{"id":"W4409163690","doi":"10.1007/s00766-025-00436-7","title":"Tracing content requirements in financial documents using multi-granularity text analysis","year":2025,"lang":"en","type":"article","venue":"Requirements Engineering","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Fonds National de la Recherche Luxembourg","keywords":"Tracing; Granularity; Computer science; Requirements analysis; Information retrieval; Software engineering; Programming language; Software","routes":{"ca_aff":true,"ca_fund":true,"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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006341533,0.0003457429,0.0005904234,0.001682361,0.0001288781,0.0001685018,0.0009443104,0.0001193972,0.000008054153],"category_scores_gemma":[0.0001811136,0.0003858583,0.0002670355,0.003678163,0.00002402801,0.001326834,0.000458686,0.0002646858,0.000003774754],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007505054,"about_ca_system_score_gemma":0.00007017302,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002830685,"about_ca_topic_score_gemma":0.0001093293,"domain_scores_codex":[0.9972449,0.00005821538,0.0008290811,0.0007447165,0.0004732499,0.0006498649],"domain_scores_gemma":[0.9987779,0.00004139858,0.0001746684,0.0008099522,0.00009972524,0.00009637356],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000471116,0.001372309,0.318984,0.0004013588,0.00299336,0.0002580489,0.001111747,0.3481484,0.2359494,0.0307482,0.00004684026,0.05993923],"study_design_scores_gemma":[0.00116313,0.00002293663,0.05339545,0.0003075041,0.0002665021,0.000001207907,0.00001580114,0.9240307,0.01961994,0.0004645163,0.0001982265,0.000514105],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1557139,0.000216582,0.843126,0.00003499359,0.0002051601,0.0002978162,0.00000184796,0.0002781544,0.0001256123],"genre_scores_gemma":[0.7972538,0.00001760168,0.2024623,0.00008774707,0.00001543004,0.00003520083,0.000005810441,0.00001350307,0.0001086729],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6415399,"threshold_uncertainty_score":0.9998593,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05193979241721546,"score_gpt":0.3293895904679666,"score_spread":0.2774497980507512,"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."}}