{"id":"W4411173295","doi":"10.1109/icse-nier66352.2025.00008","title":"Listening to the Firehose: Sonifying Z3’s Behavior","year":2025,"lang":"en","type":"article","venue":"","topic":"Reinforcement Learning in Robotics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Active listening; Computer science; Speech recognition; Psychology; Communication","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000273063,0.00009027663,0.00008061754,0.00008049454,0.0002733582,0.0003727104,0.001225827,0.00003147627,0.00003408376],"category_scores_gemma":[0.00008848348,0.00006208706,0.00004560766,0.0005176149,0.00001560106,0.0001828676,0.0006514541,0.0001441017,0.0002082212],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004408889,"about_ca_system_score_gemma":0.00005504786,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004367156,"about_ca_topic_score_gemma":0.000009325174,"domain_scores_codex":[0.9991097,0.00003044125,0.0001716502,0.0002257941,0.0002130774,0.0002492681],"domain_scores_gemma":[0.9991338,0.0001040537,0.00003331727,0.0006339916,0.00004891037,0.000045873],"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":[0.000003212347,0.00003072005,0.009154347,0.00002134313,0.00003174091,0.00001999681,0.002387032,0.5646279,0.0006134105,0.2611444,0.03390839,0.1280576],"study_design_scores_gemma":[0.0002630197,0.00008737538,0.02216016,0.00008612584,0.00002427274,0.0000079701,0.0002128011,0.7169843,0.002184782,0.0001546522,0.2575166,0.0003179946],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001894117,0.00002881592,0.9517076,0.00637798,0.000623832,0.0002103426,7.203187e-8,0.000220534,0.0389367],"genre_scores_gemma":[0.7920836,0.000003504956,0.1198209,0.005172346,0.00005814521,0.00006093538,6.718984e-7,0.000007840476,0.08279198],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8318866,"threshold_uncertainty_score":0.3594055,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01470794262932113,"score_gpt":0.2865948154057638,"score_spread":0.2718868727764427,"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."}}