{"id":"W4400582718","doi":"10.1016/j.crsus.2024.100132","title":"Human-AI collaboration to identify literature for evidence synthesis","year":2024,"lang":"en","type":"article","venue":"Cell Reports Sustainability","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canada Excellence Research Chairs, Government of Canada; Commonwealth Scientific and Industrial Research Organisation","keywords":"Data science; Computer science; Computational biology; Biology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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":[0.6085993,0.004176068,0.007933136,0.05434933,0.007969456,0.01865138,0.008182321,0.006766142,0.04267271],"category_scores_gemma":[0.7510889,0.003597012,0.006173261,0.0283229,0.006249039,0.01588911,0.03305363,0.006059747,0.009609497],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01098685,"about_ca_system_score_gemma":0.1127538,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004206209,"about_ca_topic_score_gemma":0.00930941,"domain_scores_codex":[0.28108,0.5660534,0.1041765,0.01581915,0.02859403,0.004276928],"domain_scores_gemma":[0.09241508,0.7320663,0.03804484,0.05901167,0.07056627,0.007895815],"domain_codex":"methods","domain_gemma":"methods","domain_candidate":"methods","domain_consensus":"methods","study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003528778,0.0006977416,0.004934283,0.07853862,0.00326943,0.001616488,0.08373095,0.002613059,0.007136062,0.03041803,0.03464019,0.7488764],"study_design_scores_gemma":[0.006669517,0.001842564,0.01105536,0.1019666,0.006131188,0.001846381,0.04897095,0.02599172,0.01731749,0.267929,0.5085495,0.001729717],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02234751,0.01952128,0.7476335,0.03471301,0.005030664,0.127118,0.00378717,0.00505174,0.03479706],"genre_scores_gemma":[0.06447848,0.00295281,0.806732,0.004008874,0.0007451411,0.1167097,0.001006818,0.0005365527,0.00282959],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.3914007,"threshold_uncertainty_score":0.4826668,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02086993838902473,"score_gpt":0.3690641302084106,"score_spread":0.3481941918193858,"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."}}