{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:CDP452J7K3BKJIP5HBHOSMULI4","short_pith_number":"pith:CDP452J7","canonical_record":{"source":{"id":"2606.04182","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T19:54:44Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"89eff89bbe86c69e58823bcd21241973d1758365bc07624f4a9f7693dc62a3d5","abstract_canon_sha256":"0a9226249b814814f745b83c1df417feb88cdc814471a05737fb234400dc606b"},"schema_version":"1.0"},"canonical_sha256":"10dfcee93f56c2a4a1fd384ee9328b471b773ba11b0c41f96a3b6be6bac9c13f","source":{"kind":"arxiv","id":"2606.04182","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.04182","created_at":"2026-06-04T01:08:19Z"},{"alias_kind":"arxiv_version","alias_value":"2606.04182v1","created_at":"2026-06-04T01:08:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04182","created_at":"2026-06-04T01:08:19Z"},{"alias_kind":"pith_short_12","alias_value":"CDP452J7K3BK","created_at":"2026-06-04T01:08:19Z"},{"alias_kind":"pith_short_16","alias_value":"CDP452J7K3BKJIP5","created_at":"2026-06-04T01:08:19Z"},{"alias_kind":"pith_short_8","alias_value":"CDP452J7","created_at":"2026-06-04T01:08:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:CDP452J7K3BKJIP5HBHOSMULI4","target":"record","payload":{"canonical_record":{"source":{"id":"2606.04182","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T19:54:44Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"89eff89bbe86c69e58823bcd21241973d1758365bc07624f4a9f7693dc62a3d5","abstract_canon_sha256":"0a9226249b814814f745b83c1df417feb88cdc814471a05737fb234400dc606b"},"schema_version":"1.0"},"canonical_sha256":"10dfcee93f56c2a4a1fd384ee9328b471b773ba11b0c41f96a3b6be6bac9c13f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:08:19.279792Z","signature_b64":"S4DDTOz71ofoqBQj4XOIdhrR3oFCRvlm6vScGiJv6yqEHJNDLeX9tzXUYJohHJD2PHgzLe2GThc+SriMrcM2AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"10dfcee93f56c2a4a1fd384ee9328b471b773ba11b0c41f96a3b6be6bac9c13f","last_reissued_at":"2026-06-04T01:08:19.279095Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:08:19.279095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.04182","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":"2026-06-04T01:08:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ykiw1xgYAP1OCzQIaI/A8Zb9G2vFo06JicH1y9u/iZqxnIoWgKuETMAubl+8ZmsE9m48VQHBxf9PXd/nIlEzDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T08:08:56.428330Z"},"content_sha256":"088d9cdd0f65d7c94d3db7e4e6deb09b4b6529ce5322e32015b9319ef59ef294","schema_version":"1.0","event_id":"sha256:088d9cdd0f65d7c94d3db7e4e6deb09b4b6529ce5322e32015b9319ef59ef294"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:CDP452J7K3BKJIP5HBHOSMULI4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Exact Unlearning in Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Raman Arora, Thanh Nguyen-Tang","submitted_at":"2026-06-02T19:54:44Z","abstract_excerpt":"We formulate the problem of \\emph{exact unlearning} in reinforcement learning, where the goal is to design an efficient framework that enables the removal of any user's data upon deletion request, i.e., the online learner's output after unlearning is \\emph{indistinguishable} from what would have been produced had the deleted user never interacted with the learner. For any $\\rho >0$, we show that there exists a reinforcement learning (RL) algorithm that is $\\rho$-TV-stable and supports an exact unlearning procedure whose expected computational cost is only a $\\rho \\sqrt{\\ln T}$ fraction of the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04182","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/2606.04182/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":"2026-06-04T01:08:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VD5K/pyo134++RpgNEalKLfXlKtvfLEhNi3r26yexQZGrqBL6IPb84BPOuhyTdZv3ltbY3M0mHtvEojwoHfHCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T08:08:56.428716Z"},"content_sha256":"49c6cc34d6e2e7411d6fb7b6e1d28344c556206d460e89b16f862c34f9138a22","schema_version":"1.0","event_id":"sha256:49c6cc34d6e2e7411d6fb7b6e1d28344c556206d460e89b16f862c34f9138a22"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CDP452J7K3BKJIP5HBHOSMULI4/bundle.json","state_url":"https://pith.science/pith/CDP452J7K3BKJIP5HBHOSMULI4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CDP452J7K3BKJIP5HBHOSMULI4/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":"2026-06-29T08:08:56Z","links":{"resolver":"https://pith.science/pith/CDP452J7K3BKJIP5HBHOSMULI4","bundle":"https://pith.science/pith/CDP452J7K3BKJIP5HBHOSMULI4/bundle.json","state":"https://pith.science/pith/CDP452J7K3BKJIP5HBHOSMULI4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CDP452J7K3BKJIP5HBHOSMULI4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CDP452J7K3BKJIP5HBHOSMULI4","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":"0a9226249b814814f745b83c1df417feb88cdc814471a05737fb234400dc606b","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T19:54:44Z","title_canon_sha256":"89eff89bbe86c69e58823bcd21241973d1758365bc07624f4a9f7693dc62a3d5"},"schema_version":"1.0","source":{"id":"2606.04182","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.04182","created_at":"2026-06-04T01:08:19Z"},{"alias_kind":"arxiv_version","alias_value":"2606.04182v1","created_at":"2026-06-04T01:08:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04182","created_at":"2026-06-04T01:08:19Z"},{"alias_kind":"pith_short_12","alias_value":"CDP452J7K3BK","created_at":"2026-06-04T01:08:19Z"},{"alias_kind":"pith_short_16","alias_value":"CDP452J7K3BKJIP5","created_at":"2026-06-04T01:08:19Z"},{"alias_kind":"pith_short_8","alias_value":"CDP452J7","created_at":"2026-06-04T01:08:19Z"}],"graph_snapshots":[{"event_id":"sha256:49c6cc34d6e2e7411d6fb7b6e1d28344c556206d460e89b16f862c34f9138a22","target":"graph","created_at":"2026-06-04T01:08:19Z","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/2606.04182/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We formulate the problem of \\emph{exact unlearning} in reinforcement learning, where the goal is to design an efficient framework that enables the removal of any user's data upon deletion request, i.e., the online learner's output after unlearning is \\emph{indistinguishable} from what would have been produced had the deleted user never interacted with the learner. For any $\\rho >0$, we show that there exists a reinforcement learning (RL) algorithm that is $\\rho$-TV-stable and supports an exact unlearning procedure whose expected computational cost is only a $\\rho \\sqrt{\\ln T}$ fraction of the ","authors_text":"Raman Arora, Thanh Nguyen-Tang","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T19:54:44Z","title":"Exact Unlearning in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04182","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":"sha256:088d9cdd0f65d7c94d3db7e4e6deb09b4b6529ce5322e32015b9319ef59ef294","target":"record","created_at":"2026-06-04T01:08:19Z","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":"0a9226249b814814f745b83c1df417feb88cdc814471a05737fb234400dc606b","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T19:54:44Z","title_canon_sha256":"89eff89bbe86c69e58823bcd21241973d1758365bc07624f4a9f7693dc62a3d5"},"schema_version":"1.0","source":{"id":"2606.04182","kind":"arxiv","version":1}},"canonical_sha256":"10dfcee93f56c2a4a1fd384ee9328b471b773ba11b0c41f96a3b6be6bac9c13f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"10dfcee93f56c2a4a1fd384ee9328b471b773ba11b0c41f96a3b6be6bac9c13f","first_computed_at":"2026-06-04T01:08:19.279095Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-04T01:08:19.279095Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S4DDTOz71ofoqBQj4XOIdhrR3oFCRvlm6vScGiJv6yqEHJNDLeX9tzXUYJohHJD2PHgzLe2GThc+SriMrcM2AQ==","signature_status":"signed_v1","signed_at":"2026-06-04T01:08:19.279792Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.04182","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:088d9cdd0f65d7c94d3db7e4e6deb09b4b6529ce5322e32015b9319ef59ef294","sha256:49c6cc34d6e2e7411d6fb7b6e1d28344c556206d460e89b16f862c34f9138a22"],"state_sha256":"33533c09e26a16e4286e7b6bc8ba1cf94da49135f84278153b880c1496eb587d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dK4FO0slu81XnaRBLVGYN+5vu5JibOJN5EiaWTRa/JLEGyFLh7sVqJcyPfr6PlIQDEuX4VxdnMBCUgxI/q60AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-29T08:08:56.430865Z","bundle_sha256":"38a7b008536330396f5102e82a09a21fc1234e93d6ff692c34fb16c15f005646"}}