{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GVK7FQMTWVGAUAFFQ536IG7H6Y","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":"464935306dc9b6a5446bea42f5d773f1da8583a974f2d9c7bc8285ce60de0523","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-19T01:37:45Z","title_canon_sha256":"c07f4e40c5bc8b4333323751815b805531b8859a5c7a34ad39a84f0c1590397a"},"schema_version":"1.0","source":{"id":"2603.18396","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.18396","created_at":"2026-05-20T00:01:40Z"},{"alias_kind":"arxiv_version","alias_value":"2603.18396v3","created_at":"2026-05-20T00:01:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.18396","created_at":"2026-05-20T00:01:40Z"},{"alias_kind":"pith_short_12","alias_value":"GVK7FQMTWVGA","created_at":"2026-05-20T00:01:40Z"},{"alias_kind":"pith_short_16","alias_value":"GVK7FQMTWVGAUAFF","created_at":"2026-05-20T00:01:40Z"},{"alias_kind":"pith_short_8","alias_value":"GVK7FQMT","created_at":"2026-05-20T00:01:40Z"}],"graph_snapshots":[{"event_id":"sha256:15a95d8e8d2d77d7cef65f0e71c166f660f107a010db6486b247dece26bdc6b3","target":"graph","created_at":"2026-05-20T00:01:40Z","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/2603.18396/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Bus holding control is challenging due to stochastic traffic and passenger demand. While deep reinforcement learning (DRL) shows promise, standard actor-critic algorithms suffer from Q-value instability in volatile environments. A key source of this instability is the conflation of two distinct uncertainties: aleatoric uncertainty (irreducible noise) and epistemic uncertainty (data insufficiency). Treating these as a single risk leads to value underestimation in noisy states, causing catastrophic policy collapse. We propose a robust ensemble soft actor-critic (RE-SAC) framework to explicitly d","authors_text":"Liang Zheng, Yifan Zhang","cross_cats":["cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-19T01:37:45Z","title":"RE-SAC: Disentangling aleatoric and epistemic risks in bus fleet control: A stable and robust ensemble DRL approach"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.18396","kind":"arxiv","version":3},"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":"sha256:195a5d54a30f790df56dc23ff042ff43b9fd383e76c5191db61d208fa8bdb963","target":"record","created_at":"2026-05-20T00:01:40Z","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":"464935306dc9b6a5446bea42f5d773f1da8583a974f2d9c7bc8285ce60de0523","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-03-19T01:37:45Z","title_canon_sha256":"c07f4e40c5bc8b4333323751815b805531b8859a5c7a34ad39a84f0c1590397a"},"schema_version":"1.0","source":{"id":"2603.18396","kind":"arxiv","version":3}},"canonical_sha256":"3555f2c193b54c0a00a58777e41be7f62eefc923e51c7892fd53ca82946730c6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3555f2c193b54c0a00a58777e41be7f62eefc923e51c7892fd53ca82946730c6","first_computed_at":"2026-05-20T00:01:40.251996Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:01:40.251996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7KDK+cwUy7Fijm0O3wtIlEr6N8+lgH60Ws8mY2wKbMljAhoYUZDQMt2uOY8isK9IQFaNxnEm/2QCeiux8uwZDQ==","signature_status":"signed_v1","signed_at":"2026-05-20T00:01:40.252571Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.18396","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:195a5d54a30f790df56dc23ff042ff43b9fd383e76c5191db61d208fa8bdb963","sha256:15a95d8e8d2d77d7cef65f0e71c166f660f107a010db6486b247dece26bdc6b3"],"state_sha256":"6f28668bfeb577c68e97e257e569a730172ace2548c6645450f2b9d0216cc29b"}