{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:C2M7M5UIMASORZ2PUTQO7P3VSQ","short_pith_number":"pith:C2M7M5UI","canonical_record":{"source":{"id":"2606.08032","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-06-06T07:50:50Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f5665f86f57152d4171b9ac2865a18ab0f86f0f36c97ed9b2cbb59bf2f384292","abstract_canon_sha256":"94b729b57dd22f4dd6546a3255d3522e5fe998360947b5fd209a7750b8907305"},"schema_version":"1.0"},"canonical_sha256":"1699f676886024e8e74fa4e0efbf7594288a3d17325f6950fac1b079355d7d7b","source":{"kind":"arxiv","id":"2606.08032","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.08032","created_at":"2026-06-09T01:05:23Z"},{"alias_kind":"arxiv_version","alias_value":"2606.08032v1","created_at":"2026-06-09T01:05:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08032","created_at":"2026-06-09T01:05:23Z"},{"alias_kind":"pith_short_12","alias_value":"C2M7M5UIMASO","created_at":"2026-06-09T01:05:23Z"},{"alias_kind":"pith_short_16","alias_value":"C2M7M5UIMASORZ2P","created_at":"2026-06-09T01:05:23Z"},{"alias_kind":"pith_short_8","alias_value":"C2M7M5UI","created_at":"2026-06-09T01:05:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:C2M7M5UIMASORZ2PUTQO7P3VSQ","target":"record","payload":{"canonical_record":{"source":{"id":"2606.08032","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-06-06T07:50:50Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f5665f86f57152d4171b9ac2865a18ab0f86f0f36c97ed9b2cbb59bf2f384292","abstract_canon_sha256":"94b729b57dd22f4dd6546a3255d3522e5fe998360947b5fd209a7750b8907305"},"schema_version":"1.0"},"canonical_sha256":"1699f676886024e8e74fa4e0efbf7594288a3d17325f6950fac1b079355d7d7b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:05:23.660264Z","signature_b64":"mjBdS8bd43wTH65p7hsEI8+ZGPK0NdPA3ZNdFq8FPzj/i9Ayt8rbf46zc2hPwi+YrP543CWE0NhNaYHeFo18DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1699f676886024e8e74fa4e0efbf7594288a3d17325f6950fac1b079355d7d7b","last_reissued_at":"2026-06-09T01:05:23.659685Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:05:23.659685Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.08032","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":"2026-06-09T01:05:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0viVIovNXWKLE3Tv0CKMiqQClYQZ4zXZ8E3rYQqzP8tBE5jz777c3/0+2hSNbhgsSx9EFPakkoxEqcin0Ik4DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T15:22:27.381777Z"},"content_sha256":"bcbc5c8e09bb66c695f247ee6c88006019cfcaa0b24221ce83e30c143598a3ad","schema_version":"1.0","event_id":"sha256:bcbc5c8e09bb66c695f247ee6c88006019cfcaa0b24221ce83e30c143598a3ad"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:C2M7M5UIMASORZ2PUTQO7P3VSQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Variational Proximal Policy Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Ousmane Amadou Dia","submitted_at":"2026-06-06T07:50:50Z","abstract_excerpt":"Reinforcement Learning from Human Feedback via Proximal Policy Optimization often suffers from policy mode collapse, brittle exploration loops, and distribution drift. This paper introduces Variational Proximal Policy Optimization (\\(\\textsc{VP}_2\\textsc{O}\\)), a particle-based variational inference framework that maps policy optimization to Stein Variational Gradient Descent within a Mixture-of-Experts architecture. By leveraging functional kernels over localized expert prototypes alongside an expert orthogonalization loss, \\(\\textsc{VP}_2\\textsc{O}\\) introduces a geometry-based proximal-cont"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08032","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/2606.08032/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-06-09T01:05:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MlzhHcXIiOo1JQsF1LTWpAgueRvId5B0INuPTPvyoof3FSSVUScs9k/18I46Nzt3xw7p21m7CrsI8VCX7yU6Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T15:22:27.382142Z"},"content_sha256":"a2c5322cb1583a0e134a5f2ced5c14c0ac1044f8cedee01bc991db8fcf1ffc1b","schema_version":"1.0","event_id":"sha256:a2c5322cb1583a0e134a5f2ced5c14c0ac1044f8cedee01bc991db8fcf1ffc1b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/C2M7M5UIMASORZ2PUTQO7P3VSQ/bundle.json","state_url":"https://pith.science/pith/C2M7M5UIMASORZ2PUTQO7P3VSQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/C2M7M5UIMASORZ2PUTQO7P3VSQ/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":"2026-06-28T15:22:27Z","links":{"resolver":"https://pith.science/pith/C2M7M5UIMASORZ2PUTQO7P3VSQ","bundle":"https://pith.science/pith/C2M7M5UIMASORZ2PUTQO7P3VSQ/bundle.json","state":"https://pith.science/pith/C2M7M5UIMASORZ2PUTQO7P3VSQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/C2M7M5UIMASORZ2PUTQO7P3VSQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:C2M7M5UIMASORZ2PUTQO7P3VSQ","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":"94b729b57dd22f4dd6546a3255d3522e5fe998360947b5fd209a7750b8907305","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-06-06T07:50:50Z","title_canon_sha256":"f5665f86f57152d4171b9ac2865a18ab0f86f0f36c97ed9b2cbb59bf2f384292"},"schema_version":"1.0","source":{"id":"2606.08032","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.08032","created_at":"2026-06-09T01:05:23Z"},{"alias_kind":"arxiv_version","alias_value":"2606.08032v1","created_at":"2026-06-09T01:05:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08032","created_at":"2026-06-09T01:05:23Z"},{"alias_kind":"pith_short_12","alias_value":"C2M7M5UIMASO","created_at":"2026-06-09T01:05:23Z"},{"alias_kind":"pith_short_16","alias_value":"C2M7M5UIMASORZ2P","created_at":"2026-06-09T01:05:23Z"},{"alias_kind":"pith_short_8","alias_value":"C2M7M5UI","created_at":"2026-06-09T01:05:23Z"}],"graph_snapshots":[{"event_id":"sha256:a2c5322cb1583a0e134a5f2ced5c14c0ac1044f8cedee01bc991db8fcf1ffc1b","target":"graph","created_at":"2026-06-09T01:05:23Z","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/2606.08032/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning from Human Feedback via Proximal Policy Optimization often suffers from policy mode collapse, brittle exploration loops, and distribution drift. This paper introduces Variational Proximal Policy Optimization (\\(\\textsc{VP}_2\\textsc{O}\\)), a particle-based variational inference framework that maps policy optimization to Stein Variational Gradient Descent within a Mixture-of-Experts architecture. By leveraging functional kernels over localized expert prototypes alongside an expert orthogonalization loss, \\(\\textsc{VP}_2\\textsc{O}\\) introduces a geometry-based proximal-cont","authors_text":"Ousmane Amadou Dia","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-06-06T07:50:50Z","title":"Variational Proximal Policy Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08032","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:bcbc5c8e09bb66c695f247ee6c88006019cfcaa0b24221ce83e30c143598a3ad","target":"record","created_at":"2026-06-09T01:05:23Z","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":"94b729b57dd22f4dd6546a3255d3522e5fe998360947b5fd209a7750b8907305","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-06-06T07:50:50Z","title_canon_sha256":"f5665f86f57152d4171b9ac2865a18ab0f86f0f36c97ed9b2cbb59bf2f384292"},"schema_version":"1.0","source":{"id":"2606.08032","kind":"arxiv","version":1}},"canonical_sha256":"1699f676886024e8e74fa4e0efbf7594288a3d17325f6950fac1b079355d7d7b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1699f676886024e8e74fa4e0efbf7594288a3d17325f6950fac1b079355d7d7b","first_computed_at":"2026-06-09T01:05:23.659685Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T01:05:23.659685Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mjBdS8bd43wTH65p7hsEI8+ZGPK0NdPA3ZNdFq8FPzj/i9Ayt8rbf46zc2hPwi+YrP543CWE0NhNaYHeFo18DQ==","signature_status":"signed_v1","signed_at":"2026-06-09T01:05:23.660264Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.08032","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bcbc5c8e09bb66c695f247ee6c88006019cfcaa0b24221ce83e30c143598a3ad","sha256:a2c5322cb1583a0e134a5f2ced5c14c0ac1044f8cedee01bc991db8fcf1ffc1b"],"state_sha256":"863e7ff43700b5f8bc3fb541f2ff1d6650c494e6c044d188995d94120dc16bc6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yn2Bb8MeoRb7v4IqTZ7Tmx9ieYW6lZWObAOXMr6WIgrWHHWq7sA5bbjtUE22j9fJ0A6P/PZ5ZEFgJgqbNH66Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T15:22:27.384085Z","bundle_sha256":"7f6a85e94e13bd0e89f5592913da70cef89646bae119d6d4e47e7b4f50094894"}}