{"id":"W4398347322","doi":"10.7910/dvn/ii5jzg/b8n0xq","title":"MSP_F_100_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","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0005623766,0.000398692,0.0005924363,0.0002870484,0.0001899173,0.0006331581,0.005461233,0.0003332727,0.007189798],"category_scores_gemma":[0.001132028,0.0003763748,0.0003162255,0.001009686,0.0001411793,0.0006732004,0.003267855,0.0009453175,0.4971392],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001128108,"about_ca_system_score_gemma":0.0004440604,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003758433,"about_ca_topic_score_gemma":0.00005296844,"domain_scores_codex":[0.9962788,0.0002692981,0.0004633111,0.001248924,0.001158691,0.0005810204],"domain_scores_gemma":[0.9951646,0.0003323154,0.0001799159,0.003715962,0.0001532777,0.0004539182],"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":[0.000007402724,0.00007648625,0.000004112499,0.0001323293,0.00009740121,0.0002768137,0.00001521209,0.000008474078,0.000004053067,0.0001641157,0.9972459,0.001967704],"study_design_scores_gemma":[0.000210748,0.00005789175,0.00001118882,0.00003953681,0.00005235763,0.00001289267,0.000006692774,0.001221406,0.00001889666,0.0001791677,0.9977919,0.0003973247],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[6.042837e-7,0.000002415641,0.01451402,0.0001102858,0.0004267787,0.0002065453,0.9844117,0.0002278777,0.00009983159],"genre_scores_gemma":[0.000003194951,0.0006059735,0.003659629,0.001073433,0.0003144245,0.00002711014,0.9941218,0.00001459815,0.0001798484],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.4899494,"threshold_uncertainty_score":0.9999197,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02254317685125836,"score_gpt":0.2681597623408774,"score_spread":0.245616585489619,"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."}}