{"id":"W3211375313","doi":"10.18653/v1/2021.findings-emnlp.351","title":"Textual Time Travel: A Temporally Informed Approach to Theory of Mind","year":2021,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Computer science; Theory of mind; Mental model; Artificial intelligence; Prior probability; Question answering; False belief; Cognitive science; Psychology; Cognition","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.0003107091,0.00007648139,0.0001737329,0.00006389715,0.00001994328,0.00004541222,0.0004863248,0.00004000776,0.0001065806],"category_scores_gemma":[0.00008587581,0.00006205171,0.00005546635,0.0002587273,0.00001540516,0.0001722106,0.0002464752,0.00005253283,0.0000971905],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001360779,"about_ca_system_score_gemma":0.0002736672,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006195272,"about_ca_topic_score_gemma":0.000002811268,"domain_scores_codex":[0.9991056,0.00004017261,0.0002468675,0.0002331127,0.0002178576,0.0001563421],"domain_scores_gemma":[0.9992489,0.00008201851,0.00003947588,0.0004693897,0.00008265294,0.00007758231],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001640353,0.0001790316,0.0001267676,0.00003827144,0.00004470745,0.00001120343,0.006409001,0.0008644957,0.006532351,0.8193423,0.001701995,0.1647335],"study_design_scores_gemma":[0.002865583,0.0003163472,0.004919633,0.0001275706,0.00003554346,0.0002062885,0.006041461,0.8146186,0.1318459,0.02569989,0.01194024,0.001382936],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01201217,0.00001268496,0.730394,0.0001989646,0.00002455246,0.00008431573,6.704642e-7,0.00002320093,0.2572494],"genre_scores_gemma":[0.4885709,4.328651e-7,0.4972187,0.0004827235,0.00002314946,0.000005227557,0.00000193728,0.000003897861,0.01369302],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8137541,"threshold_uncertainty_score":0.2530395,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03008536709781423,"score_gpt":0.2419270496363388,"score_spread":0.2118416825385245,"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."}}