{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IVVGP7ILO6CM7YRS26FH4XD7XO","short_pith_number":"pith:IVVGP7IL","schema_version":"1.0","canonical_sha256":"456a67fd0b7784cfe232d78a7e5c7fbbb5bad60ede67185cf3d9be794cb1867e","source":{"kind":"arxiv","id":"2403.00982","version":1},"attestation_state":"computed","paper":{"title":"LocalRQA: From Generating Data to Locally Training, Testing, and Deploying Retrieval-Augmented QA Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Xiao Yu, Yunan Lu, Zhou Yu","submitted_at":"2024-03-01T21:10:20Z","abstract_excerpt":"Retrieval-augmented question-answering systems combine retrieval techniques with large language models to provide answers that are more accurate and informative. Many existing toolkits allow users to quickly build such systems using off-the-shelf models, but they fall short in supporting researchers and developers to customize the model training, testing, and deployment process. We propose LocalRQA, an open-source toolkit that features a wide selection of model training algorithms, evaluation methods, and deployment tools curated from the latest research. As a showcase, we build QA systems usi"},"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":"2403.00982","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-01T21:10:20Z","cross_cats_sorted":[],"title_canon_sha256":"8cd18c3aa62fdfc0063af9d3c4e266e586ec785c2caf4457302176191f3be5c2","abstract_canon_sha256":"5ea86680a6d3451c78562b4b41f072ab1acd0e19f5ff420d657691f22ae131e7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:51:14.808496Z","signature_b64":"zUNVC+J9UNCgjygAir9soqg4kYQBVeaK0FzbJ/mPsv7hjlBnR/R1XxisKlul3t7ERt2m36yjVe40zR3CDBw3CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"456a67fd0b7784cfe232d78a7e5c7fbbb5bad60ede67185cf3d9be794cb1867e","last_reissued_at":"2026-07-05T07:51:14.808150Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:51:14.808150Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LocalRQA: From Generating Data to Locally Training, Testing, and Deploying Retrieval-Augmented QA Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Xiao Yu, Yunan Lu, Zhou Yu","submitted_at":"2024-03-01T21:10:20Z","abstract_excerpt":"Retrieval-augmented question-answering systems combine retrieval techniques with large language models to provide answers that are more accurate and informative. Many existing toolkits allow users to quickly build such systems using off-the-shelf models, but they fall short in supporting researchers and developers to customize the model training, testing, and deployment process. We propose LocalRQA, an open-source toolkit that features a wide selection of model training algorithms, evaluation methods, and deployment tools curated from the latest research. As a showcase, we build QA systems usi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.00982","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/2403.00982/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":"2403.00982","created_at":"2026-07-05T07:51:14.808206+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.00982v1","created_at":"2026-07-05T07:51:14.808206+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.00982","created_at":"2026-07-05T07:51:14.808206+00:00"},{"alias_kind":"pith_short_12","alias_value":"IVVGP7ILO6CM","created_at":"2026-07-05T07:51:14.808206+00:00"},{"alias_kind":"pith_short_16","alias_value":"IVVGP7ILO6CM7YRS","created_at":"2026-07-05T07:51:14.808206+00:00"},{"alias_kind":"pith_short_8","alias_value":"IVVGP7IL","created_at":"2026-07-05T07:51:14.808206+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.12494","citing_title":"FlexRAG: A Flexible and Comprehensive Framework for Retrieval-Augmented Generation","ref_index":45,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IVVGP7ILO6CM7YRS26FH4XD7XO","json":"https://pith.science/pith/IVVGP7ILO6CM7YRS26FH4XD7XO.json","graph_json":"https://pith.science/api/pith-number/IVVGP7ILO6CM7YRS26FH4XD7XO/graph.json","events_json":"https://pith.science/api/pith-number/IVVGP7ILO6CM7YRS26FH4XD7XO/events.json","paper":"https://pith.science/paper/IVVGP7IL"},"agent_actions":{"view_html":"https://pith.science/pith/IVVGP7ILO6CM7YRS26FH4XD7XO","download_json":"https://pith.science/pith/IVVGP7ILO6CM7YRS26FH4XD7XO.json","view_paper":"https://pith.science/paper/IVVGP7IL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.00982&json=true","fetch_graph":"https://pith.science/api/pith-number/IVVGP7ILO6CM7YRS26FH4XD7XO/graph.json","fetch_events":"https://pith.science/api/pith-number/IVVGP7ILO6CM7YRS26FH4XD7XO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IVVGP7ILO6CM7YRS26FH4XD7XO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IVVGP7ILO6CM7YRS26FH4XD7XO/action/storage_attestation","attest_author":"https://pith.science/pith/IVVGP7ILO6CM7YRS26FH4XD7XO/action/author_attestation","sign_citation":"https://pith.science/pith/IVVGP7ILO6CM7YRS26FH4XD7XO/action/citation_signature","submit_replication":"https://pith.science/pith/IVVGP7ILO6CM7YRS26FH4XD7XO/action/replication_record"}},"created_at":"2026-07-05T07:51:14.808206+00:00","updated_at":"2026-07-05T07:51:14.808206+00:00"}