{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:LRHCJJ4BEAAS7RDJDWRDB4R2E3","short_pith_number":"pith:LRHCJJ4B","canonical_record":{"source":{"id":"1907.06594","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-04T08:50:04Z","cross_cats_sorted":["cs.IT","math.IT","stat.ML"],"title_canon_sha256":"27b9c22478318ab76b91968420afe651f549c06952fb1f595b3fa25be3f0640d","abstract_canon_sha256":"432f3cf23a2df5009ea2e83fcaff0958aa1006d356973f872fcab3626a653816"},"schema_version":"1.0"},"canonical_sha256":"5c4e24a78120012fc4691da230f23a26ceb69d7a5b48c5a034bb10766acfe8c3","source":{"kind":"arxiv","id":"1907.06594","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.06594","created_at":"2026-05-17T23:40:29Z"},{"alias_kind":"arxiv_version","alias_value":"1907.06594v2","created_at":"2026-05-17T23:40:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.06594","created_at":"2026-05-17T23:40:29Z"},{"alias_kind":"pith_short_12","alias_value":"LRHCJJ4BEAAS","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"LRHCJJ4BEAAS7RDJ","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"LRHCJJ4B","created_at":"2026-05-18T12:33:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:LRHCJJ4BEAAS7RDJDWRDB4R2E3","target":"record","payload":{"canonical_record":{"source":{"id":"1907.06594","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-04T08:50:04Z","cross_cats_sorted":["cs.IT","math.IT","stat.ML"],"title_canon_sha256":"27b9c22478318ab76b91968420afe651f549c06952fb1f595b3fa25be3f0640d","abstract_canon_sha256":"432f3cf23a2df5009ea2e83fcaff0958aa1006d356973f872fcab3626a653816"},"schema_version":"1.0"},"canonical_sha256":"5c4e24a78120012fc4691da230f23a26ceb69d7a5b48c5a034bb10766acfe8c3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:40:29.504625Z","signature_b64":"sMA5tkULvQqf5H+pZii5tLvZLGe/48MclgbtjD9aTZijkz42biE+upYYIVd7F+RoA/zX9ODABoYqiMw/vNXZDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c4e24a78120012fc4691da230f23a26ceb69d7a5b48c5a034bb10766acfe8c3","last_reissued_at":"2026-05-17T23:40:29.504091Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:40:29.504091Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1907.06594","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:40:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XBj/ZLBy1O1mml7mNeacXOKpJpIa6NcSFEITPHZsn66Xe8JcRbyjTFBhVaMSvs3BNPiSCES1UJuX5374DWJ3Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T13:08:28.638605Z"},"content_sha256":"9e6d8c05c65d17b12aa16ab942c36bafad7068e7c68140d78f61ca33621e7016","schema_version":"1.0","event_id":"sha256:9e6d8c05c65d17b12aa16ab942c36bafad7068e7c68140d78f61ca33621e7016"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:LRHCJJ4BEAAS7RDJDWRDB4R2E3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning One-hidden-layer neural networks via Provable Gradient Descent with Random Initialization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Shuhao Xia, Yuanming Shi","submitted_at":"2019-07-04T08:50:04Z","abstract_excerpt":"Although deep learning has shown its powerful performance in many applications, the mathematical principles behind neural networks are still mysterious. In this paper, we consider the problem of learning a one-hidden-layer neural network with quadratic activations. We focus on the under-parameterized regime where the number of hidden units is smaller than the dimension of the inputs. We shall propose to solve the problem via a provable gradient-based method with random initialization. For the non-convex neural networks training problem we reveal that the gradient descent iterates are able to e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.06594","kind":"arxiv","version":2},"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":"2026-05-17T23:40:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uLXi84FunFo0sUeI8jXICIj/E5EvVPDiPE8TAtreSoWGjCZZElsV+y5MNxlhotP98ttOT0Y61EblZ0yCAZOlDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T13:08:28.639215Z"},"content_sha256":"cea0659680bb57d583c6ca1a6fa54640f7e3493b788fac8d9147b6fde18d1ba6","schema_version":"1.0","event_id":"sha256:cea0659680bb57d583c6ca1a6fa54640f7e3493b788fac8d9147b6fde18d1ba6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LRHCJJ4BEAAS7RDJDWRDB4R2E3/bundle.json","state_url":"https://pith.science/pith/LRHCJJ4BEAAS7RDJDWRDB4R2E3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LRHCJJ4BEAAS7RDJDWRDB4R2E3/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":"2026-06-06T13:08:28Z","links":{"resolver":"https://pith.science/pith/LRHCJJ4BEAAS7RDJDWRDB4R2E3","bundle":"https://pith.science/pith/LRHCJJ4BEAAS7RDJDWRDB4R2E3/bundle.json","state":"https://pith.science/pith/LRHCJJ4BEAAS7RDJDWRDB4R2E3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LRHCJJ4BEAAS7RDJDWRDB4R2E3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:LRHCJJ4BEAAS7RDJDWRDB4R2E3","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":"432f3cf23a2df5009ea2e83fcaff0958aa1006d356973f872fcab3626a653816","cross_cats_sorted":["cs.IT","math.IT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-04T08:50:04Z","title_canon_sha256":"27b9c22478318ab76b91968420afe651f549c06952fb1f595b3fa25be3f0640d"},"schema_version":"1.0","source":{"id":"1907.06594","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.06594","created_at":"2026-05-17T23:40:29Z"},{"alias_kind":"arxiv_version","alias_value":"1907.06594v2","created_at":"2026-05-17T23:40:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.06594","created_at":"2026-05-17T23:40:29Z"},{"alias_kind":"pith_short_12","alias_value":"LRHCJJ4BEAAS","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"LRHCJJ4BEAAS7RDJ","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"LRHCJJ4B","created_at":"2026-05-18T12:33:21Z"}],"graph_snapshots":[{"event_id":"sha256:cea0659680bb57d583c6ca1a6fa54640f7e3493b788fac8d9147b6fde18d1ba6","target":"graph","created_at":"2026-05-17T23:40:29Z","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":"Although deep learning has shown its powerful performance in many applications, the mathematical principles behind neural networks are still mysterious. In this paper, we consider the problem of learning a one-hidden-layer neural network with quadratic activations. We focus on the under-parameterized regime where the number of hidden units is smaller than the dimension of the inputs. We shall propose to solve the problem via a provable gradient-based method with random initialization. For the non-convex neural networks training problem we reveal that the gradient descent iterates are able to e","authors_text":"Shuhao Xia, Yuanming Shi","cross_cats":["cs.IT","math.IT","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-04T08:50:04Z","title":"Learning One-hidden-layer neural networks via Provable Gradient Descent with Random Initialization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.06594","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":"sha256:9e6d8c05c65d17b12aa16ab942c36bafad7068e7c68140d78f61ca33621e7016","target":"record","created_at":"2026-05-17T23:40:29Z","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":"432f3cf23a2df5009ea2e83fcaff0958aa1006d356973f872fcab3626a653816","cross_cats_sorted":["cs.IT","math.IT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-07-04T08:50:04Z","title_canon_sha256":"27b9c22478318ab76b91968420afe651f549c06952fb1f595b3fa25be3f0640d"},"schema_version":"1.0","source":{"id":"1907.06594","kind":"arxiv","version":2}},"canonical_sha256":"5c4e24a78120012fc4691da230f23a26ceb69d7a5b48c5a034bb10766acfe8c3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5c4e24a78120012fc4691da230f23a26ceb69d7a5b48c5a034bb10766acfe8c3","first_computed_at":"2026-05-17T23:40:29.504091Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:40:29.504091Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sMA5tkULvQqf5H+pZii5tLvZLGe/48MclgbtjD9aTZijkz42biE+upYYIVd7F+RoA/zX9ODABoYqiMw/vNXZDg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:40:29.504625Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.06594","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9e6d8c05c65d17b12aa16ab942c36bafad7068e7c68140d78f61ca33621e7016","sha256:cea0659680bb57d583c6ca1a6fa54640f7e3493b788fac8d9147b6fde18d1ba6"],"state_sha256":"90867b093ade4a2037819f2719a93046e92c4985ba6899473e0021527487b72a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LHTrAsK7jsEk8DfT+Ku85cs6DMP6jw2Cd8M9v44sbuzwhSuwQn64nTo2dwZ3CwE3kk17cJluvJY1SejzR2S/BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T13:08:28.642929Z","bundle_sha256":"d18a62c816e6702b67fc6367710b2721350f4843c5340717f98979959ea5eb64"}}