{"id":"W4392681658","doi":"10.22318/icls2023.645029","title":"Situating Evaluation: Theory Driven Evaluation in Practice","year":2023,"lang":"en","type":"article","venue":"Proceedings.","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Trent University","funders":"","keywords":"Autoethnography; Knowledge management; Computer science; Sociology; Engineering ethics; Management science; Social science; Engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.07276905,0.0001315082,0.0001833313,0.0006313874,0.0002098242,0.0003873133,0.0004320828,0.00007791772,0.002409132],"category_scores_gemma":[0.03735081,0.0001065993,0.00005412918,0.003146185,0.00004060772,0.001841069,0.0001275601,0.0002029142,0.002577051],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002565352,"about_ca_system_score_gemma":0.0004721638,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006059836,"about_ca_topic_score_gemma":0.0000215611,"domain_scores_codex":[0.9916617,0.0004066838,0.0007979491,0.0005679351,0.006240397,0.0003252923],"domain_scores_gemma":[0.9945824,0.001269924,0.0004159108,0.0002090138,0.003449332,0.0000734308],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00009194043,0.0001196696,0.06763504,0.00001596312,0.00003090562,0.000002012262,0.01853403,0.009864305,0.001232877,0.04141304,0.01551946,0.8455408],"study_design_scores_gemma":[0.00094945,0.00005910199,0.08774962,0.00004323043,0.00005708861,0.00000488254,0.01997549,0.8069899,0.000208965,0.0723581,0.01143405,0.0001701176],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6501712,0.0001259029,0.0001937846,0.005803702,0.0005879386,0.001225577,0.000001885547,0.0001431086,0.3417469],"genre_scores_gemma":[0.996646,0.00003523663,0.001353591,0.0005445853,0.0001786122,0.0003255572,0.00001487284,0.00001225117,0.000889221],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8453707,"threshold_uncertainty_score":0.9985028,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3177210124840651,"score_gpt":0.5597948644746129,"score_spread":0.2420738519905478,"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."}}