{"id":"W2774116887","doi":"10.1145/3134664","title":"Seeing Sound","year":2017,"lang":"en","type":"article","venue":"Proceedings of the ACM on Human-Computer Interaction","topic":"Music and Audio Processing","field":"Computer Science","cited_by":62,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"National Science Foundation","keywords":"Computer science; Annotation; Soundscape; Spectrogram; Redundancy (engineering); Active listening; Recall; Reliability (semiconductor); Crowdsourcing; Speech recognition; Human–computer interaction; Natural language processing; Artificial intelligence; Sound (geography); Cognitive psychology; World Wide Web","routes":{"ca_aff":true,"ca_fund":false,"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":[0.001134257,0.0008795882,0.0005279077,0.00152915,0.001219181,0.003098601,0.0007838178,0.001770416,0.04696279],"category_scores_gemma":[0.008163789,0.0004108591,0.0006076397,0.0009579467,0.001155003,0.003456029,0.003422902,0.000851904,0.02008778],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004261999,"about_ca_system_score_gemma":0.0006401632,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002239993,"about_ca_topic_score_gemma":0.003902213,"domain_scores_codex":[0.9990208,0.0001751374,0.00004770105,0.0003432508,0.0003407609,0.00007226112],"domain_scores_gemma":[0.9968414,0.001237213,0.0001436133,0.0006060207,0.0009664855,0.0002051883],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0009909495,0.00006996749,0.01061422,0.001525969,0.00009017807,0.001035298,0.006708995,0.002769281,0.1635386,0.0180636,0.06118238,0.7334105],"study_design_scores_gemma":[0.0001045719,0.0006170002,0.04789663,0.0009756959,0.0002540885,0.003381998,0.009365189,0.02073932,0.07626935,0.05338494,0.7866387,0.0003724765],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.09306212,0.002729018,0.652681,0.003346998,0.002900396,0.0005718071,0.005861948,0.01967126,0.2191754],"genre_scores_gemma":[0.5427055,0.002670394,0.3666377,0.002806713,0.0008732789,0.0005997862,0.005102311,0.00393002,0.07467439],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.04696279,"threshold_uncertainty_score":0.1571062,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08687798803912372,"score_gpt":0.3487043296533339,"score_spread":0.2618263416142101,"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."}}