docs(artifacts): reorganize generated artifacts + docs (phase 10)

README.md

@@ -45,3 +45,33 @@ pytest -q
 数据契约、导出命令和服务器 smoke-test 入口见
 [`docs/SFT_BASELINE.md`](docs/SFT_BASELINE.md)；公共 seam 与 RL 接入条件见
 [`docs/RL_FRAMEWORK.md`](docs/RL_FRAMEWORK.md)。
+
+## 文档与产物结构
+
+`docs/` 存放项目文档，`artifacts/generated/` 存放可由脚本重新生成的分析产物。
+
+```text
+docs/                  文档：设计说明、分析结论、阶段报告
+├── design/            设计文档（data_contract / prompt_interface）
+├── phase_reports/     阶段报告
+├── data_alignment.md
+├── prompt_length_analysis.md
+├── SFT_BASELINE.md / RL_FRAMEWORK.md / 新数据集运行说明.md
+
+artifacts/generated/   生成产物：统计结果、对齐报告等可复现输出
+├── alignment/         对齐报告（data_alignment_report.json/.md）
+└── prompt_stats/      统计产物
+    ├── canonical_id_baseline/   旧 canonical-id 统计（baseline）
+    └── choice_id/               choice-protocol 新统计
+```
+
+关键文档：
+
+| 文档 | 内容 |
+|---|---|
+| [`docs/design/data_contract.md`](docs/design/data_contract.md) | canonical category_id 数据契约（registry/corpus/target、身份策略、训练入口规则） |
+| [`docs/design/prompt_interface.md`](docs/design/prompt_interface.md) | prompt-facing choice protocol（choice id ↔ canonical id、共享解码层） |
+| [`docs/prompt_length_analysis.md`](docs/prompt_length_analysis.md) | prompt token 分析（old∽new、Stage1 收益、worst-case 2689/32768） |
+| [`docs/data_alignment.md`](docs/data_alignment.md) | dataset ↔ corpus/standard 对齐人工结论 |
+
+`docs/reports/` 为本地 gitignored 调研/smoke scratch，不入库。

artifacts/generated/prompt_stats/choice_id/prompt_token_stats_finance.json

@@ -0,0 +1,139 @@
+{
+ "tokenizer": "Qwen/Qwen2.5-7B-Instruct",
+ "splits": {
+  "train": {
+   "stage1": {
+    "tokens": {
+     "rows": 403,
+     "max": 2553,
+     "p95": 2543,
+     "mean": 2535.4
+    },
+    "chars": {
+     "rows": 403,
+     "max": 5048,
+     "p95": 5033,
+     "mean": 5023.1
+    }
+   },
+   "stage2": {
+    "tokens": {
+     "rows": 403,
+     "max": 740,
+     "p95": 560,
+     "mean": 494.0
+    },
+    "chars": {
+     "rows": 403,
+     "max": 1579,
+     "p95": 1261,
+     "mean": 1163.3
+    }
+   }
+  },
+  "val": {
+   "stage1": {
+    "tokens": {
+     "rows": 69,
+     "max": 2543,
+     "p95": 2538,
+     "mean": 2534.6
+    },
+    "chars": {
+     "rows": 69,
+     "max": 5031,
+     "p95": 5027,
+     "mean": 5020.7
+    }
+   },
+   "stage2": {
+    "tokens": {
+     "rows": 69,
+     "max": 556,
+     "p95": 554,
+     "mean": 453.7
+    },
+    "chars": {
+     "rows": 69,
+     "max": 1254,
+     "p95": 1249,
+     "mean": 1097.1
+    }
+   }
+  },
+  "test": {
+   "stage1": {
+    "tokens": {
+     "rows": 57,
+     "max": 2539,
+     "p95": 2537,
+     "mean": 2535.3
+    },
+    "chars": {
+     "rows": 57,
+     "max": 5030,
+     "p95": 5026,
+     "mean": 5022.3
+    }
+   },
+   "stage2": {
+    "tokens": {
+     "rows": 57,
+     "max": 560,
+     "p95": 558,
+     "mean": 495.1
+    },
+    "chars": {
+     "rows": 57,
+     "max": 1258,
+     "p95": 1257,
+     "mean": 1160.8
+    }
+   }
+  }
+ },
+ "prompt_only": {
+  "train": {
+   "stage1": {
+    "rows": 403,
+    "max": 2534,
+    "p95": 2524,
+    "mean": 2515.9
+   },
+   "stage2": {
+    "rows": 403,
+    "max": 730,
+    "p95": 550,
+    "mean": 484.0
+   }
+  },
+  "val": {
+   "stage1": {
+    "rows": 69,
+    "max": 2523,
+    "p95": 2518,
+    "mean": 2514.6
+   },
+   "stage2": {
+    "rows": 69,
+    "max": 546,
+    "p95": 544,
+    "mean": 443.7
+   }
+  },
+  "test": {
+   "stage1": {
+    "rows": 57,
+    "max": 2520,
+    "p95": 2518,
+    "mean": 2515.8
+   },
+   "stage2": {
+    "rows": 57,
+    "max": 550,
+    "p95": 548,
+    "mean": 485.1
+   }
+  }
+ }
+}

artifacts/generated/prompt_stats/choice_id/prompt_token_stats_infra.json

@@ -0,0 +1,139 @@
+{
+ "tokenizer": "Qwen/Qwen2.5-7B-Instruct",
+ "splits": {
+  "train": {
+   "stage1": {
+    "tokens": {
+     "rows": 40,
+     "max": 2588,
+     "p95": 2587,
+     "mean": 2581.6
+    },
+    "chars": {
+     "rows": 40,
+     "max": 4978,
+     "p95": 4977,
+     "mean": 4966.6
+    }
+   },
+   "stage2": {
+    "tokens": {
+     "rows": 40,
+     "max": 316,
+     "p95": 315,
+     "mean": 294.7
+    },
+    "chars": {
+     "rows": 40,
+     "max": 884,
+     "p95": 883,
+     "mean": 854.8
+    }
+   }
+  },
+  "val": {
+   "stage1": {
+    "tokens": {
+     "rows": 15,
+     "max": 2589,
+     "p95": 2583,
+     "mean": 2579.9
+    },
+    "chars": {
+     "rows": 15,
+     "max": 4973,
+     "p95": 4973,
+     "mean": 4965.1
+    }
+   },
+   "stage2": {
+    "tokens": {
+     "rows": 15,
+     "max": 311,
+     "p95": 305,
+     "mean": 301.9
+    },
+    "chars": {
+     "rows": 15,
+     "max": 876,
+     "p95": 876,
+     "mean": 868.1
+    }
+   }
+  },
+  "test": {
+   "stage1": {
+    "tokens": {
+     "rows": 9,
+     "max": 2593,
+     "p95": 2590,
+     "mean": 2588.1
+    },
+    "chars": {
+     "rows": 9,
+     "max": 4982,
+     "p95": 4980,
+     "mean": 4976.1
+    }
+   },
+   "stage2": {
+    "tokens": {
+     "rows": 9,
+     "max": 321,
+     "p95": 318,
+     "mean": 316.1
+    },
+    "chars": {
+     "rows": 9,
+     "max": 888,
+     "p95": 886,
+     "mean": 882.1
+    }
+   }
+  }
+ },
+ "prompt_only": {
+  "train": {
+   "stage1": {
+    "rows": 40,
+    "max": 2570,
+    "p95": 2569,
+    "mean": 2562.7
+   },
+   "stage2": {
+    "rows": 40,
+    "max": 306,
+    "p95": 305,
+    "mean": 284.7
+   }
+  },
+  "val": {
+   "stage1": {
+    "rows": 15,
+    "max": 2571,
+    "p95": 2565,
+    "mean": 2561.9
+   },
+   "stage2": {
+    "rows": 15,
+    "max": 301,
+    "p95": 295,
+    "mean": 291.9
+   }
+  },
+  "test": {
+   "stage1": {
+    "rows": 9,
+    "max": 2575,
+    "p95": 2572,
+    "mean": 2570.1
+   },
+   "stage2": {
+    "rows": 9,
+    "max": 311,
+    "p95": 308,
+    "mean": 306.1
+   }
+  }
+ }
+}