{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:CKEBGIFR2AZQZFFRGM3247Y5BJ","short_pith_number":"pith:CKEBGIFR","canonical_record":{"source":{"id":"1811.03962","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-09T15:16:13Z","cross_cats_sorted":["cs.DS","cs.NE","math.OC","stat.ML"],"title_canon_sha256":"391002ecee5aac98737970e823a8165d44c3d535ef6a7be3c3ff412a44681a1e","abstract_canon_sha256":"2e3e26894853044740577b0dac69088bfdcb1bcaca753833d66233dca7f015e9"},"schema_version":"1.0"},"canonical_sha256":"12881320b1d0330c94b13337ae7f1d0a6304d7d793791d988483c2e03de2aca0","source":{"kind":"arxiv","id":"1811.03962","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.03962","created_at":"2026-05-17T23:43:17Z"},{"alias_kind":"arxiv_version","alias_value":"1811.03962v5","created_at":"2026-05-17T23:43:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.03962","created_at":"2026-05-17T23:43:17Z"},{"alias_kind":"pith_short_12","alias_value":"CKEBGIFR2AZQ","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_16","alias_value":"CKEBGIFR2AZQZFFR","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_8","alias_value":"CKEBGIFR","created_at":"2026-05-18T12:32:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:CKEBGIFR2AZQZFFRGM3247Y5BJ","target":"record","payload":{"canonical_record":{"source":{"id":"1811.03962","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-09T15:16:13Z","cross_cats_sorted":["cs.DS","cs.NE","math.OC","stat.ML"],"title_canon_sha256":"391002ecee5aac98737970e823a8165d44c3d535ef6a7be3c3ff412a44681a1e","abstract_canon_sha256":"2e3e26894853044740577b0dac69088bfdcb1bcaca753833d66233dca7f015e9"},"schema_version":"1.0"},"canonical_sha256":"12881320b1d0330c94b13337ae7f1d0a6304d7d793791d988483c2e03de2aca0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:17.268578Z","signature_b64":"TDiGnhkKkIyeVGIG/MgFGEX6mQgPHz44bS69iYxIv4hYviW4WNQ4OwHTHCQC5k7ABA04ZvaDjhaU2DP2U1vnDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"12881320b1d0330c94b13337ae7f1d0a6304d7d793791d988483c2e03de2aca0","last_reissued_at":"2026-05-17T23:43:17.267722Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:17.267722Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.03962","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":"2026-05-17T23:43:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JQre8l5iB/9M0pbiJQdRH8/QnXqBqab1GzDxIyQFmcvxJ5PspLauzs5vL42wD/2aHAFspCqaJsIoekku4A/eBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T12:39:53.973253Z"},"content_sha256":"d135d6ac36d8e7ca169f9d24dd857e549248473c9bb400a43d474cd877661f60","schema_version":"1.0","event_id":"sha256:d135d6ac36d8e7ca169f9d24dd857e549248473c9bb400a43d474cd877661f60"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:CKEBGIFR2AZQZFFRGM3247Y5BJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Convergence Theory for Deep Learning via Over-Parameterization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","cs.NE","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Yuanzhi Li, Zeyuan Allen-Zhu, Zhao Song","submitted_at":"2018-11-09T15:16:13Z","abstract_excerpt":"Deep neural networks (DNNs) have demonstrated dominating performance in many fields; since AlexNet, networks used in practice are going wider and deeper. On the theoretical side, a long line of works has been focusing on training neural networks with one hidden layer. The theory of multi-layer networks remains largely unsettled.\n  In this work, we prove why stochastic gradient descent (SGD) can find $\\textit{global minima}$ on the training objective of DNNs in $\\textit{polynomial time}$. We only make two assumptions: the inputs are non-degenerate and the network is over-parameterized. The latt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.03962","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":"2026-05-17T23:43:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CPULGeV2Gpv2U+zfYuckDRfKh2FWKJh/WWamSdtKAqbxzcwTRqWZtPxzcg+cdzzMw8X5hHSzYWVcbMyRSoJJCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T12:39:53.973625Z"},"content_sha256":"0a5a6967f91716b263be782258e3a18cba9d7c6fe07ae4d6b000e072d44b62f5","schema_version":"1.0","event_id":"sha256:0a5a6967f91716b263be782258e3a18cba9d7c6fe07ae4d6b000e072d44b62f5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CKEBGIFR2AZQZFFRGM3247Y5BJ/bundle.json","state_url":"https://pith.science/pith/CKEBGIFR2AZQZFFRGM3247Y5BJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CKEBGIFR2AZQZFFRGM3247Y5BJ/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":"2026-05-28T12:39:53Z","links":{"resolver":"https://pith.science/pith/CKEBGIFR2AZQZFFRGM3247Y5BJ","bundle":"https://pith.science/pith/CKEBGIFR2AZQZFFRGM3247Y5BJ/bundle.json","state":"https://pith.science/pith/CKEBGIFR2AZQZFFRGM3247Y5BJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CKEBGIFR2AZQZFFRGM3247Y5BJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:CKEBGIFR2AZQZFFRGM3247Y5BJ","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":"2e3e26894853044740577b0dac69088bfdcb1bcaca753833d66233dca7f015e9","cross_cats_sorted":["cs.DS","cs.NE","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-09T15:16:13Z","title_canon_sha256":"391002ecee5aac98737970e823a8165d44c3d535ef6a7be3c3ff412a44681a1e"},"schema_version":"1.0","source":{"id":"1811.03962","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.03962","created_at":"2026-05-17T23:43:17Z"},{"alias_kind":"arxiv_version","alias_value":"1811.03962v5","created_at":"2026-05-17T23:43:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.03962","created_at":"2026-05-17T23:43:17Z"},{"alias_kind":"pith_short_12","alias_value":"CKEBGIFR2AZQ","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_16","alias_value":"CKEBGIFR2AZQZFFR","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_8","alias_value":"CKEBGIFR","created_at":"2026-05-18T12:32:16Z"}],"graph_snapshots":[{"event_id":"sha256:0a5a6967f91716b263be782258e3a18cba9d7c6fe07ae4d6b000e072d44b62f5","target":"graph","created_at":"2026-05-17T23:43:17Z","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"},"paper":{"abstract_excerpt":"Deep neural networks (DNNs) have demonstrated dominating performance in many fields; since AlexNet, networks used in practice are going wider and deeper. On the theoretical side, a long line of works has been focusing on training neural networks with one hidden layer. The theory of multi-layer networks remains largely unsettled.\n  In this work, we prove why stochastic gradient descent (SGD) can find $\\textit{global minima}$ on the training objective of DNNs in $\\textit{polynomial time}$. We only make two assumptions: the inputs are non-degenerate and the network is over-parameterized. The latt","authors_text":"Yuanzhi Li, Zeyuan Allen-Zhu, Zhao Song","cross_cats":["cs.DS","cs.NE","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-09T15:16:13Z","title":"A Convergence Theory for Deep Learning via Over-Parameterization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.03962","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:d135d6ac36d8e7ca169f9d24dd857e549248473c9bb400a43d474cd877661f60","target":"record","created_at":"2026-05-17T23:43:17Z","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":"2e3e26894853044740577b0dac69088bfdcb1bcaca753833d66233dca7f015e9","cross_cats_sorted":["cs.DS","cs.NE","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-09T15:16:13Z","title_canon_sha256":"391002ecee5aac98737970e823a8165d44c3d535ef6a7be3c3ff412a44681a1e"},"schema_version":"1.0","source":{"id":"1811.03962","kind":"arxiv","version":5}},"canonical_sha256":"12881320b1d0330c94b13337ae7f1d0a6304d7d793791d988483c2e03de2aca0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"12881320b1d0330c94b13337ae7f1d0a6304d7d793791d988483c2e03de2aca0","first_computed_at":"2026-05-17T23:43:17.267722Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:43:17.267722Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TDiGnhkKkIyeVGIG/MgFGEX6mQgPHz44bS69iYxIv4hYviW4WNQ4OwHTHCQC5k7ABA04ZvaDjhaU2DP2U1vnDw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:43:17.268578Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.03962","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d135d6ac36d8e7ca169f9d24dd857e549248473c9bb400a43d474cd877661f60","sha256:0a5a6967f91716b263be782258e3a18cba9d7c6fe07ae4d6b000e072d44b62f5"],"state_sha256":"acc35c40abee5dddafd9ec519a6e3639d4e0f5ebdb9058bd6d42d69c067a6137"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Iq1f8385qwet6BkIBubPbD+7FOhN17Z/etbc71BGhPvasbm7O6Z55KrFAYSdhGAmF6cdQpRWMrz35YVv9UgLAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T12:39:53.975676Z","bundle_sha256":"18d9f6ee3d0eb641a351ba755f22e3c3705b31970f2ab1e181f4cd6e829274aa"}}