{"id":"W2953536802","doi":"10.1145/3331184.3331270","title":"Time-Limits and Summaries for Faster Relevance Assessing","year":2019,"lang":"en","type":"article","venue":"","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Relevance (law); Computer science; Time limit; Information retrieval; Limit (mathematics); Recall; Quality (philosophy); Time constraint; Precision and recall; Constraint (computer-aided design); Psychology; Mathematics; Cognitive psychology; Engineering","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":[0.007191588,0.0008368894,0.0008920944,0.001303053,0.0004304106,0.002507285,0.0008483678,0.001081961,0.0120042],"category_scores_gemma":[0.1156376,0.0004527019,0.0005195591,0.001048164,0.0003771089,0.004486859,0.001362943,0.0009319866,0.001818192],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004311642,"about_ca_system_score_gemma":0.0005214459,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006301044,"about_ca_topic_score_gemma":0.000872834,"domain_scores_codex":[0.9942865,0.002648159,0.0009010285,0.000765443,0.001223648,0.0001751459],"domain_scores_gemma":[0.8702614,0.1045791,0.007890307,0.007614864,0.007139313,0.002515042],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.009453516,0.001022311,0.0205703,0.006388951,0.000226164,0.001020284,0.01314655,0.004777359,0.1943328,0.009222481,0.01864401,0.7211953],"study_design_scores_gemma":[0.004370125,0.04073983,0.2590995,0.004140777,0.001931909,0.006722191,0.01197083,0.07110517,0.1863034,0.05905741,0.3526405,0.001918379],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7718501,0.007426321,0.1953015,0.001712235,0.000621784,0.001247037,0.001337245,0.009953536,0.0105502],"genre_scores_gemma":[0.7769122,0.001228346,0.2160496,0.0004008286,0.0002066781,0.000961713,0.0009394646,0.0008105722,0.002490611],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0120042,"threshold_uncertainty_score":0.04015803,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02156852508941057,"score_gpt":0.2779240253901927,"score_spread":0.2563555003007821,"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."}}