{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:IXYNYOVT67WKTJR75XKFE447WQ","short_pith_number":"pith:IXYNYOVT","canonical_record":{"source":{"id":"2412.10713","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-14T06:56:11Z","cross_cats_sorted":["cs.AI","cs.CR","cs.RO"],"title_canon_sha256":"05bbe17440c881d4209b597f9ee51b6bb30c315cbc3bc267e039378c88ba25fd","abstract_canon_sha256":"33ea9c5ae14e1cbf8c6fff9bc2544d4d035905698151f8fbd61b966f8cbe9f66"},"schema_version":"1.0"},"canonical_sha256":"45f0dc3ab3f7eca9a63fedd452739fb43fbf7326b1e701b73622fac70d8c3b04","source":{"kind":"arxiv","id":"2412.10713","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.10713","created_at":"2026-07-05T09:49:20Z"},{"alias_kind":"arxiv_version","alias_value":"2412.10713v1","created_at":"2026-07-05T09:49:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10713","created_at":"2026-07-05T09:49:20Z"},{"alias_kind":"pith_short_12","alias_value":"IXYNYOVT67WK","created_at":"2026-07-05T09:49:20Z"},{"alias_kind":"pith_short_16","alias_value":"IXYNYOVT67WKTJR7","created_at":"2026-07-05T09:49:20Z"},{"alias_kind":"pith_short_8","alias_value":"IXYNYOVT","created_at":"2026-07-05T09:49:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:IXYNYOVT67WKTJR75XKFE447WQ","target":"record","payload":{"canonical_record":{"source":{"id":"2412.10713","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-14T06:56:11Z","cross_cats_sorted":["cs.AI","cs.CR","cs.RO"],"title_canon_sha256":"05bbe17440c881d4209b597f9ee51b6bb30c315cbc3bc267e039378c88ba25fd","abstract_canon_sha256":"33ea9c5ae14e1cbf8c6fff9bc2544d4d035905698151f8fbd61b966f8cbe9f66"},"schema_version":"1.0"},"canonical_sha256":"45f0dc3ab3f7eca9a63fedd452739fb43fbf7326b1e701b73622fac70d8c3b04","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:20.259121Z","signature_b64":"eTv+s2qvKW9G77HerKtEuqFODgP/N56yT/4mFNQ5t06lVBcK7gFOfIqj7fkUd8mIvfM/6njFci0IVhxW3kznDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45f0dc3ab3f7eca9a63fedd452739fb43fbf7326b1e701b73622fac70d8c3b04","last_reissued_at":"2026-07-05T09:49:20.258660Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:20.258660Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.10713","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":"2026-07-05T09:49:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BLJv1+pulcY1oXd/2wUZdR+uO2W0FavyYv7kfANrxnzuOJRHkC0AxX0f+V1CsHd5Dg9QDg0XpAfVKZPBSepGBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T14:07:39.606290Z"},"content_sha256":"a5886a311ef00eeee04d5fcc8e8c76f3221a533dd9316c9c9c4c487a84fd6fd5","schema_version":"1.0","event_id":"sha256:a5886a311ef00eeee04d5fcc8e8c76f3221a533dd9316c9c9c4c487a84fd6fd5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:IXYNYOVT67WKTJR75XKFE447WQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RAT: Adversarial Attacks on Deep Reinforcement Agents for Targeted Behaviors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CR","cs.RO"],"primary_cat":"cs.LG","authors_text":"Fengshuo Bai, Runze Liu, Yali Du, Yaodong Yang, Ying Wen","submitted_at":"2024-12-14T06:56:11Z","abstract_excerpt":"Evaluating deep reinforcement learning (DRL) agents against targeted behavior attacks is critical for assessing their robustness. These attacks aim to manipulate the victim into specific behaviors that align with the attacker's objectives, often bypassing traditional reward-based defenses. Prior methods have primarily focused on reducing cumulative rewards; however, rewards are typically too generic to capture complex safety requirements effectively. As a result, focusing solely on reward reduction can lead to suboptimal attack strategies, particularly in safety-critical scenarios where more p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10713","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/2412.10713/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":"2026-07-05T09:49:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KDVp4c67ebb4SYp2gIO51SzkS3KrL85Rr0r+qwplbqz7Hl2c+toTindWkLxnxMecNXaNF8SA9faWzz7ha6h+AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T14:07:39.606856Z"},"content_sha256":"0bfbc58eb4c74e096e4dfe9c6b59723f2afda671472517dcb0de16cc7e8669b9","schema_version":"1.0","event_id":"sha256:0bfbc58eb4c74e096e4dfe9c6b59723f2afda671472517dcb0de16cc7e8669b9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IXYNYOVT67WKTJR75XKFE447WQ/bundle.json","state_url":"https://pith.science/pith/IXYNYOVT67WKTJR75XKFE447WQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IXYNYOVT67WKTJR75XKFE447WQ/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":"2026-08-09T14:07:39Z","links":{"resolver":"https://pith.science/pith/IXYNYOVT67WKTJR75XKFE447WQ","bundle":"https://pith.science/pith/IXYNYOVT67WKTJR75XKFE447WQ/bundle.json","state":"https://pith.science/pith/IXYNYOVT67WKTJR75XKFE447WQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IXYNYOVT67WKTJR75XKFE447WQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IXYNYOVT67WKTJR75XKFE447WQ","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":"33ea9c5ae14e1cbf8c6fff9bc2544d4d035905698151f8fbd61b966f8cbe9f66","cross_cats_sorted":["cs.AI","cs.CR","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-14T06:56:11Z","title_canon_sha256":"05bbe17440c881d4209b597f9ee51b6bb30c315cbc3bc267e039378c88ba25fd"},"schema_version":"1.0","source":{"id":"2412.10713","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.10713","created_at":"2026-07-05T09:49:20Z"},{"alias_kind":"arxiv_version","alias_value":"2412.10713v1","created_at":"2026-07-05T09:49:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10713","created_at":"2026-07-05T09:49:20Z"},{"alias_kind":"pith_short_12","alias_value":"IXYNYOVT67WK","created_at":"2026-07-05T09:49:20Z"},{"alias_kind":"pith_short_16","alias_value":"IXYNYOVT67WKTJR7","created_at":"2026-07-05T09:49:20Z"},{"alias_kind":"pith_short_8","alias_value":"IXYNYOVT","created_at":"2026-07-05T09:49:20Z"}],"graph_snapshots":[{"event_id":"sha256:0bfbc58eb4c74e096e4dfe9c6b59723f2afda671472517dcb0de16cc7e8669b9","target":"graph","created_at":"2026-07-05T09:49:20Z","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/2412.10713/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Evaluating deep reinforcement learning (DRL) agents against targeted behavior attacks is critical for assessing their robustness. These attacks aim to manipulate the victim into specific behaviors that align with the attacker's objectives, often bypassing traditional reward-based defenses. Prior methods have primarily focused on reducing cumulative rewards; however, rewards are typically too generic to capture complex safety requirements effectively. As a result, focusing solely on reward reduction can lead to suboptimal attack strategies, particularly in safety-critical scenarios where more p","authors_text":"Fengshuo Bai, Runze Liu, Yali Du, Yaodong Yang, Ying Wen","cross_cats":["cs.AI","cs.CR","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-14T06:56:11Z","title":"RAT: Adversarial Attacks on Deep Reinforcement Agents for Targeted Behaviors"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10713","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:a5886a311ef00eeee04d5fcc8e8c76f3221a533dd9316c9c9c4c487a84fd6fd5","target":"record","created_at":"2026-07-05T09:49:20Z","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":"33ea9c5ae14e1cbf8c6fff9bc2544d4d035905698151f8fbd61b966f8cbe9f66","cross_cats_sorted":["cs.AI","cs.CR","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-14T06:56:11Z","title_canon_sha256":"05bbe17440c881d4209b597f9ee51b6bb30c315cbc3bc267e039378c88ba25fd"},"schema_version":"1.0","source":{"id":"2412.10713","kind":"arxiv","version":1}},"canonical_sha256":"45f0dc3ab3f7eca9a63fedd452739fb43fbf7326b1e701b73622fac70d8c3b04","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"45f0dc3ab3f7eca9a63fedd452739fb43fbf7326b1e701b73622fac70d8c3b04","first_computed_at":"2026-07-05T09:49:20.258660Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:49:20.258660Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eTv+s2qvKW9G77HerKtEuqFODgP/N56yT/4mFNQ5t06lVBcK7gFOfIqj7fkUd8mIvfM/6njFci0IVhxW3kznDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:49:20.259121Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.10713","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a5886a311ef00eeee04d5fcc8e8c76f3221a533dd9316c9c9c4c487a84fd6fd5","sha256:0bfbc58eb4c74e096e4dfe9c6b59723f2afda671472517dcb0de16cc7e8669b9"],"state_sha256":"291d1bda2e6a1c90d83665deb8d03d19f5a833b27f9d746df476d365c05baa23"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E2CHI7jdbcL8JEuDaWhjDYqy557cjJ3SsbjOVltcFCMwCGpvEUbqgtWgaJJkN0XXfdaNJ/DgzLxZXEaZVT42Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T14:07:39.610589Z","bundle_sha256":"0c480eedbdf3bbcaaa4ce1e389adfdc14df0a779069b89aff3478940e1e652c0"}}