{"id":"W4286531984","doi":"10.1109/saner53432.2022.00039","title":"Evaluating the Use of Semantics for Identifying Task-relevant Textual Information","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER)","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Semantics (computer science); Task (project management); Information retrieval; Natural language processing; World Wide Web; Artificial intelligence; Programming language; Engineering","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":[0.00067617,0.0001334056,0.0001936356,0.0005076712,0.0002961888,0.0002016328,0.0005931023,0.00003599184,0.00003673707],"category_scores_gemma":[0.000280572,0.0001171082,0.0001503077,0.0005450054,0.00002864015,0.0006142157,0.0002384381,0.0002228722,0.000001877937],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001462397,"about_ca_system_score_gemma":0.00007867003,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009576338,"about_ca_topic_score_gemma":0.00001539437,"domain_scores_codex":[0.9982733,0.0000715823,0.000483069,0.0002565122,0.0007464131,0.0001691316],"domain_scores_gemma":[0.9987836,0.0002314273,0.0002848153,0.0003374026,0.0003207595,0.00004203319],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001923916,0.0000228848,0.0005533186,0.00002394352,0.0003189435,7.347743e-7,0.0005146897,0.9103945,0.0011011,0.07840744,0.0001839942,0.008459137],"study_design_scores_gemma":[0.0002064216,0.00008693164,0.001172745,0.00002017435,0.00009793848,0.000006365512,0.0002166097,0.9965332,0.00005495424,0.0005729271,0.0009004185,0.0001313406],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03089186,0.00005061834,0.9676592,0.000551295,0.0005212691,0.0001767715,0.00005249928,0.00008007191,0.00001646093],"genre_scores_gemma":[0.9590403,0.00002858838,0.04044423,0.0001230914,0.0000507047,0.00006346448,0.00007464091,0.000006219072,0.0001687353],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9281484,"threshold_uncertainty_score":0.4775535,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1273810981062148,"score_gpt":0.3389998145211017,"score_spread":0.2116187164148869,"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."}}