{"id":"W2082225138","doi":"10.1145/1046456.1046458","title":"Extracting relational data from HTML repositories","year":2004,"lang":"en","type":"article","venue":"ACM SIGKDD Explorations Newsletter","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Set (abstract data type); Information retrieval; Data mining; Information extraction; Quality (philosophy)","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":[0.0002229565,0.0001487216,0.0001464707,0.0001155634,0.0004240787,0.0005240083,0.002295598,0.00006853427,0.00004777138],"category_scores_gemma":[0.000686105,0.0001441787,0.0000496479,0.0005100747,0.00005531375,0.004812952,0.001088023,0.0002147519,0.0006338899],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004635008,"about_ca_system_score_gemma":0.000111467,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002460489,"about_ca_topic_score_gemma":0.00006659404,"domain_scores_codex":[0.9983298,0.00006130678,0.0003608278,0.0006717383,0.0003609486,0.0002154163],"domain_scores_gemma":[0.9957921,0.0003500376,0.000152166,0.003549522,0.00008079632,0.00007536652],"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":[0.00003049247,0.0008515397,0.02478451,0.00001994753,0.0009527984,0.0005288162,0.01814923,0.01837353,0.08105386,0.1475038,0.6748206,0.03293088],"study_design_scores_gemma":[0.004262245,0.0002209451,0.02529628,0.0004093976,0.000585851,0.000166203,0.002451843,0.08547164,0.03518156,0.1757706,0.6662915,0.003891956],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.02391498,0.00008156543,0.9240887,0.05048844,0.0005528514,0.0000621739,0.00007072955,0.0002523164,0.0004882945],"genre_scores_gemma":[0.4474546,0.000009312016,0.5466772,0.002741223,0.001169853,0.0000231542,0.00162537,0.00001670907,0.0002826246],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4235396,"threshold_uncertainty_score":0.8147584,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1297204511692792,"score_gpt":0.3005306323875561,"score_spread":0.170810181218277,"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."}}