{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:INXENQKMWLV6EJAABH3NB2SSI5","short_pith_number":"pith:INXENQKM","schema_version":"1.0","canonical_sha256":"436e46c14cb2ebe2240009f6d0ea52475c0b3cf72a51190e832aa584f11e40bf","source":{"kind":"arxiv","id":"2501.09292","version":3},"attestation_state":"computed","paper":{"title":"To Retrieve or Not to Retrieve? Uncertainty Detection for Dynamic Retrieval Augmented Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Kaustubh D. Dhole","submitted_at":"2025-01-16T04:56:33Z","abstract_excerpt":"Retrieval-Augmented Generation equips large language models with the capability to retrieve external knowledge, thereby mitigating hallucinations by incorporating information beyond the model's intrinsic abilities. However, most prior works have focused on invoking retrieval deterministically, which makes it unsuitable for tasks such as long-form question answering. Instead, dynamically performing retrieval by invoking it only when the underlying LLM lacks the required knowledge can be more efficient. In this context, we delve deeper into the question, \"To Retrieve or Not to Retrieve?\" by expl"},"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":"2501.09292","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-16T04:56:33Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"9e83d335fccd428dbc3afb0f832cd655a0ee432a7fd865be65b6487ec4774433","abstract_canon_sha256":"95801c881c08e4ea3d05c57d6b7fb5fee077d34933a46c8df8a666078ae33494"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:33:42.503786Z","signature_b64":"VRHr3j70eC4aOGDVfJ+VjFN5UHNHohP/3kQOz1NL5ZQfHmrDUUJmNq20Q5fHDKSkwRBmHk7CyiMJAra+V9EdBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"436e46c14cb2ebe2240009f6d0ea52475c0b3cf72a51190e832aa584f11e40bf","last_reissued_at":"2026-07-05T10:33:42.503196Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:33:42.503196Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"To Retrieve or Not to Retrieve? Uncertainty Detection for Dynamic Retrieval Augmented Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Kaustubh D. Dhole","submitted_at":"2025-01-16T04:56:33Z","abstract_excerpt":"Retrieval-Augmented Generation equips large language models with the capability to retrieve external knowledge, thereby mitigating hallucinations by incorporating information beyond the model's intrinsic abilities. However, most prior works have focused on invoking retrieval deterministically, which makes it unsuitable for tasks such as long-form question answering. Instead, dynamically performing retrieval by invoking it only when the underlying LLM lacks the required knowledge can be more efficient. In this context, we delve deeper into the question, \"To Retrieve or Not to Retrieve?\" by expl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.09292","kind":"arxiv","version":3},"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/2501.09292/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":"2501.09292","created_at":"2026-07-05T10:33:42.503264+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.09292v3","created_at":"2026-07-05T10:33:42.503264+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.09292","created_at":"2026-07-05T10:33:42.503264+00:00"},{"alias_kind":"pith_short_12","alias_value":"INXENQKMWLV6","created_at":"2026-07-05T10:33:42.503264+00:00"},{"alias_kind":"pith_short_16","alias_value":"INXENQKMWLV6EJAA","created_at":"2026-07-05T10:33:42.503264+00:00"},{"alias_kind":"pith_short_8","alias_value":"INXENQKM","created_at":"2026-07-05T10:33:42.503264+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.07794","citing_title":"HiPRAG: Hierarchical Process Rewards for Efficient Agentic Retrieval Augmented Generation","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/INXENQKMWLV6EJAABH3NB2SSI5","json":"https://pith.science/pith/INXENQKMWLV6EJAABH3NB2SSI5.json","graph_json":"https://pith.science/api/pith-number/INXENQKMWLV6EJAABH3NB2SSI5/graph.json","events_json":"https://pith.science/api/pith-number/INXENQKMWLV6EJAABH3NB2SSI5/events.json","paper":"https://pith.science/paper/INXENQKM"},"agent_actions":{"view_html":"https://pith.science/pith/INXENQKMWLV6EJAABH3NB2SSI5","download_json":"https://pith.science/pith/INXENQKMWLV6EJAABH3NB2SSI5.json","view_paper":"https://pith.science/paper/INXENQKM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.09292&json=true","fetch_graph":"https://pith.science/api/pith-number/INXENQKMWLV6EJAABH3NB2SSI5/graph.json","fetch_events":"https://pith.science/api/pith-number/INXENQKMWLV6EJAABH3NB2SSI5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/INXENQKMWLV6EJAABH3NB2SSI5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/INXENQKMWLV6EJAABH3NB2SSI5/action/storage_attestation","attest_author":"https://pith.science/pith/INXENQKMWLV6EJAABH3NB2SSI5/action/author_attestation","sign_citation":"https://pith.science/pith/INXENQKMWLV6EJAABH3NB2SSI5/action/citation_signature","submit_replication":"https://pith.science/pith/INXENQKMWLV6EJAABH3NB2SSI5/action/replication_record"}},"created_at":"2026-07-05T10:33:42.503264+00:00","updated_at":"2026-07-05T10:33:42.503264+00:00"}