{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:HOMMGM5OXUO7DZBQFCDJ72SMME","short_pith_number":"pith:HOMMGM5O","schema_version":"1.0","canonical_sha256":"3b98c333aebd1df1e43028869fea4c6116eb48f049433420cf76ea91aa5e3a49","source":{"kind":"arxiv","id":"2608.10896","version":1},"attestation_state":"computed","paper":{"title":"Self-Normalized Inference for Constant-Stepsize Temporal-Difference Learning under Markovian Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Min Zeng, Xiaofeng Shao, Yichen Zhang","submitted_at":"2026-08-11T13:19:28Z","abstract_excerpt":"Constant-stepsize temporal-difference (TD) learning is attractive for policy evaluation, but inference from a single Markov trajectory must account for serial dependence and a stepsize-dependent stationary target. For fixed-stepsize linear TD, we establish a functional central limit theorem whose covariance retains the multiplicative component induced by the random TD matrix and the stationary iterate error. We then derive a joint functional limit for parallel Richardson--Romberg (RR) recursions driven by the same trajectory. A Brownian-bridge self-normalizer yields asymptotically pivotal conf"},"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":"2608.10896","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-08-11T13:19:28Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"539cd460a7579a405033ef3240e6c6f8248c134d884dc08bfff48ecf3451706b","abstract_canon_sha256":"163c1e95fc8e9a6b6f9c9b995f8f21218736387e372e5aade3b9f0890692caaf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-12T01:23:45.631447Z","signature_b64":"3+QWk1UJNwAAAqaxvr6AD+T9Z1179T6980+GJw7Ukm2UmymYCEaDqNgNKDAh6xLocjuvmIj1iRKar6ByyPD6CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b98c333aebd1df1e43028869fea4c6116eb48f049433420cf76ea91aa5e3a49","last_reissued_at":"2026-08-12T01:23:45.629852Z","signature_status":"signed_v1","first_computed_at":"2026-08-12T01:23:45.629852Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Normalized Inference for Constant-Stepsize Temporal-Difference Learning under Markovian Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Min Zeng, Xiaofeng Shao, Yichen Zhang","submitted_at":"2026-08-11T13:19:28Z","abstract_excerpt":"Constant-stepsize temporal-difference (TD) learning is attractive for policy evaluation, but inference from a single Markov trajectory must account for serial dependence and a stepsize-dependent stationary target. For fixed-stepsize linear TD, we establish a functional central limit theorem whose covariance retains the multiplicative component induced by the random TD matrix and the stationary iterate error. We then derive a joint functional limit for parallel Richardson--Romberg (RR) recursions driven by the same trajectory. A Brownian-bridge self-normalizer yields asymptotically pivotal conf"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.10896","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/2608.10896/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":"2608.10896","created_at":"2026-08-12T01:23:45.633688+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.10896v1","created_at":"2026-08-12T01:23:45.633688+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.10896","created_at":"2026-08-12T01:23:45.633688+00:00"},{"alias_kind":"pith_short_12","alias_value":"HOMMGM5OXUO7","created_at":"2026-08-12T01:23:45.633688+00:00"},{"alias_kind":"pith_short_16","alias_value":"HOMMGM5OXUO7DZBQ","created_at":"2026-08-12T01:23:45.633688+00:00"},{"alias_kind":"pith_short_8","alias_value":"HOMMGM5O","created_at":"2026-08-12T01:23:45.633688+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/HOMMGM5OXUO7DZBQFCDJ72SMME","json":"https://pith.science/pith/HOMMGM5OXUO7DZBQFCDJ72SMME.json","graph_json":"https://pith.science/api/pith-number/HOMMGM5OXUO7DZBQFCDJ72SMME/graph.json","events_json":"https://pith.science/api/pith-number/HOMMGM5OXUO7DZBQFCDJ72SMME/events.json","paper":"https://pith.science/paper/HOMMGM5O"},"agent_actions":{"view_html":"https://pith.science/pith/HOMMGM5OXUO7DZBQFCDJ72SMME","download_json":"https://pith.science/pith/HOMMGM5OXUO7DZBQFCDJ72SMME.json","view_paper":"https://pith.science/paper/HOMMGM5O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.10896&json=true","fetch_graph":"https://pith.science/api/pith-number/HOMMGM5OXUO7DZBQFCDJ72SMME/graph.json","fetch_events":"https://pith.science/api/pith-number/HOMMGM5OXUO7DZBQFCDJ72SMME/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HOMMGM5OXUO7DZBQFCDJ72SMME/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HOMMGM5OXUO7DZBQFCDJ72SMME/action/storage_attestation","attest_author":"https://pith.science/pith/HOMMGM5OXUO7DZBQFCDJ72SMME/action/author_attestation","sign_citation":"https://pith.science/pith/HOMMGM5OXUO7DZBQFCDJ72SMME/action/citation_signature","submit_replication":"https://pith.science/pith/HOMMGM5OXUO7DZBQFCDJ72SMME/action/replication_record"}},"created_at":"2026-08-12T01:23:45.633688+00:00","updated_at":"2026-08-12T01:23:45.633688+00:00"}