{"id":"W6958654200","doi":"10.6084/m9.figshare.c.6662674","title":"Supplementary material from \"Predicting and reasoning about replicability using structured groups\"","year":2023,"lang":"en","type":"other","venue":"Figshare","topic":"","field":"","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Replication (statistics); Heuristics; Replicate; Protocol (science); Field (mathematics); Subject (documents); Domain (mathematical analysis); Qualitative reasoning","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","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0001210263,0.0006133863,0.0006514553,0.0002112988,0.0001665206,0.0002426167,0.0003777526,0.0005616287,0.7642971],"category_scores_gemma":[0.001145461,0.0006606777,0.0001115178,0.0002342213,0.00002618738,0.0001070418,0.0007664268,0.0004111255,0.0008707406],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003139138,"about_ca_system_score_gemma":0.00008024872,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01054791,"about_ca_topic_score_gemma":0.006396534,"domain_scores_codex":[0.9969824,0.0001545342,0.0004671677,0.001315188,0.0004820723,0.0005986152],"domain_scores_gemma":[0.9979632,0.0001110264,0.0006348353,0.001054926,0.00004596204,0.0001900825],"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":[0.00004028155,0.000008726127,0.002739263,0.0004088248,0.000191153,0.00006238078,0.0001420697,0.000003312032,0.0007217835,8.481098e-7,0.9953771,0.0003042195],"study_design_scores_gemma":[0.002675409,0.00007503651,0.0485002,0.05369712,0.0005621095,0.00006373646,0.000367273,0.002392215,0.002091767,0.0002339893,0.8861942,0.003146936],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.01183217,0.0002589637,1.209523e-7,0.000004083007,0.000408919,0.0008294019,0.981818,0.001889094,0.002959197],"genre_scores_gemma":[0.006038346,0.000003039222,0.001103296,0.00003297537,0.003309133,0.0001496934,0.9818432,0.004618695,0.002901621],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.7634263,"threshold_uncertainty_score":0.9999072,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03727258727552094,"score_gpt":0.2941631147844553,"score_spread":0.2568905275089344,"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."}}