{"id":"W7106853700","doi":"10.48448/k3h9-vp64","title":"Agent-to-Agent Theory of Mind: Testing Interlocutor Awareness among Large Language Models","year":2025,"lang":"","type":"other","venue":"Open MIND","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Situational ethics; Adaptation (eye); Identity (music); Context (archaeology); Adversarial system; Situation awareness","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":[],"consensus_categories":[],"category_scores_codex":[0.01449091,0.000788113,0.0006859396,0.0009611167,0.0008441629,0.003268662,0.001706701,0.001451343,0.002822157],"category_scores_gemma":[0.08981577,0.0006631697,0.001206863,0.0004323208,0.003225179,0.006904982,0.004743448,0.002518322,0.0003180044],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00128758,"about_ca_system_score_gemma":0.001626664,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003838835,"about_ca_topic_score_gemma":0.001787344,"domain_scores_codex":[0.9920728,0.004943185,0.0002618883,0.001472881,0.0009900312,0.0002593598],"domain_scores_gemma":[0.9038632,0.07239847,0.007229238,0.01214473,0.002046648,0.002317701],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.004771515,0.004289628,0.2106065,0.0008357586,0.002132833,0.0007846024,0.04208326,0.3118142,0.02650116,0.1486282,0.003488895,0.2440634],"study_design_scores_gemma":[0.0002157109,0.001047949,0.01777523,0.0000718637,0.0002124229,0.0001857486,0.002444609,0.8647925,0.004182505,0.1074235,0.001549755,0.0000982176],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8070493,0.0001258573,0.1799502,0.0007089185,0.0000614301,0.0002720754,0.00009228144,0.0004959954,0.01124392],"genre_scores_gemma":[0.9728673,0.00003785259,0.02629328,0.0001371986,0.00001415283,0.0001535746,0.00007785037,0.00005440297,0.0003644324],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01449091,"threshold_uncertainty_score":0.0766362,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06060035860332392,"score_gpt":0.3364359515722423,"score_spread":0.2758355929689184,"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."}}