{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:47XEHWK2H6Y5A2W3EEDMCRABN5","short_pith_number":"pith:47XEHWK2","schema_version":"1.0","canonical_sha256":"e7ee43d95a3fb1d06adb2106c144016f4837560f2816c3626700513bc19a4c26","source":{"kind":"arxiv","id":"2406.14683","version":2},"attestation_state":"computed","paper":{"title":"TAGLAS: An atlas of text-attributed graph datasets in the era of large graph and language models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Hao Liu, Jiarui Feng, Lecheng Kong, Mingfang Zhu, Muhan Zhang, Yixin Chen","submitted_at":"2024-06-20T19:11:35Z","abstract_excerpt":"In this report, we present TAGLAS, an atlas of text-attributed graph (TAG) datasets and benchmarks. TAGs are graphs with node and edge features represented in text, which have recently gained wide applicability in training graph-language or graph foundation models. In TAGLAS, we collect and integrate more than 23 TAG datasets with domains ranging from citation graphs to molecule graphs and tasks from node classification to graph question-answering. Unlike previous graph datasets and benchmarks, all datasets in TAGLAS have a unified node and edge text feature format, which allows a graph model "},"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":"2406.14683","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-20T19:11:35Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"73c368c4f179a1f5b94601f4b54575f47869c3d0eb669457a5c5566917004076","abstract_canon_sha256":"aa15a4b6c775cb2ad4ccdd7075e0a358ae147c1688e980b3733391e9b96540a9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:22:40.786186Z","signature_b64":"CLXHkO3xISQbf8lKMXRosfLu6wUhxhJUdGVaEsist/dMeetD6ELN0Q5GKbKmfUR4OA1VZavoIR96yRphPyYnAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7ee43d95a3fb1d06adb2106c144016f4837560f2816c3626700513bc19a4c26","last_reissued_at":"2026-07-05T09:22:40.785650Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:22:40.785650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TAGLAS: An atlas of text-attributed graph datasets in the era of large graph and language models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Hao Liu, Jiarui Feng, Lecheng Kong, Mingfang Zhu, Muhan Zhang, Yixin Chen","submitted_at":"2024-06-20T19:11:35Z","abstract_excerpt":"In this report, we present TAGLAS, an atlas of text-attributed graph (TAG) datasets and benchmarks. TAGs are graphs with node and edge features represented in text, which have recently gained wide applicability in training graph-language or graph foundation models. In TAGLAS, we collect and integrate more than 23 TAG datasets with domains ranging from citation graphs to molecule graphs and tasks from node classification to graph question-answering. Unlike previous graph datasets and benchmarks, all datasets in TAGLAS have a unified node and edge text feature format, which allows a graph model "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.14683","kind":"arxiv","version":2},"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/2406.14683/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":"2406.14683","created_at":"2026-07-05T09:22:40.785703+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.14683v2","created_at":"2026-07-05T09:22:40.785703+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.14683","created_at":"2026-07-05T09:22:40.785703+00:00"},{"alias_kind":"pith_short_12","alias_value":"47XEHWK2H6Y5","created_at":"2026-07-05T09:22:40.785703+00:00"},{"alias_kind":"pith_short_16","alias_value":"47XEHWK2H6Y5A2W3","created_at":"2026-07-05T09:22:40.785703+00:00"},{"alias_kind":"pith_short_8","alias_value":"47XEHWK2","created_at":"2026-07-05T09:22:40.785703+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29773","citing_title":"GLIP: Graph and LLM Joint Pretraining for Graph-Level Tasks","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2510.16416","citing_title":"SSL4RL: Revisiting Self-supervised Learning as Intrinsic Reward for Visual-Language Reasoning","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18579","citing_title":"S2Aligner: Pair-Efficient and Transferable Pre-Training for Sparse Text-Attributed Graphs","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18579","citing_title":"S2Aligner: Pair-Efficient and Transferable Pre-Training for Sparse Text-Attributed Graphs","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2508.07117","citing_title":"From Nodes to Narratives: Explaining Graph Neural Networks with LLMs and Graph Context","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13021","citing_title":"Rethinking Efficient Graph Coarsening via a Non-Selfishness Principle","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/47XEHWK2H6Y5A2W3EEDMCRABN5","json":"https://pith.science/pith/47XEHWK2H6Y5A2W3EEDMCRABN5.json","graph_json":"https://pith.science/api/pith-number/47XEHWK2H6Y5A2W3EEDMCRABN5/graph.json","events_json":"https://pith.science/api/pith-number/47XEHWK2H6Y5A2W3EEDMCRABN5/events.json","paper":"https://pith.science/paper/47XEHWK2"},"agent_actions":{"view_html":"https://pith.science/pith/47XEHWK2H6Y5A2W3EEDMCRABN5","download_json":"https://pith.science/pith/47XEHWK2H6Y5A2W3EEDMCRABN5.json","view_paper":"https://pith.science/paper/47XEHWK2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.14683&json=true","fetch_graph":"https://pith.science/api/pith-number/47XEHWK2H6Y5A2W3EEDMCRABN5/graph.json","fetch_events":"https://pith.science/api/pith-number/47XEHWK2H6Y5A2W3EEDMCRABN5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/47XEHWK2H6Y5A2W3EEDMCRABN5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/47XEHWK2H6Y5A2W3EEDMCRABN5/action/storage_attestation","attest_author":"https://pith.science/pith/47XEHWK2H6Y5A2W3EEDMCRABN5/action/author_attestation","sign_citation":"https://pith.science/pith/47XEHWK2H6Y5A2W3EEDMCRABN5/action/citation_signature","submit_replication":"https://pith.science/pith/47XEHWK2H6Y5A2W3EEDMCRABN5/action/replication_record"}},"created_at":"2026-07-05T09:22:40.785703+00:00","updated_at":"2026-07-05T09:22:40.785703+00:00"}