{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CQZUJMPOZFDZBJTZ3QT5LKXRGC","short_pith_number":"pith:CQZUJMPO","schema_version":"1.0","canonical_sha256":"143344b1eec94790a679dc27d5aaf130960b789ad380d187584e16157f44efe3","source":{"kind":"arxiv","id":"2505.16113","version":1},"attestation_state":"computed","paper":{"title":"Tools in the Loop: Quantifying Uncertainty of LLM Question Answering Systems That Use Tools","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Panagiotis Lymperopoulos, Vasanth Sarathy","submitted_at":"2025-05-22T01:34:23Z","abstract_excerpt":"Modern Large Language Models (LLMs) often require external tools, such as machine learning classifiers or knowledge retrieval systems, to provide accurate answers in domains where their pre-trained knowledge is insufficient. This integration of LLMs with external tools expands their utility but also introduces a critical challenge: determining the trustworthiness of responses generated by the combined system. In high-stakes applications, such as medical decision-making, it is essential to assess the uncertainty of both the LLM's generated text and the tool's output to ensure the reliability of"},"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":"2505.16113","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T01:34:23Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"500760953446a41f12bd76219546257a75c5bba26cddc576a849a5fb90a99c6e","abstract_canon_sha256":"1da34c7dbd9c00aeaf21be739b835fd9000bed3eee760d2ba5f604d560aa1bb0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:07:30.148516Z","signature_b64":"7CJ9QXdHSZWCyf8F3lz3nxGlsvtoggxAdwLozJw+80NkY3e6YpOZ3m0ZFDIInljxOsHebzvCdPQwl/P6qzdODQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"143344b1eec94790a679dc27d5aaf130960b789ad380d187584e16157f44efe3","last_reissued_at":"2026-07-05T11:07:30.148022Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:07:30.148022Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tools in the Loop: Quantifying Uncertainty of LLM Question Answering Systems That Use Tools","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Panagiotis Lymperopoulos, Vasanth Sarathy","submitted_at":"2025-05-22T01:34:23Z","abstract_excerpt":"Modern Large Language Models (LLMs) often require external tools, such as machine learning classifiers or knowledge retrieval systems, to provide accurate answers in domains where their pre-trained knowledge is insufficient. This integration of LLMs with external tools expands their utility but also introduces a critical challenge: determining the trustworthiness of responses generated by the combined system. In high-stakes applications, such as medical decision-making, it is essential to assess the uncertainty of both the LLM's generated text and the tool's output to ensure the reliability of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16113","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/2505.16113/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":"2505.16113","created_at":"2026-07-05T11:07:30.148081+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.16113v1","created_at":"2026-07-05T11:07:30.148081+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16113","created_at":"2026-07-05T11:07:30.148081+00:00"},{"alias_kind":"pith_short_12","alias_value":"CQZUJMPOZFDZ","created_at":"2026-07-05T11:07:30.148081+00:00"},{"alias_kind":"pith_short_16","alias_value":"CQZUJMPOZFDZBJTZ","created_at":"2026-07-05T11:07:30.148081+00:00"},{"alias_kind":"pith_short_8","alias_value":"CQZUJMPO","created_at":"2026-07-05T11:07:30.148081+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18467","citing_title":"ToolChain-CRC: Conformal Risk Control for Agentic AI Under Retrieval and Tool-Use Drift","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23505","citing_title":"Uncertainty Propagation in LLM-Based Systems","ref_index":76,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CQZUJMPOZFDZBJTZ3QT5LKXRGC","json":"https://pith.science/pith/CQZUJMPOZFDZBJTZ3QT5LKXRGC.json","graph_json":"https://pith.science/api/pith-number/CQZUJMPOZFDZBJTZ3QT5LKXRGC/graph.json","events_json":"https://pith.science/api/pith-number/CQZUJMPOZFDZBJTZ3QT5LKXRGC/events.json","paper":"https://pith.science/paper/CQZUJMPO"},"agent_actions":{"view_html":"https://pith.science/pith/CQZUJMPOZFDZBJTZ3QT5LKXRGC","download_json":"https://pith.science/pith/CQZUJMPOZFDZBJTZ3QT5LKXRGC.json","view_paper":"https://pith.science/paper/CQZUJMPO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.16113&json=true","fetch_graph":"https://pith.science/api/pith-number/CQZUJMPOZFDZBJTZ3QT5LKXRGC/graph.json","fetch_events":"https://pith.science/api/pith-number/CQZUJMPOZFDZBJTZ3QT5LKXRGC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CQZUJMPOZFDZBJTZ3QT5LKXRGC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CQZUJMPOZFDZBJTZ3QT5LKXRGC/action/storage_attestation","attest_author":"https://pith.science/pith/CQZUJMPOZFDZBJTZ3QT5LKXRGC/action/author_attestation","sign_citation":"https://pith.science/pith/CQZUJMPOZFDZBJTZ3QT5LKXRGC/action/citation_signature","submit_replication":"https://pith.science/pith/CQZUJMPOZFDZBJTZ3QT5LKXRGC/action/replication_record"}},"created_at":"2026-07-05T11:07:30.148081+00:00","updated_at":"2026-07-05T11:07:30.148081+00:00"}