{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:RIH7YYHYYZKYI3DGQWJ6HCGVVB","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"5c93c13b5f0643d050e3c44e3d285933af4c6c0548e5a5fbd93d1ba6eb0fee46","cross_cats_sorted":["cs.CC","cs.IT","math.IT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-07T08:31:50Z","title_canon_sha256":"6289cb90f8317abbbcc07663b4dbf1ec564cc5d9476754adad6dc433e41757e6"},"schema_version":"1.0","source":{"id":"2001.02992","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2001.02992","created_at":"2026-07-05T00:32:32Z"},{"alias_kind":"arxiv_version","alias_value":"2001.02992v1","created_at":"2026-07-05T00:32:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.02992","created_at":"2026-07-05T00:32:32Z"},{"alias_kind":"pith_short_12","alias_value":"RIH7YYHYYZKY","created_at":"2026-07-05T00:32:32Z"},{"alias_kind":"pith_short_16","alias_value":"RIH7YYHYYZKYI3DG","created_at":"2026-07-05T00:32:32Z"},{"alias_kind":"pith_short_8","alias_value":"RIH7YYHY","created_at":"2026-07-05T00:32:32Z"}],"graph_snapshots":[{"event_id":"sha256:db5ee53dc1d8c0458e83776144ef115b7e24a614c59274d97c80e1eedf7d2e09","target":"graph","created_at":"2026-07-05T00:32:32Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2001.02992/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The goal of this paper is to characterize function distributions that deep learning can or cannot learn in poly-time. A universality result is proved for SGD-based deep learning and a non-universality result is proved for GD-based deep learning; this also gives a separation between SGD-based deep learning and statistical query algorithms:\n  (1) {\\it Deep learning with SGD is efficiently universal.} Any function distribution that can be learned from samples in poly-time can also be learned by a poly-size neural net trained with SGD on a poly-time initialization with poly-steps, poly-rate and po","authors_text":"Colin Sandon, Emmanuel Abbe","cross_cats":["cs.CC","cs.IT","math.IT","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-07T08:31:50Z","title":"Poly-time universality and limitations of deep learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.02992","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:68e630d65a772cdc7fac15d007e3d127089d07cc66a02a34ee2767fdc32c6692","target":"record","created_at":"2026-07-05T00:32:32Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"5c93c13b5f0643d050e3c44e3d285933af4c6c0548e5a5fbd93d1ba6eb0fee46","cross_cats_sorted":["cs.CC","cs.IT","math.IT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-07T08:31:50Z","title_canon_sha256":"6289cb90f8317abbbcc07663b4dbf1ec564cc5d9476754adad6dc433e41757e6"},"schema_version":"1.0","source":{"id":"2001.02992","kind":"arxiv","version":1}},"canonical_sha256":"8a0ffc60f8c655846c668593e388d5a86024e29ef5e8e7a7f72b0d4145d0c912","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8a0ffc60f8c655846c668593e388d5a86024e29ef5e8e7a7f72b0d4145d0c912","first_computed_at":"2026-07-05T00:32:32.516309Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:32:32.516309Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BjNzQHj/kfP8GLduClJMtiuoHQz8hkXapc224qj9Zau3S2i2gvU3H2giW7xHq551rlipZ+KfswqsYjBUcRplBg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:32:32.516765Z","signed_message":"canonical_sha256_bytes"},"source_id":"2001.02992","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:68e630d65a772cdc7fac15d007e3d127089d07cc66a02a34ee2767fdc32c6692","sha256:db5ee53dc1d8c0458e83776144ef115b7e24a614c59274d97c80e1eedf7d2e09"],"state_sha256":"aadd80d46897cb2fbb724a0512520798851de53165c911ac45bdd34b695e3030"}