{"id":"W4386699143","doi":"10.18060/26528","title":"Evaluating the Accuracy of scite, a Smart Citation Index","year":2023,"lang":"en","type":"article","venue":"Hypothesis Research Journal for Health Information Professionals","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Regina","funders":"","keywords":"Citation; Meaning (existential); Categorization; Recall; Context (archaeology); Computer science; Sample (material); Information retrieval; Precision and recall; Data science; Psychology; Artificial intelligence; Library science; Cognitive psychology; Geography","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":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.02480955,0.00009139936,0.0002344662,0.001053381,0.001799281,0.00008044751,0.0001975124,0.0001033936,0.0001516415],"category_scores_gemma":[0.03125542,0.00005800149,0.0001102231,0.001597827,0.0001082161,0.0008774307,0.00004540317,0.0006769443,0.0001846285],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002737673,"about_ca_system_score_gemma":0.004241462,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008758738,"about_ca_topic_score_gemma":0.00000802318,"domain_scores_codex":[0.9954552,0.0007093596,0.001453906,0.0001022497,0.001705147,0.0005741309],"domain_scores_gemma":[0.9868976,0.007969717,0.0008036326,0.0002533927,0.003788478,0.000287107],"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":[0.0009575459,0.00009844703,0.002808707,0.001391288,0.00003624797,4.102536e-7,0.01442641,0.0001987942,0.0003331086,0.001071154,0.09805325,0.8806247],"study_design_scores_gemma":[0.002063349,0.008597812,0.2834435,0.009688874,0.00006278403,0.0003275367,0.2032038,0.1476386,0.01418585,0.1563636,0.1738119,0.0006124031],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8161395,0.0002686236,0.001648972,0.1766649,0.001211716,0.003606896,0.00003133911,0.00005239277,0.0003756467],"genre_scores_gemma":[0.9896921,0.0008209312,0.002318077,0.004729766,0.0004807584,0.0005428861,0.00007781642,0.00001950435,0.00131816],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8800122,"threshold_uncertainty_score":0.9995002,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7332254577048797,"score_gpt":0.6609661716199537,"score_spread":0.07225928608492593,"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."}}