{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YFXT4ETD6GOTIU7U7USGPOXP35","short_pith_number":"pith:YFXT4ETD","schema_version":"1.0","canonical_sha256":"c16f3e1263f19d3453f4fd2467baefdf64f00ac408fbfafce265b78b5855d585","source":{"kind":"arxiv","id":"2411.13691","version":1},"attestation_state":"computed","paper":{"title":"Retrieval-Augmented Generation for Domain-Specific Question Answering: A Case Study on Pittsburgh and CMU","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Haojia Sun, Shuting Zhang, Yaqi Wang","submitted_at":"2024-11-20T20:10:43Z","abstract_excerpt":"We designed a Retrieval-Augmented Generation (RAG) system to provide large language models with relevant documents for answering domain-specific questions about Pittsburgh and Carnegie Mellon University (CMU). We extracted over 1,800 subpages using a greedy scraping strategy and employed a hybrid annotation process, combining manual and Mistral-generated question-answer pairs, achieving an inter-annotator agreement (IAA) score of 0.7625. Our RAG framework integrates BM25 and FAISS retrievers, enhanced with a reranker for improved document retrieval accuracy. Experimental results show that the "},"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":"2411.13691","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-20T20:10:43Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"3a763916ff8b16ba29c7946de6b73a6461fac7017b5e9163974da8fb5b82b2b1","abstract_canon_sha256":"04e0cd7116f18d5834d69e16d887b28bf59e01802578840dd2d2c21a377ab23e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:38:35.607065Z","signature_b64":"jUamlqGnG8bUFV+oJmwGxX6lU5EQuLLV7GbwgyvF2b5N4GC7T2cviM/Up2URXLPX4lE1mYVY5AV6IGB+kL7YDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c16f3e1263f19d3453f4fd2467baefdf64f00ac408fbfafce265b78b5855d585","last_reissued_at":"2026-07-05T09:38:35.606593Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:38:35.606593Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Retrieval-Augmented Generation for Domain-Specific Question Answering: A Case Study on Pittsburgh and CMU","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Haojia Sun, Shuting Zhang, Yaqi Wang","submitted_at":"2024-11-20T20:10:43Z","abstract_excerpt":"We designed a Retrieval-Augmented Generation (RAG) system to provide large language models with relevant documents for answering domain-specific questions about Pittsburgh and Carnegie Mellon University (CMU). We extracted over 1,800 subpages using a greedy scraping strategy and employed a hybrid annotation process, combining manual and Mistral-generated question-answer pairs, achieving an inter-annotator agreement (IAA) score of 0.7625. Our RAG framework integrates BM25 and FAISS retrievers, enhanced with a reranker for improved document retrieval accuracy. Experimental results show that the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.13691","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/2411.13691/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":"2411.13691","created_at":"2026-07-05T09:38:35.606651+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.13691v1","created_at":"2026-07-05T09:38:35.606651+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.13691","created_at":"2026-07-05T09:38:35.606651+00:00"},{"alias_kind":"pith_short_12","alias_value":"YFXT4ETD6GOT","created_at":"2026-07-05T09:38:35.606651+00:00"},{"alias_kind":"pith_short_16","alias_value":"YFXT4ETD6GOTIU7U","created_at":"2026-07-05T09:38:35.606651+00:00"},{"alias_kind":"pith_short_8","alias_value":"YFXT4ETD","created_at":"2026-07-05T09:38:35.606651+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YFXT4ETD6GOTIU7U7USGPOXP35","json":"https://pith.science/pith/YFXT4ETD6GOTIU7U7USGPOXP35.json","graph_json":"https://pith.science/api/pith-number/YFXT4ETD6GOTIU7U7USGPOXP35/graph.json","events_json":"https://pith.science/api/pith-number/YFXT4ETD6GOTIU7U7USGPOXP35/events.json","paper":"https://pith.science/paper/YFXT4ETD"},"agent_actions":{"view_html":"https://pith.science/pith/YFXT4ETD6GOTIU7U7USGPOXP35","download_json":"https://pith.science/pith/YFXT4ETD6GOTIU7U7USGPOXP35.json","view_paper":"https://pith.science/paper/YFXT4ETD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.13691&json=true","fetch_graph":"https://pith.science/api/pith-number/YFXT4ETD6GOTIU7U7USGPOXP35/graph.json","fetch_events":"https://pith.science/api/pith-number/YFXT4ETD6GOTIU7U7USGPOXP35/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YFXT4ETD6GOTIU7U7USGPOXP35/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YFXT4ETD6GOTIU7U7USGPOXP35/action/storage_attestation","attest_author":"https://pith.science/pith/YFXT4ETD6GOTIU7U7USGPOXP35/action/author_attestation","sign_citation":"https://pith.science/pith/YFXT4ETD6GOTIU7U7USGPOXP35/action/citation_signature","submit_replication":"https://pith.science/pith/YFXT4ETD6GOTIU7U7USGPOXP35/action/replication_record"}},"created_at":"2026-07-05T09:38:35.606651+00:00","updated_at":"2026-07-05T09:38:35.606651+00:00"}