{"id":"W3082162291","doi":"10.14778/3407790.3407810","title":"<i>Pytheas</i>","year":2020,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","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; Information retrieval; Metadata; Table (database); File format; Data extraction; Data mining; World Wide Web; Database","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001378531,0.00008343862,0.0001288337,0.00002394711,0.00006702668,0.00007479577,0.001431988,0.0000177434,0.000008399292],"category_scores_gemma":[0.00007352225,0.00005344957,0.0001015833,0.0004621142,0.00003037234,0.0002382928,0.0006164167,0.00007740207,0.00002519297],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001174289,"about_ca_system_score_gemma":0.00001636396,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001278907,"about_ca_topic_score_gemma":1.764576e-7,"domain_scores_codex":[0.9991593,0.000003416355,0.0001667707,0.0002324093,0.0002902406,0.0001479034],"domain_scores_gemma":[0.9995685,0.0000131742,0.000126031,0.0001462486,0.00006894396,0.00007707654],"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":[0.00003139592,0.000295426,0.01749649,0.0002912603,0.0003238105,0.000002686139,0.009434387,0.00009699093,0.3742716,0.374189,0.1741684,0.04939851],"study_design_scores_gemma":[0.00104436,0.0002832498,0.002062812,0.0001396374,0.000121968,0.00001777988,0.0006596342,0.0320426,0.8367914,0.007445361,0.1188719,0.0005193205],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4625249,0.001056825,0.03814412,0.3284084,0.001175398,0.001300952,0.00005337429,0.001284123,0.166052],"genre_scores_gemma":[0.9899863,0.00001307661,0.008126179,0.00164685,0.00006397918,0.000007424071,2.905285e-7,0.000004719711,0.0001511866],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5274614,"threshold_uncertainty_score":0.2661013,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01495428813388612,"score_gpt":0.1896174007940449,"score_spread":0.1746631126601587,"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."}}