{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:ESJIFUTXKFW2WK6XIEY4WMD35U","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":"de8917e9715de2006314fc2575c336769a92bd5b00781af6ec155b2edd3231a9","cross_cats_sorted":["cs.AI","cs.CR","cs.GT"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-04T03:15:57Z","title_canon_sha256":"760045bec02d8c924717c30b099ef82c17d479c301da1bd651e0f290f50e247e"},"schema_version":"1.0","source":{"id":"2206.01888","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.01888","created_at":"2026-07-05T05:49:13Z"},{"alias_kind":"arxiv_version","alias_value":"2206.01888v4","created_at":"2026-07-05T05:49:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.01888","created_at":"2026-07-05T05:49:13Z"},{"alias_kind":"pith_short_12","alias_value":"ESJIFUTXKFW2","created_at":"2026-07-05T05:49:13Z"},{"alias_kind":"pith_short_16","alias_value":"ESJIFUTXKFW2WK6X","created_at":"2026-07-05T05:49:13Z"},{"alias_kind":"pith_short_8","alias_value":"ESJIFUTX","created_at":"2026-07-05T05:49:13Z"}],"graph_snapshots":[{"event_id":"sha256:61e350f269b2c01b4defc85221b19ad31eb7e7dd6c1accc78293688377f78445","target":"graph","created_at":"2026-07-05T05:49:13Z","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/2206.01888/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In offline multi-agent reinforcement learning (MARL), agents estimate policies from a given dataset. We study reward-poisoning attacks in this setting where an exogenous attacker modifies the rewards in the dataset before the agents see the dataset. The attacker wants to guide each agent into a nefarious target policy while minimizing the $L^p$ norm of the reward modification. Unlike attacks on single-agent RL, we show that the attacker can install the target policy as a Markov Perfect Dominant Strategy Equilibrium (MPDSE), which rational agents are guaranteed to follow. This attack can be sig","authors_text":"Jeremy McMahan, Qiaomin Xie, Xiaojin Zhu, Young Wu","cross_cats":["cs.AI","cs.CR","cs.GT"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-04T03:15:57Z","title":"Reward Poisoning Attacks on Offline Multi-Agent Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.01888","kind":"arxiv","version":4},"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:e9b90448226902bf6fbdc8162920f49f590f90b83cc1cd779f958023ff94f82d","target":"record","created_at":"2026-07-05T05:49:13Z","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":"de8917e9715de2006314fc2575c336769a92bd5b00781af6ec155b2edd3231a9","cross_cats_sorted":["cs.AI","cs.CR","cs.GT"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-04T03:15:57Z","title_canon_sha256":"760045bec02d8c924717c30b099ef82c17d479c301da1bd651e0f290f50e247e"},"schema_version":"1.0","source":{"id":"2206.01888","kind":"arxiv","version":4}},"canonical_sha256":"249282d277516dab2bd74131cb307bed103faced46b7521ee8a8362a2d9c3c39","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"249282d277516dab2bd74131cb307bed103faced46b7521ee8a8362a2d9c3c39","first_computed_at":"2026-07-05T05:49:13.507304Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:49:13.507304Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AV6IU4KAsrE3c/FrZR2/gUNl56pRlSNHYFato+eVHLKd1l/9slp7aiQUPoeiGqQWZct3qqI3EtAQoMIUI0GjCw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:49:13.507742Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.01888","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e9b90448226902bf6fbdc8162920f49f590f90b83cc1cd779f958023ff94f82d","sha256:61e350f269b2c01b4defc85221b19ad31eb7e7dd6c1accc78293688377f78445"],"state_sha256":"d65215227ede8b7a75977eaed8153e4c0c3665faba8ce7f25a0aa031ab246e8d"}