{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SXFAZ4IQCVO4T7YU6NZAQ2I7B2","short_pith_number":"pith:SXFAZ4IQ","schema_version":"1.0","canonical_sha256":"95ca0cf110155dc9ff14f37208691f0ea92dcac34762da85b30c790f40fe592c","source":{"kind":"arxiv","id":"2606.06073","version":1},"attestation_state":"computed","paper":{"title":"Edge-Aware Curvature Modeling for Graph Understanding in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Hongyang Dong, Shiping Wang, Xinjie Ye, Yuhong Chen, Zhenghong Lin, Zhibin Shi","submitted_at":"2026-06-04T12:12:34Z","abstract_excerpt":"Recently, graph-aware Large Language Models (LLMs) have shown promising capabilities in jointly modeling graph-structured data and textual information. Existing approaches typically employ a graph encoder and a frozen LLM to obtain node representations from graph and textual views, followed by node-level alignment to bridge the two modalities. However, such alignment mechanisms primarily focus on node information while overlooking edge-level structures, leading to suboptimal information propagation across views. In this work, we conduct a comprehensive theoretical analysis to uncover why node-"},"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":"2606.06073","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-06-04T12:12:34Z","cross_cats_sorted":[],"title_canon_sha256":"30f5aa9a017d6e0ee49f8e46a60b1493c52d03eb632da23f7ea242e2dcff1879","abstract_canon_sha256":"6a3a829e7afc881403ddaa5140082bc4766f797b40f1944c5e89555018c36f2b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:15:32.104200Z","signature_b64":"oc9WBy8/8XrLkbZj7jTv6XQhZhoLTM4s7CTrZb+wn5TzgANs0Lxlbaiqota7ve6ry1qyQRAXZ90t9PKY/GxuCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95ca0cf110155dc9ff14f37208691f0ea92dcac34762da85b30c790f40fe592c","last_reissued_at":"2026-06-05T01:15:32.103773Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:15:32.103773Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Edge-Aware Curvature Modeling for Graph Understanding in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Hongyang Dong, Shiping Wang, Xinjie Ye, Yuhong Chen, Zhenghong Lin, Zhibin Shi","submitted_at":"2026-06-04T12:12:34Z","abstract_excerpt":"Recently, graph-aware Large Language Models (LLMs) have shown promising capabilities in jointly modeling graph-structured data and textual information. Existing approaches typically employ a graph encoder and a frozen LLM to obtain node representations from graph and textual views, followed by node-level alignment to bridge the two modalities. However, such alignment mechanisms primarily focus on node information while overlooking edge-level structures, leading to suboptimal information propagation across views. In this work, we conduct a comprehensive theoretical analysis to uncover why node-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06073","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/2606.06073/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":"2606.06073","created_at":"2026-06-05T01:15:32.103849+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.06073v1","created_at":"2026-06-05T01:15:32.103849+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06073","created_at":"2026-06-05T01:15:32.103849+00:00"},{"alias_kind":"pith_short_12","alias_value":"SXFAZ4IQCVO4","created_at":"2026-06-05T01:15:32.103849+00:00"},{"alias_kind":"pith_short_16","alias_value":"SXFAZ4IQCVO4T7YU","created_at":"2026-06-05T01:15:32.103849+00:00"},{"alias_kind":"pith_short_8","alias_value":"SXFAZ4IQ","created_at":"2026-06-05T01:15:32.103849+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/SXFAZ4IQCVO4T7YU6NZAQ2I7B2","json":"https://pith.science/pith/SXFAZ4IQCVO4T7YU6NZAQ2I7B2.json","graph_json":"https://pith.science/api/pith-number/SXFAZ4IQCVO4T7YU6NZAQ2I7B2/graph.json","events_json":"https://pith.science/api/pith-number/SXFAZ4IQCVO4T7YU6NZAQ2I7B2/events.json","paper":"https://pith.science/paper/SXFAZ4IQ"},"agent_actions":{"view_html":"https://pith.science/pith/SXFAZ4IQCVO4T7YU6NZAQ2I7B2","download_json":"https://pith.science/pith/SXFAZ4IQCVO4T7YU6NZAQ2I7B2.json","view_paper":"https://pith.science/paper/SXFAZ4IQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.06073&json=true","fetch_graph":"https://pith.science/api/pith-number/SXFAZ4IQCVO4T7YU6NZAQ2I7B2/graph.json","fetch_events":"https://pith.science/api/pith-number/SXFAZ4IQCVO4T7YU6NZAQ2I7B2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SXFAZ4IQCVO4T7YU6NZAQ2I7B2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SXFAZ4IQCVO4T7YU6NZAQ2I7B2/action/storage_attestation","attest_author":"https://pith.science/pith/SXFAZ4IQCVO4T7YU6NZAQ2I7B2/action/author_attestation","sign_citation":"https://pith.science/pith/SXFAZ4IQCVO4T7YU6NZAQ2I7B2/action/citation_signature","submit_replication":"https://pith.science/pith/SXFAZ4IQCVO4T7YU6NZAQ2I7B2/action/replication_record"}},"created_at":"2026-06-05T01:15:32.103849+00:00","updated_at":"2026-06-05T01:15:32.103849+00:00"}