{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:JEHTVZ2BZ633XWF5LDEFVSIO5W","short_pith_number":"pith:JEHTVZ2B","canonical_record":{"source":{"id":"1507.08271","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2015-07-29T19:37:24Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"ea546fd9246b3f84df7a36f434c0eadd5f9d07bcba316cd057409904825d2740","abstract_canon_sha256":"c41112c73be1effac2408b6325815ee688bf7c3b88f47164d448342d07428f80"},"schema_version":"1.0"},"canonical_sha256":"490f3ae741cfb7bbd8bd58c85ac90eed97a692658b8639fca7ae410c745c7905","source":{"kind":"arxiv","id":"1507.08271","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1507.08271","created_at":"2026-05-18T01:35:43Z"},{"alias_kind":"arxiv_version","alias_value":"1507.08271v4","created_at":"2026-05-18T01:35:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1507.08271","created_at":"2026-05-18T01:35:43Z"},{"alias_kind":"pith_short_12","alias_value":"JEHTVZ2BZ633","created_at":"2026-05-18T12:29:27Z"},{"alias_kind":"pith_short_16","alias_value":"JEHTVZ2BZ633XWF5","created_at":"2026-05-18T12:29:27Z"},{"alias_kind":"pith_short_8","alias_value":"JEHTVZ2B","created_at":"2026-05-18T12:29:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:JEHTVZ2BZ633XWF5LDEFVSIO5W","target":"record","payload":{"canonical_record":{"source":{"id":"1507.08271","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2015-07-29T19:37:24Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"ea546fd9246b3f84df7a36f434c0eadd5f9d07bcba316cd057409904825d2740","abstract_canon_sha256":"c41112c73be1effac2408b6325815ee688bf7c3b88f47164d448342d07428f80"},"schema_version":"1.0"},"canonical_sha256":"490f3ae741cfb7bbd8bd58c85ac90eed97a692658b8639fca7ae410c745c7905","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:35:43.207505Z","signature_b64":"Y6VRzXEIO6csy9F1iYVpSB/TULh8LhZSPElf4G7/JeaJCNZpkmJy1QOPpqeJhPO/DPHmjEdfdIw7dNJn+JwhBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"490f3ae741cfb7bbd8bd58c85ac90eed97a692658b8639fca7ae410c745c7905","last_reissued_at":"2026-05-18T01:35:43.207101Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:35:43.207101Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1507.08271","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:35:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HIebWMLSRjXK0vsmfGBs3wBH0dKMK6f5I/kV+yhbh60dRRUdsOS9Zk4jNgwi3n/foD+q2cTz8cyzKXN2U5l+Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T17:52:18.942377Z"},"content_sha256":"b35d26a14360162d5bd8299ee145f6736a074170003d137edb4553d7b41291fb","schema_version":"1.0","event_id":"sha256:b35d26a14360162d5bd8299ee145f6736a074170003d137edb4553d7b41291fb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:JEHTVZ2BZ633XWF5LDEFVSIO5W","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Gauss-Newton Method for Markov Decision Processes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.AI","authors_text":"Guy Lever, Thomas Furmston","submitted_at":"2015-07-29T19:37:24Z","abstract_excerpt":"Approximate Newton methods are a standard optimization tool which aim to maintain the benefits of Newton's method, such as a fast rate of convergence, whilst alleviating its drawbacks, such as computationally expensive calculation or estimation of the inverse Hessian. In this work we investigate approximate Newton methods for policy optimization in Markov Decision Processes (MDPs). We first analyse the structure of the Hessian of the objective function for MDPs. We show that, like the gradient, the Hessian exhibits useful structure in the context of MDPs and we use this analysis to motivate tw"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1507.08271","kind":"arxiv","version":4},"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":"2026-05-18T01:35:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PbtLJyaep61Li6P+MZCc2iyBVgbIU4fRpEiakC/Q0vtEo2dCVNnngcx3JDVWsm+nDEkbAn0vk/dZmIBHQm76BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T17:52:18.943055Z"},"content_sha256":"cecc6027bbb8e2cb6d07392bd554755c71f6549d29a0b3f550950b4e76e39851","schema_version":"1.0","event_id":"sha256:cecc6027bbb8e2cb6d07392bd554755c71f6549d29a0b3f550950b4e76e39851"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JEHTVZ2BZ633XWF5LDEFVSIO5W/bundle.json","state_url":"https://pith.science/pith/JEHTVZ2BZ633XWF5LDEFVSIO5W/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JEHTVZ2BZ633XWF5LDEFVSIO5W/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":"2026-06-07T17:52:18Z","links":{"resolver":"https://pith.science/pith/JEHTVZ2BZ633XWF5LDEFVSIO5W","bundle":"https://pith.science/pith/JEHTVZ2BZ633XWF5LDEFVSIO5W/bundle.json","state":"https://pith.science/pith/JEHTVZ2BZ633XWF5LDEFVSIO5W/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JEHTVZ2BZ633XWF5LDEFVSIO5W/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:JEHTVZ2BZ633XWF5LDEFVSIO5W","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":"c41112c73be1effac2408b6325815ee688bf7c3b88f47164d448342d07428f80","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2015-07-29T19:37:24Z","title_canon_sha256":"ea546fd9246b3f84df7a36f434c0eadd5f9d07bcba316cd057409904825d2740"},"schema_version":"1.0","source":{"id":"1507.08271","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1507.08271","created_at":"2026-05-18T01:35:43Z"},{"alias_kind":"arxiv_version","alias_value":"1507.08271v4","created_at":"2026-05-18T01:35:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1507.08271","created_at":"2026-05-18T01:35:43Z"},{"alias_kind":"pith_short_12","alias_value":"JEHTVZ2BZ633","created_at":"2026-05-18T12:29:27Z"},{"alias_kind":"pith_short_16","alias_value":"JEHTVZ2BZ633XWF5","created_at":"2026-05-18T12:29:27Z"},{"alias_kind":"pith_short_8","alias_value":"JEHTVZ2B","created_at":"2026-05-18T12:29:27Z"}],"graph_snapshots":[{"event_id":"sha256:cecc6027bbb8e2cb6d07392bd554755c71f6549d29a0b3f550950b4e76e39851","target":"graph","created_at":"2026-05-18T01:35:43Z","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":"Approximate Newton methods are a standard optimization tool which aim to maintain the benefits of Newton's method, such as a fast rate of convergence, whilst alleviating its drawbacks, such as computationally expensive calculation or estimation of the inverse Hessian. In this work we investigate approximate Newton methods for policy optimization in Markov Decision Processes (MDPs). We first analyse the structure of the Hessian of the objective function for MDPs. We show that, like the gradient, the Hessian exhibits useful structure in the context of MDPs and we use this analysis to motivate tw","authors_text":"Guy Lever, Thomas Furmston","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2015-07-29T19:37:24Z","title":"A Gauss-Newton Method for Markov Decision Processes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1507.08271","kind":"arxiv","version":4},"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:b35d26a14360162d5bd8299ee145f6736a074170003d137edb4553d7b41291fb","target":"record","created_at":"2026-05-18T01:35:43Z","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":"c41112c73be1effac2408b6325815ee688bf7c3b88f47164d448342d07428f80","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2015-07-29T19:37:24Z","title_canon_sha256":"ea546fd9246b3f84df7a36f434c0eadd5f9d07bcba316cd057409904825d2740"},"schema_version":"1.0","source":{"id":"1507.08271","kind":"arxiv","version":4}},"canonical_sha256":"490f3ae741cfb7bbd8bd58c85ac90eed97a692658b8639fca7ae410c745c7905","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"490f3ae741cfb7bbd8bd58c85ac90eed97a692658b8639fca7ae410c745c7905","first_computed_at":"2026-05-18T01:35:43.207101Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:35:43.207101Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Y6VRzXEIO6csy9F1iYVpSB/TULh8LhZSPElf4G7/JeaJCNZpkmJy1QOPpqeJhPO/DPHmjEdfdIw7dNJn+JwhBA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:35:43.207505Z","signed_message":"canonical_sha256_bytes"},"source_id":"1507.08271","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b35d26a14360162d5bd8299ee145f6736a074170003d137edb4553d7b41291fb","sha256:cecc6027bbb8e2cb6d07392bd554755c71f6549d29a0b3f550950b4e76e39851"],"state_sha256":"e0e14e68c68af27aef1cb001c88794661d3f7ac39411e02ccec5bf2c07fd04c8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9jMoV18O5EpSR3PTvKQZnYwi1guL+bw/4hXGLU21Bl9Jc3KXsd1DSJQXDbzAGNf+IIUFnP7cjWVAfz+mEbnaDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T17:52:18.947127Z","bundle_sha256":"216cff57950e72114fb8d962ce6100698d3f556a5ddbe35257358ea1b57bc135"}}