{"id":"W2618664687","doi":"10.3758/s13428-017-0898-2","title":"Scoring best-worst data in unbalanced many-item designs, with applications to crowdsourcing semantic judgments","year":2017,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Multi-Criteria Decision Making","field":"Decision Sciences","cited_by":44,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Crowdsourcing; Computer science; Set (abstract data type); Rank (graph theory); Scaling; Artificial intelligence; Natural language processing; Scoring rule; Machine learning; Data mining; Quality (philosophy); Information retrieval; 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","metaepi_narrow","sts","scholarly_communication","open_science"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04960864,0.0003118518,0.0006632626,0.001733071,0.001683303,0.003481882,0.009576035,0.0001470967,0.000263409],"category_scores_gemma":[0.02200771,0.0002455193,0.00006931555,0.001992724,0.0003224569,0.001339285,0.005308548,0.0008767196,0.0005637828],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002520274,"about_ca_system_score_gemma":0.0002625775,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005828234,"about_ca_topic_score_gemma":0.000495442,"domain_scores_codex":[0.9882504,0.002952903,0.001155942,0.002109154,0.004317763,0.001213854],"domain_scores_gemma":[0.9830592,0.005606873,0.0003934357,0.009432202,0.0009239921,0.0005843454],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0001252021,0.0002667971,0.3032376,0.00001576801,0.00000873786,0.0001614027,0.0004348221,0.00006846611,0.04559872,0.0001950904,0.0003152548,0.6495722],"study_design_scores_gemma":[0.001957209,0.0002645484,0.947202,0.0008197446,0.00004483429,0.00004921991,0.00302752,0.01201921,0.01085412,0.00270053,0.02016303,0.0008980081],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4419804,0.00008924911,0.5540556,0.0005118615,0.0002030216,0.002284819,0.00004677537,0.00004503837,0.0007832845],"genre_scores_gemma":[0.4993474,0.000007675524,0.498222,0.00002924174,0.0001069503,0.000751376,0.000007267521,0.000049692,0.001478416],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6486742,"threshold_uncertainty_score":0.9999997,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8789947781800274,"score_gpt":0.7240679895118148,"score_spread":0.1549267886682125,"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."}}