{"id":"W4393023501","doi":"10.48550/arxiv.2403.10758","title":"Rules still work for Open Information Extraction","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; National Office for Philosophy and Social Sciences","keywords":"Work (physics); Extraction (chemistry); Computer science; Information extraction; Data science; Information retrieval; Engineering; Chromatography; Mechanical engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007410569,0.001526727,0.001443749,0.004308328,0.002703047,0.008871527,0.003516493,0.00260268,0.01980335],"category_scores_gemma":[0.03691195,0.001154177,0.003476707,0.00490796,0.00342595,0.02167716,0.005930942,0.0049433,0.01777262],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001586953,"about_ca_system_score_gemma":0.004311786,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003914184,"about_ca_topic_score_gemma":0.005439115,"domain_scores_codex":[0.9906552,0.002386795,0.00127601,0.002669075,0.002557851,0.0004550811],"domain_scores_gemma":[0.97236,0.009020362,0.0009504817,0.01366212,0.003411308,0.0005957187],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0001720931,0.0001994935,0.003528442,0.0008096701,0.000179883,0.000349064,0.0008859044,0.01208813,0.002857841,0.4826431,0.04417522,0.4521111],"study_design_scores_gemma":[0.00003806362,0.00004162497,0.0004927592,0.0003088856,0.0001080172,0.0003934577,0.0003007335,0.07538392,0.005791263,0.6806952,0.2363826,0.00006344823],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005404326,0.00135039,0.9533792,0.002933876,0.0005082019,0.0003540328,0.002181868,0.006710992,0.02717718],"genre_scores_gemma":[0.110168,0.001929254,0.8509088,0.002024629,0.000538907,0.0006457112,0.009564851,0.0032146,0.02100531],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01980335,"threshold_uncertainty_score":0.06624877,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06192997884404722,"score_gpt":0.2379808634967504,"score_spread":0.1760508846527031,"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."}}