{"id":"W2429937759","doi":"10.1145/2932194.2932203","title":"Accurate fact harvesting from natural language text in wikipedia with Lector","year":2016,"lang":"en","type":"article","venue":"","topic":"Wikis in Education and Collaboration","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Information retrieval; Information extraction; Domain (mathematical analysis); Relationship extraction; Natural language; Natural language processing; Fraction (chemistry); Question answering; Artificial intelligence; World Wide Web; Mathematics","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":[0.0001513335,0.00005199338,0.0000563854,0.00003854789,0.0001023032,0.00008588548,0.0001003427,0.00003449963,0.001064808],"category_scores_gemma":[0.0003698068,0.00003070937,0.000008683199,0.0002941313,0.00006309986,0.0004497522,0.000007780218,0.00004708097,0.0001064782],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009350093,"about_ca_system_score_gemma":0.0002539764,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.00977298,"about_ca_topic_score_gemma":0.1162018,"domain_scores_codex":[0.9993876,0.00008764991,0.00008710945,0.0001283352,0.0001622324,0.0001470331],"domain_scores_gemma":[0.9995726,0.0002014157,0.00004304331,0.00007831144,0.00005847157,0.00004610485],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0001255332,0.0001910546,0.2606321,0.000006045429,0.00003179544,0.00001688952,0.1921605,0.000009766246,0.02653623,0.02702028,0.01500901,0.4782608],"study_design_scores_gemma":[0.001657914,0.00005461789,0.7781938,0.0001457316,0.00001253814,5.252396e-7,0.1166317,0.0001043795,0.004344975,0.0009539028,0.09726763,0.000632248],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.954995,0.00006207651,0.0001584423,0.004346822,0.0003367747,0.0001050506,0.000004295267,0.00006743888,0.03992408],"genre_scores_gemma":[0.9768027,0.000007634736,0.0006293224,0.0002429334,0.0002853075,0.000008701857,0.00000359809,0.000004429251,0.02201536],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5175617,"threshold_uncertainty_score":0.9998484,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01279322473618379,"score_gpt":0.3151136089758648,"score_spread":0.3023203842396811,"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."}}