{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006400503,0.001237108,0.001504615,0.002377898,0.001274183,0.001849546,0.001706428,0.001398386,0.007578238],"category_scores_gemma":[0.01466957,0.000568661,0.0008925679,0.001605088,0.001247567,0.001422194,0.001772835,0.001410665,0.005821596],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001621231,"about_ca_system_score_gemma":0.001670599,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004239245,"about_ca_topic_score_gemma":0.006906974,"domain_scores_codex":[0.9967073,0.000832127,0.0003446363,0.0009390592,0.0009394425,0.0002373765],"domain_scores_gemma":[0.9895795,0.003417137,0.0005917778,0.002866275,0.003204527,0.0003407522],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00140946,0.001699246,0.01977511,0.001767322,0.0001801653,0.0005780804,0.001009555,0.0105769,0.2834166,0.001872066,0.02673643,0.6509791],"study_design_scores_gemma":[0.0003886555,0.002316373,0.1791973,0.0006452784,0.0006056444,0.002591479,0.001748395,0.2178388,0.4701403,0.007412267,0.1167665,0.0003491199],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4810307,0.003972121,0.440196,0.001402671,0.0004062929,0.009987081,0.02059842,0.01451575,0.02789107],"genre_scores_gemma":[0.4170121,0.001424046,0.5343659,0.0004893369,0.00007945498,0.004564871,0.03357177,0.001059386,0.007433173],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007578238,"threshold_uncertainty_score":0.03384948,"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."}}