{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:O74PBKHIOGD2T326RR36D6GBKR","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"8a4975de91f0238b0baba7bdfe6b0a0c9d7759ac83e22aaca3d78d6b56c45201","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-05-31T15:46:20Z","title_canon_sha256":"65b8cc9dcd1ee86b3c169a25322b89bf6fc6aba8f2ad51b112a2d7eee0316c2f"},"schema_version":"1.0","source":{"id":"2606.02645","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.02645","created_at":"2026-06-03T00:05:05Z"},{"alias_kind":"arxiv_version","alias_value":"2606.02645v1","created_at":"2026-06-03T00:05:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.02645","created_at":"2026-06-03T00:05:05Z"},{"alias_kind":"pith_short_12","alias_value":"O74PBKHIOGD2","created_at":"2026-06-03T00:05:05Z"},{"alias_kind":"pith_short_16","alias_value":"O74PBKHIOGD2T326","created_at":"2026-06-03T00:05:05Z"},{"alias_kind":"pith_short_8","alias_value":"O74PBKHI","created_at":"2026-06-03T00:05:05Z"}],"graph_snapshots":[{"event_id":"sha256:3ddf3a09dd28e13b8f00c1adf55045047cc3c13995417453bdbf45e6f3c4f3a1","target":"graph","created_at":"2026-06-03T00:05:05Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2606.02645/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Periodic target updates in Q-learning and soft target updates in actor-critic methods are empirically well established stabilization mechanisms, but their precise theoretical explanation is still incomplete. This paper gives a rigorous and exact analysis of these mechanisms for Q-learning with linear function approximation (linear Q-learning) using the exact switched linear system (SLS) dynamics induced by the Bellman maximum and the joint spectral radius (JSR) of the resulting switching matrix families. Although linear Q-learning can fail to converge in general, we prove that, under explicit ","authors_text":"Donghwan Lee","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-05-31T15:46:20Z","title":"Target Updates May Stabilize Linear Q-Learning: Periodic and Soft Dynamics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.02645","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6c51e59b05dd846d696e3f2757d3572d8d8806fe2c491dacccafca07fa80685c","target":"record","created_at":"2026-06-03T00:05:05Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"8a4975de91f0238b0baba7bdfe6b0a0c9d7759ac83e22aaca3d78d6b56c45201","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2026-05-31T15:46:20Z","title_canon_sha256":"65b8cc9dcd1ee86b3c169a25322b89bf6fc6aba8f2ad51b112a2d7eee0316c2f"},"schema_version":"1.0","source":{"id":"2606.02645","kind":"arxiv","version":1}},"canonical_sha256":"77f8f0a8e87187a9ef5e8c77e1f8c1547b5abfe26f675e5d5b68db4b420dd529","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"77f8f0a8e87187a9ef5e8c77e1f8c1547b5abfe26f675e5d5b68db4b420dd529","first_computed_at":"2026-06-03T00:05:05.514596Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T00:05:05.514596Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4mY6+scY7utW70Ol3r417QV+wi++q3zSGrct/Vl370dvISr5w6sOIIE6LtDN5h6HHCpNBQHG3hkdX8rM9HH2Dg==","signature_status":"signed_v1","signed_at":"2026-06-03T00:05:05.514982Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.02645","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6c51e59b05dd846d696e3f2757d3572d8d8806fe2c491dacccafca07fa80685c","sha256:3ddf3a09dd28e13b8f00c1adf55045047cc3c13995417453bdbf45e6f3c4f3a1"],"state_sha256":"b86d88923fff45cfd430b7107162ac458d67a3181ee1a55f308772bc544a7439"}