{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TYCWOPVHFDAKGXSWFYUOSZUUOO","short_pith_number":"pith:TYCWOPVH","schema_version":"1.0","canonical_sha256":"9e05673ea728c0a35e562e28e966947380c52720ed4cf1a5c7c892650c14926e","source":{"kind":"arxiv","id":"2605.17072","version":1},"attestation_state":"computed","paper":{"title":"RAGA: Reading-And-Graph-building-Agent for Autonomous Knowledge Graph Construction and Retrieval-Augmented Generation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Chengrui Han, Zesheng Cheng","submitted_at":"2026-05-16T16:42:50Z","abstract_excerpt":"Existing LLM-driven knowledge graph (KG) construction methods predominantly employ stateless batch processing pipelines, exhibiting structural deficiencies in cross-chunk semantic relation capture, entity disambiguation, and construction process interpretability. These limitations undermine KG quality, retrieval precision, and deployment trust in high-stakes domains.\n  We propose RAGA (Reading And Graph-building Agent), an LLM-based autonomous KG construction and retrieval fusion framework. RAGA provides an atomic toolset supporting full KG lifecycle CRUD operations and embeds a Read-Search-Ve"},"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":"2605.17072","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-16T16:42:50Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"bcb457c4ab911844b550d664fff7a5243893236803f4597159740409de923902","abstract_canon_sha256":"06828c56f6d807bf0f6e0d5692396d28f69d007a77d0f7860ece5d2e5bf4fa3c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:03:39.206635Z","signature_b64":"WO5NSdoO+jvVIz+cUfbQ6DLnxxe8JTDTrt2B61lawvBHvh7ZmyEZqL+5yTX2hhB2JLoTcUO4JNuHYEkLxLBFDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e05673ea728c0a35e562e28e966947380c52720ed4cf1a5c7c892650c14926e","last_reissued_at":"2026-05-20T00:03:39.204587Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:03:39.204587Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RAGA: Reading-And-Graph-building-Agent for Autonomous Knowledge Graph Construction and Retrieval-Augmented Generation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Chengrui Han, Zesheng Cheng","submitted_at":"2026-05-16T16:42:50Z","abstract_excerpt":"Existing LLM-driven knowledge graph (KG) construction methods predominantly employ stateless batch processing pipelines, exhibiting structural deficiencies in cross-chunk semantic relation capture, entity disambiguation, and construction process interpretability. These limitations undermine KG quality, retrieval precision, and deployment trust in high-stakes domains.\n  We propose RAGA (Reading And Graph-building Agent), an LLM-based autonomous KG construction and retrieval fusion framework. RAGA provides an atomic toolset supporting full KG lifecycle CRUD operations and embeds a Read-Search-Ve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17072","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/2605.17072/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T22:33:23.813359Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T22:21:57.751506Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"37b19a9311fbbd6dedada622ab6a4ee85eb7ee36e80b478b5a4f1829fec694fd"},"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":"2605.17072","created_at":"2026-05-20T00:03:39.205989+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.17072v1","created_at":"2026-05-20T00:03:39.205989+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17072","created_at":"2026-05-20T00:03:39.205989+00:00"},{"alias_kind":"pith_short_12","alias_value":"TYCWOPVHFDAK","created_at":"2026-05-20T00:03:39.205989+00:00"},{"alias_kind":"pith_short_16","alias_value":"TYCWOPVHFDAKGXSW","created_at":"2026-05-20T00:03:39.205989+00:00"},{"alias_kind":"pith_short_8","alias_value":"TYCWOPVH","created_at":"2026-05-20T00:03:39.205989+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/TYCWOPVHFDAKGXSWFYUOSZUUOO","json":"https://pith.science/pith/TYCWOPVHFDAKGXSWFYUOSZUUOO.json","graph_json":"https://pith.science/api/pith-number/TYCWOPVHFDAKGXSWFYUOSZUUOO/graph.json","events_json":"https://pith.science/api/pith-number/TYCWOPVHFDAKGXSWFYUOSZUUOO/events.json","paper":"https://pith.science/paper/TYCWOPVH"},"agent_actions":{"view_html":"https://pith.science/pith/TYCWOPVHFDAKGXSWFYUOSZUUOO","download_json":"https://pith.science/pith/TYCWOPVHFDAKGXSWFYUOSZUUOO.json","view_paper":"https://pith.science/paper/TYCWOPVH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.17072&json=true","fetch_graph":"https://pith.science/api/pith-number/TYCWOPVHFDAKGXSWFYUOSZUUOO/graph.json","fetch_events":"https://pith.science/api/pith-number/TYCWOPVHFDAKGXSWFYUOSZUUOO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TYCWOPVHFDAKGXSWFYUOSZUUOO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TYCWOPVHFDAKGXSWFYUOSZUUOO/action/storage_attestation","attest_author":"https://pith.science/pith/TYCWOPVHFDAKGXSWFYUOSZUUOO/action/author_attestation","sign_citation":"https://pith.science/pith/TYCWOPVHFDAKGXSWFYUOSZUUOO/action/citation_signature","submit_replication":"https://pith.science/pith/TYCWOPVHFDAKGXSWFYUOSZUUOO/action/replication_record"}},"created_at":"2026-05-20T00:03:39.205989+00:00","updated_at":"2026-05-20T00:03:39.205989+00:00"}