{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZFUTQUVRUH3VIB4PMA3BSZ6LP7","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":"02c59c387b27f4ad8c32204752ab1ec4f0a7c205c82c57e1a65f526ceb0cb905","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-06T21:49:29Z","title_canon_sha256":"2c7ac1e08ef5b03f565f97324d86c4d409c13ea468ebec63b92f01285046e32f"},"schema_version":"1.0","source":{"id":"2405.03878","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.03878","created_at":"2026-07-05T08:27:07Z"},{"alias_kind":"arxiv_version","alias_value":"2405.03878v2","created_at":"2026-07-05T08:27:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.03878","created_at":"2026-07-05T08:27:07Z"},{"alias_kind":"pith_short_12","alias_value":"ZFUTQUVRUH3V","created_at":"2026-07-05T08:27:07Z"},{"alias_kind":"pith_short_16","alias_value":"ZFUTQUVRUH3VIB4P","created_at":"2026-07-05T08:27:07Z"},{"alias_kind":"pith_short_8","alias_value":"ZFUTQUVR","created_at":"2026-07-05T08:27:07Z"}],"graph_snapshots":[{"event_id":"sha256:9a2a7afa47b72eaa6ac5b1183ddac7a13bfb01d867c5276e68c73905784ad2d8","target":"graph","created_at":"2026-07-05T08:27:07Z","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/2405.03878/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Temporal credit assignment in reinforcement learning is challenging due to delayed and stochastic outcomes. Monte Carlo targets can bridge long delays between action and consequence but lead to high-variance targets due to stochasticity. Temporal difference (TD) learning uses bootstrapping to overcome variance but introduces a bias that can only be corrected through many iterations. TD($\\lambda$) provides a mechanism to navigate this bias-variance tradeoff smoothly. Appropriately selecting $\\lambda$ can significantly improve performance. Here, we propose Chunked-TD, which uses predicted probab","authors_text":"Aditya A. Ramesh, J\\\"urgen Schmidhuber, Kenny Young, Louis Kirsch","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-06T21:49:29Z","title":"Sequence Compression Speeds Up Credit Assignment in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.03878","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":"sha256:3fa8f6abea36212e01c315e6280dca9157c90804e34aaa68fda17d3151513001","target":"record","created_at":"2026-07-05T08:27:07Z","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":"02c59c387b27f4ad8c32204752ab1ec4f0a7c205c82c57e1a65f526ceb0cb905","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-06T21:49:29Z","title_canon_sha256":"2c7ac1e08ef5b03f565f97324d86c4d409c13ea468ebec63b92f01285046e32f"},"schema_version":"1.0","source":{"id":"2405.03878","kind":"arxiv","version":2}},"canonical_sha256":"c9693852b1a1f754078f60361967cb7ffe06286549422a36cf753b31f430d167","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c9693852b1a1f754078f60361967cb7ffe06286549422a36cf753b31f430d167","first_computed_at":"2026-07-05T08:27:07.951599Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:27:07.951599Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Tn6RH5Jpyfoioeq2KaHI9tVT1fRM5bEIF6XLHFLxkzurPdVxrw1QAxeECDnfD92D7BA9ikzes6M5112nYGz8DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:27:07.952059Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.03878","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3fa8f6abea36212e01c315e6280dca9157c90804e34aaa68fda17d3151513001","sha256:9a2a7afa47b72eaa6ac5b1183ddac7a13bfb01d867c5276e68c73905784ad2d8"],"state_sha256":"c89eea1cb311d6e88011328068e3f3e23401262f0f8c4e8cefe8ce1ca22ef794"}