{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:763LZF6WS6PMBRCSNTV5IVL6E2","short_pith_number":"pith:763LZF6W","schema_version":"1.0","canonical_sha256":"ffb6bc97d6979ec0c4526cebd4557e268dfe54d901065f6137539ad7e3412cd5","source":{"kind":"arxiv","id":"2201.12787","version":3},"attestation_state":"computed","paper":{"title":"GRPE: Relative Positional Encoding for Graph Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"DongGeon Lee, Juntae Kim, Seung-won Hwang, Wonpyo Park, Woonggi Chang","submitted_at":"2022-01-30T11:10:06Z","abstract_excerpt":"We propose a novel positional encoding for learning graph on Transformer architecture. Existing approaches either linearize a graph to encode absolute position in the sequence of nodes, or encode relative position with another node using bias terms. The former loses preciseness of relative position from linearization, while the latter loses a tight integration of node-edge and node-topology interaction. To overcome the weakness of the previous approaches, our method encodes a graph without linearization and considers both node-topology and node-edge interaction. We name our method Graph Relati"},"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":"2201.12787","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-01-30T11:10:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e08ab0bb4618ca3a567e6fb026519cbeeeedf0d4a8728d3ebe334e8ff9fd678c","abstract_canon_sha256":"ffabdae9d6b1c9abfb51f127fd64c72e56263114723d5abd892393053223269f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:06:29.951313Z","signature_b64":"weX9pUlgjlnSlvHTWgqtbEQB8VmzF2bPkMy8T28dwg4xJlsusE4CmV5HQZUhAX8S6nDvjpvAzvXIXRCHW80pBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ffb6bc97d6979ec0c4526cebd4557e268dfe54d901065f6137539ad7e3412cd5","last_reissued_at":"2026-07-05T05:06:29.950932Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:06:29.950932Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GRPE: Relative Positional Encoding for Graph Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"DongGeon Lee, Juntae Kim, Seung-won Hwang, Wonpyo Park, Woonggi Chang","submitted_at":"2022-01-30T11:10:06Z","abstract_excerpt":"We propose a novel positional encoding for learning graph on Transformer architecture. Existing approaches either linearize a graph to encode absolute position in the sequence of nodes, or encode relative position with another node using bias terms. The former loses preciseness of relative position from linearization, while the latter loses a tight integration of node-edge and node-topology interaction. To overcome the weakness of the previous approaches, our method encodes a graph without linearization and considers both node-topology and node-edge interaction. We name our method Graph Relati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.12787","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/2201.12787/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":"2201.12787","created_at":"2026-07-05T05:06:29.950987+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.12787v3","created_at":"2026-07-05T05:06:29.950987+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.12787","created_at":"2026-07-05T05:06:29.950987+00:00"},{"alias_kind":"pith_short_12","alias_value":"763LZF6WS6PM","created_at":"2026-07-05T05:06:29.950987+00:00"},{"alias_kind":"pith_short_16","alias_value":"763LZF6WS6PMBRCS","created_at":"2026-07-05T05:06:29.950987+00:00"},{"alias_kind":"pith_short_8","alias_value":"763LZF6W","created_at":"2026-07-05T05:06:29.950987+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.20857","citing_title":"Multi-Embodiment Robotic Retargeting via Guided Diffusion Model","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/763LZF6WS6PMBRCSNTV5IVL6E2","json":"https://pith.science/pith/763LZF6WS6PMBRCSNTV5IVL6E2.json","graph_json":"https://pith.science/api/pith-number/763LZF6WS6PMBRCSNTV5IVL6E2/graph.json","events_json":"https://pith.science/api/pith-number/763LZF6WS6PMBRCSNTV5IVL6E2/events.json","paper":"https://pith.science/paper/763LZF6W"},"agent_actions":{"view_html":"https://pith.science/pith/763LZF6WS6PMBRCSNTV5IVL6E2","download_json":"https://pith.science/pith/763LZF6WS6PMBRCSNTV5IVL6E2.json","view_paper":"https://pith.science/paper/763LZF6W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.12787&json=true","fetch_graph":"https://pith.science/api/pith-number/763LZF6WS6PMBRCSNTV5IVL6E2/graph.json","fetch_events":"https://pith.science/api/pith-number/763LZF6WS6PMBRCSNTV5IVL6E2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/763LZF6WS6PMBRCSNTV5IVL6E2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/763LZF6WS6PMBRCSNTV5IVL6E2/action/storage_attestation","attest_author":"https://pith.science/pith/763LZF6WS6PMBRCSNTV5IVL6E2/action/author_attestation","sign_citation":"https://pith.science/pith/763LZF6WS6PMBRCSNTV5IVL6E2/action/citation_signature","submit_replication":"https://pith.science/pith/763LZF6WS6PMBRCSNTV5IVL6E2/action/replication_record"}},"created_at":"2026-07-05T05:06:29.950987+00:00","updated_at":"2026-07-05T05:06:29.950987+00:00"}