{"id":"W4414253714","doi":"10.1007/978-3-032-04624-6_33","title":"DocAnnot - Accelerating the Creation of Key Information Extraction Datasets with GenAI-Powered Auto-annotation","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Glycemic Index Laboratories","funders":"","keywords":"Key (lock); Benchmark (surveying); Task (project management); Annotation; Process (computing); Minimum bounding box; Matching (statistics); Automation","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":[0.002777414,0.002887716,0.001731699,0.004260186,0.002249186,0.003734127,0.002868929,0.001367486,0.03505001],"category_scores_gemma":[0.006971816,0.001639685,0.002682335,0.005648568,0.0008710842,0.004277812,0.00475666,0.002590234,0.04786433],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001424406,"about_ca_system_score_gemma":0.002882581,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007138337,"about_ca_topic_score_gemma":0.01620476,"domain_scores_codex":[0.9971606,0.0004103603,0.0002589384,0.0009891117,0.0009930744,0.0001879974],"domain_scores_gemma":[0.9954264,0.001304457,0.0001763371,0.001851067,0.001068176,0.0001736516],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0009430797,0.0002245981,0.001914073,0.00134857,0.0003264827,0.0002774959,0.0004998769,0.001382185,0.02276765,0.006300917,0.6679206,0.2960945],"study_design_scores_gemma":[0.0004544061,0.0002722735,0.004600546,0.0003102586,0.0002618314,0.0007205664,0.0005494071,0.06252015,0.1146432,0.02641784,0.7889892,0.0002603499],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"software","genre_gemma":"methods","genre_scores_codex":[0.01105977,0.001477358,0.2898613,0.0009093767,0.001725453,0.0007186417,0.1240558,0.5534351,0.01675713],"genre_scores_gemma":[0.02856184,0.0006108751,0.5706949,0.0008767544,0.0002084024,0.0009414898,0.3472078,0.03145584,0.01944208],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.03505001,"threshold_uncertainty_score":0.117254,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01220594296914632,"score_gpt":0.2750500807634131,"score_spread":0.2628441377942667,"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."}}