{"id":"W6891699748","doi":"10.48448/xx6e-jf10","title":"AI Agents Learn to Trust","year":2023,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; McGill University","funders":"","keywords":"Task (project management); Reinforcement learning; Cornerstone; Work (physics); Social learning; Intelligent agent; Human intelligence","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":[0.001802193,0.0005152502,0.0003975859,0.0003302613,0.0006684169,0.002025561,0.0007772279,0.001401376,0.003513914],"category_scores_gemma":[0.02132463,0.0002958477,0.0003403877,0.0002600309,0.00192218,0.003181323,0.001834704,0.001998823,0.0008882763],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008373269,"about_ca_system_score_gemma":0.001070005,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002192471,"about_ca_topic_score_gemma":0.001979057,"domain_scores_codex":[0.9985337,0.0006854615,0.00007091949,0.0002679906,0.0003168268,0.0001249522],"domain_scores_gemma":[0.9936978,0.003084218,0.001049843,0.001065747,0.0007456735,0.0003566482],"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":[0.0001820857,0.0002224799,0.01592921,0.000229136,0.0002153443,0.0004387987,0.002147517,0.1672597,0.008957611,0.6748406,0.01043202,0.1191454],"study_design_scores_gemma":[0.00004630035,0.0001050061,0.00180071,0.00004753603,0.00004091006,0.0001307745,0.000426881,0.4537922,0.002029049,0.5272641,0.01428354,0.00003293491],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2289679,0.0006408474,0.6843906,0.01035197,0.0002683223,0.0001637934,0.0002037884,0.0006013898,0.07441135],"genre_scores_gemma":[0.9488665,0.0002634229,0.04375836,0.0006506742,0.00004322818,0.00009863714,0.00008750257,0.0000569841,0.006174741],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003513914,"threshold_uncertainty_score":0.01175517,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04543487919129324,"score_gpt":0.3538621786037605,"score_spread":0.3084272994124672,"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."}}