{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UXPYVQGTDHLPXRASG2IP54RJWD","short_pith_number":"pith:UXPYVQGT","schema_version":"1.0","canonical_sha256":"a5df8ac0d319d6fbc4123690fef229b0d116005ed7f6dad7dda2913e44650d11","source":{"kind":"arxiv","id":"2503.19173","version":2},"attestation_state":"computed","paper":{"title":"Graph neural networks extrapolate out-of-distribution for shortest paths","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DS"],"primary_cat":"cs.LG","authors_text":"Robert R. Nerem, Samantha Chen, Sanjoy Dasgupta, Yusu Wang","submitted_at":"2025-03-24T21:52:05Z","abstract_excerpt":"Neural networks (NNs), despite their success and wide adoption, still struggle to extrapolate out-of-distribution (OOD), i.e., to inputs that are not well-represented by their training dataset. Addressing the OOD generalization gap is crucial when models are deployed in environments significantly different from the training set, such as applying Graph Neural Networks (GNNs) trained on small graphs to large, real-world graphs. One promising approach for achieving robust OOD generalization is the framework of neural algorithmic alignment, which incorporates ideas from classical algorithms by des"},"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":"2503.19173","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-24T21:52:05Z","cross_cats_sorted":["cs.DS"],"title_canon_sha256":"5a4f8ec2b1b51ce8130713f29545e3fe65878713bfff9d35bca06d84ee13575c","abstract_canon_sha256":"b27b30216cd1617749a83fce0f952f336cf4ce1a5822aa4d83b64e13eb8c24cd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:41:54.047299Z","signature_b64":"CqYDkRkCTvJ8/fRaTSMu2mwhBuXxoOeY1zIvwEE3tEWjgq+sl8y/0L018LMdYbhgCBX/Xb6hQPZPOUzLLURqCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5df8ac0d319d6fbc4123690fef229b0d116005ed7f6dad7dda2913e44650d11","last_reissued_at":"2026-07-05T10:41:54.046817Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:41:54.046817Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Graph neural networks extrapolate out-of-distribution for shortest paths","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DS"],"primary_cat":"cs.LG","authors_text":"Robert R. Nerem, Samantha Chen, Sanjoy Dasgupta, Yusu Wang","submitted_at":"2025-03-24T21:52:05Z","abstract_excerpt":"Neural networks (NNs), despite their success and wide adoption, still struggle to extrapolate out-of-distribution (OOD), i.e., to inputs that are not well-represented by their training dataset. Addressing the OOD generalization gap is crucial when models are deployed in environments significantly different from the training set, such as applying Graph Neural Networks (GNNs) trained on small graphs to large, real-world graphs. One promising approach for achieving robust OOD generalization is the framework of neural algorithmic alignment, which incorporates ideas from classical algorithms by des"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.19173","kind":"arxiv","version":2},"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/2503.19173/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":"2503.19173","created_at":"2026-07-05T10:41:54.046874+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.19173v2","created_at":"2026-07-05T10:41:54.046874+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.19173","created_at":"2026-07-05T10:41:54.046874+00:00"},{"alias_kind":"pith_short_12","alias_value":"UXPYVQGTDHLP","created_at":"2026-07-05T10:41:54.046874+00:00"},{"alias_kind":"pith_short_16","alias_value":"UXPYVQGTDHLPXRAS","created_at":"2026-07-05T10:41:54.046874+00:00"},{"alias_kind":"pith_short_8","alias_value":"UXPYVQGT","created_at":"2026-07-05T10:41:54.046874+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.13155","citing_title":"Learning to Approximate Uniform Facility Location via Graph Neural Networks","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UXPYVQGTDHLPXRASG2IP54RJWD","json":"https://pith.science/pith/UXPYVQGTDHLPXRASG2IP54RJWD.json","graph_json":"https://pith.science/api/pith-number/UXPYVQGTDHLPXRASG2IP54RJWD/graph.json","events_json":"https://pith.science/api/pith-number/UXPYVQGTDHLPXRASG2IP54RJWD/events.json","paper":"https://pith.science/paper/UXPYVQGT"},"agent_actions":{"view_html":"https://pith.science/pith/UXPYVQGTDHLPXRASG2IP54RJWD","download_json":"https://pith.science/pith/UXPYVQGTDHLPXRASG2IP54RJWD.json","view_paper":"https://pith.science/paper/UXPYVQGT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.19173&json=true","fetch_graph":"https://pith.science/api/pith-number/UXPYVQGTDHLPXRASG2IP54RJWD/graph.json","fetch_events":"https://pith.science/api/pith-number/UXPYVQGTDHLPXRASG2IP54RJWD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UXPYVQGTDHLPXRASG2IP54RJWD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UXPYVQGTDHLPXRASG2IP54RJWD/action/storage_attestation","attest_author":"https://pith.science/pith/UXPYVQGTDHLPXRASG2IP54RJWD/action/author_attestation","sign_citation":"https://pith.science/pith/UXPYVQGTDHLPXRASG2IP54RJWD/action/citation_signature","submit_replication":"https://pith.science/pith/UXPYVQGTDHLPXRASG2IP54RJWD/action/replication_record"}},"created_at":"2026-07-05T10:41:54.046874+00:00","updated_at":"2026-07-05T10:41:54.046874+00:00"}