{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5D24WWGFMI37DQPZLKPUCXQXUL","short_pith_number":"pith:5D24WWGF","schema_version":"1.0","canonical_sha256":"e8f5cb58c56237f1c1f95a9f415e17a2c65da1695e02914c827eb1706db75ea4","source":{"kind":"arxiv","id":"2310.02579","version":3},"attestation_state":"computed","paper":{"title":"On the Stability of Expressive Positional Encodings for Graphs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Joshua Robinson, Muhan Zhang, Pan Li, Stefanie Jegelka, William Lu, Yinan Huang, Yu Yang","submitted_at":"2023-10-04T04:48:55Z","abstract_excerpt":"Designing effective positional encodings for graphs is key to building powerful graph transformers and enhancing message-passing graph neural networks. Although widespread, using Laplacian eigenvectors as positional encodings faces two fundamental challenges: (1) \\emph{Non-uniqueness}: there are many different eigendecompositions of the same Laplacian, and (2) \\emph{Instability}: small perturbations to the Laplacian could result in completely different eigenspaces, leading to unpredictable changes in positional encoding. Despite many attempts to address non-uniqueness, most methods overlook st"},"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":"2310.02579","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-04T04:48:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8c9cc990d6de6d463c890c815ca4358aa69c6658ca3e849a39a0f9a13811929d","abstract_canon_sha256":"d7fd7640fc96ced6779c562fec1dffee131a3ab780a266ed80859192658dc61c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:57.340828Z","signature_b64":"mXou8IApnogTYPQ2JvI1103/tkjVOsiVNtCIdfFH84gdg2Cf1vPzSYwCrVROScRGGtrii6gryj2a8SH97gtMAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8f5cb58c56237f1c1f95a9f415e17a2c65da1695e02914c827eb1706db75ea4","last_reissued_at":"2026-07-05T08:28:57.340405Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:57.340405Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Stability of Expressive Positional Encodings for Graphs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Joshua Robinson, Muhan Zhang, Pan Li, Stefanie Jegelka, William Lu, Yinan Huang, Yu Yang","submitted_at":"2023-10-04T04:48:55Z","abstract_excerpt":"Designing effective positional encodings for graphs is key to building powerful graph transformers and enhancing message-passing graph neural networks. Although widespread, using Laplacian eigenvectors as positional encodings faces two fundamental challenges: (1) \\emph{Non-uniqueness}: there are many different eigendecompositions of the same Laplacian, and (2) \\emph{Instability}: small perturbations to the Laplacian could result in completely different eigenspaces, leading to unpredictable changes in positional encoding. Despite many attempts to address non-uniqueness, most methods overlook st"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.02579","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/2310.02579/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":"2310.02579","created_at":"2026-07-05T08:28:57.340469+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.02579v3","created_at":"2026-07-05T08:28:57.340469+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.02579","created_at":"2026-07-05T08:28:57.340469+00:00"},{"alias_kind":"pith_short_12","alias_value":"5D24WWGFMI37","created_at":"2026-07-05T08:28:57.340469+00:00"},{"alias_kind":"pith_short_16","alias_value":"5D24WWGFMI37DQPZ","created_at":"2026-07-05T08:28:57.340469+00:00"},{"alias_kind":"pith_short_8","alias_value":"5D24WWGF","created_at":"2026-07-05T08:28:57.340469+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25293","citing_title":"Communicability-Inspired Positional Encoding (CIPE)","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29828","citing_title":"When Do Graph Foundation Models Transfer? A Data-Centric Theory","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2509.21000","citing_title":"Feature Augmentation of GNNs for ILPs: Local Uniqueness Suffices","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15699","citing_title":"Frequency-Corrupt Based Graph Self-Supervised Learning","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5D24WWGFMI37DQPZLKPUCXQXUL","json":"https://pith.science/pith/5D24WWGFMI37DQPZLKPUCXQXUL.json","graph_json":"https://pith.science/api/pith-number/5D24WWGFMI37DQPZLKPUCXQXUL/graph.json","events_json":"https://pith.science/api/pith-number/5D24WWGFMI37DQPZLKPUCXQXUL/events.json","paper":"https://pith.science/paper/5D24WWGF"},"agent_actions":{"view_html":"https://pith.science/pith/5D24WWGFMI37DQPZLKPUCXQXUL","download_json":"https://pith.science/pith/5D24WWGFMI37DQPZLKPUCXQXUL.json","view_paper":"https://pith.science/paper/5D24WWGF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.02579&json=true","fetch_graph":"https://pith.science/api/pith-number/5D24WWGFMI37DQPZLKPUCXQXUL/graph.json","fetch_events":"https://pith.science/api/pith-number/5D24WWGFMI37DQPZLKPUCXQXUL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5D24WWGFMI37DQPZLKPUCXQXUL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5D24WWGFMI37DQPZLKPUCXQXUL/action/storage_attestation","attest_author":"https://pith.science/pith/5D24WWGFMI37DQPZLKPUCXQXUL/action/author_attestation","sign_citation":"https://pith.science/pith/5D24WWGFMI37DQPZLKPUCXQXUL/action/citation_signature","submit_replication":"https://pith.science/pith/5D24WWGFMI37DQPZLKPUCXQXUL/action/replication_record"}},"created_at":"2026-07-05T08:28:57.340469+00:00","updated_at":"2026-07-05T08:28:57.340469+00:00"}