{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:MXBXCSUTHNQCNJ67H53DVMOSEA","short_pith_number":"pith:MXBXCSUT","schema_version":"1.0","canonical_sha256":"65c3714a933b6026a7df3f763ab1d22005ad9b8f8187013482ee9d8d01ac688b","source":{"kind":"arxiv","id":"2211.00692","version":2},"attestation_state":"computed","paper":{"title":"Towards Better Out-of-Distribution Generalization of Neural Algorithmic Reasoning Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Christos Thrampoulidis, Kevin Swersky, Milad Hashemi, Renjie Liao, Sadegh Mahdavi, Thomas Kipf","submitted_at":"2022-11-01T18:33:20Z","abstract_excerpt":"In this paper, we study the OOD generalization of neural algorithmic reasoning tasks, where the goal is to learn an algorithm (e.g., sorting, breadth-first search, and depth-first search) from input-output pairs using deep neural networks. First, we argue that OOD generalization in this setting is significantly different than common OOD settings. For example, some phenomena in OOD generalization of image classifications such as \\emph{accuracy on the line} are not observed here, and techniques such as data augmentation methods do not help as assumptions underlying many augmentation techniques a"},"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":"2211.00692","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-11-01T18:33:20Z","cross_cats_sorted":[],"title_canon_sha256":"81dacc3af428e3a55d9d4dd953994f6a9420b9f053db2cd73344c934ba1a5310","abstract_canon_sha256":"4c4ced90994e829f04a71a5ce671b97abe062c9d38eb59b7c07af71f418d2ae0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:52:23.453127Z","signature_b64":"sucUAEj/Jb0DXJfJugvO1GTayllvXsT8jEsYdL9kRzvG703yJLK2qjMilZXh7GEm/7BkpDWYCkRRdeHwgUqgBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65c3714a933b6026a7df3f763ab1d22005ad9b8f8187013482ee9d8d01ac688b","last_reissued_at":"2026-07-05T05:52:23.452650Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:52:23.452650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Better Out-of-Distribution Generalization of Neural Algorithmic Reasoning Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Christos Thrampoulidis, Kevin Swersky, Milad Hashemi, Renjie Liao, Sadegh Mahdavi, Thomas Kipf","submitted_at":"2022-11-01T18:33:20Z","abstract_excerpt":"In this paper, we study the OOD generalization of neural algorithmic reasoning tasks, where the goal is to learn an algorithm (e.g., sorting, breadth-first search, and depth-first search) from input-output pairs using deep neural networks. First, we argue that OOD generalization in this setting is significantly different than common OOD settings. For example, some phenomena in OOD generalization of image classifications such as \\emph{accuracy on the line} are not observed here, and techniques such as data augmentation methods do not help as assumptions underlying many augmentation techniques a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.00692","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/2211.00692/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":"2211.00692","created_at":"2026-07-05T05:52:23.452710+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.00692v2","created_at":"2026-07-05T05:52:23.452710+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.00692","created_at":"2026-07-05T05:52:23.452710+00:00"},{"alias_kind":"pith_short_12","alias_value":"MXBXCSUTHNQC","created_at":"2026-07-05T05:52:23.452710+00:00"},{"alias_kind":"pith_short_16","alias_value":"MXBXCSUTHNQCNJ67","created_at":"2026-07-05T05:52:23.452710+00:00"},{"alias_kind":"pith_short_8","alias_value":"MXBXCSUT","created_at":"2026-07-05T05:52:23.452710+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26749","citing_title":"Structure Before Collapse: Transient semantic geometry in next-token prediction","ref_index":148,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MXBXCSUTHNQCNJ67H53DVMOSEA","json":"https://pith.science/pith/MXBXCSUTHNQCNJ67H53DVMOSEA.json","graph_json":"https://pith.science/api/pith-number/MXBXCSUTHNQCNJ67H53DVMOSEA/graph.json","events_json":"https://pith.science/api/pith-number/MXBXCSUTHNQCNJ67H53DVMOSEA/events.json","paper":"https://pith.science/paper/MXBXCSUT"},"agent_actions":{"view_html":"https://pith.science/pith/MXBXCSUTHNQCNJ67H53DVMOSEA","download_json":"https://pith.science/pith/MXBXCSUTHNQCNJ67H53DVMOSEA.json","view_paper":"https://pith.science/paper/MXBXCSUT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.00692&json=true","fetch_graph":"https://pith.science/api/pith-number/MXBXCSUTHNQCNJ67H53DVMOSEA/graph.json","fetch_events":"https://pith.science/api/pith-number/MXBXCSUTHNQCNJ67H53DVMOSEA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MXBXCSUTHNQCNJ67H53DVMOSEA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MXBXCSUTHNQCNJ67H53DVMOSEA/action/storage_attestation","attest_author":"https://pith.science/pith/MXBXCSUTHNQCNJ67H53DVMOSEA/action/author_attestation","sign_citation":"https://pith.science/pith/MXBXCSUTHNQCNJ67H53DVMOSEA/action/citation_signature","submit_replication":"https://pith.science/pith/MXBXCSUTHNQCNJ67H53DVMOSEA/action/replication_record"}},"created_at":"2026-07-05T05:52:23.452710+00:00","updated_at":"2026-07-05T05:52:23.452710+00:00"}