{"id":"W2080132606","doi":"10.14778/1938545.1938547","title":"Automatic wrappers for large scale web extraction","year":2011,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":135,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Noise (video); Scale (ratio); Noisy data; Extraction (chemistry); Data extraction; Data mining; Information extraction; Training set; Artificial intelligence; Machine learning; Information retrieval; Pattern recognition (psychology)","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":[0.0004121945,0.00009426787,0.000134771,0.00008097065,0.000130293,0.0000503766,0.0008487081,0.00003029341,0.00002556905],"category_scores_gemma":[0.00004494737,0.0000645535,0.0001346095,0.0002744832,0.00002162676,0.0003980818,0.0002116503,0.00005681924,0.00001135651],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002894376,"about_ca_system_score_gemma":0.00002188755,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001733837,"about_ca_topic_score_gemma":0.000002911289,"domain_scores_codex":[0.9991307,0.000003793631,0.0002048558,0.0002304081,0.0002151883,0.0002150059],"domain_scores_gemma":[0.9994513,0.00002002495,0.0001993546,0.0001863106,0.00009833239,0.00004472669],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00008868141,0.002929436,0.0420534,0.001262166,0.0008989658,0.000001503001,0.03905774,0.00001217746,0.3998624,0.2733877,0.08925852,0.1511873],"study_design_scores_gemma":[0.001972075,0.0003952651,0.0101086,0.0003335241,0.0002984758,0.00002913727,0.003211157,0.3443504,0.609665,0.01227753,0.01675934,0.000599567],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9398059,0.0001177666,0.03362151,0.002135886,0.0008084552,0.0009767832,0.00004161059,0.0004205003,0.02207159],"genre_scores_gemma":[0.9490006,0.000009229226,0.05049328,0.00008504764,0.00002995853,0.00005939276,7.845499e-7,0.000006423864,0.0003152729],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3443382,"threshold_uncertainty_score":0.2632415,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02415002081639386,"score_gpt":0.2448207655012949,"score_spread":0.2206707446849011,"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."}}