{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:4SXXL6IAIUK6QMQRHB74MWOYMY","short_pith_number":"pith:4SXXL6IA","canonical_record":{"source":{"id":"1702.05777","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-02-19T18:12:51Z","cross_cats_sorted":[],"title_canon_sha256":"ee27cd6e5e493be8a90393e4de1d3c374ca3f12ac6c6b51a483a602d5a5850c3","abstract_canon_sha256":"90ab65f48e5bcad776fb55a0304615fc11a7195e67750f5cbdb9737a57aec06d"},"schema_version":"1.0"},"canonical_sha256":"e4af75f9004515e83211387fc659d8660229f919e04df3ac9cbaa733c28157a9","source":{"kind":"arxiv","id":"1702.05777","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.05777","created_at":"2026-05-18T00:31:51Z"},{"alias_kind":"arxiv_version","alias_value":"1702.05777v5","created_at":"2026-05-18T00:31:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.05777","created_at":"2026-05-18T00:31:51Z"},{"alias_kind":"pith_short_12","alias_value":"4SXXL6IAIUK6","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"4SXXL6IAIUK6QMQR","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"4SXXL6IA","created_at":"2026-05-18T12:31:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:4SXXL6IAIUK6QMQRHB74MWOYMY","target":"record","payload":{"canonical_record":{"source":{"id":"1702.05777","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-02-19T18:12:51Z","cross_cats_sorted":[],"title_canon_sha256":"ee27cd6e5e493be8a90393e4de1d3c374ca3f12ac6c6b51a483a602d5a5850c3","abstract_canon_sha256":"90ab65f48e5bcad776fb55a0304615fc11a7195e67750f5cbdb9737a57aec06d"},"schema_version":"1.0"},"canonical_sha256":"e4af75f9004515e83211387fc659d8660229f919e04df3ac9cbaa733c28157a9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:31:51.467781Z","signature_b64":"o+LnG544u+5BWV+Xn/RBpWElTTyQI22dUfRndXTPJp2zGGyETtka8nEjXCPdnQ+tgqEYa7KVsXJoMcOF9cK3Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e4af75f9004515e83211387fc659d8660229f919e04df3ac9cbaa733c28157a9","last_reissued_at":"2026-05-18T00:31:51.464296Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:31:51.464296Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1702.05777","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:31:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iCyrZP5A5462GYiY55mZ7Zg6WmmjO32VId8wvOkT6GtkjCr+CVAv1M0UqnEGl6Pjjw0TFQChn4yIl1Z3krQuDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T22:12:09.772963Z"},"content_sha256":"83a92a2e80f42e46119de5881f06130eaa62e33335fa6d8de6efe8aa8e777fa0","schema_version":"1.0","event_id":"sha256:83a92a2e80f42e46119de5881f06130eaa62e33335fa6d8de6efe8aa8e777fa0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:4SXXL6IAIUK6QMQRHB74MWOYMY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Exponentially vanishing sub-optimal local minima in multilayer neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Daniel Soudry, Elad Hoffer","submitted_at":"2017-02-19T18:12:51Z","abstract_excerpt":"Background: Statistical mechanics results (Dauphin et al. (2014); Choromanska et al. (2015)) suggest that local minima with high error are exponentially rare in high dimensions. However, to prove low error guarantees for Multilayer Neural Networks (MNNs), previous works so far required either a heavily modified MNN model or training method, strong assumptions on the labels (e.g., \"near\" linear separability), or an unrealistic hidden layer with $\\Omega\\left(N\\right)$ units.\n  Results: We examine a MNN with one hidden layer of piecewise linear units, a single output, and a quadratic loss. We pro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.05777","kind":"arxiv","version":5},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:31:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kNSPrKTlul7KrAqOr8qpUCmuXUU1PNsO/Okopbu6co3L2c/hjxhmvjBRXq0A380KI5qd+r49QtbJa4NC+sapAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T22:12:09.773607Z"},"content_sha256":"93f737133f0d5023616fdf039817cd07dcefa1143e4ea316cafde5416f65fec2","schema_version":"1.0","event_id":"sha256:93f737133f0d5023616fdf039817cd07dcefa1143e4ea316cafde5416f65fec2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4SXXL6IAIUK6QMQRHB74MWOYMY/bundle.json","state_url":"https://pith.science/pith/4SXXL6IAIUK6QMQRHB74MWOYMY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4SXXL6IAIUK6QMQRHB74MWOYMY/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-28T22:12:09Z","links":{"resolver":"https://pith.science/pith/4SXXL6IAIUK6QMQRHB74MWOYMY","bundle":"https://pith.science/pith/4SXXL6IAIUK6QMQRHB74MWOYMY/bundle.json","state":"https://pith.science/pith/4SXXL6IAIUK6QMQRHB74MWOYMY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4SXXL6IAIUK6QMQRHB74MWOYMY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:4SXXL6IAIUK6QMQRHB74MWOYMY","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":"90ab65f48e5bcad776fb55a0304615fc11a7195e67750f5cbdb9737a57aec06d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-02-19T18:12:51Z","title_canon_sha256":"ee27cd6e5e493be8a90393e4de1d3c374ca3f12ac6c6b51a483a602d5a5850c3"},"schema_version":"1.0","source":{"id":"1702.05777","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.05777","created_at":"2026-05-18T00:31:51Z"},{"alias_kind":"arxiv_version","alias_value":"1702.05777v5","created_at":"2026-05-18T00:31:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.05777","created_at":"2026-05-18T00:31:51Z"},{"alias_kind":"pith_short_12","alias_value":"4SXXL6IAIUK6","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"4SXXL6IAIUK6QMQR","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"4SXXL6IA","created_at":"2026-05-18T12:31:00Z"}],"graph_snapshots":[{"event_id":"sha256:93f737133f0d5023616fdf039817cd07dcefa1143e4ea316cafde5416f65fec2","target":"graph","created_at":"2026-05-18T00:31:51Z","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"},"paper":{"abstract_excerpt":"Background: Statistical mechanics results (Dauphin et al. (2014); Choromanska et al. (2015)) suggest that local minima with high error are exponentially rare in high dimensions. However, to prove low error guarantees for Multilayer Neural Networks (MNNs), previous works so far required either a heavily modified MNN model or training method, strong assumptions on the labels (e.g., \"near\" linear separability), or an unrealistic hidden layer with $\\Omega\\left(N\\right)$ units.\n  Results: We examine a MNN with one hidden layer of piecewise linear units, a single output, and a quadratic loss. We pro","authors_text":"Daniel Soudry, Elad Hoffer","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-02-19T18:12:51Z","title":"Exponentially vanishing sub-optimal local minima in multilayer neural networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.05777","kind":"arxiv","version":5},"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":"sha256:83a92a2e80f42e46119de5881f06130eaa62e33335fa6d8de6efe8aa8e777fa0","target":"record","created_at":"2026-05-18T00:31:51Z","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":"90ab65f48e5bcad776fb55a0304615fc11a7195e67750f5cbdb9737a57aec06d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-02-19T18:12:51Z","title_canon_sha256":"ee27cd6e5e493be8a90393e4de1d3c374ca3f12ac6c6b51a483a602d5a5850c3"},"schema_version":"1.0","source":{"id":"1702.05777","kind":"arxiv","version":5}},"canonical_sha256":"e4af75f9004515e83211387fc659d8660229f919e04df3ac9cbaa733c28157a9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e4af75f9004515e83211387fc659d8660229f919e04df3ac9cbaa733c28157a9","first_computed_at":"2026-05-18T00:31:51.464296Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:31:51.464296Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"o+LnG544u+5BWV+Xn/RBpWElTTyQI22dUfRndXTPJp2zGGyETtka8nEjXCPdnQ+tgqEYa7KVsXJoMcOF9cK3Ag==","signature_status":"signed_v1","signed_at":"2026-05-18T00:31:51.467781Z","signed_message":"canonical_sha256_bytes"},"source_id":"1702.05777","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:83a92a2e80f42e46119de5881f06130eaa62e33335fa6d8de6efe8aa8e777fa0","sha256:93f737133f0d5023616fdf039817cd07dcefa1143e4ea316cafde5416f65fec2"],"state_sha256":"6ae206b9c80c716f9abce998866dcd0811384bb3228dc2e8e5ab9f316c2a7f96"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W0I71edr37It1KunLeShVcQcrK10Zb8g4gkX3q+rmKA3YpI6pocfWddoI35hbGf+TIrStVS5yJjAxTDC/Gm6Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T22:12:09.777172Z","bundle_sha256":"8ab59aa27749815ff0aefe802acf4e2cc3f8cc16304259a712c733414117911c"}}