{"id":"W4400375663","doi":"10.1145/3654777.3676345","title":"Improving Steering and Verification in AI-Assisted Data Analysis with Interactive Task Decomposition","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Decomposition; Computer science; Task (project management); Human–computer interaction; Systems engineering; Chemistry; Engineering","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":[0.0001549959,0.000152041,0.0002012521,0.0002830273,0.000047814,0.000623801,0.0007455528,0.00006935229,0.000003021567],"category_scores_gemma":[0.00000353018,0.0001260141,0.00003043333,0.000804064,0.00001845575,0.0003399098,0.002633136,0.0004418617,0.000003591043],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005505353,"about_ca_system_score_gemma":0.00004849266,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006047623,"about_ca_topic_score_gemma":0.0009117523,"domain_scores_codex":[0.9985451,0.00003441844,0.0002265606,0.0009477469,0.0001211822,0.0001249969],"domain_scores_gemma":[0.9985303,0.00005664553,0.0001144718,0.00120986,0.00004385018,0.00004482695],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006400653,0.0003579819,0.002919454,0.000606084,0.001762599,0.00007804509,0.001616966,0.0744692,0.01592376,0.04248385,0.0009335654,0.8587845],"study_design_scores_gemma":[0.00005849196,0.00001156399,0.009335279,0.00008737938,0.0001472449,0.000005391375,0.00002410265,0.9889003,0.0001709183,0.001034437,0.00006120824,0.0001636649],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03878006,0.0001389473,0.9588273,0.001398809,0.00008727519,0.0002825953,0.00002630866,0.0001397513,0.0003190158],"genre_scores_gemma":[0.948954,0.00002381698,0.05054707,0.00007796861,0.00003168652,0.00006565995,0.0002552758,0.000008132755,0.00003639639],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9144311,"threshold_uncertainty_score":0.6015328,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02211765731294867,"score_gpt":0.308756620832746,"score_spread":0.2866389635197973,"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."}}