{"id":"W4400835982","doi":"10.61784/wjit3001","title":"SUMMAGAN: ENHANCING WEB NEWS SUMMARIZATION THROUGH GENERATIVE ADVERSARIAL NETWORKS","year":2024,"lang":"en","type":"article","venue":"World Journal of Information Technology ","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Automatic summarization; Adversarial system; Generative grammar; Computer science; Generative adversarial network; World Wide Web; Information retrieval; Artificial intelligence; Deep learning","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":[0.001023164,0.00009233729,0.0002021981,0.001040286,0.0002830184,0.0001936034,0.000229468,0.0001277819,0.0002292318],"category_scores_gemma":[0.0003912217,0.00008064098,0.0001250862,0.002300052,0.0001430888,0.00193526,0.00004017223,0.0003582523,0.00003514222],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001786191,"about_ca_system_score_gemma":0.0004260871,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006167738,"about_ca_topic_score_gemma":0.001263063,"domain_scores_codex":[0.9985738,0.0001389401,0.000694539,0.00007040663,0.000340316,0.0001819878],"domain_scores_gemma":[0.998837,0.0002279283,0.0003891706,0.00007025343,0.0004306598,0.000044975],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00002741196,0.00001556249,0.0004267853,0.00001301573,0.000139942,0.000009479934,0.005638415,0.01573966,0.0001220586,0.6659632,0.008919965,0.3029845],"study_design_scores_gemma":[0.0003444045,0.00006417298,0.0000578556,0.0001070047,0.00008153744,0.00001843231,0.004548939,0.03581292,0.0005265088,0.06893629,0.8893301,0.0001717836],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002301709,0.0009149974,0.9659595,0.01067725,0.00190023,0.0001062577,0.000002093207,0.0001372194,0.01800077],"genre_scores_gemma":[0.9339358,0.000926887,0.06187484,0.0006459091,0.001438415,0.000005171355,0.00002117233,0.000009238091,0.001142626],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.931634,"threshold_uncertainty_score":0.3288444,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01302985140628786,"score_gpt":0.3145772466450879,"score_spread":0.3015473952388,"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."}}