{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:NETO4J3EVUA3GT2JTSHHWT4LDA","short_pith_number":"pith:NETO4J3E","schema_version":"1.0","canonical_sha256":"6926ee2764ad01b34f499c8e7b4f8b1809a6065fd9fd1df79fdee0ed731a725e","source":{"kind":"arxiv","id":"1812.06369","version":2},"attestation_state":"computed","paper":{"title":"Provable limitations of deep learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CC","cs.IT","math.IT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Colin Sandon, Emmanuel Abbe","submitted_at":"2018-12-16T00:10:08Z","abstract_excerpt":"As the success of deep learning reaches more grounds, one would like to also envision the potential limits of deep learning. This paper gives a first set of results proving that certain deep learning algorithms fail at learning certain efficiently learnable functions. The results put forward a notion of cross-predictability that characterizes when such failures take place. Parity functions provide an extreme example with a cross-predictability that decays exponentially, while a mere super-polynomial decay of the cross-predictability is shown to be sufficient to obtain failures. Examples in com"},"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":"1812.06369","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-12-16T00:10:08Z","cross_cats_sorted":["cs.CC","cs.IT","math.IT","stat.ML"],"title_canon_sha256":"a2524cf4a8938c9a9a04a3041c221fb30e7942b28e4f1488836f5c7d4aa5bf74","abstract_canon_sha256":"9d33b0259120f0e90b9fb3a018cfd4264f8e0ddadedd209a4e7965103db16838"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:47:35.923812Z","signature_b64":"Y450AKKtJgsYh7lCMSHPC79rVv8UaK/DE6f6DFCGzvZ7vaAImaU0JylH6mJQKtioYkQvP1TX47ZdpthF0bIUDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6926ee2764ad01b34f499c8e7b4f8b1809a6065fd9fd1df79fdee0ed731a725e","last_reissued_at":"2026-05-17T23:47:35.923162Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:47:35.923162Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Provable limitations of deep learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CC","cs.IT","math.IT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Colin Sandon, Emmanuel Abbe","submitted_at":"2018-12-16T00:10:08Z","abstract_excerpt":"As the success of deep learning reaches more grounds, one would like to also envision the potential limits of deep learning. This paper gives a first set of results proving that certain deep learning algorithms fail at learning certain efficiently learnable functions. The results put forward a notion of cross-predictability that characterizes when such failures take place. Parity functions provide an extreme example with a cross-predictability that decays exponentially, while a mere super-polynomial decay of the cross-predictability is shown to be sufficient to obtain failures. Examples in com"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.06369","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":""},"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":"1812.06369","created_at":"2026-05-17T23:47:35.923256+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.06369v2","created_at":"2026-05-17T23:47:35.923256+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.06369","created_at":"2026-05-17T23:47:35.923256+00:00"},{"alias_kind":"pith_short_12","alias_value":"NETO4J3EVUA3","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_16","alias_value":"NETO4J3EVUA3GT2J","created_at":"2026-05-18T12:32:40.477152+00:00"},{"alias_kind":"pith_short_8","alias_value":"NETO4J3E","created_at":"2026-05-18T12:32:40.477152+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NETO4J3EVUA3GT2JTSHHWT4LDA","json":"https://pith.science/pith/NETO4J3EVUA3GT2JTSHHWT4LDA.json","graph_json":"https://pith.science/api/pith-number/NETO4J3EVUA3GT2JTSHHWT4LDA/graph.json","events_json":"https://pith.science/api/pith-number/NETO4J3EVUA3GT2JTSHHWT4LDA/events.json","paper":"https://pith.science/paper/NETO4J3E"},"agent_actions":{"view_html":"https://pith.science/pith/NETO4J3EVUA3GT2JTSHHWT4LDA","download_json":"https://pith.science/pith/NETO4J3EVUA3GT2JTSHHWT4LDA.json","view_paper":"https://pith.science/paper/NETO4J3E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.06369&json=true","fetch_graph":"https://pith.science/api/pith-number/NETO4J3EVUA3GT2JTSHHWT4LDA/graph.json","fetch_events":"https://pith.science/api/pith-number/NETO4J3EVUA3GT2JTSHHWT4LDA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NETO4J3EVUA3GT2JTSHHWT4LDA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NETO4J3EVUA3GT2JTSHHWT4LDA/action/storage_attestation","attest_author":"https://pith.science/pith/NETO4J3EVUA3GT2JTSHHWT4LDA/action/author_attestation","sign_citation":"https://pith.science/pith/NETO4J3EVUA3GT2JTSHHWT4LDA/action/citation_signature","submit_replication":"https://pith.science/pith/NETO4J3EVUA3GT2JTSHHWT4LDA/action/replication_record"}},"created_at":"2026-05-17T23:47:35.923256+00:00","updated_at":"2026-05-17T23:47:35.923256+00:00"}