ESS-AIST-81M-preview / event_eval.json
gcoderw's picture
Promote v9 preview checkpoint
d9e59f7 verified
{
"checkpoint": "/shared/augmem/triembed/checkpoints/ess_aist_full_v9_subjectfix_l4k/best_model.pt",
"split": "val",
"records_path": "/shared/augmem/triembed/checkpoints/ess_ait_86m_20260430T035907Z/ess_corpus_v9_subject_media_wit4096_speech100k_wavcaps100k_librispeech360_subjectfix/val.jsonl",
"views": {
"semantic_key": {
"event_same_different_auc": {
"auc": 0.827451141075551,
"positive_pairs": 181625,
"negative_pairs": 453539,
"positive_mean": 0.8296324522244216,
"negative_mean": 0.6291148030260264
},
"same_subject_different_event_rejection_auc": {
"auc": 0.6695206182798321,
"positive_pairs": 181625,
"negative_pairs": 175759,
"positive_mean": 0.8296324522244216,
"negative_mean": 0.7356056283701664
},
"stale_same_source_rejection_auc": {
"auc": null,
"positive_pairs": 181625,
"negative_pairs": 0,
"positive_mean": 0.8296324522244216,
"negative_mean": null
},
"wrong_active_rejection_auc": {
"auc": null,
"positive_pairs": 181625,
"negative_pairs": 0,
"positive_mean": 0.8296324522244216,
"negative_mean": null
},
"topic_shift_rejection_auc": {
"auc": 0.8994650340280883,
"positive_pairs": 181625,
"negative_pairs": 340388,
"positive_mean": 0.8296324522244216,
"negative_mean": 0.5938547173777865
}
},
"subject_key": {
"event_same_different_auc": {
"auc": 0.8854762132187833,
"positive_pairs": 181625,
"negative_pairs": 453539,
"positive_mean": 0.8070377156889529,
"negative_mean": 0.5549017710295172
},
"same_subject_different_event_rejection_auc": {
"auc": 0.7381349173591332,
"positive_pairs": 181625,
"negative_pairs": 175759,
"positive_mean": 0.8070377156889529,
"negative_mean": 0.6661491519755037
},
"stale_same_source_rejection_auc": {
"auc": null,
"positive_pairs": 181625,
"negative_pairs": 0,
"positive_mean": 0.8070377156889529,
"negative_mean": null
},
"wrong_active_rejection_auc": {
"auc": null,
"positive_pairs": 181625,
"negative_pairs": 0,
"positive_mean": 0.8070377156889529,
"negative_mean": null
},
"topic_shift_rejection_auc": {
"auc": 0.9512869887738572,
"positive_pairs": 181625,
"negative_pairs": 340388,
"positive_mean": 0.8070377156889529,
"negative_mean": 0.5185315754949175
}
},
"event_key": {
"event_same_different_auc": {
"auc": 0.8193492434516296,
"positive_pairs": 181625,
"negative_pairs": 453539,
"positive_mean": 0.8111014214781179,
"negative_mean": 0.560698310072904
},
"same_subject_different_event_rejection_auc": {
"auc": 0.6806606788615208,
"positive_pairs": 181625,
"negative_pairs": 175759,
"positive_mean": 0.8111014214781179,
"negative_mean": 0.673238928121084
},
"stale_same_source_rejection_auc": {
"auc": null,
"positive_pairs": 181625,
"negative_pairs": 0,
"positive_mean": 0.8111014214781179,
"negative_mean": null
},
"wrong_active_rejection_auc": {
"auc": null,
"positive_pairs": 181625,
"negative_pairs": 0,
"positive_mean": 0.8111014214781179,
"negative_mean": null
},
"topic_shift_rejection_auc": {
"auc": 0.8968700248558907,
"positive_pairs": 181625,
"negative_pairs": 340388,
"positive_mean": 0.8111014214781179,
"negative_mean": 0.5184466918134688
}
},
"full_key": {
"event_same_different_auc": {
"auc": 0.8518429254835135,
"positive_pairs": 181625,
"negative_pairs": 453539,
"positive_mean": 0.8179552220574594,
"negative_mean": 0.5906047553254696
},
"same_subject_different_event_rejection_auc": {
"auc": 0.6938164439467958,
"positive_pairs": 181625,
"negative_pairs": 175759,
"positive_mean": 0.8179552220574594,
"negative_mean": 0.6977020526065576
},
"stale_same_source_rejection_auc": {
"auc": null,
"positive_pairs": 181625,
"negative_pairs": 0,
"positive_mean": 0.8179552220574594,
"negative_mean": null
},
"wrong_active_rejection_auc": {
"auc": null,
"positive_pairs": 181625,
"negative_pairs": 0,
"positive_mean": 0.8179552220574594,
"negative_mean": null
},
"topic_shift_rejection_auc": {
"auc": 0.9288029360785891,
"positive_pairs": 181625,
"negative_pairs": 340388,
"positive_mean": 0.8179552220574594,
"negative_mean": 0.553700150467076
}
},
"prefix_512": {
"event_same_different_auc": {
"auc": 0.827451141075551,
"positive_pairs": 181625,
"negative_pairs": 453539,
"positive_mean": 0.8296324522244216,
"negative_mean": 0.6291148030260264
},
"same_subject_different_event_rejection_auc": {
"auc": 0.6695206182798321,
"positive_pairs": 181625,
"negative_pairs": 175759,
"positive_mean": 0.8296324522244216,
"negative_mean": 0.7356056283701664
},
"stale_same_source_rejection_auc": {
"auc": null,
"positive_pairs": 181625,
"negative_pairs": 0,
"positive_mean": 0.8296324522244216,
"negative_mean": null
},
"wrong_active_rejection_auc": {
"auc": null,
"positive_pairs": 181625,
"negative_pairs": 0,
"positive_mean": 0.8296324522244216,
"negative_mean": null
},
"topic_shift_rejection_auc": {
"auc": 0.8994650340280883,
"positive_pairs": 181625,
"negative_pairs": 340388,
"positive_mean": 0.8296324522244216,
"negative_mean": 0.5938547173777865
}
},
"prefix_1024": {
"event_same_different_auc": {
"auc": 0.8613090604277244,
"positive_pairs": 181625,
"negative_pairs": 453539,
"positive_mean": 0.8195616576529665,
"negative_mean": 0.5971227166902979
},
"same_subject_different_event_rejection_auc": {
"auc": 0.7009197337402358,
"positive_pairs": 181625,
"negative_pairs": 175759,
"positive_mean": 0.8195616576529665,
"negative_mean": 0.7044079956623066
},
"stale_same_source_rejection_auc": {
"auc": null,
"positive_pairs": 181625,
"negative_pairs": 0,
"positive_mean": 0.8195616576529665,
"negative_mean": null
},
"wrong_active_rejection_auc": {
"auc": null,
"positive_pairs": 181625,
"negative_pairs": 0,
"positive_mean": 0.8195616576529665,
"negative_mean": null
},
"topic_shift_rejection_auc": {
"auc": 0.934646406192986,
"positive_pairs": 181625,
"negative_pairs": 340388,
"positive_mean": 0.8195616576529665,
"negative_mean": 0.5615511370717131
}
},
"prefix_1536": {
"event_same_different_auc": {
"auc": 0.8518429254835135,
"positive_pairs": 181625,
"negative_pairs": 453539,
"positive_mean": 0.8179552220574594,
"negative_mean": 0.5906047553254696
},
"same_subject_different_event_rejection_auc": {
"auc": 0.6938164439467958,
"positive_pairs": 181625,
"negative_pairs": 175759,
"positive_mean": 0.8179552220574594,
"negative_mean": 0.6977020526065576
},
"stale_same_source_rejection_auc": {
"auc": null,
"positive_pairs": 181625,
"negative_pairs": 0,
"positive_mean": 0.8179552220574594,
"negative_mean": null
},
"wrong_active_rejection_auc": {
"auc": null,
"positive_pairs": 181625,
"negative_pairs": 0,
"positive_mean": 0.8179552220574594,
"negative_mean": null
},
"topic_shift_rejection_auc": {
"auc": 0.9288029360785891,
"positive_pairs": 181625,
"negative_pairs": 340388,
"positive_mean": 0.8179552220574594,
"negative_mean": 0.553700150467076
}
}
}
}