{"id":"W3196754070","doi":"10.1007/s10791-022-09411-0","title":"Shallow pooling for sparse labels","year":2022,"lang":"en","type":"article","venue":"Information Retrieval","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Ranking (information retrieval); Mean reciprocal rank; Information retrieval; Pooling; Computer science; Relevance (law); Set (abstract data type); Rank (graph theory); Learning to rank; Preference; Artificial intelligence; Statistics; Mathematics; Combinatorics","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":[0.001051676,0.0001191742,0.0001312044,0.0003009828,0.0007185334,0.0003476872,0.0008470055,0.00004336391,0.0002137286],"category_scores_gemma":[0.0001713136,0.0001206884,0.0001088002,0.0007920345,0.00002139512,0.003685426,0.0003918732,0.0002256353,0.0001922615],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001600988,"about_ca_system_score_gemma":0.0002050814,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006186282,"about_ca_topic_score_gemma":2.831904e-7,"domain_scores_codex":[0.9981591,0.00004089025,0.0005264307,0.0001193601,0.0008040195,0.000350185],"domain_scores_gemma":[0.9989461,0.000100815,0.0002103754,0.0003312665,0.0003007505,0.0001107154],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000644945,0.0001925728,0.0006500225,0.0001751894,0.0000629955,0.0000100564,0.01452293,0.01145196,0.0007654493,0.73159,0.01750919,0.2224247],"study_design_scores_gemma":[0.002012526,0.0006285805,0.001442775,0.000006472383,0.00001038287,0.00006582828,0.0006074102,0.318732,0.002915881,0.002673634,0.6704598,0.0004447014],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07467826,0.00003426994,0.9095519,0.002393947,0.001901267,0.001462768,0.000213074,0.0006218875,0.009142665],"genre_scores_gemma":[0.9702983,0.0000048884,0.02342345,0.004593429,0.0001012856,0.0001654993,0.0002870214,0.00001159533,0.001114538],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.89562,"threshold_uncertainty_score":0.552645,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02332481057054104,"score_gpt":0.2593679142488165,"score_spread":0.2360431036782755,"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."}}