{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:WODYYPXKLKUAKJDTLMZBEAXYBI","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":"67968a392273b8a6dfef2b0c9932314dd717b7c8a7be344825899c4e950a6d62","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T07:28:42Z","title_canon_sha256":"8bcbd009113f3f1162750dafc999a699095566d24f1242c8c617dd822d16eb30"},"schema_version":"1.0","source":{"id":"2605.15692","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.15692","created_at":"2026-05-20T00:01:12Z"},{"alias_kind":"arxiv_version","alias_value":"2605.15692v1","created_at":"2026-05-20T00:01:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15692","created_at":"2026-05-20T00:01:12Z"},{"alias_kind":"pith_short_12","alias_value":"WODYYPXKLKUA","created_at":"2026-05-20T00:01:12Z"},{"alias_kind":"pith_short_16","alias_value":"WODYYPXKLKUAKJDT","created_at":"2026-05-20T00:01:12Z"},{"alias_kind":"pith_short_8","alias_value":"WODYYPXK","created_at":"2026-05-20T00:01:12Z"}],"graph_snapshots":[{"event_id":"sha256:77c3e85f700420420054fd87cc47b11d6313c3a819fd624398f9bc7c2ac211c6","target":"graph","created_at":"2026-05-20T00:01:12Z","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":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T19:33:29.221154Z","status":"skipped","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T17:21:56.040505Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.15692/integrity.json","findings":[],"snapshot_sha256":"397537cb4ea14e201d7918334958cab6f1c69000b1a5287131b12bf4c315acb5","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study episodic reinforcement learning with fixed reward and transition functions, but with episode-dependent admissible action sets that are observed at the start of each episode. Performance is measured by cumulative regret against the episode-wise optimal value, $\\sum_{k=1}^K [V^{*,M^k} - V^{\\pi^k,M^k}]$, where $M^k$ represents the action context in the $k$-th episode. We show that the MVP algorithm naturally extends to this framework and enjoys strong theoretical guarantees. In particular, we establish a minimax regret bound of $\\widetilde{O}(\\sqrt{SAH^3K\\log L})$ for adversarial context","authors_text":"Zihan Zhang, Zijun Chen","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T07:28:42Z","title":"Tighter Regret Bounds for Contextual Action-Set Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.15692","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:a1287c89c0e3b5af941ebfc2cc2256a75b2f055ea00c1d79e13df4be4736eff3","target":"record","created_at":"2026-05-20T00:01:12Z","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":"67968a392273b8a6dfef2b0c9932314dd717b7c8a7be344825899c4e950a6d62","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T07:28:42Z","title_canon_sha256":"8bcbd009113f3f1162750dafc999a699095566d24f1242c8c617dd822d16eb30"},"schema_version":"1.0","source":{"id":"2605.15692","kind":"arxiv","version":1}},"canonical_sha256":"b3878c3eea5aa80524735b321202f80a375dbd255d431262a37e44d2aeabb9e2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b3878c3eea5aa80524735b321202f80a375dbd255d431262a37e44d2aeabb9e2","first_computed_at":"2026-05-20T00:01:12.780011Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:01:12.780011Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HHiN31GB8fPIZTjmwSrpR4GxweFZ97MKs3RqoVZdulTKx+jmCqbVCB8c4ATVJ/I6E9GuD62lmwpHQBYfqAT/DA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:01:12.780856Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.15692","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a1287c89c0e3b5af941ebfc2cc2256a75b2f055ea00c1d79e13df4be4736eff3","sha256:77c3e85f700420420054fd87cc47b11d6313c3a819fd624398f9bc7c2ac211c6"],"state_sha256":"76687c31747ddd96d2a681f968eefb46fe6416704ba1d5bdaa1d674ce62f7981"}