{"id":"W1966060376","doi":"10.1107/s0907444908028047","title":"Establishing a training set through the visual analysis of crystallization trials. Part I: ∼150 000 images","year":2008,"lang":"en","type":"article","venue":"Acta Crystallographica Section D Biological Crystallography","topic":"Cell Image Analysis Techniques","field":"Biochemistry, Genetics and Molecular Biology","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ontario Institute for Cancer Research","funders":"National Institute of General Medical Sciences","keywords":"Computer science; Set (abstract data type); Representation (politics); Artificial intelligence; Variety (cybernetics); Interpretation (philosophy); Image (mathematics); Crystallization; Scalability; Process (computing); Training set; Data mining; Pattern recognition (psychology); Data set; Machine learning; Information retrieval; Chemistry","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"],"consensus_categories":[],"category_scores_codex":[0.002356637,0.0006239531,0.001383196,0.001190237,0.0006810596,0.0001309929,0.000805149,0.0007449042,0.0002285971],"category_scores_gemma":[0.001462931,0.0004313337,0.002456753,0.006367092,0.00152892,0.00008160543,0.0003132937,0.0004824728,1.291585e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002168731,"about_ca_system_score_gemma":0.00007356781,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002623984,"about_ca_topic_score_gemma":0.0001747552,"domain_scores_codex":[0.9943088,0.001523404,0.001633639,0.001228671,0.000590218,0.0007152677],"domain_scores_gemma":[0.9966222,0.0005536657,0.001155983,0.0009766824,0.0005237932,0.0001676679],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003146905,0.0003338021,0.02528036,0.00001698523,0.004012763,0.00001288447,0.0004416143,0.0003510517,0.9629438,0.00004177989,0.005871226,0.0003790414],"study_design_scores_gemma":[0.002553558,0.004373497,0.1006673,0.00008383625,0.006748968,0.0002344057,0.005551231,0.0006549815,0.03246828,0.00170446,0.8421745,0.002785013],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9519868,0.0009439128,0.04383248,0.0002273761,0.0001283965,0.0007819553,0.0001455347,0.00025279,0.001700738],"genre_scores_gemma":[0.9904208,0.005003393,0.001434459,0.0005807697,0.0003989399,0.0001701792,0.001878749,0.00004812884,0.00006464056],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9304755,"threshold_uncertainty_score":0.9998139,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05040414061300281,"score_gpt":0.3039238057387794,"score_spread":0.2535196651257766,"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."}}