{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:2BYMIE6MHEDY6GKSSOGJIWG4XU","short_pith_number":"pith:2BYMIE6M","canonical_record":{"source":{"id":"1405.6757","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-05-26T23:11:40Z","cross_cats_sorted":[],"title_canon_sha256":"ce9944de280a2346d6f7dde493aa106800a9d884825631732fb39c8abdbf73a5","abstract_canon_sha256":"560dc58191616637ccfb02773df3ec6d110a7363240a447df32793003141c985"},"schema_version":"1.0"},"canonical_sha256":"d070c413cc39078f1952938c9458dcbd2dca8c16c74a4ac05f26217c9d6498b7","source":{"kind":"arxiv","id":"1405.6757","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1405.6757","created_at":"2026-05-18T02:51:00Z"},{"alias_kind":"arxiv_version","alias_value":"1405.6757v1","created_at":"2026-05-18T02:51:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1405.6757","created_at":"2026-05-18T02:51:00Z"},{"alias_kind":"pith_short_12","alias_value":"2BYMIE6MHEDY","created_at":"2026-05-18T12:28:09Z"},{"alias_kind":"pith_short_16","alias_value":"2BYMIE6MHEDY6GKS","created_at":"2026-05-18T12:28:09Z"},{"alias_kind":"pith_short_8","alias_value":"2BYMIE6M","created_at":"2026-05-18T12:28:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:2BYMIE6MHEDY6GKSSOGJIWG4XU","target":"record","payload":{"canonical_record":{"source":{"id":"1405.6757","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-05-26T23:11:40Z","cross_cats_sorted":[],"title_canon_sha256":"ce9944de280a2346d6f7dde493aa106800a9d884825631732fb39c8abdbf73a5","abstract_canon_sha256":"560dc58191616637ccfb02773df3ec6d110a7363240a447df32793003141c985"},"schema_version":"1.0"},"canonical_sha256":"d070c413cc39078f1952938c9458dcbd2dca8c16c74a4ac05f26217c9d6498b7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:51:00.401359Z","signature_b64":"2rA5lVA6Wb39CV0Wv19caFyCoCT2kePkAGfiHZDAYH03atpPsY0mbXQxpKkKLQdjQzEvsazc0f/cBQ3lEy2FDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d070c413cc39078f1952938c9458dcbd2dca8c16c74a4ac05f26217c9d6498b7","last_reissued_at":"2026-05-18T02:51:00.400703Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:51:00.400703Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1405.6757","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":"2026-05-18T02:51:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LmVOMX3D4ygbeDYEAIcNXk1Kkgn+mGXJJCc8zuji2ul/zcLHc/X5vbru4lCxDLYz1uQkA/IxH/wGuop/nF+NCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T15:49:06.750908Z"},"content_sha256":"3d4d217e973381c16130e81ce97e41f75572d1eb9b83d9c5b1d7277c5aa6fe5d","schema_version":"1.0","event_id":"sha256:3d4d217e973381c16130e81ce97e41f75572d1eb9b83d9c5b1d7277c5aa6fe5d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:2BYMIE6MHEDY6GKSSOGJIWG4XU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Proximal Reinforcement Learning: A New Theory of Sequential Decision Making in Primal-Dual Spaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bo Liu, Ian Gemp, Ji Liu, Nicholas Jacek, Philip Thomas, Sridhar Mahadevan, Steve Giguere, Will Dabney","submitted_at":"2014-05-26T23:11:40Z","abstract_excerpt":"In this paper, we set forth a new vision of reinforcement learning developed by us over the past few years, one that yields mathematically rigorous solutions to longstanding important questions that have remained unresolved: (i) how to design reliable, convergent, and robust reinforcement learning algorithms (ii) how to guarantee that reinforcement learning satisfies pre-specified \"safety\" guarantees, and remains in a stable region of the parameter space (iii) how to design \"off-policy\" temporal difference learning algorithms in a reliable and stable manner, and finally (iv) how to integrate t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1405.6757","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":"2026-05-18T02:51:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QJqGmWl1q3PnjvhKUzOeLMddekQNfIL4xkWKmuKUP3q/AREw81i7odWoJjdzuIBdUtTOlGv57oKlGSrDmch6DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T15:49:06.751639Z"},"content_sha256":"0884bbd1e57ce77a3e68ecc7d1b36748a34f5f85b917b2d96f04bc021e12f6d8","schema_version":"1.0","event_id":"sha256:0884bbd1e57ce77a3e68ecc7d1b36748a34f5f85b917b2d96f04bc021e12f6d8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2BYMIE6MHEDY6GKSSOGJIWG4XU/bundle.json","state_url":"https://pith.science/pith/2BYMIE6MHEDY6GKSSOGJIWG4XU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2BYMIE6MHEDY6GKSSOGJIWG4XU/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":"2026-05-25T15:49:06Z","links":{"resolver":"https://pith.science/pith/2BYMIE6MHEDY6GKSSOGJIWG4XU","bundle":"https://pith.science/pith/2BYMIE6MHEDY6GKSSOGJIWG4XU/bundle.json","state":"https://pith.science/pith/2BYMIE6MHEDY6GKSSOGJIWG4XU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2BYMIE6MHEDY6GKSSOGJIWG4XU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:2BYMIE6MHEDY6GKSSOGJIWG4XU","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":"560dc58191616637ccfb02773df3ec6d110a7363240a447df32793003141c985","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-05-26T23:11:40Z","title_canon_sha256":"ce9944de280a2346d6f7dde493aa106800a9d884825631732fb39c8abdbf73a5"},"schema_version":"1.0","source":{"id":"1405.6757","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1405.6757","created_at":"2026-05-18T02:51:00Z"},{"alias_kind":"arxiv_version","alias_value":"1405.6757v1","created_at":"2026-05-18T02:51:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1405.6757","created_at":"2026-05-18T02:51:00Z"},{"alias_kind":"pith_short_12","alias_value":"2BYMIE6MHEDY","created_at":"2026-05-18T12:28:09Z"},{"alias_kind":"pith_short_16","alias_value":"2BYMIE6MHEDY6GKS","created_at":"2026-05-18T12:28:09Z"},{"alias_kind":"pith_short_8","alias_value":"2BYMIE6M","created_at":"2026-05-18T12:28:09Z"}],"graph_snapshots":[{"event_id":"sha256:0884bbd1e57ce77a3e68ecc7d1b36748a34f5f85b917b2d96f04bc021e12f6d8","target":"graph","created_at":"2026-05-18T02:51:00Z","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":"In this paper, we set forth a new vision of reinforcement learning developed by us over the past few years, one that yields mathematically rigorous solutions to longstanding important questions that have remained unresolved: (i) how to design reliable, convergent, and robust reinforcement learning algorithms (ii) how to guarantee that reinforcement learning satisfies pre-specified \"safety\" guarantees, and remains in a stable region of the parameter space (iii) how to design \"off-policy\" temporal difference learning algorithms in a reliable and stable manner, and finally (iv) how to integrate t","authors_text":"Bo Liu, Ian Gemp, Ji Liu, Nicholas Jacek, Philip Thomas, Sridhar Mahadevan, Steve Giguere, Will Dabney","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-05-26T23:11:40Z","title":"Proximal Reinforcement Learning: A New Theory of Sequential Decision Making in Primal-Dual Spaces"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1405.6757","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":"sha256:3d4d217e973381c16130e81ce97e41f75572d1eb9b83d9c5b1d7277c5aa6fe5d","target":"record","created_at":"2026-05-18T02:51:00Z","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":"560dc58191616637ccfb02773df3ec6d110a7363240a447df32793003141c985","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-05-26T23:11:40Z","title_canon_sha256":"ce9944de280a2346d6f7dde493aa106800a9d884825631732fb39c8abdbf73a5"},"schema_version":"1.0","source":{"id":"1405.6757","kind":"arxiv","version":1}},"canonical_sha256":"d070c413cc39078f1952938c9458dcbd2dca8c16c74a4ac05f26217c9d6498b7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d070c413cc39078f1952938c9458dcbd2dca8c16c74a4ac05f26217c9d6498b7","first_computed_at":"2026-05-18T02:51:00.400703Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:51:00.400703Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2rA5lVA6Wb39CV0Wv19caFyCoCT2kePkAGfiHZDAYH03atpPsY0mbXQxpKkKLQdjQzEvsazc0f/cBQ3lEy2FDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T02:51:00.401359Z","signed_message":"canonical_sha256_bytes"},"source_id":"1405.6757","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3d4d217e973381c16130e81ce97e41f75572d1eb9b83d9c5b1d7277c5aa6fe5d","sha256:0884bbd1e57ce77a3e68ecc7d1b36748a34f5f85b917b2d96f04bc021e12f6d8"],"state_sha256":"8264c4d8ad85d1b8a24409805e599ef0e6b67dd3619cfc97afdccd576724eda0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PgiUQqTbZZZgbDQFkiHacffz1L+XaWYF/2fqrk3PahPIun0Z9A0v8xXvkgpEbVv1Vom/CmOwW+DAMr55oOBhCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T15:49:06.755635Z","bundle_sha256":"803302d58d9b6e9bc32794dd829254c1a0f2cd33b4cc41a1b1f6c282584d6210"}}