{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AMIF6PQNWQ4VXBXSSR3SBGMXMK","short_pith_number":"pith:AMIF6PQN","schema_version":"1.0","canonical_sha256":"03105f3e0db4395b86f294772099976297120ac6c31400429e24b6eba355055e","source":{"kind":"arxiv","id":"2606.18183","version":1},"attestation_state":"computed","paper":{"title":"A Diffusion Approximation for Temporal-Difference Learning with Linear Features under Markovian Noise","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.PR"],"primary_cat":"stat.ML","authors_text":"A. Pacchiano, A. Russo, E. Monzio Compagnoni, M. Forzo","submitted_at":"2026-06-16T17:16:52Z","abstract_excerpt":"Temporal difference (TD) learning with linear function approximation is a core method for policy evaluation. Its classical continuous-time description is an ordinary differential equation (ODE), which captures the asymptotic mean dynamics but neglects stochastic fluctuations determining the error floor. We introduce a stochastic differential equation (SDE) approximation for linear TD(0) under Markovian noise. The resulting model distinguishes the contraction dynamics governed by the projected Bellman operator from the influence of Markovian sampling. As a consequence, the model explains the co"},"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":"2606.18183","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-06-16T17:16:52Z","cross_cats_sorted":["cs.LG","math.PR"],"title_canon_sha256":"cf0e8c34bdff8178005de6c37d8dc23dc2af0a846473f5588a7991154d21e393","abstract_canon_sha256":"0b171dbbaf8e950b85c3af0461e083e8e12cce0c2194141d133c354ace5565de"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:10:50.487269Z","signature_b64":"cPTvb9mWImX3ENA85ntRYwJbtjOXubxSRa65B0Q1JtTRgUaZv5xvy/9D1aSo4xJtV4akDeRzxME9sjpJaKOSDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03105f3e0db4395b86f294772099976297120ac6c31400429e24b6eba355055e","last_reissued_at":"2026-06-19T16:10:50.486929Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:10:50.486929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Diffusion Approximation for Temporal-Difference Learning with Linear Features under Markovian Noise","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.PR"],"primary_cat":"stat.ML","authors_text":"A. Pacchiano, A. Russo, E. Monzio Compagnoni, M. Forzo","submitted_at":"2026-06-16T17:16:52Z","abstract_excerpt":"Temporal difference (TD) learning with linear function approximation is a core method for policy evaluation. Its classical continuous-time description is an ordinary differential equation (ODE), which captures the asymptotic mean dynamics but neglects stochastic fluctuations determining the error floor. We introduce a stochastic differential equation (SDE) approximation for linear TD(0) under Markovian noise. The resulting model distinguishes the contraction dynamics governed by the projected Bellman operator from the influence of Markovian sampling. As a consequence, the model explains the co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.18183","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/2606.18183/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":"2606.18183","created_at":"2026-06-19T16:10:50.486990+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.18183v1","created_at":"2026-06-19T16:10:50.486990+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.18183","created_at":"2026-06-19T16:10:50.486990+00:00"},{"alias_kind":"pith_short_12","alias_value":"AMIF6PQNWQ4V","created_at":"2026-06-19T16:10:50.486990+00:00"},{"alias_kind":"pith_short_16","alias_value":"AMIF6PQNWQ4VXBXS","created_at":"2026-06-19T16:10:50.486990+00:00"},{"alias_kind":"pith_short_8","alias_value":"AMIF6PQN","created_at":"2026-06-19T16:10:50.486990+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/AMIF6PQNWQ4VXBXSSR3SBGMXMK","json":"https://pith.science/pith/AMIF6PQNWQ4VXBXSSR3SBGMXMK.json","graph_json":"https://pith.science/api/pith-number/AMIF6PQNWQ4VXBXSSR3SBGMXMK/graph.json","events_json":"https://pith.science/api/pith-number/AMIF6PQNWQ4VXBXSSR3SBGMXMK/events.json","paper":"https://pith.science/paper/AMIF6PQN"},"agent_actions":{"view_html":"https://pith.science/pith/AMIF6PQNWQ4VXBXSSR3SBGMXMK","download_json":"https://pith.science/pith/AMIF6PQNWQ4VXBXSSR3SBGMXMK.json","view_paper":"https://pith.science/paper/AMIF6PQN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.18183&json=true","fetch_graph":"https://pith.science/api/pith-number/AMIF6PQNWQ4VXBXSSR3SBGMXMK/graph.json","fetch_events":"https://pith.science/api/pith-number/AMIF6PQNWQ4VXBXSSR3SBGMXMK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AMIF6PQNWQ4VXBXSSR3SBGMXMK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AMIF6PQNWQ4VXBXSSR3SBGMXMK/action/storage_attestation","attest_author":"https://pith.science/pith/AMIF6PQNWQ4VXBXSSR3SBGMXMK/action/author_attestation","sign_citation":"https://pith.science/pith/AMIF6PQNWQ4VXBXSSR3SBGMXMK/action/citation_signature","submit_replication":"https://pith.science/pith/AMIF6PQNWQ4VXBXSSR3SBGMXMK/action/replication_record"}},"created_at":"2026-06-19T16:10:50.486990+00:00","updated_at":"2026-06-19T16:10:50.486990+00:00"}