{"id":"W7108230307","doi":"10.25504/fairsharing.a94677","title":"FAIRsharing record for: Hakai Data","year":2025,"lang":"","type":"dataset","venue":"FAIRsharing.org","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Margin (machine learning); Data collection; Information system; Historical record; Data system","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","sts","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","open_science","research_integrity","insufficient_payload"],"category_scores_codex":[0.006626062,0.006031994,0.00632588,0.004197279,0.003091104,0.002408304,0.03476581,0.00479571,0.006858564],"category_scores_gemma":[0.01197702,0.007392116,0.001909238,0.004738378,0.001018364,0.004517548,0.06326393,0.008137639,0.02555653],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003357351,"about_ca_system_score_gemma":0.004297846,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003982176,"about_ca_topic_score_gemma":0.009239275,"domain_scores_codex":[0.9687179,0.0007553173,0.006527362,0.0136994,0.003405184,0.006894888],"domain_scores_gemma":[0.9539429,0.002407753,0.004641067,0.03543637,0.001658555,0.001913378],"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":[0.00145677,0.001419036,0.005426824,0.008266252,0.003390308,0.0002827239,0.0001632377,0.00004127622,0.0002893872,0.000269501,0.9755898,0.003404939],"study_design_scores_gemma":[0.005586507,0.0005843116,0.001056851,0.00824642,0.005210282,0.00006715921,0.0004264848,0.004008782,0.0003598238,0.0002692933,0.9677374,0.006446705],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0003663206,0.003249805,0.0004951224,0.000604127,0.01334035,0.008034273,0.967957,0.001619038,0.004334009],"genre_scores_gemma":[0.000935621,0.001640665,0.003579048,0.0007805918,0.006047382,0.001719888,0.9608104,0.001235407,0.02325106],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.02849812,"threshold_uncertainty_score":0.9986273,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1406474824678136,"score_gpt":0.374359654357511,"score_spread":0.2337121718896974,"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."}}