{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:W6JHQXSFIAK7YXHINZT6TACRKL","short_pith_number":"pith:W6JHQXSF","schema_version":"1.0","canonical_sha256":"b792785e454015fc5ce86e67e9805152c223ade56bbb75881b8694a9296f6e61","source":{"kind":"arxiv","id":"2209.11142","version":2},"attestation_state":"computed","paper":{"title":"A Generalist Neural Algorithmic Learner","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alex Vitvitskyi, Andreea Deac, Andrew Dudzik, Beatrice Bevilacqua, Borja Ibarz, Charles Blundell, George Papamakarios, Kyriacos Nikiforou, Matko Bo\\v{s}njak, Mehdi Bennani, Petar Veli\\v{c}kovi\\'c, R\\'obert Csord\\'as, Vitaly Kurin, Yaroslav Ganin, Yulia Rubanova","submitted_at":"2022-09-22T16:41:33Z","abstract_excerpt":"The cornerstone of neural algorithmic reasoning is the ability to solve algorithmic tasks, especially in a way that generalises out of distribution. While recent years have seen a surge in methodological improvements in this area, they mostly focused on building specialist models. Specialist models are capable of learning to neurally execute either only one algorithm or a collection of algorithms with identical control-flow backbone. Here, instead, we focus on constructing a generalist neural algorithmic learner -- a single graph neural network processor capable of learning to execute a wide r"},"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":"2209.11142","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-09-22T16:41:33Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"d266a3e1d7002eb6e846b698f9e2b9b06956b4739ae4d33c7a4524bd3b8c183a","abstract_canon_sha256":"4d085f067db454820cec41ea08fe307fc5c17ce01561033dd0930eb9cbfda2ec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:22:11.004533Z","signature_b64":"6RoR8PUn4wAFrZE0UfWDZZS/5XDpNuD0snwe53sqLM+en9PFGEpfdb5wL37sK65MlPNAQxWPPBr+mu1wWUBMAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b792785e454015fc5ce86e67e9805152c223ade56bbb75881b8694a9296f6e61","last_reissued_at":"2026-07-05T05:22:11.004021Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:22:11.004021Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Generalist Neural Algorithmic Learner","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alex Vitvitskyi, Andreea Deac, Andrew Dudzik, Beatrice Bevilacqua, Borja Ibarz, Charles Blundell, George Papamakarios, Kyriacos Nikiforou, Matko Bo\\v{s}njak, Mehdi Bennani, Petar Veli\\v{c}kovi\\'c, R\\'obert Csord\\'as, Vitaly Kurin, Yaroslav Ganin, Yulia Rubanova","submitted_at":"2022-09-22T16:41:33Z","abstract_excerpt":"The cornerstone of neural algorithmic reasoning is the ability to solve algorithmic tasks, especially in a way that generalises out of distribution. While recent years have seen a surge in methodological improvements in this area, they mostly focused on building specialist models. Specialist models are capable of learning to neurally execute either only one algorithm or a collection of algorithms with identical control-flow backbone. Here, instead, we focus on constructing a generalist neural algorithmic learner -- a single graph neural network processor capable of learning to execute a wide r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.11142","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/2209.11142/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":"2209.11142","created_at":"2026-07-05T05:22:11.004081+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.11142v2","created_at":"2026-07-05T05:22:11.004081+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.11142","created_at":"2026-07-05T05:22:11.004081+00:00"},{"alias_kind":"pith_short_12","alias_value":"W6JHQXSFIAK7","created_at":"2026-07-05T05:22:11.004081+00:00"},{"alias_kind":"pith_short_16","alias_value":"W6JHQXSFIAK7YXHI","created_at":"2026-07-05T05:22:11.004081+00:00"},{"alias_kind":"pith_short_8","alias_value":"W6JHQXSF","created_at":"2026-07-05T05:22:11.004081+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.18878","citing_title":"Prognostic Value of Lung Ultrasound Biomarkers for Readmission Risk in Congestive Heart Failure: A Pilot Data-Driven Analysis","ref_index":63,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W6JHQXSFIAK7YXHINZT6TACRKL","json":"https://pith.science/pith/W6JHQXSFIAK7YXHINZT6TACRKL.json","graph_json":"https://pith.science/api/pith-number/W6JHQXSFIAK7YXHINZT6TACRKL/graph.json","events_json":"https://pith.science/api/pith-number/W6JHQXSFIAK7YXHINZT6TACRKL/events.json","paper":"https://pith.science/paper/W6JHQXSF"},"agent_actions":{"view_html":"https://pith.science/pith/W6JHQXSFIAK7YXHINZT6TACRKL","download_json":"https://pith.science/pith/W6JHQXSFIAK7YXHINZT6TACRKL.json","view_paper":"https://pith.science/paper/W6JHQXSF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.11142&json=true","fetch_graph":"https://pith.science/api/pith-number/W6JHQXSFIAK7YXHINZT6TACRKL/graph.json","fetch_events":"https://pith.science/api/pith-number/W6JHQXSFIAK7YXHINZT6TACRKL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W6JHQXSFIAK7YXHINZT6TACRKL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W6JHQXSFIAK7YXHINZT6TACRKL/action/storage_attestation","attest_author":"https://pith.science/pith/W6JHQXSFIAK7YXHINZT6TACRKL/action/author_attestation","sign_citation":"https://pith.science/pith/W6JHQXSFIAK7YXHINZT6TACRKL/action/citation_signature","submit_replication":"https://pith.science/pith/W6JHQXSFIAK7YXHINZT6TACRKL/action/replication_record"}},"created_at":"2026-07-05T05:22:11.004081+00:00","updated_at":"2026-07-05T05:22:11.004081+00:00"}