{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6NUXOKEAB6CGBNAKGAPGEDKLNF","short_pith_number":"pith:6NUXOKEA","schema_version":"1.0","canonical_sha256":"f3697728800f8460b40a301e620d4b697042ebf66a4cf8898765ebf2e25c19be","source":{"kind":"arxiv","id":"2412.01033","version":1},"attestation_state":"computed","paper":{"title":"SAUP: Situation Awareness Uncertainty Propagation on LLM Agent","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Haifeng Chen, Huaxiu Yao, Katsushi Matsuda, Mika Oishi, Qiwei Zhao, Takao Osaki, Wei Cheng, Xujiang Zhao, Yanchi Liu, Yiyou Sun","submitted_at":"2024-12-02T01:31:13Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2412.01033","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-02T01:31:13Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a919ebd1aaa70255f6a3b679778dd733c934e95875fafef525cdeb3792f3fc41","abstract_canon_sha256":"6fbe26065ecdf66968e88b4c4ac1527ea394faa61ee7e81b17f95ee6b08986ec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:52.457382Z","signature_b64":"h4p8aFbgqPJx5+dvsKGTdB1SwE0einUr+ohwk94dEcVGg5P5EOWWPXFvOg/DU/5Qpk1uAOAArnfMYH8zVCULBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f3697728800f8460b40a301e620d4b697042ebf66a4cf8898765ebf2e25c19be","last_reissued_at":"2026-07-05T09:42:52.456866Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:52.456866Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SAUP: Situation Awareness Uncertainty Propagation on LLM Agent","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Haifeng Chen, Huaxiu Yao, Katsushi Matsuda, Mika Oishi, Qiwei Zhao, Takao Osaki, Wei Cheng, Xujiang Zhao, Yanchi Liu, Yiyou Sun","submitted_at":"2024-12-02T01:31:13Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.01033","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/2412.01033/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2412.01033","created_at":"2026-07-05T09:42:52.456935+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.01033v1","created_at":"2026-07-05T09:42:52.456935+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01033","created_at":"2026-07-05T09:42:52.456935+00:00"},{"alias_kind":"pith_short_12","alias_value":"6NUXOKEAB6CG","created_at":"2026-07-05T09:42:52.456935+00:00"},{"alias_kind":"pith_short_16","alias_value":"6NUXOKEAB6CGBNAK","created_at":"2026-07-05T09:42:52.456935+00:00"},{"alias_kind":"pith_short_8","alias_value":"6NUXOKEA","created_at":"2026-07-05T09:42:52.456935+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20662","citing_title":"Confidence Laundering in Agent Systems: Why Uncertainty Needs a Latent Carrier","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24756","citing_title":"Proper Scoring Rules for Agentic Uncertainty Quantification","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26835","citing_title":"Helicase: Uncertainty-Guided Supply Chain Knowledge Graph Construction with Autonomous Multi-Agent LLMs","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6NUXOKEAB6CGBNAKGAPGEDKLNF","json":"https://pith.science/pith/6NUXOKEAB6CGBNAKGAPGEDKLNF.json","graph_json":"https://pith.science/api/pith-number/6NUXOKEAB6CGBNAKGAPGEDKLNF/graph.json","events_json":"https://pith.science/api/pith-number/6NUXOKEAB6CGBNAKGAPGEDKLNF/events.json","paper":"https://pith.science/paper/6NUXOKEA"},"agent_actions":{"view_html":"https://pith.science/pith/6NUXOKEAB6CGBNAKGAPGEDKLNF","download_json":"https://pith.science/pith/6NUXOKEAB6CGBNAKGAPGEDKLNF.json","view_paper":"https://pith.science/paper/6NUXOKEA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.01033&json=true","fetch_graph":"https://pith.science/api/pith-number/6NUXOKEAB6CGBNAKGAPGEDKLNF/graph.json","fetch_events":"https://pith.science/api/pith-number/6NUXOKEAB6CGBNAKGAPGEDKLNF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6NUXOKEAB6CGBNAKGAPGEDKLNF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6NUXOKEAB6CGBNAKGAPGEDKLNF/action/storage_attestation","attest_author":"https://pith.science/pith/6NUXOKEAB6CGBNAKGAPGEDKLNF/action/author_attestation","sign_citation":"https://pith.science/pith/6NUXOKEAB6CGBNAKGAPGEDKLNF/action/citation_signature","submit_replication":"https://pith.science/pith/6NUXOKEAB6CGBNAKGAPGEDKLNF/action/replication_record"}},"created_at":"2026-07-05T09:42:52.456935+00:00","updated_at":"2026-07-05T09:42:52.456935+00:00"}