{"id":"W1968799289","doi":"10.1145/2808194.2809493","title":"Pooling for User-Oriented Evaluation Measures","year":2015,"lang":"en","type":"article","venue":"","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; University of Waterloo","keywords":"Pooling; Automatic summarization; Computer science; Information retrieval; Relevance (law); Focus (optics); Rank (graph theory); Order (exchange); World Wide Web; Data mining; Artificial intelligence","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":[],"consensus_categories":[],"category_scores_codex":[0.05764604,0.002883157,0.002492372,0.005302119,0.001218405,0.004776396,0.002702809,0.002126324,0.004299282],"category_scores_gemma":[0.1337782,0.0007692087,0.001767484,0.003512864,0.001826086,0.008245225,0.004378678,0.002058984,0.001003956],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002380307,"about_ca_system_score_gemma":0.002022841,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001582857,"about_ca_topic_score_gemma":0.001177029,"domain_scores_codex":[0.958465,0.02534838,0.003106511,0.004588203,0.007058783,0.001433165],"domain_scores_gemma":[0.9102951,0.05593948,0.006192429,0.01628962,0.009457757,0.001825543],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.003212957,0.001310423,0.02555662,0.001239178,0.002003223,0.0003150907,0.001470373,0.1744717,0.01419733,0.08961911,0.01288258,0.6737214],"study_design_scores_gemma":[0.0001590003,0.002877237,0.01344957,0.0001988661,0.0006182493,0.0003193733,0.0003243934,0.8125026,0.0179423,0.1421346,0.009229559,0.0002441936],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0531081,0.00142446,0.9338701,0.000534377,0.0001316491,0.001287656,0.0008349291,0.001838634,0.006969986],"genre_scores_gemma":[0.7481385,0.000314145,0.2441711,0.000374474,0.0003863105,0.001896571,0.001656584,0.00034245,0.002719703],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.05764604,"threshold_uncertainty_score":0.3048651,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1201717971347841,"score_gpt":0.3264951012284474,"score_spread":0.2063233040936634,"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."}}