{"id":"W6959539583","doi":"10.7939/dvn/shl1sl","title":"An Annotated Corpus of Webtables for Information Extraction Tasks","year":2019,"lang":"en","type":"dataset","venue":"Borealis","topic":"Wheat and Barley Genetics and Pathology","field":"Agricultural and Biological Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"JSON; Listing (finance); Relation (database); Information extraction; TypeScript; Relationship extraction; Table (database)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001744181,0.003003516,0.001315888,0.007981102,0.001540658,0.002507027,0.002742851,0.002114269,0.05894765],"category_scores_gemma":[0.006441523,0.00108409,0.001462872,0.01350737,0.0006518507,0.002051153,0.002703283,0.001960102,0.08815194],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002332556,"about_ca_system_score_gemma":0.004472219,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02087375,"about_ca_topic_score_gemma":0.04490293,"domain_scores_codex":[0.9973561,0.000458743,0.0003688185,0.0008574208,0.0007320307,0.0002269689],"domain_scores_gemma":[0.9959544,0.001456694,0.0002405948,0.001027278,0.001009784,0.0003113035],"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":[0.0001702301,0.00008311909,0.0007356654,0.001663814,0.00004892745,0.0001355545,0.0000811157,0.0005720032,0.001211967,0.001257247,0.9819244,0.01211605],"study_design_scores_gemma":[0.0002077451,0.00003360977,0.006172604,0.000388315,0.00006369298,0.0002558578,0.000185559,0.001242521,0.003274648,0.002059068,0.9860617,0.00005480026],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0006694954,0.0002621642,0.0007617032,0.00008542818,0.00006032657,0.00005971753,0.9939023,0.001509287,0.002689557],"genre_scores_gemma":[0.0005403677,0.00008003046,0.001082075,0.00003202622,0.00000490448,0.0001095182,0.9973328,0.0001248673,0.0006934761],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.05894765,"threshold_uncertainty_score":0.1971995,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02478300731730786,"score_gpt":0.267243084917823,"score_spread":0.2424600776005151,"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."}}