{"id":"W4367175790","doi":"10.1080/02763869.2023.2193122","title":"Librarian and Researcher Assessments of Search Result Relevance: How Well Do They Align?","year":2023,"lang":"en","type":"article","venue":"Medical Reference Services Quarterly","topic":"Health Sciences Research and Education","field":"Health Professions","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Rubric; Relevance (law); Interview; Medical education; Information retrieval; Computer science; Psychology; MEDLINE; Medicine; Mathematics education; Sociology; Political science","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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.007162312,0.0001607533,0.0003224037,0.0003468874,0.000610791,0.00007799964,0.0009127122,0.0003856567,0.001323765],"category_scores_gemma":[0.0006329502,0.0001171206,0.00002961882,0.001126567,0.0002524185,0.0005714826,0.0002081678,0.001373276,0.0009274194],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007717021,"about_ca_system_score_gemma":0.002372353,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004291905,"about_ca_topic_score_gemma":0.002560223,"domain_scores_codex":[0.9931548,0.001775313,0.0005994557,0.0005546881,0.002610817,0.001304902],"domain_scores_gemma":[0.9951126,0.002424312,0.0001604066,0.0005557201,0.0004289673,0.001318004],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0009562251,0.0005401963,0.2140426,0.01462125,0.0001074827,0.0001074237,0.1308448,0.000001740894,0.002627635,0.01170644,0.1135022,0.5109419],"study_design_scores_gemma":[0.002932086,0.003603317,0.6160116,0.003866096,0.00001484503,0.000003947629,0.2011033,0.006584242,0.0001040546,0.02026872,0.1449602,0.000547556],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9506224,0.0001183332,0.00003042648,0.02902833,0.0004490349,0.0007338337,0.00004374058,0.000114626,0.01885931],"genre_scores_gemma":[0.9910384,0.001309217,0.0002221451,0.0007230266,0.0003396283,0.0001308874,0.0001147521,0.00002087111,0.006101042],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5103944,"threshold_uncertainty_score":0.9998505,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1681793684858725,"score_gpt":0.5108772863021858,"score_spread":0.3426979178163133,"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."}}