{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KMHBSPUOZCZFWYPJ5KQQJEBJBF","short_pith_number":"pith:KMHBSPUO","schema_version":"1.0","canonical_sha256":"530e193e8ec8b25b61e9eaa10490290976d6950e8ec5e47657b14ffff5fb41a5","source":{"kind":"arxiv","id":"2406.14162","version":4},"attestation_state":"computed","paper":{"title":"DIRAS: Efficient LLM Annotation of Document Relevance in Retrieval Augmented Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Elliott Ash, Jingwei Ni, Markus Leippold, Meihong Lin, Mrinmaya Sachan, Tobias Schimanski","submitted_at":"2024-06-20T10:04:09Z","abstract_excerpt":"Retrieval Augmented Generation (RAG) is widely employed to ground responses to queries on domain-specific documents. But do RAG implementations leave out important information when answering queries that need an integrated analysis of information (e.g., Tell me good news in the stock market today.)? To address these concerns, RAG developers need to annotate information retrieval (IR) data for their domain of interest, which is challenging because (1) domain-specific queries usually need nuanced definitions of relevance beyond shallow semantic relevance; and (2) human or GPT-4 annotation is cos"},"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":"2406.14162","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2024-06-20T10:04:09Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"e83734075d9fd0b1dac229400549aecefb242b72169a38f3fa359bc463777714","abstract_canon_sha256":"876815397ee0d651a3a40319b7dedf36468024155a58f23da1872dc9a0d51249"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:04:13.950834Z","signature_b64":"GKSlFf5HLZ0PluUO4Pk+CJEPHuhL3A3qSAymFsv62mF+NeCHuIxC/Ko7w4RZMNnqyRK6Q4dmqenUR3bPgB3qDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"530e193e8ec8b25b61e9eaa10490290976d6950e8ec5e47657b14ffff5fb41a5","last_reissued_at":"2026-07-05T10:04:13.950407Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:04:13.950407Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DIRAS: Efficient LLM Annotation of Document Relevance in Retrieval Augmented Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Elliott Ash, Jingwei Ni, Markus Leippold, Meihong Lin, Mrinmaya Sachan, Tobias Schimanski","submitted_at":"2024-06-20T10:04:09Z","abstract_excerpt":"Retrieval Augmented Generation (RAG) is widely employed to ground responses to queries on domain-specific documents. But do RAG implementations leave out important information when answering queries that need an integrated analysis of information (e.g., Tell me good news in the stock market today.)? To address these concerns, RAG developers need to annotate information retrieval (IR) data for their domain of interest, which is challenging because (1) domain-specific queries usually need nuanced definitions of relevance beyond shallow semantic relevance; and (2) human or GPT-4 annotation is cos"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.14162","kind":"arxiv","version":4},"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/2406.14162/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":"2406.14162","created_at":"2026-07-05T10:04:13.950462+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.14162v4","created_at":"2026-07-05T10:04:13.950462+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.14162","created_at":"2026-07-05T10:04:13.950462+00:00"},{"alias_kind":"pith_short_12","alias_value":"KMHBSPUOZCZF","created_at":"2026-07-05T10:04:13.950462+00:00"},{"alias_kind":"pith_short_16","alias_value":"KMHBSPUOZCZFWYPJ","created_at":"2026-07-05T10:04:13.950462+00:00"},{"alias_kind":"pith_short_8","alias_value":"KMHBSPUO","created_at":"2026-07-05T10:04:13.950462+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.19334","citing_title":"Likert or Not: LLM Absolute Relevance Judgments on Fine-Grained Ordinal Scales","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KMHBSPUOZCZFWYPJ5KQQJEBJBF","json":"https://pith.science/pith/KMHBSPUOZCZFWYPJ5KQQJEBJBF.json","graph_json":"https://pith.science/api/pith-number/KMHBSPUOZCZFWYPJ5KQQJEBJBF/graph.json","events_json":"https://pith.science/api/pith-number/KMHBSPUOZCZFWYPJ5KQQJEBJBF/events.json","paper":"https://pith.science/paper/KMHBSPUO"},"agent_actions":{"view_html":"https://pith.science/pith/KMHBSPUOZCZFWYPJ5KQQJEBJBF","download_json":"https://pith.science/pith/KMHBSPUOZCZFWYPJ5KQQJEBJBF.json","view_paper":"https://pith.science/paper/KMHBSPUO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.14162&json=true","fetch_graph":"https://pith.science/api/pith-number/KMHBSPUOZCZFWYPJ5KQQJEBJBF/graph.json","fetch_events":"https://pith.science/api/pith-number/KMHBSPUOZCZFWYPJ5KQQJEBJBF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KMHBSPUOZCZFWYPJ5KQQJEBJBF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KMHBSPUOZCZFWYPJ5KQQJEBJBF/action/storage_attestation","attest_author":"https://pith.science/pith/KMHBSPUOZCZFWYPJ5KQQJEBJBF/action/author_attestation","sign_citation":"https://pith.science/pith/KMHBSPUOZCZFWYPJ5KQQJEBJBF/action/citation_signature","submit_replication":"https://pith.science/pith/KMHBSPUOZCZFWYPJ5KQQJEBJBF/action/replication_record"}},"created_at":"2026-07-05T10:04:13.950462+00:00","updated_at":"2026-07-05T10:04:13.950462+00:00"}