{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DUHPLOKQPVZJUJSOVXWP6GYB2F","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":"ced3e7416d03974d4e4f9161ca4e2a760654fc00081fa8226cd6198e95dc5438","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T11:41:03Z","title_canon_sha256":"6b7f0490b0d8dd8067d7f2ae8d4a54987ef8f55402a61ecc5f968239b30e5d26"},"schema_version":"1.0","source":{"id":"2605.18246","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.18246","created_at":"2026-05-20T00:05:52Z"},{"alias_kind":"arxiv_version","alias_value":"2605.18246v1","created_at":"2026-05-20T00:05:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18246","created_at":"2026-05-20T00:05:52Z"},{"alias_kind":"pith_short_12","alias_value":"DUHPLOKQPVZJ","created_at":"2026-05-20T00:05:52Z"},{"alias_kind":"pith_short_16","alias_value":"DUHPLOKQPVZJUJSO","created_at":"2026-05-20T00:05:52Z"},{"alias_kind":"pith_short_8","alias_value":"DUHPLOKQ","created_at":"2026-05-20T00:05:52Z"}],"graph_snapshots":[{"event_id":"sha256:546ed796abe58d22fbd6a1e172d3b97c2923cc7eab926af6c0f259d21f872ba6","target":"graph","created_at":"2026-05-20T00:05:52Z","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":"2026-05-19T23:33:35.274075Z","status":"skipped","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T23:21:59.005279Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.18246/integrity.json","findings":[],"snapshot_sha256":"a79e8ffebe39c11338915dfe7cd063f5007fd9fd9e29e6d52a2f90160b168e6e","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study reinforcement learning (RL) in multi-dimensional continuous state and action spaces with one-sided feedback, where the agent receives partial observations of the state and obtains reward information for only a subset of the state-action space at each time step. This setting introduces substantial challenges in both learning efficiency and privacy preservation. To address these challenges, we propose POOL, a novel privacy-preserving RL algorithm. We conduct a comprehensive theoretical analysis of POOL, deriving a sample complexity bound that matches the known lower bounds for non-priva","authors_text":"Guangyan Gan, Hanzhang Qin, Lin William Cong, Zhenzhen Yan","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T11:41:03Z","title":"Privacy Preserving Reinforcement Learning with One-Sided Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18246","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":"sha256:9fbe8cae6ff8a7d8281cd592bc2f2a482bb93d2d7f891797e0f1512cd8e58c36","target":"record","created_at":"2026-05-20T00:05:52Z","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":"ced3e7416d03974d4e4f9161ca4e2a760654fc00081fa8226cd6198e95dc5438","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T11:41:03Z","title_canon_sha256":"6b7f0490b0d8dd8067d7f2ae8d4a54987ef8f55402a61ecc5f968239b30e5d26"},"schema_version":"1.0","source":{"id":"2605.18246","kind":"arxiv","version":1}},"canonical_sha256":"1d0ef5b9507d729a264eadecff1b01d1530eab155986d9ebab17bc29e18833f8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1d0ef5b9507d729a264eadecff1b01d1530eab155986d9ebab17bc29e18833f8","first_computed_at":"2026-05-20T00:05:52.049799Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:05:52.049799Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tIlcKs5M/RnkIuphtOWxC4Ka9vdcTzuCLlNFF9AWPqcGA9pcqtRwJifRPVFD9/jJn6jKK3o57nhfgRaafZjlAQ==","signature_status":"signed_v1","signed_at":"2026-05-20T00:05:52.050503Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.18246","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9fbe8cae6ff8a7d8281cd592bc2f2a482bb93d2d7f891797e0f1512cd8e58c36","sha256:546ed796abe58d22fbd6a1e172d3b97c2923cc7eab926af6c0f259d21f872ba6"],"state_sha256":"4db2fe47865187d5dc08991d8a1cbc48fcfac009136596bf8bf1fe70391ab5f9"}