{"paper":{"title":"Control-Gibbs Distribution: Sampling for Optimal Control and Diverse Actions","arxiv_id":"2611.17034","primary_cat":"eess.SY","submitted_at":"2026-11-12T16:21:09+00:00","version_compiled":"v1"},"notice":"Every quoted sentence is the authors' text from the arXiv listing abstract. Labels and probabilities are the outputs of classifier-1.13.0 on the question bank abstract-p1-20260923, exactly as returned. No sentence in this record was written by a language model.","schema":"pith.compiled-record/v0","status":"compiled","abstract":{"source":"arXiv listing abstract v1","sentences":[{"i":0,"p":1.0,"id":"s0","own":false,"role":"background","text":"While conventional optimal control selects an optimal input sequence, probabilistic control assigns probability mass over all possible inputs and exploits a distribution of control sequences.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.06,"main_claim_p":0.04,"quantitative":false,"quantitative_p":0.42,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.0,"background":1.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":1,"p":0.97,"id":"s1","own":false,"role":"background","text":"Control distributions help enable exploration, capture diverse solutions, and solve deterministic optimal control problems.","hedge":{"p":0.85,"label":"asserted"},"own_p":0.09,"main_claim_p":0.09,"quantitative":false,"quantitative_p":0.04,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.0,"background":0.97,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.03}},{"i":2,"p":0.48,"id":"s2","own":false,"role":"contribution","text":"This work reviews an important probabilistic model for control distributions, the control-Gibbs distribution, i.e., the Gibbs distribution with an optimal control objective as the energy function.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.16,"main_claim_p":0.1,"quantitative":false,"quantitative_p":0.05,"role_probabilities":{"gap":0.0,"method":0.11,"result":0.0,"background":0.41,"limitation":0.0,"future_work":0.0,"contribution":0.48,"interpretation":0.0}},{"i":3,"p":0.78,"id":"s3","own":false,"role":"contribution","text":"We point out its fundamental role in various probabilistic control frameworks, e.g., maximum entropy control, control-as-inference framework, model predictive path integral control, and energy-based models for control.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.48,"main_claim_p":0.11,"quantitative":false,"quantitative_p":0.06,"role_probabilities":{"gap":0.0,"method":0.01,"result":0.02,"background":0.13,"limitation":0.0,"future_work":0.0,"contribution":0.78,"interpretation":0.06}},{"i":4,"p":0.59,"id":"s4","own":true,"role":"interpretation","text":"This provides a model-central perspective to unify these probabilistic control frameworks.","hedge":{"p":0.96,"label":"asserted"},"own_p":0.55,"main_claim_p":0.18,"quantitative":false,"quantitative_p":0.04,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.01,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.4,"interpretation":0.59}},{"i":5,"p":0.54,"id":"s5","own":false,"role":"contribution","text":"We also review the associated extensions of dynamic programming for computing closed-loop control distributions.","hedge":{"p":0.9,"label":"asserted"},"own_p":0.24,"main_claim_p":0.04,"quantitative":false,"quantitative_p":0.03,"role_probabilities":{"gap":0.0,"method":0.24,"result":0.0,"background":0.22,"limitation":0.0,"future_work":0.0,"contribution":0.54,"interpretation":0.0}},{"i":6,"p":0.86,"id":"s6","own":true,"role":"method","text":"To sample the control-Gibbs distribution, we consider projected Langevin sampling and develop non-asymptotic guarantees.","hedge":{"p":0.94,"label":"asserted"},"own_p":0.93,"main_claim_p":0.08,"quantitative":false,"quantitative_p":0.09,"role_probabilities":{"gap":0.0,"method":0.86,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.14,"interpretation":0.0}},{"i":7,"p":0.5,"id":"s7","own":true,"role":"result","text":"The guarantees show the dual benefits of sampling the control-Gibbs distribution: obtaining diverse control solutions and solving the deterministic optimal control problem.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.86,"main_claim_p":0.52,"quantitative":false,"quantitative_p":0.08,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.5,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.01,"interpretation":0.49}},{"i":8,"p":0.68,"id":"s8","own":true,"role":"result","text":"We provide a numerical example where diverse arm trajectories are sampled from a control-Gibbs distribution.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.94,"main_claim_p":0.06,"quantitative":false,"quantitative_p":0.06,"role_probabilities":{"gap":0.0,"method":0.02,"result":0.68,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.3,"interpretation":0.0}}]},"compiled":{"main_claim":{"p":0.94,"text":"The guarantees show the dual benefits of sampling the control-Gibbs distribution: obtaining diverse control solutions and solving the deterministic optimal control problem.","location":"abstract s7","hedge_strength":{"p":1.0,"label":"asserted"}},"provenance":{"route":{"via":"TypeSafe API","model":"classifier-1.13.0","endpoint":"https://api.typesafe.ai/v1/systemone","provider":"TypeSafe"},"packing":"one request per paper","requests":1,"input_tokens":6771,"cost_usd_reported":0.0},"compiled_at":"2026-11-13","bank_version":"abstract-p1-20260923","model_version":"classifier-1.13.0","abstract_states":{"claims_first":0.03,"states_limitation":0.09,"human_participants":0.03,"controlled_comparison":0.04,"randomized_assignment":0.01,"states_quantitative_result":0.1,"compares_with_prior_results":0.16,"mentions_code_or_data_availability":0.03},"evidential_basis":{"p":0.39,"value":"proof or derivation","probabilities":{"argument":0.08,"literature":0.36,"proof_or_derivation":0.39,"analysis_of_existing_data":0.0,"observation_or_experiment":0.0,"simulation_or_computation":0.17}},"contribution_type":{"p":0.87,"value":"review","probabilities":{"review":0.87,"method_or_tool":0.09,"empirical_study":0.0,"simulation_study":0.0,"theoretical_result":0.04,"dataset_or_benchmark":0.0,"position_or_commentary":0.0}},"contribution_statement":{"p":1.0,"text":"To sample the control-Gibbs distribution, we consider projected Langevin sampling and develop non-asymptotic guarantees.","location":"abstract s6"}},"coverage":{"tier":"abstract","levels_run":["P abstract"],"not_examined":["full text","figures and tables","references and citing sentences","relations to other papers"],"sources_read":["arXiv listing abstract v1"],"levels_not_run":["S sections","T body sentences","C citations","R cross-paper relations"],"sentences_examined":9,"sentences_in_abstract":9},"measured_accuracy":{"url":"https://pith.science/accuracy","measured_on":"2026-10-02","method":"two independent model families labelled a fresh random sample blind; the figure is how often the published label matches their consensus","sentence_role_agreement":0.92,"main_claim_agreement":0.908,"typed_citation_agreement":0.933,"typed_citation_agreement_95_interval":[0.917,0.945],"review_comments_accurate":0.758,"review_comments_accurate_95_interval":[0.684,0.82],"review_caught_admitted_error_found_or_related":0.448,"review_comments_judged":{"judged_by":["gpt-5.6-luna","grok-4.7"],"judged_against":"Pith's own text copy of each paper: text extracted from the PDF, the first 90,000 characters","measured_on":"2026-10-04","accurate":113,"decided":149,"sampled_reviews":200,"split_by_lane":false,"by_lane":"https://pith.science/accuracy#by-lane"}}}