{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2011:LD26QWKYIKZSMXBSQ4BD27UEQE","short_pith_number":"pith:LD26QWKY","canonical_record":{"source":{"id":"1106.0707","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2011-06-03T16:44:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c9f980d2e3eb92884a4254a10530cb67b4130547b6d27b178b4ce24592d9bf86","abstract_canon_sha256":"1730fd8b17bf25e43b04c4105201a91e00ca5569630245ea8a46d79eecee95bb"},"schema_version":"1.0"},"canonical_sha256":"58f5e8595842b3265c3287023d7e848103968efa725c6ff78dd297adba41f2f6","source":{"kind":"arxiv","id":"1106.0707","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1106.0707","created_at":"2026-05-18T04:20:39Z"},{"alias_kind":"arxiv_version","alias_value":"1106.0707v1","created_at":"2026-05-18T04:20:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1106.0707","created_at":"2026-05-18T04:20:39Z"},{"alias_kind":"pith_short_12","alias_value":"LD26QWKYIKZS","created_at":"2026-05-18T12:26:34Z"},{"alias_kind":"pith_short_16","alias_value":"LD26QWKYIKZSMXBS","created_at":"2026-05-18T12:26:34Z"},{"alias_kind":"pith_short_8","alias_value":"LD26QWKY","created_at":"2026-05-18T12:26:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2011:LD26QWKYIKZSMXBSQ4BD27UEQE","target":"record","payload":{"canonical_record":{"source":{"id":"1106.0707","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2011-06-03T16:44:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c9f980d2e3eb92884a4254a10530cb67b4130547b6d27b178b4ce24592d9bf86","abstract_canon_sha256":"1730fd8b17bf25e43b04c4105201a91e00ca5569630245ea8a46d79eecee95bb"},"schema_version":"1.0"},"canonical_sha256":"58f5e8595842b3265c3287023d7e848103968efa725c6ff78dd297adba41f2f6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:20:39.650625Z","signature_b64":"wcgErOCi4ZVpOsWH52fOOQrmGo0edZatmWWOFIYVdUcC8P7ReJSEM3cxY0IfD4prQhl0wePqRqq4tIyJ0//RCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58f5e8595842b3265c3287023d7e848103968efa725c6ff78dd297adba41f2f6","last_reissued_at":"2026-05-18T04:20:39.649896Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:20:39.649896Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1106.0707","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":"2026-05-18T04:20:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/OTkz5CmywR+9H+up327hsYf7ANPGXvb5DViKWII3b5AAz+CIZF04mB7sa5vLuXJtnIplfm4wtHqU8XeWF/+Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T18:15:02.199587Z"},"content_sha256":"dfb3196eabd67c7814ab69e1e970b34b2288a49bc1df77e4e199b720e03b08c1","schema_version":"1.0","event_id":"sha256:dfb3196eabd67c7814ab69e1e970b34b2288a49bc1df77e4e199b720e03b08c1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2011:LD26QWKYIKZSMXBSQ4BD27UEQE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient Reinforcement Learning Using Recursive Least-Squares Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"D. Hu, H. He, X. Xu","submitted_at":"2011-06-03T16:44:06Z","abstract_excerpt":"The recursive least-squares (RLS) algorithm is one of the    most well-known algorithms used in adaptive filtering, system    identification and adaptive control. Its popularity is mainly due to    its fast convergence speed, which is considered to be optimal in    practice. In this paper, RLS methods are used to solve reinforcement    learning problems, where two new reinforcement learning algorithms    using linear value function approximators are proposed and    analyzed. The two algorithms are called RLS-TD(lambda) and Fast-AHC    (Fast Adaptive Heuristic Critic), respectively. RLS-TD(lamb"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1106.0707","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":"2026-05-18T04:20:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xCPYTPYTS9aInav1683wvA3xC3D4qPNQ9LQew0OSzRyxN17/ztxQYDpdUqjl514iEqW7XTx0NYFOpLlW1NCTBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T18:15:02.199926Z"},"content_sha256":"4c7147ef8ad89ff93b93bffce400cc65cccf66df5e7a138664a9aff06fbec662","schema_version":"1.0","event_id":"sha256:4c7147ef8ad89ff93b93bffce400cc65cccf66df5e7a138664a9aff06fbec662"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LD26QWKYIKZSMXBSQ4BD27UEQE/bundle.json","state_url":"https://pith.science/pith/LD26QWKYIKZSMXBSQ4BD27UEQE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LD26QWKYIKZSMXBSQ4BD27UEQE/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":"2026-06-01T18:15:02Z","links":{"resolver":"https://pith.science/pith/LD26QWKYIKZSMXBSQ4BD27UEQE","bundle":"https://pith.science/pith/LD26QWKYIKZSMXBSQ4BD27UEQE/bundle.json","state":"https://pith.science/pith/LD26QWKYIKZSMXBSQ4BD27UEQE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LD26QWKYIKZSMXBSQ4BD27UEQE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2011:LD26QWKYIKZSMXBSQ4BD27UEQE","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":"1730fd8b17bf25e43b04c4105201a91e00ca5569630245ea8a46d79eecee95bb","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2011-06-03T16:44:06Z","title_canon_sha256":"c9f980d2e3eb92884a4254a10530cb67b4130547b6d27b178b4ce24592d9bf86"},"schema_version":"1.0","source":{"id":"1106.0707","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1106.0707","created_at":"2026-05-18T04:20:39Z"},{"alias_kind":"arxiv_version","alias_value":"1106.0707v1","created_at":"2026-05-18T04:20:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1106.0707","created_at":"2026-05-18T04:20:39Z"},{"alias_kind":"pith_short_12","alias_value":"LD26QWKYIKZS","created_at":"2026-05-18T12:26:34Z"},{"alias_kind":"pith_short_16","alias_value":"LD26QWKYIKZSMXBS","created_at":"2026-05-18T12:26:34Z"},{"alias_kind":"pith_short_8","alias_value":"LD26QWKY","created_at":"2026-05-18T12:26:34Z"}],"graph_snapshots":[{"event_id":"sha256:4c7147ef8ad89ff93b93bffce400cc65cccf66df5e7a138664a9aff06fbec662","target":"graph","created_at":"2026-05-18T04:20:39Z","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":"The recursive least-squares (RLS) algorithm is one of the    most well-known algorithms used in adaptive filtering, system    identification and adaptive control. Its popularity is mainly due to    its fast convergence speed, which is considered to be optimal in    practice. In this paper, RLS methods are used to solve reinforcement    learning problems, where two new reinforcement learning algorithms    using linear value function approximators are proposed and    analyzed. The two algorithms are called RLS-TD(lambda) and Fast-AHC    (Fast Adaptive Heuristic Critic), respectively. RLS-TD(lamb","authors_text":"D. Hu, H. He, X. Xu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2011-06-03T16:44:06Z","title":"Efficient Reinforcement Learning Using Recursive Least-Squares Methods"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1106.0707","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:dfb3196eabd67c7814ab69e1e970b34b2288a49bc1df77e4e199b720e03b08c1","target":"record","created_at":"2026-05-18T04:20:39Z","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":"1730fd8b17bf25e43b04c4105201a91e00ca5569630245ea8a46d79eecee95bb","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2011-06-03T16:44:06Z","title_canon_sha256":"c9f980d2e3eb92884a4254a10530cb67b4130547b6d27b178b4ce24592d9bf86"},"schema_version":"1.0","source":{"id":"1106.0707","kind":"arxiv","version":1}},"canonical_sha256":"58f5e8595842b3265c3287023d7e848103968efa725c6ff78dd297adba41f2f6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"58f5e8595842b3265c3287023d7e848103968efa725c6ff78dd297adba41f2f6","first_computed_at":"2026-05-18T04:20:39.649896Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T04:20:39.649896Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wcgErOCi4ZVpOsWH52fOOQrmGo0edZatmWWOFIYVdUcC8P7ReJSEM3cxY0IfD4prQhl0wePqRqq4tIyJ0//RCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T04:20:39.650625Z","signed_message":"canonical_sha256_bytes"},"source_id":"1106.0707","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dfb3196eabd67c7814ab69e1e970b34b2288a49bc1df77e4e199b720e03b08c1","sha256:4c7147ef8ad89ff93b93bffce400cc65cccf66df5e7a138664a9aff06fbec662"],"state_sha256":"ed4389b114ce4e440afaf91de97fee0b029780aaad763e06022a4a456eba8d26"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H4ulE7Q3c7BvEziaRQ/OSNp5YRozu91rGRxRHvc4Qb3YSemk1zu1xtwP2LOZj2jnS7hUn7LfK5MqHh4DQbbCAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T18:15:02.201745Z","bundle_sha256":"26270d234b017a189164cec243df02f10856a85e47330c878a8e34ac8761972f"}}