{
 "VERSIONS": {
  "status": "INFO",
  "text": "11 of 18 source files identical in v1, v2, v3; differing: ['Sections/4_Methodology.tex', 'Sections/5_Experiments.tex', 'Sections/Appendix.tex', 'Tables/exp_diff_judges.tex', 'Tables/human_eval.tex', 'Tables/judge_alignment.tex', 'Tables/prompts_eval_2.tex']",
  "same": [
   "Tables/exp_idood.tex",
   "Tables/exp_main_cot_full.tex",
   "Tables/exp_otherbmks.tex",
   "Tables/exp_rag.tex",
   "Tables/exp_wr.tex",
   "Tables/main_exp.tex",
   "Tables/main_exp_cf3.tex",
   "Tables/main_exp_cot.tex",
   "Tables/prompts_agent.tex",
   "Tables/prompts_agent_2.tex",
   "Tables/prompts_eval.tex"
  ],
  "differing": {
   "Tables/exp_diff_judges.tex": {
    "v1": null,
    "v2": "c8a123416ed7",
    "v3": "c8a123416ed7"
   },
   "Tables/judge_alignment.tex": {
    "v1": null,
    "v2": "c61964c5d9d6",
    "v3": "c61964c5d9d6"
   },
   "Tables/human_eval.tex": {
    "v1": null,
    "v2": "5e9dc5fd4ea4",
    "v3": "5e9dc5fd4ea4"
   },
   "Tables/prompts_eval_2.tex": {
    "v1": "fdbd743dc55f",
    "v2": "7b36a67c86b1",
    "v3": "7b36a67c86b1"
   },
   "Sections/4_Methodology.tex": {
    "v1": "456a1d7115c3",
    "v2": "bce081a0f9a1",
    "v3": "bce081a0f9a1"
   },
   "Sections/5_Experiments.tex": {
    "v1": "9cdb744621be",
    "v2": "731554ca0572",
    "v3": "731554ca0572"
   },
   "Sections/Appendix.tex": {
    "v1": "d7c78ff9b3e5",
    "v2": "447b91748dd7",
    "v3": "447b91748dd7"
   }
  }
 },
 "T01": {
  "status": "PASS",
  "text": "main table: 21 rows, identical in v1, v2, v3"
 },
 "T02": {
  "status": "PASS",
  "text": "worker and server published.ts equal the LaTeX table: 294 means and 294 ± values, 0 differ",
  "differing": []
 },
 "T03": {
  "status": "PASS",
  "text": "published.ts records the SHA-256 of Tables/main_exp.tex (99c3cfda63aa…) and the two copies are the same file"
 },
 "AVG": {
  "status": "INFO",
  "text": "Average vs the mean of the four printed dimensions: largest gap 0.0050 (Gemini Pro); within 0.005 (rounding of one value) 17/21, within 0.01 21/21",
  "gaps": {
   "Abab7-preview": 0.005,
   "Doubao-pro": 0.0025,
   "Step-1-Flash": 0.0,
   "Step-2": 0.005,
   "GPT-3.5": 0.0,
   "GPT-4o": 0.0,
   "GPT-4o Mini": 0.0025,
   "Gemini Pro": 0.005,
   "Claude-3-Haiku": 0.005,
   "Claude-3.5-Sonnet": 0.0025,
   "Mistral-7B": 0.005,
   "Qwen-2-7B": 0.0025,
   "LLaMA-3.1-8B": 0.0025,
   "CoSER-8B": 0.005,
   "Vicuna-13B-1.5": 0.005,
   "Mixtral-8x7B": 0.005,
   "Qwen-2-72B": 0.0025,
   "LLaMA-3.1-70B": 0.0025,
   "Higgs-Llama-3-70B": 0.0025,
   "CoSER-70B": 0.0025,
   "DeepSeek-V3": 0.0025
  }
 },
 "MARKS": {
  "status": "INFO",
  "text": "bold (best overall) and underlined (best open) marks against the values: 0 mismatches",
  "mismatches": []
 },
 "SPREAD": {
  "status": "INFO",
  "text": "printed ± on the 21 rows: sc 0.13-2.46 (median 1.12), an 0.16-2.35 (median 1.09), cf 0.13-2.95 (median 1.43), sq 0.14-1.75 (median 0.88), avg 0.22-1.35 (median 0.63), bleu 0.00-0.33 (median 0.10), rouge 0.02-0.56 (median 0.09); the paper states 'averaged across three runs' and does not define ±",
  "spreads": {
   "sc": 1.12,
   "an": 1.09,
   "cf": 1.43,
   "sq": 0.88,
   "avg": 0.63,
   "bleu": 0.1,
   "rouge": 0.09
  }
 },
 "SPREAD2": {
  "status": "INFO",
  "text": "rows whose ± on Average exceeds the ± of all four dimensions: 0",
  "rows": []
 },
 "IDOOD": {
  "status": "INFO",
  "text": "table exp_idood: 21 rows; mean of in-domain and out-of-domain against the main table (equal sizes, so it must equal it if it is the same runs): Average differs by up to 0.450, mean signed -0.016; any dimension up to 0.710 (GPT-4o sq); cells within 0.01: 95/105; beyond: [('GPT-3.5', 'sc', 0.415), ('GPT-3.5', 'an', -0.085), ('GPT-3.5', 'cf', 0.195), ('GPT-3.5', 'sq', -0.13), ('GPT-3.5', 'avg', 0.1), ('GPT-4o', 'sc', -0.505), ('GPT-4o', 'an', -0.135), ('GPT-4o', 'cf', -0.45), ('GPT-4o', 'sq', -0.71), ('GPT-4o', 'avg', -0.45)]",
  "cells": [
   {
    "model": "Abab7-preview",
    "col": "sc",
    "id": 55.31,
    "ood": 58.3,
    "mean": 56.805,
    "main": 56.81,
    "diff": -0.005
   },
   {
    "model": "Abab7-preview",
    "col": "an",
    "id": 42.29,
    "ood": 46.17,
    "mean": 44.23,
    "main": 44.23,
    "diff": 0.0
   },
   {
    "model": "Abab7-preview",
    "col": "cf",
    "id": 42.94,
    "ood": 44.72,
    "mean": 43.83,
    "main": 43.83,
    "diff": 0.0
   },
   {
    "model": "Abab7-preview",
    "col": "sq",
    "id": 74.13,
    "ood": 75.54,
    "mean": 74.835,
    "main": 74.83,
    "diff": 0.005
   },
   {
    "model": "Abab7-preview",
    "col": "avg",
    "id": 53.67,
    "ood": 56.18,
    "mean": 54.925,
    "main": 54.92,
    "diff": 0.005
   },
   {
    "model": "Doubao-pro",
    "col": "sc",
    "id": 60.37,
    "ood": 61.53,
    "mean": 60.95,
    "main": 60.95,
    "diff": 0.0
   },
   {
    "model": "Doubao-pro",
    "col": "an",
    "id": 49.06,
    "ood": 50.38,
    "mean": 49.72,
    "main": 49.72,
    "diff": 0.0
   },
   {
    "model": "Doubao-pro",
    "col": "cf",
    "id": 45.76,
    "ood": 48.28,
    "mean": 47.02,
    "main": 47.02,
    "diff": -0.0
   },
   {
    "model": "Doubao-pro",
    "col": "sq",
    "id": 77.87,
    "ood": 80.69,
    "mean": 79.28,
    "main": 79.28,
    "diff": 0.0
   },
   {
    "model": "Doubao-pro",
    "col": "avg",
    "id": 58.26,
    "ood": 60.22,
    "mean": 59.24,
    "main": 59.24,
    "diff": -0.0
   },
   {
    "model": "Step-1-Flash",
    "col": "sc",
    "id": 57.1,
    "ood": 58.39,
    "mean": 57.745,
    "main": 57.75,
    "diff": -0.005
   },
   {
    "model": "Step-1-Flash",
    "col": "an",
    "id": 48.31,
    "ood": 47.94,
    "mean": 48.125,
    "main": 48.12,
    "diff": 0.005
   },
   {
    "model": "Step-1-Flash",
    "col": "cf",
    "id": 41.84,
    "ood": 47.12,
    "mean": 44.48,
    "main": 44.48,
    "diff": 0.0
   },
   {
    "model": "Step-1-Flash",
    "col": "sq",
    "id": 76.18,
    "ood": 75.67,
    "mean": 75.925,
    "main": 75.93,
    "diff": -0.005
   },
   {
    "model": "Step-1-Flash",
    "col": "avg",
    "id": 55.86,
    "ood": 57.28,
    "mean": 56.57,
    "main": 56.57,
    "diff": 0.0
   },
   {
    "model": "Step-2",
    "col": "sc",
    "id": 60.55,
    "ood": 62.3,
    "mean": 61.425,
    "main": 61.43,
    "diff": -0.005
   },
   {
    "model": "Step-2",
    "col": "an",
    "id": 48.82,
    "ood": 49.3,
    "mean": 49.06,
    "main": 49.06,
    "diff": 0.0
   },
   {
    "model": "Step-2",
    "col": "cf",
    "id": 47.9,
    "ood": 46.77,
    "mean": 47.335,
    "main": 47.33,
    "diff": 0.005
   },
   {
    "model": "Step-2",
    "col": "sq",
    "id": 77.33,
    "ood": 78.59,
    "mean": 77.96,
    "main": 77.96,
    "diff": 0.0
   },
   {
    "model": "Step-2",
    "col": "avg",
    "id": 58.65,
    "ood": 59.24,
    "mean": 58.945,
    "main": 58.94,
    "diff": 0.005
   },
   {
    "model": "GPT-3.5",
    "col": "sc",
    "id": 55.58,
    "ood": 59.69,
    "mean": 57.635,
    "main": 57.22,
    "diff": 0.415
   },
   {
    "model": "GPT-3.5",
    "col": "an",
    "id": 42.18,
    "ood": 44.25,
    "mean": 43.215,
    "main": 43.3,
    "diff": -0.085
   },
   {
    "model": "GPT-3.5",
    "col": "cf",
    "id": 40.37,
    "ood": 44.6,
    "mean": 42.485,
    "main": 42.29,
    "diff": 0.195
   },
   {
    "model": "GPT-3.5",
    "col": "sq",
    "id": 72.9,
    "ood": 74.66,
    "mean": 73.78,
    "main": 73.91,
    "diff": -0.13
   },
   {
    "model": "GPT-3.5",
    "col": "avg",
    "id": 52.76,
    "ood": 55.8,
    "mean": 54.28,
    "main": 54.18,
    "diff": 0.1
   },
   {
    "model": "GPT-4o",
    "col": "sc",
    "id": 59.88,
    "ood": 62.29,
    "mean": 61.085,
    "main": 61.59,
    "diff": -0.505
   },
   {
    "model": "GPT-4o",
    "col": "an",
    "id": 48.11,
    "ood": 49.48,
    "mean": 48.795,
    "main": 48.93,
    "diff": -0.135
   },
   {
    "model": "GPT-4o",
    "col": "cf",
    "id": 47.1,
    "ood": 49.9,
    "mean": 48.5,
    "main": 48.95,
    "diff": -0.45
   },
   {
    "model": "GPT-4o",
    "col": "sq",
    "id": 79.06,
    "ood": 80.18,
    "mean": 79.62,
    "main": 80.33,
    "diff": -0.71
   },
   {
    "model": "GPT-4o",
    "col": "avg",
    "id": 58.54,
    "ood": 60.46,
    "mean": 59.5,
    "main": 59.95,
    "diff": -0.45
   },
   {
    "model": "GPT-4o Mini",
    "col": "sc",
    "id": 59.15,
    "ood": 61.02,
    "mean": 60.085,
    "main": 60.09,
    "diff": -0.005
   },
   {
    "model": "GPT-4o Mini",
    "col": "an",
    "id": 46.94,
    "ood": 49.48,
    "mean": 48.21,
    "main": 48.21,
    "diff": -0.0
   },
   {
    "model": "GPT-4o Mini",
    "col": "cf",
    "id": 43.99,
    "ood": 45.77,
    "mean": 44.88,
    "main": 44.88,
    "diff": 0.0
   },
   {
    "model": "GPT-4o Mini",
    "col": "sq",
    "id": 77.33,
    "ood": 79.77,
    "mean": 78.55,
    "main": 78.55,
    "diff": 0.0
   },
   {
    "model": "GPT-4o Mini",
    "col": "avg",
    "id": 56.85,
    "ood": 59.01,
    "mean": 57.93,
    "main": 57.93,
    "diff": 0.0
   },
   {
    "model": "Gemini Pro",
    "col": "sc",
    "id": 57.72,
    "ood": 60.5,
    "mean": 59.11,
    "main": 59.11,
    "diff": 0.0
   },
   {
    "model": "Gemini Pro",
    "col": "an",
    "id": 50.94,
    "ood": 53.88,
    "mean": 52.41,
    "main": 52.41,
    "diff": 0.0
   },
   {
    "model": "Gemini Pro",
    "col": "cf",
    "id": 46.23,
    "ood": 49.43,
    "mean": 47.83,
    "main": 47.83,
    "diff": 0.0
   },
   {
    "model": "Gemini Pro",
    "col": "sq",
    "id": 76.22,
    "ood": 78.97,
    "mean": 77.595,
    "main": 77.59,
    "diff": 0.005
   },
   {
    "model": "Gemini Pro",
    "col": "avg",
    "id": 57.78,
    "ood": 60.69,
    "mean": 59.235,
    "main": 59.24,
    "diff": -0.005
   },
   {
    "model": "Claude-3-Haiku",
    "col": "sc",
    "id": 57.61,
    "ood": 58.74,
    "mean": 58.175,
    "main": 58.18,
    "diff": -0.005
   },
   {
    "model": "Claude-3-Haiku",
    "col": "an",
    "id": 44.97,
    "ood": 44.36,
    "mean": 44.665,
    "main": 44.66,
    "diff": 0.005
   },
   {
    "model": "Claude-3-Haiku",
    "col": "cf",
    "id": 40.61,
    "ood": 43.14,
    "mean": 41.875,
    "main": 41.88,
    "diff": -0.005
   },
   {
    "model": "Claude-3-Haiku",
    "col": "sq",
    "id": 73.52,
    "ood": 74.76,
    "mean": 74.14,
    "main": 74.14,
    "diff": 0.0
   },
   {
    "model": "Claude-3-Haiku",
    "col": "avg",
    "id": 54.18,
    "ood": 55.25,
    "mean": 54.715,
    "main": 54.71,
    "diff": 0.005
   },
   {
    "model": "Claude-3.5-Sonnet",
    "col": "sc",
    "id": 56.44,
    "ood": 58.46,
    "mean": 57.45,
    "main": 57.45,
    "diff": 0.0
   },
   {
    "model": "Claude-3.5-Sonnet",
    "col": "an",
    "id": 47.24,
    "ood": 49.75,
    "mean": 48.495,
    "main": 48.5,
    "diff": -0.005
   },
   {
    "model": "Claude-3.5-Sonnet",
    "col": "cf",
    "id": 44.89,
    "ood": 46.49,
    "mean": 45.69,
    "main": 45.69,
    "diff": 0.0
   },
   {
    "model": "Claude-3.5-Sonnet",
    "col": "sq",
    "id": 76.39,
    "ood": 78.06,
    "mean": 77.225,
    "main": 77.23,
    "diff": -0.005
   },
   {
    "model": "Claude-3.5-Sonnet",
    "col": "avg",
    "id": 56.24,
    "ood": 58.19,
    "mean": 57.215,
    "main": 57.22,
    "diff": -0.005
   },
   {
    "model": "Mistral-7B",
    "col": "sc",
    "id": 60.29,
    "ood": 59.51,
    "mean": 59.9,
    "main": 59.9,
    "diff": 0.0
   },
   {
    "model": "Mistral-7B",
    "col": "an",
    "id": 38.98,
    "ood": 41.02,
    "mean": 40.0,
    "main": 40.0,
    "diff": 0.0
   },
   {
    "model": "Mistral-7B",
    "col": "cf",
    "id": 42.93,
    "ood": 46.57,
    "mean": 44.75,
    "main": 44.75,
    "diff": 0.0
   },
   {
    "model": "Mistral-7B",
    "col": "sq",
    "id": 62.2,
    "ood": 61.65,
    "mean": 61.925,
    "main": 61.93,
    "diff": -0.005
   },
   {
    "model": "Mistral-7B",
    "col": "avg",
    "id": 51.1,
    "ood": 52.19,
    "mean": 51.645,
    "main": 51.64,
    "diff": 0.005
   },
   {
    "model": "Qwen-2-7B",
    "col": "sc",
    "id": 50.77,
    "ood": 53.14,
    "mean": 51.955,
    "main": 51.96,
    "diff": -0.005
   },
   {
    "model": "Qwen-2-7B",
    "col": "an",
    "id": 34.17,
    "ood": 36.79,
    "mean": 35.48,
    "main": 35.48,
    "diff": 0.0
   },
   {
    "model": "Qwen-2-7B",
    "col": "cf",
    "id": 29.92,
    "ood": 33.09,
    "mean": 31.505,
    "main": 31.51,
    "diff": -0.005
   },
   {
    "model": "Qwen-2-7B",
    "col": "sq",
    "id": 62.58,
    "ood": 63.79,
    "mean": 63.185,
    "main": 63.18,
    "diff": 0.005
   },
   {
    "model": "Qwen-2-7B",
    "col": "avg",
    "id": 44.36,
    "ood": 46.7,
    "mean": 45.53,
    "main": 45.53,
    "diff": 0.0
   },
   {
    "model": "LLaMA-3.1-8B",
    "col": "sc",
    "id": 53.0,
    "ood": 55.2,
    "mean": 54.1,
    "main": 54.1,
    "diff": 0.0
   },
   {
    "model": "LLaMA-3.1-8B",
    "col": "an",
    "id": 43.64,
    "ood": 47.08,
    "mean": 45.36,
    "main": 45.36,
    "diff": 0.0
   },
   {
    "model": "LLaMA-3.1-8B",
    "col": "cf",
    "id": 39.05,
    "ood": 41.38,
    "mean": 40.215,
    "main": 40.22,
    "diff": -0.005
   },
   {
    "model": "LLaMA-3.1-8B",
    "col": "sq",
    "id": 71.34,
    "ood": 73.23,
    "mean": 72.285,
    "main": 72.29,
    "diff": -0.005
   },
   {
    "model": "LLaMA-3.1-8B",
    "col": "avg",
    "id": 51.76,
    "ood": 54.22,
    "mean": 52.99,
    "main": 52.99,
    "diff": -0.0
   },
   {
    "model": "CoSER-8B",
    "col": "sc",
    "id": 58.56,
    "ood": 58.66,
    "mean": 58.61,
    "main": 58.61,
    "diff": 0.0
   },
   {
    "model": "CoSER-8B",
    "col": "an",
    "id": 46.78,
    "ood": 47.69,
    "mean": 47.235,
    "main": 47.23,
    "diff": 0.005
   },
   {
    "model": "CoSER-8B",
    "col": "cf",
    "id": 45.78,
    "ood": 48.03,
    "mean": 46.905,
    "main": 46.9,
    "diff": 0.005
   },
   {
    "model": "CoSER-8B",
    "col": "sq",
    "id": 73.38,
    "ood": 72.71,
    "mean": 73.045,
    "main": 73.04,
    "diff": 0.005
   },
   {
    "model": "CoSER-8B",
    "col": "avg",
    "id": 56.12,
    "ood": 56.77,
    "mean": 56.445,
    "main": 56.45,
    "diff": -0.005
   },
   {
    "model": "Vicuna-13B-1.5",
    "col": "sc",
    "id": 51.84,
    "ood": 53.66,
    "mean": 52.75,
    "main": 52.75,
    "diff": 0.0
   },
   {
    "model": "Vicuna-13B-1.5",
    "col": "an",
    "id": 38.88,
    "ood": 39.35,
    "mean": 39.115,
    "main": 39.12,
    "diff": -0.005
   },
   {
    "model": "Vicuna-13B-1.5",
    "col": "cf",
    "id": 36.39,
    "ood": 39.69,
    "mean": 38.04,
    "main": 38.04,
    "diff": 0.0
   },
   {
    "model": "Vicuna-13B-1.5",
    "col": "sq",
    "id": 58.15,
    "ood": 62.71,
    "mean": 60.43,
    "main": 60.43,
    "diff": 0.0
   },
   {
    "model": "Vicuna-13B-1.5",
    "col": "avg",
    "id": 46.31,
    "ood": 48.85,
    "mean": 47.58,
    "main": 47.58,
    "diff": 0.0
   },
   {
    "model": "Mixtral-8x7B",
    "col": "sc",
    "id": 51.18,
    "ood": 51.32,
    "mean": 51.25,
    "main": 51.25,
    "diff": 0.0
   },
   {
    "model": "Mixtral-8x7B",
    "col": "an",
    "id": 38.76,
    "ood": 38.13,
    "mean": 38.445,
    "main": 38.44,
    "diff": 0.005
   },
   {
    "model": "Mixtral-8x7B",
    "col": "cf",
    "id": 34.37,
    "ood": 39.48,
    "mean": 36.925,
    "main": 36.92,
    "diff": 0.005
   },
   {
    "model": "Mixtral-8x7B",
    "col": "sq",
    "id": 66.44,
    "ood": 68.93,
    "mean": 67.685,
    "main": 67.69,
    "diff": -0.005
   },
   {
    "model": "Mixtral-8x7B",
    "col": "avg",
    "id": 47.69,
    "ood": 49.47,
    "mean": 48.58,
    "main": 48.58,
    "diff": 0.0
   },
   {
    "model": "Qwen-2-72B",
    "col": "sc",
    "id": 56.34,
    "ood": 59.15,
    "mean": 57.745,
    "main": 57.75,
    "diff": -0.005
   },
   {
    "model": "Qwen-2-72B",
    "col": "an",
    "id": 46.19,
    "ood": 48.37,
    "mean": 47.28,
    "main": 47.28,
    "diff": 0.0
   },
   {
    "model": "Qwen-2-72B",
    "col": "cf",
    "id": 45.59,
    "ood": 47.65,
    "mean": 46.62,
    "main": 46.62,
    "diff": 0.0
   },
   {
    "model": "Qwen-2-72B",
    "col": "sq",
    "id": 75.68,
    "ood": 77.52,
    "mean": 76.6,
    "main": 76.6,
    "diff": 0.0
   },
   {
    "model": "Qwen-2-72B",
    "col": "avg",
    "id": 55.95,
    "ood": 58.17,
    "mean": 57.06,
    "main": 57.06,
    "diff": 0.0
   },
   {
    "model": "LLaMA-3.1-70B",
    "col": "sc",
    "id": 55.44,
    "ood": 59.48,
    "mean": 57.46,
    "main": 57.46,
    "diff": -0.0
   },
   {
    "model": "LLaMA-3.1-70B",
    "col": "an",
    "id": 44.19,
    "ood": 47.72,
    "mean": 45.955,
    "main": 45.95,
    "diff": 0.005
   },
   {
    "model": "LLaMA-3.1-70B",
    "col": "cf",
    "id": 42.67,
    "ood": 44.78,
    "mean": 43.725,
    "main": 43.72,
    "diff": 0.005
   },
   {
    "model": "LLaMA-3.1-70B",
    "col": "sq",
    "id": 73.9,
    "ood": 75.78,
    "mean": 74.84,
    "main": 74.84,
    "diff": 0.0
   },
   {
    "model": "LLaMA-3.1-70B",
    "col": "avg",
    "id": 54.05,
    "ood": 56.94,
    "mean": 55.495,
    "main": 55.49,
    "diff": 0.005
   },
   {
    "model": "Higgs-Llama-3-70B",
    "col": "sc",
    "id": 55.85,
    "ood": 58.35,
    "mean": 57.1,
    "main": 57.1,
    "diff": 0.0
   },
   {
    "model": "Higgs-Llama-3-70B",
    "col": "an",
    "id": 41.18,
    "ood": 46.45,
    "mean": 43.815,
    "main": 43.82,
    "diff": -0.005
   },
   {
    "model": "Higgs-Llama-3-70B",
    "col": "cf",
    "id": 39.79,
    "ood": 45.04,
    "mean": 42.415,
    "main": 42.41,
    "diff": 0.005
   },
   {
    "model": "Higgs-Llama-3-70B",
    "col": "sq",
    "id": 73.77,
    "ood": 77.48,
    "mean": 75.625,
    "main": 75.62,
    "diff": 0.005
   },
   {
    "model": "Higgs-Llama-3-70B",
    "col": "avg",
    "id": 52.65,
    "ood": 56.83,
    "mean": 54.74,
    "main": 54.74,
    "diff": -0.0
   },
   {
    "model": "CoSER-70B",
    "col": "sc",
    "id": 57.77,
    "ood": 59.56,
    "mean": 58.665,
    "main": 58.66,
    "diff": 0.005
   },
   {
    "model": "CoSER-70B",
    "col": "an",
    "id": 51.6,
    "ood": 55.06,
    "mean": 53.33,
    "main": 53.33,
    "diff": 0.0
   },
   {
    "model": "CoSER-70B",
    "col": "cf",
    "id": 45.82,
    "ood": 51.67,
    "mean": 48.745,
    "main": 48.75,
    "diff": -0.005
   },
   {
    "model": "CoSER-70B",
    "col": "sq",
    "id": 74.27,
    "ood": 76.71,
    "mean": 75.49,
    "main": 75.49,
    "diff": 0.0
   },
   {
    "model": "CoSER-70B",
    "col": "avg",
    "id": 57.37,
    "ood": 60.75,
    "mean": 59.06,
    "main": 59.06,
    "diff": 0.0
   },
   {
    "model": "DeepSeek-V3",
    "col": "sc",
    "id": 55.36,
    "ood": 57.45,
    "mean": 56.405,
    "main": 56.4,
    "diff": 0.005
   },
   {
    "model": "DeepSeek-V3",
    "col": "an",
    "id": 47.55,
    "ood": 48.19,
    "mean": 47.87,
    "main": 47.87,
    "diff": 0.0
   },
   {
    "model": "DeepSeek-V3",
    "col": "cf",
    "id": 43.1,
    "ood": 44.93,
    "mean": 44.015,
    "main": 44.02,
    "diff": -0.005
   },
   {
    "model": "DeepSeek-V3",
    "col": "sq",
    "id": 74.91,
    "ood": 78.41,
    "mean": 76.66,
    "main": 76.66,
    "diff": 0.0
   },
   {
    "model": "DeepSeek-V3",
    "col": "avg",
    "id": 55.23,
    "ood": 57.24,
    "mean": 56.235,
    "main": 56.24,
    "diff": -0.005
   }
  ]
 },
 "JUDGES": {
  "status": "INFO",
  "text": "table exp_diff_judges: the GPT-4o column equals the in-domain Average of exp_idood for 7/7 models, the full-test Average for 0/7; the caption does not say so",
  "rows": {
   "GPT-3.5": {
    "judges_table": 52.8,
    "main_avg": 54.18,
    "in_domain_avg": 52.76
   },
   "LLaMA-3.1-8B": {
    "judges_table": 51.8,
    "main_avg": 52.99,
    "in_domain_avg": 51.76
   },
   "Abab7-preview": {
    "judges_table": 53.7,
    "main_avg": 54.92,
    "in_domain_avg": 53.67
   },
   "CoSER-8B": {
    "judges_table": 56.1,
    "main_avg": 56.45,
    "in_domain_avg": 56.12
   },
   "GPT-4o": {
    "judges_table": 58.5,
    "main_avg": 59.95,
    "in_domain_avg": 58.54
   },
   "Claude-3.5-Sonnet": {
    "judges_table": 56.2,
    "main_avg": 57.22,
    "in_domain_avg": 56.24
   },
   "CoSER-70B": {
    "judges_table": 57.4,
    "main_avg": 59.06,
    "in_domain_avg": 57.37
   }
  }
 },
 "ABL": {
  "status": "INFO",
  "text": "ablation table: Standard equals the main table's Average for 6/6 models; removing motivations raises the score for ['CoSER-8B'] although the text says improvements are 'consistent across all models'",
  "rows": {
   "GPT-4o": [
    59.95,
    59.95
   ],
   "Qwen-2-72B": [
    57.06,
    57.06
   ],
   "LLaMA-3.1-70B": [
    55.49,
    55.49
   ],
   "CoSER-70B": [
    59.06,
    59.06
   ],
   "LLaMA-3.1-8B": [
    52.99,
    52.99
   ],
   "CoSER-8B": [
    56.45,
    56.45
   ]
  }
 },
 "CLAIMS": {
  "status": "INFO",
  "text": "Average above 57%: ['Claude-3.5-Sonnet', 'CoSER-70B', 'Doubao-pro', 'GPT-4o', 'GPT-4o Mini', 'Gemini Pro', 'Qwen-2-72B', 'Step-2'] (the text lists GPT-4o, Gemini Pro, Claude-3.5-Sonnet, Doubao-pro, Step-2, Qwen-2-72B, CoSER-70B); GPT-4o Mini at 57.93 also qualifies; Claim '58% above the second-best on BLEU': CoSER-70B 10.1 / best other Doubao-pro 6.38 = 0.583; Qwen-2 72B-7B gap 11.53"
 },
 "FORMULA": {
  "status": "INFO",
  "text": "initial score in Methodology v3: True; in Appendix v3 (length correction): False (still 100 − Σv); regression quoted: True; in v1 Methodology: False"
 },
 "EX-100-5S+1.5R": {
  "status": "INFO",
  "text": "released evaluation of 3 scenes × 4 dimensions: the stored score equals clip(100-5S+1.5R) for 12/12"
 },
 "EX-100-S+1.5R": {
  "status": "INFO",
  "text": "released evaluation of 3 scenes × 4 dimensions: the stored score equals clip(100-S+1.5R) for 0/12"
 },
 "EX-100-5S": {
  "status": "INFO",
  "text": "released evaluation of 3 scenes × 4 dimensions: the stored score equals clip(100-5S) for 0/12"
 },
 "TEST": {
  "status": "INFO",
  "text": "test set: SHA-256 eb175779d1d5adf99c893ff1f82de9b18ada912d3f385b3f5419195afdfb374a; 200 scenes, 100 id, 100 ood; 101 books (69 id, 32 ood); speaking characters per scene 1-5 (mean 2.40, 479 in all), 451 with a motivation; original lines per scene 9-32 (median 12.0), 7 scenes longer than the 20-line limit; major characters per scene 1-5; Environment listed as a speaker in 130; speakers without any profile text 13"
 },
 "EXP-FILES": {
  "status": "INFO",
  "text": "released result files under exp/: ['exp/evaluation/test_set_gpt-4o.json', 'exp/simulation/test_set_gpt-4o-mini_rag=expr3_conv1.json', 'exp/simulation/test_set_gpt-4o.json', 'exp/simulation/test_set_gpt-4o_rag=expr3_conv1.json']"
 }
}