{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01023948,0.001846413,0.0007825281,0.01231031,0.0007135638,0.002431027,0.001211818,0.002252555,0.0008582853],"category_scores_gemma":[0.06738358,0.0003244368,0.001137585,0.003344754,0.0009902626,0.005340454,0.001605117,0.001150603,0.0006845262],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000853362,"about_ca_system_score_gemma":0.001523429,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004427732,"about_ca_topic_score_gemma":0.006467766,"domain_scores_codex":[0.9901919,0.004055372,0.001349059,0.001502721,0.002522161,0.0003787691],"domain_scores_gemma":[0.8819098,0.09993708,0.005724637,0.003512865,0.007751338,0.001164211],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.004009345,0.002609134,0.1582255,0.004959686,0.001077809,0.0007865732,0.006366296,0.02718885,0.05264092,0.004318273,0.009809026,0.7280086],"study_design_scores_gemma":[0.0007683326,0.006159702,0.1412889,0.0009701589,0.001905641,0.002606133,0.009224363,0.6784028,0.1132761,0.01546946,0.02948989,0.000438649],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.860563,0.004505025,0.1157478,0.000668478,0.0002394457,0.0007580576,0.002749993,0.006831096,0.007937041],"genre_scores_gemma":[0.8435463,0.0008734704,0.1486559,0.000162622,0.0001166878,0.0003042484,0.004414141,0.0002850117,0.001641681],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.01231031,"threshold_uncertainty_score":0.05415219,"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."}}