{"id":"W7128604989","doi":"10.7910/dvn/jltk6i","title":"Sub-evaluation 11 Aachen 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; Medical imaging; Image segmentation; Feature (linguistics); Data collection","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":[0.002209767,0.004299811,0.002077737,0.005093134,0.00160128,0.002871771,0.004855113,0.003391516,0.04744628],"category_scores_gemma":[0.008681721,0.0006681423,0.0021922,0.005343172,0.0009823855,0.001847619,0.003118509,0.002279412,0.07558633],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002828931,"about_ca_system_score_gemma":0.003414044,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03500064,"about_ca_topic_score_gemma":0.07911681,"domain_scores_codex":[0.9966223,0.0008721848,0.0003212969,0.0009220392,0.0008085087,0.0004537161],"domain_scores_gemma":[0.9968457,0.0008380938,0.0001978158,0.0009155973,0.0009090471,0.0002936521],"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":[0.0002007332,0.00009475293,0.0008555502,0.0007658259,0.00008638541,0.0000477605,0.0000258785,0.0006952105,0.0001870206,0.0004308028,0.9887199,0.007890034],"study_design_scores_gemma":[0.001029259,0.0001824041,0.009140354,0.0009105182,0.0001767375,0.0004677598,0.0002587828,0.004931773,0.001538913,0.003315252,0.9779379,0.0001102972],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.002210254,0.0008030989,0.0005320301,0.0003388355,0.000212569,0.0001485708,0.9900635,0.002175014,0.003516068],"genre_scores_gemma":[0.001264516,0.0001173869,0.0007350512,0.00009265013,0.000025638,0.0001965644,0.9959618,0.00012412,0.001482247],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.04744628,"threshold_uncertainty_score":0.1587236,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1256390473694409,"score_gpt":0.421166067877485,"score_spread":0.2955270205080441,"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."}}