{"id":"W4398616256","doi":"10.7910/dvn/ii5jzg/emv7pe","title":"MSP_F_100_NFL_4_5.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":[0.0005625766,0.0003931781,0.0005916703,0.0002830592,0.0001872454,0.0006258557,0.005413834,0.0003283371,0.006961303],"category_scores_gemma":[0.001120351,0.0003710345,0.000311996,0.0009981131,0.0001393043,0.0006640235,0.003243246,0.0009344266,0.4961584],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001104567,"about_ca_system_score_gemma":0.0004334065,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003762675,"about_ca_topic_score_gemma":0.00005275805,"domain_scores_codex":[0.9963167,0.0002667914,0.0004616077,0.001234578,0.001146604,0.0005737697],"domain_scores_gemma":[0.9952108,0.0003263736,0.0001790008,0.003684551,0.0001512264,0.0004480834],"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":[0.000007270032,0.00007538382,0.000003913896,0.0001315854,0.00009587892,0.0002736036,0.00001508009,0.000008372318,0.000003863346,0.0001619122,0.9971982,0.00202494],"study_design_scores_gemma":[0.0002077983,0.0000569507,0.00001109929,0.00003903729,0.00005133335,0.00001252925,0.000006684169,0.001276143,0.00001807944,0.0001719948,0.9977567,0.0003916935],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[5.752393e-7,0.000002367088,0.014501,0.0001114151,0.0004222316,0.0002035672,0.9844319,0.0002245599,0.0001024397],"genre_scores_gemma":[0.000003134208,0.0005940495,0.003641208,0.001077013,0.0003117757,0.00002521354,0.9941533,0.00001433017,0.0001799409],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.4891971,"threshold_uncertainty_score":0.9999673,"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."}}