{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PE64UAXLU23CLPNRL4M2RODKZP","short_pith_number":"pith:PE64UAXL","schema_version":"1.0","canonical_sha256":"793dca02eba6b625bdb15f19a8b86acbfc80da3aa7e71e4a977ab12a25e3ff28","source":{"kind":"arxiv","id":"2404.15729","version":1},"attestation_state":"computed","paper":{"title":"Gradformer: Graph Transformer with Exponential Decay","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chuang Liu, Shirui Pan, Wenbin Hu, Xueqi Ma, Yibing Zhan, Zelin Yao","submitted_at":"2024-04-24T08:37:13Z","abstract_excerpt":"Graph Transformers (GTs) have demonstrated their advantages across a wide range of tasks. However, the self-attention mechanism in GTs overlooks the graph's inductive biases, particularly biases related to structure, which are crucial for the graph tasks. Although some methods utilize positional encoding and attention bias to model inductive biases, their effectiveness is still suboptimal analytically. Therefore, this paper presents Gradformer, a method innovatively integrating GT with the intrinsic inductive bias by applying an exponential decay mask to the attention matrix. Specifically, the"},"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":"2404.15729","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-24T08:37:13Z","cross_cats_sorted":[],"title_canon_sha256":"620b5978c7c381189f0981581c4454cc36396d6a0f9cbc62fae3795e9516324e","abstract_canon_sha256":"20974cdb3c3ab10406a4007f5c396b40562968556b78b89757032c376032be9f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:11:44.465235Z","signature_b64":"7saHbcERbIFASj7guJJFG0u+6wWiHxm6h5xAui9fGK1gL9Qq0SKUMPVIvjSJ3fByb1ZEnAHuRCiCXeAF5HtFBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"793dca02eba6b625bdb15f19a8b86acbfc80da3aa7e71e4a977ab12a25e3ff28","last_reissued_at":"2026-07-05T08:11:44.464841Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:11:44.464841Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gradformer: Graph Transformer with Exponential Decay","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chuang Liu, Shirui Pan, Wenbin Hu, Xueqi Ma, Yibing Zhan, Zelin Yao","submitted_at":"2024-04-24T08:37:13Z","abstract_excerpt":"Graph Transformers (GTs) have demonstrated their advantages across a wide range of tasks. However, the self-attention mechanism in GTs overlooks the graph's inductive biases, particularly biases related to structure, which are crucial for the graph tasks. Although some methods utilize positional encoding and attention bias to model inductive biases, their effectiveness is still suboptimal analytically. Therefore, this paper presents Gradformer, a method innovatively integrating GT with the intrinsic inductive bias by applying an exponential decay mask to the attention matrix. Specifically, the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.15729","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/2404.15729/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":"2404.15729","created_at":"2026-07-05T08:11:44.464893+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.15729v1","created_at":"2026-07-05T08:11:44.464893+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.15729","created_at":"2026-07-05T08:11:44.464893+00:00"},{"alias_kind":"pith_short_12","alias_value":"PE64UAXLU23C","created_at":"2026-07-05T08:11:44.464893+00:00"},{"alias_kind":"pith_short_16","alias_value":"PE64UAXLU23CLPNR","created_at":"2026-07-05T08:11:44.464893+00:00"},{"alias_kind":"pith_short_8","alias_value":"PE64UAXL","created_at":"2026-07-05T08:11:44.464893+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06534","citing_title":"CAIRN: Cross-Room 3D Scene Understanding with Topology-Aware Large Multimodal Models","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PE64UAXLU23CLPNRL4M2RODKZP","json":"https://pith.science/pith/PE64UAXLU23CLPNRL4M2RODKZP.json","graph_json":"https://pith.science/api/pith-number/PE64UAXLU23CLPNRL4M2RODKZP/graph.json","events_json":"https://pith.science/api/pith-number/PE64UAXLU23CLPNRL4M2RODKZP/events.json","paper":"https://pith.science/paper/PE64UAXL"},"agent_actions":{"view_html":"https://pith.science/pith/PE64UAXLU23CLPNRL4M2RODKZP","download_json":"https://pith.science/pith/PE64UAXLU23CLPNRL4M2RODKZP.json","view_paper":"https://pith.science/paper/PE64UAXL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.15729&json=true","fetch_graph":"https://pith.science/api/pith-number/PE64UAXLU23CLPNRL4M2RODKZP/graph.json","fetch_events":"https://pith.science/api/pith-number/PE64UAXLU23CLPNRL4M2RODKZP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PE64UAXLU23CLPNRL4M2RODKZP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PE64UAXLU23CLPNRL4M2RODKZP/action/storage_attestation","attest_author":"https://pith.science/pith/PE64UAXLU23CLPNRL4M2RODKZP/action/author_attestation","sign_citation":"https://pith.science/pith/PE64UAXLU23CLPNRL4M2RODKZP/action/citation_signature","submit_replication":"https://pith.science/pith/PE64UAXLU23CLPNRL4M2RODKZP/action/replication_record"}},"created_at":"2026-07-05T08:11:44.464893+00:00","updated_at":"2026-07-05T08:11:44.464893+00:00"}