{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JA4KTNGO7AKYLRK5X674XIU5VK","short_pith_number":"pith:JA4KTNGO","schema_version":"1.0","canonical_sha256":"4838a9b4cef81585c55dbfbfcba29daa9717fd3309af3420027112c2918593c9","source":{"kind":"arxiv","id":"2607.00052","version":1},"attestation_state":"computed","paper":{"title":"AGE: Adaptive-masking for Graph Embedding in Graph Retrieval-Augmented Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Atsushi Hashimoto, Bao Long Nguyen Huu","submitted_at":"2026-06-30T01:23:09Z","abstract_excerpt":"GraphRAG is an extension of retrieval-augmented generation (RAG) that supports large language models (LLMs) by referring to graph-structured data as external knowledge. While this technique ideally captures intricate relationships, it often struggles with graph representations for LLMs, particularly for frozen LLMs, due to the misalignment between graph-based and text-based latent features. We tackle this issue by introducing the {\\it Adaptive-masking for Graph Embedding (AGE)}. AGE employs a Transformer in a mask-based self-supervised learning (SSL) approach. We designed the architecture simi"},"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":"2607.00052","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-06-30T01:23:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9d0eaa7fd7e12b76fcf8ee77f87c90d99c5d75b107581aa6d1758b65c4383dba","abstract_canon_sha256":"19cf5658b9b51914987c738daec29b231f9ea3eef1896d3a46671d9e052d6484"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T00:18:32.621353Z","signature_b64":"7N0A9kLNyzirKeDzRe/yB0aJSMEPz79gktdLUOv3dGc64O3f0aRxjATMn10FJkhII/+Yp0+84HJ4dwmRVq7fCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4838a9b4cef81585c55dbfbfcba29daa9717fd3309af3420027112c2918593c9","last_reissued_at":"2026-07-02T00:18:32.620823Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T00:18:32.620823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AGE: Adaptive-masking for Graph Embedding in Graph Retrieval-Augmented Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Atsushi Hashimoto, Bao Long Nguyen Huu","submitted_at":"2026-06-30T01:23:09Z","abstract_excerpt":"GraphRAG is an extension of retrieval-augmented generation (RAG) that supports large language models (LLMs) by referring to graph-structured data as external knowledge. While this technique ideally captures intricate relationships, it often struggles with graph representations for LLMs, particularly for frozen LLMs, due to the misalignment between graph-based and text-based latent features. We tackle this issue by introducing the {\\it Adaptive-masking for Graph Embedding (AGE)}. AGE employs a Transformer in a mask-based self-supervised learning (SSL) approach. We designed the architecture simi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.00052","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/2607.00052/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":"2607.00052","created_at":"2026-07-02T00:18:32.620879+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.00052v1","created_at":"2026-07-02T00:18:32.620879+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.00052","created_at":"2026-07-02T00:18:32.620879+00:00"},{"alias_kind":"pith_short_12","alias_value":"JA4KTNGO7AKY","created_at":"2026-07-02T00:18:32.620879+00:00"},{"alias_kind":"pith_short_16","alias_value":"JA4KTNGO7AKYLRK5","created_at":"2026-07-02T00:18:32.620879+00:00"},{"alias_kind":"pith_short_8","alias_value":"JA4KTNGO","created_at":"2026-07-02T00:18:32.620879+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/JA4KTNGO7AKYLRK5X674XIU5VK","json":"https://pith.science/pith/JA4KTNGO7AKYLRK5X674XIU5VK.json","graph_json":"https://pith.science/api/pith-number/JA4KTNGO7AKYLRK5X674XIU5VK/graph.json","events_json":"https://pith.science/api/pith-number/JA4KTNGO7AKYLRK5X674XIU5VK/events.json","paper":"https://pith.science/paper/JA4KTNGO"},"agent_actions":{"view_html":"https://pith.science/pith/JA4KTNGO7AKYLRK5X674XIU5VK","download_json":"https://pith.science/pith/JA4KTNGO7AKYLRK5X674XIU5VK.json","view_paper":"https://pith.science/paper/JA4KTNGO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.00052&json=true","fetch_graph":"https://pith.science/api/pith-number/JA4KTNGO7AKYLRK5X674XIU5VK/graph.json","fetch_events":"https://pith.science/api/pith-number/JA4KTNGO7AKYLRK5X674XIU5VK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JA4KTNGO7AKYLRK5X674XIU5VK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JA4KTNGO7AKYLRK5X674XIU5VK/action/storage_attestation","attest_author":"https://pith.science/pith/JA4KTNGO7AKYLRK5X674XIU5VK/action/author_attestation","sign_citation":"https://pith.science/pith/JA4KTNGO7AKYLRK5X674XIU5VK/action/citation_signature","submit_replication":"https://pith.science/pith/JA4KTNGO7AKYLRK5X674XIU5VK/action/replication_record"}},"created_at":"2026-07-02T00:18:32.620879+00:00","updated_at":"2026-07-02T00:18:32.620879+00:00"}