{"id":"W4403443325","doi":"10.48550/arxiv.2408.03943","title":"Building Machines that Learn and Think with People","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"AI in Service Interactions","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Cambridge Trust; Natural Sciences and Engineering Research Council of Canada; Alan Turing Institute; European Commission; Leverhulme Trust; National Science Foundation","keywords":"Psychology; Computer science","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001197647,0.0002865983,0.0002445965,0.0002703423,0.0001718084,0.0003905768,0.001208822,0.0001647993,0.00002715416],"category_scores_gemma":[0.00000937293,0.0002731357,0.00009231504,0.0004913128,0.00006285831,0.0004545275,0.00407022,0.0009342504,0.00009270685],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000119818,"about_ca_system_score_gemma":0.0001166468,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008274124,"about_ca_topic_score_gemma":0.0007909986,"domain_scores_codex":[0.9984432,0.00006400901,0.0001035745,0.001041767,0.00009470699,0.0002526937],"domain_scores_gemma":[0.9986212,0.0001416222,0.0001255074,0.0009034207,0.00008544844,0.000122784],"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":[0.00004818937,0.00009773253,0.01720382,0.000595787,0.0004460313,0.001051917,0.004498442,0.1567665,0.00007352817,0.8150308,0.0009585811,0.003228673],"study_design_scores_gemma":[0.0001867364,0.00005214257,0.00190134,0.0003285126,0.0001237687,0.00008013912,0.0002540622,0.8369054,0.00007567138,0.1584129,0.00117552,0.0005037338],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6242018,0.000189659,0.369413,0.0008054161,0.0007920805,0.0001882179,0.000008398911,0.0005289267,0.003872566],"genre_scores_gemma":[0.9877449,0.00009441945,0.009527292,0.0001270521,0.00006730013,8.170945e-7,0.00000303331,0.0000245839,0.002410642],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.680139,"threshold_uncertainty_score":0.9999721,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0462153179255044,"score_gpt":0.1981232866788791,"score_spread":0.1519079687533747,"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."}}