{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:RY5IEFHVWGTGMPK77GKJD3XK6B","short_pith_number":"pith:RY5IEFHV","canonical_record":{"source":{"id":"1906.10228","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-24T20:47:42Z","cross_cats_sorted":["cond-mat.stat-mech","cs.AI","stat.ML"],"title_canon_sha256":"9ed46163019924eb3033f578517d156adc17917386a0dd57a670f75dd49c8fbc","abstract_canon_sha256":"0adde001874354c7f8027a2af49584ee426b899b38cc4bfc53fa5ce59ebae873"},"schema_version":"1.0"},"canonical_sha256":"8e3a8214f5b1a6663d5ff99491eeeaf064e2af9674e07a30de28c492a629d145","source":{"kind":"arxiv","id":"1906.10228","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:RY5IEFHVWGTGMPK77GKJD3XK6B","target":"record","payload":{"canonical_record":{"source":{"id":"1906.10228","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-24T20:47:42Z","cross_cats_sorted":["cond-mat.stat-mech","cs.AI","stat.ML"],"title_canon_sha256":"9ed46163019924eb3033f578517d156adc17917386a0dd57a670f75dd49c8fbc","abstract_canon_sha256":"0adde001874354c7f8027a2af49584ee426b899b38cc4bfc53fa5ce59ebae873"},"schema_version":"1.0"},"canonical_sha256":"8e3a8214f5b1a6663d5ff99491eeeaf064e2af9674e07a30de28c492a629d145","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:18:23.426573Z","signature_b64":"TXhTE9/ZGEbhbafV5//PS6D3j/+O47GnM4fyMSUC/KCO27xHXRkJXgDkO0Ff/aI8faywiPS7LqE6ve/GchQMCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e3a8214f5b1a6663d5ff99491eeeaf064e2af9674e07a30de28c492a629d145","last_reissued_at":"2026-07-05T03:18:23.426103Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:18:23.426103Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.10228","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:18:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/BsVSVIUR48tQfGSLr23iNV5eCgpz6X/aTY9fqvrZmN7QqJHvNf7P38YXWhmwjUtgb/dUWAS8m+j/73WUEKzCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T16:03:50.136641Z"},"content_sha256":"c650cf9f2f63a29a8d7c1b84b91ceed528315a10762a506f43c1df69640b3929","schema_version":"1.0","event_id":"sha256:c650cf9f2f63a29a8d7c1b84b91ceed528315a10762a506f43c1df69640b3929"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:RY5IEFHVWGTGMPK77GKJD3XK6B","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Theoretical Connection Between Statistical Physics and Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.stat-mech","cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jad Rahme, Ryan P. Adams","submitted_at":"2019-06-24T20:47:42Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.10228","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1906.10228/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:18:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VDgU7DyMQX+iIxE4U/35asX0qOTVNDmHfOKNq+KxTAY1w246rgDVgObgLviTv+gODgRpG1t3gZ9SyR3XyU/rCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T16:03:50.137166Z"},"content_sha256":"8056ba83df9a66103dc5306ac7b804d7944e593ac557d39b1e8f67a0f82aec12","schema_version":"1.0","event_id":"sha256:8056ba83df9a66103dc5306ac7b804d7944e593ac557d39b1e8f67a0f82aec12"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RY5IEFHVWGTGMPK77GKJD3XK6B/bundle.json","state_url":"https://pith.science/pith/RY5IEFHVWGTGMPK77GKJD3XK6B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RY5IEFHVWGTGMPK77GKJD3XK6B/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T16:03:50Z","links":{"resolver":"https://pith.science/pith/RY5IEFHVWGTGMPK77GKJD3XK6B","bundle":"https://pith.science/pith/RY5IEFHVWGTGMPK77GKJD3XK6B/bundle.json","state":"https://pith.science/pith/RY5IEFHVWGTGMPK77GKJD3XK6B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RY5IEFHVWGTGMPK77GKJD3XK6B/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5FiFFhq/EAnRb/IFOXKn/Al1nO42s+IrTj+35Ro+NYggyUX1x34zUsAJH38bPGk/QZWxH7ePx92fQXPUqUZ5Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T16:03:50.141236Z","bundle_sha256":"59f4cc0103da4824f54786b90664566df21ef53ef3879aa0291d569d9443f501"}}