{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WE3FYVOQHTYBVQ72ALHNUSG23V","short_pith_number":"pith:WE3FYVOQ","schema_version":"1.0","canonical_sha256":"b1365c55d03cf01ac3fa02ceda48dadd5be3e8dfc14f5776e7d642b0dcea4763","source":{"kind":"arxiv","id":"2507.17399","version":1},"attestation_state":"computed","paper":{"title":"Millions of $\\text{GeAR}$-s: Extending GraphRAG to Millions of Documents","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Chenxin Diao, Jeff Z. Pan, Pascual Merita, Pavlos Vougiouklis, Zhili Shen","submitted_at":"2025-07-23T10:54:24Z","abstract_excerpt":"Recent studies have explored graph-based approaches to retrieval-augmented generation, leveraging structured or semi-structured information -- such as entities and their relations extracted from documents -- to enhance retrieval. However, these methods are typically designed to address specific tasks, such as multi-hop question answering and query-focused summarisation, and therefore, there is limited evidence of their general applicability across broader datasets. In this paper, we aim to adapt a state-of-the-art graph-based RAG solution: $\\text{GeAR}$ and explore its performance and limitati"},"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":"2507.17399","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-23T10:54:24Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"a0fc1210d2524e5afe33368bd560eaefe0574f83d6d1aaa9b3dad344b306838e","abstract_canon_sha256":"c3b28df60eb06d2b9698668c5125d57b711e82faef562819299c077d9943e820"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:42:06.947380Z","signature_b64":"/ezwsIGkkAidd1DNUA1LbXiiENixW/Ufc2Roy+sxN87gI1t29lWN95nyMNhfG8mDtnmEVCiB2ZaZPFhvaXizDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1365c55d03cf01ac3fa02ceda48dadd5be3e8dfc14f5776e7d642b0dcea4763","last_reissued_at":"2026-07-05T11:42:06.946887Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:42:06.946887Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Millions of $\\text{GeAR}$-s: Extending GraphRAG to Millions of Documents","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Chenxin Diao, Jeff Z. Pan, Pascual Merita, Pavlos Vougiouklis, Zhili Shen","submitted_at":"2025-07-23T10:54:24Z","abstract_excerpt":"Recent studies have explored graph-based approaches to retrieval-augmented generation, leveraging structured or semi-structured information -- such as entities and their relations extracted from documents -- to enhance retrieval. However, these methods are typically designed to address specific tasks, such as multi-hop question answering and query-focused summarisation, and therefore, there is limited evidence of their general applicability across broader datasets. In this paper, we aim to adapt a state-of-the-art graph-based RAG solution: $\\text{GeAR}$ and explore its performance and limitati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.17399","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/2507.17399/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":"2507.17399","created_at":"2026-07-05T11:42:06.946945+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.17399v1","created_at":"2026-07-05T11:42:06.946945+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.17399","created_at":"2026-07-05T11:42:06.946945+00:00"},{"alias_kind":"pith_short_12","alias_value":"WE3FYVOQHTYB","created_at":"2026-07-05T11:42:06.946945+00:00"},{"alias_kind":"pith_short_16","alias_value":"WE3FYVOQHTYBVQ72","created_at":"2026-07-05T11:42:06.946945+00:00"},{"alias_kind":"pith_short_8","alias_value":"WE3FYVOQ","created_at":"2026-07-05T11:42:06.946945+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/WE3FYVOQHTYBVQ72ALHNUSG23V","json":"https://pith.science/pith/WE3FYVOQHTYBVQ72ALHNUSG23V.json","graph_json":"https://pith.science/api/pith-number/WE3FYVOQHTYBVQ72ALHNUSG23V/graph.json","events_json":"https://pith.science/api/pith-number/WE3FYVOQHTYBVQ72ALHNUSG23V/events.json","paper":"https://pith.science/paper/WE3FYVOQ"},"agent_actions":{"view_html":"https://pith.science/pith/WE3FYVOQHTYBVQ72ALHNUSG23V","download_json":"https://pith.science/pith/WE3FYVOQHTYBVQ72ALHNUSG23V.json","view_paper":"https://pith.science/paper/WE3FYVOQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.17399&json=true","fetch_graph":"https://pith.science/api/pith-number/WE3FYVOQHTYBVQ72ALHNUSG23V/graph.json","fetch_events":"https://pith.science/api/pith-number/WE3FYVOQHTYBVQ72ALHNUSG23V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WE3FYVOQHTYBVQ72ALHNUSG23V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WE3FYVOQHTYBVQ72ALHNUSG23V/action/storage_attestation","attest_author":"https://pith.science/pith/WE3FYVOQHTYBVQ72ALHNUSG23V/action/author_attestation","sign_citation":"https://pith.science/pith/WE3FYVOQHTYBVQ72ALHNUSG23V/action/citation_signature","submit_replication":"https://pith.science/pith/WE3FYVOQHTYBVQ72ALHNUSG23V/action/replication_record"}},"created_at":"2026-07-05T11:42:06.946945+00:00","updated_at":"2026-07-05T11:42:06.946945+00:00"}