{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:MFOONFVY7QFYYIKYWXW45FMSAD","short_pith_number":"pith:MFOONFVY","canonical_record":{"source":{"id":"2501.19080","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-31T12:11:13Z","cross_cats_sorted":[],"title_canon_sha256":"ac8a5964292268603f30fd35e372679d5bb3d0f1a998f49c0c48d8a8a9b98657","abstract_canon_sha256":"1fe54e3aa719e004e957e8f6a9f05f5801343e81006c0d6d7ee23ba5f983c89a"},"schema_version":"1.0"},"canonical_sha256":"615ce696b8fc0b8c2158b5edce959200e38db1113129f097e5c20abbd6686b18","source":{"kind":"arxiv","id":"2501.19080","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.19080","created_at":"2026-07-05T10:07:55Z"},{"alias_kind":"arxiv_version","alias_value":"2501.19080v1","created_at":"2026-07-05T10:07:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.19080","created_at":"2026-07-05T10:07:55Z"},{"alias_kind":"pith_short_12","alias_value":"MFOONFVY7QFY","created_at":"2026-07-05T10:07:55Z"},{"alias_kind":"pith_short_16","alias_value":"MFOONFVY7QFYYIKY","created_at":"2026-07-05T10:07:55Z"},{"alias_kind":"pith_short_8","alias_value":"MFOONFVY","created_at":"2026-07-05T10:07:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:MFOONFVY7QFYYIKYWXW45FMSAD","target":"record","payload":{"canonical_record":{"source":{"id":"2501.19080","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-31T12:11:13Z","cross_cats_sorted":[],"title_canon_sha256":"ac8a5964292268603f30fd35e372679d5bb3d0f1a998f49c0c48d8a8a9b98657","abstract_canon_sha256":"1fe54e3aa719e004e957e8f6a9f05f5801343e81006c0d6d7ee23ba5f983c89a"},"schema_version":"1.0"},"canonical_sha256":"615ce696b8fc0b8c2158b5edce959200e38db1113129f097e5c20abbd6686b18","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:07:55.784121Z","signature_b64":"PSSD7VWTPWkpj/c4+Ri7Pj2QtTAE1idcFuMa8ns4W1Bwjp79f4e9J91F1EIFy1n5jJQlj2ViHa8rPtTeH5U+BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"615ce696b8fc0b8c2158b5edce959200e38db1113129f097e5c20abbd6686b18","last_reissued_at":"2026-07-05T10:07:55.783619Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:07:55.783619Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.19080","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":"2026-07-05T10:07:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rCzieu4kdgMwH1pHeYAbHMifqVKgM2KJT/wEhUsrgCPwO7487iqAGtXG38SWy1cM9vhHkpJIP/rcSLLe9o9AAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T09:25:56.774960Z"},"content_sha256":"d24e5667a4cba577c47d6d51a51058db9951786e52a2710efaaeabde1f300e92","schema_version":"1.0","event_id":"sha256:d24e5667a4cba577c47d6d51a51058db9951786e52a2710efaaeabde1f300e92"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:MFOONFVY7QFYYIKYWXW45FMSAD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Differentially Private Policy Gradient","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexandre Rio, Igor Colin, Merwan Barlier","submitted_at":"2025-01-31T12:11:13Z","abstract_excerpt":"Motivated by the increasing deployment of reinforcement learning in the real world, involving a large consumption of personal data, we introduce a differentially private (DP) policy gradient algorithm. We show that, in this setting, the introduction of Differential Privacy can be reduced to the computation of appropriate trust regions, thus avoiding the sacrifice of theoretical properties of the DP-less methods. Therefore, we show that it is possible to find the right trade-off between privacy noise and trust-region size to obtain a performant differentially private policy gradient algorithm. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.19080","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/2501.19080/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":"2026-07-05T10:07:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yWPNUtHVNbd1MQekletMMhPcSVp/eVJiEy6IXoTk44VKo1z2BScjHbNfr4tY6YpSSDzAJf5VJkRquyDemNEDBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T09:25:56.776203Z"},"content_sha256":"30469c988f231c2ce7d9474c639361538d7a4ed7cdf1a6f027713bb301dc25b3","schema_version":"1.0","event_id":"sha256:30469c988f231c2ce7d9474c639361538d7a4ed7cdf1a6f027713bb301dc25b3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MFOONFVY7QFYYIKYWXW45FMSAD/bundle.json","state_url":"https://pith.science/pith/MFOONFVY7QFYYIKYWXW45FMSAD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MFOONFVY7QFYYIKYWXW45FMSAD/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":"2026-08-10T09:25:56Z","links":{"resolver":"https://pith.science/pith/MFOONFVY7QFYYIKYWXW45FMSAD","bundle":"https://pith.science/pith/MFOONFVY7QFYYIKYWXW45FMSAD/bundle.json","state":"https://pith.science/pith/MFOONFVY7QFYYIKYWXW45FMSAD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MFOONFVY7QFYYIKYWXW45FMSAD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MFOONFVY7QFYYIKYWXW45FMSAD","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":"1fe54e3aa719e004e957e8f6a9f05f5801343e81006c0d6d7ee23ba5f983c89a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-31T12:11:13Z","title_canon_sha256":"ac8a5964292268603f30fd35e372679d5bb3d0f1a998f49c0c48d8a8a9b98657"},"schema_version":"1.0","source":{"id":"2501.19080","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.19080","created_at":"2026-07-05T10:07:55Z"},{"alias_kind":"arxiv_version","alias_value":"2501.19080v1","created_at":"2026-07-05T10:07:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.19080","created_at":"2026-07-05T10:07:55Z"},{"alias_kind":"pith_short_12","alias_value":"MFOONFVY7QFY","created_at":"2026-07-05T10:07:55Z"},{"alias_kind":"pith_short_16","alias_value":"MFOONFVY7QFYYIKY","created_at":"2026-07-05T10:07:55Z"},{"alias_kind":"pith_short_8","alias_value":"MFOONFVY","created_at":"2026-07-05T10:07:55Z"}],"graph_snapshots":[{"event_id":"sha256:30469c988f231c2ce7d9474c639361538d7a4ed7cdf1a6f027713bb301dc25b3","target":"graph","created_at":"2026-07-05T10:07:55Z","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/2501.19080/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Motivated by the increasing deployment of reinforcement learning in the real world, involving a large consumption of personal data, we introduce a differentially private (DP) policy gradient algorithm. We show that, in this setting, the introduction of Differential Privacy can be reduced to the computation of appropriate trust regions, thus avoiding the sacrifice of theoretical properties of the DP-less methods. Therefore, we show that it is possible to find the right trade-off between privacy noise and trust-region size to obtain a performant differentially private policy gradient algorithm. ","authors_text":"Alexandre Rio, Igor Colin, Merwan Barlier","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-31T12:11:13Z","title":"Differentially Private Policy Gradient"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.19080","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:d24e5667a4cba577c47d6d51a51058db9951786e52a2710efaaeabde1f300e92","target":"record","created_at":"2026-07-05T10:07:55Z","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":"1fe54e3aa719e004e957e8f6a9f05f5801343e81006c0d6d7ee23ba5f983c89a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-31T12:11:13Z","title_canon_sha256":"ac8a5964292268603f30fd35e372679d5bb3d0f1a998f49c0c48d8a8a9b98657"},"schema_version":"1.0","source":{"id":"2501.19080","kind":"arxiv","version":1}},"canonical_sha256":"615ce696b8fc0b8c2158b5edce959200e38db1113129f097e5c20abbd6686b18","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"615ce696b8fc0b8c2158b5edce959200e38db1113129f097e5c20abbd6686b18","first_computed_at":"2026-07-05T10:07:55.783619Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:07:55.783619Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PSSD7VWTPWkpj/c4+Ri7Pj2QtTAE1idcFuMa8ns4W1Bwjp79f4e9J91F1EIFy1n5jJQlj2ViHa8rPtTeH5U+BA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:07:55.784121Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.19080","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d24e5667a4cba577c47d6d51a51058db9951786e52a2710efaaeabde1f300e92","sha256:30469c988f231c2ce7d9474c639361538d7a4ed7cdf1a6f027713bb301dc25b3"],"state_sha256":"85337c1f31403bcee4c8dc5f9705cadc3c0186b274fbc7c455edd7e262573731"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YJl2KIq0hnYAalqTQ128lA9Xqh8WYdiIVenhHI5RlptMWFNDyg5pGtFfRSvFhNAzihhNNK8D8WdNpbbaTALnDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T09:25:56.785440Z","bundle_sha256":"c73fb5c5fe4020666fdb0ca3b37d02a2be215e63e2522e4a0d851b8424ce20ad"}}