{"id":"W2074126326","doi":"10.1145/2213836.2213912","title":"Automatic web-scale information extraction","year":2012,"lang":"en","type":"article","venue":"","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Scale (ratio); Extraction (chemistry); Information extraction; Information retrieval; World Wide Web; Chromatography; Geography","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000222422,0.00004044949,0.00004738005,0.00008222579,0.00005430046,0.0001165973,0.0001941065,0.00002108475,0.0001408177],"category_scores_gemma":[0.00001603444,0.00003249547,0.000025305,0.0002200226,0.000005244331,0.004731982,0.00005257588,0.00003551104,0.00134303],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001373493,"about_ca_system_score_gemma":0.0000125914,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002157603,"about_ca_topic_score_gemma":0.000002673802,"domain_scores_codex":[0.9995669,0.00001546155,0.000116087,0.00004705426,0.0001253719,0.0001291039],"domain_scores_gemma":[0.9996165,0.00002080911,0.00004455979,0.0002434065,0.00001870385,0.00005604099],"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":[4.344116e-7,0.00007540907,0.008476125,0.00001644594,0.00001911791,2.286366e-7,0.001881393,0.00002386379,0.0008170199,0.0178688,0.02811524,0.9427059],"study_design_scores_gemma":[0.0001130115,0.00001226487,0.02690059,0.000006526894,0.00001132665,0.00001642049,0.0001707994,0.9037364,0.001394419,0.0001042842,0.06740072,0.0001332875],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1105055,0.00001512004,0.8608852,0.0004751256,0.0002750485,0.00002817128,0.000001064089,0.0003652071,0.02744962],"genre_scores_gemma":[0.9257301,0.000002313289,0.07369378,0.000211196,0.00004055941,0.000003111336,0.000007980546,9.823311e-7,0.0003099469],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9425727,"threshold_uncertainty_score":0.9994345,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01052818257282117,"score_gpt":0.2457080567536289,"score_spread":0.2351798741808077,"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."}}