{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SYMYC6APZDA5QLLDXCTK7O54GS","short_pith_number":"pith:SYMYC6AP","schema_version":"1.0","canonical_sha256":"961981780fc8c1d82d63b8a6afbbbc34b8aaf1924e2869f04116d3b2fe5bb696","source":{"kind":"arxiv","id":"2503.17454","version":2},"attestation_state":"computed","paper":{"title":"Collaborative Value Function Estimation Under Model Mismatch: A Federated Temporal Difference Analysis","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ali Beikmohammadi, Peter Richt\\'arik, Sarit Khirirat, Sindri Magn\\'usson","submitted_at":"2025-03-21T18:06:28Z","abstract_excerpt":"Federated reinforcement learning (FedRL) enables collaborative learning while preserving data privacy by preventing direct data exchange between agents. However, many existing FedRL algorithms assume that all agents operate in identical environments, which is often unrealistic. In real-world applications, such as multi-robot teams, crowdsourced systems, and large-scale sensor networks, each agent may experience slightly different transition dynamics, leading to inherent model mismatches. In this paper, we first establish linear convergence guarantees for single-agent temporal difference learni"},"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":"2503.17454","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-21T18:06:28Z","cross_cats_sorted":[],"title_canon_sha256":"57185d193b12d72c66ecc510d334b9f8372ed41c2e7db3f7fbbafc5c8f86e1df","abstract_canon_sha256":"cb5780bc7ee86d324decad2cef408185489d3211278cc20c751663e4118beaec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:44.544124Z","signature_b64":"x62L9WeCI5Wu9+DZNgS/C4D/gt+QDIeALsBndkQn8tNjo9QuNnmkF1uHMFzQrkl11ZvUTixlZLwPV2nAtb64Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"961981780fc8c1d82d63b8a6afbbbc34b8aaf1924e2869f04116d3b2fe5bb696","last_reissued_at":"2026-07-05T11:21:44.543419Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:44.543419Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Collaborative Value Function Estimation Under Model Mismatch: A Federated Temporal Difference Analysis","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ali Beikmohammadi, Peter Richt\\'arik, Sarit Khirirat, Sindri Magn\\'usson","submitted_at":"2025-03-21T18:06:28Z","abstract_excerpt":"Federated reinforcement learning (FedRL) enables collaborative learning while preserving data privacy by preventing direct data exchange between agents. However, many existing FedRL algorithms assume that all agents operate in identical environments, which is often unrealistic. In real-world applications, such as multi-robot teams, crowdsourced systems, and large-scale sensor networks, each agent may experience slightly different transition dynamics, leading to inherent model mismatches. In this paper, we first establish linear convergence guarantees for single-agent temporal difference learni"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.17454","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/2503.17454/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":"2503.17454","created_at":"2026-07-05T11:21:44.543497+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.17454v2","created_at":"2026-07-05T11:21:44.543497+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.17454","created_at":"2026-07-05T11:21:44.543497+00:00"},{"alias_kind":"pith_short_12","alias_value":"SYMYC6APZDA5","created_at":"2026-07-05T11:21:44.543497+00:00"},{"alias_kind":"pith_short_16","alias_value":"SYMYC6APZDA5QLLD","created_at":"2026-07-05T11:21:44.543497+00:00"},{"alias_kind":"pith_short_8","alias_value":"SYMYC6AP","created_at":"2026-07-05T11:21:44.543497+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/SYMYC6APZDA5QLLDXCTK7O54GS","json":"https://pith.science/pith/SYMYC6APZDA5QLLDXCTK7O54GS.json","graph_json":"https://pith.science/api/pith-number/SYMYC6APZDA5QLLDXCTK7O54GS/graph.json","events_json":"https://pith.science/api/pith-number/SYMYC6APZDA5QLLDXCTK7O54GS/events.json","paper":"https://pith.science/paper/SYMYC6AP"},"agent_actions":{"view_html":"https://pith.science/pith/SYMYC6APZDA5QLLDXCTK7O54GS","download_json":"https://pith.science/pith/SYMYC6APZDA5QLLDXCTK7O54GS.json","view_paper":"https://pith.science/paper/SYMYC6AP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.17454&json=true","fetch_graph":"https://pith.science/api/pith-number/SYMYC6APZDA5QLLDXCTK7O54GS/graph.json","fetch_events":"https://pith.science/api/pith-number/SYMYC6APZDA5QLLDXCTK7O54GS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SYMYC6APZDA5QLLDXCTK7O54GS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SYMYC6APZDA5QLLDXCTK7O54GS/action/storage_attestation","attest_author":"https://pith.science/pith/SYMYC6APZDA5QLLDXCTK7O54GS/action/author_attestation","sign_citation":"https://pith.science/pith/SYMYC6APZDA5QLLDXCTK7O54GS/action/citation_signature","submit_replication":"https://pith.science/pith/SYMYC6APZDA5QLLDXCTK7O54GS/action/replication_record"}},"created_at":"2026-07-05T11:21:44.543497+00:00","updated_at":"2026-07-05T11:21:44.543497+00:00"}