{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:UHRPXHUUI4S6XRJ75UWXGCVX2H","short_pith_number":"pith:UHRPXHUU","canonical_record":{"source":{"id":"2209.04624","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-10T08:55:20Z","cross_cats_sorted":[],"title_canon_sha256":"63022470a25a240c0eedc576f8d105f7db2b49d9f7c1999eb1b11714050c3ea0","abstract_canon_sha256":"a12f7d92f8f97d3fae8ec9181aa347ca2f44e8f074eb127366a4c91b18f0a40c"},"schema_version":"1.0"},"canonical_sha256":"a1e2fb9e944725ebc53fed2d730ab7d1c039f16b99702e7c77e40f5024d62f2a","source":{"kind":"arxiv","id":"2209.04624","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.04624","created_at":"2026-07-05T04:56:03Z"},{"alias_kind":"arxiv_version","alias_value":"2209.04624v1","created_at":"2026-07-05T04:56:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.04624","created_at":"2026-07-05T04:56:03Z"},{"alias_kind":"pith_short_12","alias_value":"UHRPXHUUI4S6","created_at":"2026-07-05T04:56:03Z"},{"alias_kind":"pith_short_16","alias_value":"UHRPXHUUI4S6XRJ7","created_at":"2026-07-05T04:56:03Z"},{"alias_kind":"pith_short_8","alias_value":"UHRPXHUU","created_at":"2026-07-05T04:56:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:UHRPXHUUI4S6XRJ75UWXGCVX2H","target":"record","payload":{"canonical_record":{"source":{"id":"2209.04624","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-10T08:55:20Z","cross_cats_sorted":[],"title_canon_sha256":"63022470a25a240c0eedc576f8d105f7db2b49d9f7c1999eb1b11714050c3ea0","abstract_canon_sha256":"a12f7d92f8f97d3fae8ec9181aa347ca2f44e8f074eb127366a4c91b18f0a40c"},"schema_version":"1.0"},"canonical_sha256":"a1e2fb9e944725ebc53fed2d730ab7d1c039f16b99702e7c77e40f5024d62f2a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:56:03.556949Z","signature_b64":"7tCTDBWjAMXG80a0B2tXExCAtAwnvSgmv5gOIRB/R8sWibjN9F51VjlCjXs7/d/mWu6KNxEH5yua0WDWd39pDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1e2fb9e944725ebc53fed2d730ab7d1c039f16b99702e7c77e40f5024d62f2a","last_reissued_at":"2026-07-05T04:56:03.556618Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:56:03.556618Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2209.04624","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":"2026-07-05T04:56:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZUrhK5DkL2CGZm4Wn9CT8fOB2s2f8UqO0R9NZpZ5fhTvZQPp6Rjkd1XfWI6uO2272lG4ftsnw4zalU9heMNdBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T07:22:26.107717Z"},"content_sha256":"f2a1e1b2cc9f1e1477dddd4d93a56ce7c1aea9548b0736e1854db77aa33a2afd","schema_version":"1.0","event_id":"sha256:f2a1e1b2cc9f1e1477dddd4d93a56ce7c1aea9548b0736e1854db77aa33a2afd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:UHRPXHUUI4S6XRJ75UWXGCVX2H","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Gradient Descent Temporal Difference-difference Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"James M. Murray, Rong J.B. Zhu","submitted_at":"2022-09-10T08:55:20Z","abstract_excerpt":"Off-policy algorithms, in which a behavior policy differs from the target policy and is used to gain experience for learning, have proven to be of great practical value in reinforcement learning. However, even for simple convex problems such as linear value function approximation, these algorithms are not guaranteed to be stable. To address this, alternative algorithms that are provably convergent in such cases have been introduced, the most well known being gradient descent temporal difference (GTD) learning. This algorithm and others like it, however, tend to converge much more slowly than c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.04624","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2209.04624/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":"2026-07-05T04:56:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5sdhzl3lp+TfDv5BThQuUJ5aobgj6W1xZ/Ad39jYhhk0gKhu07sRtxuxiyYEqFJwm8wtOXCksuzqPeeTl+16Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T07:22:26.108654Z"},"content_sha256":"df33aee14c6398ecd95846a91b20f03c53814cecc362d0e9267ce2140524ca2f","schema_version":"1.0","event_id":"sha256:df33aee14c6398ecd95846a91b20f03c53814cecc362d0e9267ce2140524ca2f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UHRPXHUUI4S6XRJ75UWXGCVX2H/bundle.json","state_url":"https://pith.science/pith/UHRPXHUUI4S6XRJ75UWXGCVX2H/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UHRPXHUUI4S6XRJ75UWXGCVX2H/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":"2026-08-19T07:22:26Z","links":{"resolver":"https://pith.science/pith/UHRPXHUUI4S6XRJ75UWXGCVX2H","bundle":"https://pith.science/pith/UHRPXHUUI4S6XRJ75UWXGCVX2H/bundle.json","state":"https://pith.science/pith/UHRPXHUUI4S6XRJ75UWXGCVX2H/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UHRPXHUUI4S6XRJ75UWXGCVX2H/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:UHRPXHUUI4S6XRJ75UWXGCVX2H","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":"a12f7d92f8f97d3fae8ec9181aa347ca2f44e8f074eb127366a4c91b18f0a40c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-10T08:55:20Z","title_canon_sha256":"63022470a25a240c0eedc576f8d105f7db2b49d9f7c1999eb1b11714050c3ea0"},"schema_version":"1.0","source":{"id":"2209.04624","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2209.04624","created_at":"2026-07-05T04:56:03Z"},{"alias_kind":"arxiv_version","alias_value":"2209.04624v1","created_at":"2026-07-05T04:56:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.04624","created_at":"2026-07-05T04:56:03Z"},{"alias_kind":"pith_short_12","alias_value":"UHRPXHUUI4S6","created_at":"2026-07-05T04:56:03Z"},{"alias_kind":"pith_short_16","alias_value":"UHRPXHUUI4S6XRJ7","created_at":"2026-07-05T04:56:03Z"},{"alias_kind":"pith_short_8","alias_value":"UHRPXHUU","created_at":"2026-07-05T04:56:03Z"}],"graph_snapshots":[{"event_id":"sha256:df33aee14c6398ecd95846a91b20f03c53814cecc362d0e9267ce2140524ca2f","target":"graph","created_at":"2026-07-05T04:56:03Z","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/2209.04624/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Off-policy algorithms, in which a behavior policy differs from the target policy and is used to gain experience for learning, have proven to be of great practical value in reinforcement learning. However, even for simple convex problems such as linear value function approximation, these algorithms are not guaranteed to be stable. To address this, alternative algorithms that are provably convergent in such cases have been introduced, the most well known being gradient descent temporal difference (GTD) learning. This algorithm and others like it, however, tend to converge much more slowly than c","authors_text":"James M. Murray, Rong J.B. Zhu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-10T08:55:20Z","title":"Gradient Descent Temporal Difference-difference Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.04624","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:f2a1e1b2cc9f1e1477dddd4d93a56ce7c1aea9548b0736e1854db77aa33a2afd","target":"record","created_at":"2026-07-05T04:56:03Z","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":"a12f7d92f8f97d3fae8ec9181aa347ca2f44e8f074eb127366a4c91b18f0a40c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-10T08:55:20Z","title_canon_sha256":"63022470a25a240c0eedc576f8d105f7db2b49d9f7c1999eb1b11714050c3ea0"},"schema_version":"1.0","source":{"id":"2209.04624","kind":"arxiv","version":1}},"canonical_sha256":"a1e2fb9e944725ebc53fed2d730ab7d1c039f16b99702e7c77e40f5024d62f2a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a1e2fb9e944725ebc53fed2d730ab7d1c039f16b99702e7c77e40f5024d62f2a","first_computed_at":"2026-07-05T04:56:03.556618Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:56:03.556618Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7tCTDBWjAMXG80a0B2tXExCAtAwnvSgmv5gOIRB/R8sWibjN9F51VjlCjXs7/d/mWu6KNxEH5yua0WDWd39pDw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:56:03.556949Z","signed_message":"canonical_sha256_bytes"},"source_id":"2209.04624","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f2a1e1b2cc9f1e1477dddd4d93a56ce7c1aea9548b0736e1854db77aa33a2afd","sha256:df33aee14c6398ecd95846a91b20f03c53814cecc362d0e9267ce2140524ca2f"],"state_sha256":"2910fcfc35c1aaef2d84ebe745e186dc76a81c2b14a2010b88854ca466f0c906"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K9bKfHodPViz3jjeRF/VONTQvh7IMxMhCW25yEJGve3aD5N06cBuYjPcqY/GRFS+Q8j3MEuWAkFpNMc2HsxHBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T07:22:26.115043Z","bundle_sha256":"e40a2ee56e34c0316b838465dd61ca2a2945d18ee31d11d05c13e6b969185b24"}}