{"id":"W4398405777","doi":"10.7910/dvn/ii5jzg/ji7owm","title":"MSP_F_100_NFL_4_23.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","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000560714,0.0003980288,0.0005909891,0.0002867436,0.0001878027,0.0006328587,0.005445558,0.0003331365,0.006958432],"category_scores_gemma":[0.001130265,0.0003758811,0.0003158142,0.00100837,0.0001387782,0.0006705051,0.003258371,0.0009401998,0.497287],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001112209,"about_ca_system_score_gemma":0.0004297166,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003707896,"about_ca_topic_score_gemma":0.0000520569,"domain_scores_codex":[0.9962875,0.0002687778,0.0004617731,0.001244974,0.001157671,0.0005793584],"domain_scores_gemma":[0.995175,0.0003343854,0.0001794032,0.003706236,0.0001524029,0.0004525626],"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":[0.000007233433,0.00007514725,0.000005062759,0.0001316437,0.00009721104,0.0002790314,0.00001486852,0.000008152806,0.000004256996,0.0001577631,0.9972749,0.001944703],"study_design_scores_gemma":[0.0002082116,0.00005741833,0.00001285964,0.00004045989,0.00005226544,0.00001310559,0.000005411152,0.001232418,0.00001994485,0.0001683377,0.9977928,0.0003967746],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[6.460119e-7,0.000002457832,0.01402729,0.0001109027,0.0004251513,0.0002058545,0.9849142,0.0002276767,0.0000857929],"genre_scores_gemma":[0.000003489379,0.0006191978,0.003521266,0.001061376,0.0003146467,0.00002707963,0.9942584,0.00001459425,0.000179948],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.4903286,"threshold_uncertainty_score":0.9999354,"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."}}