{"id":"W4387951505","doi":"10.2139/ssrn.4612967","title":"Identifying Representational Structure in Ca1 to Benchmark Theoretical Models of Cognitive Mapping","year":2023,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Cognitive Science and Mapping","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"","keywords":"Benchmark (surveying); Cognitive map; Cognition; Cognitive science; Computer science; Artificial intelligence; Psychology; Machine learning; Neuroscience; Geography; Cartography","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","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.002991823,0.0002825669,0.0004242109,0.001017868,0.0001648852,0.0002746407,0.001569001,0.0001811185,0.00002420474],"category_scores_gemma":[0.0005892248,0.0002783868,0.000201051,0.001082654,0.0001503083,0.000571786,0.001792862,0.003420915,0.00001280548],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000667341,"about_ca_system_score_gemma":0.003830522,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000127524,"about_ca_topic_score_gemma":0.0005189938,"domain_scores_codex":[0.995308,0.0002477163,0.0006982745,0.000827808,0.0009258291,0.001992402],"domain_scores_gemma":[0.9982844,0.000395635,0.0003669877,0.0003438256,0.0004636965,0.0001454751],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00002413092,0.00003647378,0.000679594,0.0000383894,0.0001304711,0.00003843433,0.005413973,0.006153438,0.0005465577,0.9680958,0.00002831956,0.01881446],"study_design_scores_gemma":[0.0003092645,0.00005991656,0.002939939,0.0008186544,0.00001530551,0.0001186858,0.003724959,0.02351424,0.0001969299,0.9680196,0.000002275411,0.0002802201],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1318085,0.0003936705,0.8646148,0.001228867,0.0006921688,0.0003875702,0.00002362807,0.0000434636,0.0008072898],"genre_scores_gemma":[0.9953616,0.0005286296,0.003598202,0.000135103,0.0001914917,0.00002011673,0.00001785926,0.00001913362,0.0001278708],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8635531,"threshold_uncertainty_score":0.9999669,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03959915087315247,"score_gpt":0.3149050248051757,"score_spread":0.2753058739320233,"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."}}