{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:OFYCPJ45IUZTZ3QS6KDZFZVO4T","short_pith_number":"pith:OFYCPJ45","schema_version":"1.0","canonical_sha256":"717027a79d45333cee12f28792e6aee4dba7f19a36376e9b3641574158528d66","source":{"kind":"arxiv","id":"2308.02565","version":1},"attestation_state":"computed","paper":{"title":"SimTeG: A Frustratingly Simple Approach Improves Textual Graph Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Junxian He, Keyu Duan, Qian Liu, Qizhe Xie, Shuicheng Yan, Tat-Seng Chua, Wei Tsang Ooi","submitted_at":"2023-08-03T07:00:04Z","abstract_excerpt":"Textual graphs (TGs) are graphs whose nodes correspond to text (sentences or documents), which are widely prevalent. The representation learning of TGs involves two stages: (i) unsupervised feature extraction and (ii) supervised graph representation learning. In recent years, extensive efforts have been devoted to the latter stage, where Graph Neural Networks (GNNs) have dominated. However, the former stage for most existing graph benchmarks still relies on traditional feature engineering techniques. More recently, with the rapid development of language models (LMs), researchers have focused o"},"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":"2308.02565","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-03T07:00:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9e8502509caec04e2c73e5064cb9ddff5d01b27c4485965dc47570a71b9d0883","abstract_canon_sha256":"68b8a9a4a79f6d8fdd5c42cc72687d60876790e3e3520ff8be652456450aed38"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:38:04.571578Z","signature_b64":"jSBmbBhAlVEcZMToeN6OyWehKNl5SK92HXfBsEARzqa+BZ6vwPZ5SiPJ3BBx/W0zpiWiObvK8v6wvIdPrAsjAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"717027a79d45333cee12f28792e6aee4dba7f19a36376e9b3641574158528d66","last_reissued_at":"2026-07-05T06:38:04.571133Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:38:04.571133Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SimTeG: A Frustratingly Simple Approach Improves Textual Graph Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Junxian He, Keyu Duan, Qian Liu, Qizhe Xie, Shuicheng Yan, Tat-Seng Chua, Wei Tsang Ooi","submitted_at":"2023-08-03T07:00:04Z","abstract_excerpt":"Textual graphs (TGs) are graphs whose nodes correspond to text (sentences or documents), which are widely prevalent. The representation learning of TGs involves two stages: (i) unsupervised feature extraction and (ii) supervised graph representation learning. In recent years, extensive efforts have been devoted to the latter stage, where Graph Neural Networks (GNNs) have dominated. However, the former stage for most existing graph benchmarks still relies on traditional feature engineering techniques. More recently, with the rapid development of language models (LMs), researchers have focused o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.02565","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/2308.02565/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":"2308.02565","created_at":"2026-07-05T06:38:04.571201+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.02565v1","created_at":"2026-07-05T06:38:04.571201+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.02565","created_at":"2026-07-05T06:38:04.571201+00:00"},{"alias_kind":"pith_short_12","alias_value":"OFYCPJ45IUZT","created_at":"2026-07-05T06:38:04.571201+00:00"},{"alias_kind":"pith_short_16","alias_value":"OFYCPJ45IUZTZ3QS","created_at":"2026-07-05T06:38:04.571201+00:00"},{"alias_kind":"pith_short_8","alias_value":"OFYCPJ45","created_at":"2026-07-05T06:38:04.571201+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22975","citing_title":"TaLK: Text-attributed Graph Dataset Distillation via Coupling Language Model with Graph-Aware Kernel","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11898","citing_title":"GraspLLM: Towards Zero-Shot Generalization on Text-Attributed Graphs with LLMs","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03712","citing_title":"When Graph Tokens Sink: A Mechanistic Analysis of Graph Language Models","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2606.32016","citing_title":"FedLAB: Traceable Semantic Codebooks for Federated Multimodal Graph Foundation Learning","ref_index":173,"is_internal_anchor":false},{"citing_arxiv_id":"2504.02343","citing_title":"Toward General and Robust LLM-enhanced Text-attributed Graph Learning","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21858","citing_title":"Hypergraph as Language","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2603.01410","citing_title":"GraphScout: Empowering Large Language Models with Intrinsic Exploration Ability for Agentic Graph Reasoning","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03514","citing_title":"Revisiting Graph-Tokenizing Large Language Models: A Systematic Evaluation of Graph Token Understanding","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17411","citing_title":"DuConTE: Dual-Granularity Text Encoder with Topology-Constrained Attention for Text-attributed Graphs","ref_index":93,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OFYCPJ45IUZTZ3QS6KDZFZVO4T","json":"https://pith.science/pith/OFYCPJ45IUZTZ3QS6KDZFZVO4T.json","graph_json":"https://pith.science/api/pith-number/OFYCPJ45IUZTZ3QS6KDZFZVO4T/graph.json","events_json":"https://pith.science/api/pith-number/OFYCPJ45IUZTZ3QS6KDZFZVO4T/events.json","paper":"https://pith.science/paper/OFYCPJ45"},"agent_actions":{"view_html":"https://pith.science/pith/OFYCPJ45IUZTZ3QS6KDZFZVO4T","download_json":"https://pith.science/pith/OFYCPJ45IUZTZ3QS6KDZFZVO4T.json","view_paper":"https://pith.science/paper/OFYCPJ45","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.02565&json=true","fetch_graph":"https://pith.science/api/pith-number/OFYCPJ45IUZTZ3QS6KDZFZVO4T/graph.json","fetch_events":"https://pith.science/api/pith-number/OFYCPJ45IUZTZ3QS6KDZFZVO4T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OFYCPJ45IUZTZ3QS6KDZFZVO4T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OFYCPJ45IUZTZ3QS6KDZFZVO4T/action/storage_attestation","attest_author":"https://pith.science/pith/OFYCPJ45IUZTZ3QS6KDZFZVO4T/action/author_attestation","sign_citation":"https://pith.science/pith/OFYCPJ45IUZTZ3QS6KDZFZVO4T/action/citation_signature","submit_replication":"https://pith.science/pith/OFYCPJ45IUZTZ3QS6KDZFZVO4T/action/replication_record"}},"created_at":"2026-07-05T06:38:04.571201+00:00","updated_at":"2026-07-05T06:38:04.571201+00:00"}