{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:G334577FIYSGK6UIJYYGLIB2R2","short_pith_number":"pith:G334577F","schema_version":"1.0","canonical_sha256":"36f7ceffe54624657a884e3065a03a8eb78769a3f810d5d869c383e791579f1a","source":{"kind":"arxiv","id":"2607.11683","version":1},"attestation_state":"computed","paper":{"title":"RAGU: A Multi-Step GraphRAG Engine with a Compact Domain-Adapted LLM","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ivan Bondarenko, Matvey Solovyov, Mikhail Komarov, Nikolay O. Nikitin, Oleg Sedukhin, Roman Shuvalov, Stanislav Shtuka, Yana Dementyeva","submitted_at":"2026-07-13T15:20:51Z","abstract_excerpt":"Graph retrieval-augmented generation (GraphRAG) enhances large language models with structured knowledge, yet existing systems construct knowledge graphs in a single extraction pass, producing noisy entities and brittle retrieval. RAGU, an open-source modular GraphRAG engine, addresses this by separating extraction from consolidation: entities and relations pass through two-stage typed extraction, DBSCAN-backed deduplication, LLM summarization, and Leiden community detection. A key insight motivates a compact extractor: the skills an in-pipeline LLM needs - comprehension, extraction, reasoning"},"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":"2607.11683","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-13T15:20:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7c5f48e5e5185e69417a37089ea83c52796cd82f3edb4c20a7ef175184a29b0e","abstract_canon_sha256":"f6d2a86b4b8100afae1ca4c4ccaf3e2f4ee821558619fe16c96808188bc304dd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T02:22:18.939324Z","signature_b64":"LNgh/loaIbeBTDqcM3AAZaPevVuqfLVVFo3gzOWx3SUbnv/T/y6zz2MYuL/R2LR1nXvGotU4jJkeAAvvPgl9Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"36f7ceffe54624657a884e3065a03a8eb78769a3f810d5d869c383e791579f1a","last_reissued_at":"2026-07-14T02:22:18.938516Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T02:22:18.938516Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RAGU: A Multi-Step GraphRAG Engine with a Compact Domain-Adapted LLM","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ivan Bondarenko, Matvey Solovyov, Mikhail Komarov, Nikolay O. Nikitin, Oleg Sedukhin, Roman Shuvalov, Stanislav Shtuka, Yana Dementyeva","submitted_at":"2026-07-13T15:20:51Z","abstract_excerpt":"Graph retrieval-augmented generation (GraphRAG) enhances large language models with structured knowledge, yet existing systems construct knowledge graphs in a single extraction pass, producing noisy entities and brittle retrieval. RAGU, an open-source modular GraphRAG engine, addresses this by separating extraction from consolidation: entities and relations pass through two-stage typed extraction, DBSCAN-backed deduplication, LLM summarization, and Leiden community detection. A key insight motivates a compact extractor: the skills an in-pipeline LLM needs - comprehension, extraction, reasoning"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.11683","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/2607.11683/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":"2607.11683","created_at":"2026-07-14T02:22:18.938921+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.11683v1","created_at":"2026-07-14T02:22:18.938921+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.11683","created_at":"2026-07-14T02:22:18.938921+00:00"},{"alias_kind":"pith_short_12","alias_value":"G334577FIYSG","created_at":"2026-07-14T02:22:18.938921+00:00"},{"alias_kind":"pith_short_16","alias_value":"G334577FIYSGK6UI","created_at":"2026-07-14T02:22:18.938921+00:00"},{"alias_kind":"pith_short_8","alias_value":"G334577F","created_at":"2026-07-14T02:22:18.938921+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/G334577FIYSGK6UIJYYGLIB2R2","json":"https://pith.science/pith/G334577FIYSGK6UIJYYGLIB2R2.json","graph_json":"https://pith.science/api/pith-number/G334577FIYSGK6UIJYYGLIB2R2/graph.json","events_json":"https://pith.science/api/pith-number/G334577FIYSGK6UIJYYGLIB2R2/events.json","paper":"https://pith.science/paper/G334577F"},"agent_actions":{"view_html":"https://pith.science/pith/G334577FIYSGK6UIJYYGLIB2R2","download_json":"https://pith.science/pith/G334577FIYSGK6UIJYYGLIB2R2.json","view_paper":"https://pith.science/paper/G334577F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.11683&json=true","fetch_graph":"https://pith.science/api/pith-number/G334577FIYSGK6UIJYYGLIB2R2/graph.json","fetch_events":"https://pith.science/api/pith-number/G334577FIYSGK6UIJYYGLIB2R2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G334577FIYSGK6UIJYYGLIB2R2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G334577FIYSGK6UIJYYGLIB2R2/action/storage_attestation","attest_author":"https://pith.science/pith/G334577FIYSGK6UIJYYGLIB2R2/action/author_attestation","sign_citation":"https://pith.science/pith/G334577FIYSGK6UIJYYGLIB2R2/action/citation_signature","submit_replication":"https://pith.science/pith/G334577FIYSGK6UIJYYGLIB2R2/action/replication_record"}},"created_at":"2026-07-14T02:22:18.938921+00:00","updated_at":"2026-07-14T02:22:18.938921+00:00"}