{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:CQZUJMPOZFDZBJTZ3QT5LKXRGC","short_pith_number":"pith:CQZUJMPO","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"},"canonical_sha256":"143344b1eec94790a679dc27d5aaf130960b789ad380d187584e16157f44efe3","source":{"kind":"arxiv","id":"2505.16113","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.16113","created_at":"2026-07-05T11:07:30Z"},{"alias_kind":"arxiv_version","alias_value":"2505.16113v1","created_at":"2026-07-05T11:07:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16113","created_at":"2026-07-05T11:07:30Z"},{"alias_kind":"pith_short_12","alias_value":"CQZUJMPOZFDZ","created_at":"2026-07-05T11:07:30Z"},{"alias_kind":"pith_short_16","alias_value":"CQZUJMPOZFDZBJTZ","created_at":"2026-07-05T11:07:30Z"},{"alias_kind":"pith_short_8","alias_value":"CQZUJMPO","created_at":"2026-07-05T11:07:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:CQZUJMPOZFDZBJTZ3QT5LKXRGC","target":"record","payload":{"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"},"canonical_sha256":"143344b1eec94790a679dc27d5aaf130960b789ad380d187584e16157f44efe3","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"},"source_kind":"arxiv","source_id":"2505.16113","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":"2026-07-05T11:07:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kEzad/Yv5zjxUgd+/7KdjA4re+8z2sS7MWiA96z/nbR1ZSBdt69eyFpiMIvXSNOPrlMDU5z8/dRtbNLr/EKSCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T04:42:05.143636Z"},"content_sha256":"f462790477ce3e462c1e98946d83ba18cc8b8e87ef37cf287a925cf5825abf53","schema_version":"1.0","event_id":"sha256:f462790477ce3e462c1e98946d83ba18cc8b8e87ef37cf287a925cf5825abf53"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:CQZUJMPOZFDZBJTZ3QT5LKXRGC","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:07:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bLPgpWXtVHhASqvl3VXfoeu+jyu2SRqG881Iq3aR5licWzw1IA4hUFR85Zb3LcDfkxqi0N5ISqTXKazwNWrhCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T04:42:05.144126Z"},"content_sha256":"1690947cbfacb1253a3d7a6bf25edc9da042dd161de0f9ba9387b45ca798b7d0","schema_version":"1.0","event_id":"sha256:1690947cbfacb1253a3d7a6bf25edc9da042dd161de0f9ba9387b45ca798b7d0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CQZUJMPOZFDZBJTZ3QT5LKXRGC/bundle.json","state_url":"https://pith.science/pith/CQZUJMPOZFDZBJTZ3QT5LKXRGC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CQZUJMPOZFDZBJTZ3QT5LKXRGC/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":"2026-08-06T04:42:05Z","links":{"resolver":"https://pith.science/pith/CQZUJMPOZFDZBJTZ3QT5LKXRGC","bundle":"https://pith.science/pith/CQZUJMPOZFDZBJTZ3QT5LKXRGC/bundle.json","state":"https://pith.science/pith/CQZUJMPOZFDZBJTZ3QT5LKXRGC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CQZUJMPOZFDZBJTZ3QT5LKXRGC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CQZUJMPOZFDZBJTZ3QT5LKXRGC","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":"1da34c7dbd9c00aeaf21be739b835fd9000bed3eee760d2ba5f604d560aa1bb0","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T01:34:23Z","title_canon_sha256":"500760953446a41f12bd76219546257a75c5bba26cddc576a849a5fb90a99c6e"},"schema_version":"1.0","source":{"id":"2505.16113","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.16113","created_at":"2026-07-05T11:07:30Z"},{"alias_kind":"arxiv_version","alias_value":"2505.16113v1","created_at":"2026-07-05T11:07:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16113","created_at":"2026-07-05T11:07:30Z"},{"alias_kind":"pith_short_12","alias_value":"CQZUJMPOZFDZ","created_at":"2026-07-05T11:07:30Z"},{"alias_kind":"pith_short_16","alias_value":"CQZUJMPOZFDZBJTZ","created_at":"2026-07-05T11:07:30Z"},{"alias_kind":"pith_short_8","alias_value":"CQZUJMPO","created_at":"2026-07-05T11:07:30Z"}],"graph_snapshots":[{"event_id":"sha256:1690947cbfacb1253a3d7a6bf25edc9da042dd161de0f9ba9387b45ca798b7d0","target":"graph","created_at":"2026-07-05T11:07:30Z","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/2505.16113/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Panagiotis Lymperopoulos, Vasanth Sarathy","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T01:34:23Z","title":"Tools in the Loop: Quantifying Uncertainty of LLM Question Answering Systems That Use Tools"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16113","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:f462790477ce3e462c1e98946d83ba18cc8b8e87ef37cf287a925cf5825abf53","target":"record","created_at":"2026-07-05T11:07:30Z","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":"1da34c7dbd9c00aeaf21be739b835fd9000bed3eee760d2ba5f604d560aa1bb0","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-22T01:34:23Z","title_canon_sha256":"500760953446a41f12bd76219546257a75c5bba26cddc576a849a5fb90a99c6e"},"schema_version":"1.0","source":{"id":"2505.16113","kind":"arxiv","version":1}},"canonical_sha256":"143344b1eec94790a679dc27d5aaf130960b789ad380d187584e16157f44efe3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"143344b1eec94790a679dc27d5aaf130960b789ad380d187584e16157f44efe3","first_computed_at":"2026-07-05T11:07:30.148022Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:07:30.148022Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7CJ9QXdHSZWCyf8F3lz3nxGlsvtoggxAdwLozJw+80NkY3e6YpOZ3m0ZFDIInljxOsHebzvCdPQwl/P6qzdODQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:07:30.148516Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.16113","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f462790477ce3e462c1e98946d83ba18cc8b8e87ef37cf287a925cf5825abf53","sha256:1690947cbfacb1253a3d7a6bf25edc9da042dd161de0f9ba9387b45ca798b7d0"],"state_sha256":"6b4ed875257382702932232ca854e849eb2f98616381b7b4e645da42ec5e32c6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uKlYMqeBmK4jcMElhLDAs0G7qiYPGDD/7KuZ5imd7RGTdKlwd2RRj9xyxxBj2cL7kvlOUlUx7CHDo81tVObbAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T04:42:05.147772Z","bundle_sha256":"feb5939f34a3091b7e277d086c8198a511ec3d3819dc04888e52749704404cdf"}}