{"id":"W3021034694","doi":"10.18653/v1/2020.acl-main.695","title":"The Paradigm Discovery Problem","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"York University; New York University Abu Dhabi","keywords":"Computer science; Benchmark (surveying); Task (project management); Cluster analysis; String (physics); Heuristic; Construct (python library); Artificial intelligence; Word (group theory); Code (set theory); Natural language processing; Machine learning; Programming language","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01547656,0.001775905,0.001916558,0.003476046,0.004257271,0.007624525,0.005965292,0.005266163,0.01206957],"category_scores_gemma":[0.0725817,0.001529979,0.004278889,0.003649004,0.005045764,0.03040476,0.009727047,0.008060665,0.004185347],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002177479,"about_ca_system_score_gemma":0.003673289,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001903209,"about_ca_topic_score_gemma":0.001446014,"domain_scores_codex":[0.9793239,0.007192661,0.001570604,0.007262476,0.003771611,0.0008788305],"domain_scores_gemma":[0.9344056,0.04775465,0.002773987,0.009646507,0.004055326,0.001363872],"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":[0.0003727143,0.0002320782,0.007540875,0.001450236,0.000371635,0.0008739646,0.002335395,0.0104087,0.003085402,0.4924745,0.04440457,0.43645],"study_design_scores_gemma":[0.00004231118,0.00005782106,0.0004943399,0.0001141629,0.00006833352,0.001408926,0.0006956406,0.04791607,0.00214119,0.9108267,0.03617961,0.00005472279],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01922611,0.002160859,0.9545023,0.01012616,0.0006760683,0.0002826301,0.001291763,0.001379073,0.01035495],"genre_scores_gemma":[0.2513743,0.002600689,0.7165838,0.005228618,0.001852348,0.0008375871,0.007256854,0.001033012,0.01323265],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01547656,"threshold_uncertainty_score":0.0818488,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03907413907118272,"score_gpt":0.2561360138813221,"score_spread":0.2170618748101393,"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."}}