{"id":"W2039427737","doi":"10.3115/1220575.1220583","title":"Redundancy-based correction of automatically extracted facts","year":2005,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"York University","keywords":"Redundancy (engineering); Pipeline (software); Computer science; Information extraction; Data mining; Event (particle physics); Artificial intelligence; Machine learning","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001484499,0.00007600495,0.0001006729,0.00009850842,0.00003312212,0.00005615476,0.0004322985,0.00006161342,0.00005620414],"category_scores_gemma":[0.0001355812,0.00006094646,0.00003444358,0.0002916597,0.00002709293,0.0004134912,0.0000504443,0.000100178,0.00001850216],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003607411,"about_ca_system_score_gemma":0.00008548231,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001768065,"about_ca_topic_score_gemma":0.0000101373,"domain_scores_codex":[0.9992701,0.0000248316,0.0002068913,0.0001655736,0.0002040179,0.0001286175],"domain_scores_gemma":[0.9993665,0.00007372923,0.00009686917,0.0003024679,0.0001182468,0.00004225396],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000007971789,0.0001605118,0.00008186982,0.00003470342,0.000006314363,0.000004420015,0.0002074191,0.0001114683,0.07456258,0.02546651,0.004254195,0.895102],"study_design_scores_gemma":[0.0001001729,0.00004936225,0.0003723202,0.00004449425,0.000002229019,0.000005869424,0.000002116385,0.4173754,0.5786385,0.002515342,0.0007970725,0.00009713303],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005392442,0.000122151,0.9877286,0.0009663424,0.0001401819,0.0000819397,2.801975e-7,0.001338476,0.004229592],"genre_scores_gemma":[0.4874777,3.635757e-7,0.512009,0.0001847646,0.00001260196,0.000002265201,6.484413e-7,0.00000267105,0.0003100191],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8950049,"threshold_uncertainty_score":0.2485324,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009424979568080563,"score_gpt":0.2671534743695565,"score_spread":0.2577284948014759,"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."}}