targets = 0
    total_weight = 0.0
    total_positive = 0.0
    total_negative = 0.0
    total_pair_correct = 0.0
    batches = 0
    started = time.monotonic()

    for group_number in group_order:
        users = groups[int(group_number)]
        group_counts = target_counts[users]
        hidden = torch.zeros(
            1, len(users), config.embedding_dim, device=device
        )
        max_targets = int(group_counts.max())
        for start in range(0, max_targets, config.bptt_steps):
            steps = min(config.bptt_steps, max_targets - start)
            block = build_dense_block(
                prepared,
                target_weights,
                users,
                window_starts[users],
                group_counts,
                np.zeros(len(users), dtype=np.int64),
                start,
                steps,
                config,
            )
            sequence_outputs, _ = event_sequence(
                model,
                torch.from_numpy(block[0].astype(np.int64)).to(device),
                torch.from_numpy(block[1].astype(np.float32)).to(device),
                hidden,
            )
            hidden = torch.stack(
                [
                    sequence_outputs[row, count - 1]
                    if count
                    else hidden[0, row]
                    for row, count in enumerate(block[7])
                ]
            ).unsqueeze(0).detach()
            flat_scored = block[5].reshape(-1)
            if not np.any(flat_scored):
                continue
            mask = torch.from_numpy(flat_scored).to(device)
            sequence_vectors = sequence_outputs.reshape(
                -1, config.embedding_dim
            )[mask]
            flat_states = block[3].reshape(-1)[flat_scored]
            positive_items = torch.from_numpy(
                block[4].reshape(-1)[flat_scored].astype(np.int64)
            ).to(device)
            known_history = torch.from_numpy(
                block[6].reshape(-1, config.bptt_steps)[flat_scored].astype(
                    np.int64
                )
            ).to(device)
            liked_items = torch.from_numpy(
                prepared.liked_states[flat_states].astype(np.int64)
            ).to(device)
            flat_user_rows = np.broadcast_to(
                users[:, None], block[5].shape
            ).reshape(-1)[flat_scored]
            negatives, negative_weights = draw_training_negatives(
                positive_items,
                known_history,
                liked_items,
                flat_user_rows,
                known_positive_packed,
                prepared,
                config,
                item_correction,
                generator,
                device,
            )
            optimizer.zero_grad(set_to_none=True)
            statistics, sequence_gradient = score_target_microbatches(
                model,
                prepared,
                config,
                sequence_vectors,
                flat_states,
                block[2].reshape(-1, 4)[flat_scored].astype(np.float32),
                positive_items,
                negatives,
                negative_weights,
                block[8].reshape(-1)[flat_scored],
                device,
                backward=True,
            )
            if sequence_gradient is None:
    keep = mapped >= 0
    state = state.loc[keep, ["uid", "state"]].copy()
    state["item"] = mapped[keep].astype(np.int32, copy=False)
    user_rows = pd.Index(uids)
    liked = np.full((len(uids), LIKE_ITEMS), n_items, dtype=np.uint16)
    disliked = np.full((len(uids), DISLIKE_ITEMS), n_items, dtype=np.uint16)
    like_counts = np.zeros(len(uids), dtype=np.int32)
    dislike_counts = np.zeros(len(uids), dtype=np.int32)
    for value, width, destination, counts in (
        ("liked", LIKE_ITEMS, liked, like_counts),
        ("disliked", DISLIKE_ITEMS, disliked, dislike_counts),
    ):
        selected = state[state.state == value]
        for uid, rows in selected.groupby("uid", sort=False):
            row = int(user_rows.get_indexer([int(uid)])[0])
            if row < 0:
                continue
            items = np.sort(rows.item.unique())
            counts[row] = len(items)
            retained = items[:width]
            destination[row, : len(retained)] = retained.astype(np.uint16)
    return liked, disliked, like_counts, dislike_counts


class SequentialTwoTower(nn.Module):
    """Order-sensitive user tower and independent catalog-aware item tower."""

    def __init__(self, item_features: np.ndarray, config: TowerConfig) -> None:
        super().__init__()
        n_items, n_item_features = item_features.shape
        dim = config.embedding_dim
        self.n_items = n_items
        self.context_embedding = nn.Embedding(
            n_items + 1, dim, padding_idx=n_items
        )
        self.event_projection = nn.Sequential(
            nn.Linear(dim + 3, config.hidden_dim),
            nn.GELU(),
        )
        self.sequence_encoder = nn.GRU(
            input_size=config.hidden_dim,
            hidden_size=dim,
            num_layers=1,
            batch_first=True,
        )
        self.user_tower = nn.Sequential(
            nn.Linear(dim * 3 + 6, config.user_hidden_1),
            nn.GELU(),
            nn.Dropout(config.dropout),
            nn.Linear(config.user_hidden_1, config.user_hidden_2),
            nn.GELU(),
            nn.Dropout(config.dropout),
            nn.Linear(config.user_hidden_2, dim),
        )
        self.candidate_embedding = nn.Embedding(n_items, dim)
        self.register_buffer(
            "item_features", torch.from_numpy(item_features), persistent=True
        )
        self.item_tower = nn.Sequential(
            nn.Linear(dim + n_item_features, config.item_hidden_1),
            nn.GELU(),
            nn.Dropout(config.dropout),
            nn.Linear(config.item_hidden_1, config.item_hidden_2),
            nn.GELU(),
            nn.Dropout(config.dropout),
            nn.Linear(config.item_hidden_2, dim),
        )
        nn.init.normal_(self.context_embedding.weight, std=0.02)
        nn.init.normal_(self.candidate_embedding.weight, std=0.02)
        with torch.no_grad():
            self.context_embedding.weight[n_items].zero_()

    def _mean_context_channel(self, items: torch.Tensor) -> torch.Tensor:
        mask = items.ne(self.n_items)
        vectors = self.context_embedding(items)
        return (vectors * mask.unsqueeze(-1)).sum(dim=1) / mask.sum(
            dim=1, keepdim=True
        ).clamp_min(1)

    def encode_items(self, items: torch.Tensor) -> torch.Tensor:
        inputs = torch.cat(
            [self.candidate_embedding(items), self.item_features[items]], dim=1
        )
        return self.item_tower(inputs)


def invalid_negative_mask(
    negatives: torch.Tensor,
    targets: torch.Tensor,
    context_items: torch.Tensor,
    liked_items: torch.Tensor,
) -> torch.Tensor:
    """Identify targets, known positives, active likes, and row duplicates."""
    invalid = negatives.eq(targets[:, None])
    invalid |= negatives[:, :, None].eq(context_items[:, None, :]).any(dim=2)
    invalid |= negatives[:, :, None].eq(liked_items[:, None, :]).any(dim=2)
    for column in range(1, negatives.shape[1]):
        invalid[:, column] |= negatives[:, column, None].eq(
            negatives[:, :column]
        ).any(dim=1)
    return invalid


def draw_filtered_mixed_negatives(
    targets: torch.Tensor,
    context_items: torch.Tensor,
    liked_items: torch.Tensor,
    n_items: int,
    uniform_count: int,
    inbatch_count: int,
    item_correction: torch.Tensor,
    generator: torch.Generator,
    device: torch.device,
) -> tuple[torch.Tensor, torch.Tensor]:
    """Draw uniform and unique-target in-batch negatives."""
    batch_size = len(targets)
    uniform = torch.randint(
        n_items,
        (batch_size, uniform_count),
        generator=generator,
        device="cpu",
    )
    inbatch = torch.empty((batch_size, 0), dtype=torch.long, device="cpu")
    corrected_count = 0
    if inbatch_count:
        unique_targets = torch.unique(targets.detach().cpu())
        corrected_count = min(inbatch_count, max(len(unique_targets) - 1, 0))
        if corrected_count:
            priorities = torch.rand(
                (batch_size, len(unique_targets)), generator=generator
            )
            priorities.masked_fill_(
                unique_targets[None, :].eq(targets.detach().cpu()[:, None]),
                -1.0,
            )
            columns = torch.topk(priorities, k=corrected_count, dim=1).indices
            inbatch = unique_targets[columns]
        if corrected_count < inbatch_count:
            filler = torch.randint(
                n_items,
                (batch_size, inbatch_count - corrected_count),
                generator=generator,
                device="cpu",
            )
            inbatch = torch.cat([inbatch, filler], dim=1)

    negatives_cpu = torch.cat([uniform, inbatch], dim=1)
    correction_cpu = torch.ones_like(negatives_cpu, dtype=torch.float32)
    if corrected_count:
        correction_cpu[
            :, uniform_count : uniform_count + corrected_count
        ] = item_correction[inbatch[:, :corrected_count]]
    negatives = negatives_cpu.to(device)
    correction = correction_cpu.to(device)
    for _ in range(32):
        invalid = invalid_negative_mask(
            negatives, targets, context_items, liked_items
        )
        if not bool(invalid.any()):
            return negatives, correction
        replacements = torch.randint(
            n_items,
            (int(invalid.sum().detach().cpu()),),
            generator=generator,
            device="cpu",
        ).to(device)
        negatives[invalid] = replacements
        correction[invalid] = 1.0
    invalid = invalid_negative_mask(
        negatives, targets, context_items, liked_items
    )
    if bool(invalid.any()):
        raise RuntimeError("mixed negative resampling failed false-negative filter")
    return negatives, correction

Script completed
Wall time 0.0 seconds
Output:

{"chunk_id":"1565b3","wall_time_seconds":0.000003811,"exit_code":0,"original_token_count":10,"output":"/bin/sh: 1: /usr/bin/time: not found\n"}

Script completed
Wall time 0.2 seconds
Output:

{"chunk_id":"0222b2","wall_time_seconds":0.038482809,"exit_code":0,"original_token_count":43,"output":"Traceback (most recent call last):\n  File \"/app/solution/train_current_model.py\", line 28, in <module>\n    import numpy as np\nModuleNotFoundError: No module named 'numpy'\n"}

Script completed
Wall time 0.1 seconds
Output:

/usr/local/bin/python
/usr/local/bin/python3
Python 3.12.13
Python 3.12.13
# Exact distribution inventory for the Yambda two-tower task family.
#
# This is an input to `uv pip sync`, not a list of minimum requirements. A
# conforming task environment contains exactly these third-party Python
# distributions and no others. Python itself is pinned by task.toml and both
# Harbor image Dockerfiles.
attrs==26.1.0
bleach==6.4.0
certifi==2026.7.22
chardet==7.6.0
charset-normalizer==3.5.1
fastjsonschema==2.22.2
filelock==3.32.3
fsspec==2026.7.0
idna==3.18
Jinja2==3.1.6
joblib==1.5.3
jsonschema==4.26.0
jsonschema-specifications==2025.9.1
jupyter-core==5.9.1
jupytext==1.19.5
kaggle==2.2.4
kagglesdk==0.1.37
markdown-it-py==4.2.0
MarkupSafe==3.0.3
mdit-py-plugins==0.6.1
mdurl==0.1.2
mpmath==1.3.0
nbformat==5.11.1
networkx==3.6.1
numpy==2.2.6
packaging==26.3
pandas==2.3.3
pillow==12.3.0
pip==26.0.1
platformdirs==4.11.3
protobuf==7.35.1
pyarrow==18.1.0
python-dateutil==2.9.0.post0
python-dotenv==1.2.3
python-slugify==8.0.4
pytz==2026.3.post1
PyYAML==6.0.3
referencing==0.37.0
reportlab==4.2.5
requests==2.34.2
rpds-py==2026.6.3
scikit-learn==1.7.2
scipy==1.15.3
setuptools==84.0.0
six==1.17.0
sympy==1.14.0
text-unidecode==1.3
threadpoolctl==3.6.0
torch==2.8.0
tqdm==4.70.0
traitlets==5.16.1
typing-extensions==4.16.0
tzdata==2026.3
urllib3==2.7.0
webencodings==0.6.1
/app:
total 16
drwxr-xr-x 1 agent agent 4096 Aug 31 19:25 .
drwxr-xr-x 1 root  root  4096 Aug 31 19:28 ..
drwxr-xr-x 1 agent agent 4096 Aug 31 19:29 solution

/task:
total 40
dr-xr-xr-x 1 root root 4096 Aug 31 19:25 .
drwxr-xr-x 1 root root 4096 Aug 31 19:28 ..
-r--r--r-- 1 root root    0 Aug 31 19:23 .keep
dr-xr-xr-x 1 root root 4096 Aug 31 19:23 current_model
dr-xr-xr-x 1 root root 4096 Aug 31 19:24 data
-r--r--r-- 1 root root 5774 Aug 31 19:23 evaluate_public.py
-r--r--r-- 1 root root 8265 Aug 31 19:23 ranking_evaluation.py
-r--r--r-- 1 root root 1295 Aug 31 19:23 requirements.txt

Script completed
Wall time 0.1 seconds
Output:

CODEX_CI=1
CODEX_HOME=/tmp/codex-home
CODEX_THREAD_ID=01a0594b-b645-7843-8d58-b5b57069ab8e
COLORTERM=
GH_PAGER=cat
GIT_PAGER=cat
GPG_KEY=7169605F62C751356D054A26A821E680E5FA6305
HOME=/home/agent
HOSTNAME=1151a7ad22c4
LANG=C.UTF-8
LC_ALL=C.UTF-8
LC_CTYPE=C.UTF-8
NO_COLOR=1
PAGER=cat
PATH=/opt/codex-home/packages/standalone/releases/0.147.0-x86_64-unknown-linux-musl/codex-path:/usr/local/bin:/usr/bin:/bin:/usr/local/games:/usr/games
PWD=/app
PYTHONDONTWRITEBYTECODE=1
PYTHONNOUSERSITE=1
PYTHON_SHA256=c08bc65a81971c1dd5783182826503369466c7e67374d1646519adf05207b684
PYTHON_VERSION=3.12.13
SHLVL=1
TERM=dumb
_=/usr/local/bin/codex

Script completed
Wall time 0.2 seconds
Output:

/opt/task-venv/lib/python3.12/site-packages/numpy
/opt/task-venv/lib/python3.12/site-packages/numpy/_core/include/numpy
/opt/task-venv/lib/python3.12/site-packages/sklearn/externals/array_api_compat/numpy
/opt/task-venv/lib/python3.12/site-packages/scipy/_lib/array_api_compat/numpy
/opt/task-venv/lib/python3.12/site-packages/pandas/compat/numpy
total 20
drwxr-xr-x  4 root root 4096 Aug  5 01:13 .
drwxr-xr-x 38 root root 4096 Aug  5 01:13 ..
-rw-r--r--  1 root root  119 Aug  5 01:13 README.txt
drwxr-xr-x  5 root root 4096 Aug  5 01:13 pip
drwxr-xr-x  2 root root 4096 Aug  5 01:13 pip-25.0.1.dist-info

Script completed
Wall time 3.9 seconds
Output:

total 124
dr-xr-xr-x 1 root root 4096 Aug 31 19:25 .
dr-xr-xr-x 1 root root 4096 Aug 31 19:25 ..
-r--r--r-- 1 root root 9033 Aug 31 19:25 Activate.ps1
-r--r--r-- 1 root root 2158 Aug 31 19:25 activate
-r--r--r-- 1 root root  920 Aug 31 19:25 activate.csh
-r--r--r-- 1 root root 2195 Aug 31 19:25 activate.fish
-r-xr-xr-x 1 root root  302 Aug 31 19:25 chardetect
-r-xr-xr-x 1 root root  304 Aug 31 19:25 dotenv
-r-xr-xr-x 1 root root  308 Aug 31 19:25 f2py
-r-xr-xr-x 1 root root  299 Aug 31 19:25 idna
-r-xr-xr-x 1 root root  297 Aug 31 19:25 isympy
-r-xr-xr-x 1 root root  305 Aug 31 19:25 jsonschema
-r-xr-xr-x 1 root root  311 Aug 31 19:25 jupyter
-r-xr-xr-x 1 root root  311 Aug 31 19:25 jupyter-migrate
-r-xr-xr-x 1 root root  316 Aug 31 19:25 jupyter-troubleshoot
-r-xr-xr-x 1 root root  344 Aug 31 19:25 jupyter-trust
-r-xr-xr-x 1 root root  311 Aug 31 19:25 jupytext
-r-xr-xr-x 1 root root  315 Aug 31 19:25 jupytext-config
-r-xr-xr-x 1 root root  301 Aug 31 19:25 kaggle
-r-xr-xr-x 1 root root  312 Aug 31 19:25 markdown-it
-r-xr-xr-x 1 root root  325 Aug 31 19:25 normalizer
-r-xr-xr-x 1 root root  308 Aug 31 19:25 numpy-config
-r-xr-xr-x 1 root root  313 Aug 31 19:25 pip
-r-xr-xr-x 1 root root  313 Aug 31 19:25 pip3
-r-xr-xr-x 1 root root  313 Aug 31 19:25 pip3.12
lrwxrwxrwx 1 root root   21 Aug 31 19:25 python -> /usr/local/bin/python
lrwxrwxrwx 1 root root    6 Aug 31 19:25 python3 -> python
lrwxrwxrwx 1 root root    6 Aug 31 19:25 python3.12 -> python
-r-xr-xr-x 1 root root  307 Aug 31 19:25 slugify
-r-xr-xr-x 1 root root  321 Aug 31 19:25 torchfrtrace
-r-xr-xr-x 1 root root  312 Aug 31 19:25 torchrun
-r-xr-xr-x 1 root root  299 Aug 31 19:25 tqdm
2.2.6 2.3.3 2.8.0+cpu

Script completed
Wall time 1.2 seconds
Output:

{"chunk_id":"9dae07","wall_time_seconds":1.001908656,"session_id":51338,"original_token_count":0,"output":""}

Script completed
Wall time 5.0 seconds
Output:

{"chunk_id":"f60bec","wall_time_seconds":5.001095105,"session_id":51338,"original_token_count":13,"output":"loaded explicit events: rows=720,270 users=8,220\n"}

Script completed
Wall time 0.1 seconds
Output:

    raw = np.power(
        (1.0 / len(counts)) / probabilities,
        config.inbatch_correction_power,
    )
    normalization = float(np.sum(counts * raw) / max(total, 1.0))
    correction = np.clip(
        raw / max(normalization, 1.0e-12),
        config.inbatch_correction_min,
        config.inbatch_correction_max,
    ).astype(np.float32)
    mean_on_targets = float(np.sum(counts * correction) / max(total, 1.0))
    log(
        f"inbatch correction: min={correction.min():.3f} "
        f"mean_on_targets={mean_on_targets:.3f} max={correction.max():.3f}"
    )
    return torch.from_numpy(correction)


def build_known_positive_filter(
    prepared: SequenceData, training_counts: np.ndarray
) -> np.ndarray:
    """Pack each user's complete public-training positive-item set."""
    width = (len(prepared.item_ids) + 7) // 8
    packed = np.zeros((len(prepared.user_ids), width), dtype=np.uint8)
    retained = 0
    for user_row, target_count in enumerate(training_counts):
        if not target_count:
            continue
        offset = int(prepared.offsets[user_row])
        # T adjacent targets consume sequence positions 0 through T.  The
        # chronological BCE suffix starts at T + 1 and is intentionally absent.
        items = np.unique(
            prepared.sequence_items[
                offset : offset + int(target_count) + 1
            ].astype(np.int64)
        )
        byte_columns = items >> 3
        bit_values = np.left_shift(
            np.uint8(1), (items & 7).astype(np.uint8)
        )
        np.bitwise_or.at(packed[user_row], byte_columns, bit_values)
        retained += len(items)
    log(
        f"full-history false-negative filter: users={len(prepared.user_ids):,} "
        f"unique_user_items={retained:,} bytes={packed.nbytes:,}"
    )
    return packed


def invalid_full_history_negatives(
    negatives: np.ndarray,
    targets: np.ndarray,
    user_rows: np.ndarray,
    known_positive_packed: np.ndarray,
    liked_items: np.ndarray,
) -> np.ndarray:
    """Return row-level invalid negatives using the complete training prefix."""
    byte_columns = negatives >> 3
    bit_columns = negatives & 7
    known = known_positive_packed[user_rows[:, None], byte_columns]
    invalid = ((known >> bit_columns) & 1).astype(bool)
    invalid |= negatives == targets[:, None]
    invalid |= (negatives[:, :, None] == liked_items[:, None, :]).any(axis=2)
    for column in range(1, negatives.shape[1]):
        invalid[:, column] |= (
            negatives[:, column, None] == negatives[:, :column]
        ).any(axis=1)
    return invalid


def draw_full_history_filtered_negatives(
    targets: torch.Tensor,
    user_rows: np.ndarray,
    liked_items: torch.Tensor,
    known_positive_packed: np.ndarray,
    n_items: int,
    config: Config,
    item_correction: torch.Tensor,
    generator: torch.Generator,
    device: torch.device,
) -> tuple[torch.Tensor, torch.Tensor]:
    """Draw mixed negatives and reject all known public-training positives."""
    targets_cpu = targets.detach().cpu().numpy().astype(np.int64, copy=False)
    liked_cpu = liked_items.detach().cpu().numpy().astype(np.int64, copy=False)
    batch_size = len(targets_cpu)
    uniform = torch.randint(
        n_items,
        (batch_size, config.uniform_negatives),
        generator=generator,
        device="cpu",
    )
    inbatch = torch.empty((batch_size, 0), dtype=torch.long)
    corrected_count = 0
    if config.inbatch_negatives:
        unique_targets = torch.unique(targets.detach().cpu())
        corrected_count = min(
            config.inbatch_negatives, max(len(unique_targets) - 1, 0)
        )
        if corrected_count:
            priorities = torch.rand(
                (batch_size, len(unique_targets)), generator=generator
            )
            priorities.masked_fill_(
                unique_targets[None, :].eq(
                    torch.from_numpy(targets_cpu)[:, None]
                ),
                -1.0,
            )
            columns = torch.topk(
                priorities, k=corrected_count, dim=1
            ).indices
            inbatch = unique_targets[columns]
        if corrected_count < config.inbatch_negatives:
            filler = torch.randint(
                n_items,
                (batch_size, config.inbatch_negatives - corrected_count),
                generator=generator,
                device="cpu",
            )
            inbatch = torch.cat([inbatch, filler], dim=1)

    negatives = torch.cat([uniform, inbatch], dim=1).numpy()
    correction = np.ones_like(negatives, dtype=np.float32)
    if corrected_count:
        correction[
            :, config.uniform_negatives : config.uniform_negatives + corrected_count
        ] = item_correction[inbatch[:, :corrected_count]].numpy()
    for _ in range(32):
        invalid = invalid_full_history_negatives(
            negatives,
            targets_cpu,
            user_rows,
            known_positive_packed,
            liked_cpu,
        )
        if not np.any(invalid):
            return (
                torch.from_numpy(negatives).to(device),
                torch.from_numpy(correction).to(device),
            )
        replacements = torch.randint(
            n_items,
            (int(invalid.sum()),),
            generator=generator,
            device="cpu",
        ).numpy()
        negatives[invalid] = replacements
        # Rejected in-batch items become ordinary uniform draws.
        correction[invalid] = 1.0
    invalid = invalid_full_history_negatives(
        negatives,
        targets_cpu,
        user_rows,
        known_positive_packed,
        liked_cpu,
    )
    if np.any(invalid):
        raise RuntimeError("full-history negative resampling failed")
    return (
        torch.from_numpy(negatives).to(device),
        torch.from_numpy(correction).to(device),
    )


def draw_training_negatives(
    positive_items: torch.Tensor,
    known_history: torch.Tensor,
    liked_items: torch.Tensor,
    user_rows: np.ndarray,
    known_positive_packed: np.ndarray | None,
    prepared: SequenceData,
    config: Config,
    item_correction: torch.Tensor,
    generator: torch.Generator,
    device: torch.device,
) -> tuple[torch.Tensor, torch.Tensor]:
    if config.negative_filter_scope == "full-training-history":
        if known_positive_packed is None:
            raise RuntimeError("full-history negative filter was not built")
        return draw_full_history_filtered_negatives(
            positive_items,
            user_rows,
            liked_items,
            known_positive_packed,
            len(prepared.item_ids),
            config,
            item_correction,
            generator,
            device,
        )
    return base.draw_filtered_mixed_negatives(
        positive_items,
        known_history,
        liked_items,
        len(prepared.item_ids),
        config.uniform_negatives,
        config.inbatch_negatives,
        item_correction,
        generator,
        device,
    )


def event_sequence(
    model: base.SequentialTwoTower,
    items: torch.Tensor,
    features: torch.Tensor,
    hidden: torch.Tensor,
) -> tuple[torch.Tensor, torch.Tensor]:
    inputs = torch.cat([model.context_embedding(items), features], dim=-1)
    projected = model.event_projection(inputs)
    return model.sequence_encoder(projected, hidden)


def pool_explicit_states(
    model: base.SequentialTwoTower,
    prepared: SequenceData,
    state_ids: np.ndarray,
    device: torch.device,
) -> tuple[torch.Tensor, torch.Tensor, torch.Tensor]:
    unique_states, inverse = np.unique(state_ids, return_inverse=True)
    liked_items = torch.from_numpy(
        prepared.liked_states[unique_states].astype(np.int64)
    ).to(device)
    disliked_items = torch.from_numpy(
        prepared.disliked_states[unique_states].astype(np.int64)
    ).to(device)
    liked_vectors = model._mean_context_channel(liked_items)
    disliked_vectors = model._mean_context_channel(disliked_items)
    inverse_rows = torch.from_numpy(inverse.astype(np.int64)).to(device)
    counts = prepared.state_counts[state_ids]
    return (
        liked_vectors[inverse_rows],
        disliked_vectors[inverse_rows],
        torch.from_numpy(counts.astype(np.float32)).to(device),
    )


def user_queries(
    model: base.SequentialTwoTower,
    sequence_vectors: torch.Tensor,
    liked_vectors: torch.Tensor,
    disliked_vectors: torch.Tensor,
    user_features: torch.Tensor,
) -> torch.Tensor:
    return model.user_tower(
        torch.cat(
            [sequence_vectors, liked_vectors, disliked_vectors, user_features],
            dim=1,
        )
    )


def candidate_vectors(
    model: base.SequentialTwoTower,
    positives: torch.Tensor,
    negatives: torch.Tensor,
) -> tuple[torch.Tensor, torch.Tensor]:
    all_items = torch.cat([positives, negatives.reshape(-1)])
    unique_items, inverse = torch.unique(all_items, return_inverse=True)
    encoded = model.encode_items(unique_items)
    positive_vectors = encoded[inverse[: len(positives)]]
    negative_vectors = encoded[inverse[len(positives) :]].reshape(
        len(positives), negatives.shape[1], -1
    )
    return positive_vectors, negative_vectors


def history_windows(
    sequence: np.ndarray,
    start: int,
    count: int,
    width: int,
    padding_item: int,
) -> np.ndarray:
    base_start = max(0, start - width + 1)
    segment = sequence[base_start : start + count]
    padded = np.concatenate(
        [np.full(width - 1, padding_item, dtype=np.uint16), segment]
    )
    windows = np.lib.stride_tricks.sliding_window_view(padded, width)
    offset = start - base_start
    return windows[offset : offset + count].copy()


def corrected_negative_loss(
    logits: torch.Tensor,
    correction: torch.Tensor,
    config: Config,
) -> torch.Tensor:
    raw = F.softplus(logits)
    total = config.uniform_negatives + config.inbatch_negatives
    result = torch.zeros(len(logits), device=logits.device)
    if config.uniform_negatives:
        result += config.uniform_negatives * raw[
            :, : config.uniform_negatives
        ].mean(dim=1)
    if config.inbatch_negatives:
        selected = slice(config.uniform_negatives, total)
        weights = correction[:, selected]
        result += config.inbatch_negatives * (
            (raw[:, selected] * weights).sum(dim=1)
            / weights.sum(dim=1).clamp_min(1.0e-6)
        )
    return result / total


def retained_target_window_starts(
    total_targets: np.ndarray,
    validation_counts: np.ndarray,
    training_counts: np.ndarray,
    training_counts: np.ndarray,
) -> np.ndarray:
    """Return the discarded prefix before the retained chronological suffix."""
    training_region_ends = total_targets - validation_counts
    window_starts = training_region_ends - training_counts
    if (
        np.any(window_starts < 0)
        or np.any(training_counts < 0)
        or np.any(validation_counts < 0)
    ):
        raise RuntimeError("chronological target partition produced negative counts")
    if not np.array_equal(
        window_starts + training_counts + validation_counts, total_targets
    ):
        raise RuntimeError("chronological target window is not a final contiguous suffix")
    return window_starts


def chronological_target_partition(
    prepared: SequenceData,
    validation_fraction: float,
    max_train_targets_per_user: int,
    max_validation_targets_per_user: int,
) -> TargetPartition:
    """Select a recent contiguous window with a final out-of-time BCE suffix."""
    totals = np.maximum(prepared.lengths - 1, 0).astype(np.int64)
    validation = np.floor(totals * validation_fraction).astype(np.int64)
    validation[(totals >= 2) & (validation == 0)] = 1
    if max_validation_targets_per_user:
        validation = np.minimum(validation, max_validation_targets_per_user)

    history_training = totals - validation
    training = history_training.copy()
    if max_train_targets_per_user:
        training = np.minimum(training, max_train_targets_per_user)
    window_starts = retained_target_window_starts(totals, validation, training)
    return TargetPartition(
        window_starts=window_starts,
        training_counts=training,
        validation_counts=validation,
        history_training_counts=history_training,
    )


def load_organic_like_outcomes(
    public: Path, stage: str, item_ids: np.ndarray
) -> dict[int, dict[int, np.ndarray]]:
    """Load mapped organic-like timestamps from public fitting history."""
    prefixes = ("train",) if stage == "validation" else ("train", "val")
    frames = [
        pd.read_parquet(
            public / "data" / f"{prefix}_likes.parquet",
            columns=["uid", "timestamp", "item_id", "is_organic"],
        )
        for prefix in prefixes
    ]
    likes = pd.concat(frames, ignore_index=True)
    likes = likes[likes.is_organic == 1].copy()
    mapped = pd.Index(item_ids).get_indexer(
        likes.item_id.to_numpy(dtype=np.int64)
    )
    likes = likes.loc[mapped >= 0, ["uid", "timestamp"]].copy()
    likes["item"] = mapped[mapped >= 0].astype(np.int32, copy=False)
    likes = likes.sort_values(["uid", "item", "timestamp"], kind="stable")
    nested: dict[int, dict[int, list[int]]] = {}
    for raw_uid, raw_timestamp, raw_item in likes.itertuples(
        index=False, name=None
    ):
        nested.setdefault(int(raw_uid), {}).setdefault(int(raw_item), []).append(
            int(raw_timestamp)
        )
    result = {
        uid: {
            item: np.asarray(timestamps, dtype=np.int64)
            for item, timestamps in items.items()
        }
        for uid, items in nested.items()
    }
    log(
        f"loaded organic-like outcomes: rows={len(likes):,} "
        f"users={len(result):,}"
    )
    return result


def build_target_weights(
    public: Path,
    stage: str,
    prepared: SequenceData,
    training_counts: np.ndarray,
    config: Config,
) -> np.ndarray:
    """Build nonzero per-token weights without dropping adjacent targets."""
    if config.target_weighting == "uniform":
        weights = np.ones(len(prepared.sequence_items), dtype=np.float32)
    else:
        weights = np.full(
            len(prepared.sequence_items),
            config.ordinary_target_weight,
            dtype=np.float32,
        )
        organic_strong = (
            (prepared.event_features[:, 0] > 0.5)
            & (prepared.event_features[:, 1] >= 0.8)
        )
        weights[organic_strong] = config.organic_strong_target_weight
        if config.target_weighting == "discovery-graded":
            like_outcomes = load_organic_like_outcomes(
                public, stage, prepared.item_ids
            )
            history_end = (
                base.TRAIN_END if stage == "validation" else base.VALIDATION_END
            )
            horizon = config.discovery_horizon_days * base.DAY
            grade_three = 0
            for user_row, uid in enumerate(prepared.user_ids):
                start = int(prepared.offsets[user_row])
                end = int(prepared.offsets[user_row + 1])
                if end - start < 2:
                    continue
                last_training_target = start + int(training_counts[user_row])
                first_validation_target = last_training_target + 1
                split_timestamp = (
                    int(prepared.sequence_timestamps[first_validation_target])
                    if first_validation_target < end
                    else history_end
                )
                user_likes = like_outcomes.get(int(uid), {})
                seen = {int(prepared.sequence_items[start])}
                for position in range(start + 1, end):
                    item = int(prepared.sequence_items[position])
                    novel = item not in seen
                    seen.add(item)
                    if not novel:
                        # Repeats remain training examples, but they cannot be
                        # eligible discovery outcomes at the corresponding
                        # cutoff and therefore keep only the ordinary weight.
                        weights[position] = config.ordinary_target_weight
                        continue
                    timestamps = user_likes.get(item)
                    if timestamps is None:
                        continue
                    timestamp = int(prepared.sequence_timestamps[position])
                    upper = min(
                        timestamp + horizon,
                        split_timestamp
                        if position <= last_training_target
                        else history_end,
                    )
                    outcome = int(np.searchsorted(timestamps, timestamp, side="left"))
                    if outcome < len(timestamps) and int(timestamps[outcome]) < upper:
                        weights[position] = config.organic_like_target_weight
                        grade_three += 1
            log(
                f"grade-3 first-encounter targets={grade_three:,} "
                f"horizon_days={config.discovery_horizon_days}"
            )
    log(
        f"target weighting={config.target_weighting} "
        f"min={weights.min():.3f} mean={weights.mean():.3f} "
        f"max={weights.max():.3f}"
            "diagnostics": diagnostics,
            "model_state": model_state,
            "optimizer_state": optimizer.state_dict(),
            "generator_state": generator.get_state(),
        },
        path,
    )
    log(f"saved epoch checkpoint: {path}")
    return path


def train_model(
    public: Path,
    stage: str,
    prepared: SequenceData,
    config: Config,
    device: torch.device,
    checkpoint_dir: Path | None,
    resume_checkpoint: Path | None,
) -> tuple[base.SequentialTwoTower, list[dict[str, float]]]:
    partition = chronological_target_partition(
        prepared,
        config.validation_fraction,
        config.max_train_targets_per_user,
        config.max_validation_targets_per_user,
    )
    training_counts = partition.training_counts
    validation_counts = partition.validation_counts
    log(
        f"chronological BCE window: train={int(training_counts.sum()):,} "
        f"validation={int(validation_counts.sum()):,} "
        f"selected={partition.selected_count:,} "
        f"discarded_old_targets={int(partition.window_starts.sum()):,} "
        f"all={prepared.target_count:,}"
    )
    model = base.SequentialTwoTower(prepared.item_features, model_config(config)).to(
        device
    )
    optimizer = torch.optim.AdamW(
        model.parameters(), lr=config.learning_rate, weight_decay=config.weight_decay
    )
    generator = torch.Generator(device="cpu").manual_seed(config.seed + 10_000)
    item_correction = build_item_correction(
        prepared,
        config,
        partition.window_starts,
        training_counts,
    )
    target_weights = build_target_weights(
        public,
        stage,
        prepared,
        partition.history_training_counts,
        config,
    )
    known_positive_packed = (
        build_known_positive_filter(prepared, partition.history_training_counts)
        if config.negative_filter_scope == "full-training-history"
        else None
    )
    history: list[dict[str, float]] = []
    best_loss = float("inf")
    best_epoch = 0
    best_state: dict[str, torch.Tensor] | None = None
    epochs_without_improvement = 0
    start_epoch = 0

    if resume_checkpoint is not None:
        payload = torch.load(
            resume_checkpoint, map_location=device, weights_only=False
        )
        stored_config = payload.get("config", {})
        architecture_fields = (
            "bptt_steps",
            "embedding_dim",
            "hidden_dim",
            "user_hidden_1",
            "user_hidden_2",
            "item_hidden_1",
            "item_hidden_2",
        )
        mismatches = {
            name: (stored_config.get(name), getattr(config, name))
            for name in architecture_fields
            if stored_config.get(name) != getattr(config, name)
        }
        if mismatches:
            raise RuntimeError(
                f"resume checkpoint architecture differs: {mismatches}"
            )
        stored_filter_scope = stored_config.get(
            "negative_filter_scope", "last-100"
        )
        stored_target_weighting = stored_config.get(
            "target_weighting", "uniform"
        )
        stored_weight_values = (
            stored_config.get("ordinary_target_weight", 1.0),
            stored_config.get("organic_strong_target_weight", 1.0),
            stored_config.get("organic_like_target_weight", 3.0),
            stored_config.get("discovery_horizon_days", 7),
        )
        current_weight_values = (
            config.ordinary_target_weight,
            config.organic_strong_target_weight,
            config.organic_like_target_weight,
            config.discovery_horizon_days,
        )
        stored_window_values = (
            stored_config.get("validation_fraction", 0.10),
            stored_config.get("max_train_targets_per_user", 0),
            stored_config.get("max_validation_targets_per_user", 0),
        )
        current_window_values = (
            config.validation_fraction,
            config.max_train_targets_per_user,
            config.max_validation_targets_per_user,
        )
        objective_changed = (
            stored_filter_scope != config.negative_filter_scope
            or stored_target_weighting != config.target_weighting
            or stored_weight_values != current_weight_values
            or stored_window_values != current_window_values
        )
        model.load_state_dict(payload["model_state"])
        if "optimizer_state" in payload and not objective_changed:
            optimizer.load_state_dict(payload["optimizer_state"])
            for group in optimizer.param_groups:
                group["lr"] = config.learning_rate
                group["weight_decay"] = config.weight_decay
            log(f"restored optimizer state from {resume_checkpoint}")
        else:
            log(
                f"using a fresh AdamW optimizer after loading {resume_checkpoint}"
            )
        if "generator_state" in payload and not objective_changed:
            generator.set_state(payload["generator_state"])
        start_epoch = int(payload["epoch"])
        if start_epoch >= config.epochs:
            raise RuntimeError(
                f"resume epoch {start_epoch} must be below --epochs {config.epochs}"
            )
        prior = {
            str(name): float(value)
            for name, value in payload.get("diagnostics", {}).items()
        }
        if objective_changed:
            prior.pop("validation_loss", None)
            log(
                "BCE objective changed: filter "
                f"{stored_filter_scope}->{config.negative_filter_scope}, "
                "target weighting "
                f"{stored_target_weighting}->{config.target_weighting}, "
                f"target window {stored_window_values}->{current_window_values}; "
                "recomputing the resume checkpoint's validation BCE"
            )
        if "validation_loss" not in prior:
            prior.update(
                evaluate_validation_bce(
                    model,
                    prepared,
                    config,
                    target_weights,
                    partition.window_starts,
                    training_counts,
                    validation_counts,
                    item_correction,
                    known_positive_packed,
                    device,
                )
            )
        history.append(prior)
        best_loss = float(prior["validation_loss"])
        best_epoch = start_epoch
        best_state = snapshot_model(model)
        log(
            f"resumed validation-BCE training: epoch={start_epoch} "
            f"loss={best_loss:.6f}"
        )

    for epoch in range(start_epoch + 1, config.epochs + 1):
        diagnostics = run_training_epoch(
            model,
            optimizer,
            prepared,
            config,
            target_weights,
            partition.window_starts,
            training_counts,
            item_correction,
            known_positive_packed,
            generator,
            device,
            epoch,
        )
        validation = evaluate_validation_bce(
            model,
            prepared,
            config,
            target_weights,
            partition.window_starts,
            training_counts,
            validation_counts,
            item_correction,
            known_positive_packed,
            device,
        )
        diagnostics.update(validation)
        history.append(diagnostics)
        current_state = snapshot_model(model)
        if checkpoint_dir is not None:
            save_epoch_checkpoint(
                checkpoint_dir,
                epoch,
                current_state,
                config,
                diagnostics,
                optimizer,
                generator,
            )
        improved = (
            diagnostics["validation_loss"]
            < best_loss - config.early_stopping_min_delta
        )
        if improved:
            best_loss = diagnostics["validation_loss"]
            best_epoch = epoch
            best_state = current_state
            epochs_without_improvement = 0
            if checkpoint_dir is not None:
                torch.save(
                    {
                        "epoch": epoch,
                        "config": asdict(config),
                        "diagnostics": diagnostics,
                        "model_state": current_state,
                        "optimizer_state": optimizer.state_dict(),
                        "generator_state": generator.get_state(),
                    },
                    checkpoint_dir / "best.pt",
                )
        else:
            epochs_without_improvement += 1
        log(
            f"epoch={epoch}/{config.epochs} train_loss={diagnostics['loss']:.5f} "
            f"validation_loss={diagnostics['validation_loss']:.5f} "
            f"pair_accuracy={diagnostics['pair_accuracy']:.3f} "
            f"train_targets={int(diagnostics['targets']):,} "
            f"validation_targets={int(diagnostics['validation_targets']):,} "
            f"train_seconds={diagnostics['seconds']:.1f} "
            f"validation_seconds={diagnostics['validation_seconds']:.1f}"
        )
        release_accelerator_cache(device)
        if epochs_without_improvement >= config.early_stopping_patience:
            log(
                f"early stopping after epoch={epoch}; "
                f"best_epoch={best_epoch} best_validation_loss={best_loss:.6f}"
            )
            break

    if best_state is None:
        raise RuntimeError("training did not produce a valid checkpoint")
    model.load_state_dict(best_state)
    model.to(device).eval()
    log(
        f"restored best validation-BCE checkpoint: epoch={best_epoch} "
        f"loss={best_loss:.6f}"
    )
    return model, history


@torch.inference_mode()
def inference_queries(
    model: base.SequentialTwoTower,
    prepared: SequenceData,
    config: Config,
    device: torch.device,
) -> torch.Tensor:
    sequence_rows = prepared.inference_user_rows
    lengths = np.where(
        sequence_rows >= 0, prepared.lengths[np.maximum(sequence_rows, 0)], 0
    )
    ordered = np.argsort(lengths, kind="stable")
    result = torch.zeros(
        len(sequence_rows), config.embedding_dim, dtype=torch.float32
    )
    for group_start in range(0, len(ordered), config.user_batch_size):
        output_rows = ordered[group_start : group_start + config.user_batch_size]
        rows = sequence_rows[output_rows]
        group_lengths = lengths[output_rows]
        hidden = torch.zeros(
            1, len(output_rows), config.embedding_dim, device=device
        )
        for start in range(0, int(group_lengths.max(initial=0)), config.bptt_steps):
            steps = min(
                config.bptt_steps,
                int(group_lengths.max(initial=0)) - start,
            )
            items = np.full(
                (len(output_rows), steps),
                len(prepared.item_ids),


def main() -> int:
    parser = argparse.ArgumentParser(description=__doc__)
    parser.add_argument(
        "--stage", choices=("validation", "submission"), default="validation"
    )
    parser.add_argument("--output", type=Path, required=True)
    parser.add_argument("--public-dir", type=Path, required=True)
    parser.add_argument("--prepared-cache", type=Path)
    parser.add_argument("--device", choices=("cpu", "mps"), default="cpu")
    parser.add_argument("--threads", type=int, default=8)
    parser.add_argument("--bptt-steps", type=int, default=Config.bptt_steps)
    parser.add_argument(
        "--user-batch-size", type=int, default=Config.user_batch_size
    )
    parser.add_argument("--epochs", type=int, default=Config.epochs)
    parser.add_argument("--learning-rate", type=float, default=Config.learning_rate)
    parser.add_argument(
        "--loss-microbatch-size",
        type=int,
        default=Config.loss_microbatch_size,
    )
    parser.add_argument(
        "--negative-filter-scope",
        choices=("full-training-history", "last-100"),
        default=Config.negative_filter_scope,
    )
    parser.add_argument(
        "--target-weighting",
        choices=("discovery-graded", "organic-strong", "uniform"),
        default=Config.target_weighting,
    )
    parser.add_argument(
        "--ordinary-target-weight",
        type=float,
        default=Config.ordinary_target_weight,
    )
    parser.add_argument(
        "--organic-strong-target-weight",
        type=float,
        default=Config.organic_strong_target_weight,
    )
    parser.add_argument(
        "--organic-like-target-weight",
        type=float,
        default=Config.organic_like_target_weight,
    )
    parser.add_argument(
        "--discovery-horizon-days",
        type=int,
        default=Config.discovery_horizon_days,
    )
    parser.add_argument(
        "--validation-fraction",
        type=float,
        default=Config.validation_fraction,
    )
    parser.add_argument(
        "--max-train-targets-per-user",
        type=int,
        default=Config.max_train_targets_per_user,
        help="retain this many recent pre-validation targets per user; 0 is uncapped",
    )
    parser.add_argument(
        "--max-validation-targets-per-user",
        type=int,
        default=Config.max_validation_targets_per_user,
        help="retain this many final validation targets per user; 0 is uncapped",
    )
    parser.add_argument(
        "--early-stopping-patience",
        type=int,
        default=Config.early_stopping_patience,
    )
    parser.add_argument(
        "--early-stopping-min-delta",
        type=float,
        default=Config.early_stopping_min_delta,
    )
    parser.add_argument("--checkpoint-dir", type=Path)
    parser.add_argument("--resume-checkpoint", type=Path)
    parser.add_argument("--seed", type=int, default=Config.seed)
    parser.add_argument("--ranking-batch-size", type=int, default=64)
    parser.add_argument("--prepare-only", action="store_true")
    args = parser.parse_args()

    if args.threads < 1 or args.bptt_steps < 2 or args.user_batch_size < 1:
        parser.error("threads, BPTT steps, and user batch size must be positive")
    if (
        args.epochs < 1
        or args.learning_rate <= 0
        or args.loss_microbatch_size < 1
        or args.early_stopping_patience < 1
        or args.early_stopping_min_delta < 0
        or args.ordinary_target_weight <= 0
        or args.organic_strong_target_weight <= 0
        or args.organic_like_target_weight <= 0
        or args.discovery_horizon_days < 1
        or args.max_train_targets_per_user < 0
        or args.max_validation_targets_per_user < 0
    ):
        parser.error("training counts, learning rate, and patience are invalid")
    if not 0.0 < args.validation_fraction < 1.0:
        parser.error("validation fraction must be strictly between zero and one")
    public = args.public_dir.resolve()
    if not (public / "data" / "candidate_catalog.parquet").is_file():
        parser.error(f"public task data not found under {public}")
    config = Config(
        bptt_steps=args.bptt_steps,
        user_batch_size=args.user_batch_size,
        epochs=args.epochs,
        learning_rate=args.learning_rate,
        loss_microbatch_size=args.loss_microbatch_size,
        negative_filter_scope=args.negative_filter_scope,
        target_weighting=args.target_weighting,
        ordinary_target_weight=args.ordinary_target_weight,
        organic_strong_target_weight=args.organic_strong_target_weight,
        organic_like_target_weight=args.organic_like_target_weight,
        discovery_horizon_days=args.discovery_horizon_days,
        validation_fraction=args.validation_fraction,
        max_train_targets_per_user=args.max_train_targets_per_user,
        max_validation_targets_per_user=args.max_validation_targets_per_user,
        early_stopping_patience=args.early_stopping_patience,
        early_stopping_min_delta=args.early_stopping_min_delta,
        seed=args.seed,
    )
    torch.set_num_threads(args.threads)
    torch.set_num_interop_threads(1)
    seed_everything(config.seed)
    device = torch.device(args.device)
    if device.type == "mps" and not torch.backends.mps.is_available():
        parser.error("MPS was requested but is unavailable")

    started = time.monotonic()
    prepared, eligibility = load_or_prepare(
        public,
        args.stage,
        config,
        args.prepared_cache.resolve() if args.prepared_cache else None,
    )
    target_partition = chronological_target_partition(
        prepared,
        config.validation_fraction,
        config.max_train_targets_per_user,
        config.max_validation_targets_per_user,
    )
    if args.prepare_only:
        print(
            json.dumps(
                {
                    "stage": args.stage,
                    "sequence_users": len(prepared.user_ids),
                    "sequence_tokens": len(prepared.sequence_items),
                    "next_item_targets": prepared.target_count,
                    "selected_training_targets": int(
                        target_partition.training_counts.sum()
                    ),
                    "selected_validation_targets": int(
                        target_partition.validation_counts.sum()
                    ),
                    "discarded_old_targets": int(
                        target_partition.window_starts.sum()
                    ),
                    "target_users": len(eligibility.uids),
                    "runtime_seconds": round(time.monotonic() - started, 3),
                    "config": asdict(config),
                },
                indent=2,
            )
        )
        return 0

    model, training_history = train_model(
        public,
        args.stage,
        prepared,
        config,
        device,
        args.checkpoint_dir.resolve() if args.checkpoint_dir else None,
        args.resume_checkpoint.resolve() if args.resume_checkpoint else None,
    )
    ranking, embedding_diagnostics = rank_candidates(
        model,
        prepared,
        eligibility,
        config,
        device,
        args.ranking_batch_size,
    )
    write_ranking(ranking, args.output.resolve())
    print(
        json.dumps(
            {
                "baseline": "yambda-windowed-sequence-two-tower-base",
                "stage": args.stage,
                "output": str(args.output.resolve()),
                "rows": len(ranking),
                "users": int(ranking.uid.nunique()),
                "runtime_seconds": round(time.monotonic() - started, 3),
                "public_inputs_only": True,
                "architecture": {
                    "family": "pure-windowed-sequence-two-tower",
                    "sequence_training": (
                        "every-adjacent-target-within-recent-chronological-window"
                    ),
                    "sequence_encoder": "one-layer-GRU-dense-timestep-loss",
                    "bptt_hidden_state": "carried-and-detached",
                    "model_selection": "chronological-validation-BCE-early-stopping",
                    "loss_execution": "gradient-accumulated-microbatches",
                    "user_id_embedding": False,
                    "user_mlp": "582-512-256-192",
                    "item_mlp": "196-512-256-192",
                    "normalization": "none",
                    "score": "raw-dot-product",
                    "objective": "sample-weighted-BCE-at-every-timestep",
                    "negative_sampling": (
                        "24-uniform-plus-8-propensity-corrected-inbatch"
                    ),
                    "false_negative_filter": config.negative_filter_scope,
                    "target_weighting": config.target_weighting,
                },
                "config": asdict(config),
                "sequence_tokens": len(prepared.sequence_items),
                "all_next_item_targets": prepared.target_count,
                "selected_training_targets": int(
                    target_partition.training_counts.sum()
                ),
                "selected_validation_targets": int(
                    target_partition.validation_counts.sum()
                ),
                "discarded_old_targets": int(target_partition.window_starts.sum()),
                "training_history": training_history,
                "embedding_diagnostics": embedding_diagnostics,
                "torch_version": torch.__version__,
                "device": str(device),
            },
            indent=2,
        )
    )
    return 0

Script completed
Wall time 5.0 seconds
Output:

{"chunk_id":"a8c4f5","wall_time_seconds":5.0007211,"session_id":51338,"original_token_count":50,"output":"prepared users=1,000 tokens=2,090,746 states=35,727 elapsed=4.8s\nprepared users=2,000 tokens=4,301,266 states=71,242 elapsed=9.8s\nprepared users=3,000 tokens=6,486,146 states=109,471 elapsed=15.0s\n"}

Script completed
Wall time 0.1 seconds
Output:

#!/usr/bin/env python3
"""Score a validation-stage ranking against public discovery labels.

``build_task.py`` publishes this module with the solver-visible task files. It
loads target users, validation eligibility, and validation-window events from
the adjacent ``data`` directory, then evaluates one ranking supplied on the
command line. Stage-independent mechanics come from the adjacent public
``ranking_evaluation.py`` module. The builder installs the same checked-in
module in the private judge, so public and private scoring mechanics cannot
drift. A relevant candidate receives grade 3 for an organic like or grade 1 for
an organic listen with at least 80 percent completion; a like takes precedence
when both events exist.

Before scoring, the ranking must contain exactly 100 distinct eligible items
for every target user, with integer-valued ``uid``, ``item_id``, and ``rank``
columns and ranks 1 through 100 exactly once per user. Extra columns are
ignored. Quality is graded NDCG@10, averaged only over users who have at least
one eligible relevant item in the validation window.

The evaluator prints a JSON object containing the model path and scores. It
does not apply the task's pass threshold; its purpose is model development and
selection. The private judge applies the threshold to the final submission.

Usage::

    python evaluate_public.py <validation-ranking.parquet|csv>
"""
from __future__ import annotations

import json
import sys
from pathlib import Path

import pandas as pd

from ranking_evaluation import (
    CandidateSet,
    RankingValidationError,
    ranked_items,
    read_ranking,
    score_rankings,
    validate_ranking,
)


HERE = Path(__file__).resolve().parent
DATA = HERE / "data"
LISTEN_STRONG = 80


def validation_truth(
    eligibility: CandidateSet, targets: set[int]
) -> dict[int, dict[int, int]]:
    """Build cutoff-correct graded relevance from public validation events.

    Only target-user events for eligible candidates are retained. Organic
    listens completed to at least 80 percent receive grade 1, and organic likes
    receive grade 3. Repeated user-item events are collapsed, and processing
    likes second ensures that grade 3 wins over grade 1.

    Args:
        eligibility: Validation-cutoff candidate membership service.
        targets: Complete set of target user IDs.

    Returns:
        A nested ``uid -> item_id -> grade`` mapping. Users without an eligible
        relevant event are omitted.
    """
    listens = pd.read_parquet(DATA / "val_listens.parquet")
    likes = pd.read_parquet(DATA / "val_likes.parquet")
    strong = listens[
        listens.uid.isin(targets)
        & (listens.is_organic == 1)
        & (listens.played_ratio_pct >= LISTEN_STRONG)
    ][["uid", "item_id"]].drop_duplicates()
    organic_likes = likes[
        likes.uid.isin(targets) & (likes.is_organic == 1)
    ][["uid", "item_id"]].drop_duplicates()

    graded: dict[int, dict[int, int]] = {}
    for raw_uid, raw_item in strong.itertuples(index=False, name=None):
        uid, item = int(raw_uid), int(raw_item)
        if eligibility.is_eligible(uid, item):
            graded.setdefault(uid, {})[item] = 1
    for raw_uid, raw_item in organic_likes.itertuples(index=False, name=None):
        uid, item = int(raw_uid), int(raw_item)
        if eligibility.is_eligible(uid, item):
            graded.setdefault(uid, {})[item] = 3
    return graded


def load_submission(
    path: Path, eligibility: CandidateSet, targets: set[int]
) -> dict[int, list[int]]:
    """Load and validate a public validation ranking.

    Files ending in ``.parquet`` are read as parquet; every other suffix is
    read as CSV. The required columns must be integer-valued, cover exactly the
    target-user set, contain 100 rows and ranks 1 through 100 per user, avoid
    duplicate user-item pairs, and contain only cutoff-eligible items.

    Args:
        path: Ranking file to read.
        eligibility: Validation-cutoff candidate membership service.
        targets: Exact set of users the ranking must cover.

    Returns:
        A ``uid -> ranked item IDs`` mapping ordered by ascending rank.

    Raises:
        ValueError: If the ranking violates the required schema or invariants.
    """
    frame = validate_ranking(read_ranking(path), targets)
    if not all(
        eligibility.is_eligible(uid, item)
        for uid, item in frame[["uid", "item_id"]].itertuples(index=False, name=None)
    ):
        raise RankingValidationError(
            "submission contains an item rejected by eligibility service"
        )
    return ranked_items(frame)


def score(
    ranked: dict[int, list[int]],
    graded: dict[int, dict[int, int]],
) -> dict[str, float | int]:
    """Aggregate per-user NDCG@10 over users with public relevance labels.

    Args:
        ranked: Ranked item IDs for every target user.
        graded: Eligible validation relevance keyed by user and item.

    Returns:
        The six-decimal ``quality_ndcg@10`` value and number of scored users.
    """
    return score_rankings(ranked, graded)


def main() -> None:
    """Run the public evaluator CLI and print its JSON score report."""
    targets_frame = pd.read_parquet(DATA / "target_users.parquet")
    targets = set(targets_frame.uid.astype(int))
    eligibility = CandidateSet(DATA / "validation_eligible_candidates.npz")
    graded = validation_truth(eligibility, targets)

    if len(sys.argv) != 2:
        raise SystemExit(
            "usage: evaluate_public.py <validation-ranking.parquet|csv>"
        )
    path = Path(sys.argv[1])
    ranked = load_submission(path, eligibility, targets)
    print(json.dumps({"model": str(path), "scores": score(ranked, graded)}, indent=2))


if __name__ == "__main__":
    main()
"""Shared public primitives for Yambda discovery-ranking evaluation.

Both the solver-visible validation evaluator and the private submission judge
import this module from the generated task's ``public`` directory. It owns the
stage-independent contract: reading a ranking, validating its shape, converting
it to per-user rank order, looking up packed candidate eligibility, and
computing graded NDCG@10.

The module deliberately contains no event-derived labels, private artifact
paths, or pass thresholds. Each evaluator supplies its own relevance data and
per-cutoff eligibility checks around these common operations.
"""
from __future__ import annotations

from pathlib import Path

import numpy as np
import pandas as pd


__all__ = [
    "CandidateSet",
    "QUALITY_K",
    "RankingValidationError",
    "REQUIRED_COLUMNS",
    "TOP_N",
    "ndcg_at_k",
    "ranked_items",
    "read_ranking",
    "score_rankings",
    "validate_ranking",
]

TOP_N = 100
QUALITY_K = 10
REQUIRED_COLUMNS = ("uid", "item_id", "rank")


class RankingValidationError(ValueError):
    """Report a ranking-schema or structural-contract violation."""


class CandidateSet:
    """Provide membership lookups over one packed candidate-set archive.

    The archive contains aligned ``uids``, ``item_ids``, and
    ``packed_eligible`` arrays. Candidate column ``c`` is represented by bit
    ``c % 8`` of byte ``c // 8`` using little-endian bit order. Arrays are
    copied into memory so they remain valid after the archive is closed.
    """

    def __init__(self, path: Path):
        """Load an eligibility archive and build ID-to-position indexes.

        Args:
            path: Path to a ``.npz`` archive with the candidate-set schema.
        """
        with np.load(path, allow_pickle=False) as artifact:
            self.uids = artifact["uids"].astype(np.int64, copy=True)
            self.item_ids = artifact["item_ids"].astype(np.int64, copy=True)
            self.packed = artifact["packed_eligible"].astype(np.uint8, copy=True)
        self.uid_row = {int(uid): row for row, uid in enumerate(self.uids)}
        self.item_column = {
            int(item): column for column, item in enumerate(self.item_ids)
        }

    def is_eligible(self, uid: int, item_id: int) -> bool:
        """Return whether ``item_id`` is eligible for ``uid``.

        IDs absent from the target-user or candidate-item arrays are treated as
        ineligible rather than raising an exception.

        Args:
            uid: Target user ID to query.
            item_id: Candidate item ID to query.

        Returns:
            ``True`` only when the corresponding packed eligibility bit is set.
        """
        row = self.uid_row.get(int(uid))
        column = self.item_column.get(int(item_id))
        if row is None or column is None:
            return False
        byte, bit = divmod(column, 8)
        return bool((int(self.packed[row, byte]) >> bit) & 1)


def read_ranking(path: Path) -> pd.DataFrame:
    """Read a parquet or CSV ranking into a pandas frame.

    Args:
        path: Input path. A ``.parquet`` suffix selects parquet; every other
            suffix is interpreted as CSV.

    Returns:
        The ranking frame as loaded by pandas.
    """
    return pd.read_parquet(path) if path.suffix == ".parquet" else pd.read_csv(path)


def validate_ranking(
    frame: pd.DataFrame,
    targets: set[int],
) -> pd.DataFrame:
    """Normalize and validate the stage-independent ranking contract.

    Required values must be finite integers. The user set must exactly match
    ``targets``; every user must have 100 rows, distinct items, and each rank
    from 1 through 100 exactly once. Cutoff-specific candidate eligibility is
    intentionally left to the calling evaluator.

    Args:
        frame: Raw ranking frame. Extra columns are discarded from an internal
            copy; the caller's frame is not modified.
        targets: Exact set of target user IDs the ranking must cover.

    Returns:
        A normalized frame containing only the required ``int64`` columns.

    Raises:
        RankingValidationError: If the ranking violates the shared contract.
    """
    required = list(REQUIRED_COLUMNS)
    if not all(column in frame for column in required):
        raise RankingValidationError(f"submission requires columns {required}")

    normalized = frame[required].copy()
    for column in required:
        numeric = pd.to_numeric(normalized[column], errors="coerce")
        values = numeric.to_numpy(dtype=float)
        if numeric.isna().any() or not np.isfinite(values).all():
            raise RankingValidationError(
                f"submission {column} must be finite numeric values"
            )
        if not np.equal(numeric, np.floor(numeric)).all():
            raise RankingValidationError(
                f"submission {column} must contain integers"
            )
        normalized[column] = numeric.astype(np.int64)

    submitted_users = set(map(int, normalized.uid.unique()))
    if submitted_users != targets:
        raise RankingValidationError(
            f"submission user set mismatch: missing={len(targets - submitted_users)} "
            f"extra={len(submitted_users - targets)}"
        )
    counts = normalized.groupby("uid").size()
    if not (counts == TOP_N).all():
        raise RankingValidationError(
            f"submission must contain exactly {TOP_N} rows for every target user"
        )
    if normalized.duplicated(["uid", "item_id"]).any():
        raise RankingValidationError(
            "submission contains duplicate (uid, item_id) pairs"
        )
    valid_ranks = set(range(1, TOP_N + 1))
    ranks_are_valid = normalized.groupby("uid")["rank"].apply(
        lambda values: set(map(int, values)) == valid_ranks
    )
    if not ranks_are_valid.all():
        raise RankingValidationError(
            f"each user must have every rank from 1 through {TOP_N} exactly once"
        )
    return normalized


def ranked_items(frame: pd.DataFrame) -> dict[int, list[int]]:
    """Convert a validated ranking frame to ordered items keyed by user.

    Args:
        frame: Frame that has passed :func:`validate_ranking`.

    Returns:
        A ``uid -> item IDs`` mapping ordered by ascending rank.
    """
    ordered = frame.sort_values(["uid", "rank"])
    return {
        int(uid): list(map(int, values))
        for uid, values in ordered.groupby("uid").item_id
    }


def ndcg_at_k(ranked: list[int], gold: dict[int, int], k: int) -> float:
    """Compute graded normalized discounted cumulative gain at ``k``.

    Relevance gain is ``2**grade - 1`` and the discount at one-based rank
    ``r`` is ``1 / log2(r + 1)``. Items absent from ``gold`` have grade zero.

    Args:
        ranked: Item IDs in predicted rank order.
        gold: Mapping from relevant item IDs to integer relevance grades.
        k: Maximum number of predicted positions to score.

    Returns:
        For a valid duplicate-free ranking, NDCG in ``[0, 1]``; returns
        ``0.0`` when the ideal gain is zero.
    """
    gains = np.asarray([gold.get(item, 0) for item in ranked[:k]], dtype=np.float64)
    discounts = 1.0 / np.log2(np.arange(2, len(gains) + 2))
    dcg = float(np.sum((np.power(2.0, gains) - 1.0) * discounts))
    ideal = np.asarray(sorted(gold.values(), reverse=True)[:k], dtype=np.float64)
    ideal_discounts = 1.0 / np.log2(np.arange(2, len(ideal) + 2))
    idcg = float(np.sum((np.power(2.0, ideal) - 1.0) * ideal_discounts))
    return dcg / idcg if idcg else 0.0


def score_rankings(
    ranked: dict[int, list[int]],
    graded: dict[int, dict[int, int]],
) -> dict[str, float | int]:
    """Aggregate per-user NDCG@10 over users with relevance labels.

    Args:
        ranked: Ranked item IDs for every target user.
        graded: Relevant item grades keyed by user and item.

    Returns:
        The six-decimal ``quality_ndcg@10`` value and number of scored users.
    """
    quality = float(
        np.mean(
            [
                ndcg_at_k(ranked[uid], gold, QUALITY_K)
                for uid, gold in graded.items()
            ]
        )
    )
    return {
        "quality_ndcg@10": round(quality, 6),
        "quality_users": len(graded),
    }

Script completed
Wall time 5.0 seconds
Output:

{"chunk_id":"30f8a0","wall_time_seconds":5.002030301,"session_id":51338,"original_token_count":229,"output":"prepared users=4,000 tokens=8,793,043 states=148,210 elapsed=20.4s\nprepared users=5,000 tokens=10,992,205 states=182,596 elapsed=25.2s\nprepared users=6,000 tokens=13,061,727 states=217,148 elapsed=29.9s\nprepared users=7,000 tokens=15,334,418 states=256,914 elapsed=35.4s\nprepared users=8,000 tokens=17,462,672 states=296,703 elapsed=40.7s\nprepared users=9,000 tokens=19,568,405 states=331,551 elapsed=45.4s\ntarget users without qualifying catalog sequence=7\nprepared stage=validation sequence_users=9,135 tokens=20,056,329 next_item_targets=20,047,194 states=339,133\nchronological BCE window: train=1,052,953 validation=130,103 selected=1,183,056 discarded_old_targets=18,864,138 all=20,047,194\ninbatch correction: min=0.250 mean_on_targets=1.001 max=4.000\ntarget weighting=organic-strong min=0.250 mean=0.575 max=1.000\nfull-history false-negative filter: users=9,135 unique_user_items=5,524,275 bytes=34,256,250\n"}

Script completed
Wall time 5.0 seconds
Output:

{"chunk_id":"971bbd","wall_time_seconds":5.001526969,"session_id":51338,"original_token_count":0,"output":""}

Script completed
Wall time 0.1 seconds
Output:

loaded explicit events: rows=720,270 users=8,220
prepared users=1,000 tokens=2,090,746 states=35,727 elapsed=4.8s
prepared users=2,000 tokens=4,301,266 states=71,242 elapsed=9.8s
prepared users=3,000 tokens=6,486,146 states=109,471 elapsed=15.0s
prepared users=4,000 tokens=8,793,043 states=148,210 elapsed=20.4s
prepared users=5,000 tokens=10,992,205 states=182,596 elapsed=25.2s
prepared users=6,000 tokens=13,061,727 states=217,148 elapsed=29.9s
prepared users=7,000 tokens=15,334,418 states=256,914 elapsed=35.4s
prepared users=8,000 tokens=17,462,672 states=296,703 elapsed=40.7s
prepared users=9,000 tokens=19,568,405 states=331,551 elapsed=45.4s
target users without qualifying catalog sequence=7
prepared stage=validation sequence_users=9,135 tokens=20,056,329 next_item_targets=20,047,194 states=339,133
chronological BCE window: train=1,052,953 validation=130,103 selected=1,183,056 discarded_old_targets=18,864,138 all=20,047,194
inbatch correction: min=0.250 mean_on_targets=1.001 max=4.000
target weighting=organic-strong min=0.250 mean=0.575 max=1.000
full-history false-negative filter: users=9,135 unique_user_items=5,524,275 bytes=34,256,250
/bin/sh: 2: ps: not found
/bin/sh: 2: rg: not found

Script completed
Wall time 5.1 seconds
Output:

{"chunk_id":"f7466e","wall_time_seconds":5.002340881,"session_id":51338,"original_token_count":0,"output":""}

Script completed
Wall time 9.1 seconds
Output:

catalog 30000 users 8456 eligible mean 29067.306291390727
truth 266887 users 6511 grades {1: 249692, 3: 17195}
          count         mean          std  min    10%      25%     50%      75%      90%      max
grade                                                                                            
1      167201.0  7190.356134  7798.668689  1.0  205.0   988.00  4056.0  11221.0  20049.0  30000.0
3        8528.0  8415.048311  8123.488549  1.0  442.0  1648.75  5554.0  13506.5  21728.7  29989.0
{
  "model": "/app/solution/popularity_validation.parquet",
  "scores": {
    "quality_ndcg@10": 0.01071,
    "quality_users": 4263
  }
}

Script completed
Wall time 5.0 seconds
Output:

{"chunk_id":"abe27f","wall_time_seconds":5.001002214,"session_id":51338,"original_token_count":0,"output":""}

Script completed
Wall time 0.1 seconds
Output:

Warning: truncated output (original token count: 4569)
Total output lines: 357

/proc/315/cmdline /bin/sh -lc /opt/task-venv/bin/python /app/solution/train_current_model.py --stage validation --public-dir /task --output /app/solution/production_validation.parquet 2>&1 | tee /app/solution/production_validation.log 
/proc/318/cmdline /opt/task-venv/bin/python /app/solution/train_current_model.py --stage validation --public-dir /task --output /app/solution/production_validation.parquet 
/proc/462/cmdline /bin/sh -c for f in /proc/[0-9]*/cmdline; do s=$(tr '' ' ' < "$f" 2>/dev/null); case "$s" in *train_current_model.py*) echo "$f $s";; esac; done 
/proc/60/cmdline bash -c set -o pipefail; if [ -s ~/.nvm/nvm.sh ]; then . ~/.nvm/nvm.sh; fi; codex exec --dangerously-bypass-approvals-and-sandbox --skip-git-repo-check --model gpt-5.6-sol --json --enable unified_exec -c model_reasoning_effort=high -- '# Improve a production music-discovery two-tower

You have joined the recommendations team for a music streaming service. The
"Made for You" shelf is served by a mature production two-tower model. Its
chronological data protocol and indexed serving path are sound, but its offline
retrieval quality no longer clears the team'"'"'s next launch gate.

Your job is to investigate the production model, improve its retrieval quality,
and ship a better ranking artifact. Use the implementation and public validation
data to form and test your own diagnosis.

The source used to reproduce the production model is included under
`/task/current_model/`. You may copy it into `/app/solution/`, edit it, add
tests, and improve its training objective, but keep the data protocol,
two-tower serving contract, and evaluation boundary intact.

## Production Context

The model must satisfy a strict request-time latency budget. Item vectors are
precomputed offline. At request time, one user vector is computed from observed
interaction history and compared with candidate item vectors by a batchable
two-tower score. Do not introduce a cross-encoder, per-candidate sequence model,
or user-ID lookup table.

The current trainer is a mature baseline with chronological internal
validation. Focus your investigation on how its training objective selects and
uses negative examples. Diagnose limitations in the current negative-sampling
strategy and improve it under the fixed CPU budget. Validate changes with the
public backtest. The final approach must still train and rank within the supplied
CPU environment while preserving the serving and data boundaries above.

## What You Have

All public inputs are under `/task/data/`. A stage cutoff is the timestamp at
which observed history and candidate eligibility are frozen for a ranking. The
public validation stage cutoff is `24786800`, when `train_*` ends. A 30-minute
gap precedes the seven-day `val_*` window. For the final submission, that
validation window becomes observed history, and another 30-minute gap precedes
the hidden seven-day outcome window.

The package includes:

- `/task/current_model/train_current_model.py`: the production training and
  ranking script. It can reproduce the public validation ranking and produce a
  hidden-test submission after refitting.
- `/task/current_model/two_tower_model.py`: model primitives used by the
  production script.
- `/task/evaluate_public.py`: the public validation evaluator for development.
- `/task/data/validation_eligible_candidates.npz` and
  `/task/data/test_eligible_candidates.npz`: platform-owned candidate sets for
  the validation and hidden-test cutoffs.
- `/task/data/validation_preference_state.parquet` and
  `/task/data/test_preference_state.parquet`: active explicit preference state
  at the corresponding cutoffs.
- `/task/requirements.txt`: the exact offline Python distribution inventory.

You can reproduce the production public backtest with:

```sh
python /task/current_model/train_current_model.py \
  --stage validation \
  --public-dir /task \
  --output /app/solution/production_validation.parquet
python /task/evaluate_public.py /app/solution/production_validation.parquet
```

## Data

For each event family there is a `train_*.parquet` and `val_*.parquet` file:

| Family | Meaning | Columns |
| --- | --- | --- |
| `listens` | Playback events | `uid`, `timestamp`, `item_id`, `is_organic`, `played_ratio_pct`, `track_length_seconds` |
| `likes` | Explicit positive actions | `uid`, `timestamp`, `item_id`, `is_organic` |
| `dislikes` | Explicit negative actions | `uid`, `timestamp`, `item_id`, `is_organic` |
| `unlikes` | Reversal of a prior like | `uid`, `timestamp`, `item_id`, `is_organic` |
| `undislikes` | Reversal of a prior dislike | `uid`, `timestamp`, `item_id`, `is_organic` |

`is_organic=1` means the listener sought out the track; `0` means the action came
through a recommendation surface. A listen is a conventional positive at 50%
completion. The discovery-quality objective below uses the stronger 80%
threshold.

The two public windows have different roles:

1. For model development and selection, train only from `train_*` and score the
   subsequent `val_*` outcomes.
2. After selecting an improvement, refit it on `train_* + val_*`. At hidden-test
   time the validation events are observed history, not recommendable outcomes.

Do not use `val_*` events as features when measuring a validation ranking. They
may and should be used when refitting the final hidden-test ranker.

Additional files under `/task/data/`:

- `candidate_catalog.parquet`: the 30,000 retrieval-catalog tracks, ordered by
  training positive-listen popularity.
- `target_users.parquet`: users with at least 20 positive listens in the 90 days
  before the training cutoff, selected without future labels.
- `validation_preference_state.parquet`: active explicit state at the training
  cutoff, for validation ranking.
- `test_preference_state.parquet`: active explicit state after validation, for
  the final hidden-test ranking. State is `liked` or `disliked`; a pair may have
  both active channels.
- `validation_eligible_candidates.npz` and…1569 tokens truncated… sets for
  the validation and hidden-test cutoffs.
- `/task/data/validation_preference_state.parquet` and
  `/task/data/test_preference_state.parquet`: active explicit preference state
  at the corresponding cutoffs.
- `/task/requirements.txt`: the exact offline Python distribution inventory.

You can reproduce the production public backtest with:

```sh
python /task/current_model/train_current_model.py \
  --stage validation \
  --public-dir /task \
  --output /app/solution/production_validation.parquet
python /task/evaluate_public.py /app/solution/production_validation.parquet
```

## Data

For each event family there is a `train_*.parquet` and `val_*.parquet` file:

| Family | Meaning | Columns |
| --- | --- | --- |
| `listens` | Playback events | `uid`, `timestamp`, `item_id`, `is_organic`, `played_ratio_pct`, `track_length_seconds` |
| `likes` | Explicit positive actions | `uid`, `timestamp`, `item_id`, `is_organic` |
| `dislikes` | Explicit negative actions | `uid`, `timestamp`, `item_id`, `is_organic` |
| `unlikes` | Reversal of a prior like | `uid`, `timestamp`, `item_id`, `is_organic` |
| `undislikes` | Reversal of a prior dislike | `uid`, `timestamp`, `item_id`, `is_organic` |

`is_organic=1` means the listener sought out the track; `0` means the action came
through a recommendation surface. A listen is a conventional positive at 50%
completion. The discovery-quality objective below uses the stronger 80%
threshold.

The two public windows have different roles:

1. For model development and selection, train only from `train_*` and score the
   subsequent `val_*` outcomes.
2. After selecting an improvement, refit it on `train_* + val_*`. At hidden-test
   time the validation events are observed history, not recommendable outcomes.

Do not use `val_*` events as features when measuring a validation ranking. They
may and should be used when refitting the final hidden-test ranker.

Additional files under `/task/data/`:

- `candidate_catalog.parquet`: the 30,000 retrieval-catalog tracks, ordered by
  training positive-listen popularity.
- `target_users.parquet`: users with at least 20 positive listens in the 90 days
  before the training cutoff, selected without future labels.
- `validation_preference_state.parquet`: active explicit state at the training
  cutoff, for validation ranking.
- `test_preference_state.parquet`: active explicit state after validation, for
  the final hidden-test ranking. State is `liked` or `disliked`; a pair may have
  both active channels.
- `validation_eligible_candidates.npz` and `test_eligible_candidates.npz`:
  cutoff-correct candidate sets for every target user. Each contains aligned
  arrays `uids`, `item_ids`, and `packed_eligible`. For user row `r`, recover
  the Boolean item mask with `np.unpackbits(packed_eligible[r],
  count=len(item_ids), bitorder="little")`.

Validation candidates exclude all `train_*` encounters. Test candidates exclude
all `train_*` and `val_*` encounters. Future test interactions are hidden and
used only by the separate Harbor verifier.

## Discovery Objective

Rank only the candidates returned for the relevant cutoff. Relevance is based
on organic behavior in the immediately following window:

- grade 3: the user organically likes the track;
- grade 1: the user organically listens to at least 80% of the track;
- grade 0: otherwise.

If both positive events occur, grade 3 wins. Ranking quality is measured with
graded NDCG@10. DCG uses gain `2^grade - 1` and discount
`1/log2(rank + 1)`, then averages per-user NDCG over users with at least one
relevant item.

The public evaluator reports this same objective for development, but its score
is not a separate acceptance stage. Final acceptance is determined on the
hidden test using the same objective. The Yambda logs contain interactions, not
impression propensities; treat the organic objective as a robust offline target,
not as a causal estimate of online lift.

## Deliverable

Submit one final ranking as `/app/solution/submission.parquet` or
`/app/solution/submission.csv`. It must be a regular file, not a symbolic link.
If both files exist, the verifier evaluates `submission.parquet` and ignores
`submission.csv`.

The ranking must:

- include the columns `uid`, `item_id`, and `rank`; only these columns are
  evaluated;
- use finite, integer-valued entries in all three required columns;
- cover exactly the users in `target_users.parquet`, with no missing or extra
  users;
- contain exactly 100 rows and 100 distinct items for every target user;
- contain every integer rank from 1 through 100 exactly once per user; and
- use only items present in that user's `test_eligible_candidates.npz`
  candidate set.

Also leave the improved implementation used to build the artifact at
`/app/solution/train_current_model.py`, along with any local modules it imports.
A concise `/app/solution/README.md` with the diagnosis, before-and-after public
score, model change, and submission command is useful for the experiment record,
but it is not an automated acceptance gate.

## Constraints

- Write deliverables and intermediate artifacts only under `/app/solution/`.
- Treat `/task/` and the installed Python environment as read-only.
- Do not invoke nested agents or attempt to access verifier files, credentials,
  other trials, or host paths.
- Do not install packages or use network access except for the model-provider
  connection managed by Harbor.
- Do not alter cutoff definitions, target users, candidate eligibility, or
  relevance labels.
- Improve the production pipeline in place. Do not substitute an unrelated
  model family or evade the indexed two-tower serving constraint.
- The environment includes CPU PyTorch 2.8.0. No accelerator is available.
- You have up to 60 minutes. Prioritize measured validation improvements, a
  correct final refit, and a valid submission over broad architecture search.
- Keep the best valid submission saved throughout the attempt so it survives
  the deadline.
 

Script completed
Wall time 0.1 seconds
Output:

Name:	python
Umask:	0022
State:	R (running)
Tgid:	318
Ngid:	0
Pid:	318
PPid:	315
TracerPid:	0
Uid:	1000	1000	1000	1000
Gid:	1000	1000	1000	1000
FDSize:	64
Groups:	1000 
NStgid:	318
NSpid:	318
NSpgid:	315
NSsid:	315
Kthread:	0
VmPeak:	 7518428 kB
VmSize:	 6971628 kB
VmLck:	       0 kB
VmPin:	       0 kB
VmHWM:	 5026444 kB
VmRSS:	 4468296 kB
RssAnon:	 4318196 kB
RssFile:	  150100 kB
RssShmem:	       0 kB
VmData:	 5096848 kB
VmStk:	     136 kB
VmExe:	       4 kB
VmLib:	  452620 kB
VmPTE:	    9660 kB
VmSwap:	       0 kB
HugetlbPages:	       0 kB
CoreDumping:	0
THP_enabled:	1
untag_mask:	0xffffffffffffffff
Threads:	32
SigQ:	0/56399
SigPnd:	0000000000000000
ShdPnd:	0000000000000000
SigBlk:	0000000000000000
SigIgn:	0000000001001000
SigCgt:	0000000100000002
CapInh:	0000000000000000
CapPrm:	0000000000000000
CapEff:	0000000000000000
CapBnd:	00000000a80425fb
CapAmb:	0000000000000000
NoNewPrivs:	0
Seccomp:	2
Seccomp_filters:	1
Speculation_Store_Bypass:	thread vulnerable
SpeculationIndirectBranch:	conditional enabled
Cpus_allowed:	ff
Cpus_allowed_list:	0-7
Mems_allowed:	00000000,00000000,00000000,00000000,00000000,00000000,00000000,00000000,00000000,00000000,00000000,00000000,00000000,00000000,00000000,00000000,00000000,00000000,00000000,00000000,00000000,00000000,00000000,00000000,00000000,00000000,00000000,00000000,00000000,00000000,00000000,00000001
Mems_allowed_list:	0
voluntary_ctxt_switches:	671
nonvoluntary_ctxt_switches:	4727
x86_Thread_features:	
x86_Thread_features_locked:	
70759 5602 0 0 20 0 32 0 64382 7138947072 1117344

Script completed
Wall time 5.0 seconds
Output:

{"chunk_id":"09331c","wall_time_seconds":5.00135141,"session_id":51338,"original_token_count":0,"output":""}

Script completed
Wall time 0.0 seconds
Output:

101826 8520 0 0 20 0 32 0 64382 7469117440 1171966
VmPin:	       0 kB
VmHWM:	 5316952 kB
VmRSS:	 4689468 kB
RssAnon:	 4539368 kB
RssFile:	  150100 kB
RssShmem:	       0 kB
VmData:	 5419280 kB
VmStk:	     136 kB
VmExe:	       4 kB
VmLib:	  452620 kB
VmPTE:	   10220 kB
VmSwap:	       0 kB
HugetlbPages:	       0 kB
CoreDumping:	0
THP_enabled:	1
prepared stage=validation sequence_users=9,135 tokens=20,056,329 next_item_targets=20,047,194 states=339,133
chronological BCE window: train=1,052,953 validation=130,103 selected=1,183,056 discarded_old_targets=18,864,138 all=20,047,194
inbatch correction: min=0.250 mean_on_targets=1.001 max=4.000
target weighting=organic-strong min=0.250 mean=0.575 max=1.000
full-history false-negative filter: users=9,135 unique_user_items=5,524,275 bytes=34,256,250

Script failed
Wall time 0.1 seconds
Output:

Script error:
Exit code: 1
Wall time: 0 seconds
Output:
Failed to write file /app/solution/train_current_model.py

Script completed
Wall time 0.1 seconds
Output:

-rw-r--r-- 1 agent agent 80058 Aug 31 19:29 /app/solution/train_current_model.py

Script completed
Wall time 0.1 seconds
Output:

{}

Script completed
Wall time 4.1 seconds
Output:

usage: train_current_model.py [-h] [--stage {validation,submission}] --output
                              OUTPUT --public-dir PUBLIC_DIR
                              [--prepared-cache PREPARED_CACHE]
                              [--device {cpu,mps}] [--threads THREADS]
                              [--bptt-steps BPTT_STEPS]
                              [--user-batch-size USER_BATCH_SIZE]
                              [--epochs EPOCHS]
                              [--learning-rate LEARNING_RATE]
                              [--loss-microbatch-size LOSS_MICROBATCH_SIZE]
                              [--uniform-negatives UNIFORM_NEGATIVES]
                              [--inbatch-negatives INBATCH_NEGATIVES]
                              [--negative-loss {self-adversarial,corrected-mean}]
                              [--hard-negative-temperature HARD_NEGATIVE_TEMPERATURE]
                              [--hard-negative-mix HARD_NEGATIVE_MIX]
                              [--negative-filter-scope {full-training-history,last-100}]
                              [--target-weighting {discovery-graded,organic-strong,uniform}]
                              [--ordinary-target-weight ORDINARY_TARGET_WEIGHT]
                              [--organic-strong-target-weight ORGANIC_STRONG_TARGET_WEIGHT]
                              [--organic-like-target-weight ORGANIC_LIKE_TARGET_WEIGHT]
                              [--discovery-horizon-days DISCOVERY_HORIZON_DAYS]
                              [--validation-fraction VALIDATION_FRACTION]
                              [--max-train-targets-per-user MAX_TRAIN_TARGETS_PER_USER]
                              [--max-validation-targets-per-user MAX_VALIDATION_TARGETS_PER_USER]
                              [--early-stopping-patience EARLY_STOPPING_PATIENCE]
                              [--early-stopping-min-delta EARLY_STOPPING_MIN_DELTA]
                              [--checkpoint-dir CHECKPOINT_DIR]
                              [--resume-checkpoint RESUME_CHECKPOINT]
                              [--seed SEED]
                              [--ranking-batch-size RANKING_BATCH_SIZE]
                              [--prepare-only]

Train the Yambda windowed two-tower baseline. Every catalog listen with at
least 50 percent completion is a sequence token. Within each selected
chronological window, every adjacent target contributes a loss. The fast
default retains each user's most recent 128 training targets and 16 held-out
validation targets; passing zero for either cap restores the uncapped behavior
for that side of the split. A 100-step truncated-BPTT block computes all of
its timestep losses and carries the detached GRU hidden state into the next
block. The model is a pure two-tower retriever: no user-ID embedding, no
output normalization, raw dot-product retrieval, sample-weighted binary cross
entropy, and 24 uniform plus eight propensity-corrected unique in-batch
negatives. Every selected adjacent target retains a nonzero weight. Only files
under the supplied public directory are read.

options:
  -h, --help            show this help message and exit
  --stage {validation,submission}
  --output OUTPUT
  --public-dir PUBLIC_DIR
  --prepared-cache PREPARED_CACHE
  --device {cpu,mps}
  --threads THREADS
  --bptt-steps BPTT_STEPS
  --user-batch-size USER_BATCH_SIZE
  --epochs EPOCHS
  --learning-rate LEARNING_RATE
  --loss-microbatch-size LOSS_MICROBATCH_SIZE
  --uniform-negatives UNIFORM_NEGATIVES
  --inbatch-negatives INBATCH_NEGATIVES
  --negative-loss {self-adversarial,corrected-mean}
  --hard-negative-temperature HARD_NEGATIVE_TEMPERATURE
  --hard-negative-mix HARD_NEGATIVE_MIX
  --negative-filter-scope {full-training-history,last-100}
  --target-weighting {discovery-graded,organic-strong,uniform}
  --ordinary-target-weight ORDINARY_TARGET_WEIGHT
  --organic-strong-target-weight ORGANIC_STRONG_TARGET_WEIGHT
  --organic-like-target-weight ORGANIC_LIKE_TARGET_WEIGHT
  --discovery-horizon-days DISCOVERY_HORIZON_DAYS
  --validation-fraction VALIDATION_FRACTION
  --max-train-targets-per-user MAX_TRAIN_TARGETS_PER_USER
                        retain this many recent pre-validation targets per
                        user; 0 is uncapped
  --max-validation-targets-per-user MAX_VALIDATION_TARGETS_PER_USER
                        retain this many final validation targets per user; 0
                        is uncapped
  --early-stopping-patience EARLY_STOPPING_PATIENCE
  --early-stopping-min-delta EARLY_STOPPING_MIN_DELTA
  --checkpoint-dir CHECKPOINT_DIR
  --resume-checkpoint RESUME_CHECKPOINT
  --seed SEED
  --ranking-batch-size RANKING_BATCH_SIZE
  --prepare-only

Script completed
Wall time 0.0 seconds
Output:

{"chunk_id":"fc0085","wall_time_seconds":0.00000719,"exit_code":0,"original_token_count":885,"output":"epoch=1/1 batches=250 targets=987,417 batch_bce=0.547529 running_bce=0.541614 elapsed=204.3s\nepoch=1/1 train_loss=0.53984 validation_loss=0.49664 pair_accuracy=0.755 train_targets=1,052,953 validation_targets=130,103 train_seconds=217.3 validation_seconds=15.6\nrestored best validation-BCE checkpoint: epoch=1 loss=0.496636\nranked users=1,024/8,456\nranked users=2,048/8,456\nranked users=3,072/8,456\nranked users=4,096/8,456\nranked users=5,120/8,456\nranked users=6,144/8,456\nranked users=7,168/8,456\nranked users=8,192/8,456\nranked users=8,456/8,456\n{\n  \"baseline\": \"yambda-windowed-sequence-two-tower-base\",\n  \"stage\": \"validation\",\n  \"output\": \"/app/solution/production_validation.parquet\",\n  \"rows\": 845600,\n  \"users\": 8456,\n  \"runtime_seconds\": 365.417,\n  \"public_inputs_only\": true,\n  \"architecture\": {\n    \"family\": \"pure-windowed-sequence-two-tower\",\n    \"sequence_training\": \"every-adjacent-target-within-recent-chronological-window\",\n    \"sequence_encoder\": \"one-layer-GRU-dense-timestep-loss\",\n    \"bptt_hidden_state\": \"carried-and-detached\",\n    \"model_selection\": \"chronological-validation-BCE-early-stopping\",\n    \"loss_execution\": \"gradient-accumulated-microbatches\",\n    \"user_id_embedding\": false,\n    \"user_mlp\": \"582-512-256-192\",\n    \"item_mlp\": \"196-512-256-192\",\n    \"normalization\": \"none\",\n    \"score\": \"raw-dot-product\",\n    \"objective\": \"sample-weighted-BCE-at-every-timestep\",\n    \"negative_sampling\": \"24-uniform-plus-8-propensity-corrected-inbatch\",\n    \"false_negative_filter\": \"full-training-history\",\n    \"target_weighting\": \"organic-strong\"\n  },\n  \"config\": {\n    \"bptt_steps\": 100,\n    \"user_batch_size\": 64,\n    \"embedding_dim\": 192,\n    \"hidden_dim\": 192,\n    \"user_hidden_1\": 512,\n    \"user_hidden_2\": 256,\n    \"item_hidden_1\": 512,\n    \"item_hidden_2\": 256,\n    \"dropout\": 0.05,\n    \"epochs\": 1,\n    \"learning_rate\": 0.001,\n    \"weight_decay\": 1e-05,\n    \"gradient_clip\": 2.0,\n    \"loss_microbatch_size\": 65536,\n    \"uniform_negatives\": 24,\n    \"inbatch_negatives\": 8,\n    \"inbatch_correction_power\": 0.5,\n    \"inbatch_correction_min\": 0.25,\n    \"inbatch_correction_max\": 4.0,\n    \"negative_filter_scope\": \"full-training-history\",\n    \"target_weighting\": \"organic-strong\",\n    \"ordinary_target_weight\": 0.25,\n    \"organic_strong_target_weight\": 1.0,\n    \"organic_like_target_weight\": 3.0,\n    \"discovery_horizon_days\": 7,\n    \"validation_fraction\": 0.1,\n    \"max_train_targets_per_user\": 128,\n    \"max_validation_targets_per_user\": 16,\n    \"early_stopping_patience\": 1,\n    \"early_stopping_min_delta\": 0.0001,\n    \"seed\": 29\n  },\n  \"sequence_tokens\": 20056329,\n  \"all_next_item_targets\": 20047194,\n  \"selected_training_targets\": 1052953,\n  \"selected_validation_targets\": 130103,\n  \"discarded_old_targets\": 18864138,\n  \"training_history\": [\n    {\n      \"epoch\": 1.0,\n      \"loss\": 0.5398380443854521,\n      \"positive_logit\": 0.7427799617194347,\n      \"negative_logit\": -0.6222247057241568,\n      \"pair_accuracy\": 0.7547733315257186,\n      \"targets\": 1052953.0,\n      \"target_weight_sum\": 632551.0,\n      \"batches\": 266.0,\n      \"seconds\": 217.30003871099996,\n      \"validation_loss\": 0.49663621489170984,\n      \"validation_targets\": 130103.0,\n      \"validation_target_weight_sum\": 78769.25,\n      \"validation_seconds\": 15.614260562000027\n    }\n  ],\n  \"embedding_diagnostics\": {\n    \"query_norm_mean\": 1.6030172109603882,\n    \"query_norm_std\": 0.7697498202323914,\n    \"item_norm_mean\": 1.7570278644561768,\n    \"item_norm_std\": 0.8279486298561096\n  },\n  \"torch_version\": \"2.8.0+cpu\",\n  \"device\": \"cpu\"\n}\n"}

Script completed
Wall time 3.4 seconds
Output:

{
  "model": "/app/solution/production_validation.parquet",
  "scores": {
    "quality_ndcg@10": 0.02128,
    "quality_users": 4263
  }
}

Script completed
Wall time 0.0 seconds
Output:

        inference_disliked_items=inference_dislikes,
        inference_user_features=inference_user_features,
    )
    log(
        f"prepared stage={stage} sequence_users={len(prepared.user_ids):,} "
        f"tokens={len(prepared.sequence_items):,} "
        f"next_item_targets={prepared.target_count:,} "
        f"states={len(prepared.liked_states):,}"
    )
    return prepared, eligibility


def cache_metadata(stage: str, config: Config) -> dict[str, object]:
    return {
        "cache_version": CACHE_VERSION,
        "stage": stage,
        "positive_listen_threshold": base.LISTEN_POSITIVE_THRESHOLD,
        "profile_lookback_days": base.PROFILE_LOOKBACK_DAYS,
        "event_time_feature": "exp-negative-gap-over-60-days",
    }


def save_cache(
    path: Path, prepared: SequenceData, stage: str, config: Config
) -> None:
    path.parent.mkdir(parents=True, exist_ok=True)
    np.savez(
        path,
        metadata=np.asarray(json.dumps(cache_metadata(stage, config), sort_keys=True)),
        **prepared.__dict__,
    )
    log(f"saved public-derived full-sequence cache: {path}")


def load_cache(path: Path, stage: str, config: Config) -> SequenceData:
    with np.load(path, allow_pickle=False) as artifact:
        actual = json.loads(str(artifact["metadata"].item()))
        expected = cache_metadata(stage, config)
        if actual != expected:
            raise RuntimeError(f"sequence cache differs: {actual} != {expected}")
        values = {
            field: artifact[field].copy()
            for field in SequenceData.__dataclass_fields__
        }
    prepared = SequenceData(**values)
    log(
        f"loaded full-sequence cache: tokens={len(prepared.sequence_items):,} "
        f"targets={prepared.target_count:,}"
    )
    return prepared


def load_or_prepare(
    public: Path,
    stage: str,
    config: Config,
    cache: Path | None,
) -> tuple[SequenceData, CandidateSet]:
    candidate_name = (
        "validation_eligible_candidates.npz"
        if stage == "validation"
        else "test_eligible_candidates.npz"
    )
    eligibility = CandidateSet.read(public / "data" / candidate_name)
    if cache is not None and cache.is_file():
        prepared = load_cache(cache, stage, config)
        if not np.array_equal(prepared.item_ids, eligibility.item_ids):
            raise RuntimeError("cached catalog differs from candidate artifact")
        return prepared, eligibility
    prepared, built_eligibility = prepare_data(public, stage, config)
    if cache is not None:
        save_cache(cache, prepared, stage, config)
    return prepared, built_eligibility


def build_item_correction(
    prepared: SequenceData,
    config: Config,
    target_starts: np.ndarray,
    target_counts: np.ndarray,
) -> torch.Tensor:
    """Estimate in-batch propensities from the selected training targets."""
    counts = np.zeros(len(prepared.item_ids), dtype=np.float64)
    for user_row, count in enumerate(target_counts):
        if not count:
            continue

Script completed
Wall time 1.2 seconds
Output:

{"chunk_id":"758e6b","wall_time_seconds":1.001243351,"session_id":85133,"original_token_count":0,"output":""}

Script completed
Wall time 5.0 seconds
Output:

{"chunk_id":"73afa8","wall_time_seconds":5.000921621,"session_id":85133,"original_token_count":13,"output":"loaded explicit events: rows=720,270 users=8,220\n"}

Script completed
Wall time 5.0 seconds
Output:

{"chunk_id":"86d398","wall_time_seconds":5.001221564,"session_id":85133,"original_token_count":66,"output":"prepared users=1,000 tokens=2,090,746 states=35,727 elapsed=4.9s\nprepared users=2,000 tokens=4,301,266 states=71,242 elapsed=9.8s\nprepared users=3,000 tokens=6,486,146 states=109,471 elapsed=15.0s\nprepared users=4,000 tokens=8,793,043 states=148,210 elapsed=20.4s\n"}

Script completed
Wall time 5.0 seconds
Output:

{"chunk_id":"75d2e4","wall_time_seconds":5.001387922,"session_id":85133,"original_token_count":51,"output":"prepared users=5,000 tokens=10,992,205 states=182,596 elapsed=25.2s\nprepared users=6,000 tokens=13,061,727 states=217,148 elapsed=29.9s\nprepared users=7,000 tokens=15,334,418 states=256,914 elapsed=35.4s\n"}

Script completed
Wall time 5.0 seconds
Output:

{"chunk_id":"955728","wall_time_seconds":5.001504206,"session_id":85133,"original_token_count":17,"output":"prepared users=8,000 tokens=17,462,672 states=296,703 elapsed=40.7s\n"}

Script completed
Wall time 5.0 seconds
Output:

{"chunk_id":"5b433c","wall_time_seconds":5.001353694,"session_id":85133,"original_token_count":164,"output":"prepared users=9,000 tokens=19,568,405 states=331,551 elapsed=45.4s\ntarget users without qualifying catalog sequence=7\nprepared stage=validation sequence_users=9,135 tokens=20,056,329 next_item_targets=20,047,194 states=339,133\nsaved public-derived full-sequence cache: /app/solution/validation_prepared.npz\nchronological BCE window: train=1,052,953 validation=130,103 selected=1,183,056 discarded_old_targets=18,864,138 all=20,047,194\ninbatch correction: min=0.250 mean_on_targets=1.001 max=4.000\ntarget weighting=organic-strong min=0.250 mean=0.575 max=1.000\nfull-history false-negative filter: users=9,135 unique_user_items=5,524,275 bytes=34,256,250\n"}

Script completed
Wall time 0.5 seconds
Output:

{"chunk_id":"193ab1","wall_time_seconds":0.440858004,"exit_code":130,"original_token_count":0,"output":""}

Script completed
Wall time 1.2 seconds
Output:

{"chunk_id":"152b77","wall_time_seconds":1.000281233,"session_id":27745,"original_token_count":0,"output":""}

Script completed
Wall time 0.1 seconds
Output:

        if epochs_without_improvement >= config.early_stopping_patience:
            log(
                f"early stopping after epoch={epoch}; "
                f"best_epoch={best_epoch} best_validation_loss={best_loss:.6f}"
            )
            break

    if best_state is None:
        raise RuntimeError("training did not produce a valid checkpoint")
    model.load_state_dict(best_state)
    model.to(device).eval()
    log(
        f"restored best validation-BCE checkpoint: epoch={best_epoch} "
        f"loss={best_loss:.6f}"
    )
    return model, history


@torch.inference_mode()
def inference_queries(
    model: base.SequentialTwoTower,
    prepared: SequenceData,
    config: Config,
    device: torch.device,
) -> torch.Tensor:
    sequence_rows = prepared.inference_user_rows
    lengths = np.where(
        sequence_rows >= 0, prepared.lengths[np.maximum(sequence_rows, 0)], 0
    )
    ordered = np.argsort(lengths, kind="stable")
    result = torch.zeros(
        len(sequence_rows), config.embedding_dim, dtype=torch.float32
    )
    for group_start in range(0, len(ordered), config.user_batch_size):
        output_rows = ordered[group_start : group_start + config.user_batch_size]
        rows = sequence_rows[output_rows]
        group_lengths = lengths[output_rows]
        hidden = torch.zeros(
            1, len(output_rows), config.embedding_dim, device=device
        )
        for start in range(0, int(group_lengths.max(initial=0)), config.bptt_steps):
            steps = min(
                config.bptt_steps,
                int(group_lengths.max(initial=0)) - start,
            )
            items = np.full(
                (len(output_rows), steps),
                len(prepared.item_ids),
                dtype=np.uint16,
            )
            features = np.zeros((len(output_rows), steps, 3), dtype=np.float16)
            counts = np.zeros(len(output_rows), dtype=np.int32)
            for local_row, sequence_row in enumerate(rows):
                if sequence_row < 0:
                    continue
                count = min(steps, max(int(group_lengths[local_row]) - start, 0))
                if not count:
                    continue
                offset = int(prepared.offsets[sequence_row])
                selected = slice(offset + start, offset + start + count)
                items[local_row, :count] = prepared.sequence_items[selected]
                features[local_row, :count] = prepared.event_features[selected]
                counts[local_row] = count
            outputs, _ = event_sequence(
                model,
                torch.from_numpy(items.astype(np.int64)).to(device),
                torch.from_numpy(features.astype(np.float32)).to(device),
                hidden,
            )
            next_rows: list[torch.Tensor] = []
            for local_row, count in enumerate(counts):
                next_rows.append(
                    outputs[local_row, count - 1]
                    if count
                    else hidden[0, local_row]
                )
            hidden = torch.stack(next_rows).unsqueeze(0)

        liked_items = torch.from_numpy(
            prepared.inference_liked_items[output_rows].astype(np.int64)
        ).to(device)
        disliked_items = torch.from_numpy(
            prepared.inference_disliked_items[output_rows].astype(np.int64)
        ).to(device)
        queries = user_queries(
            model,
            hidden.squeeze(0),
            model._mean_context_channel(liked_items),
            model._mean_context_channel(disliked_items),
            torch.from_numpy(
                prepared.inference_user_features[output_rows].astype(np.float32)
            ).to(device),
        )
        result[torch.from_numpy(output_rows.astype(np.int64))] = queries.cpu()
    return result


@torch.inference_mode()
def rank_candidates(
    model: base.SequentialTwoTower,
    prepared: SequenceData,
    eligibility: CandidateSet,
    config: Config,
    device: torch.device,
    ranking_batch_size: int,
) -> tuple[pd.DataFrame, dict[str, float]]:
    model.eval()
    queries = inference_queries(model, prepared, config, device)
    item_parts: list[torch.Tensor] = []
    for start in range(0, len(prepared.item_ids), 2_048):
        rows = torch.arange(
            start,
            min(start + 2_048, len(prepared.item_ids)),
            dtype=torch.long,
            device=device,
        )
        item_parts.append(model.encode_items(rows).cpu())
    items = torch.cat(item_parts)
    rows: list[tuple[int, int, int]] = []
    for start in range(0, len(eligibility.uids), ranking_batch_size):
        end = min(start + ranking_batch_size, len(eligibility.uids))
        scores = queries[start:end] @ items.T
        eligible = np.unpackbits(
            eligibility.packed[start:end],
            axis=1,
            count=len(prepared.item_ids),
            timestamps,
            history_end - base.PROFILE_LOOKBACK_DAYS * base.DAY,
            side="left",
        )
    )
    result = np.zeros(6, dtype=np.float32)
    recent_items = items[start:]
    if len(recent_items):
        result[0] = np.log1p(len(recent_items)) / 8.0
        result[1] = np.log1p(len(np.unique(recent_items))) / 6.0
        result[2] = float(np.mean(event_features[start:, 0]))
        result[3] = float(np.mean(event_features[start:, 1]))
    result[4] = np.log1p(like_count) / 6.0
    result[5] = np.log1p(dislike_count) / 4.0
    return result


def prepare_data(
    public: Path, stage: str, config: Config
) -> tuple[SequenceData, CandidateSet]:
    data = public / "data"
    catalog = pd.read_parquet(data / "candidate_catalog.parquet").sort_values(
        "popularity_rank"
    )
    item_ids = catalog.item_id.to_numpy(dtype=np.int64, copy=True)
    item_index = pd.Index(item_ids)
    n_items = len(item_ids)
    if n_items >= np.iinfo(np.uint16).max:
        raise RuntimeError("uint16 item storage is too small for this catalog")

    if stage == "validation":
        prefixes = ("train",)
        history_end = base.TRAIN_END
        candidate_name = "validation_eligible_candidates.npz"
        state_name = "validation_preference_state.parquet"
    else:
        prefixes = ("train", "val")
        history_end = base.VALIDATION_END
        candidate_name = "test_eligible_candidates.npz"
        state_name = "test_preference_state.parquet"
    eligibility = CandidateSet.read(data / candidate_name)
    if not np.array_equal(eligibility.item_ids, item_ids):
        raise RuntimeError("catalog and candidate artifact item order differ")

    explicit_by_user = base.load_explicit_events(data, prefixes, item_index)
    inference_likes, inference_dislikes, like_counts, dislike_counts = (
        base.load_inference_state(
            data / state_name,
            item_index,
            eligibility.uids,
            n_items,
        )
    )
    inference_rows = {int(uid): row for row, uid in enumerate(eligibility.uids)}
    inference_user_features = np.zeros((len(eligibility.uids), 6), dtype=np.float32)
    inference_sequence_rows = np.full(len(eligibility.uids), -1, dtype=np.int32)

    # Snapshot zero is the shared empty explicit state.
    liked_states = [np.full(base.LIKE_ITEMS, n_items, dtype=np.uint16)]
    disliked_states = [
        np.full(base.DISLIKE_ITEMS, n_items, dtype=np.uint16)
    ]
    state_counts: list[tuple[int, int]] = [(0, 0)]
    user_ids: list[int] = []
    offsets = [0]
    timestamp_parts: list[np.ndarray] = []
    item_parts: list[np.ndarray] = []
    event_parts: list[np.ndarray] = []
    activity_parts: list[np.ndarray] = []
    state_parts: list[np.ndarray] = []

    listen_paths = [data / f"{prefix}_listens.parquet" for prefix in prefixes]
    started = time.monotonic()
    for seen_users, (uid, listens) in enumerate(
        base.merge_listen_streams(listen_paths, item_index), start=1
    ):
        parts = build_sequence_parts(
            listens,
            explicit_by_user.get(uid, base.empty_explicit_events()),
            n_items,
            liked_states,
            disliked_states,
            state_counts,
        )
        if parts is None:
            continue
        sequence_row = len(user_ids)
        user_ids.append(uid)
        timestamp_parts.append(parts[0].astype(np.uint32, copy=False))
        item_parts.append(parts[1])
        event_parts.append(parts[2])
        activity_parts.append(parts[3])
        state_parts.append(parts[4])
        offsets.append(offsets[-1] + len(parts[1]))
        inference_row = inference_rows.get(uid)
        if inference_row is not None:
            inference_sequence_rows[inference_row] = sequence_row
            inference_user_features[inference_row] = final_user_features(
                parts[0],
                parts[1],
                parts[2],
                history_end,
                int(like_counts[inference_row]),
                int(dislike_counts[inference_row]),
            )
        if seen_users % 1_000 == 0:
            log(
                f"prepared users={seen_users:,} tokens={offsets[-1]:,} "
                f"states={len(liked_states):,} "
                f"elapsed={time.monotonic() - started:.1f}s"
            )

    missing = np.flatnonzero(inference_sequence_rows < 0)
    if len(missing):
        inference_user_features[missing, 4] = np.log1p(like_counts[missing]) / 6.0
        inference_user_features[missing, 5] = (
            np.log1p(dislike_counts[missing]) / 4.0
        )
        log(f"target users without qualifying catalog sequence={len(missing):,}")

    prepared = SequenceData(
        item_ids=item_ids,
        item_features=base.build_item_features(catalog),
        user_ids=np.asarray(user_ids, dtype=np.int64),
        offsets=np.asarray(offsets, dtype=np.int64),
        sequence_timestamps=np.concatenate(timestamp_parts),
        sequence_items=np.concatenate(item_parts),
        event_features=np.concatenate(event_parts),
        activity_features=np.concatenate(activity_parts),
        state_ids=np.concatenate(state_parts),
        liked_states=np.stack(liked_states),
        disliked_states=np.stack(disliked_states),
        state_counts=np.asarray(state_counts, dtype=np.int32),
        inference_user_rows=inference_sequence_rows,
        inference_liked_items=inference_likes,
        inference_disliked_items=inference_dislikes,

Script completed
Wall time 0.1 seconds
Output:

                prepared.inference_user_features[output_rows].astype(np.float32)
            ).to(device),
        )
        result[torch.from_numpy(output_rows.astype(np.int64))] = queries.cpu()
    return result


@torch.inference_mode()
def rank_candidates(
    model: base.SequentialTwoTower,
    prepared: SequenceData,
    eligibility: CandidateSet,
    config: Config,
    device: torch.device,
    ranking_batch_size: int,
) -> tuple[pd.DataFrame, dict[str, float]]:
    model.eval()
    queries = inference_queries(model, prepared, config, device)
    item_parts: list[torch.Tensor] = []
    for start in range(0, len(prepared.item_ids), 2_048):
        rows = torch.arange(
            start,
            min(start + 2_048, len(prepared.item_ids)),
            dtype=torch.long,
            device=device,
        )
        item_parts.append(model.encode_items(rows).cpu())
    items = torch.cat(item_parts)
    rows: list[tuple[int, int, int]] = []
    for start in range(0, len(eligibility.uids), ranking_batch_size):
        end = min(start + ranking_batch_size, len(eligibility.uids))
        scores = queries[start:end] @ items.T
        eligible = np.unpackbits(
            eligibility.packed[start:end],
            axis=1,
            count=len(prepared.item_ids),
            bitorder="little",
        ).astype(bool, copy=False)
        scores.masked_fill_(~torch.from_numpy(eligible), -torch.inf)
        selected = torch.topk(scores, k=base.TOP_N, dim=1).indices.numpy()
        for local_row, columns in enumerate(selected):
            uid = int(eligibility.uids[start + local_row])
            rows.extend(
                (uid, int(prepared.item_ids[column]), rank)
                for rank, column in enumerate(columns, start=1)
            )
        if end == len(eligibility.uids) or end % 1_024 == 0:
            log(f"ranked users={end:,}/{len(eligibility.uids):,}")
    query_norm = torch.linalg.vector_norm(queries, dim=1).numpy()
    item_norm = torch.linalg.vector_norm(items, dim=1).numpy()
    diagnostics = {
        "query_norm_mean": float(query_norm.mean()),
        "query_norm_std": float(query_norm.std()),
        "item_norm_mean": float(item_norm.mean()),
        "item_norm_std": float(item_norm.std()),
    }

Script completed
Wall time 5.0 seconds
Output:

{"chunk_id":"1d254d","wall_time_seconds":5.001077425,"session_id":27745,"original_token_count":103,"output":"loaded full-sequence cache: tokens=20,056,329 targets=20,047,194\nchronological BCE window: train=1,052,953 validation=130,103 selected=1,183,056 discarded_old_targets=18,864,138 all=20,047,194\ninbatch correction: min=0.250 mean_on_targets=1.001 max=4.000\ntarget weighting=organic-strong min=0.250 mean=0.575 max=1.000\nfull-history false-negative filter: users=9,135 unique_user_items=5,524,275 bytes=34,256,250\n"}

Script completed
Wall time 2.2 seconds
Output:

production_validation.parquet {'count': 84560.0, 'mean': 2597.0539025543994, 'std': 5715.185504100687, 'min': 1.0, '10%': 5.0, '25%': 14.0, '50%': 111.0, '75%': 2124.0, '90%': 7317.0, 'max': 29868.0}
popularity_validation.parquet {'count': 84560.0, 'mean': 17.020068590350046, 'std': 19.375080290167947, 'min': 1.0, '10%': 3.0, '25%': 6.0, '50%': 11.0, '75%': 20.0, '90%': 40.0, 'max': 250.0}

Script completed
Wall time 10.2 seconds
Output:

Script completed
Wall time 0.1 seconds
Output:

/proc/60/cmdline bash -c set -o pipefail; if [ -s ~/.nvm/nvm.sh ]; then . ~/.nvm/nvm.sh; fi; codex exec --dangerously-bypass-approvals-and-sandbox --skip-git-repo-check --model gpt-5.6-sol --json --enable unified_exec -c model_reasoning_effort=high -- '# Improve a production music-discovery two-tower

You have joined the recommendations team for a music streaming service. The
"Made for You" shelf is served by a mature production two-tower model. Its
chronological data protocol and indexed serving path are sound, but its offline
retrieval quality no longer clears the team'"'"'s next launch gate.

Your job is to investigate the production model, improve its retrieval quality,
and ship a better ranking artifact. Use the implementation and public validation
data to form and test your own diagnosis.

The source used to reproduce the production model is included under
`/task/current_model/`. You may copy it into `/app/solution/`, edit it, add
tests, and improve its training objective, but keep the data protocol,
two-tower serving contract, and evaluation boundary intact.

## Production Context

The model must satisfy a strict request-time latency budget. Item vectors are
precomputed offline. At request time, one user vector is computed from observed

Script completed
Wall time 5.0 seconds
Output:

{"chunk_id":"51a47a","wall_time_seconds":5.001118341,"session_id":27745,"original_token_count":0,"output":""}

Script completed
Wall time 5.0 seconds
Output:

{"chunk_id":"f0eebc","wall_time_seconds":5.001183263,"session_id":27745,"original_token_count":0,"output":""}

Script completed
Wall time 0.1 seconds
Output:

/proc/639
0 0 0 0 20 0 1 0 111916 2654208 406
NSsid:	639
Kthread:	0
VmPeak:	    2592 kB
VmSize:	    2592 kB
VmLck:	       0 kB
VmPin:	       0 kB
VmHWM:	    1812 kB
VmRSS:	    1812 kB
RssAnon:	     124 kB
RssFile:	    1688 kB
/proc/643
60561 4353 0 0 20 0 23 0 111916 6793273344 1245109
NSsid:	639
Kthread:	0
VmPeak:	 6634056 kB
VmSize:	 6634056 kB
VmLck:	       0 kB
VmPin:	       0 kB
VmHWM:	 5040532 kB
VmRSS:	 5000364 kB
RssAnon:	 4861028 kB
RssFile:	  139336 kB
/proc/773
0 0 0 1 20 0 1 0 124287 2654208 385
NSsid:	773
Kthread:	0
VmPeak:	    2592 kB
VmSize:	    2592 kB
VmLck:	       0 kB
VmPin:	       0 kB
VmHWM:	    1688 kB
VmRSS:	    1688 kB
RssAnon:	     148 kB
RssFile:	    1540 kB

Script running with cell ID 48
Wall time 11.0 seconds
Output:

Script completed
Wall time 15.0 seconds
Output:

{"chunk_id":"cbc637","wall_time_seconds":30.003584068,"session_id":27745,"original_token_count":0,"output":""}

Script running with cell ID 49
Wall time 11.0 seconds
Output:

Script completed
Wall time 16.5 seconds
Output:

{"chunk_id":"e59ee2","wall_time_seconds":30.001929814,"session_id":27745,"original_token_count":24,"output":"epoch=1/1 batches=250 targets=987,417 batch_bce=0.633467 running_bce=0.626976 elapsed=179.0s\n"}

Script running with cell ID 50
Wall time 11.0 seconds
Output:

Script completed
Wall time 15.5 seconds
Output:

{"chunk_id":"2ff9b4","wall_time_seconds":30.001898908,"session_id":27745,"original_token_count":76,"output":"saved epoch checkpoint: /app/solution/improved_checkpoints/epoch-01.pt\nepoch=1/1 train_loss=0.62610 validation_loss=0.61428 pair_accuracy=0.685 train_targets=1,052,953 validation_targets=130,103 train_seconds=190.5 validation_seconds=12.5\nrestored best validation-BCE checkpoint: epoch=1 loss=0.614283\n"}

Script running with cell ID 51
Wall time 11.0 seconds
Output:

Script completed
Wall time 16.6 seconds
Output:

{"chunk_id":"d910a2","wall_time_seconds":30.001459358,"session_id":27745,"original_token_count":0,"output":""}

Script running with cell ID 52
Wall time 11.0 seconds
Output:

Script completed
Wall time 15.0 seconds
Output:

{"chunk_id":"49ea8b","wall_time_seconds":28.26923203,"exit_code":0,"original_token_count":839,"output":"ranked users=1,024/8,456\nranked users=2,048/8,456\nranked users=3,072/8,456\nranked users=4,096/8,456\nranked users=5,120/8,456\nranked users=6,144/8,456\nranked users=7,168/8,456\nranked users=8,192/8,456\nranked users=8,456/8,456\n{\n  \"baseline\": \"yambda-windowed-sequence-two-tower-base\",\n  \"stage\": \"validation\",\n  \"output\": \"/app/solution/improved_validation.parquet\",\n  \"rows\": 845600,\n  \"users\": 8456,\n  \"runtime_seconds\": 288.348,\n  \"public_inputs_only\": true,\n  \"architecture\": {\n    \"family\": \"pure-windowed-sequence-two-tower\",\n    \"sequence_training\": \"every-adjacent-target-within-recent-chronological-window\",\n    \"sequence_encoder\": \"one-layer-GRU-dense-timestep-loss\",\n    \"bptt_hidden_state\": \"carried-and-detached\",\n    \"model_selection\": \"chronological-validation-BCE-early-stopping\",\n    \"loss_execution\": \"gradient-accumulated-microbatches\",\n    \"user_id_embedding\": false,\n    \"user_mlp\": \"582-512-256-192\",\n    \"item_mlp\": \"196-512-256-192\",\n    \"normalization\": \"none\",\n    \"score\": \"raw-dot-product\",\n    \"objective\": \"sample-weighted-BCE-at-every-timestep\",\n    \"negative_sampling\": \"8-uniform-plus-24-propensity-corrected-inbatch\",\n    \"negative_loss\": \"self-adversarial\",\n    \"false_negative_filter\": \"full-training-history\",\n    \"target_weighting\": \"organic-strong\"\n  },\n  \"config\": {\n    \"bptt_steps\": 100,\n    \"user_batch_size\": 64,\n    \"embedding_dim\": 192,\n    \"hidden_dim\": 192,\n    \"user_hidden_1\": 512,\n    \"user_hidden_2\": 256,\n    \"item_hidden_1\": 512,\n    \"item_hidden_2\": 256,\n    \"dropout\": 0.05,\n    \"epochs\": 1,\n    \"learning_rate\": 0.001,\n    \"weight_decay\": 1e-05,\n    \"gradient_clip\": 2.0,\n    \"loss_microbatch_size\": 65536,\n    \"uniform_negatives\": 8,\n    \"inbatch_negatives\": 24,\n    \"inbatch_correction_power\": 0.5,\n    \"inbatch_correction_min\": 0.25,\n    \"inbatch_correction_max\": 4.0,\n    \"negative_loss\": \"self-adversarial\",\n    \"hard_negative_temperature\": 1.0,\n    \"hard_negative_mix\": 0.5,\n    \"negative_filter_scope\": \"full-training-history\",\n    \"target_weighting\": \"organic-strong\",\n    \"ordinary_target_weight\": 0.25,\n    \"organic_strong_target_weight\": 1.0,\n    \"organic_like_target_weight\": 3.0,\n    \"discovery_horizon_days\": 7,\n    \"validation_fraction\": 0.1,\n    \"max_train_targets_per_user\": 128,\n    \"max_validation_targets_per_user\": 16,\n    \"early_stopping_patience\": 1,\n    \"early_stopping_min_delta\": 0.0001,\n    \"seed\": 29\n  },\n  \"sequence_tokens\": 20056329,\n  \"all_next_item_targets\": 20047194,\n  \"selected_training_targets\": 1052953,\n  \"selected_validation_targets\": 130103,\n  \"discarded_old_targets\": 18864138,\n  \"training_history\": [\n    {\n      \"epoch\": 1.0,\n      \"loss\": 0.6260950342916247,\n      \"positive_logit\": 0.24608733355265647,\n      \"negative_logit\": -0.3620728148957655,\n      \"pair_accuracy\": 0.6851729137008015,\n      \"targets\": 1052953.0,\n      \"target_weight_sum\": 632551.0,\n      \"batches\": 266.0,\n      \"seconds\": 190.50535212,\n      \"validation_loss\": 0.6142827711081374,\n      \"validation_targets\": 130103.0,\n      \"validation_target_weight_sum\": 78769.25,\n      \"validation_seconds\": 12.49514246700005\n    }\n  ],\n  \"embedding_diagnostics\": {\n    \"query_norm_mean\": 1.3063349723815918,\n    \"query_norm_std\": 0.5731095671653748,\n    \"item_norm_mean\": 1.8118765354156494,\n    \"item_norm_std\": 0.8034171462059021\n  },\n  \"torch_version\": \"2.8.0+cpu\",\n  \"device\": \"cpu\"\n}\n"}

Script completed
Wall time 3.3 seconds
Output:

{
  "model": "/app/solution/improved_validation.parquet",
  "scores": {
    "quality_ndcg@10": 0.017985,
    "quality_users": 4263
  }
}

Script completed
Wall time 1.2 seconds
Output:

{"chunk_id":"a6662c","wall_time_seconds":1.001196558,"session_id":12574,"original_token_count":0,"output":""}

Script completed
Wall time 0.0 seconds
Output:

{}

Script completed
Wall time 0.3 seconds
Output:

Script running with cell ID 57
Wall time 11.0 seconds
Output:

Script completed
Wall time 16.5 seconds
Output:

{"chunk_id":"d226e9","wall_time_seconds":30.001921052,"session_id":12574,"original_token_count":103,"output":"loaded full-sequence cache: tokens=20,056,329 targets=20,047,194\nchronological BCE window: train=1,052,953 validation=130,103 selected=1,183,056 discarded_old_targets=18,864,138 all=20,047,194\ninbatch correction: min=0.250 mean_on_targets=1.001 max=4.000\ntarget weighting=organic-strong min=0.250 mean=0.575 max=1.000\nfull-history false-negative filter: users=9,135 unique_user_items=5,524,275 bytes=34,256,250\n"}

Script running with cell ID 58
Wall time 11.0 seconds
Output:

Script completed
Wall time 15.7 seconds
Output:

{"chunk_id":"de55d8","wall_time_seconds":30.001755538,"session_id":12574,"original_token_count":0,"output":""}

Script running with cell ID 59
Wall time 11.0 seconds
Output:

Script completed
Wall time 15.5 seconds
Output:

{"chunk_id":"7501eb","wall_time_seconds":30.001617484,"session_id":12574,"original_token_count":0,"output":""}

Script running with cell ID 60
Wall time 11.0 seconds
Output:

Script completed
Wall time 16.4 seconds
Output:

{"chunk_id":"35be19","wall_time_seconds":30.000768751,"session_id":12574,"original_token_count":24,"output":"epoch=1/1 batches=250 targets=987,417 batch_bce=0.552496 running_bce=0.565818 elapsed=169.3s\n"}

Script running with cell ID 61
Wall time 11.0 seconds
Output:

Script completed
Wall time 16.1 seconds
Output:

{"chunk_id":"ec3157","wall_time_seconds":30.001360116,"session_id":12574,"original_token_count":77,"output":"saved epoch checkpoint: /app/solution/more_inbatch_checkpoints/epoch-01.pt\nepoch=1/1 train_loss=0.56380 validation_loss=0.52553 pair_accuracy=0.685 train_targets=1,052,953 validation_targets=130,103 train_seconds=180.8 validation_seconds=12.4\nrestored best validation-BCE checkpoint: epoch=1 loss=0.525533\n"}

Script running with cell ID 62
Wall time 11.0 seconds
Output:

Script completed
Wall time 16.3 seconds
Output:

{"chunk_id":"9395ca","wall_time_seconds":30.001985135,"session_id":12574,"original_token_count":0,"output":""}

Script running with cell ID 63
Wall time 11.0 seconds
Output:

Script completed
Wall time 0.0 seconds
Output:

{"chunk_id":"557e59","wall_time_seconds":13.38600947,"exit_code":0,"original_token_count":840,"output":"ranked users=1,024/8,456\nranked users=2,048/8,456\nranked users=3,072/8,456\nranked users=4,096/8,456\nranked users=5,120/8,456\nranked users=6,144/8,456\nranked users=7,168/8,456\nranked users=8,192/8,456\nranked users=8,456/8,456\n{\n  \"baseline\": \"yambda-windowed-sequence-two-tower-base\",\n  \"stage\": \"validation\",\n  \"output\": \"/app/solution/more_inbatch_validation.parquet\",\n  \"rows\": 845600,\n  \"users\": 8456,\n  \"runtime_seconds\": 276.749,\n  \"public_inputs_only\": true,\n  \"architecture\": {\n    \"family\": \"pure-windowed-sequence-two-tower\",\n    \"sequence_training\": \"every-adjacent-target-within-recent-chronological-window\",\n    \"sequence_encoder\": \"one-layer-GRU-dense-timestep-loss\",\n    \"bptt_hidden_state\": \"carried-and-detached\",\n    \"model_selection\": \"chronological-validation-BCE-early-stopping\",\n    \"loss_execution\": \"gradient-accumulated-microbatches\",\n    \"user_id_embedding\": false,\n    \"user_mlp\": \"582-512-256-192\",\n    \"item_mlp\": \"196-512-256-192\",\n    \"normalization\": \"none\",\n    \"score\": \"raw-dot-product\",\n    \"objective\": \"sample-weighted-BCE-at-every-timestep\",\n    \"negative_sampling\": \"8-uniform-plus-24-propensity-corrected-inbatch\",\n    \"negative_loss\": \"corrected-mean\",\n    \"false_negative_filter\": \"full-training-history\",\n    \"target_weighting\": \"organic-strong\"\n  },\n  \"config\": {\n    \"bptt_steps\": 100,\n    \"user_batch_size\": 64,\n    \"embedding_dim\": 192,\n    \"hidden_dim\": 192,\n    \"user_hidden_1\": 512,\n    \"user_hidden_2\": 256,\n    \"item_hidden_1\": 512,\n    \"item_hidden_2\": 256,\n    \"dropout\": 0.05,\n    \"epochs\": 1,\n    \"learning_rate\": 0.001,\n    \"weight_decay\": 1e-05,\n    \"gradient_clip\": 2.0,\n    \"loss_microbatch_size\": 65536,\n    \"uniform_negatives\": 8,\n    \"inbatch_negatives\": 24,\n    \"inbatch_correction_power\": 0.5,\n    \"inbatch_correction_min\": 0.25,\n    \"inbatch_correction_max\": 4.0,\n    \"negative_loss\": \"corrected-mean\",\n    \"hard_negative_temperature\": 1.0,\n    \"hard_negative_mix\": 0.5,\n    \"negative_filter_scope\": \"full-training-history\",\n    \"target_weighting\": \"organic-strong\",\n    \"ordinary_target_weight\": 0.25,\n    \"organic_strong_target_weight\": 1.0,\n    \"organic_like_target_weight\": 3.0,\n    \"discovery_horizon_days\": 7,\n    \"validation_fraction\": 0.1,\n    \"max_train_targets_per_user\": 128,\n    \"max_validation_targets_per_user\": 16,\n    \"early_stopping_patience\": 1,\n    \"early_stopping_min_delta\": 0.0001,\n    \"seed\": 29\n  },\n  \"sequence_tokens\": 20056329,\n  \"all_next_item_targets\": 20047194,\n  \"selected_training_targets\": 1052953,\n  \"selected_validation_targets\": 130103,\n  \"discarded_old_targets\": 18864138,\n  \"training_history\": [\n    {\n      \"epoch\": 1.0,\n      \"loss\": 0.5637978504676405,\n      \"positive_logit\": 0.5812679772549766,\n      \"negative_logit\": -0.3587096033388017,\n      \"pair_accuracy\": 0.6852083794338398,\n      \"targets\": 1052953.0,\n      \"target_weight_sum\": 632551.0,\n      \"batches\": 266.0,\n      \"seconds\": 180.81290498900012,\n      \"validation_loss\": 0.5255333822060628,\n      \"validation_targets\": 130103.0,\n      \"validation_target_weight_sum\": 78769.25,\n      \"validation_seconds\": 12.403299938000146\n    }\n  ],\n  \"embedding_diagnostics\": {\n    \"query_norm_mean\": 1.545462727546692,\n    \"query_norm_std\": 0.7970317006111145,\n    \"item_norm_mean\": 1.8892877101898193,\n    \"item_norm_std\": 0.8114685416221619\n  },\n  \"torch_version\": \"2.8.0+cpu\",\n  \"device\": \"cpu\"\n}\n"}

Script completed
Wall time 3.3 seconds
Output:

{
  "model": "/app/solution/more_inbatch_validation.parquet",
  "scores": {
    "quality_ndcg@10": 0.019215,
    "quality_users": 4263
  }
}

Script completed
Wall time 1.2 seconds
Output:

{"chunk_id":"40deff","wall_time_seconds":1.001260338,"session_id":62251,"original_token_count":0,"output":""}

Script running with cell ID 66
Wall time 11.0 seconds
Output:

Script completed
Wall time 16.5 seconds
Output:

{"chunk_id":"52cd74","wall_time_seconds":30.000787493,"session_id":62251,"original_token_count":103,"output":"loaded full-sequence cache: tokens=20,056,329 targets=20,047,194\nchronological BCE window: train=1,052,953 validation=130,103 selected=1,183,056 discarded_old_targets=18,864,138 all=20,047,194\ninbatch correction: min=0.250 mean_on_targets=1.001 max=4.000\ntarget weighting=organic-strong min=0.250 mean=0.575 max=1.000\nfull-history false-negative filter: users=9,135 unique_user_items=5,524,275 bytes=34,256,250\n"}

Script running with cell ID 67
Wall time 11.0 seconds
Output:

Script completed
Wall time 16.4 seconds
Output:

{"chunk_id":"c700ca","wall_time_seconds":30.001231624,"session_id":62251,"original_token_count":0,"output":""}

Script running with cell ID 68
Wall time 11.0 seconds
Output:

Script completed
Wall time 16.5 seconds
Output:

{"chunk_id":"97e664","wall_time_seconds":30.002040128,"session_id":62251,"original_token_count":0,"output":""}

Script running with cell ID 69
Wall time 11.0 seconds
Output:

Script completed
Wall time 15.9 seconds
Output:

{"chunk_id":"be24ac","wall_time_seconds":30.001798639,"session_id":62251,"original_token_count":0,"output":""}

Script running with cell ID 70
Wall time 11.0 seconds
Output:

Script completed
Wall time 16.2 seconds
Output:

{"chunk_id":"fd0c70","wall_time_seconds":30.002025346,"session_id":62251,"original_token_count":0,"output":""}

Script running with cell ID 71
Wall time 11.0 seconds
Output:

Script completed
Wall time 16.4 seconds
Output:

{"chunk_id":"df6961","wall_time_seconds":30.001809896,"session_id":62251,"original_token_count":24,"output":"epoch=1/1 batches=250 targets=987,417 batch_bce=0.438960 running_bce=0.436776 elapsed=196.8s\n"}

Script running with cell ID 72
Wall time 11.0 seconds
Output:

Script completed
Wall time 16.0 seconds
Output:

{"chunk_id":"fe168f","wall_time_seconds":30.000688148,"session_id":62251,"original_token_count":76,"output":"saved epoch checkpoint: /app/solution/pairwise_checkpoints/epoch-01.pt\nepoch=1/1 train_loss=0.43457 validation_loss=0.37468 pair_accuracy=0.759 train_targets=1,052,953 validation_targets=130,103 train_seconds=210.3 validation_seconds=15.8\nrestored best validation-BCE checkpoint: epoch=1 loss=0.374678\n"}

Script running with cell ID 73
Wall time 11.0 seconds
Output:

Script completed
Wall time 16.2 seconds
Output:

{"chunk_id":"7e645f","wall_time_seconds":30.001939508,"session_id":62251,"original_token_count":0,"output":""}

Script running with cell ID 74
Wall time 11.0 seconds
Output:

Script completed
Wall time 2.0 seconds
Output:

{"chunk_id":"bab8cb","wall_time_seconds":15.690089116,"exit_code":0,"original_token_count":850,"output":"ranked users=1,024/8,456\nranked users=2,048/8,456\nranked users=3,072/8,456\nranked users=4,096/8,456\nranked users=5,120/8,456\nranked users=6,144/8,456\nranked users=7,168/8,456\nranked users=8,192/8,456\nranked users=8,456/8,456\n{\n  \"baseline\": \"yambda-windowed-sequence-two-tower-base\",\n  \"stage\": \"validation\",\n  \"output\": \"/app/solution/pairwise_validation.parquet\",\n  \"rows\": 845600,\n  \"users\": 8456,\n  \"runtime_seconds\": 310.48,\n  \"public_inputs_only\": true,\n  \"architecture\": {\n    \"family\": \"pure-windowed-sequence-two-tower\",\n    \"sequence_training\": \"every-adjacent-target-within-recent-chronological-window\",\n    \"sequence_encoder\": \"one-layer-GRU-dense-timestep-loss\",\n    \"bptt_hidden_state\": \"carried-and-detached\",\n    \"model_selection\": \"chronological-validation-BCE-early-stopping\",\n    \"loss_execution\": \"gradient-accumulated-microbatches\",\n    \"user_id_embedding\": false,\n    \"user_mlp\": \"582-512-256-192\",\n    \"item_mlp\": \"196-512-256-192\",\n    \"normalization\": \"none\",\n    \"score\": \"raw-dot-product\",\n    \"objective\": \"sample-weighted-pairwise-at-every-timestep\",\n    \"negative_sampling\": \"24-uniform-plus-8-propensity-corrected-inbatch\",\n    \"negative_loss\": \"corrected-mean\",\n    \"false_negative_filter\": \"full-training-history\",\n    \"target_weighting\": \"organic-strong\"\n  },\n  \"config\": {\n    \"bptt_steps\": 100,\n    \"user_batch_size\": 64,\n    \"embedding_dim\": 192,\n    \"hidden_dim\": 192,\n    \"user_hidden_1\": 512,\n    \"user_hidden_2\": 256,\n    \"item_hidden_1\": 512,\n    \"item_hidden_2\": 256,\n    \"dropout\": 0.05,\n    \"epochs\": 1,\n    \"learning_rate\": 0.001,\n    \"weight_decay\": 1e-05,\n    \"gradient_clip\": 2.0,\n    \"loss_microbatch_size\": 65536,\n    \"uniform_negatives\": 24,\n    \"inbatch_negatives\": 8,\n    \"inbatch_correction_power\": 0.5,\n    \"inbatch_correction_min\": 0.25,\n    \"inbatch_correction_max\": 4.0,\n    \"negative_loss\": \"corrected-mean\",\n    \"hard_negative_temperature\": 1.0,\n    \"hard_negative_mix\": 0.5,\n    \"training_objective\": \"pairwise\",\n    \"negative_filter_scope\": \"full-training-history\",\n    \"target_weighting\": \"organic-strong\",\n    \"ordinary_target_weight\": 0.25,\n    \"organic_strong_target_weight\": 1.0,\n    \"organic_like_target_weight\": 3.0,\n    \"discovery_horizon_days\": 7,\n    \"validation_fraction\": 0.1,\n    \"max_train_targets_per_user\": 128,\n    \"max_validation_targets_per_user\": 16,\n    \"early_stopping_patience\": 1,\n    \"early_stopping_min_delta\": 0.0001,\n    \"seed\": 29\n  },\n  \"sequence_tokens\": 20056329,\n  \"all_next_item_targets\": 20047194,\n  \"selected_training_targets\": 1052953,\n  \"selected_validation_targets\": 130103,\n  \"discarded_old_targets\": 18864138,\n  \"training_history\": [\n    {\n      \"epoch\": 1.0,\n      \"loss\": 0.4345719331787778,\n      \"positive_logit\": 0.9072138249181301,\n      \"negative_logit\": -0.4947895908564299,\n      \"pair_accuracy\": 0.759422221362207,\n      \"targets\": 1052953.0,\n      \"target_weight_sum\": 632551.0,\n      \"batches\": 266.0,\n      \"seconds\": 210.31189397000003,\n      \"validation_loss\": 0.37467752265494014,\n      \"validation_targets\": 130103.0,\n      \"validation_target_weight_sum\": 78769.25,\n      \"validation_seconds\": 15.806733069000074\n    }\n  ],\n  \"embedding_diagnostics\": {\n    \"query_norm_mean\": 1.4167587757110596,\n    \"query_norm_std\": 0.5332574844360352,\n    \"item_norm_mean\": 1.7329493761062622,\n    \"item_norm_std\": 0.9284447431564331\n  },\n  \"torch_version\": \"2.8.0+cpu\",\n  \"device\": \"cpu\"\n}\n"}

Script completed
Wall time 3.3 seconds
Output:

{
  "model": "/app/solution/pairwise_validation.parquet",
  "scores": {
    "quality_ndcg@10": 0.025707,
    "quality_users": 4263
  }
}

Script failed
Wall time 0.0 seconds
Output:

Script error:
SyntaxError: Unexpected string

Script completed
Wall time 0.0 seconds
Output:

{}

Script completed
Wall time 3.9 seconds
Output:

fallback valid rows=845,600 users=8,456
-rw-r--r-- 1 agent agent 719K Aug 31 19:55 /app/solution/submission.parquet
-rw-r--r-- 1 agent agent 511M Aug 31 19:37 /app/solution/validation_prepared.npz

Script completed
Wall time 1.2 seconds
Output:

{"chunk_id":"276704","wall_time_seconds":1.001872996,"session_id":10407,"original_token_count":0,"output":""}

Script completed
Wall time 0.0 seconds
Output:

{}

Script running with cell ID 81
Wall time 11.0 seconds
Output:

Script completed
Wall time 15.9 seconds
Output:

{"chunk_id":"dd2139","wall_time_seconds":30.001395189,"session_id":10407,"original_token_count":130,"output":"loaded explicit events: rows=746,504 users=8,307\nprepared users=1,000 tokens=2,167,338 states=37,073 elapsed=5.1s\nprepared users=2,000 tokens=4,450,246 states=73,784 elapsed=10.2s\nprepared users=3,000 tokens=6,703,970 states=113,190 elapsed=15.6s\nprepared users=4,000 tokens=9,087,187 states=153,283 elapsed=21.2s\nprepared users=5,000 tokens=11,354,844 states=188,776 elapsed=26.2s\nprepared users=6,000 tokens=13,485,786 states=224,384 elapsed=31.1s\nprepared users=7,000 tokens=15,826,114 states=265,318 elapsed=36.8s\n"}

Script running with cell ID 82
Wall time 11.0 seconds
Output:

Script completed
Wall time 14.5 seconds
Output:

{"chunk_id":"cc4522","wall_time_seconds":30.002435178,"session_id":10407,"original_token_count":181,"output":"prepared users=8,000 tokens=18,028,622 states=306,474 elapsed=42.3s\nprepared users=9,000 tokens=20,195,749 states=342,272 elapsed=47.2s\ntarget users without qualifying catalog sequence=6\nprepared stage=submission sequence_users=9,153 tokens=20,712,971 next_item_targets=20,703,818 states=350,322\nsaved public-derived full-sequence cache: /app/solution/submission_prepared.npz\nchronological BCE window: train=1,067,606 validation=131,997 selected=1,199,603 discarded_old_targets=19,504,215 all=20,703,818\ninbatch correction: min=0.250 mean_on_targets=1.001 max=4.000\ntarget weighting=organic-strong min=0.250 mean=0.576 max=1.000\nfull-history false-negative filter: users=9,153 unique_user_items=5,682,910 bytes=34,323,750\n"}

Script running with cell ID 83
Wall time 11.0 seconds
Output:

Script completed
Wall time 15.2 seconds
Output:

{"chunk_id":"2e6553","wall_time_seconds":30.002003814,"session_id":10407,"original_token_count":0,"output":""}

Script running with cell ID 84
Wall time 11.0 seconds
Output:

Script completed
Wall time 15.9 seconds
Output:

{"chunk_id":"1d6cf9","wall_time_seconds":30.000983367,"session_id":10407,"original_token_count":0,"output":""}

Script running with cell ID 85
Wall time 11.0 seconds
Output:

Script completed
Wall time 16.3 seconds
Output:

{"chunk_id":"068e2a","wall_time_seconds":30.001719747,"session_id":10407,"original_token_count":0,"output":""}

Script running with cell ID 86
Wall time 11.0 seconds
Output:

Script completed
Wall time 15.6 seconds
Output:

{"chunk_id":"65ad04","wall_time_seconds":30.001287296,"session_id":10407,"original_token_count":0,"output":""}

Script running with cell ID 87
Wall time 11.0 seconds
Output:

Script completed
Wall time 15.8 seconds
Output:

{"chunk_id":"426992","wall_time_seconds":30.001975484,"session_id":10407,"original_token_count":0,"output":""}

Script running with cell ID 88
Wall time 11.0 seconds
Output:

Script completed
Wall time 16.4 seconds
Output:

{"chunk_id":"ea52b5","wall_time_seconds":30.001691652,"session_id":10407,"original_token_count":24,"output":"epoch=1/1 batches=250 targets=994,228 batch_bce=0.334134 running_bce=0.439095 elapsed=199.7s\n"}

Script running with cell ID 89
Wall time 11.0 seconds
Output:

Script completed
Wall time 16.3 seconds
Output:

{"chunk_id":"744924","wall_time_seconds":30.001991346,"session_id":10407,"original_token_count":75,"output":"saved epoch checkpoint: /app/solution/final_checkpoints/epoch-01.pt\nepoch=1/1 train_loss=0.43487 validation_loss=0.37903 pair_accuracy=0.758 train_targets=1,067,606 validation_targets=131,997 train_seconds=214.3 validation_seconds=16.3\nrestored best validation-BCE checkpoint: epoch=1 loss=0.379033\n"}

Script running with cell ID 90
Wall time 11.0 seconds
Output:

Script completed
Wall time 16.3 seconds
Output:

{"chunk_id":"a29e4b","wall_time_seconds":30.0014538,"session_id":10407,"original_token_count":0,"output":""}

Script running with cell ID 91
Wall time 11.0 seconds
Output:

Script completed
Wall time 0.0 seconds
Output:

{"chunk_id":"e36b26","wall_time_seconds":13.266270837,"exit_code":0,"original_token_count":849,"output":"ranked users=1,024/8,456\nranked users=2,048/8,456\nranked users=3,072/8,456\nranked users=4,096/8,456\nranked users=5,120/8,456\nranked users=6,144/8,456\nranked users=7,168/8,456\nranked users=8,192/8,456\nranked users=8,456/8,456\n{\n  \"baseline\": \"yambda-windowed-sequence-two-tower-base\",\n  \"stage\": \"submission\",\n  \"output\": \"/app/solution/final_candidate.parquet\",\n  \"rows\": 845600,\n  \"users\": 8456,\n  \"runtime_seconds\": 369.456,\n  \"public_inputs_only\": true,\n  \"architecture\": {\n    \"family\": \"pure-windowed-sequence-two-tower\",\n    \"sequence_training\": \"every-adjacent-target-within-recent-chronological-window\",\n    \"sequence_encoder\": \"one-layer-GRU-dense-timestep-loss\",\n    \"bptt_hidden_state\": \"carried-and-detached\",\n    \"model_selection\": \"chronological-validation-BCE-early-stopping\",\n    \"loss_execution\": \"gradient-accumulated-microbatches\",\n    \"user_id_embedding\": false,\n    \"user_mlp\": \"582-512-256-192\",\n    \"item_mlp\": \"196-512-256-192\",\n    \"normalization\": \"none\",\n    \"score\": \"raw-dot-product\",\n    \"objective\": \"sample-weighted-pairwise-at-every-timestep\",\n    \"negative_sampling\": \"24-uniform-plus-8-propensity-corrected-inbatch\",\n    \"negative_loss\": \"corrected-mean\",\n    \"false_negative_filter\": \"full-training-history\",\n    \"target_weighting\": \"organic-strong\"\n  },\n  \"config\": {\n    \"bptt_steps\": 100,\n    \"user_batch_size\": 64,\n    \"embedding_dim\": 192,\n    \"hidden_dim\": 192,\n    \"user_hidden_1\": 512,\n    \"user_hidden_2\": 256,\n    \"item_hidden_1\": 512,\n    \"item_hidden_2\": 256,\n    \"dropout\": 0.05,\n    \"epochs\": 1,\n    \"learning_rate\": 0.001,\n    \"weight_decay\": 1e-05,\n    \"gradient_clip\": 2.0,\n    \"loss_microbatch_size\": 65536,\n    \"uniform_negatives\": 24,\n    \"inbatch_negatives\": 8,\n    \"inbatch_correction_power\": 0.5,\n    \"inbatch_correction_min\": 0.25,\n    \"inbatch_correction_max\": 4.0,\n    \"negative_loss\": \"corrected-mean\",\n    \"hard_negative_temperature\": 1.0,\n    \"hard_negative_mix\": 0.0,\n    \"training_objective\": \"pairwise\",\n    \"negative_filter_scope\": \"full-training-history\",\n    \"target_weighting\": \"organic-strong\",\n    \"ordinary_target_weight\": 0.25,\n    \"organic_strong_target_weight\": 1.0,\n    \"organic_like_target_weight\": 3.0,\n    \"discovery_horizon_days\": 7,\n    \"validation_fraction\": 0.1,\n    \"max_train_targets_per_user\": 128,\n    \"max_validation_targets_per_user\": 16,\n    \"early_stopping_patience\": 1,\n    \"early_stopping_min_delta\": 0.0001,\n    \"seed\": 29\n  },\n  \"sequence_tokens\": 20712971,\n  \"all_next_item_targets\": 20703818,\n  \"selected_training_targets\": 1067606,\n  \"selected_validation_targets\": 131997,\n  \"discarded_old_targets\": 19504215,\n  \"training_history\": [\n    {\n      \"epoch\": 1.0,\n      \"loss\": 0.43486819283980155,\n      \"positive_logit\": 0.8567554155875343,\n      \"negative_logit\": -0.5406865185658274,\n      \"pair_accuracy\": 0.7584716119523495,\n      \"targets\": 1067606.0,\n      \"target_weight_sum\": 641383.25,\n      \"batches\": 270.0,\n      \"seconds\": 214.26273486799982,\n      \"validation_loss\": 0.37903303406332534,\n      \"validation_targets\": 131997.0,\n      \"validation_target_weight_sum\": 80328.75,\n      \"validation_seconds\": 16.27803837500005\n    }\n  ],\n  \"embedding_diagnostics\": {\n    \"query_norm_mean\": 1.3882863521575928,\n    \"query_norm_std\": 0.5058810114860535,\n    \"item_norm_mean\": 1.8689460754394531,\n    \"item_norm_std\": 0.955160915851593\n  },\n  \"torch_version\": \"2.8.0+cpu\",\n  \"device\": \"cpu\"\n}\n"}

Script completed
Wall time 3.0 seconds
Output:

{'rows': 845600, 'users': 8456, 'items_per_user_min': 100, 'items_per_user_max': 100, 'rank_min': 1, 'rank_max': 100, 'ineligible_rows': 0, 'all_integer': True}
{'regular_file': True, 'bytes': 1208689}
-rw-r--r-- 1 agent agent 1.2M Aug 31 20:01 /app/solution/submission.parquet
-rw-r--r-- 1 agent agent  83K Aug 31 19:54 /app/solution/train_current_model.py
-rw-r--r-- 1 agent agent  16K Aug 31 19:29 /app/solution/two_tower_model.py

Script failed
Wall time 0.0 seconds
Output:

Script error:
SyntaxError: Unexpected identifier 'softplus'

Script completed
Wall time 0.0 seconds
Output:

{}

Script completed
Wall time 6.1 seconds
Output:

/bin/sh: 2: rg: not found
{
  "model": "/app/solution/pairwise_validation.parquet",
  "scores": {
    "quality_ndcg@10": 0.025707,
    "quality_users": 4263
  }
}
FINAL_OK 845600 8456 True True ['uid', 'item_id', 'rank'] {'uid': 'int64', 'item_id': 'int64', 'rank': 'int64'}
submission_csv_exists False
-rw-r--r-- 1 agent agent 2.5K Aug 31 20:03 /app/solution/README.md
-rw-r--r-- 1 agent agent 1.2M Aug 31 19:53 /app/solution/pairwise_validation.parquet
-rw-r--r-- 1 agent agent 1.2M Aug 31 20:01 /app/solution/submission.parquet

Script completed
Wall time 0.0 seconds
Output:

58:    uniform_negatives: int = 24
59:    inbatch_negatives: int = 8
63:    negative_loss: str = "corrected-mean"
65:    hard_negative_mix: float = 0.0
66:    training_objective: str = "pairwise"
659:    if config.inbatch_negatives:
678:        if corrected_count < config.inbatch_negatives:
867:    if config.uniform_negatives:
871:    if config.inbatch_negatives:
887:    if config.inbatch_negatives:
    user_batch_size: int = 64
    embedding_dim: int = 192
    hidden_dim: int = 192
    user_hidden_1: int = 512
    user_hidden_2: int = 256
    item_hidden_1: int = 512
    item_hidden_2: int = 256
    dropout: float = 0.05
    epochs: int = 1
    learning_rate: float = 1.0e-3
    weight_decay: float = 1.0e-5
    gradient_clip: float = 2.0
    loss_microbatch_size: int = 65_536
    uniform_negatives: int = 24
    inbatch_negatives: int = 8
    inbatch_correction_power: float = 0.5
    inbatch_correction_min: float = 0.25
    inbatch_correction_max: float = 4.0
    negative_loss: str = "corrected-mean"
    hard_negative_temperature: float = 1.0
    hard_negative_mix: float = 0.0
    training_objective: str = "pairwise"
    negative_filter_scope: str = "full-training-history"
    target_weighting: str = "organic-strong"
    ordinary_target_weight: float = 0.25
    organic_strong_target_weight: float = 1.0
    organic_like_target_weight: float = 3.0
    discovery_horizon_days: int = 7
    validation_fraction: float = 0.10
    max_train_targets_per_user: int = 128
    max_validation_targets_per_user: int = 16
    early_stopping_patience: int = 1
    early_stopping_min_delta: float = 1.0e-4
    seed: int = 29



{}