{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:AZZZ3COPHEKTNZDQ7VLATT6662","short_pith_number":"pith:AZZZ3COP","canonical_record":{"source":{"id":"2411.00465","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-01T09:28:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8d37c26da2111a5bfc522fe4fafe7b046327b5199fd2a2bbfc7ab9a700574621","abstract_canon_sha256":"34b33b8937203d40a05ebc6e0444fe81f1fb9ecc5f7875d2203446ef5eac6784"},"schema_version":"1.0"},"canonical_sha256":"06739d89cf391536e470fd5609cfdef68328b47cba307b9e257effad1bbce250","source":{"kind":"arxiv","id":"2411.00465","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.00465","created_at":"2026-07-05T09:29:42Z"},{"alias_kind":"arxiv_version","alias_value":"2411.00465v1","created_at":"2026-07-05T09:29:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.00465","created_at":"2026-07-05T09:29:42Z"},{"alias_kind":"pith_short_12","alias_value":"AZZZ3COPHEKT","created_at":"2026-07-05T09:29:42Z"},{"alias_kind":"pith_short_16","alias_value":"AZZZ3COPHEKTNZDQ","created_at":"2026-07-05T09:29:42Z"},{"alias_kind":"pith_short_8","alias_value":"AZZZ3COP","created_at":"2026-07-05T09:29:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:AZZZ3COPHEKTNZDQ7VLATT6662","target":"record","payload":{"canonical_record":{"source":{"id":"2411.00465","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-01T09:28:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8d37c26da2111a5bfc522fe4fafe7b046327b5199fd2a2bbfc7ab9a700574621","abstract_canon_sha256":"34b33b8937203d40a05ebc6e0444fe81f1fb9ecc5f7875d2203446ef5eac6784"},"schema_version":"1.0"},"canonical_sha256":"06739d89cf391536e470fd5609cfdef68328b47cba307b9e257effad1bbce250","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:29:42.995101Z","signature_b64":"gXi+i4fQRfKcLNg7Lt11pKEKkFyalERKXr/PSK+kzxz4ZKFjZ+WYqmTqxBLrsXIKiaGsLewl26xEmJPtBBugBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"06739d89cf391536e470fd5609cfdef68328b47cba307b9e257effad1bbce250","last_reissued_at":"2026-07-05T09:29:42.994765Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:29:42.994765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.00465","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":"2026-07-05T09:29:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5mV//N6vpcNy9arFwF6JTu8F987+6BiNDWSCke63c1W0+cE87WV5bo+yFgOe9CIw9lvcDQUzNiDrAxPBXAUwBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T22:38:23.351546Z"},"content_sha256":"f8a88c0c425b3ca5a56521901ce2636ff5e24c8546d12d7b2c8edfa47e2487cd","schema_version":"1.0","event_id":"sha256:f8a88c0c425b3ca5a56521901ce2636ff5e24c8546d12d7b2c8edfa47e2487cd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:AZZZ3COPHEKTNZDQ7VLATT6662","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Uncertainty-based Offline Variational Bayesian Reinforcement Learning for Robustness under Diverse Data Corruptions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bin Li, Guoping Wu, Jie Wang, Rui Yang","submitted_at":"2024-11-01T09:28:24Z","abstract_excerpt":"Real-world offline datasets are often subject to data corruptions (such as noise or adversarial attacks) due to sensor failures or malicious attacks. Despite advances in robust offline reinforcement learning (RL), existing methods struggle to learn robust agents under high uncertainty caused by the diverse corrupted data (i.e., corrupted states, actions, rewards, and dynamics), leading to performance degradation in clean environments. To tackle this problem, we propose a novel robust variational Bayesian inference for offline RL (TRACER). It introduces Bayesian inference for the first time to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.00465","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/2411.00465/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":"2026-07-05T09:29:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e6f9EV8Z4qaMqMFBY2mr+9+Cypl9AZg0k5kglI36W6q2p8UqPe0v71cyQPWJuWyM3m5KJyMh2wsejZOYzvlnDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T22:38:23.352069Z"},"content_sha256":"97f5b8d98a28d94c261a4f08ab71b590f715bfc4e3c9fa5da04554f1999e896b","schema_version":"1.0","event_id":"sha256:97f5b8d98a28d94c261a4f08ab71b590f715bfc4e3c9fa5da04554f1999e896b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AZZZ3COPHEKTNZDQ7VLATT6662/bundle.json","state_url":"https://pith.science/pith/AZZZ3COPHEKTNZDQ7VLATT6662/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AZZZ3COPHEKTNZDQ7VLATT6662/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":"2026-08-12T22:38:23Z","links":{"resolver":"https://pith.science/pith/AZZZ3COPHEKTNZDQ7VLATT6662","bundle":"https://pith.science/pith/AZZZ3COPHEKTNZDQ7VLATT6662/bundle.json","state":"https://pith.science/pith/AZZZ3COPHEKTNZDQ7VLATT6662/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AZZZ3COPHEKTNZDQ7VLATT6662/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AZZZ3COPHEKTNZDQ7VLATT6662","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":"34b33b8937203d40a05ebc6e0444fe81f1fb9ecc5f7875d2203446ef5eac6784","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-01T09:28:24Z","title_canon_sha256":"8d37c26da2111a5bfc522fe4fafe7b046327b5199fd2a2bbfc7ab9a700574621"},"schema_version":"1.0","source":{"id":"2411.00465","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.00465","created_at":"2026-07-05T09:29:42Z"},{"alias_kind":"arxiv_version","alias_value":"2411.00465v1","created_at":"2026-07-05T09:29:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.00465","created_at":"2026-07-05T09:29:42Z"},{"alias_kind":"pith_short_12","alias_value":"AZZZ3COPHEKT","created_at":"2026-07-05T09:29:42Z"},{"alias_kind":"pith_short_16","alias_value":"AZZZ3COPHEKTNZDQ","created_at":"2026-07-05T09:29:42Z"},{"alias_kind":"pith_short_8","alias_value":"AZZZ3COP","created_at":"2026-07-05T09:29:42Z"}],"graph_snapshots":[{"event_id":"sha256:97f5b8d98a28d94c261a4f08ab71b590f715bfc4e3c9fa5da04554f1999e896b","target":"graph","created_at":"2026-07-05T09:29:42Z","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/2411.00465/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Real-world offline datasets are often subject to data corruptions (such as noise or adversarial attacks) due to sensor failures or malicious attacks. Despite advances in robust offline reinforcement learning (RL), existing methods struggle to learn robust agents under high uncertainty caused by the diverse corrupted data (i.e., corrupted states, actions, rewards, and dynamics), leading to performance degradation in clean environments. To tackle this problem, we propose a novel robust variational Bayesian inference for offline RL (TRACER). It introduces Bayesian inference for the first time to ","authors_text":"Bin Li, Guoping Wu, Jie Wang, Rui Yang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-01T09:28:24Z","title":"Uncertainty-based Offline Variational Bayesian Reinforcement Learning for Robustness under Diverse Data Corruptions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.00465","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:f8a88c0c425b3ca5a56521901ce2636ff5e24c8546d12d7b2c8edfa47e2487cd","target":"record","created_at":"2026-07-05T09:29:42Z","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":"34b33b8937203d40a05ebc6e0444fe81f1fb9ecc5f7875d2203446ef5eac6784","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-11-01T09:28:24Z","title_canon_sha256":"8d37c26da2111a5bfc522fe4fafe7b046327b5199fd2a2bbfc7ab9a700574621"},"schema_version":"1.0","source":{"id":"2411.00465","kind":"arxiv","version":1}},"canonical_sha256":"06739d89cf391536e470fd5609cfdef68328b47cba307b9e257effad1bbce250","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"06739d89cf391536e470fd5609cfdef68328b47cba307b9e257effad1bbce250","first_computed_at":"2026-07-05T09:29:42.994765Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:29:42.994765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gXi+i4fQRfKcLNg7Lt11pKEKkFyalERKXr/PSK+kzxz4ZKFjZ+WYqmTqxBLrsXIKiaGsLewl26xEmJPtBBugBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:29:42.995101Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.00465","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f8a88c0c425b3ca5a56521901ce2636ff5e24c8546d12d7b2c8edfa47e2487cd","sha256:97f5b8d98a28d94c261a4f08ab71b590f715bfc4e3c9fa5da04554f1999e896b"],"state_sha256":"ae34dad6ad44d39d34d39abce5e94d11a2db8820ef9d05eba45fd8455058702d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P+OC4T7FZEMhOoTBJyAreSuhRxXxl0CetRnLcIoZQopz9XDpR74qwgigDmqRpYokS7ga4OKpfD3/S+NSstLzBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T22:38:23.365275Z","bundle_sha256":"c39f4780d3fb2440c3d43102346c922612a468c5dd8d01aab6939560ce822c97"}}