{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:PRR5OLPRCW7IYALNLTJRSD3OEU","short_pith_number":"pith:PRR5OLPR","canonical_record":{"source":{"id":"2302.13851","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-27T14:52:15Z","cross_cats_sorted":["cs.AI","cs.CR","cs.MA"],"title_canon_sha256":"40e3b76c1ffd3e289cbb67b5941fb0aad689746e4167735f8c815d7e0d912b29","abstract_canon_sha256":"cbd08c4b0b2e4501b8b5988cdd1ff34dabb56ea64dbc611ce8307cf6a125b3c5"},"schema_version":"1.0"},"canonical_sha256":"7c63d72df115be8c016d5cd3190f6e250fec822be37e688f7b7c6044c1b2fae8","source":{"kind":"arxiv","id":"2302.13851","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.13851","created_at":"2026-07-05T05:45:51Z"},{"alias_kind":"arxiv_version","alias_value":"2302.13851v1","created_at":"2026-07-05T05:45:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.13851","created_at":"2026-07-05T05:45:51Z"},{"alias_kind":"pith_short_12","alias_value":"PRR5OLPRCW7I","created_at":"2026-07-05T05:45:51Z"},{"alias_kind":"pith_short_16","alias_value":"PRR5OLPRCW7IYALN","created_at":"2026-07-05T05:45:51Z"},{"alias_kind":"pith_short_8","alias_value":"PRR5OLPR","created_at":"2026-07-05T05:45:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:PRR5OLPRCW7IYALNLTJRSD3OEU","target":"record","payload":{"canonical_record":{"source":{"id":"2302.13851","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-27T14:52:15Z","cross_cats_sorted":["cs.AI","cs.CR","cs.MA"],"title_canon_sha256":"40e3b76c1ffd3e289cbb67b5941fb0aad689746e4167735f8c815d7e0d912b29","abstract_canon_sha256":"cbd08c4b0b2e4501b8b5988cdd1ff34dabb56ea64dbc611ce8307cf6a125b3c5"},"schema_version":"1.0"},"canonical_sha256":"7c63d72df115be8c016d5cd3190f6e250fec822be37e688f7b7c6044c1b2fae8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:45:51.552429Z","signature_b64":"j9IFgHlLre9KiNbDz5N3Ibot85SaqncPfvGo79bKL6Qg+vJoiuZEOfyEFs6aEbyOCjyy1+jGWBZ/KgpVfOCJBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c63d72df115be8c016d5cd3190f6e250fec822be37e688f7b7c6044c1b2fae8","last_reissued_at":"2026-07-05T05:45:51.551927Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:45:51.551927Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.13851","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":"2026-07-05T05:45:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HH9IR4cP0UjwDflxLDbavIMidt5DYzkltpydD+uymkvn/bK+zrd31WFI+a+SRDmt41AxTiSvFFbffe8TjzY9Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T02:15:09.575598Z"},"content_sha256":"86242ae4a8569963faba5852e49065191a08744c7f22302dcfccb70f196e6b62","schema_version":"1.0","event_id":"sha256:86242ae4a8569963faba5852e49065191a08744c7f22302dcfccb70f196e6b62"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:PRR5OLPRCW7IYALNLTJRSD3OEU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Implicit Poisoning Attacks in Two-Agent Reinforcement Learning: Adversarial Policies for Training-Time Attacks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR","cs.MA"],"primary_cat":"cs.LG","authors_text":"Adish Singla, Debmalya Mandal, Goran Radanovic, Jonathan N\\\"other, Mohammad Mohammadi","submitted_at":"2023-02-27T14:52:15Z","abstract_excerpt":"In targeted poisoning attacks, an attacker manipulates an agent-environment interaction to force the agent into adopting a policy of interest, called target policy. Prior work has primarily focused on attacks that modify standard MDP primitives, such as rewards or transitions. In this paper, we study targeted poisoning attacks in a two-agent setting where an attacker implicitly poisons the effective environment of one of the agents by modifying the policy of its peer. We develop an optimization framework for designing optimal attacks, where the cost of the attack measures how much the solution"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.13851","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/2302.13851/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":"2026-07-05T05:45:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JTmSdAUFL/CbSvb4UtaGlF8Akuod0h3T3WjNTM4QBizebj0WBcSpfRBRSYhItodbxjxLHADIfZ/kGnI1YwMLAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T02:15:09.575902Z"},"content_sha256":"6f756f96f9a0a3e44b4981891d35f5bf7bff8d401e6241c5ca40968abb08017f","schema_version":"1.0","event_id":"sha256:6f756f96f9a0a3e44b4981891d35f5bf7bff8d401e6241c5ca40968abb08017f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PRR5OLPRCW7IYALNLTJRSD3OEU/bundle.json","state_url":"https://pith.science/pith/PRR5OLPRCW7IYALNLTJRSD3OEU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PRR5OLPRCW7IYALNLTJRSD3OEU/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":"2026-08-08T02:15:09Z","links":{"resolver":"https://pith.science/pith/PRR5OLPRCW7IYALNLTJRSD3OEU","bundle":"https://pith.science/pith/PRR5OLPRCW7IYALNLTJRSD3OEU/bundle.json","state":"https://pith.science/pith/PRR5OLPRCW7IYALNLTJRSD3OEU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PRR5OLPRCW7IYALNLTJRSD3OEU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:PRR5OLPRCW7IYALNLTJRSD3OEU","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":"cbd08c4b0b2e4501b8b5988cdd1ff34dabb56ea64dbc611ce8307cf6a125b3c5","cross_cats_sorted":["cs.AI","cs.CR","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-27T14:52:15Z","title_canon_sha256":"40e3b76c1ffd3e289cbb67b5941fb0aad689746e4167735f8c815d7e0d912b29"},"schema_version":"1.0","source":{"id":"2302.13851","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.13851","created_at":"2026-07-05T05:45:51Z"},{"alias_kind":"arxiv_version","alias_value":"2302.13851v1","created_at":"2026-07-05T05:45:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.13851","created_at":"2026-07-05T05:45:51Z"},{"alias_kind":"pith_short_12","alias_value":"PRR5OLPRCW7I","created_at":"2026-07-05T05:45:51Z"},{"alias_kind":"pith_short_16","alias_value":"PRR5OLPRCW7IYALN","created_at":"2026-07-05T05:45:51Z"},{"alias_kind":"pith_short_8","alias_value":"PRR5OLPR","created_at":"2026-07-05T05:45:51Z"}],"graph_snapshots":[{"event_id":"sha256:6f756f96f9a0a3e44b4981891d35f5bf7bff8d401e6241c5ca40968abb08017f","target":"graph","created_at":"2026-07-05T05:45:51Z","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/2302.13851/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In targeted poisoning attacks, an attacker manipulates an agent-environment interaction to force the agent into adopting a policy of interest, called target policy. Prior work has primarily focused on attacks that modify standard MDP primitives, such as rewards or transitions. In this paper, we study targeted poisoning attacks in a two-agent setting where an attacker implicitly poisons the effective environment of one of the agents by modifying the policy of its peer. We develop an optimization framework for designing optimal attacks, where the cost of the attack measures how much the solution","authors_text":"Adish Singla, Debmalya Mandal, Goran Radanovic, Jonathan N\\\"other, Mohammad Mohammadi","cross_cats":["cs.AI","cs.CR","cs.MA"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-27T14:52:15Z","title":"Implicit Poisoning Attacks in Two-Agent Reinforcement Learning: Adversarial Policies for Training-Time Attacks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.13851","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":"sha256:86242ae4a8569963faba5852e49065191a08744c7f22302dcfccb70f196e6b62","target":"record","created_at":"2026-07-05T05:45:51Z","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":"cbd08c4b0b2e4501b8b5988cdd1ff34dabb56ea64dbc611ce8307cf6a125b3c5","cross_cats_sorted":["cs.AI","cs.CR","cs.MA"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-27T14:52:15Z","title_canon_sha256":"40e3b76c1ffd3e289cbb67b5941fb0aad689746e4167735f8c815d7e0d912b29"},"schema_version":"1.0","source":{"id":"2302.13851","kind":"arxiv","version":1}},"canonical_sha256":"7c63d72df115be8c016d5cd3190f6e250fec822be37e688f7b7c6044c1b2fae8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7c63d72df115be8c016d5cd3190f6e250fec822be37e688f7b7c6044c1b2fae8","first_computed_at":"2026-07-05T05:45:51.551927Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:45:51.551927Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"j9IFgHlLre9KiNbDz5N3Ibot85SaqncPfvGo79bKL6Qg+vJoiuZEOfyEFs6aEbyOCjyy1+jGWBZ/KgpVfOCJBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:45:51.552429Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.13851","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:86242ae4a8569963faba5852e49065191a08744c7f22302dcfccb70f196e6b62","sha256:6f756f96f9a0a3e44b4981891d35f5bf7bff8d401e6241c5ca40968abb08017f"],"state_sha256":"7ac739a4b8985f9a90b89c664d8496f219a3a25bc1dde012eab16b4393a78ea1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P8wEvUdsOW01lAjHRQrjfKr7j5Izwr+vqPSclBm9e7zcDQiszzc8gE2TFZ1spXZY7WgzJEObyH1YFrZ71kvFCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T02:15:09.606875Z","bundle_sha256":"8ef8e804ca36bdb18c7264d70670a05fde94c0a4fc7c1ec73c0f5c35c0faad3b"}}