{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:UQ73SWSO7GBRCH72KFVAW7OYHX","short_pith_number":"pith:UQ73SWSO","canonical_record":{"source":{"id":"2009.00774","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-02T01:43:30Z","cross_cats_sorted":["cs.CR","stat.ML"],"title_canon_sha256":"dcc63378d95da6311db0a9adfa3eccf23777b2946232029da701f846130de2a5","abstract_canon_sha256":"7f460d1409384f982cc29b349f1e0dc013b25b9a0574b4470df192181ac3a2f8"},"schema_version":"1.0"},"canonical_sha256":"a43fb95a4ef983111ffa516a0b7dd83dff1a45c2278d85cc4e858325a390a21a","source":{"kind":"arxiv","id":"2009.00774","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.00774","created_at":"2026-07-05T03:57:24Z"},{"alias_kind":"arxiv_version","alias_value":"2009.00774v5","created_at":"2026-07-05T03:57:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.00774","created_at":"2026-07-05T03:57:24Z"},{"alias_kind":"pith_short_12","alias_value":"UQ73SWSO7GBR","created_at":"2026-07-05T03:57:24Z"},{"alias_kind":"pith_short_16","alias_value":"UQ73SWSO7GBRCH72","created_at":"2026-07-05T03:57:24Z"},{"alias_kind":"pith_short_8","alias_value":"UQ73SWSO","created_at":"2026-07-05T03:57:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:UQ73SWSO7GBRCH72KFVAW7OYHX","target":"record","payload":{"canonical_record":{"source":{"id":"2009.00774","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-02T01:43:30Z","cross_cats_sorted":["cs.CR","stat.ML"],"title_canon_sha256":"dcc63378d95da6311db0a9adfa3eccf23777b2946232029da701f846130de2a5","abstract_canon_sha256":"7f460d1409384f982cc29b349f1e0dc013b25b9a0574b4470df192181ac3a2f8"},"schema_version":"1.0"},"canonical_sha256":"a43fb95a4ef983111ffa516a0b7dd83dff1a45c2278d85cc4e858325a390a21a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:57:24.285562Z","signature_b64":"MfyeJW86UKMWDL/Nb9yVEBl/rlqi6AbllRJjtWktJlh+nEDgZcChtChT74FOCAc0pNzQ10AwJjamh3XJy+BoDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a43fb95a4ef983111ffa516a0b7dd83dff1a45c2278d85cc4e858325a390a21a","last_reissued_at":"2026-07-05T03:57:24.285136Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:57:24.285136Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2009.00774","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:57:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Fk5Gx4KLfyvQZP1FxmayF+1MHtopXCdsJgAwXoWdYKmGf6EfmX7ufOh8eeHNLRFMbqvXoB0fQwjocA9ktwP/Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:53:08.948372Z"},"content_sha256":"8d8200155e380c6aed6c0985764d45e17cd7b9d8919983d775f5bd00dd2f87be","schema_version":"1.0","event_id":"sha256:8d8200155e380c6aed6c0985764d45e17cd7b9d8919983d775f5bd00dd2f87be"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:UQ73SWSO7GBRCH72KFVAW7OYHX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Vulnerability-Aware Poisoning Mechanism for Online RL with Unknown Dynamics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Da Huo, Furong Huang, Yanchao Sun","submitted_at":"2020-09-02T01:43:30Z","abstract_excerpt":"Poisoning attacks on Reinforcement Learning (RL) systems could take advantage of RL algorithm's vulnerabilities and cause failure of the learning. However, prior works on poisoning RL usually either unrealistically assume the attacker knows the underlying Markov Decision Process (MDP), or directly apply the poisoning methods in supervised learning to RL. In this work, we build a generic poisoning framework for online RL via a comprehensive investigation of heterogeneous poisoning models in RL. Without any prior knowledge of the MDP, we propose a strategic poisoning algorithm called Vulnerabili"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.00774","kind":"arxiv","version":5},"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/2009.00774/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":"2026-07-05T03:57:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"obDqzOcnRAAxclWmoUIA0QqUizvPNGzuj22tk9Oc/GrMTSF3KzBku4kE/Qq3p4zwwAinPweJbVUpQbwdlqL/Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:53:08.948758Z"},"content_sha256":"b6da879fb1f639cda0b0fce385cfa60f79679c25fd06b3c61634422fb49c9d0f","schema_version":"1.0","event_id":"sha256:b6da879fb1f639cda0b0fce385cfa60f79679c25fd06b3c61634422fb49c9d0f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UQ73SWSO7GBRCH72KFVAW7OYHX/bundle.json","state_url":"https://pith.science/pith/UQ73SWSO7GBRCH72KFVAW7OYHX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UQ73SWSO7GBRCH72KFVAW7OYHX/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":"2026-07-06T20:53:08Z","links":{"resolver":"https://pith.science/pith/UQ73SWSO7GBRCH72KFVAW7OYHX","bundle":"https://pith.science/pith/UQ73SWSO7GBRCH72KFVAW7OYHX/bundle.json","state":"https://pith.science/pith/UQ73SWSO7GBRCH72KFVAW7OYHX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UQ73SWSO7GBRCH72KFVAW7OYHX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:UQ73SWSO7GBRCH72KFVAW7OYHX","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":"7f460d1409384f982cc29b349f1e0dc013b25b9a0574b4470df192181ac3a2f8","cross_cats_sorted":["cs.CR","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-02T01:43:30Z","title_canon_sha256":"dcc63378d95da6311db0a9adfa3eccf23777b2946232029da701f846130de2a5"},"schema_version":"1.0","source":{"id":"2009.00774","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2009.00774","created_at":"2026-07-05T03:57:24Z"},{"alias_kind":"arxiv_version","alias_value":"2009.00774v5","created_at":"2026-07-05T03:57:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.00774","created_at":"2026-07-05T03:57:24Z"},{"alias_kind":"pith_short_12","alias_value":"UQ73SWSO7GBR","created_at":"2026-07-05T03:57:24Z"},{"alias_kind":"pith_short_16","alias_value":"UQ73SWSO7GBRCH72","created_at":"2026-07-05T03:57:24Z"},{"alias_kind":"pith_short_8","alias_value":"UQ73SWSO","created_at":"2026-07-05T03:57:24Z"}],"graph_snapshots":[{"event_id":"sha256:b6da879fb1f639cda0b0fce385cfa60f79679c25fd06b3c61634422fb49c9d0f","target":"graph","created_at":"2026-07-05T03:57:24Z","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/2009.00774/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Poisoning attacks on Reinforcement Learning (RL) systems could take advantage of RL algorithm's vulnerabilities and cause failure of the learning. However, prior works on poisoning RL usually either unrealistically assume the attacker knows the underlying Markov Decision Process (MDP), or directly apply the poisoning methods in supervised learning to RL. In this work, we build a generic poisoning framework for online RL via a comprehensive investigation of heterogeneous poisoning models in RL. Without any prior knowledge of the MDP, we propose a strategic poisoning algorithm called Vulnerabili","authors_text":"Da Huo, Furong Huang, Yanchao Sun","cross_cats":["cs.CR","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-02T01:43:30Z","title":"Vulnerability-Aware Poisoning Mechanism for Online RL with Unknown Dynamics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.00774","kind":"arxiv","version":5},"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":"sha256:8d8200155e380c6aed6c0985764d45e17cd7b9d8919983d775f5bd00dd2f87be","target":"record","created_at":"2026-07-05T03:57:24Z","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":"7f460d1409384f982cc29b349f1e0dc013b25b9a0574b4470df192181ac3a2f8","cross_cats_sorted":["cs.CR","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-02T01:43:30Z","title_canon_sha256":"dcc63378d95da6311db0a9adfa3eccf23777b2946232029da701f846130de2a5"},"schema_version":"1.0","source":{"id":"2009.00774","kind":"arxiv","version":5}},"canonical_sha256":"a43fb95a4ef983111ffa516a0b7dd83dff1a45c2278d85cc4e858325a390a21a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a43fb95a4ef983111ffa516a0b7dd83dff1a45c2278d85cc4e858325a390a21a","first_computed_at":"2026-07-05T03:57:24.285136Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:57:24.285136Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MfyeJW86UKMWDL/Nb9yVEBl/rlqi6AbllRJjtWktJlh+nEDgZcChtChT74FOCAc0pNzQ10AwJjamh3XJy+BoDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:57:24.285562Z","signed_message":"canonical_sha256_bytes"},"source_id":"2009.00774","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8d8200155e380c6aed6c0985764d45e17cd7b9d8919983d775f5bd00dd2f87be","sha256:b6da879fb1f639cda0b0fce385cfa60f79679c25fd06b3c61634422fb49c9d0f"],"state_sha256":"e692eda3f2fcf0cdfe5e1f49f28f08c3927674704b3e0c72248cfbdfcc39f211"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3tK837xPYrM1VLen+N9j1EtkZgZw06dovf0wZNPvcAHmrgzsDY+ZcDbWXWtVUfuvKonoCsbDIAMqWC7dU7BdBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T20:53:08.950870Z","bundle_sha256":"85b5a213fd228f4d3b679d48b1faeabb31a95f60f6f43cd9a51248991bad2d54"}}