{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:DUHPLOKQPVZJUJSOVXWP6GYB2F","short_pith_number":"pith:DUHPLOKQ","canonical_record":{"source":{"id":"2605.18246","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T11:41:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6b7f0490b0d8dd8067d7f2ae8d4a54987ef8f55402a61ecc5f968239b30e5d26","abstract_canon_sha256":"ced3e7416d03974d4e4f9161ca4e2a760654fc00081fa8226cd6198e95dc5438"},"schema_version":"1.0"},"canonical_sha256":"1d0ef5b9507d729a264eadecff1b01d1530eab155986d9ebab17bc29e18833f8","source":{"kind":"arxiv","id":"2605.18246","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:DUHPLOKQPVZJUJSOVXWP6GYB2F","target":"record","payload":{"canonical_record":{"source":{"id":"2605.18246","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T11:41:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6b7f0490b0d8dd8067d7f2ae8d4a54987ef8f55402a61ecc5f968239b30e5d26","abstract_canon_sha256":"ced3e7416d03974d4e4f9161ca4e2a760654fc00081fa8226cd6198e95dc5438"},"schema_version":"1.0"},"canonical_sha256":"1d0ef5b9507d729a264eadecff1b01d1530eab155986d9ebab17bc29e18833f8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:05:52.050503Z","signature_b64":"tIlcKs5M/RnkIuphtOWxC4Ka9vdcTzuCLlNFF9AWPqcGA9pcqtRwJifRPVFD9/jJn6jKK3o57nhfgRaafZjlAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1d0ef5b9507d729a264eadecff1b01d1530eab155986d9ebab17bc29e18833f8","last_reissued_at":"2026-05-20T00:05:52.049799Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:05:52.049799Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.18246","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:05:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vf/uiWmshaol7/5QDGf6wBz9hcPQM68i3rWVVKzKcrKZPmafP4Rw/BYvZ1WGGGjXcEyRPw5idAfHIHJ9wjQ+AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T17:20:06.300957Z"},"content_sha256":"9fbe8cae6ff8a7d8281cd592bc2f2a482bb93d2d7f891797e0f1512cd8e58c36","schema_version":"1.0","event_id":"sha256:9fbe8cae6ff8a7d8281cd592bc2f2a482bb93d2d7f891797e0f1512cd8e58c36"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:DUHPLOKQPVZJUJSOVXWP6GYB2F","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Privacy Preserving Reinforcement Learning with One-Sided Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Guangyan Gan, Hanzhang Qin, Lin William Cong, Zhenzhen Yan","submitted_at":"2026-05-18T11:41:03Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18246","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/2605.18246/integrity.json","findings":[],"available":true,"detectors_run":[{"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","findings_count":0}],"snapshot_sha256":"a79e8ffebe39c11338915dfe7cd063f5007fd9fd9e29e6d52a2f90160b168e6e"},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:05:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eaFXMX82qWZ0l8DLyDocVzsDjKZixLIrGnLc9Z6MO8OuaFKVlhnruZYlDE9rh+5UxscRefWq6AV6Vcc4h139Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T17:20:06.301754Z"},"content_sha256":"546ed796abe58d22fbd6a1e172d3b97c2923cc7eab926af6c0f259d21f872ba6","schema_version":"1.0","event_id":"sha256:546ed796abe58d22fbd6a1e172d3b97c2923cc7eab926af6c0f259d21f872ba6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DUHPLOKQPVZJUJSOVXWP6GYB2F/bundle.json","state_url":"https://pith.science/pith/DUHPLOKQPVZJUJSOVXWP6GYB2F/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DUHPLOKQPVZJUJSOVXWP6GYB2F/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-25T17:20:06Z","links":{"resolver":"https://pith.science/pith/DUHPLOKQPVZJUJSOVXWP6GYB2F","bundle":"https://pith.science/pith/DUHPLOKQPVZJUJSOVXWP6GYB2F/bundle.json","state":"https://pith.science/pith/DUHPLOKQPVZJUJSOVXWP6GYB2F/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DUHPLOKQPVZJUJSOVXWP6GYB2F/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lRjfV/8G3INyXVTbz4Wk48rZmYw1oZunODDgXdkJY+V9+NvwBWv+nG6rG9eOj2Tl12js3KBgciRPOs8MfH9GBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T17:20:06.305764Z","bundle_sha256":"54a613bb378483861642e53307a6eee7e07706c897d2f2fcb834b4a24a22cffb"}}