{"id":"W2960780327","doi":"10.3758/s13428-019-01270-w","title":"The role of number of items per trial in best–worst scaling experiments","year":2019,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Decision-Making and Behavioral Economics","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Scaling; Latent semantic analysis; Set (abstract data type); Computer science; Dimension (graph theory); Value (mathematics); Statistics; Cognitive psychology; Natural language processing; Artificial intelligence; Psychology; Machine learning; Mathematics","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","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.03751411,0.0001540687,0.0005867789,0.0004909112,0.0001597042,0.0002264467,0.001741616,0.0001752175,0.001044736],"category_scores_gemma":[0.003997165,0.0000985205,0.0002569762,0.001095572,0.0003835403,0.0002564439,0.0006115073,0.0005306545,0.0004379502],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009930014,"about_ca_system_score_gemma":0.0001824018,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004520066,"about_ca_topic_score_gemma":0.0000225137,"domain_scores_codex":[0.9919124,0.003167466,0.001517996,0.0005957253,0.00225171,0.0005546602],"domain_scores_gemma":[0.9890143,0.008456059,0.0003531472,0.001362506,0.0006749153,0.0001390798],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001967838,0.0005174216,0.07867879,0.000001678785,0.000004370988,0.000002774314,0.0007973807,0.00001098742,0.03218628,0.0003977132,0.00005728958,0.8853775],"study_design_scores_gemma":[0.0484401,0.003244326,0.07776773,0.0005623159,0.0001076966,0.000049764,0.1062294,0.003358951,0.3913872,0.2590115,0.1081803,0.001660791],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9922188,0.0003254417,0.00009036763,0.00003373731,0.0007073535,0.0008893122,0.00001127329,0.000006812703,0.005716931],"genre_scores_gemma":[0.9785376,0.0000246217,0.01979317,0.000003089227,0.00005319129,0.0001196766,0.000001017572,0.00002304226,0.001444542],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8837167,"threshold_uncertainty_score":0.9998685,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5703808539984128,"score_gpt":0.6897069463044384,"score_spread":0.1193260923060256,"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."}}