{"id":"W2489879551","doi":"","title":"Evidence-based Principles to Guide Collaborative Approaches to Evaluation: Technical Report","year":2015,"lang":"en","type":"article","venue":"","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University","funders":"","keywords":"Computer science; Management science; Engineering ethics; Data science; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2053217,0.003170287,0.00289581,0.01070073,0.00226223,0.01027801,0.004767956,0.00620599,0.01370208],"category_scores_gemma":[0.3388346,0.002470997,0.004613761,0.006447819,0.003494766,0.009166517,0.008579923,0.006270851,0.009770391],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00509887,"about_ca_system_score_gemma":0.02382791,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004349248,"about_ca_topic_score_gemma":0.005841093,"domain_scores_codex":[0.8489664,0.08811612,0.02019597,0.003209933,0.03817458,0.001336937],"domain_scores_gemma":[0.7128268,0.1785785,0.01231456,0.02211264,0.07186645,0.002300968],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000169,0.0004849893,0.002133941,0.006615704,0.0006799491,0.0003030471,0.001793098,0.01397626,0.001641206,0.2142191,0.1235143,0.6344693],"study_design_scores_gemma":[0.0003294868,0.0005694827,0.004165086,0.02037997,0.00131275,0.000988027,0.0014646,0.04559298,0.01116178,0.5103879,0.403275,0.0003729475],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0007738491,0.004159754,0.9721127,0.009732466,0.0004870985,0.003157706,0.0005643852,0.000621529,0.008390605],"genre_scores_gemma":[0.008065338,0.002973567,0.9826912,0.0006726389,0.0002331465,0.00235894,0.0006393563,0.0001760075,0.00218966],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7946783,"threshold_uncertainty_score":0.9799798,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9049027782050624,"score_gpt":0.5776800492054441,"score_spread":0.3272227289996182,"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."}}