效度 · 模型在漂移吗?
模型健康 / 漂移监测
leakage-safe · 最近 6 个实现月 vs 历史
PSI
0.226
IC 最近
-0.002
IC 全程
0.004
base rate
0.54→0.52
PSI
0.542
IC 最近
0.081
IC 全程
-0.046
base rate
0.45→0.40
身份
| 字段 | 值 |
|---|---|
| 阶段(ledger 行) | B |
| config_sig | 17245a75d2d4cd17c68f36a9d0f4b4f7f3baf1db31b33b87be79e6e4a11400da |
| 结果目录 | runs/results/17245a75d2d4cd17c68f36a9d0f4b4f7f3baf1db31b33b87be79e6e4a11400da |
| Aionis 版本 | 0.1.0 |
| schema | 1 |
| H6 确定性 | PASS |
| run 时间(工件 ts,非时钟) | 2026-07-28T04:27:39+00:00 |
预期用途
| 字段 | 值 |
|---|---|
| 主张 | Display-layer documentation of the frozen confirmatory model: a pre-registered, two-tailed, null-expected rank-IC claim whose config was committed to the append-only ledger before any out-of-sample metric was observed. The card exists for transparency and reproducibility inspection, not for performance advertisement. |
| 仅展示 | true |
| 非投资建议 | true |
| 预注册文档(sha256 钉定) | c0ecaadfc317278b1ca514528a22f4415e17727be9da0ccf48964114a30fad51预注册原文(GitHub) |
数据输入
| 字段 | 值 |
|---|---|
| fundamentals sha256 | df1f27cecc20acb6f2b5e2d75e88618733e42cec07c48187825a53330151ad7b |
| prices sha256 | c86551c35e3503b02565eada4c8a5e343ad40e008e26f47b2b99e9c36876dc46 |
| membership sha256 | 59374fda51c515eadd4cb7565c7f896abe54d95fae4a79476b1e157434eb2bf3 |
| 期末滞后(申报后月数) | 10-K: 6 · 10-Q: 4 |
| 特征列 | 9 · mktcap, pb_ratio, roa, fund_assets, fund_revenue, fund_net_income, fund_equity, fund_shares_out, fund_long_term_debt |
| 宇宙语义 | Universe membership is point-in-time (resolved as-of each historical panel date, never a today snapshot); fundamentals enter via filing dates. The input sha256 pins identify the exact frozen data artifacts behind the feature table. |
模型
| 字段 | 值 |
|---|---|
| 学习器 | lightgbm 4.7.0 |
| 库版本 | lightgbm 4.7.0 · purgedcv 0.1.2 · arch 8.0.0 |
| 冻结超参 | objective=regression · n_estimators=500 · learning_rate=0.05 · num_leaves=31 · min_child_samples=20 · reg_lambda=1 · feature_fraction=0.8 · bagging_fraction=0.8 · bagging_freq=1 · n_jobs=1 · random_state=0 · bagging_seed=0 · feature_fraction_seed=0 · drop_seed=0 · verbose=-1 |
| 确定性种子 | random_state=0 · bagging_seed=0 · feature_fraction_seed=0 · drop_seed=0 · n_jobs=1 |
评估协议
| 字段 | 值 |
|---|---|
| CV 方案 | 5-fold PurgedGroupKFold (group=month, embargo=21 sessions) over the 2016+ resolvable window; the explicit 2011-2016/2017-2026 split in pre-reg §8.0 is superseded because the resolvable universe is 2016+ |
| horizon | 21 |
| n_splits | 5 |
| embargo sessions | 21 |
结果(头条实值逐字嵌入)
| 字段 | 值 |
|---|---|
| combined rank-IC | -0.0088 |
| 置信区间(95%) | [-0.0336, 0.0159] |
| p(HAC) | 0.484 |
| 实现月数 | 71 |
| 裁决 | NULL |
| SESOI | 0.01 |
| 结果 config sig | e14b9d44 |
| ledger 行 | #49 |
治理 · 账本链
| 字段 | 值 |
|---|---|
| 冻结行(config_committed) | #27 · 2026-07-28T04:15:16+00:00 |
| 冻结行(config_committed) · sha256 | 818c94fd55a03966d05e8452febbb8772db06145c171116ce8440f18003c9abb |
| 结果行(confirmatory:first) | #28 |
| 契约 | The config_committed row precedes the result row sharing its sha256 — the anti-leakage ordering, verifiable against runs/ledger.jsonl. |
| uv.lock(冻结时) | e045a023c5ea8d9a91ef41f183dc95447f61788d79c5fa974229c7b32d5b34a0 |
| uv.lock(当前) | 5c5cff1c84ece3e556fce275191377bca3eb2f84d97326527e3439a7e9cbc845 |
| uv.lock 一致 | falseDependency lock drifted since the freeze (later repo lanes added dependencies); the frozen training environment stays pinned by uv_lock_sha256 and versions. The current lock hash is embedded beside it for honest comparison. |
| 账本审计(/discipline) | 账本审计(/discipline) |
溯源
| 字段 | 值 |
|---|---|
| 生成器 | scripts/export_terminal_data.py::export_model_card (model_card_version v1) |
| 再生成命令 | uv run python -c "import sys; sys.path.insert(0,'scripts'); import export_terminal_data as m; m._safe_export('model_card', m.export_model_card)" |
| 字节稳定 | Zero-clock panel: no snapshot timestamp and no wall-clock reads; every value is machine-read verbatim from the pinned artifacts, so consecutive exports of unchanged artifacts are byte-identical. Output is LF. |
| 源(S 编号) | S1 frozen artifact · runs/results/17245a75d2d4cd17c68f36a9d0f4b4f7f3baf1db31b33b87be79e6e4a11400da/config.json — sha256:21da28dd91747ae5bc242867ac13850569c3109a59123c5f5c52cf21e6d363e7 (file bytes)S2 frozen artifact · runs/results/17245a75d2d4cd17c68f36a9d0f4b4f7f3baf1db31b33b87be79e6e4a11400da/meta.json — sha256:4eb28d84645378953392bcc51ffa9a25f0ed74dc69cbddf32c39f3ec9093f088 (file bytes)S3 ledger row · runs/ledger.jsonl line 27 — sha256:818c94fd55a03966d05e8452febbb8772db06145c171116ce8440f18003c9abb (line text)S4 ledger row · runs/ledger.jsonl line 28 — sha256:d8405c22044b2470928f901801ab27ef2d7e401cb7f5d676f0b1bfa64683b5ed (line text)S5 panel · web/src/data/aionis/metrics.json — verbatim value embed (results section); the source file carries a snapshot_ts clock, so no file hash is pinnedS6 repo doc · docs/track-c-preregistration.md — sha256:c0ecaadfc317278b1ca514528a22f4415e17727be9da0ccf48964114a30fad51 (LF bytes)S7 repo file · uv.lock — sha256:5c5cff1c84ece3e556fce275191377bca3eb2f84d97326527e3439a7e9cbc845 (LF bytes) |
展示层档案——非投资建议,不构成任何交易信号;冻结面只在冻结工件变化时更新。
覆盖账本行截至: 2026-08-08
| 阶段 | config_sig(前 12) | 冻结 ts(ledger) | H6 | 差分 mean_diff [95% CI] | 零假设 | 本地目录 |
|---|---|---|---|---|---|---|
| B | 17245a75d2d4 | #27 · 2026-07-28T04:15:16+00:00 | PASS | -0.0008 [-0.010573, 0.008972] | 未知 | v0.1.0 |
| C | a7fdb48f5942 | #29 · 2026-07-28T12:01:16+00:00 | PASS | -0.006487 [-0.019531, 0.006556] | 未知 | v0.1.0 |
| D | d31580630ff3 | #33 · 2026-07-29T02:31:16+00:00 | PASS | -0.00298 [-0.013714, 0.007755] | 未知 | v0.1.0 |
| E1 | ef321e9ee808 | #35 · 2026-07-29T03:29:39+00:00 | PASS | -0.002793 [-0.011457, 0.005871] | 未知 | v0.1.0 |
| track_c | e14b9d445411 | #48 · 2026-08-05T04:19:50.785179+00:00 | — | — | 未知 | 无目录(诚实未知) |
config-only 提交: 11
已提交账本、本地无结果目录——可能被后续配置取代或目录未保留(原因不猜测);不逐行展开,明细见 model_inventory.json。
建模决策谱系
#46ΔIC —#47ΔIC —#48ΔIC -0.0088 · p 0.484#51取代理由(ledger amendment 原文)amend1: WEEKLY cadence + truly-frozen baseline. Supersedes #51 (monthly-A, redundant with Track C).ΔIC —#52取代理由(ledger amendment 原文)amend2: n_estimators 500→100 (feasibility ~5min vs ~27min; both arms; comparison self-contained, valid at any n_estimators). Supersedes #52.ΔIC —#53ΔIC —显式取代 = ledger amendment 原文声明(Supersedes #NN),取代理由挂在被取代行下;账本序演化 = 按账本序推断的排列,非显式取代声明。emerald 行 = 该配置已有 confirmatory 结果或本地冻结目录。
清单为展示层治理记录——runs/ 只读;无本地目录=诚实未知而非不存在;非投资建议。
- 冻结截止
- 2023-03-10
- 出处
- empirical-probe-v1 (dual-blind dated-event ladder; NOT a vendor declaration) — frozen in config/e3_live_contracts.yaml
- 探针边界
- known ≤ 2023-03-10 · unknown ≥ 2024-11-06
- 最近漂移检查
- stable
经验探针边界不是厂商声明;安全向漂移(模型学得更新)也必须走显式契约修订,绝不静默改值。钉住的 LLM 在冻结样本外管线中从不产生信号。
Leakage-safe model-drift monitor (display-only). Population Stability Index (PSI) compares the recent realized score distribution to the historical one; rolling cross-sectional rank-IC (recent mean vs full mean) is reported for context. All metrics use only realized (score, forward_return) pairs strictly before the latest unread month. PSI<0.1 stable / 0.1–0.25 moderate / ≥0.25 significant. NOT a research claim and NOT a retrain trigger (rerun-to-significance is forbidden).
信息性显示——非研究 claim,不触发重训(rerun-to-significance 禁)。