{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6NUXOKEAB6CGBNAKGAPGEDKLNF","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":"6fbe26065ecdf66968e88b4c4ac1527ea394faa61ee7e81b17f95ee6b08986ec","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-02T01:31:13Z","title_canon_sha256":"a919ebd1aaa70255f6a3b679778dd733c934e95875fafef525cdeb3792f3fc41"},"schema_version":"1.0","source":{"id":"2412.01033","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.01033","created_at":"2026-07-05T09:42:52Z"},{"alias_kind":"arxiv_version","alias_value":"2412.01033v1","created_at":"2026-07-05T09:42:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01033","created_at":"2026-07-05T09:42:52Z"},{"alias_kind":"pith_short_12","alias_value":"6NUXOKEAB6CG","created_at":"2026-07-05T09:42:52Z"},{"alias_kind":"pith_short_16","alias_value":"6NUXOKEAB6CGBNAK","created_at":"2026-07-05T09:42:52Z"},{"alias_kind":"pith_short_8","alias_value":"6NUXOKEA","created_at":"2026-07-05T09:42:52Z"}],"graph_snapshots":[{"event_id":"sha256:cb9da76d7785d0ad3370d805bc34e22e82cf16ab6665f88d53ab5cf9937e83c7","target":"graph","created_at":"2026-07-05T09:42:52Z","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/2412.01033/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) integrated into multistep agent systems enable complex decision-making processes across various applications. However, their outputs often lack reliability, making uncertainty estimation crucial. Existing uncertainty estimation methods primarily focus on final-step outputs, which fail to account for cumulative uncertainty over the multistep decision-making process and the dynamic interactions between agents and their environments. To address these limitations, we propose SAUP (Situation Awareness Uncertainty Propagation), a novel framework that propagates uncertain","authors_text":"Haifeng Chen, Huaxiu Yao, Katsushi Matsuda, Mika Oishi, Qiwei Zhao, Takao Osaki, Wei Cheng, Xujiang Zhao, Yanchi Liu, Yiyou Sun","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-02T01:31:13Z","title":"SAUP: Situation Awareness Uncertainty Propagation on LLM Agent"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.01033","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":"sha256:26af385684521135b225eb4eeb3a6226725fb9dca8f24db1c67444beec321b8a","target":"record","created_at":"2026-07-05T09:42:52Z","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":"6fbe26065ecdf66968e88b4c4ac1527ea394faa61ee7e81b17f95ee6b08986ec","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-02T01:31:13Z","title_canon_sha256":"a919ebd1aaa70255f6a3b679778dd733c934e95875fafef525cdeb3792f3fc41"},"schema_version":"1.0","source":{"id":"2412.01033","kind":"arxiv","version":1}},"canonical_sha256":"f3697728800f8460b40a301e620d4b697042ebf66a4cf8898765ebf2e25c19be","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f3697728800f8460b40a301e620d4b697042ebf66a4cf8898765ebf2e25c19be","first_computed_at":"2026-07-05T09:42:52.456866Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:42:52.456866Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"h4p8aFbgqPJx5+dvsKGTdB1SwE0einUr+ohwk94dEcVGg5P5EOWWPXFvOg/DU/5Qpk1uAOAArnfMYH8zVCULBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:42:52.457382Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.01033","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:26af385684521135b225eb4eeb3a6226725fb9dca8f24db1c67444beec321b8a","sha256:cb9da76d7785d0ad3370d805bc34e22e82cf16ab6665f88d53ab5cf9937e83c7"],"state_sha256":"5966fa58b44f9f0bbecc28dcc7c906651da1af7f38b8609efdcd3982316643ef"}