{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:TU52P7R42NZTF3JY6CSVAZGBCU","short_pith_number":"pith:TU52P7R4","canonical_record":{"source":{"id":"1805.09545","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-05-24T08:28:01Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"d4084a0d4c4a02bb6765cae84fa81868ce507fab80998da80b6c5c7be53f9d32","abstract_canon_sha256":"223463b3bffb175fa4a796cde52157138f2b8785fdbbc597092a6b5f37166f20"},"schema_version":"1.0"},"canonical_sha256":"9d3ba7fe3cd37332ed38f0a55064c1151eb306804bcf7ef4c948dda9b224f406","source":{"kind":"arxiv","id":"1805.09545","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.09545","created_at":"2026-05-18T00:02:09Z"},{"alias_kind":"arxiv_version","alias_value":"1805.09545v2","created_at":"2026-05-18T00:02:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.09545","created_at":"2026-05-18T00:02:09Z"},{"alias_kind":"pith_short_12","alias_value":"TU52P7R42NZT","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"TU52P7R42NZTF3JY","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"TU52P7R4","created_at":"2026-05-18T12:32:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:TU52P7R42NZTF3JY6CSVAZGBCU","target":"record","payload":{"canonical_record":{"source":{"id":"1805.09545","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-05-24T08:28:01Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"d4084a0d4c4a02bb6765cae84fa81868ce507fab80998da80b6c5c7be53f9d32","abstract_canon_sha256":"223463b3bffb175fa4a796cde52157138f2b8785fdbbc597092a6b5f37166f20"},"schema_version":"1.0"},"canonical_sha256":"9d3ba7fe3cd37332ed38f0a55064c1151eb306804bcf7ef4c948dda9b224f406","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:02:09.906807Z","signature_b64":"IyueQAVUz7OQ7WMkvNVES2fS3xcAKu7M0kIY86Pok/zEW3gvFcnWKlLB0ggWW7xetzlY+Pz6xnQZDRThXQn8Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d3ba7fe3cd37332ed38f0a55064c1151eb306804bcf7ef4c948dda9b224f406","last_reissued_at":"2026-05-18T00:02:09.906157Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:02:09.906157Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.09545","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":"2026-05-18T00:02:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x9WP692VsB6xD889muElwweociAAPQKcA4zbbYLzWaNZ6UPiWfq9G3/xZQSoIH2J4c7SqnCLQjIxDjnwLsLxDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T23:40:13.515246Z"},"content_sha256":"8cdf71dda0836e2b17e49da5d331edf9afe616316840f2e7a4d667eb24563a74","schema_version":"1.0","event_id":"sha256:8cdf71dda0836e2b17e49da5d331edf9afe616316840f2e7a4d667eb24563a74"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:TU52P7R42NZTF3JY6CSVAZGBCU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the Global Convergence of Gradient Descent for Over-parameterized Models using Optimal Transport","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"math.OC","authors_text":"Francis Bach (SIERRA), Lenaic Chizat (SIERRA)","submitted_at":"2018-05-24T08:28:01Z","abstract_excerpt":"Many tasks in machine learning and signal processing can be solved by minimizing a convex function of a measure. This includes sparse spikes deconvolution or training a neural network with a single hidden layer. For these problems, we study a simple minimization method: the unknown measure is discretized into a mixture of particles and a continuous-time gradient descent is performed on their weights and positions. This is an idealization of the usual way to train neural networks with a large hidden layer. We show that, when initialized correctly and in the many-particle limit, this gradient fl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.09545","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":"2026-05-18T00:02:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Hs88Q6dWLc6Wi3ZEBeKV0PC/a3W/7N1l5VsOwvpxlj0JfyJZO59LWf6JNqv5LR/bOQIaO2z3NJlYL+Pv11hRDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T23:40:13.515620Z"},"content_sha256":"016c63278129395e6efae73c5a492b480d11370d78ed38abea0933b881522a16","schema_version":"1.0","event_id":"sha256:016c63278129395e6efae73c5a492b480d11370d78ed38abea0933b881522a16"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TU52P7R42NZTF3JY6CSVAZGBCU/bundle.json","state_url":"https://pith.science/pith/TU52P7R42NZTF3JY6CSVAZGBCU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TU52P7R42NZTF3JY6CSVAZGBCU/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":"2026-05-21T23:40:13Z","links":{"resolver":"https://pith.science/pith/TU52P7R42NZTF3JY6CSVAZGBCU","bundle":"https://pith.science/pith/TU52P7R42NZTF3JY6CSVAZGBCU/bundle.json","state":"https://pith.science/pith/TU52P7R42NZTF3JY6CSVAZGBCU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TU52P7R42NZTF3JY6CSVAZGBCU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:TU52P7R42NZTF3JY6CSVAZGBCU","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":"223463b3bffb175fa4a796cde52157138f2b8785fdbbc597092a6b5f37166f20","cross_cats_sorted":["cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-05-24T08:28:01Z","title_canon_sha256":"d4084a0d4c4a02bb6765cae84fa81868ce507fab80998da80b6c5c7be53f9d32"},"schema_version":"1.0","source":{"id":"1805.09545","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.09545","created_at":"2026-05-18T00:02:09Z"},{"alias_kind":"arxiv_version","alias_value":"1805.09545v2","created_at":"2026-05-18T00:02:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.09545","created_at":"2026-05-18T00:02:09Z"},{"alias_kind":"pith_short_12","alias_value":"TU52P7R42NZT","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_16","alias_value":"TU52P7R42NZTF3JY","created_at":"2026-05-18T12:32:56Z"},{"alias_kind":"pith_short_8","alias_value":"TU52P7R4","created_at":"2026-05-18T12:32:56Z"}],"graph_snapshots":[{"event_id":"sha256:016c63278129395e6efae73c5a492b480d11370d78ed38abea0933b881522a16","target":"graph","created_at":"2026-05-18T00:02:09Z","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":"Many tasks in machine learning and signal processing can be solved by minimizing a convex function of a measure. This includes sparse spikes deconvolution or training a neural network with a single hidden layer. For these problems, we study a simple minimization method: the unknown measure is discretized into a mixture of particles and a continuous-time gradient descent is performed on their weights and positions. This is an idealization of the usual way to train neural networks with a large hidden layer. We show that, when initialized correctly and in the many-particle limit, this gradient fl","authors_text":"Francis Bach (SIERRA), Lenaic Chizat (SIERRA)","cross_cats":["cs.NE","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-05-24T08:28:01Z","title":"On the Global Convergence of Gradient Descent for Over-parameterized Models using Optimal Transport"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.09545","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":"sha256:8cdf71dda0836e2b17e49da5d331edf9afe616316840f2e7a4d667eb24563a74","target":"record","created_at":"2026-05-18T00:02:09Z","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":"223463b3bffb175fa4a796cde52157138f2b8785fdbbc597092a6b5f37166f20","cross_cats_sorted":["cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2018-05-24T08:28:01Z","title_canon_sha256":"d4084a0d4c4a02bb6765cae84fa81868ce507fab80998da80b6c5c7be53f9d32"},"schema_version":"1.0","source":{"id":"1805.09545","kind":"arxiv","version":2}},"canonical_sha256":"9d3ba7fe3cd37332ed38f0a55064c1151eb306804bcf7ef4c948dda9b224f406","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9d3ba7fe3cd37332ed38f0a55064c1151eb306804bcf7ef4c948dda9b224f406","first_computed_at":"2026-05-18T00:02:09.906157Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:02:09.906157Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IyueQAVUz7OQ7WMkvNVES2fS3xcAKu7M0kIY86Pok/zEW3gvFcnWKlLB0ggWW7xetzlY+Pz6xnQZDRThXQn8Dg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:02:09.906807Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.09545","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8cdf71dda0836e2b17e49da5d331edf9afe616316840f2e7a4d667eb24563a74","sha256:016c63278129395e6efae73c5a492b480d11370d78ed38abea0933b881522a16"],"state_sha256":"e1025efad044586ceec256148e33cb1546fa513ce5ac1bfff5328f7a38809389"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tAw1esekvwS3rmMZG0/BK4acI4IRvbMDz0IJ50zlOdLNUuxyLbhT3RsA7yCNMBrxU1KdYvzppvPu/fnmOHxPDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T23:40:13.517819Z","bundle_sha256":"cdd1df67da8c6d2cdc9bb54207ff000d197f14f8cae414b4e2d97bcfdd9f56fd"}}