{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0649516,0.0009022214,0.0007264442,0.0006228613,0.001332267,0.001329193,0.002865507,0.001551526,0.0008959809],"category_scores_gemma":[0.102559,0.0004066031,0.0005748659,0.000303195,0.006513532,0.003283354,0.001914958,0.005303258,0.0002796687],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001710434,"about_ca_system_score_gemma":0.00288839,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0130953,"about_ca_topic_score_gemma":0.0186549,"domain_scores_codex":[0.986007,0.009509934,0.0007706602,0.001436147,0.001992679,0.0002835663],"domain_scores_gemma":[0.9535818,0.02651825,0.002086156,0.009053684,0.007923448,0.0008366755],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001649656,0.001798107,0.04311232,0.001547505,0.000425051,0.002497138,0.09155264,0.00194881,0.01989316,0.03243003,0.01611434,0.7870314],"study_design_scores_gemma":[0.001063232,0.0213773,0.2517846,0.01258412,0.001566784,0.01710477,0.04901943,0.01377779,0.1051871,0.1483512,0.3770972,0.00108652],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8273392,0.01142892,0.1044498,0.03668929,0.002432266,0.001254672,0.0003112649,0.0003509859,0.01574362],"genre_scores_gemma":[0.768375,0.008827231,0.1954823,0.01399455,0.000760808,0.003002315,0.0003199111,0.0003792193,0.008858603],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9350484,"threshold_uncertainty_score":0.343501,"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."}}