{"id":"W7128633953","doi":"10.7910/dvn/skhkqn","title":"Sub-evaluation 4 Queens Dataset","year":2025,"lang":"","type":"dataset","venue":"Open MIND","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Segmentation; Image segmentation; Feature (linguistics); Field (mathematics); Pattern recognition (psychology)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002602014,0.004294698,0.002305767,0.004381116,0.002399703,0.003064672,0.006020602,0.003881618,0.04497536],"category_scores_gemma":[0.01016565,0.0006782529,0.002791541,0.004426129,0.0011057,0.002498738,0.003715483,0.002843499,0.0622706],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003176171,"about_ca_system_score_gemma":0.004221537,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03946517,"about_ca_topic_score_gemma":0.1005166,"domain_scores_codex":[0.9961964,0.0009136978,0.0003641237,0.001011292,0.001086226,0.000428277],"domain_scores_gemma":[0.9959501,0.0009984029,0.0001999634,0.00109485,0.00131343,0.0004431643],"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":[0.0002250079,0.0001358079,0.0009667234,0.0006648433,0.0000935108,0.00004020381,0.00002670752,0.000588296,0.0002754678,0.0005167138,0.9887068,0.007759819],"study_design_scores_gemma":[0.001281631,0.000261091,0.008309309,0.0006107106,0.0001893594,0.0004808509,0.000318421,0.006511372,0.001994751,0.003784789,0.9761397,0.0001181372],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.003971837,0.001065981,0.0008055812,0.0007185825,0.0004349574,0.0002523029,0.9844943,0.002680963,0.005575518],"genre_scores_gemma":[0.001582924,0.0001092427,0.001342016,0.0001621845,0.00003787009,0.0002027043,0.9943787,0.0001469839,0.002037326],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.04497536,"threshold_uncertainty_score":0.1504576,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1059091584915674,"score_gpt":0.4226388832803454,"score_spread":0.3167297247887781,"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."}}