{"id":"W7111194251","doi":"10.1371/journal.pone.0334756.s001","title":"Minimal Data Set Definition.","year":2025,"lang":"","type":"article","venue":"Figshare","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Inference; Representation (politics); Mixture model; Pattern recognition (psychology); Set (abstract data type); Gaussian; Similarity (geometry); Graph; Key (lock)","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":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0002064044,0.0002558308,0.000232691,0.0001794957,0.0003130466,0.0008367347,0.004418811,0.0002161553,0.1005061],"category_scores_gemma":[0.002558769,0.0002684091,0.00008938572,0.001292659,0.00002627779,0.001150182,0.00328412,0.0003313402,0.007839136],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006724124,"about_ca_system_score_gemma":0.0007432519,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004982638,"about_ca_topic_score_gemma":0.000001479589,"domain_scores_codex":[0.9975973,0.0001071997,0.0004562227,0.0009700996,0.0004693104,0.0003998179],"domain_scores_gemma":[0.9960812,0.0002473387,0.0001916921,0.002771051,0.000599967,0.0001087658],"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":[0.000004921113,0.00005704095,0.000004172614,0.0002210379,0.00001998425,0.00001326842,0.00004688802,5.220697e-8,0.00004801933,0.003994802,0.9107826,0.08480715],"study_design_scores_gemma":[0.0001923929,0.00004514875,0.0009483857,0.002433484,0.00001891098,0.000009393041,0.00002179662,0.02662779,0.007182025,0.002287943,0.9599078,0.0003248746],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.000001782449,0.002952009,0.03160825,0.007038987,0.0003671731,0.000529811,0.8724077,0.0006132532,0.08448105],"genre_scores_gemma":[0.05963314,0.0001625806,0.02452453,0.006207344,0.0004400379,0.0003585939,0.8847337,0.00004324589,0.02389683],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.09266696,"threshold_uncertainty_score":0.9999768,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2095507505672338,"score_gpt":0.3451337315990653,"score_spread":0.1355829810318315,"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."}}