{"id":"W2889713213","doi":"","title":"Bayesian Inference of Temporal Task Specifications from Demonstrations","year":2018,"lang":"en","type":"article","venue":"DSpace@MIT (Massachusetts Institute of Technology)","topic":"Formal Methods in Verification","field":"Computer Science","cited_by":46,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Inference; Task (project management); Artificial intelligence; Machine learning; Prior probability; Probabilistic logic; Bayesian inference; Bayesian probability; Domain (mathematical analysis)","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006417848,0.0009361388,0.000963927,0.001890451,0.0004872351,0.002039349,0.001863718,0.001598691,0.006761936],"category_scores_gemma":[0.07423412,0.001486272,0.00154489,0.001033822,0.001506971,0.003604124,0.002302542,0.003043792,0.001190662],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001796996,"about_ca_system_score_gemma":0.002436153,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01227438,"about_ca_topic_score_gemma":0.02362621,"domain_scores_codex":[0.9961588,0.001699421,0.0002359321,0.0007775393,0.0008508745,0.0002775197],"domain_scores_gemma":[0.9437303,0.04716896,0.002508208,0.002803267,0.003004225,0.0007850079],"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":[0.001672464,0.0002500035,0.01321747,0.0006652168,0.0003605231,0.0007510455,0.0009058638,0.6121289,0.006237217,0.1762618,0.007601178,0.1799484],"study_design_scores_gemma":[0.00006562989,0.00004568745,0.001213834,0.00007167241,0.00003110169,0.00005059601,0.00004399082,0.89025,0.001806004,0.1050526,0.001343134,0.00002574821],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06034791,0.0003978926,0.9297957,0.0009499094,0.00005926553,0.0001398689,0.002004856,0.001833312,0.004471219],"genre_scores_gemma":[0.877364,0.0003197202,0.1154102,0.0001921027,0.00006683281,0.0002757465,0.003089508,0.0004138838,0.002868066],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01227438,"threshold_uncertainty_score":0.03394121,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03832744405571576,"score_gpt":0.293282919196827,"score_spread":0.2549554751411112,"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."}}