{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GEZJ44UM7F53LNLWWK2L7TZ3GX","short_pith_number":"pith:GEZJ44UM","schema_version":"1.0","canonical_sha256":"31329e728cf97bb5b576b2b4bfcf3b35e58899bd7d93a110e231934e1346d807","source":{"kind":"arxiv","id":"2605.16103","version":1},"attestation_state":"computed","paper":{"title":"Sign-Separated Finite-Time Error Analysis of Q-Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Donghwan Lee","submitted_at":"2026-05-15T15:54:35Z","abstract_excerpt":"This paper develops a sign-separated finite-time error analysis for constant step-size Q-learning. Starting from the switching-system representation, the error is decomposed into its componentwise negative and positive parts. The negative part is dominated by a lower comparison linear time-invariant (LTI) system associated with a fixed optimal policy, whereas the positive part is controlled by a linear switching system. The resulting bounds show that the negative-side LTI certificate is no slower than the positive-side switching certificate and may produce a faster exponential envelope. The an"},"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":"2605.16103","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-15T15:54:35Z","cross_cats_sorted":[],"title_canon_sha256":"295637a8e804e23eb10fdcb9d3122b1e77e308952cb1450cb602c9832aa49011","abstract_canon_sha256":"d89934462fcc86e6e0a809207ae275ed74b48a1f081d6b6a54714b7a7d061e74"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:52.781012Z","signature_b64":"PM6s0vyX2y0dM4V/DsCd95EfA1OekwysWAtzJsb6mDPzhUd0J31KkN5HQF8boTxzQ9NkOvkMBM+re0lXMUgrBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31329e728cf97bb5b576b2b4bfcf3b35e58899bd7d93a110e231934e1346d807","last_reissued_at":"2026-05-20T00:01:52.780187Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:52.780187Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sign-Separated Finite-Time Error Analysis of Q-Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Donghwan Lee","submitted_at":"2026-05-15T15:54:35Z","abstract_excerpt":"This paper develops a sign-separated finite-time error analysis for constant step-size Q-learning. Starting from the switching-system representation, the error is decomposed into its componentwise negative and positive parts. The negative part is dominated by a lower comparison linear time-invariant (LTI) system associated with a fixed optimal policy, whereas the positive part is controlled by a linear switching system. The resulting bounds show that the negative-side LTI certificate is no slower than the positive-side switching certificate and may produce a faster exponential envelope. The an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.16103","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/2605.16103/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T17:33:38.072291Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T16:41:55.487085Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"3a4fd6c71d03f415d8c3919bcbfe8e7ee79b44b8c7caf8277af00bc8d05e2c49"},"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":"2605.16103","created_at":"2026-05-20T00:01:52.780338+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.16103v1","created_at":"2026-05-20T00:01:52.780338+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16103","created_at":"2026-05-20T00:01:52.780338+00:00"},{"alias_kind":"pith_short_12","alias_value":"GEZJ44UM7F53","created_at":"2026-05-20T00:01:52.780338+00:00"},{"alias_kind":"pith_short_16","alias_value":"GEZJ44UM7F53LNLW","created_at":"2026-05-20T00:01:52.780338+00:00"},{"alias_kind":"pith_short_8","alias_value":"GEZJ44UM","created_at":"2026-05-20T00:01:52.780338+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/GEZJ44UM7F53LNLWWK2L7TZ3GX","json":"https://pith.science/pith/GEZJ44UM7F53LNLWWK2L7TZ3GX.json","graph_json":"https://pith.science/api/pith-number/GEZJ44UM7F53LNLWWK2L7TZ3GX/graph.json","events_json":"https://pith.science/api/pith-number/GEZJ44UM7F53LNLWWK2L7TZ3GX/events.json","paper":"https://pith.science/paper/GEZJ44UM"},"agent_actions":{"view_html":"https://pith.science/pith/GEZJ44UM7F53LNLWWK2L7TZ3GX","download_json":"https://pith.science/pith/GEZJ44UM7F53LNLWWK2L7TZ3GX.json","view_paper":"https://pith.science/paper/GEZJ44UM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.16103&json=true","fetch_graph":"https://pith.science/api/pith-number/GEZJ44UM7F53LNLWWK2L7TZ3GX/graph.json","fetch_events":"https://pith.science/api/pith-number/GEZJ44UM7F53LNLWWK2L7TZ3GX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GEZJ44UM7F53LNLWWK2L7TZ3GX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GEZJ44UM7F53LNLWWK2L7TZ3GX/action/storage_attestation","attest_author":"https://pith.science/pith/GEZJ44UM7F53LNLWWK2L7TZ3GX/action/author_attestation","sign_citation":"https://pith.science/pith/GEZJ44UM7F53LNLWWK2L7TZ3GX/action/citation_signature","submit_replication":"https://pith.science/pith/GEZJ44UM7F53LNLWWK2L7TZ3GX/action/replication_record"}},"created_at":"2026-05-20T00:01:52.780338+00:00","updated_at":"2026-05-20T00:01:52.780338+00:00"}