{"id":"W2805607905","doi":"","title":"UZH at TAC KBP 2017: Event Nugget Detection via Joint Learning with Softmax-Margin Objective.","year":2017,"lang":"en","type":"article","venue":"Theory and applications of categories","topic":"Topic Modeling","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Softmax function; Margin (machine learning); Joint (building); Computer science; Event (particle physics); Artificial intelligence; Machine learning; Deep learning; Engineering; Physics; Structural engineering","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000518121,0.0001075446,0.0001423526,0.000052559,0.0009260058,0.000100188,0.0004031487,0.00004363653,0.000006928793],"category_scores_gemma":[0.00004244658,0.00009055881,0.00002585481,0.00006947384,0.0002241574,0.0003602465,0.0002500182,0.0001175176,0.00001010113],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000273401,"about_ca_system_score_gemma":0.00002932091,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005868068,"about_ca_topic_score_gemma":0.00003695305,"domain_scores_codex":[0.9992297,0.00006759323,0.0001580288,0.0002814859,0.0001244336,0.0001387112],"domain_scores_gemma":[0.9988212,0.0000869884,0.00024128,0.0007137887,0.00008808696,0.00004863888],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00006156034,0.00004575862,0.0008449137,0.00006155743,0.00003671498,0.000001022135,0.001845473,0.0008622009,0.009490532,0.8121865,0.000007859009,0.1745559],"study_design_scores_gemma":[0.0007621688,0.0003231937,0.01317894,0.00005149978,0.00006056814,0.00009270284,0.0008420638,0.01524686,0.1639507,0.795477,0.009458696,0.0005555745],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07681964,0.00018698,0.9204292,0.0001283295,0.00003659747,0.000212539,0.000001223523,0.00007177071,0.002113748],"genre_scores_gemma":[0.9960125,0.00003685158,0.002891412,0.00001410193,0.00005641159,0.000127009,0.000002247809,0.00000735327,0.0008520904],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9191929,"threshold_uncertainty_score":0.7122182,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01043420943244808,"score_gpt":0.2388014463683573,"score_spread":0.2283672369359092,"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."}}