{"id":"W4409813933","doi":"10.1016/j.procs.2025.03.116","title":"Harnessing Large Language Models for Precision Topic Extraction and Technology Patent Nomination: A GPT-centric Methodology","year":2025,"lang":"en","type":"article","venue":"Procedia Computer Science","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Cégep de Rimouski; Université du Québec à Rimouski","funders":"","keywords":"Computer science; Nomination; Patent analysis; Extraction (chemistry); Data science; Data mining","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":[],"consensus_categories":[],"category_scores_codex":[0.001240161,0.0001511705,0.0002348693,0.001094821,0.0003809396,0.0002481401,0.001061967,0.00009748287,8.467633e-7],"category_scores_gemma":[0.000264794,0.0001391645,0.00004005905,0.002644734,0.0001686312,0.001506248,0.0008153834,0.0001367588,0.000001073599],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001167575,"about_ca_system_score_gemma":0.0001906029,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002815941,"about_ca_topic_score_gemma":0.000004361428,"domain_scores_codex":[0.9981924,0.00004544543,0.0002837042,0.000836662,0.0002367241,0.0004050662],"domain_scores_gemma":[0.9986023,0.0002852446,0.0001531965,0.0004775914,0.0004211895,0.00006050917],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000004674598,0.00006381311,0.0003648118,0.0000405981,0.000006620153,0.000003315907,0.0006071475,0.0002571459,0.007501202,0.1600098,0.00006334122,0.8310775],"study_design_scores_gemma":[0.0002728058,0.00005896132,0.000417366,0.00004240782,0.000009918082,0.00001937841,0.0000266196,0.8633972,0.02362499,0.1115496,0.0004412569,0.0001394572],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009205055,0.0005810159,0.9877444,0.001203335,0.000375145,0.0004085095,7.820467e-7,0.0003832533,0.00009851494],"genre_scores_gemma":[0.3713441,0.00002607742,0.6282994,0.0001599385,0.00003244031,0.00007053462,7.14379e-7,0.000003434814,0.0000633471],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.86314,"threshold_uncertainty_score":0.5674963,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04369533804685807,"score_gpt":0.3513519287723578,"score_spread":0.3076565907254998,"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."}}