{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001290963,0.00152082,0.0007553052,0.01006046,0.001656268,0.001929657,0.001693958,0.001125969,0.01523412],"category_scores_gemma":[0.007010464,0.0003424674,0.0008145195,0.008165689,0.000635856,0.001744191,0.00175616,0.001268032,0.01706601],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001253924,"about_ca_system_score_gemma":0.002258762,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02865908,"about_ca_topic_score_gemma":0.06357514,"domain_scores_codex":[0.9982643,0.0003768541,0.0003008933,0.0004086338,0.0004999057,0.0001494969],"domain_scores_gemma":[0.9962499,0.0009431156,0.0004565173,0.0006662777,0.001364327,0.0003198456],"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":[0.0003598587,0.0001232996,0.004223583,0.004117615,0.0001358148,0.0004683925,0.001409456,0.0008871929,0.007635419,0.001515506,0.9088137,0.07031018],"study_design_scores_gemma":[0.0001291802,0.0001115156,0.02937214,0.0004795081,0.0001819175,0.0005522068,0.001720241,0.004465381,0.007828698,0.001212929,0.9537964,0.0001499731],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.01512606,0.002559237,0.004601604,0.0008140111,0.0005151177,0.000333671,0.9469258,0.01318762,0.01593684],"genre_scores_gemma":[0.00906199,0.0004076653,0.008968535,0.0001445131,0.0001080833,0.0003019292,0.9769732,0.0004865294,0.003547567],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.02865908,"threshold_uncertainty_score":0.05698454,"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."}}