{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:5QFEPWSVQECMX54D56QRSNAE5Q","short_pith_number":"pith:5QFEPWSV","canonical_record":{"source":{"id":"1906.03830","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-10T08:01:27Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"61796a1f62e2bb4d816212278cba7109cdc04cf90b847739f9ef43d23b90fcde","abstract_canon_sha256":"97c865992e638e6e6900c8fc3ba1884ac27927667df7527c921d787ec30e47f2"},"schema_version":"1.0"},"canonical_sha256":"ec0a47da558104cbf783efa1193404ec358ca29598d725252a6ffac4538a6a3b","source":{"kind":"arxiv","id":"1906.03830","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.03830","created_at":"2026-05-17T23:43:44Z"},{"alias_kind":"arxiv_version","alias_value":"1906.03830v1","created_at":"2026-05-17T23:43:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.03830","created_at":"2026-05-17T23:43:44Z"},{"alias_kind":"pith_short_12","alias_value":"5QFEPWSVQECM","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"5QFEPWSVQECMX54D","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"5QFEPWSV","created_at":"2026-05-18T12:33:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:5QFEPWSVQECMX54D56QRSNAE5Q","target":"record","payload":{"canonical_record":{"source":{"id":"1906.03830","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-10T08:01:27Z","cross_cats_sorted":["math.OC","stat.ML"],"title_canon_sha256":"61796a1f62e2bb4d816212278cba7109cdc04cf90b847739f9ef43d23b90fcde","abstract_canon_sha256":"97c865992e638e6e6900c8fc3ba1884ac27927667df7527c921d787ec30e47f2"},"schema_version":"1.0"},"canonical_sha256":"ec0a47da558104cbf783efa1193404ec358ca29598d725252a6ffac4538a6a3b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:44.811497Z","signature_b64":"nThMMLFYJPaQrkv1yjcmwFPIxJu7lzjn6JzqDZcvnjkdhVK7Elop7nfVkw0CGm9wBM3atYHH2ij5kd9VDc8fCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec0a47da558104cbf783efa1193404ec358ca29598d725252a6ffac4538a6a3b","last_reissued_at":"2026-05-17T23:43:44.810807Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:44.810807Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.03830","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":"2026-05-17T23:43:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q0dFxGQRa1ZR8Yxy6DQ+Qk1kRGDfK7CTby4wE/yzSI//ph05HBOoYdtzf3UA41at8qXWVlfsd+penp/5TOdcBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T22:44:36.367223Z"},"content_sha256":"73e9d94f634ef0b4fa881b99f750093de72bb0cfbdb72d18e46fd0f36bd47296","schema_version":"1.0","event_id":"sha256:73e9d94f634ef0b4fa881b99f750093de72bb0cfbdb72d18e46fd0f36bd47296"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:5QFEPWSVQECMX54D56QRSNAE5Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Stochastic Mirror Descent on Overparameterized Nonlinear Models: Convergence, Implicit Regularization, and Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Babak Hassibi, Navid Azizan, Sahin Lale","submitted_at":"2019-06-10T08:01:27Z","abstract_excerpt":"Most modern learning problems are highly overparameterized, meaning that there are many more parameters than the number of training data points, and as a result, the training loss may have infinitely many global minima (parameter vectors that perfectly interpolate the training data). Therefore, it is important to understand which interpolating solutions we converge to, how they depend on the initialization point and the learning algorithm, and whether they lead to different generalization performances. In this paper, we study these questions for the family of stochastic mirror descent (SMD) al"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.03830","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":"2026-05-17T23:43:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qyC0qjBZdZARj963wsPIoZflNhEpHplmj82rtHrYjrw2GrzawX2MS8actNgDPkYa8iseD/vD8aPNkmwYEXL/Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T22:44:36.367710Z"},"content_sha256":"940cb6fe13e3c2bdda827721f468fea1e6d586c76c9d2d616be81b87aef81fed","schema_version":"1.0","event_id":"sha256:940cb6fe13e3c2bdda827721f468fea1e6d586c76c9d2d616be81b87aef81fed"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5QFEPWSVQECMX54D56QRSNAE5Q/bundle.json","state_url":"https://pith.science/pith/5QFEPWSVQECMX54D56QRSNAE5Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5QFEPWSVQECMX54D56QRSNAE5Q/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":"2026-08-12T22:44:36Z","links":{"resolver":"https://pith.science/pith/5QFEPWSVQECMX54D56QRSNAE5Q","bundle":"https://pith.science/pith/5QFEPWSVQECMX54D56QRSNAE5Q/bundle.json","state":"https://pith.science/pith/5QFEPWSVQECMX54D56QRSNAE5Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5QFEPWSVQECMX54D56QRSNAE5Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:5QFEPWSVQECMX54D56QRSNAE5Q","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":"97c865992e638e6e6900c8fc3ba1884ac27927667df7527c921d787ec30e47f2","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-10T08:01:27Z","title_canon_sha256":"61796a1f62e2bb4d816212278cba7109cdc04cf90b847739f9ef43d23b90fcde"},"schema_version":"1.0","source":{"id":"1906.03830","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.03830","created_at":"2026-05-17T23:43:44Z"},{"alias_kind":"arxiv_version","alias_value":"1906.03830v1","created_at":"2026-05-17T23:43:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.03830","created_at":"2026-05-17T23:43:44Z"},{"alias_kind":"pith_short_12","alias_value":"5QFEPWSVQECM","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"5QFEPWSVQECMX54D","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"5QFEPWSV","created_at":"2026-05-18T12:33:10Z"}],"graph_snapshots":[{"event_id":"sha256:940cb6fe13e3c2bdda827721f468fea1e6d586c76c9d2d616be81b87aef81fed","target":"graph","created_at":"2026-05-17T23:43:44Z","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":"Most modern learning problems are highly overparameterized, meaning that there are many more parameters than the number of training data points, and as a result, the training loss may have infinitely many global minima (parameter vectors that perfectly interpolate the training data). Therefore, it is important to understand which interpolating solutions we converge to, how they depend on the initialization point and the learning algorithm, and whether they lead to different generalization performances. In this paper, we study these questions for the family of stochastic mirror descent (SMD) al","authors_text":"Babak Hassibi, Navid Azizan, Sahin Lale","cross_cats":["math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-10T08:01:27Z","title":"Stochastic Mirror Descent on Overparameterized Nonlinear Models: Convergence, Implicit Regularization, and Generalization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.03830","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":"sha256:73e9d94f634ef0b4fa881b99f750093de72bb0cfbdb72d18e46fd0f36bd47296","target":"record","created_at":"2026-05-17T23:43:44Z","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":"97c865992e638e6e6900c8fc3ba1884ac27927667df7527c921d787ec30e47f2","cross_cats_sorted":["math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-10T08:01:27Z","title_canon_sha256":"61796a1f62e2bb4d816212278cba7109cdc04cf90b847739f9ef43d23b90fcde"},"schema_version":"1.0","source":{"id":"1906.03830","kind":"arxiv","version":1}},"canonical_sha256":"ec0a47da558104cbf783efa1193404ec358ca29598d725252a6ffac4538a6a3b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ec0a47da558104cbf783efa1193404ec358ca29598d725252a6ffac4538a6a3b","first_computed_at":"2026-05-17T23:43:44.810807Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:43:44.810807Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nThMMLFYJPaQrkv1yjcmwFPIxJu7lzjn6JzqDZcvnjkdhVK7Elop7nfVkw0CGm9wBM3atYHH2ij5kd9VDc8fCw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:43:44.811497Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.03830","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:73e9d94f634ef0b4fa881b99f750093de72bb0cfbdb72d18e46fd0f36bd47296","sha256:940cb6fe13e3c2bdda827721f468fea1e6d586c76c9d2d616be81b87aef81fed"],"state_sha256":"59cc450b27e1074f8ee44977f74d7a325d1f73dd58da36ca78589ce0e6574927"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+LI30cXcjvqIECmMsqQZdT6xCWXbF0Ljkx8cbZZburzhj07AXdYnQKrdR2C/8vfAe3SUkEl8lgKumY5TeDNZCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T22:44:36.373466Z","bundle_sha256":"fc12c926749dffcfb3233f3e012236f63d0fd11684f976ea181e6c1e0b53976c"}}