{"id":"W4417070120","doi":"10.1145/3769829","title":"ST-Raptor: LLM-Powered Semi-Structured Table Question Answering","year":2025,"lang":"en","type":"article","venue":"Proceedings of the ACM on Management of Data","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Table (database); Correctness; Tree (set theory); Set (abstract data type); Benchmark (surveying); Pipeline (software); Question answering","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":[0.007122713,0.00170836,0.001209398,0.002025845,0.0009965374,0.003233228,0.004999233,0.002571185,0.01818994],"category_scores_gemma":[0.03604563,0.001182408,0.002598759,0.001270633,0.002242547,0.008227798,0.007029453,0.003278474,0.01059901],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001343792,"about_ca_system_score_gemma":0.004356821,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005198085,"about_ca_topic_score_gemma":0.006700838,"domain_scores_codex":[0.9913845,0.003823354,0.0005900752,0.001429417,0.002350216,0.0004224913],"domain_scores_gemma":[0.9803193,0.0116582,0.0006564366,0.004245865,0.002703304,0.0004169844],"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":[0.001315583,0.0005915498,0.004868027,0.002285352,0.0002006015,0.001036256,0.005028586,0.04882607,0.04919832,0.1477364,0.1173388,0.6215744],"study_design_scores_gemma":[0.0001434509,0.0002185468,0.0006576998,0.0001336518,0.00005046182,0.0004660384,0.0004850698,0.8496262,0.03120858,0.06915355,0.04773639,0.0001204691],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005129872,0.0001312527,0.9337869,0.0004794906,0.00008264359,0.0005232813,0.001699521,0.05521103,0.002955927],"genre_scores_gemma":[0.09696149,0.0001442294,0.8896387,0.000618017,0.00007187905,0.0007174174,0.005927822,0.002885153,0.003035236],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01818994,"threshold_uncertainty_score":0.0608514,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1373690653317707,"score_gpt":0.4113977177010211,"score_spread":0.2740286523692504,"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."}}