{"id":"W4405761894","doi":"10.1007/978-3-031-73147-1_6","title":"Generative Information Retrieval Evaluation","year":2024,"lang":"en","type":"book-chapter","venue":"˜The œinformation retrieval series","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Generative grammar; Information retrieval; Computer science; Artificial intelligence","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":[0.004486223,0.0009759371,0.001265296,0.001919482,0.0006852454,0.004073926,0.001677483,0.001219627,0.02225921],"category_scores_gemma":[0.01971113,0.0005743284,0.0008491206,0.002015957,0.001846821,0.004332582,0.002000132,0.001930706,0.006585587],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002627495,"about_ca_system_score_gemma":0.001182925,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00170752,"about_ca_topic_score_gemma":0.002557416,"domain_scores_codex":[0.9941972,0.003197213,0.0001632455,0.0005144457,0.001698573,0.0002293348],"domain_scores_gemma":[0.9919862,0.004946543,0.0001761759,0.001738813,0.0009902067,0.0001620637],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009054865,0.0001184426,0.0005134942,0.0001841051,0.00004447612,0.00002923257,0.0001653988,0.01769478,0.001374979,0.6222066,0.03032144,0.3272565],"study_design_scores_gemma":[0.00002889803,0.00008434276,0.0007780382,0.00009917357,0.00004721419,0.0001246983,0.00007509531,0.2568102,0.003713905,0.7042145,0.03398485,0.00003913343],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01749895,0.006038916,0.7350858,0.002514583,0.0003271069,0.000336562,0.0006065536,0.00315169,0.2344398],"genre_scores_gemma":[0.6364752,0.003037666,0.2308344,0.001020257,0.0004871638,0.0004814925,0.0020146,0.00176827,0.1238809],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02225921,"threshold_uncertainty_score":0.07446444,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02459505392412266,"score_gpt":0.2591735759338347,"score_spread":0.234578522009712,"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."}}