{"id":"W4412554184","doi":"10.22214/ijraset.2025.73052","title":"Enhancing Technical Documentation through Intelligent Text Summarization Techniques","year":2025,"lang":"en","type":"article","venue":"International Journal for Research in Applied Science and Engineering Technology","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Automatic summarization; Documentation; Computer science; Technical documentation; Information retrieval; Natural language processing; World Wide Web; Programming language","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":[0.003485153,0.001829991,0.0009209435,0.006735365,0.0008690841,0.002522903,0.001409568,0.0009354036,0.002648505],"category_scores_gemma":[0.01780965,0.0004437126,0.001386156,0.00446507,0.0005074871,0.003184392,0.001650453,0.001341589,0.003461689],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006536476,"about_ca_system_score_gemma":0.001419015,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002153049,"about_ca_topic_score_gemma":0.003561141,"domain_scores_codex":[0.9973815,0.0009513263,0.0003811481,0.0006236984,0.0005634594,0.00009885047],"domain_scores_gemma":[0.9889671,0.005609158,0.001458384,0.001332599,0.002471943,0.000160912],"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":[0.0002483995,0.0001690345,0.002046798,0.00170864,0.0001100466,0.0002911911,0.001544017,0.01203143,0.02839136,0.002090517,0.01776946,0.9335991],"study_design_scores_gemma":[0.0003759128,0.001644762,0.01569059,0.0008601087,0.001163121,0.001461564,0.003795119,0.5807056,0.1566588,0.02341178,0.2139169,0.0003157306],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07990965,0.003388589,0.8715758,0.0009951296,0.0003851107,0.0009995452,0.005564443,0.03176273,0.005418943],"genre_scores_gemma":[0.1655772,0.001913051,0.8015342,0.0001822823,0.0003069466,0.0008286092,0.0239945,0.001025262,0.004637985],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006735365,"threshold_uncertainty_score":0.01843148,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03231267546222466,"score_gpt":0.425018475019682,"score_spread":0.3927057995574573,"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."}}