{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:IN44AKBHV6PHVO3UQS4JOO7DGT","short_pith_number":"pith:IN44AKBH","canonical_record":{"source":{"id":"1902.06015","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-02-16T00:01:01Z","cross_cats_sorted":["cond-mat.stat-mech","cs.LG","math.ST","stat.TH"],"title_canon_sha256":"5bcab1190c0b557c31a230b3d4cd15d3f864d2b345f13810de64c82da07c1f2c","abstract_canon_sha256":"dcc6aed78091313627b0025f3a6ef0e9621595785b699d6875ace309c83c7038"},"schema_version":"1.0"},"canonical_sha256":"4379c02827af9e7abb7484b8973be334cbd7a12b8327ef751bcd31d661949e55","source":{"kind":"arxiv","id":"1902.06015","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.06015","created_at":"2026-05-17T23:53:46Z"},{"alias_kind":"arxiv_version","alias_value":"1902.06015v1","created_at":"2026-05-17T23:53:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.06015","created_at":"2026-05-17T23:53:46Z"},{"alias_kind":"pith_short_12","alias_value":"IN44AKBHV6PH","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"IN44AKBHV6PHVO3U","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"IN44AKBH","created_at":"2026-05-18T12:33:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:IN44AKBHV6PHVO3UQS4JOO7DGT","target":"record","payload":{"canonical_record":{"source":{"id":"1902.06015","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-02-16T00:01:01Z","cross_cats_sorted":["cond-mat.stat-mech","cs.LG","math.ST","stat.TH"],"title_canon_sha256":"5bcab1190c0b557c31a230b3d4cd15d3f864d2b345f13810de64c82da07c1f2c","abstract_canon_sha256":"dcc6aed78091313627b0025f3a6ef0e9621595785b699d6875ace309c83c7038"},"schema_version":"1.0"},"canonical_sha256":"4379c02827af9e7abb7484b8973be334cbd7a12b8327ef751bcd31d661949e55","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:53:46.885631Z","signature_b64":"WJo95EKl4JTscM4lE7hcVLevDBTtQlBh269aQu51B8D648AOdgR/yVcj0OIeNOdqXNRrM0hO07kM4wc0mC6VBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4379c02827af9e7abb7484b8973be334cbd7a12b8327ef751bcd31d661949e55","last_reissued_at":"2026-05-17T23:53:46.884947Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:53:46.884947Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1902.06015","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":"2026-05-17T23:53:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JeYclOPgZDR9GJzDQ3iO2h06AAUJRt5lUtqsFIdupRGpNZmYabFIaMy6+4p1ztaFrY1nM0511NfXIm+0fCRKAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T04:08:10.923856Z"},"content_sha256":"a52919850087b53b2881852ae9a326cfd12581caf9b688986d96c863c86bac24","schema_version":"1.0","event_id":"sha256:a52919850087b53b2881852ae9a326cfd12581caf9b688986d96c863c86bac24"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:IN44AKBHV6PHVO3UQS4JOO7DGT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mean-field theory of two-layers neural networks: dimension-free bounds and kernel limit","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, Song Mei, Theodor Misiakiewicz","submitted_at":"2019-02-16T00:01:01Z","abstract_excerpt":"We consider learning two layer neural networks using stochastic gradient descent. The mean-field description of this learning dynamics approximates the evolution of the network weights by an evolution in the space of probability distributions in $R^D$ (where $D$ is the number of parameters associated to each neuron). This evolution can be defined through a partial differential equation or, equivalently, as the gradient flow in the Wasserstein space of probability distributions. Earlier work shows that (under some regularity assumptions), the mean field description is accurate as soon as the nu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.06015","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":"2026-05-17T23:53:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JcfhVRtKTHSxYZsyPYfk4BxznBP2AvtOAjGbe2pzk8GcKhmzkvBaBFGyO1SKEAgrbLUQk52Nu6+36DuC9pRqCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T04:08:10.924205Z"},"content_sha256":"13f87371463d4d4dfd7bcd19d3fbeeb784ac53fd80de039bdb571b96d87af3f8","schema_version":"1.0","event_id":"sha256:13f87371463d4d4dfd7bcd19d3fbeeb784ac53fd80de039bdb571b96d87af3f8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IN44AKBHV6PHVO3UQS4JOO7DGT/bundle.json","state_url":"https://pith.science/pith/IN44AKBHV6PHVO3UQS4JOO7DGT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IN44AKBHV6PHVO3UQS4JOO7DGT/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":"2026-06-02T04:08:10Z","links":{"resolver":"https://pith.science/pith/IN44AKBHV6PHVO3UQS4JOO7DGT","bundle":"https://pith.science/pith/IN44AKBHV6PHVO3UQS4JOO7DGT/bundle.json","state":"https://pith.science/pith/IN44AKBHV6PHVO3UQS4JOO7DGT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IN44AKBHV6PHVO3UQS4JOO7DGT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:IN44AKBHV6PHVO3UQS4JOO7DGT","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":"dcc6aed78091313627b0025f3a6ef0e9621595785b699d6875ace309c83c7038","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":"2019-02-16T00:01:01Z","title_canon_sha256":"5bcab1190c0b557c31a230b3d4cd15d3f864d2b345f13810de64c82da07c1f2c"},"schema_version":"1.0","source":{"id":"1902.06015","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.06015","created_at":"2026-05-17T23:53:46Z"},{"alias_kind":"arxiv_version","alias_value":"1902.06015v1","created_at":"2026-05-17T23:53:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.06015","created_at":"2026-05-17T23:53:46Z"},{"alias_kind":"pith_short_12","alias_value":"IN44AKBHV6PH","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"IN44AKBHV6PHVO3U","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"IN44AKBH","created_at":"2026-05-18T12:33:18Z"}],"graph_snapshots":[{"event_id":"sha256:13f87371463d4d4dfd7bcd19d3fbeeb784ac53fd80de039bdb571b96d87af3f8","target":"graph","created_at":"2026-05-17T23:53:46Z","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":"We consider learning two layer neural networks using stochastic gradient descent. The mean-field description of this learning dynamics approximates the evolution of the network weights by an evolution in the space of probability distributions in $R^D$ (where $D$ is the number of parameters associated to each neuron). This evolution can be defined through a partial differential equation or, equivalently, as the gradient flow in the Wasserstein space of probability distributions. Earlier work shows that (under some regularity assumptions), the mean field description is accurate as soon as the nu","authors_text":"Andrea Montanari, Song Mei, Theodor Misiakiewicz","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":"2019-02-16T00:01:01Z","title":"Mean-field theory of two-layers neural networks: dimension-free bounds and kernel limit"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.06015","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:a52919850087b53b2881852ae9a326cfd12581caf9b688986d96c863c86bac24","target":"record","created_at":"2026-05-17T23:53:46Z","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":"dcc6aed78091313627b0025f3a6ef0e9621595785b699d6875ace309c83c7038","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":"2019-02-16T00:01:01Z","title_canon_sha256":"5bcab1190c0b557c31a230b3d4cd15d3f864d2b345f13810de64c82da07c1f2c"},"schema_version":"1.0","source":{"id":"1902.06015","kind":"arxiv","version":1}},"canonical_sha256":"4379c02827af9e7abb7484b8973be334cbd7a12b8327ef751bcd31d661949e55","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4379c02827af9e7abb7484b8973be334cbd7a12b8327ef751bcd31d661949e55","first_computed_at":"2026-05-17T23:53:46.884947Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:53:46.884947Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WJo95EKl4JTscM4lE7hcVLevDBTtQlBh269aQu51B8D648AOdgR/yVcj0OIeNOdqXNRrM0hO07kM4wc0mC6VBg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:53:46.885631Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.06015","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a52919850087b53b2881852ae9a326cfd12581caf9b688986d96c863c86bac24","sha256:13f87371463d4d4dfd7bcd19d3fbeeb784ac53fd80de039bdb571b96d87af3f8"],"state_sha256":"96287868378ac24e32eb3d91bc3d8fee01e725038082d069311e202c43efc35c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5J3/R+a2h1TFamTmXLcj5w9YiczFIxjnONNKjMsTzQNvYzGrTN3rl7dGQ2IS0ZdRQ3i9ykKxgYBa2FFLxLtRDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T04:08:10.926086Z","bundle_sha256":"e24c22fdfae61784831b277c60d7f926e7658cdccd446cfb4e0284529016c4eb"}}