{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BF6GTROFYVAJTSSHPES6UL3BTC","short_pith_number":"pith:BF6GTROF","schema_version":"1.0","canonical_sha256":"097c69c5c5c54099ca477925ea2f6198a01d83050dcf8ca1b730f2e11c3531e4","source":{"kind":"arxiv","id":"2412.08937","version":1},"attestation_state":"computed","paper":{"title":"Multi-Scale Heterogeneous Text-Attributed Graph Datasets From Diverse Domains","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Jiaxu Shen, Jinwei Shi, Qizhuo Xie, Tieke He, Yunhui Liu","submitted_at":"2024-12-12T04:58:32Z","abstract_excerpt":"Heterogeneous Text-Attributed Graphs (HTAGs), where different types of entities are not only associated with texts but also connected by diverse relationships, have gained widespread popularity and application across various domains. However, current research on text-attributed graph learning predominantly focuses on homogeneous graphs, which feature a single node and edge type, thus leaving a gap in understanding how methods perform on HTAGs. One crucial reason is the lack of comprehensive HTAG datasets that offer original textual content and span multiple domains of varying sizes. To this en"},"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":"2412.08937","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-12-12T04:58:32Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"4852c03104f82ace54ac0bb926936f75c103e8d99709098dc960a68fa505f8cb","abstract_canon_sha256":"ad139ed52dfcafa2fcdb7449c0660c33aba43ddd9809bb9def2a6b37a10257df"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:48:04.246838Z","signature_b64":"xlSvcHS3uv/yYO5i0ariIefAY3LHLxDDxFOGJpocl8StlvUQiYsbjPxDXXVpXetIhgxZeEvgpIq/a3/cWzZEDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"097c69c5c5c54099ca477925ea2f6198a01d83050dcf8ca1b730f2e11c3531e4","last_reissued_at":"2026-07-05T09:48:04.246349Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:48:04.246349Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Scale Heterogeneous Text-Attributed Graph Datasets From Diverse Domains","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Jiaxu Shen, Jinwei Shi, Qizhuo Xie, Tieke He, Yunhui Liu","submitted_at":"2024-12-12T04:58:32Z","abstract_excerpt":"Heterogeneous Text-Attributed Graphs (HTAGs), where different types of entities are not only associated with texts but also connected by diverse relationships, have gained widespread popularity and application across various domains. However, current research on text-attributed graph learning predominantly focuses on homogeneous graphs, which feature a single node and edge type, thus leaving a gap in understanding how methods perform on HTAGs. One crucial reason is the lack of comprehensive HTAG datasets that offer original textual content and span multiple domains of varying sizes. To this en"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.08937","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/2412.08937/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":"2412.08937","created_at":"2026-07-05T09:48:04.246413+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.08937v1","created_at":"2026-07-05T09:48:04.246413+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.08937","created_at":"2026-07-05T09:48:04.246413+00:00"},{"alias_kind":"pith_short_12","alias_value":"BF6GTROFYVAJ","created_at":"2026-07-05T09:48:04.246413+00:00"},{"alias_kind":"pith_short_16","alias_value":"BF6GTROFYVAJTSSH","created_at":"2026-07-05T09:48:04.246413+00:00"},{"alias_kind":"pith_short_8","alias_value":"BF6GTROF","created_at":"2026-07-05T09:48:04.246413+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.08298","citing_title":"H$^2$GFM: Towards unifying Homogeneity and Heterogeneity on Text-Attributed Graphs","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BF6GTROFYVAJTSSHPES6UL3BTC","json":"https://pith.science/pith/BF6GTROFYVAJTSSHPES6UL3BTC.json","graph_json":"https://pith.science/api/pith-number/BF6GTROFYVAJTSSHPES6UL3BTC/graph.json","events_json":"https://pith.science/api/pith-number/BF6GTROFYVAJTSSHPES6UL3BTC/events.json","paper":"https://pith.science/paper/BF6GTROF"},"agent_actions":{"view_html":"https://pith.science/pith/BF6GTROFYVAJTSSHPES6UL3BTC","download_json":"https://pith.science/pith/BF6GTROFYVAJTSSHPES6UL3BTC.json","view_paper":"https://pith.science/paper/BF6GTROF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.08937&json=true","fetch_graph":"https://pith.science/api/pith-number/BF6GTROFYVAJTSSHPES6UL3BTC/graph.json","fetch_events":"https://pith.science/api/pith-number/BF6GTROFYVAJTSSHPES6UL3BTC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BF6GTROFYVAJTSSHPES6UL3BTC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BF6GTROFYVAJTSSHPES6UL3BTC/action/storage_attestation","attest_author":"https://pith.science/pith/BF6GTROFYVAJTSSHPES6UL3BTC/action/author_attestation","sign_citation":"https://pith.science/pith/BF6GTROFYVAJTSSHPES6UL3BTC/action/citation_signature","submit_replication":"https://pith.science/pith/BF6GTROFYVAJTSSHPES6UL3BTC/action/replication_record"}},"created_at":"2026-07-05T09:48:04.246413+00:00","updated_at":"2026-07-05T09:48:04.246413+00:00"}