{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:UKSJ3UUN67SVH5QPFDLBIDZHBQ","short_pith_number":"pith:UKSJ3UUN","schema_version":"1.0","canonical_sha256":"a2a49dd28df7e553f60f28d6140f270c161f964f5c0b1fa4f1ef7026dc8edb4d","source":{"kind":"arxiv","id":"2111.10447","version":3},"attestation_state":"computed","paper":{"title":"DyFormer: A Scalable Dynamic Graph Transformer with Provable Benefits on Generalization Ability","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chun-cheng Jason Chen, Mehrdad Mahdavi, Mengting Gu, Weilin Cong, Yanhong Wu, Yinglong Xia, Yuandong Tian","submitted_at":"2021-11-19T21:44:23Z","abstract_excerpt":"Transformers have achieved great success in several domains, including Natural Language Processing and Computer Vision. However, its application to real-world graphs is less explored, mainly due to its high computation cost and its poor generalizability caused by the lack of enough training data in the graph domain. To fill in this gap, we propose a scalable Transformer-like dynamic graph learning method named Dynamic Graph Transformer (DyFormer) with spatial-temporal encoding to effectively learn graph topology and capture implicit links. To achieve efficient and scalable training, we propose"},"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":"2111.10447","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-11-19T21:44:23Z","cross_cats_sorted":[],"title_canon_sha256":"4568998311aac31f876f0be0ac8bb9ef599456067ea4692dae5884956dadef73","abstract_canon_sha256":"f60e1c1a3fbfb6e9a56e8c56a9f733c708af52d61d80a822ce864e40c7c4a524"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:36:45.498002Z","signature_b64":"fsmoTErncddVGDzcrjABB96xlfXttX/okDpIjo87aJhWzysEjW8OxUKzfJXxnYS2Bg7cWU6PIF/HcymvjPgLAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2a49dd28df7e553f60f28d6140f270c161f964f5c0b1fa4f1ef7026dc8edb4d","last_reissued_at":"2026-07-05T05:36:45.497586Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:36:45.497586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DyFormer: A Scalable Dynamic Graph Transformer with Provable Benefits on Generalization Ability","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chun-cheng Jason Chen, Mehrdad Mahdavi, Mengting Gu, Weilin Cong, Yanhong Wu, Yinglong Xia, Yuandong Tian","submitted_at":"2021-11-19T21:44:23Z","abstract_excerpt":"Transformers have achieved great success in several domains, including Natural Language Processing and Computer Vision. However, its application to real-world graphs is less explored, mainly due to its high computation cost and its poor generalizability caused by the lack of enough training data in the graph domain. To fill in this gap, we propose a scalable Transformer-like dynamic graph learning method named Dynamic Graph Transformer (DyFormer) with spatial-temporal encoding to effectively learn graph topology and capture implicit links. To achieve efficient and scalable training, we propose"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.10447","kind":"arxiv","version":3},"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/2111.10447/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":"2111.10447","created_at":"2026-07-05T05:36:45.497642+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.10447v3","created_at":"2026-07-05T05:36:45.497642+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.10447","created_at":"2026-07-05T05:36:45.497642+00:00"},{"alias_kind":"pith_short_12","alias_value":"UKSJ3UUN67SV","created_at":"2026-07-05T05:36:45.497642+00:00"},{"alias_kind":"pith_short_16","alias_value":"UKSJ3UUN67SVH5QP","created_at":"2026-07-05T05:36:45.497642+00:00"},{"alias_kind":"pith_short_8","alias_value":"UKSJ3UUN","created_at":"2026-07-05T05:36:45.497642+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17628","citing_title":"OPD-Evolver: Cultivating Holistic Agent Evolver via On-Policy Distillation","ref_index":186,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16112","citing_title":"Attention Dispersion in Dynamic Graph Transformers: Diagnosis and a Transferable Fix","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UKSJ3UUN67SVH5QPFDLBIDZHBQ","json":"https://pith.science/pith/UKSJ3UUN67SVH5QPFDLBIDZHBQ.json","graph_json":"https://pith.science/api/pith-number/UKSJ3UUN67SVH5QPFDLBIDZHBQ/graph.json","events_json":"https://pith.science/api/pith-number/UKSJ3UUN67SVH5QPFDLBIDZHBQ/events.json","paper":"https://pith.science/paper/UKSJ3UUN"},"agent_actions":{"view_html":"https://pith.science/pith/UKSJ3UUN67SVH5QPFDLBIDZHBQ","download_json":"https://pith.science/pith/UKSJ3UUN67SVH5QPFDLBIDZHBQ.json","view_paper":"https://pith.science/paper/UKSJ3UUN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.10447&json=true","fetch_graph":"https://pith.science/api/pith-number/UKSJ3UUN67SVH5QPFDLBIDZHBQ/graph.json","fetch_events":"https://pith.science/api/pith-number/UKSJ3UUN67SVH5QPFDLBIDZHBQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UKSJ3UUN67SVH5QPFDLBIDZHBQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UKSJ3UUN67SVH5QPFDLBIDZHBQ/action/storage_attestation","attest_author":"https://pith.science/pith/UKSJ3UUN67SVH5QPFDLBIDZHBQ/action/author_attestation","sign_citation":"https://pith.science/pith/UKSJ3UUN67SVH5QPFDLBIDZHBQ/action/citation_signature","submit_replication":"https://pith.science/pith/UKSJ3UUN67SVH5QPFDLBIDZHBQ/action/replication_record"}},"created_at":"2026-07-05T05:36:45.497642+00:00","updated_at":"2026-07-05T05:36:45.497642+00:00"}