{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:ATJUTU3PCJBJLCYTE5UQAUI6II","short_pith_number":"pith:ATJUTU3P","canonical_record":{"source":{"id":"1512.04087","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2015-12-13T17:13:33Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"951503db87114e0a7676bbfbfb267b68a3315dea957fd25255d184d40bb3b0de","abstract_canon_sha256":"8006a85e8c849178a9037e534bef67a042614fae17f482ece0ae2aa78e5e8b61"},"schema_version":"1.0"},"canonical_sha256":"04d349d36f1242958b13276900511e421ff0f86afeb42a055d106582a2cad44e","source":{"kind":"arxiv","id":"1512.04087","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1512.04087","created_at":"2026-05-18T01:04:57Z"},{"alias_kind":"arxiv_version","alias_value":"1512.04087v2","created_at":"2026-05-18T01:04:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1512.04087","created_at":"2026-05-18T01:04:57Z"},{"alias_kind":"pith_short_12","alias_value":"ATJUTU3PCJBJ","created_at":"2026-05-18T12:29:10Z"},{"alias_kind":"pith_short_16","alias_value":"ATJUTU3PCJBJLCYT","created_at":"2026-05-18T12:29:10Z"},{"alias_kind":"pith_short_8","alias_value":"ATJUTU3P","created_at":"2026-05-18T12:29:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:ATJUTU3PCJBJLCYTE5UQAUI6II","target":"record","payload":{"canonical_record":{"source":{"id":"1512.04087","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2015-12-13T17:13:33Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"951503db87114e0a7676bbfbfb267b68a3315dea957fd25255d184d40bb3b0de","abstract_canon_sha256":"8006a85e8c849178a9037e534bef67a042614fae17f482ece0ae2aa78e5e8b61"},"schema_version":"1.0"},"canonical_sha256":"04d349d36f1242958b13276900511e421ff0f86afeb42a055d106582a2cad44e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:04:57.708947Z","signature_b64":"fL6/iWGpq3JjmeI7aEKaXKUMXC/MGshnhhCDATQM7CNhtxy7Vqv9PyJMql9EblJV2iPzRngRePQ1wu+d/YreAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04d349d36f1242958b13276900511e421ff0f86afeb42a055d106582a2cad44e","last_reissued_at":"2026-05-18T01:04:57.708375Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:04:57.708375Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1512.04087","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:04:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YhcJwei+493HyvryVV/ss4kdkh6S/MB+7B2n4F1ewfF1UcLjwVWX+/e5d63ZN2+BhvhiCO+b3Idg6Poo/KSQDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T07:29:29.026440Z"},"content_sha256":"fcfffe892ee1cb3dfe10d1169e6fdab198787861bea12739139216c57545339f","schema_version":"1.0","event_id":"sha256:fcfffe892ee1cb3dfe10d1169e6fdab198787861bea12739139216c57545339f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:ATJUTU3PCJBJLCYTE5UQAUI6II","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"True Online Temporal-Difference Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"A. Rupam Mahmood, Harm van Seijen, Marlos C. Machado, Patrick M. Pilarski, Richard S. Sutton","submitted_at":"2015-12-13T17:13:33Z","abstract_excerpt":"The temporal-difference methods TD($\\lambda$) and Sarsa($\\lambda$) form a core part of modern reinforcement learning. Their appeal comes from their good performance, low computational cost, and their simple interpretation, given by their forward view. Recently, new versions of these methods were introduced, called true online TD($\\lambda$) and true online Sarsa($\\lambda$), respectively (van Seijen & Sutton, 2014). These new versions maintain an exact equivalence with the forward view at all times, whereas the traditional versions only approximate it for small step-sizes. We hypothesize that th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1512.04087","kind":"arxiv","version":2},"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":"2026-05-18T01:04:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Kd6fHK8xjC4iv0p+KgXzYRN8Gia1R9vpmyc9yzr/Ww8fdXwq4Iq8xJH1is4J6QamECBL/EzOacgb/062NGMxDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T07:29:29.026791Z"},"content_sha256":"e075a819bae0edabbb6392a726bdca53fea51dc85373c883c6d0ede2cf66efa8","schema_version":"1.0","event_id":"sha256:e075a819bae0edabbb6392a726bdca53fea51dc85373c883c6d0ede2cf66efa8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ATJUTU3PCJBJLCYTE5UQAUI6II/bundle.json","state_url":"https://pith.science/pith/ATJUTU3PCJBJLCYTE5UQAUI6II/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ATJUTU3PCJBJLCYTE5UQAUI6II/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":"2026-06-01T07:29:29Z","links":{"resolver":"https://pith.science/pith/ATJUTU3PCJBJLCYTE5UQAUI6II","bundle":"https://pith.science/pith/ATJUTU3PCJBJLCYTE5UQAUI6II/bundle.json","state":"https://pith.science/pith/ATJUTU3PCJBJLCYTE5UQAUI6II/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ATJUTU3PCJBJLCYTE5UQAUI6II/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:ATJUTU3PCJBJLCYTE5UQAUI6II","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":"8006a85e8c849178a9037e534bef67a042614fae17f482ece0ae2aa78e5e8b61","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2015-12-13T17:13:33Z","title_canon_sha256":"951503db87114e0a7676bbfbfb267b68a3315dea957fd25255d184d40bb3b0de"},"schema_version":"1.0","source":{"id":"1512.04087","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1512.04087","created_at":"2026-05-18T01:04:57Z"},{"alias_kind":"arxiv_version","alias_value":"1512.04087v2","created_at":"2026-05-18T01:04:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1512.04087","created_at":"2026-05-18T01:04:57Z"},{"alias_kind":"pith_short_12","alias_value":"ATJUTU3PCJBJ","created_at":"2026-05-18T12:29:10Z"},{"alias_kind":"pith_short_16","alias_value":"ATJUTU3PCJBJLCYT","created_at":"2026-05-18T12:29:10Z"},{"alias_kind":"pith_short_8","alias_value":"ATJUTU3P","created_at":"2026-05-18T12:29:10Z"}],"graph_snapshots":[{"event_id":"sha256:e075a819bae0edabbb6392a726bdca53fea51dc85373c883c6d0ede2cf66efa8","target":"graph","created_at":"2026-05-18T01:04:57Z","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 temporal-difference methods TD($\\lambda$) and Sarsa($\\lambda$) form a core part of modern reinforcement learning. Their appeal comes from their good performance, low computational cost, and their simple interpretation, given by their forward view. Recently, new versions of these methods were introduced, called true online TD($\\lambda$) and true online Sarsa($\\lambda$), respectively (van Seijen & Sutton, 2014). These new versions maintain an exact equivalence with the forward view at all times, whereas the traditional versions only approximate it for small step-sizes. We hypothesize that th","authors_text":"A. Rupam Mahmood, Harm van Seijen, Marlos C. Machado, Patrick M. Pilarski, Richard S. Sutton","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2015-12-13T17:13:33Z","title":"True Online Temporal-Difference Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1512.04087","kind":"arxiv","version":2},"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:fcfffe892ee1cb3dfe10d1169e6fdab198787861bea12739139216c57545339f","target":"record","created_at":"2026-05-18T01:04:57Z","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":"8006a85e8c849178a9037e534bef67a042614fae17f482ece0ae2aa78e5e8b61","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2015-12-13T17:13:33Z","title_canon_sha256":"951503db87114e0a7676bbfbfb267b68a3315dea957fd25255d184d40bb3b0de"},"schema_version":"1.0","source":{"id":"1512.04087","kind":"arxiv","version":2}},"canonical_sha256":"04d349d36f1242958b13276900511e421ff0f86afeb42a055d106582a2cad44e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"04d349d36f1242958b13276900511e421ff0f86afeb42a055d106582a2cad44e","first_computed_at":"2026-05-18T01:04:57.708375Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:04:57.708375Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fL6/iWGpq3JjmeI7aEKaXKUMXC/MGshnhhCDATQM7CNhtxy7Vqv9PyJMql9EblJV2iPzRngRePQ1wu+d/YreAg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:04:57.708947Z","signed_message":"canonical_sha256_bytes"},"source_id":"1512.04087","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fcfffe892ee1cb3dfe10d1169e6fdab198787861bea12739139216c57545339f","sha256:e075a819bae0edabbb6392a726bdca53fea51dc85373c883c6d0ede2cf66efa8"],"state_sha256":"0ad958691da698b13a0850e39c69d49fcea9d69d9c334151ed9ebe14a48cc67f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n9lInB3VgeTkgjeGo3dJyIfV7LllpxeImi7SjFevWMpmyeWPYg/7XVSHsgrMasHrgoNk9i5k1GKhpl0qM4U3Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T07:29:29.028791Z","bundle_sha256":"b0de3f9b88d655ba9b88498c4660581f8dd2a42860b7968d6138c0c7d0faa5b7"}}