{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:X63TVNMRK6JX7IKIO2RV4P7CSM","short_pith_number":"pith:X63TVNMR","schema_version":"1.0","canonical_sha256":"bfb73ab59157937fa14876a35e3fe29339fc95302e883b1b9b7e41337c3d6e5c","source":{"kind":"arxiv","id":"2410.23605","version":2},"attestation_state":"computed","paper":{"title":"Dynamic Uncertainty Ranking: Enhancing Retrieval-Augmented In-Context Learning for Long-Tail Knowledge in LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cao Xiao, Jiayu Zhou, Parminder Bhatia, Runxue Bao, Shuyang Yu, Taha Kass-hout","submitted_at":"2024-10-31T03:42:17Z","abstract_excerpt":"Large language models (LLMs) can learn vast amounts of knowledge from diverse domains during pre-training. However, long-tail knowledge from specialized domains is often scarce and underrepresented, rarely appearing in the models' memorization. Prior work has shown that in-context learning (ICL) with retriever augmentation can help LLMs better capture long-tail knowledge, reducing their reliance on pre-trained data. Despite these advances, we observe that LLM predictions for long-tail questions remain uncertain to variations in retrieved samples. To take advantage of the uncertainty in ICL for"},"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":"2410.23605","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-31T03:42:17Z","cross_cats_sorted":[],"title_canon_sha256":"0f76e07e940dfcc940945da2e8c2c6a3d5a3963497530c8447796985353557f4","abstract_canon_sha256":"078e5261b7e7a49d4477cd886a4a1962d2a1a9d2196c922bdcb26f9ab30e3af7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:11:27.974212Z","signature_b64":"+ZEjcfKwLUI9ng3Z5m6CrjMfBcyRBvvBzG84PB6bgXQqg1l65nK98EEQ8vVs9NfeS/h12fS2WLwzgQ15hSyZBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bfb73ab59157937fa14876a35e3fe29339fc95302e883b1b9b7e41337c3d6e5c","last_reissued_at":"2026-07-05T10:11:27.973661Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:11:27.973661Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dynamic Uncertainty Ranking: Enhancing Retrieval-Augmented In-Context Learning for Long-Tail Knowledge in LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cao Xiao, Jiayu Zhou, Parminder Bhatia, Runxue Bao, Shuyang Yu, Taha Kass-hout","submitted_at":"2024-10-31T03:42:17Z","abstract_excerpt":"Large language models (LLMs) can learn vast amounts of knowledge from diverse domains during pre-training. However, long-tail knowledge from specialized domains is often scarce and underrepresented, rarely appearing in the models' memorization. Prior work has shown that in-context learning (ICL) with retriever augmentation can help LLMs better capture long-tail knowledge, reducing their reliance on pre-trained data. Despite these advances, we observe that LLM predictions for long-tail questions remain uncertain to variations in retrieved samples. To take advantage of the uncertainty in ICL for"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.23605","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/2410.23605/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":"2410.23605","created_at":"2026-07-05T10:11:27.973718+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.23605v2","created_at":"2026-07-05T10:11:27.973718+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.23605","created_at":"2026-07-05T10:11:27.973718+00:00"},{"alias_kind":"pith_short_12","alias_value":"X63TVNMRK6JX","created_at":"2026-07-05T10:11:27.973718+00:00"},{"alias_kind":"pith_short_16","alias_value":"X63TVNMRK6JX7IKI","created_at":"2026-07-05T10:11:27.973718+00:00"},{"alias_kind":"pith_short_8","alias_value":"X63TVNMR","created_at":"2026-07-05T10:11:27.973718+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.16172","citing_title":"SGIC: A Self-Guided Iterative Calibration Framework for RAG","ref_index":49,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X63TVNMRK6JX7IKIO2RV4P7CSM","json":"https://pith.science/pith/X63TVNMRK6JX7IKIO2RV4P7CSM.json","graph_json":"https://pith.science/api/pith-number/X63TVNMRK6JX7IKIO2RV4P7CSM/graph.json","events_json":"https://pith.science/api/pith-number/X63TVNMRK6JX7IKIO2RV4P7CSM/events.json","paper":"https://pith.science/paper/X63TVNMR"},"agent_actions":{"view_html":"https://pith.science/pith/X63TVNMRK6JX7IKIO2RV4P7CSM","download_json":"https://pith.science/pith/X63TVNMRK6JX7IKIO2RV4P7CSM.json","view_paper":"https://pith.science/paper/X63TVNMR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.23605&json=true","fetch_graph":"https://pith.science/api/pith-number/X63TVNMRK6JX7IKIO2RV4P7CSM/graph.json","fetch_events":"https://pith.science/api/pith-number/X63TVNMRK6JX7IKIO2RV4P7CSM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X63TVNMRK6JX7IKIO2RV4P7CSM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X63TVNMRK6JX7IKIO2RV4P7CSM/action/storage_attestation","attest_author":"https://pith.science/pith/X63TVNMRK6JX7IKIO2RV4P7CSM/action/author_attestation","sign_citation":"https://pith.science/pith/X63TVNMRK6JX7IKIO2RV4P7CSM/action/citation_signature","submit_replication":"https://pith.science/pith/X63TVNMRK6JX7IKIO2RV4P7CSM/action/replication_record"}},"created_at":"2026-07-05T10:11:27.973718+00:00","updated_at":"2026-07-05T10:11:27.973718+00:00"}