{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:RZAHTOB6MNLHRD3JCCAYNHOS6R","short_pith_number":"pith:RZAHTOB6","canonical_record":{"source":{"id":"1610.09300","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-10-28T16:28:23Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"6a8fda59ce7c04708c9d74c7d960f312ff459e47e522f7e8e982f065bc97d397","abstract_canon_sha256":"5df81441537552632e77a0669f69909547048665d12fed07e339bd5421804dd8"},"schema_version":"1.0"},"canonical_sha256":"8e4079b83e6356788f691081869dd2f45b203c20de8164f72cc98e94f9bc7804","source":{"kind":"arxiv","id":"1610.09300","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1610.09300","created_at":"2026-05-18T01:00:58Z"},{"alias_kind":"arxiv_version","alias_value":"1610.09300v1","created_at":"2026-05-18T01:00:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.09300","created_at":"2026-05-18T01:00:58Z"},{"alias_kind":"pith_short_12","alias_value":"RZAHTOB6MNLH","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_16","alias_value":"RZAHTOB6MNLHRD3J","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_8","alias_value":"RZAHTOB6","created_at":"2026-05-18T12:30:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:RZAHTOB6MNLHRD3JCCAYNHOS6R","target":"record","payload":{"canonical_record":{"source":{"id":"1610.09300","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-10-28T16:28:23Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"6a8fda59ce7c04708c9d74c7d960f312ff459e47e522f7e8e982f065bc97d397","abstract_canon_sha256":"5df81441537552632e77a0669f69909547048665d12fed07e339bd5421804dd8"},"schema_version":"1.0"},"canonical_sha256":"8e4079b83e6356788f691081869dd2f45b203c20de8164f72cc98e94f9bc7804","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:00:58.525820Z","signature_b64":"8wI0fQQ+6KeD0xOx2J4Ic+cI2UpRbLrgVvPf0wKO7VkrytfbGC5ePIhr5vGfAQDTjQwGtcEaXW31YbHJa0wIAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e4079b83e6356788f691081869dd2f45b203c20de8164f72cc98e94f9bc7804","last_reissued_at":"2026-05-18T01:00:58.525173Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:00:58.525173Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1610.09300","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:00:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YNWRtgpFAnfcpPgC6wAWdWDfqS8JfAh1WmmW+/9VgrttvD2ndx1nyLrrJYO0AGiGiFy1TX010/h3IneG+HYiAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T22:05:14.303178Z"},"content_sha256":"692a2e805139c9bc416620ecdcdbc7f79a7092fbfd3620ccff5e04a757d04201","schema_version":"1.0","event_id":"sha256:692a2e805139c9bc416620ecdcdbc7f79a7092fbfd3620ccff5e04a757d04201"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:RZAHTOB6MNLHRD3JCCAYNHOS6R","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Globally Optimal Training of Generalized Polynomial Neural Networks with Nonlinear Spectral Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Antoine Gautier, Matthias Hein, Quynh Nguyen","submitted_at":"2016-10-28T16:28:23Z","abstract_excerpt":"The optimization problem behind neural networks is highly non-convex. Training with stochastic gradient descent and variants requires careful parameter tuning and provides no guarantee to achieve the global optimum. In contrast we show under quite weak assumptions on the data that a particular class of feedforward neural networks can be trained globally optimal with a linear convergence rate with our nonlinear spectral method. Up to our knowledge this is the first practically feasible method which achieves such a guarantee. While the method can in principle be applied to deep networks, we rest"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.09300","kind":"arxiv","version":1},"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":"2026-05-18T01:00:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XyjkvYAm0hG2UFKWF49lsvrjQHv9iX415tLKkd3nnAi8EFyaCcs+0z0xAzLP6fqRSYS9jf5oF70SxgtZ5AdABA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T22:05:14.303837Z"},"content_sha256":"d6b44fd6df9e5ac21794b3de03f433f07f2feb1d9e263b9348d8649514f7887c","schema_version":"1.0","event_id":"sha256:d6b44fd6df9e5ac21794b3de03f433f07f2feb1d9e263b9348d8649514f7887c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RZAHTOB6MNLHRD3JCCAYNHOS6R/bundle.json","state_url":"https://pith.science/pith/RZAHTOB6MNLHRD3JCCAYNHOS6R/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RZAHTOB6MNLHRD3JCCAYNHOS6R/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":"2026-06-05T22:05:14Z","links":{"resolver":"https://pith.science/pith/RZAHTOB6MNLHRD3JCCAYNHOS6R","bundle":"https://pith.science/pith/RZAHTOB6MNLHRD3JCCAYNHOS6R/bundle.json","state":"https://pith.science/pith/RZAHTOB6MNLHRD3JCCAYNHOS6R/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RZAHTOB6MNLHRD3JCCAYNHOS6R/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:RZAHTOB6MNLHRD3JCCAYNHOS6R","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":"5df81441537552632e77a0669f69909547048665d12fed07e339bd5421804dd8","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-10-28T16:28:23Z","title_canon_sha256":"6a8fda59ce7c04708c9d74c7d960f312ff459e47e522f7e8e982f065bc97d397"},"schema_version":"1.0","source":{"id":"1610.09300","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1610.09300","created_at":"2026-05-18T01:00:58Z"},{"alias_kind":"arxiv_version","alias_value":"1610.09300v1","created_at":"2026-05-18T01:00:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1610.09300","created_at":"2026-05-18T01:00:58Z"},{"alias_kind":"pith_short_12","alias_value":"RZAHTOB6MNLH","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_16","alias_value":"RZAHTOB6MNLHRD3J","created_at":"2026-05-18T12:30:41Z"},{"alias_kind":"pith_short_8","alias_value":"RZAHTOB6","created_at":"2026-05-18T12:30:41Z"}],"graph_snapshots":[{"event_id":"sha256:d6b44fd6df9e5ac21794b3de03f433f07f2feb1d9e263b9348d8649514f7887c","target":"graph","created_at":"2026-05-18T01:00:58Z","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":"The optimization problem behind neural networks is highly non-convex. Training with stochastic gradient descent and variants requires careful parameter tuning and provides no guarantee to achieve the global optimum. In contrast we show under quite weak assumptions on the data that a particular class of feedforward neural networks can be trained globally optimal with a linear convergence rate with our nonlinear spectral method. Up to our knowledge this is the first practically feasible method which achieves such a guarantee. While the method can in principle be applied to deep networks, we rest","authors_text":"Antoine Gautier, Matthias Hein, Quynh Nguyen","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-10-28T16:28:23Z","title":"Globally Optimal Training of Generalized Polynomial Neural Networks with Nonlinear Spectral Methods"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1610.09300","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":"sha256:692a2e805139c9bc416620ecdcdbc7f79a7092fbfd3620ccff5e04a757d04201","target":"record","created_at":"2026-05-18T01:00:58Z","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":"5df81441537552632e77a0669f69909547048665d12fed07e339bd5421804dd8","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-10-28T16:28:23Z","title_canon_sha256":"6a8fda59ce7c04708c9d74c7d960f312ff459e47e522f7e8e982f065bc97d397"},"schema_version":"1.0","source":{"id":"1610.09300","kind":"arxiv","version":1}},"canonical_sha256":"8e4079b83e6356788f691081869dd2f45b203c20de8164f72cc98e94f9bc7804","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8e4079b83e6356788f691081869dd2f45b203c20de8164f72cc98e94f9bc7804","first_computed_at":"2026-05-18T01:00:58.525173Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:00:58.525173Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8wI0fQQ+6KeD0xOx2J4Ic+cI2UpRbLrgVvPf0wKO7VkrytfbGC5ePIhr5vGfAQDTjQwGtcEaXW31YbHJa0wIAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:00:58.525820Z","signed_message":"canonical_sha256_bytes"},"source_id":"1610.09300","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:692a2e805139c9bc416620ecdcdbc7f79a7092fbfd3620ccff5e04a757d04201","sha256:d6b44fd6df9e5ac21794b3de03f433f07f2feb1d9e263b9348d8649514f7887c"],"state_sha256":"0bdd529eb108b4e26fd48a676646537211e8546de4d4074c36508b5cfaded972"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0lwRrUhQ6PZw2lQ8IvNtkPSMwngm5bBviCN84FLesnfJb44nBmGeXexew+SAaIxs3G40RkcBXSnxCGeUFboCCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T22:05:14.307385Z","bundle_sha256":"373a19e59e35a6871e45f889afab720daa541feaa1f13b315f7137a3af1e343b"}}