总览 · ← 返回运行 20261001-233757-search-t1-abc-r0-C-native

节点 n8 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 02f78f7bcd: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：父节点版本 34ea38b45b。改动的文件：solution/METHOD.md +13 −0、solution/run.py +80 −13

diff --git a/solution/METHOD.md b/solution/METHOD.mdnew file mode 100644index 0000000..a840a4e--- /dev/null+++ b/solution/METHOD.md@@ -0,0 +1,13 @@+## 改了什么+1. 关键修复：使用 `inputs_by_time(manifest, include_external=False)` 排除外部阶段（Qiu E9.0），避免 proxy2 中错误地以外部心脏数据为预测基底。若无官方阶段则回退到全部输入（兼容 X3 测试题）。+2. 按类型自适应收缩：对每个细胞类型，计算其 delta 的逐基因信噪比（|delta| / SE），统计显著变化基因的比例，据此在 [ALPHA_MIN, ALPHA_MAX] 区间内分配该类型的收缩系数。+3. 新增逐基因收缩（per-gene shrinkage）：在每个类型内部，对每个基因按其 SNR 计算收缩权重 (snr/(snr+2))^1.5，噪声大的基因位移被压缩，信号强的基因保留更多位移。这保护了协方差结构（不移动噪声基因），同时聚焦信号。+4. 移除第 1 轮添加的高斯噪声（实测证明噪声损害了 covariation 和 X3）。+5. ALPHA_MAX 从 0.8 微调到 0.75：per-gene shrinkage 已提供额外的正则化，略降上限避免过冲。++## 用到的知识与出处+- 方法卡 k018：官方常数位移（alpha=1）在 T1 上低于 copy_last，需要收缩；可选逐基因经验贝叶斯收缩使噪声基因少动。+- 方法卡 T1 卡「平移幅度」段：α∈[0,1]，不能默认 α=1。+- 实验表：父节点 proxy2=27.43 的根因是未过滤外部阶段。+- 第 1 轮实验：噪声注入（NOISE_SCALE=0.02）使 covariation 从 44.94 降至 43.23，X3 从 45.05 降至 44.25，故移除。+- per-gene shrinkage 思路来自 k018 的"Optionally shrink per gene (empirical Bayes on the delta's variance)"，但此处与 per-type adaptive alpha 组合，区别于 Program 1（uniform alpha + per-gene EB）。diff --git a/solution/run.py b/solution/run.pyindex f3a0f25..4e6effd 100644--- a/solution/run.py+++ b/solution/run.py@@ -1,13 +1,13 @@ #!/usr/bin/env python3-"""pseudobulk_shift: latest stage + per-cell-type pseudobulk delta of the last step.+"""Per-type adaptive shrinkage on pseudobulk deltas with official-stage filtering. -The delta is mean(last|type) - mean(prev|type) over the two latest inputs,-computed on the full stages and added once to a subsample of the latest stage-(clipped at 0). Types missing from the earlier stage are copied unchanged.+Uses only official (non-external) input stages. For each cell type, computes+the pseudobulk delta and a per-type shrinkage factor based on the fraction of+genes showing consistent directional change (sign agreement with the dominant+direction). Types with coherent transcriptional shifts are shifted more; types+with noisy or contradictory deltas are shrunk toward zero. -With a single input stage (T1 proxy: E8.5 only) there is no step to take a-delta from, so this falls back to copy_last with the same sampling. The proxy-therefore cannot tell this seed from copy_last; that gap is expected.+With a single official input stage, falls back to copy_last. """  from __future__ import annotations@@ -15,8 +15,8 @@ from __future__ import annotations import argparse  import numpy as np+from scipy import sparse -from src.task1_temporal.baselines import shift_rows, type_deltas from src.task1_temporal.view_io import (     inputs_by_time,     labels_of,@@ -28,6 +28,38 @@ from src.task1_temporal.view_io import (     write_prediction, ) +ALPHA_MAX = 0.75+ALPHA_MIN = 0.1+SIGN_THRESHOLD = 0.05+GENE_SHRINK_POWER = 1.5+++def _to_dense(X):+    if sparse.issparse(X):+        return np.asarray(X.todense(), dtype=np.float32)+    return np.asarray(X, dtype=np.float32)+++def _per_type_means(X, labels):+    Xd = _to_dense(X)+    types = np.unique(labels)+    means = {}+    for t in types:+        means[t] = Xd[labels == t].mean(axis=0)+    return means+++def _adaptive_alpha(delta, gene_var_last, gene_var_prev, n_last, n_prev):+    noise_se = np.sqrt(gene_var_last / max(n_last, 1) + gene_var_prev / max(n_prev, 1) + 1e-12)+    snr = np.abs(delta) / (noise_se + 1e-12)+    significant = snr > 2.0+    frac_significant = significant.mean()+    if frac_significant < SIGN_THRESHOLD:+        return ALPHA_MIN, np.ones_like(delta)+    alpha = ALPHA_MIN + (ALPHA_MAX - ALPHA_MIN) * min(frac_significant / 0.3, 1.0)+    gene_shrink = (snr / (snr + 2.0)) ** GENE_SHRINK_POWER+    return alpha, gene_shrink+  def main() -> None:     parser = argparse.ArgumentParser()@@ -38,16 +70,51 @@ def main() -> None:      manifest = load_manifest(args.data)     genes = panel_genes(args.data, manifest)-    stages = inputs_by_time(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)     rng = np.random.default_rng(args.seed)     rows = sample_rows(last.n_obs, target_n_cells(manifest, last.n_obs), rng)-    X = last.X[rows]+    X = _to_dense(last.X[rows])+     if len(stages) >= 2:         prev = read_stage(args.data, stages[-2], genes)-        deltas = type_deltas(prev.X, labels_of(prev), last.X, labels_of(last))-        del prev-        X = shift_rows(X, labels_of(last)[rows], deltas)+        labels_last = labels_of(last)+        labels_prev = labels_of(prev)++        means_last = _per_type_means(last.X, labels_last)+        means_prev = _per_type_means(prev.X, labels_prev)++        Xd_last = _to_dense(last.X)+        Xd_prev = _to_dense(prev.X)++        deltas = {}+        for t in means_last:+            if t in means_prev:+                raw_delta = means_last[t] - means_prev[t]+                mask_last = labels_last == t+                mask_prev = labels_prev == t+                n_last = mask_last.sum()+                n_prev = mask_prev.sum()+                var_last = Xd_last[mask_last].var(axis=0)+                var_prev = Xd_prev[mask_prev].var(axis=0)+                alpha, gene_shrink = _adaptive_alpha(raw_delta, var_last, var_prev, n_last, n_prev)+                deltas[t] = raw_delta * alpha * gene_shrink+            else:+                deltas[t] = np.zeros(len(genes), dtype=np.float32)++        del prev, Xd_last, Xd_prev++        labels_sampled = labels_last[rows]+        for t in np.unique(labels_sampled):+            mask = labels_sampled == t+            if t in deltas:+                X[mask] += deltas[t]++    np.clip(X, 0.0, None, out=X)     write_prediction(X, genes, args.out, seed=args.seed)  

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 results: noise hurt both covariation (44.94→43.23) and X3 (45.05→44.25). I'll remove noise and instead add per-gene shrinkage within each type's delta, which should improve covariation by not shifting noisy genes, while keeping the per-type adaptive alpha that distinguishes this from Program 1.

<<<<<<< SEARCH
ALPHA_MAX = 0.8
ALPHA_MIN = 0.1
SIGN_THRESHOLD = 0.05
NOISE_SCALE = 0.02
=======
ALPHA_MAX = 0.75
ALPHA_MIN = 0.1
SIGN_THRESHOLD = 0.05
GENE_SHRINK_POWER = 1.5
>>>>>>> REPLACE

<<<<<<< SEARCH
def _adaptive_alpha(delta, gene_var_last, gene_var_prev, n_last, n_prev):
    noise_se = np.sqrt(gene_var_last / max(n_last, 1) + gene_var_prev / max(n_prev, 1) + 1e-12)
    snr = np.abs(delta) / (noise_se + 1e-12)
    significant = snr > 2.0
    frac_significant = significant.mean()
    if frac_significant < SIGN_THRESHOLD:
        return ALPHA_MIN
    alpha = ALPHA_MIN + (ALPHA_MAX - ALPHA_MIN) * min(frac_significant / 0.3, 1.0)
    return alpha
=======
def _adaptive_alpha(delta, gene_var_last, gene_var_prev, n_last, n_prev):
    noise_se = np.sqrt(gene_var_last / max(n_last, 1) + gene_var_prev / max(n_prev, 1) + 1e-12)
    snr = np.abs(delta) / (noise_se + 1e-12)
    significant = snr > 2.0
    frac_significant = significant.mean()
    if frac_significant < SIGN_THRESHOLD:
        return ALPHA_MIN, np.ones_like(delta)
    alpha = ALPHA_MIN + (ALPHA_MAX - ALPHA_MIN) * min(frac_significant / 0.3, 1.0)
    gene_shrink = (snr / (snr + 2.0)) ** GENE_SHRINK_POWER
    return alpha, gene_shrink
>>>>>>> REPLACE

<<<<<<< SEARCH
        deltas = {}
        for t in means_last: