{"id":"W2004193186","doi":"10.1145/584931.584940","title":"A framework for web table mining","year":2002,"lang":"en","type":"article","venue":"","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Table (database); Web page; Information retrieval; World Wide Web; Web mining; Table of contents; Information extraction; Process (computing); 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":[],"consensus_categories":[],"category_scores_codex":[0.0001171398,0.00005669616,0.0000884178,0.00005366192,0.00009323288,0.000158507,0.0004950073,0.00003462961,0.0002314135],"category_scores_gemma":[0.0001072721,0.00004751666,0.00004533713,0.0003559986,0.000008941631,0.0002468905,0.00008864133,0.00003758592,0.0001229213],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005876903,"about_ca_system_score_gemma":0.000008292463,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006109663,"about_ca_topic_score_gemma":0.000002611293,"domain_scores_codex":[0.9993995,0.000008424297,0.00009312033,0.000221597,0.00008975797,0.000187641],"domain_scores_gemma":[0.9993388,0.0001588233,0.00002743993,0.0003995751,0.00002536243,0.0000499837],"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":[0.000001181367,0.00009965175,0.001236666,0.00001428983,0.00006273838,0.000006697542,0.0009685101,0.0000802383,0.0004038124,0.4920527,0.3233583,0.1817151],"study_design_scores_gemma":[0.0001175315,0.00003603698,0.00003439834,0.00001616208,0.000008601788,0.000002815118,0.00006657362,0.8842532,0.000288478,0.003680669,0.1113669,0.0001285891],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.002208981,0.00008689753,0.984776,0.001496203,0.00009847465,0.00002987228,0.000003741252,0.0001512496,0.01114855],"genre_scores_gemma":[0.2172014,0.00000539847,0.7761476,0.0005835572,0.00006845301,0.00001054832,0.000001478058,0.000003655254,0.005977941],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.884173,"threshold_uncertainty_score":0.2533816,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04721870685743441,"score_gpt":0.2677927006460024,"score_spread":0.220573993788568,"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."}}