{"id":"W2572801983","doi":"","title":"On Measuring Learning in Search: A Position Paper.","year":2016,"lang":"en","type":"article","venue":"International ACM SIGIR Conference on Research and Development in Information Retrieval","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Position (finance); Position paper; Artificial intelligence; World Wide Web; Business","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":[],"consensus_categories":[],"category_scores_codex":[0.002485545,0.0001604625,0.0001460868,0.001714472,0.0001963887,0.0005561628,0.0009731079,0.0001070578,0.0001987185],"category_scores_gemma":[0.002020401,0.0001197642,0.0000225295,0.0006310417,0.00009399194,0.003268639,0.0004808233,0.0006039075,0.0006072358],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005838822,"about_ca_system_score_gemma":0.0005324457,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002564316,"about_ca_topic_score_gemma":0.00001301442,"domain_scores_codex":[0.9963912,0.0001689803,0.0006243131,0.0002646083,0.002036165,0.0005147113],"domain_scores_gemma":[0.9978524,0.0008563731,0.00008756274,0.0002498383,0.0007872569,0.0001665061],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00154657,0.0003045027,0.01582461,0.00005387566,0.00002419792,0.00005534713,0.005823573,0.0002228717,0.002823713,0.5336387,0.0002874652,0.4393946],"study_design_scores_gemma":[0.01895153,0.004160909,0.7170405,0.004252336,0.000001994673,0.0001048701,0.002980557,0.04273108,0.1027564,0.05541367,0.04919762,0.002408563],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9483938,0.000006301076,0.02045588,0.0120979,0.0003322929,0.0005944079,0.000009481513,0.000123046,0.0179869],"genre_scores_gemma":[0.9972332,0.0001018337,0.001816201,0.0003254733,0.00001724581,0.00003875616,0.00002577925,0.000004554621,0.0004370278],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7012159,"threshold_uncertainty_score":0.780499,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1178411601090776,"score_gpt":0.3387865003556234,"score_spread":0.2209453402465458,"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."}}