{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:WE3FYVOQHTYBVQ72ALHNUSG23V","short_pith_number":"pith:WE3FYVOQ","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"},"canonical_sha256":"b1365c55d03cf01ac3fa02ceda48dadd5be3e8dfc14f5776e7d642b0dcea4763","source":{"kind":"arxiv","id":"2507.17399","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.17399","created_at":"2026-07-05T11:42:06Z"},{"alias_kind":"arxiv_version","alias_value":"2507.17399v1","created_at":"2026-07-05T11:42:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.17399","created_at":"2026-07-05T11:42:06Z"},{"alias_kind":"pith_short_12","alias_value":"WE3FYVOQHTYB","created_at":"2026-07-05T11:42:06Z"},{"alias_kind":"pith_short_16","alias_value":"WE3FYVOQHTYBVQ72","created_at":"2026-07-05T11:42:06Z"},{"alias_kind":"pith_short_8","alias_value":"WE3FYVOQ","created_at":"2026-07-05T11:42:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:WE3FYVOQHTYBVQ72ALHNUSG23V","target":"record","payload":{"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"},"canonical_sha256":"b1365c55d03cf01ac3fa02ceda48dadd5be3e8dfc14f5776e7d642b0dcea4763","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"},"source_kind":"arxiv","source_id":"2507.17399","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:42:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BWCB/1yTb6k2X443939MhEtXYTc8JZ2jhqYvB64/Hhp6Le/pVWXIKnMblifM3ndQVbABYiA1bmwzZsjLwwwABQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:05:47.207274Z"},"content_sha256":"02f6a5dd2e091cfec52ecf2205c195a3ec55173c2a2893dfea3ecd85cff27c3c","schema_version":"1.0","event_id":"sha256:02f6a5dd2e091cfec52ecf2205c195a3ec55173c2a2893dfea3ecd85cff27c3c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:WE3FYVOQHTYBVQ72ALHNUSG23V","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:42:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"y0upyJYAlPpC/LDRxIgh/m0hmTwFQeAFfBrXSPxVjCnrAn65WaUkmz8R9U7QiyLP1CeRfDZ+dBvmbK43Qvi9Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T11:05:47.207670Z"},"content_sha256":"43fcae9aae17a8104e58b45c9cf4d9fa2d49170177c6bc058dca0d2443ecbae6","schema_version":"1.0","event_id":"sha256:43fcae9aae17a8104e58b45c9cf4d9fa2d49170177c6bc058dca0d2443ecbae6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WE3FYVOQHTYBVQ72ALHNUSG23V/bundle.json","state_url":"https://pith.science/pith/WE3FYVOQHTYBVQ72ALHNUSG23V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WE3FYVOQHTYBVQ72ALHNUSG23V/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-07T11:05:47Z","links":{"resolver":"https://pith.science/pith/WE3FYVOQHTYBVQ72ALHNUSG23V","bundle":"https://pith.science/pith/WE3FYVOQHTYBVQ72ALHNUSG23V/bundle.json","state":"https://pith.science/pith/WE3FYVOQHTYBVQ72ALHNUSG23V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WE3FYVOQHTYBVQ72ALHNUSG23V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WE3FYVOQHTYBVQ72ALHNUSG23V","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c3b28df60eb06d2b9698668c5125d57b711e82faef562819299c077d9943e820","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-23T10:54:24Z","title_canon_sha256":"a0fc1210d2524e5afe33368bd560eaefe0574f83d6d1aaa9b3dad344b306838e"},"schema_version":"1.0","source":{"id":"2507.17399","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.17399","created_at":"2026-07-05T11:42:06Z"},{"alias_kind":"arxiv_version","alias_value":"2507.17399v1","created_at":"2026-07-05T11:42:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.17399","created_at":"2026-07-05T11:42:06Z"},{"alias_kind":"pith_short_12","alias_value":"WE3FYVOQHTYB","created_at":"2026-07-05T11:42:06Z"},{"alias_kind":"pith_short_16","alias_value":"WE3FYVOQHTYBVQ72","created_at":"2026-07-05T11:42:06Z"},{"alias_kind":"pith_short_8","alias_value":"WE3FYVOQ","created_at":"2026-07-05T11:42:06Z"}],"graph_snapshots":[{"event_id":"sha256:43fcae9aae17a8104e58b45c9cf4d9fa2d49170177c6bc058dca0d2443ecbae6","target":"graph","created_at":"2026-07-05T11:42:06Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2507.17399/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chenxin Diao, Jeff Z. Pan, Pascual Merita, Pavlos Vougiouklis, Zhili Shen","cross_cats":["cs.AI","cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-23T10:54:24Z","title":"Millions of $\\text{GeAR}$-s: Extending GraphRAG to Millions of Documents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.17399","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:02f6a5dd2e091cfec52ecf2205c195a3ec55173c2a2893dfea3ecd85cff27c3c","target":"record","created_at":"2026-07-05T11:42:06Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c3b28df60eb06d2b9698668c5125d57b711e82faef562819299c077d9943e820","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-23T10:54:24Z","title_canon_sha256":"a0fc1210d2524e5afe33368bd560eaefe0574f83d6d1aaa9b3dad344b306838e"},"schema_version":"1.0","source":{"id":"2507.17399","kind":"arxiv","version":1}},"canonical_sha256":"b1365c55d03cf01ac3fa02ceda48dadd5be3e8dfc14f5776e7d642b0dcea4763","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b1365c55d03cf01ac3fa02ceda48dadd5be3e8dfc14f5776e7d642b0dcea4763","first_computed_at":"2026-07-05T11:42:06.946887Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:42:06.946887Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/ezwsIGkkAidd1DNUA1LbXiiENixW/Ufc2Roy+sxN87gI1t29lWN95nyMNhfG8mDtnmEVCiB2ZaZPFhvaXizDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:42:06.947380Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.17399","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:02f6a5dd2e091cfec52ecf2205c195a3ec55173c2a2893dfea3ecd85cff27c3c","sha256:43fcae9aae17a8104e58b45c9cf4d9fa2d49170177c6bc058dca0d2443ecbae6"],"state_sha256":"ebfefd382ce6786711b819cb536e267ff9e62261a88ce7db8a3d8517b32e5b4a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R9vDcg9weR7LwZavA0602/ebTHdgRtccXHoIOZIdPqUWf9ugkxjDfJIilhmRr+2xgPdeNsIZWOa0Nk3RNJYFDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T11:05:47.209619Z","bundle_sha256":"9b131cd028c65bc40aaa72ba1c822c960e4153a1850a8ba455e42f16210b09cf"}}