{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MHRNZC7YHSRG2V47PRZUBSP5I6","short_pith_number":"pith:MHRNZC7Y","schema_version":"1.0","canonical_sha256":"61e2dc8bf83ca26d579f7c7340c9fd47b5694d7c480c27154aa63648392aedfb","source":{"kind":"arxiv","id":"2407.12860","version":1},"attestation_state":"computed","paper":{"title":"STAGE: Simplified Text-Attributed Graph Embeddings Using Pre-trained LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aaron Zolnai-Lucas, Chris Hokamp, Jack Boylan, Parsa Ghaffari","submitted_at":"2024-07-10T08:50:25Z","abstract_excerpt":"We present Simplified Text-Attributed Graph Embeddings (STAGE), a straightforward yet effective method for enhancing node features in Graph Neural Network (GNN) models that encode Text-Attributed Graphs (TAGs). Our approach leverages Large-Language Models (LLMs) to generate embeddings for textual attributes. STAGE achieves competitive results on various node classification benchmarks while also maintaining a simplicity in implementation relative to current state-of-the-art (SoTA) techniques. We show that utilizing pre-trained LLMs as embedding generators provides robust features for ensemble G"},"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":"2407.12860","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-10T08:50:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0497e74df34d45ea1b640c32bd24271722c391b51715734eab50c93927d762db","abstract_canon_sha256":"1c02d14aa45a520de5684d607c4adf8b26d40db8ba473b56f36d9ba8641b968b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:45:12.744805Z","signature_b64":"OzYEMundiL9zlAxHpW0DZIKzwJxtjO5vwKB9vLHcb18xEvVJ7sNq7/9eJfK14/FC/O7aQqtvpABf5Vu1vec7Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"61e2dc8bf83ca26d579f7c7340c9fd47b5694d7c480c27154aa63648392aedfb","last_reissued_at":"2026-07-05T08:45:12.744365Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:45:12.744365Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"STAGE: Simplified Text-Attributed Graph Embeddings Using Pre-trained LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aaron Zolnai-Lucas, Chris Hokamp, Jack Boylan, Parsa Ghaffari","submitted_at":"2024-07-10T08:50:25Z","abstract_excerpt":"We present Simplified Text-Attributed Graph Embeddings (STAGE), a straightforward yet effective method for enhancing node features in Graph Neural Network (GNN) models that encode Text-Attributed Graphs (TAGs). Our approach leverages Large-Language Models (LLMs) to generate embeddings for textual attributes. STAGE achieves competitive results on various node classification benchmarks while also maintaining a simplicity in implementation relative to current state-of-the-art (SoTA) techniques. We show that utilizing pre-trained LLMs as embedding generators provides robust features for ensemble G"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12860","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/2407.12860/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":"2407.12860","created_at":"2026-07-05T08:45:12.744424+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.12860v1","created_at":"2026-07-05T08:45:12.744424+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12860","created_at":"2026-07-05T08:45:12.744424+00:00"},{"alias_kind":"pith_short_12","alias_value":"MHRNZC7YHSRG","created_at":"2026-07-05T08:45:12.744424+00:00"},{"alias_kind":"pith_short_16","alias_value":"MHRNZC7YHSRG2V47","created_at":"2026-07-05T08:45:12.744424+00:00"},{"alias_kind":"pith_short_8","alias_value":"MHRNZC7Y","created_at":"2026-07-05T08:45:12.744424+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/MHRNZC7YHSRG2V47PRZUBSP5I6","json":"https://pith.science/pith/MHRNZC7YHSRG2V47PRZUBSP5I6.json","graph_json":"https://pith.science/api/pith-number/MHRNZC7YHSRG2V47PRZUBSP5I6/graph.json","events_json":"https://pith.science/api/pith-number/MHRNZC7YHSRG2V47PRZUBSP5I6/events.json","paper":"https://pith.science/paper/MHRNZC7Y"},"agent_actions":{"view_html":"https://pith.science/pith/MHRNZC7YHSRG2V47PRZUBSP5I6","download_json":"https://pith.science/pith/MHRNZC7YHSRG2V47PRZUBSP5I6.json","view_paper":"https://pith.science/paper/MHRNZC7Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.12860&json=true","fetch_graph":"https://pith.science/api/pith-number/MHRNZC7YHSRG2V47PRZUBSP5I6/graph.json","fetch_events":"https://pith.science/api/pith-number/MHRNZC7YHSRG2V47PRZUBSP5I6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MHRNZC7YHSRG2V47PRZUBSP5I6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MHRNZC7YHSRG2V47PRZUBSP5I6/action/storage_attestation","attest_author":"https://pith.science/pith/MHRNZC7YHSRG2V47PRZUBSP5I6/action/author_attestation","sign_citation":"https://pith.science/pith/MHRNZC7YHSRG2V47PRZUBSP5I6/action/citation_signature","submit_replication":"https://pith.science/pith/MHRNZC7YHSRG2V47PRZUBSP5I6/action/replication_record"}},"created_at":"2026-07-05T08:45:12.744424+00:00","updated_at":"2026-07-05T08:45:12.744424+00:00"}