{"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":"codex-gemma-dda1882f352a","candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.004589377,0.0001902699,0.0003469302,0.0003353163,0.0001466706,0.0002305001,0.01354192,0.00005505337,0.0001036157],"category_scores_gemma":[0.002736851,0.0001319879,0.00007724066,0.00141199,0.0001371963,0.001187272,0.01392516,0.0001364371,0.00001738261],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004017593,"about_ca_system_score_gemma":0.00001743541,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003939051,"about_ca_topic_score_gemma":0.000008334242,"domain_scores_codex":[0.996578,0.00002592972,0.0008279958,0.0007839422,0.00152624,0.0002578941],"domain_scores_gemma":[0.9951386,0.0001805702,0.0006581854,0.003723342,0.0002570845,0.00004218798],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002094153,0.0002834424,0.002763894,0.0007572036,0.0003440762,7.503498e-7,0.0001046866,0.00006004163,0.002227288,0.3225597,0.6057335,0.064956],"study_design_scores_gemma":[0.001309752,0.000152241,0.01995722,0.001184405,0.0003417159,6.492049e-7,0.004922315,0.001181659,0.01221279,0.4279818,0.5303765,0.0003789175],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4741293,0.001232714,0.01066175,0.0632491,0.00700108,0.007664409,0.005984611,0.0005818234,0.4294952],"genre_scores_gemma":[0.953068,0.0003909626,0.02908194,0.0009074103,0.00006657454,0.00003000252,0.0001662103,0.00002413148,0.01626475],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4789387,"threshold_uncertainty_score":0.99405,"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."}}