{"id":"W4400909907","doi":"10.1109/icde60146.2024.00146","title":"FeatAug: Automatic Feature Augmentation From One-to-Many Relationship Tables","year":2024,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Feature (linguistics); Artificial intelligence; Pattern recognition (psychology); Data mining","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002362229,0.0001014599,0.00008621011,0.0001624131,0.0001351309,0.0007237121,0.0004228804,0.0000599967,0.00018965],"category_scores_gemma":[0.0001279616,0.00008881387,0.00003133769,0.0005926529,0.000009683229,0.0007713899,0.000105196,0.0001859893,0.001634364],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006013977,"about_ca_system_score_gemma":0.00005291913,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002163556,"about_ca_topic_score_gemma":0.00004793487,"domain_scores_codex":[0.9989496,0.00008384252,0.0001511923,0.0004165474,0.000257126,0.0001416924],"domain_scores_gemma":[0.999015,0.0003162046,0.00003202574,0.0005268133,0.00002646143,0.0000834833],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002971063,0.00005070598,0.006133433,0.00006492988,0.0000383442,0.000008660058,0.001804334,0.0003491442,0.002007653,0.6640652,0.09221112,0.2332635],"study_design_scores_gemma":[0.0001186675,0.0000325804,0.2108053,0.0001127045,0.00001880375,0.000004063535,0.00006093418,0.7383531,0.0003234909,0.01354118,0.03643056,0.0001985378],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01235757,0.0002465924,0.9577131,0.02038972,0.0004190103,0.0001646437,0.00002172563,0.001148665,0.007538919],"genre_scores_gemma":[0.7790029,0.000005481784,0.2120441,0.0004907571,0.0001102895,0.00002941484,0.0003452257,0.00001080959,0.007960957],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7666454,"threshold_uncertainty_score":0.999143,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02920513358580999,"score_gpt":0.2927907284485727,"score_spread":0.2635855948627627,"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."}}