{"id":"W4398277276","doi":"10.7910/dvn/ii5jzg/z9n0pc","title":"MSP_F_100_NFL_4_32.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":[0.0005594673,0.0003980199,0.0005909926,0.0002853355,0.0001890209,0.0006324584,0.00544571,0.0003313553,0.007279332],"category_scores_gemma":[0.001122273,0.0003757706,0.0003156933,0.001007142,0.0001405847,0.0006970303,0.003250221,0.0009433133,0.5068253],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000111651,"about_ca_system_score_gemma":0.0004372918,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003580569,"about_ca_topic_score_gemma":0.00005028128,"domain_scores_codex":[0.9962889,0.0002687109,0.0004622209,0.001245223,0.00115517,0.0005797757],"domain_scores_gemma":[0.9951801,0.0003312801,0.0001795035,0.003702999,0.0001529064,0.0004531568],"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":[0.000007530455,0.00007635836,0.000003892135,0.0001322457,0.0000972385,0.0002764218,0.00001717312,0.000008265583,0.000003947175,0.0001591445,0.9973605,0.001857244],"study_design_scores_gemma":[0.0002109479,0.00005834987,0.000010695,0.00003945699,0.00005224487,0.00001288373,0.000007738012,0.001247318,0.0000184389,0.0001746131,0.9977706,0.0003967026],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[6.734188e-7,0.000002563708,0.01456885,0.0001074471,0.0004263979,0.0002057473,0.9843667,0.000227755,0.00009392261],"genre_scores_gemma":[0.000003663275,0.0005702637,0.003620717,0.001058831,0.0003134413,0.00002711538,0.9942098,0.00001457244,0.0001815406],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.4995459,"threshold_uncertainty_score":0.9999353,"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."}}