{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QHRP72LPNXWKPBNO4CRRLU74DO","short_pith_number":"pith:QHRP72LP","schema_version":"1.0","canonical_sha256":"81e2ffe96f6deca785aee0a315d3fc1ba809bbc10637bb0b62757255d56ca6a4","source":{"kind":"arxiv","id":"2605.26286","version":1},"attestation_state":"computed","paper":{"title":"Decoupled Delay Compensation: Enhancing Pre-trained MARL Policies via Learned Dynamics Filtering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.MA","authors_text":"Maxim Mednikov, Oren Gal","submitted_at":"2026-05-25T19:19:46Z","abstract_excerpt":"Real-world multi-agent reinforcement learning (MARL) systems must often operate under stale observations, stochastic communication delays, and intermittent packet loss. Policies trained under idealized synchronous conditions frequently exhibit significant performance degradation in these regimes because they act on outdated feedback. We propose a modular execution-stage state-estimation layer that replaces delayed communicated observations with current belief-state estimates. The framework integrates a learned Gated transition model with a recursive Kalman filtering layer to estimate instantan"},"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":"2605.26286","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2026-05-25T19:19:46Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"26002591c86dbc2289cfc64266512e577e79341dede2f40137488ba58f55abf6","abstract_canon_sha256":"785c3945b42c7bcd1442e573b15f97454f51d55476943017df7c4a874b41ebce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:05:10.179527Z","signature_b64":"BUGXnoAsH98sIVk2tGelIeVlIzzXPX+tHXc8ESdhX1oGCOXYTHA7ZqATH6KKKbrQqxfchIIVFfnGTY9+jSiJAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81e2ffe96f6deca785aee0a315d3fc1ba809bbc10637bb0b62757255d56ca6a4","last_reissued_at":"2026-05-27T01:05:10.178809Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:05:10.178809Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Decoupled Delay Compensation: Enhancing Pre-trained MARL Policies via Learned Dynamics Filtering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.MA","authors_text":"Maxim Mednikov, Oren Gal","submitted_at":"2026-05-25T19:19:46Z","abstract_excerpt":"Real-world multi-agent reinforcement learning (MARL) systems must often operate under stale observations, stochastic communication delays, and intermittent packet loss. Policies trained under idealized synchronous conditions frequently exhibit significant performance degradation in these regimes because they act on outdated feedback. We propose a modular execution-stage state-estimation layer that replaces delayed communicated observations with current belief-state estimates. The framework integrates a learned Gated transition model with a recursive Kalman filtering layer to estimate instantan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26286","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/2605.26286/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":"2605.26286","created_at":"2026-05-27T01:05:10.178907+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.26286v1","created_at":"2026-05-27T01:05:10.178907+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26286","created_at":"2026-05-27T01:05:10.178907+00:00"},{"alias_kind":"pith_short_12","alias_value":"QHRP72LPNXWK","created_at":"2026-05-27T01:05:10.178907+00:00"},{"alias_kind":"pith_short_16","alias_value":"QHRP72LPNXWKPBNO","created_at":"2026-05-27T01:05:10.178907+00:00"},{"alias_kind":"pith_short_8","alias_value":"QHRP72LP","created_at":"2026-05-27T01:05:10.178907+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/QHRP72LPNXWKPBNO4CRRLU74DO","json":"https://pith.science/pith/QHRP72LPNXWKPBNO4CRRLU74DO.json","graph_json":"https://pith.science/api/pith-number/QHRP72LPNXWKPBNO4CRRLU74DO/graph.json","events_json":"https://pith.science/api/pith-number/QHRP72LPNXWKPBNO4CRRLU74DO/events.json","paper":"https://pith.science/paper/QHRP72LP"},"agent_actions":{"view_html":"https://pith.science/pith/QHRP72LPNXWKPBNO4CRRLU74DO","download_json":"https://pith.science/pith/QHRP72LPNXWKPBNO4CRRLU74DO.json","view_paper":"https://pith.science/paper/QHRP72LP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.26286&json=true","fetch_graph":"https://pith.science/api/pith-number/QHRP72LPNXWKPBNO4CRRLU74DO/graph.json","fetch_events":"https://pith.science/api/pith-number/QHRP72LPNXWKPBNO4CRRLU74DO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QHRP72LPNXWKPBNO4CRRLU74DO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QHRP72LPNXWKPBNO4CRRLU74DO/action/storage_attestation","attest_author":"https://pith.science/pith/QHRP72LPNXWKPBNO4CRRLU74DO/action/author_attestation","sign_citation":"https://pith.science/pith/QHRP72LPNXWKPBNO4CRRLU74DO/action/citation_signature","submit_replication":"https://pith.science/pith/QHRP72LPNXWKPBNO4CRRLU74DO/action/replication_record"}},"created_at":"2026-05-27T01:05:10.178907+00:00","updated_at":"2026-05-27T01:05:10.178907+00:00"}