{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:U6ODENF2JWIIOFFYPRGABWYUCD","short_pith_number":"pith:U6ODENF2","canonical_record":{"source":{"id":"1807.10244","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-07-26T17:07:05Z","cross_cats_sorted":[],"title_canon_sha256":"482812628abfe3b782dd95fc3f7ebab4cf0cce0fb774580c4adc0e7d57685c0f","abstract_canon_sha256":"e49303f477a24e146da7f1de6bb89ee0b97b0a3c39b757d33cda6d4e0ae068ca"},"schema_version":"1.0"},"canonical_sha256":"a79c3234ba4d908714b87c4c00db1410ffcbfdceb85eee83269a3a28a5286f0e","source":{"kind":"arxiv","id":"1807.10244","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.10244","created_at":"2026-05-18T00:09:42Z"},{"alias_kind":"arxiv_version","alias_value":"1807.10244v1","created_at":"2026-05-18T00:09:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.10244","created_at":"2026-05-18T00:09:42Z"},{"alias_kind":"pith_short_12","alias_value":"U6ODENF2JWII","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"U6ODENF2JWIIOFFY","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"U6ODENF2","created_at":"2026-05-18T12:32:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:U6ODENF2JWIIOFFYPRGABWYUCD","target":"record","payload":{"canonical_record":{"source":{"id":"1807.10244","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-07-26T17:07:05Z","cross_cats_sorted":[],"title_canon_sha256":"482812628abfe3b782dd95fc3f7ebab4cf0cce0fb774580c4adc0e7d57685c0f","abstract_canon_sha256":"e49303f477a24e146da7f1de6bb89ee0b97b0a3c39b757d33cda6d4e0ae068ca"},"schema_version":"1.0"},"canonical_sha256":"a79c3234ba4d908714b87c4c00db1410ffcbfdceb85eee83269a3a28a5286f0e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:09:42.759742Z","signature_b64":"ANB2+fll0H7CX6Lv/cog7K6Fb2K5lcPJsj4r/KDjXAw6otq3EAiIhA73T9CdSDdg/cjFQXl9LP5dYVTtGnBCBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a79c3234ba4d908714b87c4c00db1410ffcbfdceb85eee83269a3a28a5286f0e","last_reissued_at":"2026-05-18T00:09:42.759158Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:09:42.759158Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1807.10244","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:09:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oAn/Tv0fdd7ssCbo+kTC1zllrPncBy2CHuk/h7Qs1WXNCjRuG4eqdX84UPLrQnEdAkdypl24COZHBkC0zHVAAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T08:06:17.139661Z"},"content_sha256":"a3426611e22f969aaaab280cb3893823f319d38410fa5a787d02adfff8fd6e0a","schema_version":"1.0","event_id":"sha256:a3426611e22f969aaaab280cb3893823f319d38410fa5a787d02adfff8fd6e0a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:U6ODENF2JWIIOFFYPRGABWYUCD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Action-Constrained Markov Decision Processes With Kullback-Leibler Cost","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Ana Bu\\v{s}i\\'c, Sean Meyn","submitted_at":"2018-07-26T17:07:05Z","abstract_excerpt":"This paper concerns computation of optimal policies in which the one-step reward function contains a cost term that models Kullback-Leibler divergence with respect to nominal dynamics. This technique was introduced by Todorov in 2007, where it was shown under general conditions that the solution to the average-reward optimality equations reduce to a simple eigenvector problem. Since then many authors have sought to apply this technique to control problems and models of bounded rationality in economics.\n  A crucial assumption is that the input process is essentially unconstrained. For example, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.10244","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2026-05-18T00:09:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rzjZITLH4ZxJsWwg9TLk49ftdmzL9VpZY/5f4StxkQL4llNjwiNoMe59RasIcR4uDodZUCxtm+BlCJMGMONuBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T08:06:17.140007Z"},"content_sha256":"fc217e8bfadbf8db5aa2e25392833a694b0b27207c8f2a78dc39e7d2f0440641","schema_version":"1.0","event_id":"sha256:fc217e8bfadbf8db5aa2e25392833a694b0b27207c8f2a78dc39e7d2f0440641"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/U6ODENF2JWIIOFFYPRGABWYUCD/bundle.json","state_url":"https://pith.science/pith/U6ODENF2JWIIOFFYPRGABWYUCD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/U6ODENF2JWIIOFFYPRGABWYUCD/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":"2026-06-27T08:06:17Z","links":{"resolver":"https://pith.science/pith/U6ODENF2JWIIOFFYPRGABWYUCD","bundle":"https://pith.science/pith/U6ODENF2JWIIOFFYPRGABWYUCD/bundle.json","state":"https://pith.science/pith/U6ODENF2JWIIOFFYPRGABWYUCD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/U6ODENF2JWIIOFFYPRGABWYUCD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:U6ODENF2JWIIOFFYPRGABWYUCD","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":"e49303f477a24e146da7f1de6bb89ee0b97b0a3c39b757d33cda6d4e0ae068ca","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-07-26T17:07:05Z","title_canon_sha256":"482812628abfe3b782dd95fc3f7ebab4cf0cce0fb774580c4adc0e7d57685c0f"},"schema_version":"1.0","source":{"id":"1807.10244","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.10244","created_at":"2026-05-18T00:09:42Z"},{"alias_kind":"arxiv_version","alias_value":"1807.10244v1","created_at":"2026-05-18T00:09:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.10244","created_at":"2026-05-18T00:09:42Z"},{"alias_kind":"pith_short_12","alias_value":"U6ODENF2JWII","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"U6ODENF2JWIIOFFY","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"U6ODENF2","created_at":"2026-05-18T12:32:56Z"}],"graph_snapshots":[{"event_id":"sha256:fc217e8bfadbf8db5aa2e25392833a694b0b27207c8f2a78dc39e7d2f0440641","target":"graph","created_at":"2026-05-18T00:09:42Z","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"},"paper":{"abstract_excerpt":"This paper concerns computation of optimal policies in which the one-step reward function contains a cost term that models Kullback-Leibler divergence with respect to nominal dynamics. This technique was introduced by Todorov in 2007, where it was shown under general conditions that the solution to the average-reward optimality equations reduce to a simple eigenvector problem. Since then many authors have sought to apply this technique to control problems and models of bounded rationality in economics.\n  A crucial assumption is that the input process is essentially unconstrained. For example, ","authors_text":"Ana Bu\\v{s}i\\'c, Sean Meyn","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-07-26T17:07:05Z","title":"Action-Constrained Markov Decision Processes With Kullback-Leibler Cost"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.10244","kind":"arxiv","version":1},"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:a3426611e22f969aaaab280cb3893823f319d38410fa5a787d02adfff8fd6e0a","target":"record","created_at":"2026-05-18T00:09:42Z","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":"e49303f477a24e146da7f1de6bb89ee0b97b0a3c39b757d33cda6d4e0ae068ca","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-07-26T17:07:05Z","title_canon_sha256":"482812628abfe3b782dd95fc3f7ebab4cf0cce0fb774580c4adc0e7d57685c0f"},"schema_version":"1.0","source":{"id":"1807.10244","kind":"arxiv","version":1}},"canonical_sha256":"a79c3234ba4d908714b87c4c00db1410ffcbfdceb85eee83269a3a28a5286f0e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a79c3234ba4d908714b87c4c00db1410ffcbfdceb85eee83269a3a28a5286f0e","first_computed_at":"2026-05-18T00:09:42.759158Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:09:42.759158Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ANB2+fll0H7CX6Lv/cog7K6Fb2K5lcPJsj4r/KDjXAw6otq3EAiIhA73T9CdSDdg/cjFQXl9LP5dYVTtGnBCBg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:09:42.759742Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.10244","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a3426611e22f969aaaab280cb3893823f319d38410fa5a787d02adfff8fd6e0a","sha256:fc217e8bfadbf8db5aa2e25392833a694b0b27207c8f2a78dc39e7d2f0440641"],"state_sha256":"a921ddfe3b80086b36c36d15cd6c4450abb7a733e1d7c7f50c707f017f6056e3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l590eHvyIDPps8sLK+8XuxhY0HrWO1wvWZyVPv43y1GCg7CCHhl0jDj5zE7klqkPB13NcSRQ9cmaxSjMGlZ5DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-27T08:06:17.141907Z","bundle_sha256":"7918f821b19c727ea0be234825920577410d36b6af76e7f1956d0348eba99d59"}}