{"id":"W2050611670","doi":"10.1371/journal.pcbi.1000391","title":"How to Get the Most out of Your Curation Effort","year":2009,"lang":"en","type":"article","venue":"PLoS Computational Biology","topic":"Topic Modeling","field":"Computer Science","cited_by":46,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"U.S. National Library of Medicine; National Institute of General Medical Sciences; National Institutes of Health; National Science Foundation","keywords":"Annotation; Computer science; Data curation; Sentence; Probabilistic logic; Set (abstract data type); Natural language processing; Task (project management); Information retrieval; Artificial intelligence; Machine learning; Data science; Data mining","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":[],"consensus_categories":[],"category_scores_codex":[0.0001095808,0.00006941793,0.0001049763,0.00005817617,0.00006116103,0.00003931781,0.0004409229,0.00003881559,0.000002201931],"category_scores_gemma":[0.00006562829,0.00004974661,0.00002720182,0.0001343417,0.00002275544,0.0001423591,0.00007364499,0.00005987038,0.00001512699],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001620485,"about_ca_system_score_gemma":0.00005032492,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003444459,"about_ca_topic_score_gemma":0.00000233126,"domain_scores_codex":[0.9993379,0.00004175792,0.0001619398,0.0002060802,0.0001286507,0.000123742],"domain_scores_gemma":[0.9994436,0.0001070337,0.00007701263,0.0001968889,0.0001420465,0.0000334414],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000009536629,0.00009365519,0.001760205,0.000005771426,0.00003195818,0.000001678753,0.00145635,0.08950587,0.007501886,0.8232108,0.0005625964,0.07585964],"study_design_scores_gemma":[0.0001863505,0.0002211058,0.01047896,0.000008626407,0.000004622478,0.000005748265,0.00001983784,0.8312784,0.001120548,0.1549542,0.001600282,0.0001213425],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07784742,0.00003100043,0.8994334,0.02205781,0.0001783969,0.000139617,0.000003631187,0.00004206398,0.0002666924],"genre_scores_gemma":[0.9137221,8.444453e-7,0.08449406,0.001620209,0.00009601119,0.0000052215,0.00001514301,0.000001883062,0.00004451544],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8358747,"threshold_uncertainty_score":0.2028608,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04654170247765851,"score_gpt":0.2859339761740192,"score_spread":0.2393922736963607,"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."}}