{"id":"W4254782289","doi":"10.31234/osf.io/f86jq","title":"ManyDogs 1: A Multi-lab replication study of dogs' pointing comprehension (pre-registered report)","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Human-Animal Interaction Studies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Ostensive definition; Comprehension; Replicate; Psychology; Cognitive psychology; Open science; Computer science; Communication; Linguistics; Statistics; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004075137,0.0003428403,0.0005543505,0.00008903215,0.000103152,0.00007084046,0.0002989463,0.0002973735,0.00006396438],"category_scores_gemma":[0.0004870544,0.0003370333,0.0002405022,0.00007473964,0.00006150734,0.000004917491,0.002332115,0.0003394475,0.000005127452],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003895108,"about_ca_system_score_gemma":0.00007105817,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001641786,"about_ca_topic_score_gemma":0.001975504,"domain_scores_codex":[0.996816,0.0001862248,0.00107441,0.001448181,0.000273757,0.0002014657],"domain_scores_gemma":[0.9954637,0.00002473953,0.001079198,0.002539297,0.0008372883,0.0000558057],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0002101355,0.001865961,0.01931554,0.0002817242,0.0009874527,0.00009861522,0.001721327,0.0002514917,0.9707349,0.000008800938,0.003041948,0.001482108],"study_design_scores_gemma":[0.005811162,0.002398306,0.4750935,0.0009832446,0.0007997312,0.0007673239,0.02307847,0.002643659,0.4686209,0.0000366478,0.01725463,0.002512427],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9935125,0.000491064,0.002848401,0.0001027863,0.0004367278,0.0009079111,0.000008710009,0.00004803402,0.001643854],"genre_scores_gemma":[0.9903097,0.00008350565,0.004228223,0.0001010085,0.0001326269,0.0001370816,0.0003888916,0.00004456006,0.004574458],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.502114,"threshold_uncertainty_score":0.9999081,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07902633004438037,"score_gpt":0.4084373751120144,"score_spread":0.3294110450676341,"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."}}