{"id":"W2741782787","doi":"10.29007/fm8f","title":"Overview of COLIEE 2017","year":2018,"lang":"en","type":"article","venue":"EPiC series in computing","topic":"Topic Modeling","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Core Research for Evolutional Science and Technology; Ministry of Education, Culture, Sports, Science and Technology; Alberta Machine Intelligence Institute","keywords":"Task (project management); Computer science; Logical consequence; Textual entailment; Information retrieval; Information extraction; Group (periodic table); Task group; Question answering; Natural language processing; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0004292226,0.00008239611,0.000177306,0.00007200451,0.00007060052,0.00003467869,0.0007268271,0.00003853764,0.00001843583],"category_scores_gemma":[0.00008842827,0.00008463184,0.00003080828,0.0002831329,0.00008327836,0.0002372608,0.0005106573,0.00008562148,0.0000171422],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002680478,"about_ca_system_score_gemma":0.00004769672,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005960265,"about_ca_topic_score_gemma":0.00002977656,"domain_scores_codex":[0.9990187,0.00005332443,0.000305493,0.0002512805,0.0001521889,0.0002189829],"domain_scores_gemma":[0.9991729,0.00009384071,0.0001128733,0.0005259699,0.00006510806,0.00002933361],"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":[0.00001437714,0.00008849409,0.02930154,0.0002475293,0.00002704218,0.00004406902,0.01225221,0.001883989,0.0007468303,0.6173054,0.00133734,0.3367512],"study_design_scores_gemma":[0.0007873254,0.0002853576,0.03902278,0.0006801572,0.000005057138,0.00009094391,0.0002321884,0.8928713,0.008367153,0.04314824,0.01399261,0.0005168467],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3631476,0.0006964172,0.618722,0.0006054249,0.001653869,0.000131499,4.386278e-7,0.000129226,0.01491358],"genre_scores_gemma":[0.8705374,0.00001393932,0.1290037,0.0001802391,0.0001877235,7.941092e-7,1.781134e-7,0.00000406428,0.00007194451],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8909873,"threshold_uncertainty_score":0.3451186,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08135760093089604,"score_gpt":0.3317747509200041,"score_spread":0.2504171499891081,"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."}}