{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:RY5IEFHVWGTGMPK77GKJD3XK6B","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"0adde001874354c7f8027a2af49584ee426b899b38cc4bfc53fa5ce59ebae873","cross_cats_sorted":["cond-mat.stat-mech","cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-24T20:47:42Z","title_canon_sha256":"9ed46163019924eb3033f578517d156adc17917386a0dd57a670f75dd49c8fbc"},"schema_version":"1.0","source":{"id":"1906.10228","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.10228","created_at":"2026-07-05T03:18:23Z"},{"alias_kind":"arxiv_version","alias_value":"1906.10228v2","created_at":"2026-07-05T03:18:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.10228","created_at":"2026-07-05T03:18:23Z"},{"alias_kind":"pith_short_12","alias_value":"RY5IEFHVWGTG","created_at":"2026-07-05T03:18:23Z"},{"alias_kind":"pith_short_16","alias_value":"RY5IEFHVWGTGMPK7","created_at":"2026-07-05T03:18:23Z"},{"alias_kind":"pith_short_8","alias_value":"RY5IEFHV","created_at":"2026-07-05T03:18:23Z"}],"graph_snapshots":[{"event_id":"sha256:8056ba83df9a66103dc5306ac7b804d7944e593ac557d39b1e8f67a0f82aec12","target":"graph","created_at":"2026-07-05T03:18:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1906.10228/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sequential decision making in the presence of uncertainty and stochastic dynamics gives rise to distributions over state/action trajectories in reinforcement learning (RL) and optimal control problems. This observation has led to a variety of connections between RL and inference in probabilistic graphical models (PGMs). Here we explore a different dimension to this relationship, examining reinforcement learning using the tools and abstractions of statistical physics. The central object in the statistical physics abstraction is the idea of a partition function $\\mathcal{Z}$, and here we constru","authors_text":"Jad Rahme, Ryan P. Adams","cross_cats":["cond-mat.stat-mech","cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-24T20:47:42Z","title":"A Theoretical Connection Between Statistical Physics and Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.10228","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c650cf9f2f63a29a8d7c1b84b91ceed528315a10762a506f43c1df69640b3929","target":"record","created_at":"2026-07-05T03:18:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"0adde001874354c7f8027a2af49584ee426b899b38cc4bfc53fa5ce59ebae873","cross_cats_sorted":["cond-mat.stat-mech","cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-24T20:47:42Z","title_canon_sha256":"9ed46163019924eb3033f578517d156adc17917386a0dd57a670f75dd49c8fbc"},"schema_version":"1.0","source":{"id":"1906.10228","kind":"arxiv","version":2}},"canonical_sha256":"8e3a8214f5b1a6663d5ff99491eeeaf064e2af9674e07a30de28c492a629d145","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8e3a8214f5b1a6663d5ff99491eeeaf064e2af9674e07a30de28c492a629d145","first_computed_at":"2026-07-05T03:18:23.426103Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:18:23.426103Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TXhTE9/ZGEbhbafV5//PS6D3j/+O47GnM4fyMSUC/KCO27xHXRkJXgDkO0Ff/aI8faywiPS7LqE6ve/GchQMCg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:18:23.426573Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.10228","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c650cf9f2f63a29a8d7c1b84b91ceed528315a10762a506f43c1df69640b3929","sha256:8056ba83df9a66103dc5306ac7b804d7944e593ac557d39b1e8f67a0f82aec12"],"state_sha256":"59b01a775ae81f8cc81c24d6f1708ff1fe01103736222958ee54761ff00cb500"}