{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZEKEZLMXLT7FLUEVNHV7UI2OGU","short_pith_number":"pith:ZEKEZLMX","schema_version":"1.0","canonical_sha256":"c9144cad975cfe55d09569ebfa234e35362df89aceb7e19c5f46e64fb560a0ac","source":{"kind":"arxiv","id":"2405.13576","version":2},"attestation_state":"computed","paper":{"title":"FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Research","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Chenghao Zhang, Guanting Dong, Jiajie Jin, Ji-Rong Wen, Tong Zhao, Xinyu Yang, Yutao Zhu, Yuyao Zhang, Zhao Yang, Zhicheng Dou","submitted_at":"2024-05-22T12:12:40Z","abstract_excerpt":"With the advent of large language models (LLMs) and multimodal large language models (MLLMs), the potential of retrieval-augmented generation (RAG) has attracted considerable research attention. Various novel algorithms and models have been introduced to enhance different aspects of RAG systems. However, the absence of a standardized framework for implementation, coupled with the inherently complex RAG process, makes it challenging and time-consuming for researchers to compare and evaluate these approaches in a consistent environment. Existing RAG toolkits, such as LangChain and LlamaIndex, wh"},"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":"2405.13576","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-22T12:12:40Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"870fc3a90a117878dfb1b6b0af86c02377be7fee375b156102551e1984c66a35","abstract_canon_sha256":"aad84da278a90e84a7b0fc8d9b869d8651cb02d5dad478ca1ceb78ff1d9656fc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:18:37.225376Z","signature_b64":"3vyAC8OFUJb0yCA0eOhd9hlAtW43CZatZodEx8nrfuBsDHtAWYwvmA85jaM6WQ9VnC9fNBfG6Z7B5VGRxsaLDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c9144cad975cfe55d09569ebfa234e35362df89aceb7e19c5f46e64fb560a0ac","last_reissued_at":"2026-07-05T10:18:37.224840Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:18:37.224840Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Research","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Chenghao Zhang, Guanting Dong, Jiajie Jin, Ji-Rong Wen, Tong Zhao, Xinyu Yang, Yutao Zhu, Yuyao Zhang, Zhao Yang, Zhicheng Dou","submitted_at":"2024-05-22T12:12:40Z","abstract_excerpt":"With the advent of large language models (LLMs) and multimodal large language models (MLLMs), the potential of retrieval-augmented generation (RAG) has attracted considerable research attention. Various novel algorithms and models have been introduced to enhance different aspects of RAG systems. However, the absence of a standardized framework for implementation, coupled with the inherently complex RAG process, makes it challenging and time-consuming for researchers to compare and evaluate these approaches in a consistent environment. Existing RAG toolkits, such as LangChain and LlamaIndex, wh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.13576","kind":"arxiv","version":2},"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/2405.13576/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":"2405.13576","created_at":"2026-07-05T10:18:37.224901+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.13576v2","created_at":"2026-07-05T10:18:37.224901+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.13576","created_at":"2026-07-05T10:18:37.224901+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZEKEZLMXLT7F","created_at":"2026-07-05T10:18:37.224901+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZEKEZLMXLT7FLUEV","created_at":"2026-07-05T10:18:37.224901+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZEKEZLMX","created_at":"2026-07-05T10:18:37.224901+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29328","citing_title":"Covering the Unseen: Information Demand Coverage Optimization for Retrieval-Augmented Generation","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2509.00798","citing_title":"Progressive Multimodal Search and Reasoning for Knowledge-Intensive Visual Question Answering","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2503.19470","citing_title":"ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2603.27253","citing_title":"Mitigating Hallucination on Hallucination in RAG via Ensemble Voting","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2503.05592","citing_title":"R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10530","citing_title":"Personalized Deep Research: A User-Centric Framework, Dataset, and Hybrid Evaluation for Knowledge Discovery","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZEKEZLMXLT7FLUEVNHV7UI2OGU","json":"https://pith.science/pith/ZEKEZLMXLT7FLUEVNHV7UI2OGU.json","graph_json":"https://pith.science/api/pith-number/ZEKEZLMXLT7FLUEVNHV7UI2OGU/graph.json","events_json":"https://pith.science/api/pith-number/ZEKEZLMXLT7FLUEVNHV7UI2OGU/events.json","paper":"https://pith.science/paper/ZEKEZLMX"},"agent_actions":{"view_html":"https://pith.science/pith/ZEKEZLMXLT7FLUEVNHV7UI2OGU","download_json":"https://pith.science/pith/ZEKEZLMXLT7FLUEVNHV7UI2OGU.json","view_paper":"https://pith.science/paper/ZEKEZLMX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.13576&json=true","fetch_graph":"https://pith.science/api/pith-number/ZEKEZLMXLT7FLUEVNHV7UI2OGU/graph.json","fetch_events":"https://pith.science/api/pith-number/ZEKEZLMXLT7FLUEVNHV7UI2OGU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZEKEZLMXLT7FLUEVNHV7UI2OGU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZEKEZLMXLT7FLUEVNHV7UI2OGU/action/storage_attestation","attest_author":"https://pith.science/pith/ZEKEZLMXLT7FLUEVNHV7UI2OGU/action/author_attestation","sign_citation":"https://pith.science/pith/ZEKEZLMXLT7FLUEVNHV7UI2OGU/action/citation_signature","submit_replication":"https://pith.science/pith/ZEKEZLMXLT7FLUEVNHV7UI2OGU/action/replication_record"}},"created_at":"2026-07-05T10:18:37.224901+00:00","updated_at":"2026-07-05T10:18:37.224901+00:00"}