{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:53ZFH4LOJRHMPB6YQCESXYAYOS","short_pith_number":"pith:53ZFH4LO","schema_version":"1.0","canonical_sha256":"eef253f16e4c4ec787d880892be01874be7ed29e105fcd7686aeaed679b640e3","source":{"kind":"arxiv","id":"2501.09957","version":2},"attestation_state":"computed","paper":{"title":"FRAG: A Flexible Modular Framework for Retrieval-Augmented Generation based on Knowledge Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ao Ke, Hairu Wang, S Kevin Zhou, Xike Xie, Yuan Feng, Yukun Cao, Zengyi Gao","submitted_at":"2025-01-17T05:19:14Z","abstract_excerpt":"To mitigate the hallucination and knowledge deficiency in large language models (LLMs), Knowledge Graph (KG)-based Retrieval-Augmented Generation (RAG) has shown promising potential by utilizing KGs as external resource to enhance LLMs reasoning. However, existing KG-RAG approaches struggle with a trade-off between flexibility and retrieval quality. Modular methods prioritize flexibility by avoiding the use of KG-fine-tuned models during retrieval, leading to fixed retrieval strategies and suboptimal retrieval quality. Conversely, coupled methods embed KG information within models to improve r"},"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":"2501.09957","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-17T05:19:14Z","cross_cats_sorted":[],"title_canon_sha256":"9f16b1a52199f604c3cbe2aae5facacb8449120c57c78d9ae8f48e838eb3764a","abstract_canon_sha256":"4adaadf7972e25a996a8380de5af43ae744dd15f8cd0de0c5378546f56124cdc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:03:51.235482Z","signature_b64":"05U0a/bNjtjJBix6d8mUS3lnuy7G/+ZdWEFYW1QtFJ7iLeoV4e1IBLkp/L19EyV7Hf4hqd5Wu+CFbfP57Ft6AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eef253f16e4c4ec787d880892be01874be7ed29e105fcd7686aeaed679b640e3","last_reissued_at":"2026-07-05T10:03:51.234951Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:03:51.234951Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FRAG: A Flexible Modular Framework for Retrieval-Augmented Generation based on Knowledge Graphs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ao Ke, Hairu Wang, S Kevin Zhou, Xike Xie, Yuan Feng, Yukun Cao, Zengyi Gao","submitted_at":"2025-01-17T05:19:14Z","abstract_excerpt":"To mitigate the hallucination and knowledge deficiency in large language models (LLMs), Knowledge Graph (KG)-based Retrieval-Augmented Generation (RAG) has shown promising potential by utilizing KGs as external resource to enhance LLMs reasoning. However, existing KG-RAG approaches struggle with a trade-off between flexibility and retrieval quality. Modular methods prioritize flexibility by avoiding the use of KG-fine-tuned models during retrieval, leading to fixed retrieval strategies and suboptimal retrieval quality. Conversely, coupled methods embed KG information within models to improve r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.09957","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/2501.09957/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":"2501.09957","created_at":"2026-07-05T10:03:51.235011+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.09957v2","created_at":"2026-07-05T10:03:51.235011+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.09957","created_at":"2026-07-05T10:03:51.235011+00:00"},{"alias_kind":"pith_short_12","alias_value":"53ZFH4LOJRHM","created_at":"2026-07-05T10:03:51.235011+00:00"},{"alias_kind":"pith_short_16","alias_value":"53ZFH4LOJRHMPB6Y","created_at":"2026-07-05T10:03:51.235011+00:00"},{"alias_kind":"pith_short_8","alias_value":"53ZFH4LO","created_at":"2026-07-05T10:03:51.235011+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.11502","citing_title":"HKGAI-V1: Towards Regional Sovereign Large Language Model for Hong Kong","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/53ZFH4LOJRHMPB6YQCESXYAYOS","json":"https://pith.science/pith/53ZFH4LOJRHMPB6YQCESXYAYOS.json","graph_json":"https://pith.science/api/pith-number/53ZFH4LOJRHMPB6YQCESXYAYOS/graph.json","events_json":"https://pith.science/api/pith-number/53ZFH4LOJRHMPB6YQCESXYAYOS/events.json","paper":"https://pith.science/paper/53ZFH4LO"},"agent_actions":{"view_html":"https://pith.science/pith/53ZFH4LOJRHMPB6YQCESXYAYOS","download_json":"https://pith.science/pith/53ZFH4LOJRHMPB6YQCESXYAYOS.json","view_paper":"https://pith.science/paper/53ZFH4LO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.09957&json=true","fetch_graph":"https://pith.science/api/pith-number/53ZFH4LOJRHMPB6YQCESXYAYOS/graph.json","fetch_events":"https://pith.science/api/pith-number/53ZFH4LOJRHMPB6YQCESXYAYOS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/53ZFH4LOJRHMPB6YQCESXYAYOS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/53ZFH4LOJRHMPB6YQCESXYAYOS/action/storage_attestation","attest_author":"https://pith.science/pith/53ZFH4LOJRHMPB6YQCESXYAYOS/action/author_attestation","sign_citation":"https://pith.science/pith/53ZFH4LOJRHMPB6YQCESXYAYOS/action/citation_signature","submit_replication":"https://pith.science/pith/53ZFH4LOJRHMPB6YQCESXYAYOS/action/replication_record"}},"created_at":"2026-07-05T10:03:51.235011+00:00","updated_at":"2026-07-05T10:03:51.235011+00:00"}