{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:7HQQ52CGOA6DJAUBGOGPNAKV54","short_pith_number":"pith:7HQQ52CG","canonical_record":{"source":{"id":"2102.06587","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-12T15:53:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bd8673c909de38ec484e7e3878a5a8d971264e4fbb2181c9170d40a0b77ecbcb","abstract_canon_sha256":"96a4272cd50fb9329553ed76046d016f0e319809e2151a86df2af5cf5d862559"},"schema_version":"1.0"},"canonical_sha256":"f9e10ee846703c348281338cf68155ef1bde8cb31371c78f1b631e3ef37c59d0","source":{"kind":"arxiv","id":"2102.06587","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.06587","created_at":"2026-07-05T02:14:49Z"},{"alias_kind":"arxiv_version","alias_value":"2102.06587v1","created_at":"2026-07-05T02:14:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.06587","created_at":"2026-07-05T02:14:49Z"},{"alias_kind":"pith_short_12","alias_value":"7HQQ52CGOA6D","created_at":"2026-07-05T02:14:49Z"},{"alias_kind":"pith_short_16","alias_value":"7HQQ52CGOA6DJAUB","created_at":"2026-07-05T02:14:49Z"},{"alias_kind":"pith_short_8","alias_value":"7HQQ52CG","created_at":"2026-07-05T02:14:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:7HQQ52CGOA6DJAUBGOGPNAKV54","target":"record","payload":{"canonical_record":{"source":{"id":"2102.06587","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-12T15:53:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bd8673c909de38ec484e7e3878a5a8d971264e4fbb2181c9170d40a0b77ecbcb","abstract_canon_sha256":"96a4272cd50fb9329553ed76046d016f0e319809e2151a86df2af5cf5d862559"},"schema_version":"1.0"},"canonical_sha256":"f9e10ee846703c348281338cf68155ef1bde8cb31371c78f1b631e3ef37c59d0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:14:49.635366Z","signature_b64":"dXPBmZFno6L9UGX7+uFWc1VqUX2xbqt1GEza42scaamhIu2TvuVpTKz/pBCD/YrxopKT0GG32r77vXqlwaBQBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9e10ee846703c348281338cf68155ef1bde8cb31371c78f1b631e3ef37c59d0","last_reissued_at":"2026-07-05T02:14:49.634818Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:14:49.634818Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2102.06587","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":"2026-07-05T02:14:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"66CDV4r9geqOxLPMDda1ggfcwAgkxKzWvaax9tctPzXG1Ir8rxcDhwk3lhPOW01r74nZsAnkDsOqdG83V1BnBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T19:39:49.555985Z"},"content_sha256":"2c395418e65d63c4b086e0aaf050a47be339fed5fd15bb89b08436ee39976027","schema_version":"1.0","event_id":"sha256:2c395418e65d63c4b086e0aaf050a47be339fed5fd15bb89b08436ee39976027"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:7HQQ52CGOA6DJAUBGOGPNAKV54","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Disturbing Reinforcement Learning Agents with Corrupted Rewards","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Fernando Fern\\'andez, Javier Garc\\'ia, Rub\\'en Majadas","submitted_at":"2021-02-12T15:53:48Z","abstract_excerpt":"Reinforcement Learning (RL) algorithms have led to recent successes in solving complex games, such as Atari or Starcraft, and to a huge impact in real-world applications, such as cybersecurity or autonomous driving. In the side of the drawbacks, recent works have shown how the performance of RL algorithms decreases under the influence of soft changes in the reward function. However, little work has been done about how sensitive these disturbances are depending on the aggressiveness of the attack and the learning exploration strategy. In this paper, we propose to fill this gap in the literature"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.06587","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/2102.06587/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":"2026-07-05T02:14:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DDevKRNZzzF5qPhUllaNLsDfdN/YNiiCn7HX4dX6BCsOm5DfYhoM47R51eSZ59ZPAmD+eX0obx+285op/r/ZAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T19:39:49.556694Z"},"content_sha256":"52b6bfcf717f87cc7d67bf7e6e58f6c5a94cbd52c35ca5ff057d717064cf435a","schema_version":"1.0","event_id":"sha256:52b6bfcf717f87cc7d67bf7e6e58f6c5a94cbd52c35ca5ff057d717064cf435a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7HQQ52CGOA6DJAUBGOGPNAKV54/bundle.json","state_url":"https://pith.science/pith/7HQQ52CGOA6DJAUBGOGPNAKV54/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7HQQ52CGOA6DJAUBGOGPNAKV54/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":"2026-08-13T19:39:49Z","links":{"resolver":"https://pith.science/pith/7HQQ52CGOA6DJAUBGOGPNAKV54","bundle":"https://pith.science/pith/7HQQ52CGOA6DJAUBGOGPNAKV54/bundle.json","state":"https://pith.science/pith/7HQQ52CGOA6DJAUBGOGPNAKV54/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7HQQ52CGOA6DJAUBGOGPNAKV54/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:7HQQ52CGOA6DJAUBGOGPNAKV54","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":"96a4272cd50fb9329553ed76046d016f0e319809e2151a86df2af5cf5d862559","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-12T15:53:48Z","title_canon_sha256":"bd8673c909de38ec484e7e3878a5a8d971264e4fbb2181c9170d40a0b77ecbcb"},"schema_version":"1.0","source":{"id":"2102.06587","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.06587","created_at":"2026-07-05T02:14:49Z"},{"alias_kind":"arxiv_version","alias_value":"2102.06587v1","created_at":"2026-07-05T02:14:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.06587","created_at":"2026-07-05T02:14:49Z"},{"alias_kind":"pith_short_12","alias_value":"7HQQ52CGOA6D","created_at":"2026-07-05T02:14:49Z"},{"alias_kind":"pith_short_16","alias_value":"7HQQ52CGOA6DJAUB","created_at":"2026-07-05T02:14:49Z"},{"alias_kind":"pith_short_8","alias_value":"7HQQ52CG","created_at":"2026-07-05T02:14:49Z"}],"graph_snapshots":[{"event_id":"sha256:52b6bfcf717f87cc7d67bf7e6e58f6c5a94cbd52c35ca5ff057d717064cf435a","target":"graph","created_at":"2026-07-05T02:14:49Z","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/2102.06587/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning (RL) algorithms have led to recent successes in solving complex games, such as Atari or Starcraft, and to a huge impact in real-world applications, such as cybersecurity or autonomous driving. In the side of the drawbacks, recent works have shown how the performance of RL algorithms decreases under the influence of soft changes in the reward function. However, little work has been done about how sensitive these disturbances are depending on the aggressiveness of the attack and the learning exploration strategy. In this paper, we propose to fill this gap in the literature","authors_text":"Fernando Fern\\'andez, Javier Garc\\'ia, Rub\\'en Majadas","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-12T15:53:48Z","title":"Disturbing Reinforcement Learning Agents with Corrupted Rewards"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.06587","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":"sha256:2c395418e65d63c4b086e0aaf050a47be339fed5fd15bb89b08436ee39976027","target":"record","created_at":"2026-07-05T02:14:49Z","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":"96a4272cd50fb9329553ed76046d016f0e319809e2151a86df2af5cf5d862559","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-12T15:53:48Z","title_canon_sha256":"bd8673c909de38ec484e7e3878a5a8d971264e4fbb2181c9170d40a0b77ecbcb"},"schema_version":"1.0","source":{"id":"2102.06587","kind":"arxiv","version":1}},"canonical_sha256":"f9e10ee846703c348281338cf68155ef1bde8cb31371c78f1b631e3ef37c59d0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f9e10ee846703c348281338cf68155ef1bde8cb31371c78f1b631e3ef37c59d0","first_computed_at":"2026-07-05T02:14:49.634818Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:14:49.634818Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dXPBmZFno6L9UGX7+uFWc1VqUX2xbqt1GEza42scaamhIu2TvuVpTKz/pBCD/YrxopKT0GG32r77vXqlwaBQBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:14:49.635366Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.06587","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2c395418e65d63c4b086e0aaf050a47be339fed5fd15bb89b08436ee39976027","sha256:52b6bfcf717f87cc7d67bf7e6e58f6c5a94cbd52c35ca5ff057d717064cf435a"],"state_sha256":"2a54b74250f537d548f8b3fe01826427d67f1aac7f26700166525d69229989e5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"81Xy+SNzPW220u66jkm5LXMYIk3jKSMTnBIZg5w7l2m4uId6TPyaJqWY8agmQ+FZV2NNyUKHVTim4Oxl5C5CCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T19:39:49.571077Z","bundle_sha256":"8607c7d6dedfd34fd5a60dc19942c19d78c13d98e3b37eed5316cfd68b23c2b8"}}