{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YNLIOXTVO4MW45JJSGCBLPQQGY","short_pith_number":"pith:YNLIOXTV","schema_version":"1.0","canonical_sha256":"c356875e7577196e7529918415be10361b5f4fb23a81776673e4328868fbfdf9","source":{"kind":"arxiv","id":"2505.01361","version":2},"attestation_state":"computed","paper":{"title":"Stabilizing Temporal Difference Learning via Implicit Stochastic Recursion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.PR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Eric Laber, Hwanwoo Kim, Panos Toulis","submitted_at":"2025-05-02T15:57:54Z","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 "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2505.01361","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-02T15:57:54Z","cross_cats_sorted":["math.PR","stat.ML"],"title_canon_sha256":"53979d11f135810c40d5051b7ef5a98b571d1304c325ad490b4b70d0850b4657","abstract_canon_sha256":"364cb822254aa408bc60e023f5fefafd40ece69b8103a1f12fb9469fc56c49e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:25:10.240479Z","signature_b64":"hjByfoOqFeZ6rQIJg/HiTbdcn6Wzs8D+pHM+CQ4qhlmqUyzKP6HG+b40nmTt/JRMfdV05DDc5UvXBsmAZSNRDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c356875e7577196e7529918415be10361b5f4fb23a81776673e4328868fbfdf9","last_reissued_at":"2026-07-05T11:25:10.239992Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:25:10.239992Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stabilizing Temporal Difference Learning via Implicit Stochastic Recursion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.PR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Eric Laber, Hwanwoo Kim, Panos Toulis","submitted_at":"2025-05-02T15:57:54Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.01361","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/2505.01361/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2505.01361","created_at":"2026-07-05T11:25:10.240051+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.01361v2","created_at":"2026-07-05T11:25:10.240051+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.01361","created_at":"2026-07-05T11:25:10.240051+00:00"},{"alias_kind":"pith_short_12","alias_value":"YNLIOXTVO4MW","created_at":"2026-07-05T11:25:10.240051+00:00"},{"alias_kind":"pith_short_16","alias_value":"YNLIOXTVO4MW45JJ","created_at":"2026-07-05T11:25:10.240051+00:00"},{"alias_kind":"pith_short_8","alias_value":"YNLIOXTV","created_at":"2026-07-05T11:25:10.240051+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YNLIOXTVO4MW45JJSGCBLPQQGY","json":"https://pith.science/pith/YNLIOXTVO4MW45JJSGCBLPQQGY.json","graph_json":"https://pith.science/api/pith-number/YNLIOXTVO4MW45JJSGCBLPQQGY/graph.json","events_json":"https://pith.science/api/pith-number/YNLIOXTVO4MW45JJSGCBLPQQGY/events.json","paper":"https://pith.science/paper/YNLIOXTV"},"agent_actions":{"view_html":"https://pith.science/pith/YNLIOXTVO4MW45JJSGCBLPQQGY","download_json":"https://pith.science/pith/YNLIOXTVO4MW45JJSGCBLPQQGY.json","view_paper":"https://pith.science/paper/YNLIOXTV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.01361&json=true","fetch_graph":"https://pith.science/api/pith-number/YNLIOXTVO4MW45JJSGCBLPQQGY/graph.json","fetch_events":"https://pith.science/api/pith-number/YNLIOXTVO4MW45JJSGCBLPQQGY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YNLIOXTVO4MW45JJSGCBLPQQGY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YNLIOXTVO4MW45JJSGCBLPQQGY/action/storage_attestation","attest_author":"https://pith.science/pith/YNLIOXTVO4MW45JJSGCBLPQQGY/action/author_attestation","sign_citation":"https://pith.science/pith/YNLIOXTVO4MW45JJSGCBLPQQGY/action/citation_signature","submit_replication":"https://pith.science/pith/YNLIOXTVO4MW45JJSGCBLPQQGY/action/replication_record"}},"created_at":"2026-07-05T11:25:10.240051+00:00","updated_at":"2026-07-05T11:25:10.240051+00:00"}