{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002599262,0.001661281,0.00082611,0.007179614,0.001417374,0.004020772,0.00304766,0.001348189,0.05081009],"category_scores_gemma":[0.02578024,0.0009935838,0.001178062,0.0107499,0.001592451,0.006331537,0.004091737,0.001753821,0.04787798],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002878406,"about_ca_system_score_gemma":0.005822015,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.108166,"about_ca_topic_score_gemma":0.1207659,"domain_scores_codex":[0.9975503,0.0001925856,0.0002364098,0.0005374386,0.00123627,0.0002470124],"domain_scores_gemma":[0.9831871,0.003703442,0.001217462,0.005718846,0.00540029,0.0007728932],"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":[0.0002907939,0.00004070865,0.005571277,0.0005753144,0.00004645067,0.0001967563,0.0004395073,0.000829757,0.004446347,0.004313097,0.8754288,0.1078212],"study_design_scores_gemma":[0.00004590421,0.00004272292,0.01007797,0.0002071694,0.00001988429,0.0003583104,0.0002812416,0.01002222,0.01886643,0.00504396,0.9549149,0.0001192311],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.007709616,0.0006335343,0.09302559,0.002339601,0.0007328788,0.0006765134,0.4453925,0.4226052,0.0268846],"genre_scores_gemma":[0.04140585,0.0007234283,0.1848109,0.001402944,0.000226226,0.0009479696,0.7138702,0.03572326,0.02088919],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.108166,"threshold_uncertainty_score":0.2150728,"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."}}