{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TQ7AST4IY326FTOYK2GW3XQT4Z","short_pith_number":"pith:TQ7AST4I","schema_version":"1.0","canonical_sha256":"9c3e094f88c6f5e2cdd8568d6dde13e6570a7dc99c13b23298de42362ef4a507","source":{"kind":"arxiv","id":"2605.19735","version":1},"attestation_state":"computed","paper":{"title":"ContextRAG: Extraction-Free Hierarchical Graph Construction for Retrieval-Augmented Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Roman Prosvirnin, Sergei Kuznetsov, Seungmin Jin","submitted_at":"2026-05-19T12:08:19Z","abstract_excerpt":"Graph-structured retrieval-augmented generation (RAG) systems can improve answer quality on multi-hop questions, but many current systems rely on large language models (LLMs) to extract entities, relations, and summaries during indexing. These calls add token and wall-clock costs that grow with corpus size. We present ContextRAG, a graph RAG system whose graph topology is constructed without LLM-based entity or relation extraction. ContextRAG derives a fuzzy concept graph over chunk embeddings using residual-quantization k-means and Formal Concept Analysis with Lukasiewicz residuated logic. Br"},"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":"2605.19735","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-19T12:08:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"86abe1199a58fbaecf3a8d4fd344cbb67d7c52f452005364ca04cf17164d5552","abstract_canon_sha256":"7428520f0a5247af6445dcb61d405bfe7e61b50cd58bb9374dc157f65887bcdf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T01:06:11.553695Z","signature_b64":"UAIRVpYZANo7aqvKpn5xG/0YixeKel6Aj0OyiuEVd9T8vKPH0RBrNuRvoInQe0CG6yGuMPJaBTEnNwS+NSbKAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c3e094f88c6f5e2cdd8568d6dde13e6570a7dc99c13b23298de42362ef4a507","last_reissued_at":"2026-05-20T01:06:11.553103Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T01:06:11.553103Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ContextRAG: Extraction-Free Hierarchical Graph Construction for Retrieval-Augmented Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Roman Prosvirnin, Sergei Kuznetsov, Seungmin Jin","submitted_at":"2026-05-19T12:08:19Z","abstract_excerpt":"Graph-structured retrieval-augmented generation (RAG) systems can improve answer quality on multi-hop questions, but many current systems rely on large language models (LLMs) to extract entities, relations, and summaries during indexing. These calls add token and wall-clock costs that grow with corpus size. We present ContextRAG, a graph RAG system whose graph topology is constructed without LLM-based entity or relation extraction. ContextRAG derives a fuzzy concept graph over chunk embeddings using residual-quantization k-means and Formal Concept Analysis with Lukasiewicz residuated logic. Br"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.19735","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/2605.19735/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":"2605.19735","created_at":"2026-05-20T01:06:11.553187+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.19735v1","created_at":"2026-05-20T01:06:11.553187+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.19735","created_at":"2026-05-20T01:06:11.553187+00:00"},{"alias_kind":"pith_short_12","alias_value":"TQ7AST4IY326","created_at":"2026-05-20T01:06:11.553187+00:00"},{"alias_kind":"pith_short_16","alias_value":"TQ7AST4IY326FTOY","created_at":"2026-05-20T01:06:11.553187+00:00"},{"alias_kind":"pith_short_8","alias_value":"TQ7AST4I","created_at":"2026-05-20T01:06:11.553187+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/TQ7AST4IY326FTOYK2GW3XQT4Z","json":"https://pith.science/pith/TQ7AST4IY326FTOYK2GW3XQT4Z.json","graph_json":"https://pith.science/api/pith-number/TQ7AST4IY326FTOYK2GW3XQT4Z/graph.json","events_json":"https://pith.science/api/pith-number/TQ7AST4IY326FTOYK2GW3XQT4Z/events.json","paper":"https://pith.science/paper/TQ7AST4I"},"agent_actions":{"view_html":"https://pith.science/pith/TQ7AST4IY326FTOYK2GW3XQT4Z","download_json":"https://pith.science/pith/TQ7AST4IY326FTOYK2GW3XQT4Z.json","view_paper":"https://pith.science/paper/TQ7AST4I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.19735&json=true","fetch_graph":"https://pith.science/api/pith-number/TQ7AST4IY326FTOYK2GW3XQT4Z/graph.json","fetch_events":"https://pith.science/api/pith-number/TQ7AST4IY326FTOYK2GW3XQT4Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TQ7AST4IY326FTOYK2GW3XQT4Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TQ7AST4IY326FTOYK2GW3XQT4Z/action/storage_attestation","attest_author":"https://pith.science/pith/TQ7AST4IY326FTOYK2GW3XQT4Z/action/author_attestation","sign_citation":"https://pith.science/pith/TQ7AST4IY326FTOYK2GW3XQT4Z/action/citation_signature","submit_replication":"https://pith.science/pith/TQ7AST4IY326FTOYK2GW3XQT4Z/action/replication_record"}},"created_at":"2026-05-20T01:06:11.553187+00:00","updated_at":"2026-05-20T01:06:11.553187+00:00"}