{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:3OD7622KO55DOJL54DJIANV4AX","short_pith_number":"pith:3OD7622K","canonical_record":{"source":{"id":"1810.01032","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-02T01:43:45Z","cross_cats_sorted":["cs.CR","cs.CV","stat.ML"],"title_canon_sha256":"19e5d56b4df0ae5a19cbeb662c7bf725ba1ab4e0055d7c92e96fda721746b31a","abstract_canon_sha256":"a733d9a8ae186dddf8c27fe4e9428372e0a5172eb692eeefd42b8b661ac7ed04"},"schema_version":"1.0"},"canonical_sha256":"db87ff6b4a777a37257de0d28036bc05ff250d874130cfb40f40d9b0bb96433f","source":{"kind":"arxiv","id":"1810.01032","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.01032","created_at":"2026-07-05T00:37:43Z"},{"alias_kind":"arxiv_version","alias_value":"1810.01032v4","created_at":"2026-07-05T00:37:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.01032","created_at":"2026-07-05T00:37:43Z"},{"alias_kind":"pith_short_12","alias_value":"3OD7622KO55D","created_at":"2026-07-05T00:37:43Z"},{"alias_kind":"pith_short_16","alias_value":"3OD7622KO55DOJL5","created_at":"2026-07-05T00:37:43Z"},{"alias_kind":"pith_short_8","alias_value":"3OD7622K","created_at":"2026-07-05T00:37:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:3OD7622KO55DOJL54DJIANV4AX","target":"record","payload":{"canonical_record":{"source":{"id":"1810.01032","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-02T01:43:45Z","cross_cats_sorted":["cs.CR","cs.CV","stat.ML"],"title_canon_sha256":"19e5d56b4df0ae5a19cbeb662c7bf725ba1ab4e0055d7c92e96fda721746b31a","abstract_canon_sha256":"a733d9a8ae186dddf8c27fe4e9428372e0a5172eb692eeefd42b8b661ac7ed04"},"schema_version":"1.0"},"canonical_sha256":"db87ff6b4a777a37257de0d28036bc05ff250d874130cfb40f40d9b0bb96433f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:37:43.407496Z","signature_b64":"qKBq6Q9br3ElV21eKsJCndCw8em5nnnTCofF2tgVFMYPpywSqrf2CNJEra5nejqb74P7DjgxgstltPZUJmX0Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db87ff6b4a777a37257de0d28036bc05ff250d874130cfb40f40d9b0bb96433f","last_reissued_at":"2026-07-05T00:37:43.407083Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:37:43.407083Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.01032","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:37:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a9hUmJG0Zudpq8R4V4eYDYc4P3oZqDjxRTp6qyAX3rijDbTD+AgyLmz4UhL7irFZ+xvzTb5Qlbq4nWMVhGbBDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T07:41:38.044834Z"},"content_sha256":"bb6faac00d44e826200b8dbbfc762547bdef8373bc21626f809584d1531e2f6d","schema_version":"1.0","event_id":"sha256:bb6faac00d44e826200b8dbbfc762547bdef8373bc21626f809584d1531e2f6d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:3OD7622KO55DOJL54DJIANV4AX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reinforcement Learning with Perturbed Rewards","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bo Li, Jingkang Wang, Yang Liu","submitted_at":"2018-10-02T01:43:45Z","abstract_excerpt":"Recent studies have shown that reinforcement learning (RL) models are vulnerable in various noisy scenarios. For instance, the observed reward channel is often subject to noise in practice (e.g., when rewards are collected through sensors), and is therefore not credible. In addition, for applications such as robotics, a deep reinforcement learning (DRL) algorithm can be manipulated to produce arbitrary errors by receiving corrupted rewards. In this paper, we consider noisy RL problems with perturbed rewards, which can be approximated with a confusion matrix. We develop a robust RL framework th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.01032","kind":"arxiv","version":4},"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/1810.01032/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":"2026-07-05T00:37:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mhvCntc9cq2UZCD4+JuMFJe/EiCP6WJtzBTCqUArnxwfdXoYPH6d816PD3BPMVEFliV5ruG3XmupC3HNc4IhDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T07:41:38.045211Z"},"content_sha256":"3857c3b53cdeb39676143296d7e949c83ba329797ceca2ff8125055b49e2da57","schema_version":"1.0","event_id":"sha256:3857c3b53cdeb39676143296d7e949c83ba329797ceca2ff8125055b49e2da57"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3OD7622KO55DOJL54DJIANV4AX/bundle.json","state_url":"https://pith.science/pith/3OD7622KO55DOJL54DJIANV4AX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3OD7622KO55DOJL54DJIANV4AX/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":"2026-07-05T07:41:38Z","links":{"resolver":"https://pith.science/pith/3OD7622KO55DOJL54DJIANV4AX","bundle":"https://pith.science/pith/3OD7622KO55DOJL54DJIANV4AX/bundle.json","state":"https://pith.science/pith/3OD7622KO55DOJL54DJIANV4AX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3OD7622KO55DOJL54DJIANV4AX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:3OD7622KO55DOJL54DJIANV4AX","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":"a733d9a8ae186dddf8c27fe4e9428372e0a5172eb692eeefd42b8b661ac7ed04","cross_cats_sorted":["cs.CR","cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-02T01:43:45Z","title_canon_sha256":"19e5d56b4df0ae5a19cbeb662c7bf725ba1ab4e0055d7c92e96fda721746b31a"},"schema_version":"1.0","source":{"id":"1810.01032","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.01032","created_at":"2026-07-05T00:37:43Z"},{"alias_kind":"arxiv_version","alias_value":"1810.01032v4","created_at":"2026-07-05T00:37:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.01032","created_at":"2026-07-05T00:37:43Z"},{"alias_kind":"pith_short_12","alias_value":"3OD7622KO55D","created_at":"2026-07-05T00:37:43Z"},{"alias_kind":"pith_short_16","alias_value":"3OD7622KO55DOJL5","created_at":"2026-07-05T00:37:43Z"},{"alias_kind":"pith_short_8","alias_value":"3OD7622K","created_at":"2026-07-05T00:37:43Z"}],"graph_snapshots":[{"event_id":"sha256:3857c3b53cdeb39676143296d7e949c83ba329797ceca2ff8125055b49e2da57","target":"graph","created_at":"2026-07-05T00:37:43Z","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/1810.01032/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent studies have shown that reinforcement learning (RL) models are vulnerable in various noisy scenarios. For instance, the observed reward channel is often subject to noise in practice (e.g., when rewards are collected through sensors), and is therefore not credible. In addition, for applications such as robotics, a deep reinforcement learning (DRL) algorithm can be manipulated to produce arbitrary errors by receiving corrupted rewards. In this paper, we consider noisy RL problems with perturbed rewards, which can be approximated with a confusion matrix. We develop a robust RL framework th","authors_text":"Bo Li, Jingkang Wang, Yang Liu","cross_cats":["cs.CR","cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-02T01:43:45Z","title":"Reinforcement Learning with Perturbed Rewards"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.01032","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:bb6faac00d44e826200b8dbbfc762547bdef8373bc21626f809584d1531e2f6d","target":"record","created_at":"2026-07-05T00:37:43Z","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":"a733d9a8ae186dddf8c27fe4e9428372e0a5172eb692eeefd42b8b661ac7ed04","cross_cats_sorted":["cs.CR","cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-02T01:43:45Z","title_canon_sha256":"19e5d56b4df0ae5a19cbeb662c7bf725ba1ab4e0055d7c92e96fda721746b31a"},"schema_version":"1.0","source":{"id":"1810.01032","kind":"arxiv","version":4}},"canonical_sha256":"db87ff6b4a777a37257de0d28036bc05ff250d874130cfb40f40d9b0bb96433f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"db87ff6b4a777a37257de0d28036bc05ff250d874130cfb40f40d9b0bb96433f","first_computed_at":"2026-07-05T00:37:43.407083Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:37:43.407083Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qKBq6Q9br3ElV21eKsJCndCw8em5nnnTCofF2tgVFMYPpywSqrf2CNJEra5nejqb74P7DjgxgstltPZUJmX0Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:37:43.407496Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.01032","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bb6faac00d44e826200b8dbbfc762547bdef8373bc21626f809584d1531e2f6d","sha256:3857c3b53cdeb39676143296d7e949c83ba329797ceca2ff8125055b49e2da57"],"state_sha256":"01ff3dc81217f9721b7c98efa326dc7554e4e31a2eb61895453f4ee7d77b7c38"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jACB9GQGOvwWBHbMlM8fA8wU1kTC56ZUOcFKLw15UdZlQsDTNjjAslU806RKpAKZcWNk7sS+5jkFVtIaFThQCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T07:41:38.047265Z","bundle_sha256":"6e11a9ef125fd359c7979f52a1642e93933587a464fe7e13d6779c18685a536f"}}