{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YNLIOXTVO4MW45JJSGCBLPQQGY","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":"364cb822254aa408bc60e023f5fefafd40ece69b8103a1f12fb9469fc56c49e6","cross_cats_sorted":["math.PR","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-02T15:57:54Z","title_canon_sha256":"53979d11f135810c40d5051b7ef5a98b571d1304c325ad490b4b70d0850b4657"},"schema_version":"1.0","source":{"id":"2505.01361","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.01361","created_at":"2026-07-05T11:25:10Z"},{"alias_kind":"arxiv_version","alias_value":"2505.01361v2","created_at":"2026-07-05T11:25:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.01361","created_at":"2026-07-05T11:25:10Z"},{"alias_kind":"pith_short_12","alias_value":"YNLIOXTVO4MW","created_at":"2026-07-05T11:25:10Z"},{"alias_kind":"pith_short_16","alias_value":"YNLIOXTVO4MW45JJ","created_at":"2026-07-05T11:25:10Z"},{"alias_kind":"pith_short_8","alias_value":"YNLIOXTV","created_at":"2026-07-05T11:25:10Z"}],"graph_snapshots":[{"event_id":"sha256:96dc1064cd2adfa40255b8785ac4b9096c49fcc1501365caac9f3b094ca755b5","target":"graph","created_at":"2026-07-05T11:25:10Z","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/2505.01361/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Temporal difference (TD) learning is a foundational algorithm in reinforcement learning (RL). For nearly forty years, TD learning has served as a workhorse for applied RL as well as a building block for more complex and specialized algorithms. However, despite its widespread use, TD procedures are generally sensitive to step size specification. A poor choice of step size can dramatically increase variance and slow convergence in both on-policy and off-policy evaluation tasks. In practice, researchers use trial and error to identify stable step sizes, but these approaches tend to be ad hoc and ","authors_text":"Eric Laber, Hwanwoo Kim, Panos Toulis","cross_cats":["math.PR","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-02T15:57:54Z","title":"Stabilizing Temporal Difference Learning via Implicit Stochastic Recursion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.01361","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":"sha256:0a1ecd56be4975662a2ebbe6ebac2f40e811e5f98d7e684cdee2b002a5d95900","target":"record","created_at":"2026-07-05T11:25:10Z","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":"364cb822254aa408bc60e023f5fefafd40ece69b8103a1f12fb9469fc56c49e6","cross_cats_sorted":["math.PR","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-02T15:57:54Z","title_canon_sha256":"53979d11f135810c40d5051b7ef5a98b571d1304c325ad490b4b70d0850b4657"},"schema_version":"1.0","source":{"id":"2505.01361","kind":"arxiv","version":2}},"canonical_sha256":"c356875e7577196e7529918415be10361b5f4fb23a81776673e4328868fbfdf9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c356875e7577196e7529918415be10361b5f4fb23a81776673e4328868fbfdf9","first_computed_at":"2026-07-05T11:25:10.239992Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:25:10.239992Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hjByfoOqFeZ6rQIJg/HiTbdcn6Wzs8D+pHM+CQ4qhlmqUyzKP6HG+b40nmTt/JRMfdV05DDc5UvXBsmAZSNRDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:25:10.240479Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.01361","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0a1ecd56be4975662a2ebbe6ebac2f40e811e5f98d7e684cdee2b002a5d95900","sha256:96dc1064cd2adfa40255b8785ac4b9096c49fcc1501365caac9f3b094ca755b5"],"state_sha256":"c71cfd25ad006980d8ba1e488a9942825c5af826c5be74aa9c690f6cfc719aae"}