{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:DPRVM74NWXIISL4EZMY3KUMEVE","short_pith_number":"pith:DPRVM74N","canonical_record":{"source":{"id":"2003.12909","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-28T23:22:28Z","cross_cats_sorted":["cs.AI","cs.CR","stat.ML"],"title_canon_sha256":"9a19f7822c6817fe6483f6e47f6cb39f579fad5262cfeb94a1d3f7cb0713fd29","abstract_canon_sha256":"e672970894382258d7fa936991599e6b3a968738a45ff413a258cb54d1f087f7"},"schema_version":"1.0"},"canonical_sha256":"1be3567f8db5d0892f84cb31b55184a93ea54b3912d130b03cc7841c651b8bec","source":{"kind":"arxiv","id":"2003.12909","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.12909","created_at":"2026-07-05T01:28:19Z"},{"alias_kind":"arxiv_version","alias_value":"2003.12909v2","created_at":"2026-07-05T01:28:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.12909","created_at":"2026-07-05T01:28:19Z"},{"alias_kind":"pith_short_12","alias_value":"DPRVM74NWXII","created_at":"2026-07-05T01:28:19Z"},{"alias_kind":"pith_short_16","alias_value":"DPRVM74NWXIISL4E","created_at":"2026-07-05T01:28:19Z"},{"alias_kind":"pith_short_8","alias_value":"DPRVM74N","created_at":"2026-07-05T01:28:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:DPRVM74NWXIISL4EZMY3KUMEVE","target":"record","payload":{"canonical_record":{"source":{"id":"2003.12909","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-28T23:22:28Z","cross_cats_sorted":["cs.AI","cs.CR","stat.ML"],"title_canon_sha256":"9a19f7822c6817fe6483f6e47f6cb39f579fad5262cfeb94a1d3f7cb0713fd29","abstract_canon_sha256":"e672970894382258d7fa936991599e6b3a968738a45ff413a258cb54d1f087f7"},"schema_version":"1.0"},"canonical_sha256":"1be3567f8db5d0892f84cb31b55184a93ea54b3912d130b03cc7841c651b8bec","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:28:19.510282Z","signature_b64":"TL5Q3cqULS7qyUsks4ZCxmSJagBa5j49wW45vcxRReCX+/h0NlyNI5kcYvSdyBs2LgLcWMsb+q7/FyXXsZ8gAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1be3567f8db5d0892f84cb31b55184a93ea54b3912d130b03cc7841c651b8bec","last_reissued_at":"2026-07-05T01:28:19.509956Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:28:19.509956Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2003.12909","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":"2026-07-05T01:28:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Aecr53H/nf8D9yyKFvPItdBJ79RF++6esnoWCCambYiTMoWONM8obrRc3ZubDoFVOz8L2Md6eY86rH0awbK3CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T12:04:21.136082Z"},"content_sha256":"82dab636439605beb135e8ffb2407714a545ed6779e885b06a541bcc76f162a8","schema_version":"1.0","event_id":"sha256:82dab636439605beb135e8ffb2407714a545ed6779e885b06a541bcc76f162a8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:DPRVM74NWXIISL4EZMY3KUMEVE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Policy Teaching via Environment Poisoning: Training-time Adversarial Attacks against Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Adish Singla, Amin Rakhsha, Goran Radanovic, Rati Devidze, Xiaojin Zhu","submitted_at":"2020-03-28T23:22:28Z","abstract_excerpt":"We study a security threat to reinforcement learning where an attacker poisons the learning environment to force the agent into executing a target policy chosen by the attacker. As a victim, we consider RL agents whose objective is to find a policy that maximizes average reward in undiscounted infinite-horizon problem settings. The attacker can manipulate the rewards or the transition dynamics in the learning environment at training-time and is interested in doing so in a stealthy manner. We propose an optimization framework for finding an \\emph{optimal stealthy attack} for different measures "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.12909","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/2003.12909/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":"2026-07-05T01:28:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cYeD7WTg8anpjPerSqmFuo98ontqMX6THK2xm6ItaSpYzH9h5+++NQJDwrGTTVpxUvSqRLADHZEHDHURZTDzAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T12:04:21.136714Z"},"content_sha256":"c575a89f0927fb717ef8916c455d4df376d9ba83cecfc9ad1f71e884d0666deb","schema_version":"1.0","event_id":"sha256:c575a89f0927fb717ef8916c455d4df376d9ba83cecfc9ad1f71e884d0666deb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DPRVM74NWXIISL4EZMY3KUMEVE/bundle.json","state_url":"https://pith.science/pith/DPRVM74NWXIISL4EZMY3KUMEVE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DPRVM74NWXIISL4EZMY3KUMEVE/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":"2026-08-23T12:04:21Z","links":{"resolver":"https://pith.science/pith/DPRVM74NWXIISL4EZMY3KUMEVE","bundle":"https://pith.science/pith/DPRVM74NWXIISL4EZMY3KUMEVE/bundle.json","state":"https://pith.science/pith/DPRVM74NWXIISL4EZMY3KUMEVE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DPRVM74NWXIISL4EZMY3KUMEVE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:DPRVM74NWXIISL4EZMY3KUMEVE","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":"e672970894382258d7fa936991599e6b3a968738a45ff413a258cb54d1f087f7","cross_cats_sorted":["cs.AI","cs.CR","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-28T23:22:28Z","title_canon_sha256":"9a19f7822c6817fe6483f6e47f6cb39f579fad5262cfeb94a1d3f7cb0713fd29"},"schema_version":"1.0","source":{"id":"2003.12909","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.12909","created_at":"2026-07-05T01:28:19Z"},{"alias_kind":"arxiv_version","alias_value":"2003.12909v2","created_at":"2026-07-05T01:28:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.12909","created_at":"2026-07-05T01:28:19Z"},{"alias_kind":"pith_short_12","alias_value":"DPRVM74NWXII","created_at":"2026-07-05T01:28:19Z"},{"alias_kind":"pith_short_16","alias_value":"DPRVM74NWXIISL4E","created_at":"2026-07-05T01:28:19Z"},{"alias_kind":"pith_short_8","alias_value":"DPRVM74N","created_at":"2026-07-05T01:28:19Z"}],"graph_snapshots":[{"event_id":"sha256:c575a89f0927fb717ef8916c455d4df376d9ba83cecfc9ad1f71e884d0666deb","target":"graph","created_at":"2026-07-05T01:28:19Z","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/2003.12909/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study a security threat to reinforcement learning where an attacker poisons the learning environment to force the agent into executing a target policy chosen by the attacker. As a victim, we consider RL agents whose objective is to find a policy that maximizes average reward in undiscounted infinite-horizon problem settings. The attacker can manipulate the rewards or the transition dynamics in the learning environment at training-time and is interested in doing so in a stealthy manner. We propose an optimization framework for finding an \\emph{optimal stealthy attack} for different measures ","authors_text":"Adish Singla, Amin Rakhsha, Goran Radanovic, Rati Devidze, Xiaojin Zhu","cross_cats":["cs.AI","cs.CR","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-28T23:22:28Z","title":"Policy Teaching via Environment Poisoning: Training-time Adversarial Attacks against Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.12909","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":"sha256:82dab636439605beb135e8ffb2407714a545ed6779e885b06a541bcc76f162a8","target":"record","created_at":"2026-07-05T01:28:19Z","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":"e672970894382258d7fa936991599e6b3a968738a45ff413a258cb54d1f087f7","cross_cats_sorted":["cs.AI","cs.CR","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-28T23:22:28Z","title_canon_sha256":"9a19f7822c6817fe6483f6e47f6cb39f579fad5262cfeb94a1d3f7cb0713fd29"},"schema_version":"1.0","source":{"id":"2003.12909","kind":"arxiv","version":2}},"canonical_sha256":"1be3567f8db5d0892f84cb31b55184a93ea54b3912d130b03cc7841c651b8bec","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1be3567f8db5d0892f84cb31b55184a93ea54b3912d130b03cc7841c651b8bec","first_computed_at":"2026-07-05T01:28:19.509956Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:28:19.509956Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TL5Q3cqULS7qyUsks4ZCxmSJagBa5j49wW45vcxRReCX+/h0NlyNI5kcYvSdyBs2LgLcWMsb+q7/FyXXsZ8gAA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:28:19.510282Z","signed_message":"canonical_sha256_bytes"},"source_id":"2003.12909","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:82dab636439605beb135e8ffb2407714a545ed6779e885b06a541bcc76f162a8","sha256:c575a89f0927fb717ef8916c455d4df376d9ba83cecfc9ad1f71e884d0666deb"],"state_sha256":"0c3dc7f5b64173ee66b7c75967d5fe6b28964e27a76a1c3b7c850c32b1e5fda6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fbzCl2G6bD3lmrhLfEtT4JS5fv3OE2/Z2nL3CEgCo0wHym8MGGlNJRZ+uUiNPT46KgHryAs20Mhx9HGIUuUsAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T12:04:21.139888Z","bundle_sha256":"7faf57e1c113cd1c2feb5558ba83b3b910bc56a0fb372e4ff39db0cc01d73728"}}