{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01989158,0.00154929,0.001690202,0.003303248,0.0009475274,0.003518926,0.002432174,0.001184088,0.001995481],"category_scores_gemma":[0.07063317,0.0005447837,0.0006631002,0.001982076,0.0008848154,0.004737599,0.001928159,0.001740263,0.0009082495],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001572173,"about_ca_system_score_gemma":0.002620996,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005936036,"about_ca_topic_score_gemma":0.006909025,"domain_scores_codex":[0.9815395,0.009531423,0.001600195,0.002023609,0.004748022,0.0005571861],"domain_scores_gemma":[0.9223487,0.0508955,0.004409085,0.008054656,0.01246192,0.001830047],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.005323207,0.001560658,0.01921914,0.0009825864,0.0004469433,0.0002180225,0.001474112,0.08349424,0.04646783,0.008625009,0.008160511,0.8240277],"study_design_scores_gemma":[0.0003166984,0.002222776,0.007567165,0.0000705622,0.000162931,0.0001483908,0.0002977181,0.9490947,0.02763653,0.008440946,0.003901457,0.0001402243],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1460529,0.001305302,0.8353775,0.0003741175,0.0001734897,0.001591617,0.000657135,0.01059339,0.003874555],"genre_scores_gemma":[0.6573714,0.000174995,0.3382344,0.0001428028,0.0001224557,0.0008942721,0.00104639,0.0005254887,0.001487718],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9801084,"threshold_uncertainty_score":0.105198,"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."}}