{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:HXZVMTFV3LRZTPWMORPCI2WCXB","short_pith_number":"pith:HXZVMTFV","schema_version":"1.0","canonical_sha256":"3df3564cb5dae399becc745e246ac2b87fc9dea69b72be55fb612d163ab34f92","source":{"kind":"arxiv","id":"2305.17589","version":1},"attestation_state":"computed","paper":{"title":"Graph Inductive Biases in Transformers without Message Passing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Adriana Romero-Soriano, Chen Lin, Derek Lim, Liheng Ma, Mark Coates, Philip Torr, Puneet K. Dokania, Ser-Nam Lim","submitted_at":"2023-05-27T22:26:27Z","abstract_excerpt":"Transformers for graph data are increasingly widely studied and successful in numerous learning tasks. Graph inductive biases are crucial for Graph Transformers, and previous works incorporate them using message-passing modules and/or positional encodings. However, Graph Transformers that use message-passing inherit known issues of message-passing, and differ significantly from Transformers used in other domains, thus making transfer of research advances more difficult. On the other hand, Graph Transformers without message-passing often perform poorly on smaller datasets, where inductive biase"},"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":"2305.17589","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-27T22:26:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d4ec4d7784c0d1d7e8f2c0bfe7aeddfe4c192b35233bc91e0b46d9a1eb218af2","abstract_canon_sha256":"d0b4d38c0b139f204d13d7bf7b100878767ba50ae6b3d8ccf8570533902b0fb8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:43:01.593724Z","signature_b64":"aFvRut5SrRfm8qSHVE+fdnHgIQrjT9Y7mUd2Slpv/3YU/lCZ480KjtBLbecN5AdZ1R3I1U7TQ39tv0n9irmuCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3df3564cb5dae399becc745e246ac2b87fc9dea69b72be55fb612d163ab34f92","last_reissued_at":"2026-07-05T06:43:01.593213Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:43:01.593213Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Graph Inductive Biases in Transformers without Message Passing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Adriana Romero-Soriano, Chen Lin, Derek Lim, Liheng Ma, Mark Coates, Philip Torr, Puneet K. Dokania, Ser-Nam Lim","submitted_at":"2023-05-27T22:26:27Z","abstract_excerpt":"Transformers for graph data are increasingly widely studied and successful in numerous learning tasks. Graph inductive biases are crucial for Graph Transformers, and previous works incorporate them using message-passing modules and/or positional encodings. However, Graph Transformers that use message-passing inherit known issues of message-passing, and differ significantly from Transformers used in other domains, thus making transfer of research advances more difficult. On the other hand, Graph Transformers without message-passing often perform poorly on smaller datasets, where inductive biase"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.17589","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/2305.17589/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":"2305.17589","created_at":"2026-07-05T06:43:01.593281+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.17589v1","created_at":"2026-07-05T06:43:01.593281+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.17589","created_at":"2026-07-05T06:43:01.593281+00:00"},{"alias_kind":"pith_short_12","alias_value":"HXZVMTFV3LRZ","created_at":"2026-07-05T06:43:01.593281+00:00"},{"alias_kind":"pith_short_16","alias_value":"HXZVMTFV3LRZTPWM","created_at":"2026-07-05T06:43:01.593281+00:00"},{"alias_kind":"pith_short_8","alias_value":"HXZVMTFV","created_at":"2026-07-05T06:43:01.593281+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.02075","citing_title":"Graph Transformers and Stabilized Reinforcement Learning for Large-Scale Dynamic Routing Modulation and Spectrum Allocation in Elastic Optical Networks","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02075","citing_title":"Graph Transformers and Stabilized Reinforcement Learning for Large-Scale Dynamic Routing Modulation and Spectrum Allocation in Elastic Optical Networks","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HXZVMTFV3LRZTPWMORPCI2WCXB","json":"https://pith.science/pith/HXZVMTFV3LRZTPWMORPCI2WCXB.json","graph_json":"https://pith.science/api/pith-number/HXZVMTFV3LRZTPWMORPCI2WCXB/graph.json","events_json":"https://pith.science/api/pith-number/HXZVMTFV3LRZTPWMORPCI2WCXB/events.json","paper":"https://pith.science/paper/HXZVMTFV"},"agent_actions":{"view_html":"https://pith.science/pith/HXZVMTFV3LRZTPWMORPCI2WCXB","download_json":"https://pith.science/pith/HXZVMTFV3LRZTPWMORPCI2WCXB.json","view_paper":"https://pith.science/paper/HXZVMTFV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.17589&json=true","fetch_graph":"https://pith.science/api/pith-number/HXZVMTFV3LRZTPWMORPCI2WCXB/graph.json","fetch_events":"https://pith.science/api/pith-number/HXZVMTFV3LRZTPWMORPCI2WCXB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HXZVMTFV3LRZTPWMORPCI2WCXB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HXZVMTFV3LRZTPWMORPCI2WCXB/action/storage_attestation","attest_author":"https://pith.science/pith/HXZVMTFV3LRZTPWMORPCI2WCXB/action/author_attestation","sign_citation":"https://pith.science/pith/HXZVMTFV3LRZTPWMORPCI2WCXB/action/citation_signature","submit_replication":"https://pith.science/pith/HXZVMTFV3LRZTPWMORPCI2WCXB/action/replication_record"}},"created_at":"2026-07-05T06:43:01.593281+00:00","updated_at":"2026-07-05T06:43:01.593281+00:00"}