{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:ROC472EEIY6M3LNEB6BLQHFXUT","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":"526e363ccdb8f3ec943494178b68b806c18a5b4fe38ea6758a3cb91753d0b4d4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2022-12-26T12:29:12Z","title_canon_sha256":"5d045218c247d7eac91ee024e366afd75678ee04c3c2aae840c1f53e596dd1f7"},"schema_version":"1.0","source":{"id":"2212.13111","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2212.13111","created_at":"2026-07-05T12:01:17Z"},{"alias_kind":"arxiv_version","alias_value":"2212.13111v2","created_at":"2026-07-05T12:01:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.13111","created_at":"2026-07-05T12:01:17Z"},{"alias_kind":"pith_short_12","alias_value":"ROC472EEIY6M","created_at":"2026-07-05T12:01:17Z"},{"alias_kind":"pith_short_16","alias_value":"ROC472EEIY6M3LNE","created_at":"2026-07-05T12:01:17Z"},{"alias_kind":"pith_short_8","alias_value":"ROC472EE","created_at":"2026-07-05T12:01:17Z"}],"graph_snapshots":[{"event_id":"sha256:5b675e985aa8681eb1c21227051d1c0aed5c5a65fe78e86f75b313514a3f53bf","target":"graph","created_at":"2026-07-05T12:01:17Z","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/2212.13111/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Gradient descent (GD) methods for the training of artificial neural networks (ANNs) belong nowadays to the most heavily employed computational schemes in the digital world. Despite the compelling success of such methods, it remains an open problem to provide a rigorous theoretical justification for the success of GD methods in the training of ANNs. The main difficulty is that the optimization risk landscapes associated to ANNs usually admit many non-optimal critical points (saddle points as well as non-global local minima) whose risk values are strictly larger than the optimal risk value. It i","authors_text":"Adrian Riekert, Arnulf Jentzen, Shokhrukh Ibragimov","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2022-12-26T12:29:12Z","title":"Convergence to good non-optimal critical points in the training of neural networks: Gradient descent optimization with one random initialization overcomes all bad non-global local minima with high probability"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.13111","kind":"arxiv","version":2},"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":"sha256:08592807d7b3fe558b656aa5b8f200f7805e19e90f64593ecdae6fc2f7175d24","target":"record","created_at":"2026-07-05T12:01:17Z","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":"526e363ccdb8f3ec943494178b68b806c18a5b4fe38ea6758a3cb91753d0b4d4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2022-12-26T12:29:12Z","title_canon_sha256":"5d045218c247d7eac91ee024e366afd75678ee04c3c2aae840c1f53e596dd1f7"},"schema_version":"1.0","source":{"id":"2212.13111","kind":"arxiv","version":2}},"canonical_sha256":"8b85cfe884463ccdada40f82b81cb7a4f1e78159528126b354744a6492f9336e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8b85cfe884463ccdada40f82b81cb7a4f1e78159528126b354744a6492f9336e","first_computed_at":"2026-07-05T12:01:17.012676Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:01:17.012676Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TzWbpW84D7yaZHkA6rgxjbwWfAY7zULzgglVuT3Xz5+kDfRY7szlCRGomxjrb8VtPSa2DQi2uB39dCfJ5Wo9Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T12:01:17.013098Z","signed_message":"canonical_sha256_bytes"},"source_id":"2212.13111","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:08592807d7b3fe558b656aa5b8f200f7805e19e90f64593ecdae6fc2f7175d24","sha256:5b675e985aa8681eb1c21227051d1c0aed5c5a65fe78e86f75b313514a3f53bf"],"state_sha256":"11b85a29bbf57212b4901f669adeb5f8262ee2345045d1852c8ff4b877525878"}