{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RQKFL476CH3HYUW5PYX6GPOGY7","short_pith_number":"pith:RQKFL476","schema_version":"1.0","canonical_sha256":"8c1455f3fe11f67c52dd7e2fe33dc6c7cb2dc44b71c348ed1336e7cfeb56cdc6","source":{"kind":"arxiv","id":"2606.30291","version":1},"attestation_state":"computed","paper":{"title":"PromptGNN-sim: Deep Fusion and Alignment of GNN and LLMs for Text-Attributed Graph Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alexandra I. Cristea, Zhifei Hu","submitted_at":"2026-06-29T13:35:05Z","abstract_excerpt":"Text-Attributed Graphs (TAGs) combine textual semantics with graph structure and are central to many graph learning tasks. However, existing fusion methods often treat text and structure as separate inputs in a shallow, one-way pipeline, which limits deep interaction between modalities and weakens performance under sparse connectivity or cross-graph generalisation. To address this issue, we propose PromptGNN-sim, a bi-directional structure-semantic fusion framework for collaborative GNN-LLM learning. PromptGNN-sim uses a Graph Attention Network (GAT) for semantically aware neighborhood selecti"},"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":"2606.30291","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-29T13:35:05Z","cross_cats_sorted":[],"title_canon_sha256":"fd7de065d5b4518d3f531cbf987af172683aabc80c667171a2cf5c4c7b2b3073","abstract_canon_sha256":"acd8f3d2d369506986cbd5c3ea8b9062710e2de32c67a2aeb1d3c565701ec3bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:17:57.631505Z","signature_b64":"ttW6eL8zT7JqCMoqjLpfTB5yFyAQTNwqNnMKBtEQus4YtWJfmjS4J+t6dcb5zIJsMQM3e1OYnGEc+odcw8ORBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c1455f3fe11f67c52dd7e2fe33dc6c7cb2dc44b71c348ed1336e7cfeb56cdc6","last_reissued_at":"2026-06-30T02:17:57.630988Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:17:57.630988Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PromptGNN-sim: Deep Fusion and Alignment of GNN and LLMs for Text-Attributed Graph Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alexandra I. Cristea, Zhifei Hu","submitted_at":"2026-06-29T13:35:05Z","abstract_excerpt":"Text-Attributed Graphs (TAGs) combine textual semantics with graph structure and are central to many graph learning tasks. However, existing fusion methods often treat text and structure as separate inputs in a shallow, one-way pipeline, which limits deep interaction between modalities and weakens performance under sparse connectivity or cross-graph generalisation. To address this issue, we propose PromptGNN-sim, a bi-directional structure-semantic fusion framework for collaborative GNN-LLM learning. PromptGNN-sim uses a Graph Attention Network (GAT) for semantically aware neighborhood selecti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.30291","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/2606.30291/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":"2606.30291","created_at":"2026-06-30T02:17:57.631055+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.30291v1","created_at":"2026-06-30T02:17:57.631055+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.30291","created_at":"2026-06-30T02:17:57.631055+00:00"},{"alias_kind":"pith_short_12","alias_value":"RQKFL476CH3H","created_at":"2026-06-30T02:17:57.631055+00:00"},{"alias_kind":"pith_short_16","alias_value":"RQKFL476CH3HYUW5","created_at":"2026-06-30T02:17:57.631055+00:00"},{"alias_kind":"pith_short_8","alias_value":"RQKFL476","created_at":"2026-06-30T02:17:57.631055+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/RQKFL476CH3HYUW5PYX6GPOGY7","json":"https://pith.science/pith/RQKFL476CH3HYUW5PYX6GPOGY7.json","graph_json":"https://pith.science/api/pith-number/RQKFL476CH3HYUW5PYX6GPOGY7/graph.json","events_json":"https://pith.science/api/pith-number/RQKFL476CH3HYUW5PYX6GPOGY7/events.json","paper":"https://pith.science/paper/RQKFL476"},"agent_actions":{"view_html":"https://pith.science/pith/RQKFL476CH3HYUW5PYX6GPOGY7","download_json":"https://pith.science/pith/RQKFL476CH3HYUW5PYX6GPOGY7.json","view_paper":"https://pith.science/paper/RQKFL476","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.30291&json=true","fetch_graph":"https://pith.science/api/pith-number/RQKFL476CH3HYUW5PYX6GPOGY7/graph.json","fetch_events":"https://pith.science/api/pith-number/RQKFL476CH3HYUW5PYX6GPOGY7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RQKFL476CH3HYUW5PYX6GPOGY7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RQKFL476CH3HYUW5PYX6GPOGY7/action/storage_attestation","attest_author":"https://pith.science/pith/RQKFL476CH3HYUW5PYX6GPOGY7/action/author_attestation","sign_citation":"https://pith.science/pith/RQKFL476CH3HYUW5PYX6GPOGY7/action/citation_signature","submit_replication":"https://pith.science/pith/RQKFL476CH3HYUW5PYX6GPOGY7/action/replication_record"}},"created_at":"2026-06-30T02:17:57.631055+00:00","updated_at":"2026-06-30T02:17:57.631055+00:00"}