{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NI53VVUDOLEQFI374O2MMSLC4T","short_pith_number":"pith:NI53VVUD","schema_version":"1.0","canonical_sha256":"6a3bbad68372c902a37fe3b4c64962e4dd0550bc3d45da1910554bca724ad961","source":{"kind":"arxiv","id":"2411.16278","version":1},"attestation_state":"computed","paper":{"title":"Even Sparser Graph Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ameya Velingker, Balaji Venkatachalam, Danica Sutherland, David Woodruff, Hamed Shirzad, Honghao Lin","submitted_at":"2024-11-25T10:59:25Z","abstract_excerpt":"Graph Transformers excel in long-range dependency modeling, but generally require quadratic memory complexity in the number of nodes in an input graph, and hence have trouble scaling to large graphs. Sparse attention variants such as Exphormer can help, but may require high-degree augmentations to the input graph for good performance, and do not attempt to sparsify an already-dense input graph. As the learned attention mechanisms tend to use few of these edges, such high-degree connections may be unnecessary. We show (empirically and with theoretical backing) that attention scores on graphs ar"},"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":"2411.16278","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-25T10:59:25Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"938d558f62fc98149098d9ab0e7f7fe7c0c54a466599732b2294bf73ebf9d821","abstract_canon_sha256":"14bbeec00c3e27895aa7a8add0225c7e22bc5b0bda67375d4bcc3d2ace580632"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:40:07.123783Z","signature_b64":"zK2pC0/hN55iYxnCFh+PcWf05y7/xSgyGRFm8bNrDXZjWtRQeYCYCB6YURLImXiGQmUSra8TuTDhxcNLR+01DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a3bbad68372c902a37fe3b4c64962e4dd0550bc3d45da1910554bca724ad961","last_reissued_at":"2026-07-05T09:40:07.123290Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:40:07.123290Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Even Sparser Graph Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ameya Velingker, Balaji Venkatachalam, Danica Sutherland, David Woodruff, Hamed Shirzad, Honghao Lin","submitted_at":"2024-11-25T10:59:25Z","abstract_excerpt":"Graph Transformers excel in long-range dependency modeling, but generally require quadratic memory complexity in the number of nodes in an input graph, and hence have trouble scaling to large graphs. Sparse attention variants such as Exphormer can help, but may require high-degree augmentations to the input graph for good performance, and do not attempt to sparsify an already-dense input graph. As the learned attention mechanisms tend to use few of these edges, such high-degree connections may be unnecessary. We show (empirically and with theoretical backing) that attention scores on graphs ar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.16278","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/2411.16278/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":"2411.16278","created_at":"2026-07-05T09:40:07.123355+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.16278v1","created_at":"2026-07-05T09:40:07.123355+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.16278","created_at":"2026-07-05T09:40:07.123355+00:00"},{"alias_kind":"pith_short_12","alias_value":"NI53VVUDOLEQ","created_at":"2026-07-05T09:40:07.123355+00:00"},{"alias_kind":"pith_short_16","alias_value":"NI53VVUDOLEQFI37","created_at":"2026-07-05T09:40:07.123355+00:00"},{"alias_kind":"pith_short_8","alias_value":"NI53VVUD","created_at":"2026-07-05T09:40:07.123355+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NI53VVUDOLEQFI374O2MMSLC4T","json":"https://pith.science/pith/NI53VVUDOLEQFI374O2MMSLC4T.json","graph_json":"https://pith.science/api/pith-number/NI53VVUDOLEQFI374O2MMSLC4T/graph.json","events_json":"https://pith.science/api/pith-number/NI53VVUDOLEQFI374O2MMSLC4T/events.json","paper":"https://pith.science/paper/NI53VVUD"},"agent_actions":{"view_html":"https://pith.science/pith/NI53VVUDOLEQFI374O2MMSLC4T","download_json":"https://pith.science/pith/NI53VVUDOLEQFI374O2MMSLC4T.json","view_paper":"https://pith.science/paper/NI53VVUD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.16278&json=true","fetch_graph":"https://pith.science/api/pith-number/NI53VVUDOLEQFI374O2MMSLC4T/graph.json","fetch_events":"https://pith.science/api/pith-number/NI53VVUDOLEQFI374O2MMSLC4T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NI53VVUDOLEQFI374O2MMSLC4T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NI53VVUDOLEQFI374O2MMSLC4T/action/storage_attestation","attest_author":"https://pith.science/pith/NI53VVUDOLEQFI374O2MMSLC4T/action/author_attestation","sign_citation":"https://pith.science/pith/NI53VVUDOLEQFI374O2MMSLC4T/action/citation_signature","submit_replication":"https://pith.science/pith/NI53VVUDOLEQFI374O2MMSLC4T/action/replication_record"}},"created_at":"2026-07-05T09:40:07.123355+00:00","updated_at":"2026-07-05T09:40:07.123355+00:00"}