{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:M2W6VPURXCDH53XIMXCXO75QR4","short_pith_number":"pith:M2W6VPUR","schema_version":"1.0","canonical_sha256":"66adeabe91b8867eeee865c5777fb08f378387c4525b2dc51b5c2ebed0c96020","source":{"kind":"arxiv","id":"2412.12456","version":1},"attestation_state":"computed","paper":{"title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.DB"],"primary_cat":"cs.LG","authors_text":"Guoren Wang, Hanwen Cui, Jiayi Wu, Jishuo Jia, Rong-Hua Li, Xunkai Li, Zhengyu Wu","submitted_at":"2024-12-17T01:41:17Z","abstract_excerpt":"With the increasing prevalence of cross-domain Text-Attributed Graph (TAG) Data (e.g., citation networks, recommendation systems, social networks, and ai4science), the integration of Graph Neural Networks (GNNs) and Large Language Models (LLMs) into a unified Model architecture (e.g., LLM as enhancer, LLM as collaborators, LLM as predictor) has emerged as a promising technological paradigm. The core of this new graph learning paradigm lies in the synergistic combination of GNNs' ability to capture complex structural relationships and LLMs' proficiency in understanding informative contexts from"},"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":"2412.12456","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-17T01:41:17Z","cross_cats_sorted":["cs.AI","cs.CL","cs.DB"],"title_canon_sha256":"441ff8cede1c6d57e68b26caefc40db15ed3e7d87708e99feea6d7da9248ad9f","abstract_canon_sha256":"e7bb5878810186fda647ade38e5c3346cbd63394f82f997fea11c038f1c17311"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:50:15.190410Z","signature_b64":"+ET2Zm6MisVNX9PLoXwexFMCiBcMnF8nkqHU2NKMqn0/hg/+LZlQWBpsmxgx1n5feSCYOwS0n7Z6yb72wOVOBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66adeabe91b8867eeee865c5777fb08f378387c4525b2dc51b5c2ebed0c96020","last_reissued_at":"2026-07-05T09:50:15.189946Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:50:15.189946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.DB"],"primary_cat":"cs.LG","authors_text":"Guoren Wang, Hanwen Cui, Jiayi Wu, Jishuo Jia, Rong-Hua Li, Xunkai Li, Zhengyu Wu","submitted_at":"2024-12-17T01:41:17Z","abstract_excerpt":"With the increasing prevalence of cross-domain Text-Attributed Graph (TAG) Data (e.g., citation networks, recommendation systems, social networks, and ai4science), the integration of Graph Neural Networks (GNNs) and Large Language Models (LLMs) into a unified Model architecture (e.g., LLM as enhancer, LLM as collaborators, LLM as predictor) has emerged as a promising technological paradigm. The core of this new graph learning paradigm lies in the synergistic combination of GNNs' ability to capture complex structural relationships and LLMs' proficiency in understanding informative contexts from"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.12456","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/2412.12456/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":"2412.12456","created_at":"2026-07-05T09:50:15.190002+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.12456v1","created_at":"2026-07-05T09:50:15.190002+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.12456","created_at":"2026-07-05T09:50:15.190002+00:00"},{"alias_kind":"pith_short_12","alias_value":"M2W6VPURXCDH","created_at":"2026-07-05T09:50:15.190002+00:00"},{"alias_kind":"pith_short_16","alias_value":"M2W6VPURXCDH53XI","created_at":"2026-07-05T09:50:15.190002+00:00"},{"alias_kind":"pith_short_8","alias_value":"M2W6VPUR","created_at":"2026-07-05T09:50:15.190002+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09484","citing_title":"Detecting Differences Is Not Understanding Structure: Large Language Models Fail at Graph Isomorphism","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2510.08952","citing_title":"When LLM Agents Meet Graph Optimization: An Automated Data Quality Improvement Approach","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M2W6VPURXCDH53XIMXCXO75QR4","json":"https://pith.science/pith/M2W6VPURXCDH53XIMXCXO75QR4.json","graph_json":"https://pith.science/api/pith-number/M2W6VPURXCDH53XIMXCXO75QR4/graph.json","events_json":"https://pith.science/api/pith-number/M2W6VPURXCDH53XIMXCXO75QR4/events.json","paper":"https://pith.science/paper/M2W6VPUR"},"agent_actions":{"view_html":"https://pith.science/pith/M2W6VPURXCDH53XIMXCXO75QR4","download_json":"https://pith.science/pith/M2W6VPURXCDH53XIMXCXO75QR4.json","view_paper":"https://pith.science/paper/M2W6VPUR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.12456&json=true","fetch_graph":"https://pith.science/api/pith-number/M2W6VPURXCDH53XIMXCXO75QR4/graph.json","fetch_events":"https://pith.science/api/pith-number/M2W6VPURXCDH53XIMXCXO75QR4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M2W6VPURXCDH53XIMXCXO75QR4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M2W6VPURXCDH53XIMXCXO75QR4/action/storage_attestation","attest_author":"https://pith.science/pith/M2W6VPURXCDH53XIMXCXO75QR4/action/author_attestation","sign_citation":"https://pith.science/pith/M2W6VPURXCDH53XIMXCXO75QR4/action/citation_signature","submit_replication":"https://pith.science/pith/M2W6VPURXCDH53XIMXCXO75QR4/action/replication_record"}},"created_at":"2026-07-05T09:50:15.190002+00:00","updated_at":"2026-07-05T09:50:15.190002+00:00"}