{"id":"W4398258577","doi":"10.7910/dvn/ii5jzg/uyd6xb","title":"MSP_F_20_NFL_4_10.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; Artificial intelligence; History; 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":[0.0005263027,0.0003821507,0.0005627004,0.0002735208,0.0001817153,0.000609763,0.005249838,0.0003211283,0.007538689],"category_scores_gemma":[0.001064688,0.0003596714,0.0003018446,0.0009547317,0.0001310157,0.0006402776,0.003085124,0.0009131287,0.5161753],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001059019,"about_ca_system_score_gemma":0.0004156073,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003276426,"about_ca_topic_score_gemma":0.00004459261,"domain_scores_codex":[0.9964421,0.000251753,0.0004412652,0.001198892,0.001108134,0.0005577886],"domain_scores_gemma":[0.9953764,0.0003026192,0.0001710089,0.003573981,0.0001418918,0.0004340936],"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":[0.000007133082,0.00007430564,0.000003556256,0.000125086,0.00009317415,0.0002604771,0.0000149524,0.000007743698,0.000004071588,0.0001578926,0.9972163,0.002035351],"study_design_scores_gemma":[0.0002021417,0.00005681251,0.000009932736,0.00003771043,0.00005099306,0.00001212026,0.000006382907,0.001284163,0.00001874321,0.0001763831,0.9977644,0.0003801823],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[4.943944e-7,0.000002359943,0.01556171,0.0001069252,0.0004013722,0.0002010699,0.9834046,0.0002183349,0.000103161],"genre_scores_gemma":[0.0000027992,0.0005607874,0.003920986,0.001063026,0.0003074942,0.00002660142,0.9939174,0.00001399528,0.0001869223],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.5086366,"threshold_uncertainty_score":0.9998855,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0232250654835378,"score_gpt":0.2685905390350408,"score_spread":0.245365473551503,"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."}}