{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VNJV5CS2CF6XT67ZJXMS2UL3BG","short_pith_number":"pith:VNJV5CS2","schema_version":"1.0","canonical_sha256":"ab535e8a5a117d79fbf94dd92d517b09af895333eb024bc3bb46b0bd3f30c6ce","source":{"kind":"arxiv","id":"2504.15068","version":1},"attestation_state":"computed","paper":{"title":"The Great Nugget Recall: Automating Fact Extraction and RAG Evaluation with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Daniel Campos, Jimmy Lin, Nandan Thakur, Nick Craswell, Ronak Pradeep, Shivani Upadhyay","submitted_at":"2025-04-21T12:55:06Z","abstract_excerpt":"Large Language Models (LLMs) have significantly enhanced the capabilities of information access systems, especially with retrieval-augmented generation (RAG). Nevertheless, the evaluation of RAG systems remains a barrier to continued progress, a challenge we tackle in this work by proposing an automatic evaluation framework that is validated against human annotations. We believe that the nugget evaluation methodology provides a solid foundation for evaluating RAG systems. This approach, originally developed for the TREC Question Answering (QA) Track in 2003, evaluates systems based on atomic f"},"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":"2504.15068","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-04-21T12:55:06Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"857bf5e23a0c8e8c831425f6f60fc3ee5d2abfefb5c83dfa66214c2f91e2cd4d","abstract_canon_sha256":"03d8601fcbb0162715f2cde32c424d2443221faf6933bacc376d6704a7d36953"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:51:55.729284Z","signature_b64":"O/uY6upI0F6ZKZQ1dZwawrdDmt30GMIawhnsksf4z/KXpcQdYQ08Ysk2A0spc2LDvORPfAH8T52h78csmPiPCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab535e8a5a117d79fbf94dd92d517b09af895333eb024bc3bb46b0bd3f30c6ce","last_reissued_at":"2026-07-05T10:51:55.728782Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:51:55.728782Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Great Nugget Recall: Automating Fact Extraction and RAG Evaluation with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.IR","authors_text":"Daniel Campos, Jimmy Lin, Nandan Thakur, Nick Craswell, Ronak Pradeep, Shivani Upadhyay","submitted_at":"2025-04-21T12:55:06Z","abstract_excerpt":"Large Language Models (LLMs) have significantly enhanced the capabilities of information access systems, especially with retrieval-augmented generation (RAG). Nevertheless, the evaluation of RAG systems remains a barrier to continued progress, a challenge we tackle in this work by proposing an automatic evaluation framework that is validated against human annotations. We believe that the nugget evaluation methodology provides a solid foundation for evaluating RAG systems. This approach, originally developed for the TREC Question Answering (QA) Track in 2003, evaluates systems based on atomic f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.15068","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/2504.15068/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":"2504.15068","created_at":"2026-07-05T10:51:55.728848+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.15068v1","created_at":"2026-07-05T10:51:55.728848+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.15068","created_at":"2026-07-05T10:51:55.728848+00:00"},{"alias_kind":"pith_short_12","alias_value":"VNJV5CS2CF6X","created_at":"2026-07-05T10:51:55.728848+00:00"},{"alias_kind":"pith_short_16","alias_value":"VNJV5CS2CF6XT67Z","created_at":"2026-07-05T10:51:55.728848+00:00"},{"alias_kind":"pith_short_8","alias_value":"VNJV5CS2","created_at":"2026-07-05T10:51:55.728848+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2505.20825","citing_title":"Reinforced Informativeness Optimization for Long-Form Retrieval-Augmented Generation","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VNJV5CS2CF6XT67ZJXMS2UL3BG","json":"https://pith.science/pith/VNJV5CS2CF6XT67ZJXMS2UL3BG.json","graph_json":"https://pith.science/api/pith-number/VNJV5CS2CF6XT67ZJXMS2UL3BG/graph.json","events_json":"https://pith.science/api/pith-number/VNJV5CS2CF6XT67ZJXMS2UL3BG/events.json","paper":"https://pith.science/paper/VNJV5CS2"},"agent_actions":{"view_html":"https://pith.science/pith/VNJV5CS2CF6XT67ZJXMS2UL3BG","download_json":"https://pith.science/pith/VNJV5CS2CF6XT67ZJXMS2UL3BG.json","view_paper":"https://pith.science/paper/VNJV5CS2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.15068&json=true","fetch_graph":"https://pith.science/api/pith-number/VNJV5CS2CF6XT67ZJXMS2UL3BG/graph.json","fetch_events":"https://pith.science/api/pith-number/VNJV5CS2CF6XT67ZJXMS2UL3BG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VNJV5CS2CF6XT67ZJXMS2UL3BG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VNJV5CS2CF6XT67ZJXMS2UL3BG/action/storage_attestation","attest_author":"https://pith.science/pith/VNJV5CS2CF6XT67ZJXMS2UL3BG/action/author_attestation","sign_citation":"https://pith.science/pith/VNJV5CS2CF6XT67ZJXMS2UL3BG/action/citation_signature","submit_replication":"https://pith.science/pith/VNJV5CS2CF6XT67ZJXMS2UL3BG/action/replication_record"}},"created_at":"2026-07-05T10:51:55.728848+00:00","updated_at":"2026-07-05T10:51:55.728848+00:00"}