{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001719401,0.001432507,0.002121566,0.001166741,0.0007461854,0.001815102,0.002124665,0.002058574,0.008960826],"category_scores_gemma":[0.006325822,0.0008750011,0.00138168,0.001576713,0.001129561,0.004686048,0.00298583,0.002314791,0.002275381],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001455712,"about_ca_system_score_gemma":0.001562808,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009584728,"about_ca_topic_score_gemma":0.01471811,"domain_scores_codex":[0.9992208,0.000184027,0.0000481915,0.0002270214,0.0001525008,0.0001673862],"domain_scores_gemma":[0.99806,0.0009865154,0.0001309907,0.0005402643,0.000179737,0.0001024108],"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":[0.0007602893,0.0003662741,0.001364476,0.0005191336,0.0002626531,0.0002362693,0.000255457,0.1290361,0.02177069,0.1074845,0.03245687,0.7054873],"study_design_scores_gemma":[0.00002883352,0.00006922768,0.0004070293,0.0000312474,0.00005796073,0.00004178239,0.00002636457,0.8792862,0.004380703,0.1134881,0.002160218,0.00002219116],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01883929,0.0008545947,0.973186,0.0006998106,0.00009826892,0.00007427199,0.0008081374,0.002788971,0.002650663],"genre_scores_gemma":[0.5975841,0.001203764,0.3711297,0.0007501825,0.0004374877,0.0003437189,0.005846831,0.0008018462,0.02190244],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009584728,"threshold_uncertainty_score":0.0299769,"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."}}