{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:BBAEVC2GGWYNCQUBFMBUGXVPVN","short_pith_number":"pith:BBAEVC2G","schema_version":"1.0","canonical_sha256":"08404a8b4635b0d142812b03435eafab5b9851850723f3691356918a314a1f73","source":{"kind":"arxiv","id":"2003.01332","version":1},"attestation_state":"computed","paper":{"title":"Heterogeneous Graph Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Kuansan Wang, Yizhou Sun, Yuxiao Dong, Ziniu Hu","submitted_at":"2020-03-03T04:49:21Z","abstract_excerpt":"Recent years have witnessed the emerging success of graph neural networks (GNNs) for modeling structured data. However, most GNNs are designed for homogeneous graphs, in which all nodes and edges belong to the same types, making them infeasible to represent heterogeneous structures. In this paper, we present the Heterogeneous Graph Transformer (HGT) architecture for modeling Web-scale heterogeneous graphs. To model heterogeneity, we design node- and edge-type dependent parameters to characterize the heterogeneous attention over each edge, empowering HGT to maintain dedicated representations fo"},"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":"2003.01332","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-03T04:49:21Z","cross_cats_sorted":["cs.SI","stat.ML"],"title_canon_sha256":"bc11d04aa44cd6ef132ef5ffa6fdafd726b4f32f349fb7d8a7e7d099e6fb7c49","abstract_canon_sha256":"c893d636637c7d6d7cce6c22cecc240dc394515907aa11d771e6c39de2ef1316"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:45:27.675572Z","signature_b64":"nouOcR7JIDCyJ04grOq5xPpNu3Rd2KlJCNAqvY9DVBI4Gk+N0e9eg07sr/7zedgYrrVqq3iKaWd0PiC/3bodDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08404a8b4635b0d142812b03435eafab5b9851850723f3691356918a314a1f73","last_reissued_at":"2026-07-05T00:45:27.675044Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:45:27.675044Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Heterogeneous Graph Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Kuansan Wang, Yizhou Sun, Yuxiao Dong, Ziniu Hu","submitted_at":"2020-03-03T04:49:21Z","abstract_excerpt":"Recent years have witnessed the emerging success of graph neural networks (GNNs) for modeling structured data. However, most GNNs are designed for homogeneous graphs, in which all nodes and edges belong to the same types, making them infeasible to represent heterogeneous structures. In this paper, we present the Heterogeneous Graph Transformer (HGT) architecture for modeling Web-scale heterogeneous graphs. To model heterogeneity, we design node- and edge-type dependent parameters to characterize the heterogeneous attention over each edge, empowering HGT to maintain dedicated representations fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.01332","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/2003.01332/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":"2003.01332","created_at":"2026-07-05T00:45:27.675108+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.01332v1","created_at":"2026-07-05T00:45:27.675108+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.01332","created_at":"2026-07-05T00:45:27.675108+00:00"},{"alias_kind":"pith_short_12","alias_value":"BBAEVC2GGWYN","created_at":"2026-07-05T00:45:27.675108+00:00"},{"alias_kind":"pith_short_16","alias_value":"BBAEVC2GGWYNCQUB","created_at":"2026-07-05T00:45:27.675108+00:00"},{"alias_kind":"pith_short_8","alias_value":"BBAEVC2G","created_at":"2026-07-05T00:45:27.675108+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06224","citing_title":"Canopy: A Heterograph Foundation Model for Metabolic Engineering","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2605.24207","citing_title":"Incorporating Deep Learning Design in Database Queries","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28643","citing_title":"GraphLit: Learning Text-Enriched Dynamic Character Network Representations for Literary Study","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2409.08036","citing_title":"Heterogeneous Sheaf Neural Networks","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21093","citing_title":"TRAVELFRAUDBENCH: A Configurable Evaluation Framework for GNN Fraud Ring Detection in Travel Networks","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BBAEVC2GGWYNCQUBFMBUGXVPVN","json":"https://pith.science/pith/BBAEVC2GGWYNCQUBFMBUGXVPVN.json","graph_json":"https://pith.science/api/pith-number/BBAEVC2GGWYNCQUBFMBUGXVPVN/graph.json","events_json":"https://pith.science/api/pith-number/BBAEVC2GGWYNCQUBFMBUGXVPVN/events.json","paper":"https://pith.science/paper/BBAEVC2G"},"agent_actions":{"view_html":"https://pith.science/pith/BBAEVC2GGWYNCQUBFMBUGXVPVN","download_json":"https://pith.science/pith/BBAEVC2GGWYNCQUBFMBUGXVPVN.json","view_paper":"https://pith.science/paper/BBAEVC2G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.01332&json=true","fetch_graph":"https://pith.science/api/pith-number/BBAEVC2GGWYNCQUBFMBUGXVPVN/graph.json","fetch_events":"https://pith.science/api/pith-number/BBAEVC2GGWYNCQUBFMBUGXVPVN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BBAEVC2GGWYNCQUBFMBUGXVPVN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BBAEVC2GGWYNCQUBFMBUGXVPVN/action/storage_attestation","attest_author":"https://pith.science/pith/BBAEVC2GGWYNCQUBFMBUGXVPVN/action/author_attestation","sign_citation":"https://pith.science/pith/BBAEVC2GGWYNCQUBFMBUGXVPVN/action/citation_signature","submit_replication":"https://pith.science/pith/BBAEVC2GGWYNCQUBFMBUGXVPVN/action/replication_record"}},"created_at":"2026-07-05T00:45:27.675108+00:00","updated_at":"2026-07-05T00:45:27.675108+00:00"}