重排序

CLERC_FILE = (
    "https://huggingface.co/datasets/jhu-clsp/CLERC/resolve/main/"
    "teva_train_dir/train_data.jsonl.gz"
)
 
 
def cid(text: str) -> str:
    """Corpus id: a content hash, so passages shared across queries dedupe."""
    return hashlib.sha1(text.encode("utf-8")).hexdigest()[:16]
 
 
@json_cache
def build_slice(n_rows: int, n_queries: int, seed: int) -> dict:
    """Stream CLERC rows, pool ``n_rows`` of them into a corpus, pick ``n_queries`` to evaluate."""
    from datasets import load_dataset  # heavy import, keep local
 
    stream = load_dataset("json", data_files=CLERC_FILE, streaming=True, split="train")
    rows = []
    for row in stream:
        if (
            row.get("positive_passages")
            and len(row.get("negative_passages") or []) == 20
        ):
            rows.append(row)
        if len(rows) >= 1000:
            break
 
    rng = random.Random(seed)
    picked = rng.sample(rows, n_rows)
    corpus, pool = {}, []
    for row in picked:
        gold = row["positive_passages"][0]["text"]
        corpus[cid(gold)] = gold
        for neg in row["negative_passages"]:
            corpus[cid(neg["text"])] = neg["text"]
        pool.append(
            {"qid": str(row["query_id"]), "query": row["query"], "gold": cid(gold)}
        )
    # hold out the first 20 pooled rows; evaluate on the rest
    queries = rng.sample(pool[20:], n_queries)
    # sort the corpus by id so every run — live or cache replay — iterates it identically
    return {"queries": queries, "corpus": dict(sorted(corpus.items()))}
 
 
def bm25_rankings(corpus: dict[str, str], queries: dict[str, str], k: int = 100):
    """Rank every passage in the corpus by word overlap with each query."""
    import bm25s
 
    cids = list(corpus)
    retriever = bm25s.BM25()
    retriever.index(bm25s.tokenize([corpus[c] for c in cids], stopwords="en"))
    qids = list(queries)
    idxs, _ = retriever.retrieve(
        bm25s.tokenize([queries[q] for q in qids], stopwords="en"), k=min(k, len(cids))
    )
    return {q: [cids[i] for i in idxs[row]] for row, q in enumerate(qids)}
 
 
def gold_rank(ranked: list[str], gold: str) -> int | None:
    """1-based rank of the gold id, or None if it isn't in the list."""
    return ranked.index(gold) + 1 if gold in ranked else None
 
 
SURFACE, INK, INK2, MUTED = "#f8f8f2", "#34342f", "#34342f", "#7c7c77"
GRID, AXIS, BLUE, GREEN = "#d8d8cf", "#d8d8cf", "#5d76a2", "#6f9b52"
 
 
def bar_chart(labels: list[str], shares: list[float], title: str) -> None:
    """A small single-series bar chart of shares (0-1, shown as percentages)."""
    import matplotlib.pyplot as plt
 
    fig, ax = plt.subplots(figsize=(5, 3.2), facecolor=SURFACE)
    ax.set_facecolor(SURFACE)
    for side in ("top", "right"):
        ax.spines[side].set_visible(False)
    for side in ("left", "bottom"):
        ax.spines[side].set_color(AXIS)
    ax.tick_params(colors=MUTED, labelcolor=INK2, labelsize=9)
    ax.set_axisbelow(True)
    ax.grid(axis="y", color=GRID, linewidth=0.8)
 
    bars = ax.bar(labels, shares, width=0.55, color=[BLUE, GREEN][: len(labels)])
    ax.bar_label(
        bars,
        labels=[f"{s * 100:.0f}%" for s in shares],
        padding=4,
        color=INK,
        fontsize=11,
    )
    ax.set_ylim(0, 1.1)
    ax.set_yticks([0, 0.25, 0.5, 0.75, 1.0])
    ax.set_yticklabels(["0%", "25%", "50%", "75%", "100%"])
    ax.set_ylabel(f"share of {len(queries)} queries", color=INK2, fontsize=9)
    ax.set_title(title, loc="left", color=INK, fontsize=11)
    plt.tight_layout()
    display(fig)
    plt.close(fig)
 
 
ds = build_slice(N_ROWS, N_QUERIES, seed=0)
corpus: dict[str, str] = ds["corpus"]
queries = {q["qid"]: q["query"] for q in ds["queries"]}
golds = {q["qid"]: q["gold"] for q in ds["queries"]}
 
candidates = {q: ranked[:TOP_K] for q, ranked in bm25_rankings(corpus, queries).items()}
 
in_top_k = sum(golds[q] in candidates[q] for q in queries)
at_rank_1 = sum(candidates[q][0] == golds[q] for q in queries)
 
bar_chart(
    [f"In top {TOP_K}", "At rank 1"],
    [in_top_k / len(queries), at_rank_1 / len(queries)],
    f"Where the correct passage lands, {len(queries)} queries against {len(corpus):,} candidates",
)
 

is_cited_source = Noul(
    instructions=(
        "The query excerpt comes from a US federal court opinion and was written "
        "immediately around a citation to a precedent; the citation itself has been "
        "removed. Could the candidate passage be from that cited precedent — does it "
        "establish the specific legal proposition the query excerpt invokes at its "
        "citation point?"
    ),
    criteria=NoulCriteria(
        true=(
            "The candidate passage states or establishes the specific rule, standard, "
            "holding, or fact pattern that the query excerpt attributes to its removed "
            "citation."
        ),
        false=(
            "The candidate passage is merely on a similar topic or doctrine; it does not "
            "supply the specific proposition the query excerpt relies on."
        ),
    ),
)
 
 
@json_cache
def score_candidate(model: str, query: str, candidate: str, question_json: str) -> dict:
    """One TypeSafe call about one (query, candidate) pair: a noul, plus token usage."""
    # the SDK takes a question as its JSON dict, so the cached string decodes straight in
    question = json.loads(question_json)
    response = client.system_one(
        state={"query_excerpt": query, "candidate_passage": candidate},
        questions={"is_cited_source": question},
        model=model,
    )
    return {
        "noul": response.answers["is_cited_source"].noul,
        "input_tokens": response.usage.input_tokens or 0,
        "output_tokens": response.usage.output_tokens or 0,
    }
 
 
# Each of the 40 queries has 30 candidates, so re-ranking every shortlist means 1,200 independent
# calls — cheap enough to fire all at once with a thread pool instead of one after another.
pair_list = [(q, c) for q in queries for c in candidates[q]]
question_json = msgspec.json.encode(is_cited_source).decode()
with ThreadPoolExecutor(max_workers=12) as pool:
    results = pool.map(
        lambda p: score_candidate(
            TYPESAFE_MODEL, queries[p[0]], corpus[p[1]], question_json
        ),
        pair_list,
    )
pair_scores = {q: {} for q in queries}
for (q, c), result in zip(pair_list, results):
    pair_scores[q][c] = result
 
reranked = {
    q: sorted(candidates[q], key=lambda c: -pair_scores[q][c]["noul"]) for q in queries
}
 
 
def chart_before_after(
    runs: dict[str, dict[str, list[str]]], thresholds: list[int]
) -> None:
    """Grouped bar chart: how often the correct passage lands in the top N, for each run."""
    import numpy as np
    import matplotlib.pyplot as plt
 
    labels = list(runs)
    colors = [BLUE, GREEN]
 
    def share_in_top(rankings, k):
        return sum(
            gold_rank(rankings[q], golds[q]) in range(1, k + 1) for q in queries
        ) / len(queries)
 
    fig, ax = plt.subplots(figsize=(6.5, 3.6), facecolor=SURFACE)
    ax.set_facecolor(SURFACE)
    for side in ("top", "right"):
        ax.spines[side].set_visible(False)
    for side in ("left", "bottom"):
        ax.spines[side].set_color(AXIS)
    ax.tick_params(colors=MUTED, labelcolor=INK2, labelsize=9)
    ax.set_axisbelow(True)
    ax.grid(axis="y", color=GRID, linewidth=0.8)
 
    x = np.arange(len(thresholds))
    width = 0.35
    for i, (label, rankings) in enumerate(runs.items()):
        shares = [share_in_top(rankings, k) for k in thresholds]
        offset = (i - (len(labels) - 1) / 2) * width
        bars = ax.bar(x + offset, shares, width * 0.92, color=colors[i], label=label)
        ax.bar_label(
            bars,
            labels=[f"{s * 100:.0f}%" for s in shares],
            padding=3,
            color=INK2,
            fontsize=8.5,
        )
 
    ax.set_xticks(x, [f"top {k}" for k in thresholds])
    ax.set_ylim(0, 1)
    ax.set_yticks([0, 0.25, 0.5, 0.75, 1.0])
    ax.set_yticklabels(["0%", "25%", "50%", "75%", "100%"])
    ax.set_ylabel(f"share of {len(queries)} queries", color=INK2, fontsize=9)
    ax.set_title(
        "How often the correct passage lands near the top",
        loc="left",
        color=INK,
        fontsize=11,
    )
    ax.legend(frameon=False, labelcolor=INK2, fontsize=9, loc="upper left")
    plt.tight_layout()
    display(fig)
    plt.close(fig)
 
 
chart_before_after(
    {"Fast search": candidates, "+ TypeSafe re-rank": reranked}, [1, 5, 10]
)
 
calls = [pair_scores[q][c] for q in queries for c in pair_scores[q]]
input_tokens = sum(call["input_tokens"] for call in calls)
output_tokens = sum(call["output_tokens"] for call in calls)
cost = input_tokens / 1_000_000 * PRICE[0] + output_tokens / 1_000_000 * PRICE[1]
print(
    f"{len(calls)} TypeSafe calls used {input_tokens:,} input and "
    f"{output_tokens:,} output tokens, costing ${cost:.4f}."
)