{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003233985,0.0002535541,0.0003991395,0.0008005167,0.0002301396,0.00004653845,0.002272447,0.0004014243,0.00003513056],"category_scores_gemma":[0.0007515097,0.0002607213,0.0001028998,0.002148313,0.001752762,0.001069503,0.0003798045,0.000340293,0.00005741224],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007735762,"about_ca_system_score_gemma":0.0003073601,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001285684,"about_ca_topic_score_gemma":0.0001975385,"domain_scores_codex":[0.9978607,0.0000618572,0.0007533017,0.0006019972,0.0003796871,0.0003423987],"domain_scores_gemma":[0.9965466,0.0000628874,0.0006599337,0.002143709,0.0004955662,0.00009129458],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001321349,0.0002944375,0.0256859,0.00002571308,0.0001131525,0.000004984049,0.0006056781,0.00004999261,0.05311622,0.8652304,0.0009980337,0.05386221],"study_design_scores_gemma":[0.00141965,0.0009075698,0.04415816,0.0003801223,0.0001333613,0.00003356506,0.0003438722,0.05095508,0.5834877,0.1356727,0.1811987,0.001309459],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04502602,0.0001256903,0.9453655,0.003329942,0.0007970048,0.0003386998,0.0001066312,0.0004738593,0.004436674],"genre_scores_gemma":[0.5174311,0.00001875841,0.4824019,0.00002228314,0.00004121814,0.00002391806,0.00001301537,0.000007808527,0.00003991181],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7295578,"threshold_uncertainty_score":0.9999845,"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."}}