{"id":"W3217492267","doi":"10.1007/978-3-030-99739-7_18","title":"Less is Less: When are Snippets Insufficient for Human vs Machine Relevance Estimation?","year":2022,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Topic Modeling","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"Microsoft (Canada)","funders":"","keywords":"Snippet; Computer science; Information retrieval; Relevance (law); Ranking (information retrieval); Search engine; Document retrieval; Query expansion; Language model; Range (aeronautics); Artificial intelligence; Natural language processing","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":[0.008126549,0.000887038,0.001383122,0.003699747,0.001274176,0.003725786,0.001193369,0.002714832,0.007608545],"category_scores_gemma":[0.09465191,0.0005829975,0.0006964881,0.002224734,0.00141966,0.01407326,0.001527046,0.002302862,0.006082228],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006866038,"about_ca_system_score_gemma":0.00130652,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003209426,"about_ca_topic_score_gemma":0.005802188,"domain_scores_codex":[0.9930109,0.002563251,0.0006555503,0.001213687,0.002174532,0.0003819396],"domain_scores_gemma":[0.9400612,0.0444869,0.002710708,0.00388653,0.007707442,0.00114722],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003893448,0.0005494636,0.08007272,0.00165731,0.000391297,0.0007938748,0.001607416,0.00277812,0.01992393,0.007236035,0.08092405,0.8001724],"study_design_scores_gemma":[0.0005257249,0.002785228,0.280328,0.003185168,0.00258751,0.008564576,0.01401295,0.2005795,0.06532852,0.2144163,0.2069804,0.0007061716],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.711716,0.02762343,0.1647073,0.02085041,0.003379047,0.0006108157,0.007644428,0.01089275,0.05257577],"genre_scores_gemma":[0.9291766,0.002718657,0.04800677,0.0024639,0.001966572,0.0001586596,0.005981333,0.002254799,0.007272759],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008126549,"threshold_uncertainty_score":0.04297775,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03607754583885837,"score_gpt":0.2760300977723595,"score_spread":0.2399525519335012,"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."}}