{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:5HXMLC5IJGRHMI2HHFQ4YOADYR","short_pith_number":"pith:5HXMLC5I","canonical_record":{"source":{"id":"1710.05387","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-10-15T19:59:13Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"bd865f593abce48716abc79d3fd799cb15c783c8db6dadb195f26ff7ef6940fb","abstract_canon_sha256":"f67bf1610557958781388055af7d71929cf04650de32cca70196eb8bd27f4033"},"schema_version":"1.0"},"canonical_sha256":"e9eec58ba849a27623473961cc3803c46eb397e5acf6b6a5ea5db81fbaff0300","source":{"kind":"arxiv","id":"1710.05387","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.05387","created_at":"2026-05-18T00:32:49Z"},{"alias_kind":"arxiv_version","alias_value":"1710.05387v1","created_at":"2026-05-18T00:32:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.05387","created_at":"2026-05-18T00:32:49Z"},{"alias_kind":"pith_short_12","alias_value":"5HXMLC5IJGRH","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"5HXMLC5IJGRHMI2H","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"5HXMLC5I","created_at":"2026-05-18T12:31:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:5HXMLC5IJGRHMI2HHFQ4YOADYR","target":"record","payload":{"canonical_record":{"source":{"id":"1710.05387","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-10-15T19:59:13Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"bd865f593abce48716abc79d3fd799cb15c783c8db6dadb195f26ff7ef6940fb","abstract_canon_sha256":"f67bf1610557958781388055af7d71929cf04650de32cca70196eb8bd27f4033"},"schema_version":"1.0"},"canonical_sha256":"e9eec58ba849a27623473961cc3803c46eb397e5acf6b6a5ea5db81fbaff0300","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:32:49.716982Z","signature_b64":"xvu0aIWTvH+JAWliZExjUolVK+Ps3X+4vlVe19WVBBAzXFwDUqtzNfz+WUwsM79TGZoiLF2HRa5E06nrh2RYAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9eec58ba849a27623473961cc3803c46eb397e5acf6b6a5ea5db81fbaff0300","last_reissued_at":"2026-05-18T00:32:49.716232Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:32:49.716232Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1710.05387","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":"2026-05-18T00:32:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wZQcfiWptvN1R2wEPzeS5GAXBr+y2T3DXhJOQkthtEMGZRSiUSEXA6Z1+YSdLry35+q7xHH/XKENenAMNM8sDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T06:52:23.579384Z"},"content_sha256":"e7c3ad7084e5549f5f2207d0237cce1e73feca243300b5f342b07da63069e1af","schema_version":"1.0","event_id":"sha256:e7c3ad7084e5549f5f2207d0237cce1e73feca243300b5f342b07da63069e1af"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:5HXMLC5IJGRHMI2HHFQ4YOADYR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Manifold Regularization for Kernelized LSTD","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Byron Boots, Krzysztof Choromanski, Vikas Sindhwani, Xinyan Yan","submitted_at":"2017-10-15T19:59:13Z","abstract_excerpt":"Policy evaluation or value function or Q-function approximation is a key procedure in reinforcement learning (RL). It is a necessary component of policy iteration and can be used for variance reduction in policy gradient methods. Therefore its quality has a significant impact on most RL algorithms. Motivated by manifold regularized learning, we propose a novel kernelized policy evaluation method that takes advantage of the intrinsic geometry of the state space learned from data, in order to achieve better sample efficiency and higher accuracy in Q-function approximation. Applying the proposed "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.05387","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":"2026-05-18T00:32:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kJP5cyrekeaBKUDdLSjE6jbr2LNdIkHQ7fhTKMhUoP4R5Bt2aEyay+SDLKFfNKQVsjk2TPD2zrNOy7Omvlc6DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T06:52:23.579765Z"},"content_sha256":"c1547f8bf387f57765800d438cd057fd08ac977d896a32df96d73e7d0aa201ae","schema_version":"1.0","event_id":"sha256:c1547f8bf387f57765800d438cd057fd08ac977d896a32df96d73e7d0aa201ae"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5HXMLC5IJGRHMI2HHFQ4YOADYR/bundle.json","state_url":"https://pith.science/pith/5HXMLC5IJGRHMI2HHFQ4YOADYR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5HXMLC5IJGRHMI2HHFQ4YOADYR/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":"2026-06-01T06:52:23Z","links":{"resolver":"https://pith.science/pith/5HXMLC5IJGRHMI2HHFQ4YOADYR","bundle":"https://pith.science/pith/5HXMLC5IJGRHMI2HHFQ4YOADYR/bundle.json","state":"https://pith.science/pith/5HXMLC5IJGRHMI2HHFQ4YOADYR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5HXMLC5IJGRHMI2HHFQ4YOADYR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:5HXMLC5IJGRHMI2HHFQ4YOADYR","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":"f67bf1610557958781388055af7d71929cf04650de32cca70196eb8bd27f4033","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-10-15T19:59:13Z","title_canon_sha256":"bd865f593abce48716abc79d3fd799cb15c783c8db6dadb195f26ff7ef6940fb"},"schema_version":"1.0","source":{"id":"1710.05387","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.05387","created_at":"2026-05-18T00:32:49Z"},{"alias_kind":"arxiv_version","alias_value":"1710.05387v1","created_at":"2026-05-18T00:32:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.05387","created_at":"2026-05-18T00:32:49Z"},{"alias_kind":"pith_short_12","alias_value":"5HXMLC5IJGRH","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"5HXMLC5IJGRHMI2H","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"5HXMLC5I","created_at":"2026-05-18T12:31:00Z"}],"graph_snapshots":[{"event_id":"sha256:c1547f8bf387f57765800d438cd057fd08ac977d896a32df96d73e7d0aa201ae","target":"graph","created_at":"2026-05-18T00:32:49Z","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":"Policy evaluation or value function or Q-function approximation is a key procedure in reinforcement learning (RL). It is a necessary component of policy iteration and can be used for variance reduction in policy gradient methods. Therefore its quality has a significant impact on most RL algorithms. Motivated by manifold regularized learning, we propose a novel kernelized policy evaluation method that takes advantage of the intrinsic geometry of the state space learned from data, in order to achieve better sample efficiency and higher accuracy in Q-function approximation. Applying the proposed ","authors_text":"Byron Boots, Krzysztof Choromanski, Vikas Sindhwani, Xinyan Yan","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-10-15T19:59:13Z","title":"Manifold Regularization for Kernelized LSTD"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.05387","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:e7c3ad7084e5549f5f2207d0237cce1e73feca243300b5f342b07da63069e1af","target":"record","created_at":"2026-05-18T00:32:49Z","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":"f67bf1610557958781388055af7d71929cf04650de32cca70196eb8bd27f4033","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-10-15T19:59:13Z","title_canon_sha256":"bd865f593abce48716abc79d3fd799cb15c783c8db6dadb195f26ff7ef6940fb"},"schema_version":"1.0","source":{"id":"1710.05387","kind":"arxiv","version":1}},"canonical_sha256":"e9eec58ba849a27623473961cc3803c46eb397e5acf6b6a5ea5db81fbaff0300","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e9eec58ba849a27623473961cc3803c46eb397e5acf6b6a5ea5db81fbaff0300","first_computed_at":"2026-05-18T00:32:49.716232Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:32:49.716232Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xvu0aIWTvH+JAWliZExjUolVK+Ps3X+4vlVe19WVBBAzXFwDUqtzNfz+WUwsM79TGZoiLF2HRa5E06nrh2RYAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:32:49.716982Z","signed_message":"canonical_sha256_bytes"},"source_id":"1710.05387","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e7c3ad7084e5549f5f2207d0237cce1e73feca243300b5f342b07da63069e1af","sha256:c1547f8bf387f57765800d438cd057fd08ac977d896a32df96d73e7d0aa201ae"],"state_sha256":"1a657364dbdc494033a9fc879472c9bd76788797f735164ba8fe42e0fb4b577e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"di0RGX+8yQnr1UAgWQQBOa99ywMfbvIrAUMHGnYwmJV7TYi8AS7LCavgDhz+SkGjuEblZqve/UJDZZ5NSUXwAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T06:52:23.582255Z","bundle_sha256":"f7c0aab525f05c5252d5a91de225441918f083dfea6c77a732b1e012f7ac26f0"}}