{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RPFBE2IW6M6DPXPKUBIYTYC4YB","short_pith_number":"pith:RPFBE2IW","schema_version":"1.0","canonical_sha256":"8bca126916f33c37ddeaa05189e05cc044192af559421e6a6825e1763352cd5a","source":{"kind":"arxiv","id":"2407.00994","version":2},"attestation_state":"computed","paper":{"title":"LLM Uncertainty Quantification through Directional Entailment Graph and Claim Level Response Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hua Wei, Longchao Da, Lu Cheng, Tiejin Chen","submitted_at":"2024-07-01T06:11:30Z","abstract_excerpt":"The Large language models (LLMs) have showcased superior capabilities in sophisticated tasks across various domains, stemming from basic question-answer (QA), they are nowadays used as decision assistants or explainers for unfamiliar content. However, they are not always correct due to the data sparsity in specific domain corpus, or the model's hallucination problems. Given this, how much should we trust the responses from LLMs? This paper presents a novel way to evaluate the uncertainty that captures the directional instability, by constructing a directional graph from entailment probabilitie"},"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":"2407.00994","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-01T06:11:30Z","cross_cats_sorted":[],"title_canon_sha256":"84af5107a9680b6ab2772f3e7e7475784636a549ea053d05565af4d00df39612","abstract_canon_sha256":"8c42c511c01f8e1bd82f5b7f2927376f171a50601e8629221a0b67666b8b1bad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:41:05.072559Z","signature_b64":"SJSD0AM1CZFk3vnqA1dJwvbyYRjEP4Tl6yiR2PFGrLvj8FqpyABtlm9TpbpjP8e1B1kHMCmc2/3Q3LezS6ibDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8bca126916f33c37ddeaa05189e05cc044192af559421e6a6825e1763352cd5a","last_reissued_at":"2026-07-05T08:41:05.072048Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:41:05.072048Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM Uncertainty Quantification through Directional Entailment Graph and Claim Level Response Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hua Wei, Longchao Da, Lu Cheng, Tiejin Chen","submitted_at":"2024-07-01T06:11:30Z","abstract_excerpt":"The Large language models (LLMs) have showcased superior capabilities in sophisticated tasks across various domains, stemming from basic question-answer (QA), they are nowadays used as decision assistants or explainers for unfamiliar content. However, they are not always correct due to the data sparsity in specific domain corpus, or the model's hallucination problems. Given this, how much should we trust the responses from LLMs? This paper presents a novel way to evaluate the uncertainty that captures the directional instability, by constructing a directional graph from entailment probabilitie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.00994","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/2407.00994/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":"2407.00994","created_at":"2026-07-05T08:41:05.072102+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.00994v2","created_at":"2026-07-05T08:41:05.072102+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.00994","created_at":"2026-07-05T08:41:05.072102+00:00"},{"alias_kind":"pith_short_12","alias_value":"RPFBE2IW6M6D","created_at":"2026-07-05T08:41:05.072102+00:00"},{"alias_kind":"pith_short_16","alias_value":"RPFBE2IW6M6DPXPK","created_at":"2026-07-05T08:41:05.072102+00:00"},{"alias_kind":"pith_short_8","alias_value":"RPFBE2IW","created_at":"2026-07-05T08:41:05.072102+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05721","citing_title":"SpanUQ: Span-Level Uncertainty Quantification for Large Language Model Generation","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2606.22792","citing_title":"The Origins of Stochasticity: Comprehensive Investigations on Uncertainty Quantification for Large Language Models","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07017","citing_title":"The Sim-to-Real Gap of Foundation Model Agents: A Unified MDP Perspective","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19220","citing_title":"Position: Uncertainty Quantification in LLMs is Just Unsupervised Clustering","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19974","citing_title":"Are LLM Uncertainty and Correctness Encoded by the Same Features? A Functional Dissociation via Sparse Autoencoders","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RPFBE2IW6M6DPXPKUBIYTYC4YB","json":"https://pith.science/pith/RPFBE2IW6M6DPXPKUBIYTYC4YB.json","graph_json":"https://pith.science/api/pith-number/RPFBE2IW6M6DPXPKUBIYTYC4YB/graph.json","events_json":"https://pith.science/api/pith-number/RPFBE2IW6M6DPXPKUBIYTYC4YB/events.json","paper":"https://pith.science/paper/RPFBE2IW"},"agent_actions":{"view_html":"https://pith.science/pith/RPFBE2IW6M6DPXPKUBIYTYC4YB","download_json":"https://pith.science/pith/RPFBE2IW6M6DPXPKUBIYTYC4YB.json","view_paper":"https://pith.science/paper/RPFBE2IW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.00994&json=true","fetch_graph":"https://pith.science/api/pith-number/RPFBE2IW6M6DPXPKUBIYTYC4YB/graph.json","fetch_events":"https://pith.science/api/pith-number/RPFBE2IW6M6DPXPKUBIYTYC4YB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RPFBE2IW6M6DPXPKUBIYTYC4YB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RPFBE2IW6M6DPXPKUBIYTYC4YB/action/storage_attestation","attest_author":"https://pith.science/pith/RPFBE2IW6M6DPXPKUBIYTYC4YB/action/author_attestation","sign_citation":"https://pith.science/pith/RPFBE2IW6M6DPXPKUBIYTYC4YB/action/citation_signature","submit_replication":"https://pith.science/pith/RPFBE2IW6M6DPXPKUBIYTYC4YB/action/replication_record"}},"created_at":"2026-07-05T08:41:05.072102+00:00","updated_at":"2026-07-05T08:41:05.072102+00:00"}