{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:DMPBXSO53ZQROEG5JNKITOQTDY","short_pith_number":"pith:DMPBXSO5","canonical_record":{"source":{"id":"1909.03906","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-09T14:57:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"eb8c264b5e72f263efdc243e2a129a73b159484dc1a9fdb81f3c14a6fa1ddc46","abstract_canon_sha256":"f796c56cfb7f25cc0d8e51425afededc2ddd04c8eb05e69a2e0e2f0577805690"},"schema_version":"1.0"},"canonical_sha256":"1b1e1bc9ddde611710dd4b5489ba131e226c458755d4c8c4e7a9ca7b3bcfe1b5","source":{"kind":"arxiv","id":"1909.03906","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.03906","created_at":"2026-07-05T00:39:38Z"},{"alias_kind":"arxiv_version","alias_value":"1909.03906v2","created_at":"2026-07-05T00:39:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.03906","created_at":"2026-07-05T00:39:38Z"},{"alias_kind":"pith_short_12","alias_value":"DMPBXSO53ZQR","created_at":"2026-07-05T00:39:38Z"},{"alias_kind":"pith_short_16","alias_value":"DMPBXSO53ZQROEG5","created_at":"2026-07-05T00:39:38Z"},{"alias_kind":"pith_short_8","alias_value":"DMPBXSO5","created_at":"2026-07-05T00:39:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:DMPBXSO53ZQROEG5JNKITOQTDY","target":"record","payload":{"canonical_record":{"source":{"id":"1909.03906","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-09T14:57:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"eb8c264b5e72f263efdc243e2a129a73b159484dc1a9fdb81f3c14a6fa1ddc46","abstract_canon_sha256":"f796c56cfb7f25cc0d8e51425afededc2ddd04c8eb05e69a2e0e2f0577805690"},"schema_version":"1.0"},"canonical_sha256":"1b1e1bc9ddde611710dd4b5489ba131e226c458755d4c8c4e7a9ca7b3bcfe1b5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:39:38.342909Z","signature_b64":"UEy9uFqW1QUL5QuPKMf38wEr50MyQ8nlT2nNhyR+e7dm8eAd3UWDQNfveo0rUDYNiG7FXVOSLCawodVypYsvBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b1e1bc9ddde611710dd4b5489ba131e226c458755d4c8c4e7a9ca7b3bcfe1b5","last_reissued_at":"2026-07-05T00:39:38.342480Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:39:38.342480Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1909.03906","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":"2026-07-05T00:39:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0vwU3yTFdnn3MURuRcjUpEOg+935Uur7liFutsXEUXpixAS0T98M4Spok9nNWqY80DZNa7A8uKJKGtxni0XCDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T11:59:45.557088Z"},"content_sha256":"8945762d6d25460bef605c5ba597d3437e9159c2021d7b32571fb3b592c09ca4","schema_version":"1.0","event_id":"sha256:8945762d6d25460bef605c5ba597d3437e9159c2021d7b32571fb3b592c09ca4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:DMPBXSO53ZQROEG5JNKITOQTDY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fixed-Horizon Temporal Difference Methods for Stable Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Alan Chan, Daniel Graves, Kristopher De Asis, Richard S. Sutton, Silviu Pitis","submitted_at":"2019-09-09T14:57:42Z","abstract_excerpt":"We explore fixed-horizon temporal difference (TD) methods, reinforcement learning algorithms for a new kind of value function that predicts the sum of rewards over a $\\textit{fixed}$ number of future time steps. To learn the value function for horizon $h$, these algorithms bootstrap from the value function for horizon $h-1$, or some shorter horizon. Because no value function bootstraps from itself, fixed-horizon methods are immune to the stability problems that plague other off-policy TD methods using function approximation (also known as \"the deadly triad\"). Although fixed-horizon methods req"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.03906","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1909.03906/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T00:39:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SgiZH22TCve9K+G32t3+TsFFIHCvdZoOEMCCLYOF5uQDB1vLgyb6Qr8mll/Z6Mlbr48+sd6X8Y3LH3tCEh6DAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T11:59:45.557475Z"},"content_sha256":"941798733236510dcaad4bbe10fae803d45f4783aee32125e7d69c5678764d31","schema_version":"1.0","event_id":"sha256:941798733236510dcaad4bbe10fae803d45f4783aee32125e7d69c5678764d31"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DMPBXSO53ZQROEG5JNKITOQTDY/bundle.json","state_url":"https://pith.science/pith/DMPBXSO53ZQROEG5JNKITOQTDY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DMPBXSO53ZQROEG5JNKITOQTDY/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":"2026-07-24T11:59:45Z","links":{"resolver":"https://pith.science/pith/DMPBXSO53ZQROEG5JNKITOQTDY","bundle":"https://pith.science/pith/DMPBXSO53ZQROEG5JNKITOQTDY/bundle.json","state":"https://pith.science/pith/DMPBXSO53ZQROEG5JNKITOQTDY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DMPBXSO53ZQROEG5JNKITOQTDY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:DMPBXSO53ZQROEG5JNKITOQTDY","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":"f796c56cfb7f25cc0d8e51425afededc2ddd04c8eb05e69a2e0e2f0577805690","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-09T14:57:42Z","title_canon_sha256":"eb8c264b5e72f263efdc243e2a129a73b159484dc1a9fdb81f3c14a6fa1ddc46"},"schema_version":"1.0","source":{"id":"1909.03906","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.03906","created_at":"2026-07-05T00:39:38Z"},{"alias_kind":"arxiv_version","alias_value":"1909.03906v2","created_at":"2026-07-05T00:39:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.03906","created_at":"2026-07-05T00:39:38Z"},{"alias_kind":"pith_short_12","alias_value":"DMPBXSO53ZQR","created_at":"2026-07-05T00:39:38Z"},{"alias_kind":"pith_short_16","alias_value":"DMPBXSO53ZQROEG5","created_at":"2026-07-05T00:39:38Z"},{"alias_kind":"pith_short_8","alias_value":"DMPBXSO5","created_at":"2026-07-05T00:39:38Z"}],"graph_snapshots":[{"event_id":"sha256:941798733236510dcaad4bbe10fae803d45f4783aee32125e7d69c5678764d31","target":"graph","created_at":"2026-07-05T00:39:38Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1909.03906/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We explore fixed-horizon temporal difference (TD) methods, reinforcement learning algorithms for a new kind of value function that predicts the sum of rewards over a $\\textit{fixed}$ number of future time steps. To learn the value function for horizon $h$, these algorithms bootstrap from the value function for horizon $h-1$, or some shorter horizon. Because no value function bootstraps from itself, fixed-horizon methods are immune to the stability problems that plague other off-policy TD methods using function approximation (also known as \"the deadly triad\"). Although fixed-horizon methods req","authors_text":"Alan Chan, Daniel Graves, Kristopher De Asis, Richard S. Sutton, Silviu Pitis","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-09T14:57:42Z","title":"Fixed-Horizon Temporal Difference Methods for Stable Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.03906","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":"sha256:8945762d6d25460bef605c5ba597d3437e9159c2021d7b32571fb3b592c09ca4","target":"record","created_at":"2026-07-05T00:39:38Z","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":"f796c56cfb7f25cc0d8e51425afededc2ddd04c8eb05e69a2e0e2f0577805690","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-09T14:57:42Z","title_canon_sha256":"eb8c264b5e72f263efdc243e2a129a73b159484dc1a9fdb81f3c14a6fa1ddc46"},"schema_version":"1.0","source":{"id":"1909.03906","kind":"arxiv","version":2}},"canonical_sha256":"1b1e1bc9ddde611710dd4b5489ba131e226c458755d4c8c4e7a9ca7b3bcfe1b5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1b1e1bc9ddde611710dd4b5489ba131e226c458755d4c8c4e7a9ca7b3bcfe1b5","first_computed_at":"2026-07-05T00:39:38.342480Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:39:38.342480Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UEy9uFqW1QUL5QuPKMf38wEr50MyQ8nlT2nNhyR+e7dm8eAd3UWDQNfveo0rUDYNiG7FXVOSLCawodVypYsvBg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:39:38.342909Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.03906","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8945762d6d25460bef605c5ba597d3437e9159c2021d7b32571fb3b592c09ca4","sha256:941798733236510dcaad4bbe10fae803d45f4783aee32125e7d69c5678764d31"],"state_sha256":"b721e8282aade56387b1c9534d6c1828520fdef4e8786fb71ebb41cf926b7f03"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"soeeXp9zUVipUKiZ6YA7TGhDte61soQtl0STHSdfdD4CAw/Ogzg0RGtixVnGsO4clGSa2jirzIU/UVsrgGUmDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-24T11:59:45.559655Z","bundle_sha256":"e611f41960a3e72b208209865b017310707ec74123d9158663577f178880615e"}}