{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:R54K2ANPNG2FM6JYVZBMUMB3CJ","short_pith_number":"pith:R54K2ANP","schema_version":"1.0","canonical_sha256":"8f78ad01af69b4567938ae42ca303b125633f397baf778391238b0eb369ff89f","source":{"kind":"arxiv","id":"2110.09485","version":2},"attestation_state":"computed","paper":{"title":"Learning in High Dimension Always Amounts to Extrapolation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Jerome Pesenti, Randall Balestriero, Yann LeCun","submitted_at":"2021-10-18T17:32:25Z","abstract_excerpt":"The notion of interpolation and extrapolation is fundamental in various fields from deep learning to function approximation. Interpolation occurs for a sample $x$ whenever this sample falls inside or on the boundary of the given dataset's convex hull. Extrapolation occurs when $x$ falls outside of that convex hull. One fundamental (mis)conception is that state-of-the-art algorithms work so well because of their ability to correctly interpolate training data. A second (mis)conception is that interpolation happens throughout tasks and datasets, in fact, many intuitions and theories rely on that "},"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":"2110.09485","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-18T17:32:25Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"2e6c175b008b8e1526a308d5f8fb25e6deb083e9b795e3e45e239b327acd9859","abstract_canon_sha256":"e566c02b91b9f32c7a1944aec735197dcccfb6dc6bd4f0c6884db839765c55ee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:27:36.592278Z","signature_b64":"5TiIo3RgtfTk8Z/9QeG6FvZGOVFqiyaI0arukzuIp/Ni4he+VTn/cdK8niFEcTOVYbGq3MH6yVpXK7gY03HfCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f78ad01af69b4567938ae42ca303b125633f397baf778391238b0eb369ff89f","last_reissued_at":"2026-07-05T03:27:36.590674Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:27:36.590674Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning in High Dimension Always Amounts to Extrapolation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Jerome Pesenti, Randall Balestriero, Yann LeCun","submitted_at":"2021-10-18T17:32:25Z","abstract_excerpt":"The notion of interpolation and extrapolation is fundamental in various fields from deep learning to function approximation. Interpolation occurs for a sample $x$ whenever this sample falls inside or on the boundary of the given dataset's convex hull. Extrapolation occurs when $x$ falls outside of that convex hull. One fundamental (mis)conception is that state-of-the-art algorithms work so well because of their ability to correctly interpolate training data. A second (mis)conception is that interpolation happens throughout tasks and datasets, in fact, many intuitions and theories rely on that "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.09485","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/2110.09485/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":"2110.09485","created_at":"2026-07-05T03:27:36.591815+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.09485v2","created_at":"2026-07-05T03:27:36.591815+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.09485","created_at":"2026-07-05T03:27:36.591815+00:00"},{"alias_kind":"pith_short_12","alias_value":"R54K2ANPNG2F","created_at":"2026-07-05T03:27:36.591815+00:00"},{"alias_kind":"pith_short_16","alias_value":"R54K2ANPNG2FM6JY","created_at":"2026-07-05T03:27:36.591815+00:00"},{"alias_kind":"pith_short_8","alias_value":"R54K2ANP","created_at":"2026-07-05T03:27:36.591815+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19642","citing_title":"Rigorous uncertainty quantification of probabilistic AI weather forecasts with conformal prediction","ref_index":130,"is_internal_anchor":false},{"citing_arxiv_id":"2512.24365","citing_title":"A Critical Assessment of PINNs and Operator Learning for Geotechnical Engineering","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17642","citing_title":"TabKDE: Simple and Scalable Tabular Data Generation with Kernel Density Estimates","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2411.15633","citing_title":"Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detection","ref_index":116,"is_internal_anchor":false},{"citing_arxiv_id":"2309.16797","citing_title":"Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19653","citing_title":"A Dual Perspective on Synthetic Trajectory Generators: Utility Framework and Privacy Vulnerabilities","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07565","citing_title":"Ensemble Distributionally Robust Bayesian Optimisation with Continuous Context","ref_index":92,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00510","citing_title":"Scale-Aware Adversarial Analysis: A Diagnostic for Generative AI in Multiscale Complex Systems","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05493","citing_title":"A renormalization-group inspired lattice-based framework for piecewise generalized linear models","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R54K2ANPNG2FM6JYVZBMUMB3CJ","json":"https://pith.science/pith/R54K2ANPNG2FM6JYVZBMUMB3CJ.json","graph_json":"https://pith.science/api/pith-number/R54K2ANPNG2FM6JYVZBMUMB3CJ/graph.json","events_json":"https://pith.science/api/pith-number/R54K2ANPNG2FM6JYVZBMUMB3CJ/events.json","paper":"https://pith.science/paper/R54K2ANP"},"agent_actions":{"view_html":"https://pith.science/pith/R54K2ANPNG2FM6JYVZBMUMB3CJ","download_json":"https://pith.science/pith/R54K2ANPNG2FM6JYVZBMUMB3CJ.json","view_paper":"https://pith.science/paper/R54K2ANP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.09485&json=true","fetch_graph":"https://pith.science/api/pith-number/R54K2ANPNG2FM6JYVZBMUMB3CJ/graph.json","fetch_events":"https://pith.science/api/pith-number/R54K2ANPNG2FM6JYVZBMUMB3CJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R54K2ANPNG2FM6JYVZBMUMB3CJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R54K2ANPNG2FM6JYVZBMUMB3CJ/action/storage_attestation","attest_author":"https://pith.science/pith/R54K2ANPNG2FM6JYVZBMUMB3CJ/action/author_attestation","sign_citation":"https://pith.science/pith/R54K2ANPNG2FM6JYVZBMUMB3CJ/action/citation_signature","submit_replication":"https://pith.science/pith/R54K2ANPNG2FM6JYVZBMUMB3CJ/action/replication_record"}},"created_at":"2026-07-05T03:27:36.591815+00:00","updated_at":"2026-07-05T03:27:36.591815+00:00"}