{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:IDQVSIU6PNP4UTHNI6ZCEWQC6A","short_pith_number":"pith:IDQVSIU6","canonical_record":{"source":{"id":"2411.13116","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-20T08:20:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"43e552ddb8561d77b46bf588c50d6158c4d86c64b4dd76f258334409e3ee0980","abstract_canon_sha256":"f927768e207e54236ad2aae3f6847077f2aabd159ee0e06635be88937fceb193"},"schema_version":"1.0"},"canonical_sha256":"40e159229e7b5fca4ced47b2225a02f0387841b6ac92013db7506e9aeef8c027","source":{"kind":"arxiv","id":"2411.13116","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.13116","created_at":"2026-07-05T09:38:05Z"},{"alias_kind":"arxiv_version","alias_value":"2411.13116v1","created_at":"2026-07-05T09:38:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.13116","created_at":"2026-07-05T09:38:05Z"},{"alias_kind":"pith_short_12","alias_value":"IDQVSIU6PNP4","created_at":"2026-07-05T09:38:05Z"},{"alias_kind":"pith_short_16","alias_value":"IDQVSIU6PNP4UTHN","created_at":"2026-07-05T09:38:05Z"},{"alias_kind":"pith_short_8","alias_value":"IDQVSIU6","created_at":"2026-07-05T09:38:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:IDQVSIU6PNP4UTHNI6ZCEWQC6A","target":"record","payload":{"canonical_record":{"source":{"id":"2411.13116","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-20T08:20:29Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"43e552ddb8561d77b46bf588c50d6158c4d86c64b4dd76f258334409e3ee0980","abstract_canon_sha256":"f927768e207e54236ad2aae3f6847077f2aabd159ee0e06635be88937fceb193"},"schema_version":"1.0"},"canonical_sha256":"40e159229e7b5fca4ced47b2225a02f0387841b6ac92013db7506e9aeef8c027","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:38:05.348367Z","signature_b64":"KXmzts4c+XGk22MWg2eIlagbp3cdLG9SS6Oxj3y4CBBxMLdBmYN6phKI99RjcipU2HW4dzMSYddHrxK9sAfTCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40e159229e7b5fca4ced47b2225a02f0387841b6ac92013db7506e9aeef8c027","last_reissued_at":"2026-07-05T09:38:05.347890Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:38:05.347890Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.13116","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":"2026-07-05T09:38:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sFqjMEU62o1UYMGGpUerrddGB2mFuJ2nh/6zKWBExP22UsCcBL35X5G2wi+6PBqxWfGtZT5HduX91Slnmt8tCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T17:24:14.076243Z"},"content_sha256":"ed117f6ddb14470041384248535bbf491872f276ab8eda392a47d1e54d43bfe1","schema_version":"1.0","event_id":"sha256:ed117f6ddb14470041384248535bbf491872f276ab8eda392a47d1e54d43bfe1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:IDQVSIU6PNP4UTHNI6ZCEWQC6A","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Di Wang, Pan Zhou, Xiyuan Yang, Zhi Luo","submitted_at":"2024-11-20T08:20:29Z","abstract_excerpt":"Manipulating the interaction trajectories between the intelligent agent and the environment can control the agent's training and behavior, exposing the potential vulnerabilities of reinforcement learning (RL). For example, in Cyber-Physical Systems (CPS) controlled by RL, the attacker can manipulate the actions of the adopted RL to other actions during the training phase, which will lead to bad consequences. Existing work has studied action-manipulation attacks in tabular settings, where the states and actions are discrete. As seen in many up-and-coming RL applications, such as autonomous driv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.13116","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/2411.13116/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":"2026-07-05T09:38:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tbkOduFmkbAilL/qV6VO7oapqHW1A9pkp1xHsAnkd2GOQH8rIISikMAfaS5CFEnhAXE/cTv7Jp/Aks7artJzDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T17:24:14.076691Z"},"content_sha256":"7f04cb5010a2c1167cb9e2fe6590fd8a3f4efcb8d53fc51df4b4512ee90b9584","schema_version":"1.0","event_id":"sha256:7f04cb5010a2c1167cb9e2fe6590fd8a3f4efcb8d53fc51df4b4512ee90b9584"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IDQVSIU6PNP4UTHNI6ZCEWQC6A/bundle.json","state_url":"https://pith.science/pith/IDQVSIU6PNP4UTHNI6ZCEWQC6A/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IDQVSIU6PNP4UTHNI6ZCEWQC6A/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":"2026-08-13T17:24:14Z","links":{"resolver":"https://pith.science/pith/IDQVSIU6PNP4UTHNI6ZCEWQC6A","bundle":"https://pith.science/pith/IDQVSIU6PNP4UTHNI6ZCEWQC6A/bundle.json","state":"https://pith.science/pith/IDQVSIU6PNP4UTHNI6ZCEWQC6A/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IDQVSIU6PNP4UTHNI6ZCEWQC6A/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IDQVSIU6PNP4UTHNI6ZCEWQC6A","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":"f927768e207e54236ad2aae3f6847077f2aabd159ee0e06635be88937fceb193","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-20T08:20:29Z","title_canon_sha256":"43e552ddb8561d77b46bf588c50d6158c4d86c64b4dd76f258334409e3ee0980"},"schema_version":"1.0","source":{"id":"2411.13116","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.13116","created_at":"2026-07-05T09:38:05Z"},{"alias_kind":"arxiv_version","alias_value":"2411.13116v1","created_at":"2026-07-05T09:38:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.13116","created_at":"2026-07-05T09:38:05Z"},{"alias_kind":"pith_short_12","alias_value":"IDQVSIU6PNP4","created_at":"2026-07-05T09:38:05Z"},{"alias_kind":"pith_short_16","alias_value":"IDQVSIU6PNP4UTHN","created_at":"2026-07-05T09:38:05Z"},{"alias_kind":"pith_short_8","alias_value":"IDQVSIU6","created_at":"2026-07-05T09:38:05Z"}],"graph_snapshots":[{"event_id":"sha256:7f04cb5010a2c1167cb9e2fe6590fd8a3f4efcb8d53fc51df4b4512ee90b9584","target":"graph","created_at":"2026-07-05T09:38:05Z","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/2411.13116/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Manipulating the interaction trajectories between the intelligent agent and the environment can control the agent's training and behavior, exposing the potential vulnerabilities of reinforcement learning (RL). For example, in Cyber-Physical Systems (CPS) controlled by RL, the attacker can manipulate the actions of the adopted RL to other actions during the training phase, which will lead to bad consequences. Existing work has studied action-manipulation attacks in tabular settings, where the states and actions are discrete. As seen in many up-and-coming RL applications, such as autonomous driv","authors_text":"Di Wang, Pan Zhou, Xiyuan Yang, Zhi Luo","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-20T08:20:29Z","title":"Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.13116","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:ed117f6ddb14470041384248535bbf491872f276ab8eda392a47d1e54d43bfe1","target":"record","created_at":"2026-07-05T09:38:05Z","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":"f927768e207e54236ad2aae3f6847077f2aabd159ee0e06635be88937fceb193","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-20T08:20:29Z","title_canon_sha256":"43e552ddb8561d77b46bf588c50d6158c4d86c64b4dd76f258334409e3ee0980"},"schema_version":"1.0","source":{"id":"2411.13116","kind":"arxiv","version":1}},"canonical_sha256":"40e159229e7b5fca4ced47b2225a02f0387841b6ac92013db7506e9aeef8c027","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"40e159229e7b5fca4ced47b2225a02f0387841b6ac92013db7506e9aeef8c027","first_computed_at":"2026-07-05T09:38:05.347890Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:38:05.347890Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KXmzts4c+XGk22MWg2eIlagbp3cdLG9SS6Oxj3y4CBBxMLdBmYN6phKI99RjcipU2HW4dzMSYddHrxK9sAfTCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:38:05.348367Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.13116","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ed117f6ddb14470041384248535bbf491872f276ab8eda392a47d1e54d43bfe1","sha256:7f04cb5010a2c1167cb9e2fe6590fd8a3f4efcb8d53fc51df4b4512ee90b9584"],"state_sha256":"f64070d6ba69bac8f4bd14e3d6eae62b068b1106c0c3983ac77ceff14316e4d5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jkipV+H3i1hCb92xBoWog2luwnqBGzkaOxgqNSEyxtREVUjtQNoSDBsv9lABs1P91VYualitGfBUm9mnV1UcAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T17:24:14.080132Z","bundle_sha256":"a59f67a4e67dbcb41e0e6c2acb17866ab817c6c38210431a51bd14f7bae35a8d"}}