{"id":"W4416575445","doi":"10.3390/computers14120508","title":"NewsSumm: The World’s Largest Human-Annotated Multi-Document News Summarization Dataset for Indian English","year":2025,"lang":"en","type":"article","venue":"Computers","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Automatic summarization; Newspaper; Timeline; Journalism; Consistency (knowledge bases); Scale (ratio); Indian English; Domain (mathematical analysis); Quality (philosophy)","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":[0.0003185782,0.0001743867,0.0001714519,0.0002107753,0.0003638675,0.0004679016,0.00153576,0.00004924578,0.0000047446],"category_scores_gemma":[0.00005611117,0.0001458949,0.0000646868,0.0005738373,0.00003857249,0.0003963022,0.0005662118,0.0001509841,0.000008562076],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008222429,"about_ca_system_score_gemma":0.00007976369,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000179686,"about_ca_topic_score_gemma":0.0007773488,"domain_scores_codex":[0.9985623,0.00009081587,0.0003358461,0.0005101426,0.0001640727,0.000336829],"domain_scores_gemma":[0.9985331,0.0002055899,0.0001062264,0.0009763284,0.0001088365,0.00006987522],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001676864,0.0002353876,0.004591604,0.0001356958,0.0001976395,0.00002082472,0.004448527,0.02575433,0.0001818662,0.2011644,0.6028648,0.1603882],"study_design_scores_gemma":[0.001714185,0.00004038202,0.001330497,0.0001028503,0.00002587914,0.000001147208,0.00008337093,0.4912609,0.000555541,0.002333232,0.5021979,0.000354052],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001702717,0.00006176165,0.9912996,0.003623153,0.002197456,0.0006711012,0.0000775001,0.000180782,0.0001859371],"genre_scores_gemma":[0.4314404,0.00002647181,0.5373236,0.02010001,0.001066355,0.0003544638,0.004738703,0.00006031457,0.004889736],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4655066,"threshold_uncertainty_score":0.5949421,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02732516811302219,"score_gpt":0.3085124555013454,"score_spread":0.2811872873883232,"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."}}