{"id":"W3083137311","doi":"10.1145/3409256.3409816","title":"Offline Evaluation without Gain","year":2020,"lang":"en","type":"article","venue":"","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Compatibility (geochemistry); Computer science; Learning to rank; Ranking (information retrieval); Ideal solution; Information retrieval; Data mining; Artificial intelligence; Machine learning; Engineering","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":[0.01018573,0.001824423,0.002273585,0.002470372,0.0009461395,0.004847242,0.00217011,0.001489456,0.01216768],"category_scores_gemma":[0.03511453,0.0005692546,0.00081156,0.002151376,0.001363503,0.006679889,0.003564004,0.001716736,0.005714823],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001831627,"about_ca_system_score_gemma":0.002263337,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001982635,"about_ca_topic_score_gemma":0.002518973,"domain_scores_codex":[0.9788675,0.00890494,0.0009495441,0.002210626,0.008077447,0.0009900022],"domain_scores_gemma":[0.9715968,0.01247503,0.001235219,0.009087946,0.004675847,0.0009291128],"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":[0.002449866,0.001000151,0.006813703,0.0005837595,0.0002300101,0.0002359479,0.0006521785,0.03179564,0.02794992,0.05818114,0.01939727,0.8507105],"study_design_scores_gemma":[0.0003514743,0.002612627,0.00861217,0.0002422627,0.000253635,0.0009367484,0.0006937531,0.7604314,0.04015344,0.1467637,0.0386994,0.0002493068],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.08186799,0.001889386,0.8587125,0.0008911216,0.0002557219,0.0008257207,0.0008857258,0.007205341,0.0474666],"genre_scores_gemma":[0.6861792,0.0003984693,0.2962973,0.0004357767,0.0003162764,0.0005509959,0.001115914,0.001218227,0.01348777],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.01216768,"threshold_uncertainty_score":0.05386794,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08723976651019504,"score_gpt":0.3242659391810598,"score_spread":0.2370261726708648,"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."}}