{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:424XTHUQFTC4N7HKR3OXA3G63S","short_pith_number":"pith:424XTHUQ","schema_version":"1.0","canonical_sha256":"e6b9799e902cc5c6fcea8edd706cdedc8d57a02aadb83210a8bd0bfb157bc71f","source":{"kind":"arxiv","id":"2402.12984","version":1},"attestation_state":"computed","paper":{"title":"Can GNN be Good Adapter for LLMs?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dezheng Bao, Kaiqiao Han, Qi Zhu, Quanjin Tao, Xuanwen Huang, Yang Yang, Ziwei Chai","submitted_at":"2024-02-20T13:13:13Z","abstract_excerpt":"Recently, large language models (LLMs) have demonstrated superior capabilities in understanding and zero-shot learning on textual data, promising significant advances for many text-related domains. In the graph domain, various real-world scenarios also involve textual data, where tasks and node features can be described by text. These text-attributed graphs (TAGs) have broad applications in social media, recommendation systems, etc. Thus, this paper explores how to utilize LLMs to model TAGs. Previous methods for TAG modeling are based on million-scale LMs. When scaled up to billion-scale LLMs"},"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":"2402.12984","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-20T13:13:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7678355108deb75406f870a75681d7e7a3577bf51e188c78cc5c74a8d0616d61","abstract_canon_sha256":"21c53e4d57951a09a0c3557f4a0d83e4de45ef098fbac4b214efbdaa5d018a75"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:47:19.330343Z","signature_b64":"Z+DGoNR3AOgvrE6aLkczQNwicKkxHS2asDbBdeV+adTQLtuPmctsnSV0QkZp6mEkuY/5lobkAvlf/0lEPdDvCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e6b9799e902cc5c6fcea8edd706cdedc8d57a02aadb83210a8bd0bfb157bc71f","last_reissued_at":"2026-07-05T07:47:19.329838Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:47:19.329838Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can GNN be Good Adapter for LLMs?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dezheng Bao, Kaiqiao Han, Qi Zhu, Quanjin Tao, Xuanwen Huang, Yang Yang, Ziwei Chai","submitted_at":"2024-02-20T13:13:13Z","abstract_excerpt":"Recently, large language models (LLMs) have demonstrated superior capabilities in understanding and zero-shot learning on textual data, promising significant advances for many text-related domains. In the graph domain, various real-world scenarios also involve textual data, where tasks and node features can be described by text. These text-attributed graphs (TAGs) have broad applications in social media, recommendation systems, etc. Thus, this paper explores how to utilize LLMs to model TAGs. Previous methods for TAG modeling are based on million-scale LMs. When scaled up to billion-scale LLMs"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.12984","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/2402.12984/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":"2402.12984","created_at":"2026-07-05T07:47:19.329899+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.12984v1","created_at":"2026-07-05T07:47:19.329899+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.12984","created_at":"2026-07-05T07:47:19.329899+00:00"},{"alias_kind":"pith_short_12","alias_value":"424XTHUQFTC4","created_at":"2026-07-05T07:47:19.329899+00:00"},{"alias_kind":"pith_short_16","alias_value":"424XTHUQFTC4N7HK","created_at":"2026-07-05T07:47:19.329899+00:00"},{"alias_kind":"pith_short_8","alias_value":"424XTHUQ","created_at":"2026-07-05T07:47:19.329899+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2504.02343","citing_title":"Toward General and Robust LLM-enhanced Text-attributed Graph Learning","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/424XTHUQFTC4N7HKR3OXA3G63S","json":"https://pith.science/pith/424XTHUQFTC4N7HKR3OXA3G63S.json","graph_json":"https://pith.science/api/pith-number/424XTHUQFTC4N7HKR3OXA3G63S/graph.json","events_json":"https://pith.science/api/pith-number/424XTHUQFTC4N7HKR3OXA3G63S/events.json","paper":"https://pith.science/paper/424XTHUQ"},"agent_actions":{"view_html":"https://pith.science/pith/424XTHUQFTC4N7HKR3OXA3G63S","download_json":"https://pith.science/pith/424XTHUQFTC4N7HKR3OXA3G63S.json","view_paper":"https://pith.science/paper/424XTHUQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.12984&json=true","fetch_graph":"https://pith.science/api/pith-number/424XTHUQFTC4N7HKR3OXA3G63S/graph.json","fetch_events":"https://pith.science/api/pith-number/424XTHUQFTC4N7HKR3OXA3G63S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/424XTHUQFTC4N7HKR3OXA3G63S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/424XTHUQFTC4N7HKR3OXA3G63S/action/storage_attestation","attest_author":"https://pith.science/pith/424XTHUQFTC4N7HKR3OXA3G63S/action/author_attestation","sign_citation":"https://pith.science/pith/424XTHUQFTC4N7HKR3OXA3G63S/action/citation_signature","submit_replication":"https://pith.science/pith/424XTHUQFTC4N7HKR3OXA3G63S/action/replication_record"}},"created_at":"2026-07-05T07:47:19.329899+00:00","updated_at":"2026-07-05T07:47:19.329899+00:00"}