{"id":"W4398286541","doi":"10.7910/dvn/ii5jzg/7fnwwf","title":"MSP_F_20_NFL_4_40.xlsx","year":2020,"lang":"en","type":"dataset","venue":"Harvard Dataverse","topic":"Software Reliability and Analysis Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Context (archaeology); Resolution (logic); Computer science; History; Artificial intelligence; Archaeology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0005264081,0.0003822758,0.0005629989,0.0002736868,0.0001814538,0.0006099094,0.005249454,0.0003212466,0.00716844],"category_scores_gemma":[0.001063142,0.0003598049,0.0003019382,0.0009555563,0.0001308047,0.0006403833,0.003085879,0.0009113692,0.5884678],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001059398,"about_ca_system_score_gemma":0.0004183964,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003277134,"about_ca_topic_score_gemma":0.00004613659,"domain_scores_codex":[0.9964409,0.0002517869,0.0004414684,0.00120009,0.001107856,0.0005579042],"domain_scores_gemma":[0.995374,0.0003023887,0.0001710622,0.003576653,0.000141647,0.0004342516],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000007151772,0.00007432325,0.000003531032,0.0001252279,0.00009321796,0.000261246,0.00001512149,0.000007804521,0.000003338706,0.0001625503,0.9970628,0.002183699],"study_design_scores_gemma":[0.0002022652,0.00005692903,0.000009559141,0.00003775288,0.00005102167,0.00001223394,0.000006463286,0.001276109,0.00001885685,0.0001828476,0.9977657,0.0003803081],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[5.136333e-7,0.000002310578,0.0157922,0.0001059612,0.0004080756,0.0002013922,0.9831668,0.0002183801,0.0001043281],"genre_scores_gemma":[0.000002826006,0.0005711482,0.003934399,0.001074436,0.0003072567,0.00002662049,0.9938563,0.00001401812,0.0002129747],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.5812994,"threshold_uncertainty_score":0.9998854,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02351315628031347,"score_gpt":0.2693241825604176,"score_spread":0.2458110262801041,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}