{"id":"W2807789242","doi":"10.46867/ijcp.2018.31.01.13","title":"More than a Fluke: Lessons Learned from a Failure to Replicate the False Belief Task in Dolphins","year":2018,"lang":"en","type":"article","venue":"International Journal of Comparative Psychology","topic":"Primate Behavior and Ecology","field":"Psychology","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"St. Mary's University","funders":"","keywords":"Replicate; Psychology; Task (project management); Comparative cognition; Feeling; Cognitive psychology; Replication (statistics); Theory of mind; Social psychology; Cognition","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":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0006214313,0.0002245562,0.0004994426,0.0004588114,0.00008119073,0.00004838962,0.00156946,0.0001877547,0.001803845],"category_scores_gemma":[0.00007864169,0.0001661491,0.0001650473,0.0002851202,0.0003974945,0.0001335828,0.0001631715,0.000684004,0.001048961],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001194395,"about_ca_system_score_gemma":0.00006627559,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002225296,"about_ca_topic_score_gemma":0.001362427,"domain_scores_codex":[0.9975969,0.0004373328,0.000823095,0.000438642,0.0003244575,0.00037954],"domain_scores_gemma":[0.9979436,0.0003074921,0.0005246971,0.0005013896,0.0005819382,0.0001408582],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.01461416,0.00482763,0.1644794,0.000003259677,0.002851065,0.00166138,0.1594372,0.0001544685,0.1464119,0.04079054,0.4262004,0.03856865],"study_design_scores_gemma":[0.003096645,0.0009409946,0.8296908,0.00003910393,0.00004579512,0.0006828374,0.00286787,0.00001840335,0.0008163755,0.01457682,0.1469782,0.0002461224],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8979625,0.0001458763,0.001879764,0.09083609,0.003335269,0.00019533,0.00007446356,0.00001741766,0.005553273],"genre_scores_gemma":[0.9923956,0.0000230727,0.0006456512,0.005588624,0.0009443884,0.00004270312,0.00001447398,0.00001894908,0.0003265854],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6652114,"threshold_uncertainty_score":0.9997289,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1605285553001988,"score_gpt":0.4939250825684105,"score_spread":0.3333965272682117,"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."}}