{"id":"W4398329608","doi":"10.7910/dvn/ii5jzg/rnnvk8","title":"MSP_F_50_NFL_4_12.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; Geography; 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":[0.0005448695,0.0003938276,0.0005808554,0.0002818548,0.0001895028,0.0006324355,0.005428487,0.00033172,0.007289127],"category_scores_gemma":[0.001122221,0.0003714906,0.0003121601,0.0009696711,0.0001379748,0.0006664281,0.003243893,0.0009460225,0.4988895],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001090372,"about_ca_system_score_gemma":0.0004185519,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003408012,"about_ca_topic_score_gemma":0.00004813293,"domain_scores_codex":[0.9963323,0.0002584524,0.0004577367,0.001235363,0.001140403,0.000575682],"domain_scores_gemma":[0.9952328,0.0003139692,0.000176514,0.003680284,0.0001466641,0.0004497746],"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":[0.00001061105,0.00007768335,0.000003959263,0.0001300118,0.00009636935,0.0002722947,0.00001518691,0.000008179758,0.000003318346,0.0001703336,0.9972366,0.001975418],"study_design_scores_gemma":[0.0002082419,0.00008121272,0.0000105598,0.00004025062,0.00005258101,0.00001279568,0.000006624779,0.001182372,0.00001608664,0.0001783705,0.9978188,0.0003921521],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[5.660102e-7,0.000002498607,0.01403139,0.0001117762,0.00041811,0.0002057801,0.9849057,0.0002237805,0.0001003723],"genre_scores_gemma":[0.000003783847,0.0006017783,0.003765024,0.001075238,0.0003129045,0.00002734102,0.9940469,0.000014235,0.0001527425],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.4916004,"threshold_uncertainty_score":0.9999526,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02345769106095168,"score_gpt":0.2691457205047474,"score_spread":0.2456880294437957,"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."}}