总览 · ← 返回运行 20261002-034201-search-t1-abc-r1-C-native

节点 n9 在终选来历上

改了什么

方法说明?节点程序自带的 METHOD.md：这个程序做了什么、为什么。

来自 programs.git 34254aa790:solution/METHOD.md

调研员的计划

代码改动?这个节点的程序和父节点程序的逐行差别：绿色是新增，红色是删除。

对比：这个提交的上一版（种子程序：相对空仓库）。改动的文件：solution/METHOD.md +4 −0、solution/README.md +4 −0、solution/run.py +84 −0

diff --git a/solution/METHOD.md b/solution/METHOD.mdnew file mode 100644index 0000000..58fac39--- /dev/null+++ b/solution/METHOD.md@@ -0,0 +1,4 @@+## 改了什么+从 pseudobulk_shift 改为组成重加权（T1-01 方向）。核心变化：(1) 使用 include_external=False 避免 proxy2 中 Qiu E9.0 标签不匹配导致的崩溃（原程序 proxy2 仅 27.43）；(2) 按正则模式将细胞类型分为 heart（×1.6）、reduced（×0.15，含 surface ectoderm/EXEM/paraxial/neural）、gut（×0.9）、neutral（×1.0）四族，用加权抽样替代均匀抽样，不改表达值；(3) 对 X3 等无官方输入的视图有退路（回退到全部输入）。权重规则按名称模式定义，不写死特定阶段的名字。+## 用到的知识与出处+方向库 T1-01（种子 heart_jcf_peri：心脏类 ×1.6，表面外胚层/EXEM/轴旁中胚层 ×0.25，丢 Neural Tube；proxy 55.97）；方法卡 T1 标签节（E8.5 独有名应降权或丢弃）；k012（cell_state 权重 30%，组成匹配是关键得分项）。diff --git a/solution/README.md b/solution/README.mdnew file mode 100644index 0000000..ba29577--- /dev/null+++ b/solution/README.md@@ -0,0 +1,4 @@+# pseudobulk_shift++最新阶段抽样后，每个细胞加上所属类型在最后一步的伪批量差值 mean(last|type) − mean(prev|type)，夹到 ≥0；前一阶段没有的类型原样复制。+T1 proxy 只有一个输入阶段，没有差值可取，退化成 copy_last（同样的抽样），所以 proxy 分 = copy_last（seed 0 实测 49.77）。final 才真正平移；官方在真实 T1 上报的常数位移是 48.6，低于地板。diff --git a/solution/run.py b/solution/run.pynew file mode 100644index 0000000..4710196--- /dev/null+++ b/solution/run.py@@ -0,0 +1,84 @@+#!/usr/bin/env python3+"""Composition reweighting: weighted sampling from latest official input stage.++Cell types are classified into families by regex patterns on their names.+Heart-related types are upweighted, surface ectoderm / extraembryonic /+neural types are downweighted or dropped. Expression values are unchanged.++Uses include_external=False to avoid mismatched-label external stages in+proxy2. Falls back to all stages if no official inputs exist (X3).+"""++from __future__ import annotations++import argparse+import re++import numpy as np++from src.task1_temporal.view_io import (+    inputs_by_time,+    labels_of,+    load_manifest,+    panel_genes,+    read_stage,+    target_n_cells,+    write_prediction,+)++_HEART_PAT = re.compile(+    r"cm\b|cardi|heart|shf|endocard|oft\b|avc|ift\b|sv[- ]cm|v[- ]cm|"+    r"proepicard|pericard|epicard|blood",+    re.IGNORECASE,+)+_REDUCED_PAT = re.compile(+    r"surface\s*ectoderm|exem|paraxial|neural\s*tube|neural|notochord",+    re.IGNORECASE,+)+_GUT_PAT = re.compile(+    r"foregut|endoderm|gut|hepato|epithel",+    re.IGNORECASE,+)+++def family_weight(name: str) -> float:+    if _HEART_PAT.search(name):+        return 1.6+    if _REDUCED_PAT.search(name):+        return 0.15+    if _GUT_PAT.search(name):+        return 0.9+    return 1.0+++def main() -> None:+    parser = argparse.ArgumentParser()+    parser.add_argument("--data", required=True)+    parser.add_argument("--out", required=True)+    parser.add_argument("--seed", type=int, default=0)+    args = parser.parse_args()++    manifest = load_manifest(args.data)+    genes = panel_genes(args.data, manifest)++    stages = inputs_by_time(manifest, include_external=False)+    if not stages:+        stages = inputs_by_time(manifest)++    last = read_stage(args.data, stages[-1], genes)+    labels = labels_of(last)+    rng = np.random.default_rng(args.seed)+    n_target = target_n_cells(manifest, last.n_obs)++    weights = np.array([family_weight(str(l)) for l in labels], dtype=np.float64)+    if weights.sum() == 0:+        weights[:] = 1.0+    weights /= weights.sum()++    rows = rng.choice(last.n_obs, size=n_target, replace=True, p=weights)+    X = last.X[rows]+    write_prediction(X, genes, args.out, seed=args.seed)+++if __name__ == "__main__":+    main()

调研来源?调研员查到并用到的知识条目和文献检索结果（只列标题和编号）。

没有记录调研来源。

分析结果?分析员写的 ANALYSIS.json：改了什么、各组分数怎么变、假设是否成立、经验和下一步建议。

对话摘要?每个角色和大模型对话的统计：轮数、工具调用、用时、token 数和最后的回答摘录；原始记录只给路径。

只给统计和最后回答的摘录；完整对话请到原始记录位置里列出的文件看。

分析员

ANALYSIS.json written

native

审查员

REVIEW.json written

stream

Looking at the scores, Round 1 (48.60) is worse than Round 0 (51.47). The pseudobulk shift destroyed covariation (51.37→38.86) and X3 (47.31→40.07). The fix is to remove the shift entirely and match the seed's proven weights (which got proxy 55.97 without any expression modification).

<<<<<<< SEARCH
#!/usr/bin/env python3
"""Composition reweighting + pseudobulk shift from latest official input stage.

Cell types are classified into families by regex patterns on their names.
Heart-related types are upweighted, surface ectoderm / EXEM / paraxial are
downweighted, Neural Tube is dropped entirely. When two official stages are
available, per-type pseudobulk deltas are applied to improve DE recovery
and direction scores.

Uses include_external=False to avoid mismatched-label external stages in
proxy2. Falls back to all stages if no official inputs exist (X3).
"""

from __future__ import annotations

import argparse
import re

import numpy as np

from src.task1_temporal.baselines import shift_rows, type_deltas
from src.task1_temporal.view_io import (
    inputs_by_time,
    labels_of,
    load_manifest,
    panel_genes,
    read_stage,
    target_n_cells,
    write_prediction,
)

_HEART_PAT = re.compile(
    r"cm\b|cardi|heart|shf|endocard|oft\b|avc|ift\b|sv[- ]cm|v[- ]cm|"
    r"proepicard|pericard|epicard|blood",
    re.IGNORECASE,
)
_DROP_PAT = re.compile(r"neural\s*tube", re.IGNORECASE)