{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FLQJWUTAMERVU2L3VE5UUVJEGK","short_pith_number":"pith:FLQJWUTA","schema_version":"1.0","canonical_sha256":"2ae09b526061235a697ba93b4a552432b9001e6944e5b23e8fc74cab9fb9d727","source":{"kind":"arxiv","id":"2407.19994","version":3},"attestation_state":"computed","paper":{"title":"A Study on the Implementation Method of an Agent-Based Advanced RAG System Using Graph","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Cheonsu Jeong","submitted_at":"2024-07-29T13:26:43Z","abstract_excerpt":"This study aims to improve knowledge-based question-answering (QA) systems by overcoming the limitations of existing Retrieval-Augmented Generation (RAG) models and implementing an advanced RAG system based on Graph technology to develop high-quality generative AI services. While existing RAG models demonstrate high accuracy and fluency by utilizing retrieved information, they may suffer from accuracy degradation as they generate responses using pre-loaded knowledge without reprocessing. Additionally, they cannot incorporate real-time data after the RAG configuration stage, leading to issues w"},"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":"2407.19994","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2024-07-29T13:26:43Z","cross_cats_sorted":[],"title_canon_sha256":"e57e2db735bdf3dddd8d052422984e28e5b273ce2c5b9f37ce8f2f197db79d50","abstract_canon_sha256":"c2831a25cff912bf91c1fba6b937c3ec3b521c7fc3bcef8a0bb84af6d307caff"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:14:54.995028Z","signature_b64":"u1/RyF3imqkXlRJweT085r2gbUTY98zFfeRPnEFB+veEfRjIvYB0o17WsoPet/7+fJoCkeylzxoxWbgJVdmkBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ae09b526061235a697ba93b4a552432b9001e6944e5b23e8fc74cab9fb9d727","last_reissued_at":"2026-07-05T09:14:54.994582Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:14:54.994582Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Study on the Implementation Method of an Agent-Based Advanced RAG System Using Graph","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Cheonsu Jeong","submitted_at":"2024-07-29T13:26:43Z","abstract_excerpt":"This study aims to improve knowledge-based question-answering (QA) systems by overcoming the limitations of existing Retrieval-Augmented Generation (RAG) models and implementing an advanced RAG system based on Graph technology to develop high-quality generative AI services. While existing RAG models demonstrate high accuracy and fluency by utilizing retrieved information, they may suffer from accuracy degradation as they generate responses using pre-loaded knowledge without reprocessing. Additionally, they cannot incorporate real-time data after the RAG configuration stage, leading to issues w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.19994","kind":"arxiv","version":3},"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/2407.19994/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":"2407.19994","created_at":"2026-07-05T09:14:54.994638+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.19994v3","created_at":"2026-07-05T09:14:54.994638+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.19994","created_at":"2026-07-05T09:14:54.994638+00:00"},{"alias_kind":"pith_short_12","alias_value":"FLQJWUTAMERV","created_at":"2026-07-05T09:14:54.994638+00:00"},{"alias_kind":"pith_short_16","alias_value":"FLQJWUTAMERVU2L3","created_at":"2026-07-05T09:14:54.994638+00:00"},{"alias_kind":"pith_short_8","alias_value":"FLQJWUTA","created_at":"2026-07-05T09:14:54.994638+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.21307","citing_title":"MultiFluxAI Enhancing Platform Engineering with Advanced Agent-Orchestrated Retrieval Systems","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FLQJWUTAMERVU2L3VE5UUVJEGK","json":"https://pith.science/pith/FLQJWUTAMERVU2L3VE5UUVJEGK.json","graph_json":"https://pith.science/api/pith-number/FLQJWUTAMERVU2L3VE5UUVJEGK/graph.json","events_json":"https://pith.science/api/pith-number/FLQJWUTAMERVU2L3VE5UUVJEGK/events.json","paper":"https://pith.science/paper/FLQJWUTA"},"agent_actions":{"view_html":"https://pith.science/pith/FLQJWUTAMERVU2L3VE5UUVJEGK","download_json":"https://pith.science/pith/FLQJWUTAMERVU2L3VE5UUVJEGK.json","view_paper":"https://pith.science/paper/FLQJWUTA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.19994&json=true","fetch_graph":"https://pith.science/api/pith-number/FLQJWUTAMERVU2L3VE5UUVJEGK/graph.json","fetch_events":"https://pith.science/api/pith-number/FLQJWUTAMERVU2L3VE5UUVJEGK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FLQJWUTAMERVU2L3VE5UUVJEGK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FLQJWUTAMERVU2L3VE5UUVJEGK/action/storage_attestation","attest_author":"https://pith.science/pith/FLQJWUTAMERVU2L3VE5UUVJEGK/action/author_attestation","sign_citation":"https://pith.science/pith/FLQJWUTAMERVU2L3VE5UUVJEGK/action/citation_signature","submit_replication":"https://pith.science/pith/FLQJWUTAMERVU2L3VE5UUVJEGK/action/replication_record"}},"created_at":"2026-07-05T09:14:54.994638+00:00","updated_at":"2026-07-05T09:14:54.994638+00:00"}