{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:QKKVI5KOKOXZ3KR2MFEMRW2CR4","short_pith_number":"pith:QKKVI5KO","canonical_record":{"source":{"id":"1804.06561","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-04-18T05:31:45Z","cross_cats_sorted":["cond-mat.stat-mech","cs.LG","math.ST","stat.TH"],"title_canon_sha256":"61a37ea0e2bb3a0c37948c82ad37fe231150b2f3f4a03549baa48e81affd5fbb","abstract_canon_sha256":"2d2d5bb02eae10e97f37ed99585fc296858f30f20f912aed61ba54c1aec55d24"},"schema_version":"1.0"},"canonical_sha256":"829554754e53af9daa3a6148c8db428f129da243fc49ae5c2cfe618b1fde0543","source":{"kind":"arxiv","id":"1804.06561","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.06561","created_at":"2026-07-05T04:29:21Z"},{"alias_kind":"arxiv_version","alias_value":"1804.06561v2","created_at":"2026-07-05T04:29:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.06561","created_at":"2026-07-05T04:29:21Z"},{"alias_kind":"pith_short_12","alias_value":"QKKVI5KOKOXZ","created_at":"2026-07-05T04:29:21Z"},{"alias_kind":"pith_short_16","alias_value":"QKKVI5KOKOXZ3KR2","created_at":"2026-07-05T04:29:21Z"},{"alias_kind":"pith_short_8","alias_value":"QKKVI5KO","created_at":"2026-07-05T04:29:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:QKKVI5KOKOXZ3KR2MFEMRW2CR4","target":"record","payload":{"canonical_record":{"source":{"id":"1804.06561","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-04-18T05:31:45Z","cross_cats_sorted":["cond-mat.stat-mech","cs.LG","math.ST","stat.TH"],"title_canon_sha256":"61a37ea0e2bb3a0c37948c82ad37fe231150b2f3f4a03549baa48e81affd5fbb","abstract_canon_sha256":"2d2d5bb02eae10e97f37ed99585fc296858f30f20f912aed61ba54c1aec55d24"},"schema_version":"1.0"},"canonical_sha256":"829554754e53af9daa3a6148c8db428f129da243fc49ae5c2cfe618b1fde0543","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:29:21.787154Z","signature_b64":"fmOd6XouxZxQ+doc0C0z6+7vCA5hD7PX9xDC9gyz3c4DIYxyjZCqia1/HkcraZ+nkwVJO/qe02xENhEHhut6Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"829554754e53af9daa3a6148c8db428f129da243fc49ae5c2cfe618b1fde0543","last_reissued_at":"2026-07-05T04:29:21.786678Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:29:21.786678Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1804.06561","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":"2026-07-05T04:29:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ErS0D07rp50zoCI8E9W5HNc/Bl1dBwurV6k3C+f8gqZzPKW1uKHsG6Um7p6TxnjZ17KeYl53njsH8EVgAtYNBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T12:24:18.659516Z"},"content_sha256":"60d36570668abfe146b843d536c056358b2d2b76e94a0b56a3362df0d9ffd928","schema_version":"1.0","event_id":"sha256:60d36570668abfe146b843d536c056358b2d2b76e94a0b56a3362df0d9ffd928"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:QKKVI5KOKOXZ3KR2MFEMRW2CR4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Mean Field View of the Landscape of Two-Layers Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.stat-mech","cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Andrea Montanari, Phan-Minh Nguyen, Song Mei","submitted_at":"2018-04-18T05:31:45Z","abstract_excerpt":"Multi-layer neural networks are among the most powerful models in machine learning, yet the fundamental reasons for this success defy mathematical understanding. Learning a neural network requires to optimize a non-convex high-dimensional objective (risk function), a problem which is usually attacked using stochastic gradient descent (SGD). Does SGD converge to a global optimum of the risk or only to a local optimum? In the first case, does this happen because local minima are absent, or because SGD somehow avoids them? In the second, why do local minima reached by SGD have good generalization"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.06561","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1804.06561/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T04:29:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NC14T3XtVjR1CO+4nnM3amxSBu9yO8yF5GckBWmyfV4epE3RH97Mt1RQp/o/oBllbiXDdZqbV5j9Xq9nCBmhAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T12:24:18.660063Z"},"content_sha256":"7a32a8627547d91fdaf68587fff329a99c97df48a54ae8efd4d8e1f2f86bb973","schema_version":"1.0","event_id":"sha256:7a32a8627547d91fdaf68587fff329a99c97df48a54ae8efd4d8e1f2f86bb973"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QKKVI5KOKOXZ3KR2MFEMRW2CR4/bundle.json","state_url":"https://pith.science/pith/QKKVI5KOKOXZ3KR2MFEMRW2CR4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QKKVI5KOKOXZ3KR2MFEMRW2CR4/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":"2026-08-15T12:24:18Z","links":{"resolver":"https://pith.science/pith/QKKVI5KOKOXZ3KR2MFEMRW2CR4","bundle":"https://pith.science/pith/QKKVI5KOKOXZ3KR2MFEMRW2CR4/bundle.json","state":"https://pith.science/pith/QKKVI5KOKOXZ3KR2MFEMRW2CR4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QKKVI5KOKOXZ3KR2MFEMRW2CR4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:QKKVI5KOKOXZ3KR2MFEMRW2CR4","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":"2d2d5bb02eae10e97f37ed99585fc296858f30f20f912aed61ba54c1aec55d24","cross_cats_sorted":["cond-mat.stat-mech","cs.LG","math.ST","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-04-18T05:31:45Z","title_canon_sha256":"61a37ea0e2bb3a0c37948c82ad37fe231150b2f3f4a03549baa48e81affd5fbb"},"schema_version":"1.0","source":{"id":"1804.06561","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.06561","created_at":"2026-07-05T04:29:21Z"},{"alias_kind":"arxiv_version","alias_value":"1804.06561v2","created_at":"2026-07-05T04:29:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.06561","created_at":"2026-07-05T04:29:21Z"},{"alias_kind":"pith_short_12","alias_value":"QKKVI5KOKOXZ","created_at":"2026-07-05T04:29:21Z"},{"alias_kind":"pith_short_16","alias_value":"QKKVI5KOKOXZ3KR2","created_at":"2026-07-05T04:29:21Z"},{"alias_kind":"pith_short_8","alias_value":"QKKVI5KO","created_at":"2026-07-05T04:29:21Z"}],"graph_snapshots":[{"event_id":"sha256:7a32a8627547d91fdaf68587fff329a99c97df48a54ae8efd4d8e1f2f86bb973","target":"graph","created_at":"2026-07-05T04:29:21Z","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/1804.06561/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-layer neural networks are among the most powerful models in machine learning, yet the fundamental reasons for this success defy mathematical understanding. Learning a neural network requires to optimize a non-convex high-dimensional objective (risk function), a problem which is usually attacked using stochastic gradient descent (SGD). Does SGD converge to a global optimum of the risk or only to a local optimum? In the first case, does this happen because local minima are absent, or because SGD somehow avoids them? In the second, why do local minima reached by SGD have good generalization","authors_text":"Andrea Montanari, Phan-Minh Nguyen, Song Mei","cross_cats":["cond-mat.stat-mech","cs.LG","math.ST","stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-04-18T05:31:45Z","title":"A Mean Field View of the Landscape of Two-Layers Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.06561","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":"sha256:60d36570668abfe146b843d536c056358b2d2b76e94a0b56a3362df0d9ffd928","target":"record","created_at":"2026-07-05T04:29:21Z","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":"2d2d5bb02eae10e97f37ed99585fc296858f30f20f912aed61ba54c1aec55d24","cross_cats_sorted":["cond-mat.stat-mech","cs.LG","math.ST","stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-04-18T05:31:45Z","title_canon_sha256":"61a37ea0e2bb3a0c37948c82ad37fe231150b2f3f4a03549baa48e81affd5fbb"},"schema_version":"1.0","source":{"id":"1804.06561","kind":"arxiv","version":2}},"canonical_sha256":"829554754e53af9daa3a6148c8db428f129da243fc49ae5c2cfe618b1fde0543","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"829554754e53af9daa3a6148c8db428f129da243fc49ae5c2cfe618b1fde0543","first_computed_at":"2026-07-05T04:29:21.786678Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:29:21.786678Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fmOd6XouxZxQ+doc0C0z6+7vCA5hD7PX9xDC9gyz3c4DIYxyjZCqia1/HkcraZ+nkwVJO/qe02xENhEHhut6Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:29:21.787154Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.06561","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:60d36570668abfe146b843d536c056358b2d2b76e94a0b56a3362df0d9ffd928","sha256:7a32a8627547d91fdaf68587fff329a99c97df48a54ae8efd4d8e1f2f86bb973"],"state_sha256":"30101d682f39673590ce37ccba8f8c0bf4a0aaca4987c3f6ec707b8a17ae548f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZeGeCP3ttUtQPt4VW0P8fkdANfNpZQZrCqfifCfHPIdp3zio3Ao7nCJybShne8KDG/gxgRMzocto8ObG+4iHDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T12:24:18.663697Z","bundle_sha256":"c41a69b0877fcef9dba63b51213e39155e069663934d0f87dc5c45ac05e49f0b"}}