{"id":"W1979359179","doi":"10.1107/s1399004714017581","title":"Using textons to rank crystallization droplets by the likely presence of crystals","year":2014,"lang":"en","type":"article","venue":"Acta Crystallographica Section D Biological Crystallography","topic":"Image Retrieval and Classification Techniques","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Ministero dello Sviluppo Economico; Wellcome Trust; University of Oxford; Ontario Ministry of Economic Development and Innovation; Engineering and Physical Sciences Research Council; Genome Canada; Pfizer; Eli Lilly and Company","keywords":"Crystallization; Artificial intelligence; Set (abstract data type); Computer science; Random forest; Classifier (UML); Ranking (information retrieval); Rank (graph theory); Crystal (programming language); Pattern recognition (psychology); Computer vision; Crystallography; Chemistry; Mathematics; Combinatorics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001555558,0.0005354041,0.0006079584,0.0007996673,0.0006528957,0.0003101989,0.002246274,0.000465064,0.00005453265],"category_scores_gemma":[0.000565852,0.0003654852,0.0005560492,0.005278534,0.0007920976,0.0006426695,0.0005596951,0.0004665892,7.300485e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000463303,"about_ca_system_score_gemma":0.00005604616,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009734748,"about_ca_topic_score_gemma":0.00001457562,"domain_scores_codex":[0.9953496,0.0008991061,0.00103442,0.001155365,0.0007900518,0.0007714859],"domain_scores_gemma":[0.9963994,0.0006799487,0.0006278193,0.001358425,0.0006009958,0.0003334268],"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":[0.00005516273,0.0002520506,0.001835229,0.00002736913,0.00006858518,0.000001164924,0.0001401617,0.0000388094,0.9887974,0.00494814,0.0016308,0.002205162],"study_design_scores_gemma":[0.002122483,0.005127362,0.02900604,0.0002849673,0.0001841258,0.0002581167,0.0004844203,0.02089371,0.05534378,0.03670032,0.8463472,0.003247497],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.130793,0.0001773288,0.8644136,0.001859763,0.0002849312,0.001015934,0.00003618614,0.0006780403,0.0007412698],"genre_scores_gemma":[0.9818662,0.0002221474,0.01678646,0.0007751497,0.000110099,0.000128968,0.00003646993,0.00003082604,0.00004369064],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9334536,"threshold_uncertainty_score":0.9998797,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03283404330126088,"score_gpt":0.2696393137003805,"score_spread":0.2368052703991196,"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."}}