{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:DJVUNF7OLQTCVEDYUL7Y2MALFP","short_pith_number":"pith:DJVUNF7O","canonical_record":{"source":{"id":"1805.00869","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-02T15:40:24Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"34d309dd2936a519583c04c3fbb4b6060c460c2c3c785d3e4fb415a12649bbbd","abstract_canon_sha256":"a77d88c4da8fb0cb298bad55271aa28ff348443772b34f5afa6987d34a370ede"},"schema_version":"1.0"},"canonical_sha256":"1a6b4697ee5c262a9078a2ff8d300b2bcd441e3523f0fc7d4486132c70afce6c","source":{"kind":"arxiv","id":"1805.00869","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.00869","created_at":"2026-05-18T00:16:57Z"},{"alias_kind":"arxiv_version","alias_value":"1805.00869v1","created_at":"2026-05-18T00:16:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.00869","created_at":"2026-05-18T00:16:57Z"},{"alias_kind":"pith_short_12","alias_value":"DJVUNF7OLQTC","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"DJVUNF7OLQTCVEDY","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"DJVUNF7O","created_at":"2026-05-18T12:32:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:DJVUNF7OLQTCVEDYUL7Y2MALFP","target":"record","payload":{"canonical_record":{"source":{"id":"1805.00869","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-02T15:40:24Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"34d309dd2936a519583c04c3fbb4b6060c460c2c3c785d3e4fb415a12649bbbd","abstract_canon_sha256":"a77d88c4da8fb0cb298bad55271aa28ff348443772b34f5afa6987d34a370ede"},"schema_version":"1.0"},"canonical_sha256":"1a6b4697ee5c262a9078a2ff8d300b2bcd441e3523f0fc7d4486132c70afce6c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:16:57.412919Z","signature_b64":"auK3RBR//U4U6qXufEYZUskv2PeTdv5kvUK4xQYawmnD0cqdGCEn+bSeFjPwvh1/xTLC2VvRXOCnj8xShx7sDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a6b4697ee5c262a9078a2ff8d300b2bcd441e3523f0fc7d4486132c70afce6c","last_reissued_at":"2026-05-18T00:16:57.412249Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:16:57.412249Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.00869","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":"2026-05-18T00:16:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DKkcILI+K4eeGWQRje2GcLO1NACIjW7wRL5NK/CzHa28jRj9jXBRLKGapt7L+/7ObQ3Y+yhiaS/HYj2CQ0N3DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T04:08:35.441893Z"},"content_sha256":"ef34fe7a3d1b618e9042c2d3359d37a1d5a0b68f74c9c72733bf80c01d31d957","schema_version":"1.0","event_id":"sha256:ef34fe7a3d1b618e9042c2d3359d37a1d5a0b68f74c9c72733bf80c01d31d957"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:DJVUNF7OLQTCVEDYUL7Y2MALFP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Approximate Temporal Difference Learning is a Gradient Descent for Reversible Policies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Yann Ollivier","submitted_at":"2018-05-02T15:40:24Z","abstract_excerpt":"In reinforcement learning, temporal difference (TD) is the most direct algorithm to learn the value function of a policy. For large or infinite state spaces, exact representations of the value function are usually not available, and it must be approximated by a function in some parametric family.\n  However, with \\emph{nonlinear} parametric approximations (such as neural networks), TD is not guaranteed to converge to a good approximation of the true value function within the family, and is known to diverge even in relatively simple cases. TD lacks an interpretation as a stochastic gradient desc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.00869","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":"2026-05-18T00:16:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"apZyUaQhvwretGZiAsGqvvHJSqzkeOoiYLrOQDfg3lnZ2DB7rANr5eTLnVa/5bKnFxmfn2Xr0Hn+8gIZs49+AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T04:08:35.442644Z"},"content_sha256":"dfeeed280a6c05d42e507a6e44f5fa6f5a910db243689220d6799ca29546d8ce","schema_version":"1.0","event_id":"sha256:dfeeed280a6c05d42e507a6e44f5fa6f5a910db243689220d6799ca29546d8ce"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DJVUNF7OLQTCVEDYUL7Y2MALFP/bundle.json","state_url":"https://pith.science/pith/DJVUNF7OLQTCVEDYUL7Y2MALFP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DJVUNF7OLQTCVEDYUL7Y2MALFP/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":"2026-06-06T04:08:35Z","links":{"resolver":"https://pith.science/pith/DJVUNF7OLQTCVEDYUL7Y2MALFP","bundle":"https://pith.science/pith/DJVUNF7OLQTCVEDYUL7Y2MALFP/bundle.json","state":"https://pith.science/pith/DJVUNF7OLQTCVEDYUL7Y2MALFP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DJVUNF7OLQTCVEDYUL7Y2MALFP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:DJVUNF7OLQTCVEDYUL7Y2MALFP","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":"a77d88c4da8fb0cb298bad55271aa28ff348443772b34f5afa6987d34a370ede","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-02T15:40:24Z","title_canon_sha256":"34d309dd2936a519583c04c3fbb4b6060c460c2c3c785d3e4fb415a12649bbbd"},"schema_version":"1.0","source":{"id":"1805.00869","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.00869","created_at":"2026-05-18T00:16:57Z"},{"alias_kind":"arxiv_version","alias_value":"1805.00869v1","created_at":"2026-05-18T00:16:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.00869","created_at":"2026-05-18T00:16:57Z"},{"alias_kind":"pith_short_12","alias_value":"DJVUNF7OLQTC","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"DJVUNF7OLQTCVEDY","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"DJVUNF7O","created_at":"2026-05-18T12:32:19Z"}],"graph_snapshots":[{"event_id":"sha256:dfeeed280a6c05d42e507a6e44f5fa6f5a910db243689220d6799ca29546d8ce","target":"graph","created_at":"2026-05-18T00:16:57Z","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":"In reinforcement learning, temporal difference (TD) is the most direct algorithm to learn the value function of a policy. For large or infinite state spaces, exact representations of the value function are usually not available, and it must be approximated by a function in some parametric family.\n  However, with \\emph{nonlinear} parametric approximations (such as neural networks), TD is not guaranteed to converge to a good approximation of the true value function within the family, and is known to diverge even in relatively simple cases. TD lacks an interpretation as a stochastic gradient desc","authors_text":"Yann Ollivier","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-02T15:40:24Z","title":"Approximate Temporal Difference Learning is a Gradient Descent for Reversible Policies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.00869","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:ef34fe7a3d1b618e9042c2d3359d37a1d5a0b68f74c9c72733bf80c01d31d957","target":"record","created_at":"2026-05-18T00:16:57Z","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":"a77d88c4da8fb0cb298bad55271aa28ff348443772b34f5afa6987d34a370ede","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-02T15:40:24Z","title_canon_sha256":"34d309dd2936a519583c04c3fbb4b6060c460c2c3c785d3e4fb415a12649bbbd"},"schema_version":"1.0","source":{"id":"1805.00869","kind":"arxiv","version":1}},"canonical_sha256":"1a6b4697ee5c262a9078a2ff8d300b2bcd441e3523f0fc7d4486132c70afce6c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1a6b4697ee5c262a9078a2ff8d300b2bcd441e3523f0fc7d4486132c70afce6c","first_computed_at":"2026-05-18T00:16:57.412249Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:16:57.412249Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"auK3RBR//U4U6qXufEYZUskv2PeTdv5kvUK4xQYawmnD0cqdGCEn+bSeFjPwvh1/xTLC2VvRXOCnj8xShx7sDw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:16:57.412919Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.00869","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ef34fe7a3d1b618e9042c2d3359d37a1d5a0b68f74c9c72733bf80c01d31d957","sha256:dfeeed280a6c05d42e507a6e44f5fa6f5a910db243689220d6799ca29546d8ce"],"state_sha256":"50466d8c54e6aac03ac42bd497578f137a631419fb5bec9bb5ad6d246ab86159"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eUvXh5iBv5xsv58or7x0lL64Itg68ipy5BxfpSS5QHGo/urMNtKJV6f4+mHNaaYT8K35xXdWv6fnIv8A/J1gCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T04:08:35.445440Z","bundle_sha256":"e71454c9589987b05d0e3f7dd15ad9ff7edab462d4a8b29b7c83b7c1a72809fb"}}