{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:WDFHDCH3NDGRKFURVUPZKJQ7BU","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":"4096c04a2c09835e7ae6d0f55757f066dc4a085a0d8fa51f04c573dd7d7eb617","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-02-18T14:23:44Z","title_canon_sha256":"4c10782922219242957ab14cac35785fdcfb2f73ac7d6bb33ce60df9c63d8f8c"},"schema_version":"1.0","source":{"id":"1802.06384","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.06384","created_at":"2026-07-05T01:10:53Z"},{"alias_kind":"arxiv_version","alias_value":"1802.06384v4","created_at":"2026-07-05T01:10:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.06384","created_at":"2026-07-05T01:10:53Z"},{"alias_kind":"pith_short_12","alias_value":"WDFHDCH3NDGR","created_at":"2026-07-05T01:10:53Z"},{"alias_kind":"pith_short_16","alias_value":"WDFHDCH3NDGRKFUR","created_at":"2026-07-05T01:10:53Z"},{"alias_kind":"pith_short_8","alias_value":"WDFHDCH3","created_at":"2026-07-05T01:10:53Z"}],"graph_snapshots":[{"event_id":"sha256:13e355d36f87824b37b13350339d4f510d1739eb916dcfd589c81135e98f836d","target":"graph","created_at":"2026-07-05T01:10:53Z","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/1802.06384/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Neural networks provide a rich class of high-dimensional, non-convex optimization problems. Despite their non-convexity, gradient-descent methods often successfully optimize these models. This has motivated a recent spur in research attempting to characterize properties of their loss surface that may explain such success.\n  In this paper, we address this phenomenon by studying a key topological property of the loss: the presence or absence of spurious valleys, defined as connected components of sub-level sets that do not include a global minimum. Focusing on a class of two-layer neural network","authors_text":"Afonso S. Bandeira, Joan Bruna, Luca Venturi","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-02-18T14:23:44Z","title":"Spurious Valleys in Two-layer Neural Network Optimization Landscapes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.06384","kind":"arxiv","version":4},"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:adc6391e793897c674d87a6d7c08b21e3dbc506b9e30ca19ad8c0b6b268bb556","target":"record","created_at":"2026-07-05T01:10:53Z","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":"4096c04a2c09835e7ae6d0f55757f066dc4a085a0d8fa51f04c573dd7d7eb617","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-02-18T14:23:44Z","title_canon_sha256":"4c10782922219242957ab14cac35785fdcfb2f73ac7d6bb33ce60df9c63d8f8c"},"schema_version":"1.0","source":{"id":"1802.06384","kind":"arxiv","version":4}},"canonical_sha256":"b0ca7188fb68cd151691ad1f95261f0d0ec549818c457c04a8a7d60f1973f962","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b0ca7188fb68cd151691ad1f95261f0d0ec549818c457c04a8a7d60f1973f962","first_computed_at":"2026-07-05T01:10:53.759742Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:10:53.759742Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LA4PKKsrQu6+xezE5pXHoaZGS43M5guQ8V15TvZ13aaI+ELuaYXargCIzx9j2aFduJUwnfB1pMOUM1eAAKCBAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:10:53.760223Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.06384","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:adc6391e793897c674d87a6d7c08b21e3dbc506b9e30ca19ad8c0b6b268bb556","sha256:13e355d36f87824b37b13350339d4f510d1739eb916dcfd589c81135e98f836d"],"state_sha256":"962a678ca938645869a8a87afc7e469efc3470c9143b657f93b2a71c472d753a"}