{"id":"W2338920854","doi":"10.1145/2911451.2911494","title":"Interleaved Evaluation for Retrospective Summarization and Prospective Notification on Document Streams","year":2016,"lang":"en","type":"article","venue":"","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Automatic summarization; Redundancy (engineering); Timeline; Information retrieval; Interleaving; Ranking (information retrieval); Multi-document summarization; Task (project management); Data mining","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0006704773,0.00008267808,0.00008268523,0.000101983,0.0001245844,0.0001378728,0.0001416856,0.00003185211,0.00003190962],"category_scores_gemma":[0.0001665644,0.00005100565,0.00002618286,0.0001544759,0.00002705505,0.0008461189,0.00004359556,0.00003028656,0.00002786308],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003589895,"about_ca_system_score_gemma":0.00006222641,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007421117,"about_ca_topic_score_gemma":0.000007875869,"domain_scores_codex":[0.9989994,0.00004549675,0.0001924844,0.0002565481,0.000367195,0.0001389472],"domain_scores_gemma":[0.9990881,0.00007038414,0.0001034427,0.0002081762,0.0004781224,0.00005173914],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00003802958,0.00004137524,0.002450381,0.000005084314,0.000009323679,4.732956e-8,0.0009450141,0.000003766178,0.001736081,0.3947167,0.000369992,0.5996843],"study_design_scores_gemma":[0.007211328,0.003956118,0.5170864,0.0001864141,0.00003107514,0.000004935462,0.0003758459,0.1382114,0.2019328,0.1283131,0.001936308,0.0007542067],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03265543,0.000004893026,0.9607646,0.003171535,0.00015719,0.001514666,0.000008841506,0.00009679965,0.001626048],"genre_scores_gemma":[0.9928034,0.00000724249,0.005767426,0.0001296801,0.00002392066,0.0001985,0.0000131093,0.000003857298,0.001052873],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.960148,"threshold_uncertainty_score":0.207995,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0216528133450966,"score_gpt":0.2928018438465414,"score_spread":0.2711490305014448,"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."}}