{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:JNT2GJLCCSCRIM6JVZAQESOITF","short_pith_number":"pith:JNT2GJLC","schema_version":"1.0","canonical_sha256":"4b67a3256214851433c9ae410249c8995e3b7fe4cf1a3ad128a6da3ad2908ff1","source":{"kind":"arxiv","id":"1911.06455","version":2},"attestation_state":"computed","paper":{"title":"Graph Transformer Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hyunwoo J. Kim, Jaewoo Kang, Minbyul Jeong, Raehyun Kim, Seongjun Yun","submitted_at":"2019-11-06T06:40:05Z","abstract_excerpt":"Graph neural networks (GNNs) have been widely used in representation learning on graphs and achieved state-of-the-art performance in tasks such as node classification and link prediction. However, most existing GNNs are designed to learn node representations on the fixed and homogeneous graphs. The limitations especially become problematic when learning representations on a misspecified graph or a heterogeneous graph that consists of various types of nodes and edges. In this paper, we propose Graph Transformer Networks (GTNs) that are capable of generating new graph structures, which involve i"},"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":"1911.06455","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-06T06:40:05Z","cross_cats_sorted":["cs.SI","stat.ML"],"title_canon_sha256":"d397b19a1960b4b4327348f3ae6af78dd41d6de28b01bb42d5d70ca202b4b00c","abstract_canon_sha256":"e6105d0e71d8a4d81addbe7303f1067054f61736566b58f1a3c754282a9af2a5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:38:34.772983Z","signature_b64":"vYyWoom5YyKlHqw/59sa/Ajzbf9Ohu6PIyuluV4T6fhnBVZIJaP9EnNy3CaX1TI74NNMf93iYTitfVxsDEiMDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b67a3256214851433c9ae410249c8995e3b7fe4cf1a3ad128a6da3ad2908ff1","last_reissued_at":"2026-07-05T00:38:34.772518Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:38:34.772518Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Graph Transformer Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Hyunwoo J. Kim, Jaewoo Kang, Minbyul Jeong, Raehyun Kim, Seongjun Yun","submitted_at":"2019-11-06T06:40:05Z","abstract_excerpt":"Graph neural networks (GNNs) have been widely used in representation learning on graphs and achieved state-of-the-art performance in tasks such as node classification and link prediction. However, most existing GNNs are designed to learn node representations on the fixed and homogeneous graphs. The limitations especially become problematic when learning representations on a misspecified graph or a heterogeneous graph that consists of various types of nodes and edges. In this paper, we propose Graph Transformer Networks (GTNs) that are capable of generating new graph structures, which involve i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.06455","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/1911.06455/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":"1911.06455","created_at":"2026-07-05T00:38:34.772578+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.06455v2","created_at":"2026-07-05T00:38:34.772578+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.06455","created_at":"2026-07-05T00:38:34.772578+00:00"},{"alias_kind":"pith_short_12","alias_value":"JNT2GJLCCSCR","created_at":"2026-07-05T00:38:34.772578+00:00"},{"alias_kind":"pith_short_16","alias_value":"JNT2GJLCCSCRIM6J","created_at":"2026-07-05T00:38:34.772578+00:00"},{"alias_kind":"pith_short_8","alias_value":"JNT2GJLC","created_at":"2026-07-05T00:38:34.772578+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.01484","citing_title":"Evaluating LLMs on Large-Scale Graph Property Estimation via Random Walks","ref_index":80,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JNT2GJLCCSCRIM6JVZAQESOITF","json":"https://pith.science/pith/JNT2GJLCCSCRIM6JVZAQESOITF.json","graph_json":"https://pith.science/api/pith-number/JNT2GJLCCSCRIM6JVZAQESOITF/graph.json","events_json":"https://pith.science/api/pith-number/JNT2GJLCCSCRIM6JVZAQESOITF/events.json","paper":"https://pith.science/paper/JNT2GJLC"},"agent_actions":{"view_html":"https://pith.science/pith/JNT2GJLCCSCRIM6JVZAQESOITF","download_json":"https://pith.science/pith/JNT2GJLCCSCRIM6JVZAQESOITF.json","view_paper":"https://pith.science/paper/JNT2GJLC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.06455&json=true","fetch_graph":"https://pith.science/api/pith-number/JNT2GJLCCSCRIM6JVZAQESOITF/graph.json","fetch_events":"https://pith.science/api/pith-number/JNT2GJLCCSCRIM6JVZAQESOITF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JNT2GJLCCSCRIM6JVZAQESOITF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JNT2GJLCCSCRIM6JVZAQESOITF/action/storage_attestation","attest_author":"https://pith.science/pith/JNT2GJLCCSCRIM6JVZAQESOITF/action/author_attestation","sign_citation":"https://pith.science/pith/JNT2GJLCCSCRIM6JVZAQESOITF/action/citation_signature","submit_replication":"https://pith.science/pith/JNT2GJLCCSCRIM6JVZAQESOITF/action/replication_record"}},"created_at":"2026-07-05T00:38:34.772578+00:00","updated_at":"2026-07-05T00:38:34.772578+00:00"}