{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:AZN5GXQ7W5IFSBJPTDXHUDRKZQ","short_pith_number":"pith:AZN5GXQ7","canonical_record":{"source":{"id":"1407.5358","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-07-21T01:20:45Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"cadd1ebe35be2208360a232dcda01f9c17e4b588796f46a13727e1a342459de5","abstract_canon_sha256":"82b5a32302918014f2e3050004a2563f86a281647009b44c34a44d67143e4f76"},"schema_version":"1.0"},"canonical_sha256":"065bd35e1fb75059052f98ee7a0e2acc25305fe007e43c5f9c3158ae4b91eb01","source":{"kind":"arxiv","id":"1407.5358","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1407.5358","created_at":"2026-05-18T02:47:14Z"},{"alias_kind":"arxiv_version","alias_value":"1407.5358v1","created_at":"2026-05-18T02:47:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1407.5358","created_at":"2026-05-18T02:47:14Z"},{"alias_kind":"pith_short_12","alias_value":"AZN5GXQ7W5IF","created_at":"2026-05-18T12:28:19Z"},{"alias_kind":"pith_short_16","alias_value":"AZN5GXQ7W5IFSBJP","created_at":"2026-05-18T12:28:19Z"},{"alias_kind":"pith_short_8","alias_value":"AZN5GXQ7","created_at":"2026-05-18T12:28:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:AZN5GXQ7W5IFSBJPTDXHUDRKZQ","target":"record","payload":{"canonical_record":{"source":{"id":"1407.5358","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-07-21T01:20:45Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"cadd1ebe35be2208360a232dcda01f9c17e4b588796f46a13727e1a342459de5","abstract_canon_sha256":"82b5a32302918014f2e3050004a2563f86a281647009b44c34a44d67143e4f76"},"schema_version":"1.0"},"canonical_sha256":"065bd35e1fb75059052f98ee7a0e2acc25305fe007e43c5f9c3158ae4b91eb01","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:47:14.250151Z","signature_b64":"WZNCEfvEHpGN/ISj7rtWLXz9b2L9AFIy14R6leDat0W41Bi/8EDy0a8HH7cOTsEnusjZIHYxGcu4OIbry/TeAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"065bd35e1fb75059052f98ee7a0e2acc25305fe007e43c5f9c3158ae4b91eb01","last_reissued_at":"2026-05-18T02:47:14.249612Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:47:14.249612Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1407.5358","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":"2026-05-18T02:47:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0xSoWkbbJS3LJbuXuk8wHqhfceHMm9j6OffUSR/6nsEC4Q2NaK503I+ra76fgArh4bpUS4qdgG36bRW5yUe3Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T21:19:07.246694Z"},"content_sha256":"531aee0a61e6d7aebd604bb9cb0b2400d5d177e42874129285fc24491a715b0d","schema_version":"1.0","event_id":"sha256:531aee0a61e6d7aebd604bb9cb0b2400d5d177e42874129285fc24491a715b0d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:AZN5GXQ7W5IFSBJPTDXHUDRKZQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Practical Kernel-Based Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andr\\'e M. S. Barreto, Doina Precup, Joelle Pineau","submitted_at":"2014-07-21T01:20:45Z","abstract_excerpt":"Kernel-based reinforcement learning (KBRL) stands out among reinforcement learning algorithms for its strong theoretical guarantees. By casting the learning problem as a local kernel approximation, KBRL provides a way of computing a decision policy which is statistically consistent and converges to a unique solution. Unfortunately, the model constructed by KBRL grows with the number of sample transitions, resulting in a computational cost that precludes its application to large-scale or on-line domains. In this paper we introduce an algorithm that turns KBRL into a practical reinforcement lear"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1407.5358","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":"2026-05-18T02:47:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8a4TjM704GbgvlFq/HiU/Ia2LfSRR6xsUMvdhNdknkFC+aZdk0mm/Q63C9A7rcuYSyolGv9Fne6wp4+W9eyGCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T21:19:07.247039Z"},"content_sha256":"d78f465057f0ccec049e906f374fb9199f9ffdb6d810b941c3cbd09f5d7f8f91","schema_version":"1.0","event_id":"sha256:d78f465057f0ccec049e906f374fb9199f9ffdb6d810b941c3cbd09f5d7f8f91"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AZN5GXQ7W5IFSBJPTDXHUDRKZQ/bundle.json","state_url":"https://pith.science/pith/AZN5GXQ7W5IFSBJPTDXHUDRKZQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AZN5GXQ7W5IFSBJPTDXHUDRKZQ/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":"2026-06-01T21:19:07Z","links":{"resolver":"https://pith.science/pith/AZN5GXQ7W5IFSBJPTDXHUDRKZQ","bundle":"https://pith.science/pith/AZN5GXQ7W5IFSBJPTDXHUDRKZQ/bundle.json","state":"https://pith.science/pith/AZN5GXQ7W5IFSBJPTDXHUDRKZQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AZN5GXQ7W5IFSBJPTDXHUDRKZQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:AZN5GXQ7W5IFSBJPTDXHUDRKZQ","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":"82b5a32302918014f2e3050004a2563f86a281647009b44c34a44d67143e4f76","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-07-21T01:20:45Z","title_canon_sha256":"cadd1ebe35be2208360a232dcda01f9c17e4b588796f46a13727e1a342459de5"},"schema_version":"1.0","source":{"id":"1407.5358","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1407.5358","created_at":"2026-05-18T02:47:14Z"},{"alias_kind":"arxiv_version","alias_value":"1407.5358v1","created_at":"2026-05-18T02:47:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1407.5358","created_at":"2026-05-18T02:47:14Z"},{"alias_kind":"pith_short_12","alias_value":"AZN5GXQ7W5IF","created_at":"2026-05-18T12:28:19Z"},{"alias_kind":"pith_short_16","alias_value":"AZN5GXQ7W5IFSBJP","created_at":"2026-05-18T12:28:19Z"},{"alias_kind":"pith_short_8","alias_value":"AZN5GXQ7","created_at":"2026-05-18T12:28:19Z"}],"graph_snapshots":[{"event_id":"sha256:d78f465057f0ccec049e906f374fb9199f9ffdb6d810b941c3cbd09f5d7f8f91","target":"graph","created_at":"2026-05-18T02:47:14Z","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":"Kernel-based reinforcement learning (KBRL) stands out among reinforcement learning algorithms for its strong theoretical guarantees. By casting the learning problem as a local kernel approximation, KBRL provides a way of computing a decision policy which is statistically consistent and converges to a unique solution. Unfortunately, the model constructed by KBRL grows with the number of sample transitions, resulting in a computational cost that precludes its application to large-scale or on-line domains. In this paper we introduce an algorithm that turns KBRL into a practical reinforcement lear","authors_text":"Andr\\'e M. S. Barreto, Doina Precup, Joelle Pineau","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-07-21T01:20:45Z","title":"Practical Kernel-Based Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1407.5358","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":"sha256:531aee0a61e6d7aebd604bb9cb0b2400d5d177e42874129285fc24491a715b0d","target":"record","created_at":"2026-05-18T02:47:14Z","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":"82b5a32302918014f2e3050004a2563f86a281647009b44c34a44d67143e4f76","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-07-21T01:20:45Z","title_canon_sha256":"cadd1ebe35be2208360a232dcda01f9c17e4b588796f46a13727e1a342459de5"},"schema_version":"1.0","source":{"id":"1407.5358","kind":"arxiv","version":1}},"canonical_sha256":"065bd35e1fb75059052f98ee7a0e2acc25305fe007e43c5f9c3158ae4b91eb01","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"065bd35e1fb75059052f98ee7a0e2acc25305fe007e43c5f9c3158ae4b91eb01","first_computed_at":"2026-05-18T02:47:14.249612Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:47:14.249612Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WZNCEfvEHpGN/ISj7rtWLXz9b2L9AFIy14R6leDat0W41Bi/8EDy0a8HH7cOTsEnusjZIHYxGcu4OIbry/TeAg==","signature_status":"signed_v1","signed_at":"2026-05-18T02:47:14.250151Z","signed_message":"canonical_sha256_bytes"},"source_id":"1407.5358","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:531aee0a61e6d7aebd604bb9cb0b2400d5d177e42874129285fc24491a715b0d","sha256:d78f465057f0ccec049e906f374fb9199f9ffdb6d810b941c3cbd09f5d7f8f91"],"state_sha256":"def61e0b3b2803a2f88397733f9a37a9f89d5008250d2768a497ffc3f87d3c5b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ckE9A5mzsPfGyWo3g8Z/tcrfOihSkEDhuRp4Fqw0Z3Yh3ckBcLKVlTHlgQ14ugaLNo6Mg009Zbr6IN9jmLJZDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T21:19:07.249000Z","bundle_sha256":"fa23854e75f0a3f33f17c8d212d6f698be6a8af4bcc1b0984505e3e833f66855"}}