{"id":"W7117232809","doi":"10.5206/cjils-rcsib.v49i1.23075","title":"Assessing the Effectiveness of AI Tools (Elicit, SciSpace, and Consensus) in Literature Review and Research","year":2025,"lang":"en","type":"article","venue":"Canadian Journal of Information and Library Science","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Automatic summarization; Strengths and weaknesses; Workflow; Relation (database); Systematic review; Sample (material)","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6111416,0.002288064,0.003388527,0.07445661,0.006388727,0.02120339,0.004603324,0.004089714,0.003889716],"category_scores_gemma":[0.7893592,0.002767443,0.004951034,0.04765427,0.006709295,0.02828304,0.02062506,0.003518501,0.001292425],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0123363,"about_ca_system_score_gemma":0.02779803,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002398743,"about_ca_topic_score_gemma":0.01035451,"domain_scores_codex":[0.2213796,0.5982031,0.105841,0.009964904,0.06121715,0.003394207],"domain_scores_gemma":[0.05053503,0.8311973,0.03442048,0.02605788,0.05574063,0.00204867],"domain_codex":"methods","domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001249752,0.0007022195,0.02027931,0.05168707,0.001969998,0.0003629833,0.08875167,0.002453562,0.00309539,0.01642946,0.008667703,0.8043509],"study_design_scores_gemma":[0.004113588,0.01031978,0.1014318,0.1785557,0.01277991,0.003594865,0.2781917,0.04878802,0.03346004,0.1492778,0.1758847,0.003602259],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2948873,0.02516772,0.4990718,0.02558487,0.002279393,0.0794551,0.002820219,0.005582266,0.06515134],"genre_scores_gemma":[0.1819903,0.003240354,0.7811955,0.001528916,0.000209485,0.03053868,0.000408654,0.0002092322,0.0006788829],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.3888584,"threshold_uncertainty_score":0.4795316,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3458123296977866,"score_gpt":0.5079584312152706,"score_spread":0.162146101517484,"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."}}