{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:S4NH5EEI6KEGDCWJPZAICYWKWQ","short_pith_number":"pith:S4NH5EEI","schema_version":"1.0","canonical_sha256":"971a7e9088f288618ac97e408162cab420494522b2e4c2656cf627daa3775170","source":{"kind":"arxiv","id":"2601.11956","version":2},"attestation_state":"computed","paper":{"title":"Double-Calibration: Towards Reliable LLMs via Calibrating Knowledge and Reasoning Confidence","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Fu Lee Wang, Qing Li, Wenqi Fan, Yanghui Rao, Yuyin Lu, Ziran Liang","submitted_at":"2026-01-17T08:18:38Z","abstract_excerpt":"Reliable reasoning in Large Language Models (LLMs) is challenged by their propensity for hallucination. While augmenting LLMs with Knowledge Graphs (KGs) improves factual accuracy, existing KG-augmented methods fail to quantify epistemic uncertainty in both the retrieved evidence and LLMs' reasoning. To bridge this gap, we introduce DoublyCal, a framework built on a novel double-calibration principle. DoublyCal employs a lightweight proxy model to first generate KG evidence alongside a calibrated evidence confidence. This calibrated supporting evidence then guides a black-box LLM, yielding fin"},"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":"2601.11956","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-17T08:18:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"82f973a10aa609299405070123d27612209f5a575ff9501daf6688368e3d40e8","abstract_canon_sha256":"a9c900ac47a99c0104cd1ae0c03235d2f875c320092ac83a9a568c0e09343ab1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:03:02.522142Z","signature_b64":"xYohPLfIJQOsFIiimMKzmhBsxDbmYfYdaX0uLYTNx6BMqRo8qvKwHEjye3XKkxPNp5yMCLZBdCH25eGHbkNwAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"971a7e9088f288618ac97e408162cab420494522b2e4c2656cf627daa3775170","last_reissued_at":"2026-05-20T00:03:02.521305Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:03:02.521305Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Double-Calibration: Towards Reliable LLMs via Calibrating Knowledge and Reasoning Confidence","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Fu Lee Wang, Qing Li, Wenqi Fan, Yanghui Rao, Yuyin Lu, Ziran Liang","submitted_at":"2026-01-17T08:18:38Z","abstract_excerpt":"Reliable reasoning in Large Language Models (LLMs) is challenged by their propensity for hallucination. While augmenting LLMs with Knowledge Graphs (KGs) improves factual accuracy, existing KG-augmented methods fail to quantify epistemic uncertainty in both the retrieved evidence and LLMs' reasoning. To bridge this gap, we introduce DoublyCal, a framework built on a novel double-calibration principle. DoublyCal employs a lightweight proxy model to first generate KG evidence alongside a calibrated evidence confidence. This calibrated supporting evidence then guides a black-box LLM, yielding fin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.11956","kind":"arxiv","version":2},"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/2601.11956/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":"2601.11956","created_at":"2026-05-20T00:03:02.521442+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.11956v2","created_at":"2026-05-20T00:03:02.521442+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.11956","created_at":"2026-05-20T00:03:02.521442+00:00"},{"alias_kind":"pith_short_12","alias_value":"S4NH5EEI6KEG","created_at":"2026-05-20T00:03:02.521442+00:00"},{"alias_kind":"pith_short_16","alias_value":"S4NH5EEI6KEGDCWJ","created_at":"2026-05-20T00:03:02.521442+00:00"},{"alias_kind":"pith_short_8","alias_value":"S4NH5EEI","created_at":"2026-05-20T00:03:02.521442+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S4NH5EEI6KEGDCWJPZAICYWKWQ","json":"https://pith.science/pith/S4NH5EEI6KEGDCWJPZAICYWKWQ.json","graph_json":"https://pith.science/api/pith-number/S4NH5EEI6KEGDCWJPZAICYWKWQ/graph.json","events_json":"https://pith.science/api/pith-number/S4NH5EEI6KEGDCWJPZAICYWKWQ/events.json","paper":"https://pith.science/paper/S4NH5EEI"},"agent_actions":{"view_html":"https://pith.science/pith/S4NH5EEI6KEGDCWJPZAICYWKWQ","download_json":"https://pith.science/pith/S4NH5EEI6KEGDCWJPZAICYWKWQ.json","view_paper":"https://pith.science/paper/S4NH5EEI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.11956&json=true","fetch_graph":"https://pith.science/api/pith-number/S4NH5EEI6KEGDCWJPZAICYWKWQ/graph.json","fetch_events":"https://pith.science/api/pith-number/S4NH5EEI6KEGDCWJPZAICYWKWQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S4NH5EEI6KEGDCWJPZAICYWKWQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S4NH5EEI6KEGDCWJPZAICYWKWQ/action/storage_attestation","attest_author":"https://pith.science/pith/S4NH5EEI6KEGDCWJPZAICYWKWQ/action/author_attestation","sign_citation":"https://pith.science/pith/S4NH5EEI6KEGDCWJPZAICYWKWQ/action/citation_signature","submit_replication":"https://pith.science/pith/S4NH5EEI6KEGDCWJPZAICYWKWQ/action/replication_record"}},"created_at":"2026-05-20T00:03:02.521442+00:00","updated_at":"2026-05-20T00:03:02.521442+00:00"}