{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:TJGPHWCG3M5NYUT7IXSRBH3NPI","short_pith_number":"pith:TJGPHWCG","canonical_record":{"source":{"id":"2208.00081","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-29T21:29:29Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"719daa7a84bacd25b1bfb3527ca2fe8a2202ffb721f6e3fd411f122e1527917e","abstract_canon_sha256":"5150ee5aa6679dae2c151c0c2f9491ab2b7759e8116b9b4cd3d206bb667e36a7"},"schema_version":"1.0"},"canonical_sha256":"9a4cf3d846db3adc527f45e5109f6d7a0f7ca487753475f0b29497c8b65781c6","source":{"kind":"arxiv","id":"2208.00081","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.00081","created_at":"2026-07-05T05:49:14Z"},{"alias_kind":"arxiv_version","alias_value":"2208.00081v2","created_at":"2026-07-05T05:49:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.00081","created_at":"2026-07-05T05:49:14Z"},{"alias_kind":"pith_short_12","alias_value":"TJGPHWCG3M5N","created_at":"2026-07-05T05:49:14Z"},{"alias_kind":"pith_short_16","alias_value":"TJGPHWCG3M5NYUT7","created_at":"2026-07-05T05:49:14Z"},{"alias_kind":"pith_short_8","alias_value":"TJGPHWCG","created_at":"2026-07-05T05:49:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:TJGPHWCG3M5NYUT7IXSRBH3NPI","target":"record","payload":{"canonical_record":{"source":{"id":"2208.00081","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-29T21:29:29Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"719daa7a84bacd25b1bfb3527ca2fe8a2202ffb721f6e3fd411f122e1527917e","abstract_canon_sha256":"5150ee5aa6679dae2c151c0c2f9491ab2b7759e8116b9b4cd3d206bb667e36a7"},"schema_version":"1.0"},"canonical_sha256":"9a4cf3d846db3adc527f45e5109f6d7a0f7ca487753475f0b29497c8b65781c6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:49:14.035730Z","signature_b64":"4/dwdctwm1f9qvGPuu23QpkikELd2eHth+DM2dZQLXTSeWWrvFARFRLkTCYbDNCzL3OOippV5bBPOB7gieMiCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a4cf3d846db3adc527f45e5109f6d7a0f7ca487753475f0b29497c8b65781c6","last_reissued_at":"2026-07-05T05:49:14.035241Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:49:14.035241Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2208.00081","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:49:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N/aDJAB4L+06B/MAzjFj1tsk433gE6GdS7qozmK6Kxxz/Je6ycaSYRn71kpKgflTfUGJ7sf/Mv83vvhbDxpHCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T15:33:41.452612Z"},"content_sha256":"54f758f8d6789c637f73a4a4b5a75b9f8fde81727bc727fd89445fed73973fd0","schema_version":"1.0","event_id":"sha256:54f758f8d6789c637f73a4a4b5a75b9f8fde81727bc727fd89445fed73973fd0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:TJGPHWCG3M5NYUT7IXSRBH3NPI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sampling Attacks on Meta Reinforcement Learning: A Minimax Formulation and Complexity Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Haozhe Lei, Quanyan Zhu, Tao Li","submitted_at":"2022-07-29T21:29:29Z","abstract_excerpt":"Meta reinforcement learning (meta RL), as a combination of meta-learning ideas and reinforcement learning (RL), enables the agent to adapt to different tasks using a few samples. However, this sampling-based adaptation also makes meta RL vulnerable to adversarial attacks. By manipulating the reward feedback from sampling processes in meta RL, an attacker can mislead the agent into building wrong knowledge from training experience, which deteriorates the agent's performance when dealing with different tasks after adaptation. This paper provides a game-theoretical underpinning for understanding "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.00081","kind":"arxiv","version":2},"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/2208.00081/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":"2026-07-05T05:49:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ikflP5yqzYz1uaM1Kg4jaJr5859TGGggIsF2HFclTimCF4lK/ywxQY5DcvKKynxryOCLpOSjOs5cd44NCfumAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T15:33:41.453197Z"},"content_sha256":"72859bc3135cdbb518eeecd92c1120ea573e07d1b0bf48ca5ec6df86cadbf462","schema_version":"1.0","event_id":"sha256:72859bc3135cdbb518eeecd92c1120ea573e07d1b0bf48ca5ec6df86cadbf462"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TJGPHWCG3M5NYUT7IXSRBH3NPI/bundle.json","state_url":"https://pith.science/pith/TJGPHWCG3M5NYUT7IXSRBH3NPI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TJGPHWCG3M5NYUT7IXSRBH3NPI/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":"2026-07-13T15:33:41Z","links":{"resolver":"https://pith.science/pith/TJGPHWCG3M5NYUT7IXSRBH3NPI","bundle":"https://pith.science/pith/TJGPHWCG3M5NYUT7IXSRBH3NPI/bundle.json","state":"https://pith.science/pith/TJGPHWCG3M5NYUT7IXSRBH3NPI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TJGPHWCG3M5NYUT7IXSRBH3NPI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:TJGPHWCG3M5NYUT7IXSRBH3NPI","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":"5150ee5aa6679dae2c151c0c2f9491ab2b7759e8116b9b4cd3d206bb667e36a7","cross_cats_sorted":["cs.CR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-29T21:29:29Z","title_canon_sha256":"719daa7a84bacd25b1bfb3527ca2fe8a2202ffb721f6e3fd411f122e1527917e"},"schema_version":"1.0","source":{"id":"2208.00081","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.00081","created_at":"2026-07-05T05:49:14Z"},{"alias_kind":"arxiv_version","alias_value":"2208.00081v2","created_at":"2026-07-05T05:49:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.00081","created_at":"2026-07-05T05:49:14Z"},{"alias_kind":"pith_short_12","alias_value":"TJGPHWCG3M5N","created_at":"2026-07-05T05:49:14Z"},{"alias_kind":"pith_short_16","alias_value":"TJGPHWCG3M5NYUT7","created_at":"2026-07-05T05:49:14Z"},{"alias_kind":"pith_short_8","alias_value":"TJGPHWCG","created_at":"2026-07-05T05:49:14Z"}],"graph_snapshots":[{"event_id":"sha256:72859bc3135cdbb518eeecd92c1120ea573e07d1b0bf48ca5ec6df86cadbf462","target":"graph","created_at":"2026-07-05T05:49:14Z","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/2208.00081/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Meta reinforcement learning (meta RL), as a combination of meta-learning ideas and reinforcement learning (RL), enables the agent to adapt to different tasks using a few samples. However, this sampling-based adaptation also makes meta RL vulnerable to adversarial attacks. By manipulating the reward feedback from sampling processes in meta RL, an attacker can mislead the agent into building wrong knowledge from training experience, which deteriorates the agent's performance when dealing with different tasks after adaptation. This paper provides a game-theoretical underpinning for understanding ","authors_text":"Haozhe Lei, Quanyan Zhu, Tao Li","cross_cats":["cs.CR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-29T21:29:29Z","title":"Sampling Attacks on Meta Reinforcement Learning: A Minimax Formulation and Complexity Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.00081","kind":"arxiv","version":2},"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":"sha256:54f758f8d6789c637f73a4a4b5a75b9f8fde81727bc727fd89445fed73973fd0","target":"record","created_at":"2026-07-05T05:49:14Z","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":"5150ee5aa6679dae2c151c0c2f9491ab2b7759e8116b9b4cd3d206bb667e36a7","cross_cats_sorted":["cs.CR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-29T21:29:29Z","title_canon_sha256":"719daa7a84bacd25b1bfb3527ca2fe8a2202ffb721f6e3fd411f122e1527917e"},"schema_version":"1.0","source":{"id":"2208.00081","kind":"arxiv","version":2}},"canonical_sha256":"9a4cf3d846db3adc527f45e5109f6d7a0f7ca487753475f0b29497c8b65781c6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9a4cf3d846db3adc527f45e5109f6d7a0f7ca487753475f0b29497c8b65781c6","first_computed_at":"2026-07-05T05:49:14.035241Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:49:14.035241Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4/dwdctwm1f9qvGPuu23QpkikELd2eHth+DM2dZQLXTSeWWrvFARFRLkTCYbDNCzL3OOippV5bBPOB7gieMiCw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:49:14.035730Z","signed_message":"canonical_sha256_bytes"},"source_id":"2208.00081","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:54f758f8d6789c637f73a4a4b5a75b9f8fde81727bc727fd89445fed73973fd0","sha256:72859bc3135cdbb518eeecd92c1120ea573e07d1b0bf48ca5ec6df86cadbf462"],"state_sha256":"020f65b91c00779a5d953be12fae083978d41326558125bccfcda17bfefbcfe7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WGMlAhf1bvCn5cWGnOindzsWEmqaRBf/wn2I98YryNgQQbbgpIdvHFfQ6cMD9bN2OO6t8hccmHWUNwtQxPEeDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-13T15:33:41.456848Z","bundle_sha256":"4c4b67167dcf6b98a0c295f5ca212f6c5e8821801d744fad9c50fbdac68840ca"}}