Files
natural-memory-nm21/_smoke_scorecard_v5.json
WpyQwq 643e22ecb9 Natural Memory NM2.1: 记忆路由器分叉、数据集缺陷修复与全轴评测证据
- 引入 MemoryRouterXL 与 v5/v6 流式多线程训练/编码管线
- 修复 prepare_memory_router_dataset 候选池重建缺陷(mega 家族 3568x 加速,输出逐字节相同)
- 修复 v5 被破坏的拒答与多跳标签(train 未知样本 319 -> 16319,multi_hop 平均正例 1.00 -> 2.00)
- 同存储预算下 V2-128 v6 逐轴 22/22 通过:Top-1 41.12% -> 94.62%,未知拒答 0.00% -> 100.00%
- 记录三条被实测推翻的显然优化(logits_to_keep=1 反而慢 55%、XL 容量未带来收益)
- 记忆手术跨架构可移植性 14/14,读写关闭时与原生模型逐位相同
2026-09-19 11:11:31 +08:00

832 lines
27 KiB
JSON

{
"V2-128 deployed": {
"checkpoint": "H:\\Memory\\dynamic_memory_lab\\checkpoints\\natural_memory_v2_qwen_router_entities\\memory_router_v2.pt",
"router": {
"kind": "router_v2",
"step": null,
"arch_config": {
"arch": "router_v2",
"hidden_size": 2560,
"router_dim": 128,
"num_heads": 8,
"max_hops": 3
},
"parameters": 2037774,
"checkpoint_bytes": 8157561
},
"storage": {
"address_bytes_per_record": 512,
"address_mb_per_1m_records": 512,
"checkpoint_bytes": 8157561
},
"latency": {
"cpu": {
"single_query_latency_ms_mean": 0.4756599897518754,
"single_query_latency_ms_p50": 0.5036999937146902,
"single_query_latency_ms_p95": 0.6246999837458134,
"queries_per_second": 2102.3420542931153,
"samples": 5
}
},
"metrics": {
"episodes": 21920,
"answerable_episodes": 21814,
"unknown_episodes": 106,
"top1": 0.37274227560282386,
"recall1": 0.37274227560282386,
"recall3": 0.5745392866966168,
"recall5": 0.7406252865132483,
"recall8": 0.8605941138718254,
"mrr": 0.4984150474242403,
"ndcg3": 0.46099764820049244,
"mean_first_positive_rank": 8.257541028697167,
"all_evidence_in_top3": 0.5159988997891263,
"multi_positive_episodes": 2000,
"all_evidence_in_top3_multi": 0.436,
"hop_accuracy": 0.7322992700729927,
"hop_accuracy_answerable": 0.7358577060603282,
"hop_under_prediction": 0.1299165673420739,
"hop_over_prediction": 0.13422572659759788,
"mean_score_margin": -10.438775865636897,
"median_score_margin": -12.105871319770813,
"negative_margin_rate": 0.6272577243971761,
"hop_confusion": {
"true_0_pred_0": 0,
"true_0_pred_1": 42,
"true_0_pred_2": 64,
"true_1_pred_0": 834,
"true_1_pred_1": 16052,
"true_1_pred_2": 2928,
"true_2_pred_0": 0,
"true_2_pred_1": 2000,
"true_2_pred_2": 0
},
"known_mean_need_prob": 0.9804023649948944,
"unknown_mean_need_prob": 0.9999472358316746,
"thr0.30": {
"need_precision": 0.9951642335766423,
"need_recall": 1.0,
"need_f1": 0.9975762564595051,
"specificity_unknown_refusal": 0.0,
"abstention_accuracy": 0.9951642335766423,
"known_question_refusal_rate": 0.0,
"unknown_question_read_rate": 1.0,
"counts": {
"tp": 21814,
"tn": 0,
"fp": 106,
"fn": 0
}
},
"thr0.40": {
"need_precision": 0.9951642335766423,
"need_recall": 1.0,
"need_f1": 0.9975762564595051,
"specificity_unknown_refusal": 0.0,
"abstention_accuracy": 0.9951642335766423,
"known_question_refusal_rate": 0.0,
"unknown_question_read_rate": 1.0,
"counts": {
"tp": 21814,
"tn": 0,
"fp": 106,
"fn": 0
}
},
"thr0.50": {
"need_precision": 0.99515716374269,
"need_recall": 0.9985330521683322,
"need_f1": 0.9968422497826185,
"specificity_unknown_refusal": 0.0,
"abstention_accuracy": 0.9937043795620438,
"known_question_refusal_rate": 0.0014669478316677363,
"unknown_question_read_rate": 1.0,
"counts": {
"tp": 21782,
"tn": 0,
"fp": 106,
"fn": 32
}
},
"thr0.60": {
"need_precision": 0.995134936662383,
"need_recall": 0.9939488401943706,
"need_f1": 0.994541534791982,
"specificity_unknown_refusal": 0.0,
"abstention_accuracy": 0.9891423357664234,
"known_question_refusal_rate": 0.0060511598056294125,
"unknown_question_read_rate": 1.0,
"counts": {
"tp": 21682,
"tn": 0,
"fp": 106,
"fn": 132
}
},
"thr0.70": {
"need_precision": 0.9951266608431796,
"need_recall": 0.9922526817640047,
"need_f1": 0.9936875932514634,
"specificity_unknown_refusal": 0.0,
"abstention_accuracy": 0.9874543795620438,
"known_question_refusal_rate": 0.0077473182359952325,
"unknown_question_read_rate": 1.0,
"counts": {
"tp": 21645,
"tn": 0,
"fp": 106,
"fn": 169
}
},
"thr0.80": {
"need_precision": 0.9951118284528476,
"need_recall": 0.9892271018611901,
"need_f1": 0.9921607393273408,
"specificity_unknown_refusal": 0.0,
"abstention_accuracy": 0.9844434306569343,
"known_question_refusal_rate": 0.010772898138809939,
"unknown_question_read_rate": 1.0,
"counts": {
"tp": 21579,
"tn": 0,
"fp": 106,
"fn": 235
}
}
},
"by_family": {
"benchmark_qa": {
"episodes": 64,
"answerable_episodes": 0,
"unknown_episodes": 64,
"top1": 0.0,
"recall1": 0.0,
"recall3": 0.0,
"recall5": 0.0,
"recall8": 0.0,
"mrr": 0.0,
"ndcg3": 0.0,
"mean_first_positive_rank": 0.0,
"all_evidence_in_top3": 0.0,
"multi_positive_episodes": 0,
"all_evidence_in_top3_multi": 0.0,
"hop_accuracy": 0.0,
"hop_accuracy_answerable": 0.0,
"hop_under_prediction": 0.0,
"hop_over_prediction": 0.0,
"mean_score_margin": 0.0,
"median_score_margin": 0.0,
"negative_margin_rate": 0.0,
"hop_confusion": {
"true_0_pred_0": 0,
"true_0_pred_2": 64
},
"known_mean_need_prob": 0.0,
"unknown_mean_need_prob": 0.9999341862276196,
"thr0.50": {
"need_precision": 0.0,
"need_recall": 0.0,
"need_f1": 0.0,
"specificity_unknown_refusal": 0.0,
"abstention_accuracy": 0.0,
"known_question_refusal_rate": 0.0,
"unknown_question_read_rate": 1.0,
"counts": {
"tp": 0,
"tn": 0,
"fp": 64,
"fn": 0
}
}
},
"mega_validation": {
"episodes": 20000,
"answerable_episodes": 20000,
"unknown_episodes": 0,
"top1": 0.39425,
"recall1": 0.39425,
"recall3": 0.6039,
"recall5": 0.7746,
"recall8": 0.88695,
"mrr": 0.5189064291859179,
"ndcg3": 0.48454538178459833,
"mean_first_positive_rank": 8.22755,
"all_evidence_in_top3": 0.54005,
"multi_positive_episodes": 2000,
"all_evidence_in_top3_multi": 0.436,
"hop_accuracy": 0.74955,
"hop_accuracy_answerable": 0.74955,
"hop_under_prediction": 0.11285,
"hop_over_prediction": 0.1376,
"mean_score_margin": -9.574584903246164,
"median_score_margin": -10.816837549209595,
"negative_margin_rate": 0.60575,
"hop_confusion": {
"true_1_pred_0": 257,
"true_1_pred_1": 14991,
"true_1_pred_2": 2752,
"true_2_pred_0": 0,
"true_2_pred_1": 2000,
"true_2_pred_2": 0
},
"known_mean_need_prob": 0.9854895650088787,
"unknown_mean_need_prob": 0.0,
"thr0.50": {
"need_precision": 1.0,
"need_recall": 1.0,
"need_f1": 1.0,
"specificity_unknown_refusal": 0.0,
"abstention_accuracy": 1.0,
"known_question_refusal_rate": 0.0,
"unknown_question_read_rate": 0.0,
"counts": {
"tp": 20000,
"tn": 0,
"fp": 0,
"fn": 0
}
}
},
"memory_policy": {
"episodes": 1728,
"answerable_episodes": 1707,
"unknown_episodes": 21,
"top1": 0.14411247803163443,
"recall1": 0.14411247803163443,
"recall3": 0.26362038664323373,
"recall5": 0.380199179847686,
"recall8": 0.5752782659636789,
"mrr": 0.2814257926451813,
"ndcg3": 0.21245701956649282,
"mean_first_positive_rank": 8.519625073227886,
"all_evidence_in_top3": 0.26362038664323373,
"multi_positive_episodes": 0,
"all_evidence_in_top3_multi": 0.0,
"hop_accuracy": 0.5740740740740741,
"hop_accuracy_answerable": 0.5811364967779731,
"hop_under_prediction": 0.3380199179847686,
"hop_over_prediction": 0.08084358523725835,
"mean_score_margin": -19.398099298226114,
"median_score_margin": -18.179970741271973,
"negative_margin_rate": 0.8558875219683656,
"hop_confusion": {
"true_0_pred_0": 0,
"true_0_pred_1": 21,
"true_0_pred_2": 0,
"true_1_pred_0": 577,
"true_1_pred_1": 992,
"true_1_pred_2": 138
},
"known_mean_need_prob": 0.9195722369471697,
"unknown_mean_need_prob": 0.9999671209426153,
"thr0.50": {
"need_precision": 0.9876179245283019,
"need_recall": 0.981253661394259,
"need_f1": 0.9844255069056715,
"specificity_unknown_refusal": 0.0,
"abstention_accuracy": 0.9693287037037037,
"known_question_refusal_rate": 0.018746338605741066,
"unknown_question_read_rate": 1.0,
"counts": {
"tp": 1675,
"tn": 0,
"fp": 21,
"fn": 32
}
}
},
"native_memory": {
"episodes": 128,
"answerable_episodes": 107,
"unknown_episodes": 21,
"top1": 0.0,
"recall1": 0.0,
"recall3": 0.04672897196261682,
"recall5": 0.14018691588785046,
"recall8": 0.48598130841121495,
"mrr": 0.12993862381957846,
"ndcg3": 0.024588128538051007,
"mean_first_positive_rank": 9.682242990654206,
"all_evidence_in_top3": 0.04672897196261682,
"multi_positive_episodes": 0,
"all_evidence_in_top3_multi": 0.0,
"hop_accuracy": 0.5390625,
"hop_accuracy_answerable": 0.6448598130841121,
"hop_under_prediction": 0.0,
"hop_over_prediction": 0.35514018691588783,
"mean_score_margin": -29.03928192530837,
"median_score_margin": -29.07152795791626,
"negative_margin_rate": 1.0,
"hop_confusion": {
"true_0_pred_0": 0,
"true_0_pred_1": 21,
"true_0_pred_2": 0,
"true_1_pred_0": 0,
"true_1_pred_1": 69,
"true_1_pred_2": 38
},
"known_mean_need_prob": 0.9999633771236812,
"unknown_mean_need_prob": 0.9999671209426153,
"thr0.50": {
"need_precision": 0.8359375,
"need_recall": 1.0,
"need_f1": 0.9106382978723404,
"specificity_unknown_refusal": 0.0,
"abstention_accuracy": 0.8359375,
"known_question_refusal_rate": 0.0,
"unknown_question_read_rate": 1.0,
"counts": {
"tp": 107,
"tn": 0,
"fp": 21,
"fn": 0
}
}
}
},
"by_category": {
"conflict_update": {
"episodes": 2000,
"answerable_episodes": 2000,
"unknown_episodes": 0,
"top1": 0.8285,
"recall1": 0.8285,
"recall3": 0.968,
"recall5": 0.9915,
"recall8": 1.0,
"mrr": 0.9000553571428571,
"ndcg3": 0.9126522728928603,
"mean_first_positive_rank": 1.2975,
"all_evidence_in_top3": 0.968,
"multi_positive_episodes": 0,
"all_evidence_in_top3_multi": 0.0,
"hop_accuracy": 0.4955,
"hop_accuracy_answerable": 0.4955,
"hop_under_prediction": 0.1285,
"hop_over_prediction": 0.376,
"mean_score_margin": 23.08462015709281,
"median_score_margin": 23.422454118728638,
"negative_margin_rate": 0.1715,
"hop_confusion": {
"true_1_pred_0": 257,
"true_1_pred_1": 991,
"true_1_pred_2": 752
},
"known_mean_need_prob": 0.9764632487297058,
"unknown_mean_need_prob": 0.0,
"thr0.50": {
"need_precision": 1.0,
"need_recall": 1.0,
"need_f1": 1.0,
"specificity_unknown_refusal": 0.0,
"abstention_accuracy": 1.0,
"known_question_refusal_rate": 0.0,
"unknown_question_read_rate": 0.0,
"counts": {
"tp": 2000,
"tn": 0,
"fp": 0,
"fn": 0
}
}
},
"distractor_128": {
"episodes": 2000,
"answerable_episodes": 2000,
"unknown_episodes": 0,
"top1": 0.2455,
"recall1": 0.2455,
"recall3": 0.375,
"recall5": 0.539,
"recall8": 0.632,
"mrr": 0.36134907557720053,
"ndcg3": 0.3170583471857158,
"mean_first_positive_rank": 13.3785,
"all_evidence_in_top3": 0.375,
"multi_positive_episodes": 0,
"all_evidence_in_top3_multi": 0.0,
"hop_accuracy": 1.0,
"hop_accuracy_answerable": 1.0,
"hop_under_prediction": 0.0,
"hop_over_prediction": 0.0,
"mean_score_margin": -23.816504290685057,
"median_score_margin": -35.661601066589355,
"negative_margin_rate": 0.7545,
"hop_confusion": {
"true_1_pred_1": 2000
},
"known_mean_need_prob": 0.9723067943453789,
"unknown_mean_need_prob": 0.0,
"thr0.50": {
"need_precision": 1.0,
"need_recall": 1.0,
"need_f1": 1.0,
"specificity_unknown_refusal": 0.0,
"abstention_accuracy": 1.0,
"known_question_refusal_rate": 0.0,
"unknown_question_read_rate": 0.0,
"counts": {
"tp": 2000,
"tn": 0,
"fp": 0,
"fn": 0
}
}
},
"distractor_32": {
"episodes": 2000,
"answerable_episodes": 2000,
"unknown_episodes": 0,
"top1": 0.238,
"recall1": 0.238,
"recall3": 0.3575,
"recall5": 0.5285,
"recall8": 0.64,
"mrr": 0.3534111817914967,
"ndcg3": 0.30423102280178715,
"mean_first_positive_rank": 13.3855,
"all_evidence_in_top3": 0.3575,
"multi_positive_episodes": 0,
"all_evidence_in_top3_multi": 0.0,
"hop_accuracy": 1.0,
"hop_accuracy_answerable": 1.0,
"hop_under_prediction": 0.0,
"hop_over_prediction": 0.0,
"mean_score_margin": -24.995892224468292,
"median_score_margin": -35.90759539604187,
"negative_margin_rate": 0.762,
"hop_confusion": {
"true_1_pred_1": 2000
},
"known_mean_need_prob": 0.9724746745526791,
"unknown_mean_need_prob": 0.0,
"thr0.50": {
"need_precision": 1.0,
"need_recall": 1.0,
"need_f1": 1.0,
"specificity_unknown_refusal": 0.0,
"abstention_accuracy": 1.0,
"known_question_refusal_rate": 0.0,
"unknown_question_read_rate": 0.0,
"counts": {
"tp": 2000,
"tn": 0,
"fp": 0,
"fn": 0
}
}
},
"forget_correction": {
"episodes": 2000,
"answerable_episodes": 2000,
"unknown_episodes": 0,
"top1": 0.416,
"recall1": 0.416,
"recall3": 1.0745,
"recall5": 1.532,
"recall8": 1.909,
"mrr": 0.5771349386724387,
"ndcg3": 0.4913475872584595,
"mean_first_positive_rank": 2.921,
"all_evidence_in_top3": 0.436,
"multi_positive_episodes": 2000,
"all_evidence_in_top3_multi": 0.436,
"hop_accuracy": 0.0,
"hop_accuracy_answerable": 0.0,
"hop_under_prediction": 1.0,
"hop_over_prediction": 0.0,
"mean_score_margin": 4.576246764823795,
"median_score_margin": -5.306148529052734,
"negative_margin_rate": 0.584,
"hop_confusion": {
"true_2_pred_1": 2000,
"true_2_pred_2": 0
},
"known_mean_need_prob": 0.99774328109622,
"unknown_mean_need_prob": 0.0,
"thr0.50": {
"need_precision": 1.0,
"need_recall": 1.0,
"need_f1": 1.0,
"specificity_unknown_refusal": 0.0,
"abstention_accuracy": 1.0,
"known_question_refusal_rate": 0.0,
"unknown_question_read_rate": 0.0,
"counts": {
"tp": 2000,
"tn": 0,
"fp": 0,
"fn": 0
}
}
},
"long_context": {
"episodes": 2000,
"answerable_episodes": 2000,
"unknown_episodes": 0,
"top1": 0.2345,
"recall1": 0.2345,
"recall3": 0.2865,
"recall5": 0.3325,
"recall8": 0.3705,
"mrr": 0.2950555862194011,
"ndcg3": 0.26455882236071515,
"mean_first_positive_rank": 19.348,
"all_evidence_in_top3": 0.2865,
"multi_positive_episodes": 0,
"all_evidence_in_top3_multi": 0.0,
"hop_accuracy": 1.0,
"hop_accuracy_answerable": 1.0,
"hop_under_prediction": 0.0,
"hop_over_prediction": 0.0,
"mean_score_margin": -15.633986071705818,
"median_score_margin": -15.739282608032227,
"negative_margin_rate": 0.7655,
"hop_confusion": {
"true_1_pred_1": 2000
},
"known_mean_need_prob": 0.9875293919146061,
"unknown_mean_need_prob": 0.0,
"thr0.50": {
"need_precision": 1.0,
"need_recall": 1.0,
"need_f1": 1.0,
"specificity_unknown_refusal": 0.0,
"abstention_accuracy": 1.0,
"known_question_refusal_rate": 0.0,
"unknown_question_read_rate": 0.0,
"counts": {
"tp": 2000,
"tn": 0,
"fp": 0,
"fn": 0
}
}
},
"multi_hop": {
"episodes": 2000,
"answerable_episodes": 2000,
"unknown_episodes": 0,
"top1": 0.715,
"recall1": 0.715,
"recall3": 0.9805,
"recall5": 0.998,
"recall8": 0.999,
"mrr": 0.8446400793650793,
"ndcg3": 0.8766200106625064,
"mean_first_positive_rank": 1.383,
"all_evidence_in_top3": 0.9805,
"multi_positive_episodes": 0,
"all_evidence_in_top3_multi": 0.0,
"hop_accuracy": 0.0,
"hop_accuracy_answerable": 0.0,
"hop_under_prediction": 0.0,
"hop_over_prediction": 1.0,
"mean_score_margin": 3.2684113913476467,
"median_score_margin": 5.575284242630005,
"negative_margin_rate": 0.285,
"hop_confusion": {
"true_1_pred_1": 0,
"true_1_pred_2": 2000
},
"known_mean_need_prob": 0.9993210689723492,
"unknown_mean_need_prob": 0.0,
"thr0.50": {
"need_precision": 1.0,
"need_recall": 1.0,
"need_f1": 1.0,
"specificity_unknown_refusal": 0.0,
"abstention_accuracy": 1.0,
"known_question_refusal_rate": 0.0,
"unknown_question_read_rate": 0.0,
"counts": {
"tp": 2000,
"tn": 0,
"fp": 0,
"fn": 0
}
}
},
"paraphrase": {
"episodes": 2000,
"answerable_episodes": 2000,
"unknown_episodes": 0,
"top1": 0.4255,
"recall1": 0.4255,
"recall3": 0.605,
"recall5": 0.7305,
"recall8": 0.809,
"mrr": 0.5507020870945611,
"ndcg3": 0.5297832026464318,
"mean_first_positive_rank": 7.688,
"all_evidence_in_top3": 0.605,
"multi_positive_episodes": 0,
"all_evidence_in_top3_multi": 0.0,
"hop_accuracy": 1.0,
"hop_accuracy_answerable": 1.0,
"hop_under_prediction": 0.0,
"hop_over_prediction": 0.0,
"mean_score_margin": -4.418384120300412,
"median_score_margin": -5.730679512023926,
"negative_margin_rate": 0.5745,
"hop_confusion": {
"true_1_pred_1": 2000
},
"known_mean_need_prob": 0.9880377072393894,
"unknown_mean_need_prob": 0.0,
"thr0.50": {
"need_precision": 1.0,
"need_recall": 1.0,
"need_f1": 1.0,
"specificity_unknown_refusal": 0.0,
"abstention_accuracy": 1.0,
"known_question_refusal_rate": 0.0,
"unknown_question_read_rate": 0.0,
"counts": {
"tp": 2000,
"tn": 0,
"fp": 0,
"fn": 0
}
}
},
"random_position": {
"episodes": 2000,
"answerable_episodes": 2000,
"unknown_episodes": 0,
"top1": 0.2755,
"recall1": 0.2755,
"recall3": 0.474,
"recall5": 0.7665,
"recall8": 0.9335,
"mrr": 0.4512681556346879,
"ndcg3": 0.38633728319107397,
"mean_first_positive_rank": 4.9905,
"all_evidence_in_top3": 0.474,
"multi_positive_episodes": 0,
"all_evidence_in_top3_multi": 0.0,
"hop_accuracy": 1.0,
"hop_accuracy_answerable": 1.0,
"hop_under_prediction": 0.0,
"hop_over_prediction": 0.0,
"mean_score_margin": -17.09528378547728,
"median_score_margin": -19.91835129261017,
"negative_margin_rate": 0.7245,
"hop_confusion": {
"true_1_pred_1": 2000
},
"known_mean_need_prob": 0.9656237260401249,
"unknown_mean_need_prob": 0.0,
"thr0.50": {
"need_precision": 1.0,
"need_recall": 1.0,
"need_f1": 1.0,
"specificity_unknown_refusal": 0.0,
"abstention_accuracy": 1.0,
"known_question_refusal_rate": 0.0,
"unknown_question_read_rate": 0.0,
"counts": {
"tp": 2000,
"tn": 0,
"fp": 0,
"fn": 0
}
}
},
"single_fact": {
"episodes": 2000,
"answerable_episodes": 2000,
"unknown_episodes": 0,
"top1": 0.3585,
"recall1": 0.3585,
"recall3": 0.5315,
"recall5": 0.748,
"recall8": 0.8755,
"mrr": 0.5041280494591153,
"ndcg3": 0.4566527480678597,
"mean_first_positive_rank": 6.2835,
"all_evidence_in_top3": 0.5315,
"multi_positive_episodes": 0,
"all_evidence_in_top3_multi": 0.0,
"hop_accuracy": 1.0,
"hop_accuracy_answerable": 1.0,
"hop_under_prediction": 0.0,
"hop_over_prediction": 0.0,
"mean_score_margin": -5.610978243432939,
"median_score_margin": -14.75244402885437,
"negative_margin_rate": 0.6415,
"hop_confusion": {
"true_1_pred_1": 2000
},
"known_mean_need_prob": 0.9954859737157822,
"unknown_mean_need_prob": 0.0,
"thr0.50": {
"need_precision": 1.0,
"need_recall": 1.0,
"need_f1": 1.0,
"specificity_unknown_refusal": 0.0,
"abstention_accuracy": 1.0,
"known_question_refusal_rate": 0.0,
"unknown_question_read_rate": 0.0,
"counts": {
"tp": 2000,
"tn": 0,
"fp": 0,
"fn": 0
}
}
},
"unknown": {
"episodes": 1920,
"answerable_episodes": 1814,
"unknown_episodes": 106,
"top1": 0.13561190738699008,
"recall1": 0.13561190738699008,
"recall3": 0.2508269018743109,
"recall5": 0.36604189636163176,
"recall8": 0.5700110253583242,
"mrr": 0.2724902209448839,
"ndcg3": 0.20137544771420876,
"mean_first_positive_rank": 8.588202866593164,
"all_evidence_in_top3": 0.2508269018743109,
"multi_positive_episodes": 0,
"all_evidence_in_top3_multi": 0.0,
"hop_accuracy": 0.5526041666666667,
"hop_accuracy_answerable": 0.5848952590959207,
"hop_under_prediction": 0.31808158765159866,
"hop_over_prediction": 0.0970231532524807,
"mean_score_margin": -19.966790886482894,
"median_score_margin": -18.91780662536621,
"negative_margin_rate": 0.86438809261301,
"hop_confusion": {
"true_0_pred_0": 0,
"true_0_pred_1": 42,
"true_0_pred_2": 64,
"true_1_pred_0": 577,
"true_1_pred_1": 1061,
"true_1_pred_2": 176
},
"known_mean_need_prob": 0.9243141619741194,
"unknown_mean_need_prob": 0.9999472358316746,
"thr0.50": {
"need_precision": 0.9438559322033898,
"need_recall": 0.9823594266813671,
"need_f1": 0.9627228525121555,
"specificity_unknown_refusal": 0.0,
"abstention_accuracy": 0.928125,
"known_question_refusal_rate": 0.017640573318632856,
"unknown_question_read_rate": 1.0,
"counts": {
"tp": 1782,
"tn": 0,
"fp": 106,
"fn": 32
}
}
},
"unknown_abstention": {
"episodes": 2000,
"answerable_episodes": 2000,
"unknown_episodes": 0,
"top1": 0.2055,
"recall1": 0.2055,
"recall3": 0.3865,
"recall5": 0.5795,
"recall8": 0.701,
"mrr": 0.3513197809023414,
"ndcg3": 0.30621252077857364,
"mean_first_positive_rank": 11.6,
"all_evidence_in_top3": 0.3865,
"multi_positive_episodes": 0,
"all_evidence_in_top3_multi": 0.0,
"hop_accuracy": 1.0,
"hop_accuracy_answerable": 1.0,
"hop_under_prediction": 0.0,
"hop_over_prediction": 0.0,
"mean_score_margin": -35.1040986096561,
"median_score_margin": -36.334869384765625,
"negative_margin_rate": 0.7945,
"hop_confusion": {
"true_1_pred_1": 2000
},
"known_mean_need_prob": 0.9999097834825516,
"unknown_mean_need_prob": 0.0,
"thr0.50": {
"need_precision": 1.0,
"need_recall": 1.0,
"need_f1": 1.0,
"specificity_unknown_refusal": 0.0,
"abstention_accuracy": 1.0,
"known_question_refusal_rate": 0.0,
"unknown_question_read_rate": 0.0,
"counts": {
"tp": 2000,
"tn": 0,
"fp": 0,
"fn": 0
}
}
}
}
}
}