{"as_of":"2026-08-16T23:49:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:0647318486c38da0732d3bceebc99b32e6e223425f8e0a95eb3533882916354e","coverage":[{"denominator":33,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":33,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-14T12:38:57.687348Z","state":"measured"},{"denominator":33,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":33,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-16T06:30:59.297886+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/1908.07023/citation-record","integrity":"/paper/1908.07023/integrity","json":"/paper/1908.07023/citation-record.json","paper":"/paper/1908.07023"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:38:58.208461Z","title":"A stochastic approximation met hod,","venue":null,"work_id":"fe222d03-1156-4846-a179-c0afe89c0a32","year":1951},"citing_paper":{"arxiv_id":"1908.07023","last_updated":"2019-08-19T18:56:40Z","snapshot_observed_at":"2026-08-16T16:26:24.233008Z","submitted_at":"2019-08-19T18:56:40Z","title":"Second-Order Guarantees of Stochastic Gradient Descent in Non-Convex Optimization","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-14T12:38:57.524632Z"},"links":{"citing_paper":"/paper/1908.07023"},"observation_digest":"sha256:9262952b67ef7af37b5d403254e009fe29c77a0c4c13e8c8fa3835452b8e6036","observation_id":"380e9864-8795-4755-a3c1-4e24f244d8c7","resolution":{"observed_at":"2026-08-14T12:38:58.214620Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:38:58.188612Z","title":null,"venue":null,"work_id":"2ee07648-fcc2-4659-9972-71e7abafb31c","year":1997},"citing_paper":{"arxiv_id":"1908.07023","last_updated":"2019-08-19T18:56:40Z","snapshot_observed_at":"2026-08-16T16:26:24.233008Z","submitted_at":"2019-08-19T18:56:40Z","title":"Second-Order Guarantees of Stochastic Gradient Descent in Non-Convex Optimization","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-14T12:38:57.530503Z"},"links":{"citing_paper":"/paper/1908.07023"},"observation_digest":"sha256:08c1556a8cbce506cb62db995b188a29094386c0dcd9dc79d5ce709245f9f000","observation_id":"0dfe696a-4d19-4903-ba6d-ecb74fa940bf","resolution":{"observed_at":"2026-08-14T12:38:58.194660Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:38:57.535536Z","title":"Adaptive networks,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"1908.07023","last_updated":"2019-08-19T18:56:40Z","snapshot_observed_at":"2026-08-16T16:26:24.233008Z","submitted_at":"2019-08-19T18:56:40Z","title":"Second-Order Guarantees of Stochastic Gradient Descent in Non-Convex Optimization","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-14T12:38:57.535536Z"},"links":{"citing_paper":"/paper/1908.07023"},"observation_digest":"sha256:e5941d9d429698e6c37b3f1c89af75979184405d77b57334832a6ba9dd552bbe","observation_id":"74bd3fe5-cfb0-4d75-be6e-20604c480807","resolution":{"observed_at":"2026-08-14T12:38:57.535536Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:38:57.540658Z","title":"Adaptation, learning, and optimization ov er networks,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"1908.07023","last_updated":"2019-08-19T18:56:40Z","snapshot_observed_at":"2026-08-16T16:26:24.233008Z","submitted_at":"2019-08-19T18:56:40Z","title":"Second-Order Guarantees of Stochastic Gradient Descent in Non-Convex Optimization","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-14T12:38:57.540658Z"},"links":{"citing_paper":"/paper/1908.07023"},"observation_digest":"sha256:e433988d2c1ef8f3307cbf0e90288f2af25ac88d88d228176f4d26666ff0ba11","observation_id":"687bb502-8689-42b8-af17-928afe84d457","resolution":{"observed_at":"2026-08-14T12:38:57.540658Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1705.10412","last_updated":"2017-11-05T16:35:27Z","snapshot_observed_at":"2026-08-14T20:57:25.812592Z","submitted_at":"2017-05-29T23:03:01Z","title":"Gradient Descent Can Take Exponential Time to Escape Saddle Points","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1705.10412","snapshot_observed_at":"2026-08-14T12:38:57.545530Z","title":"Gradient descent can take exponential time to escape saddl e points,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.07023","last_updated":"2019-08-19T18:56:40Z","snapshot_observed_at":"2026-08-16T16:26:24.233008Z","submitted_at":"2019-08-19T18:56:40Z","title":"Second-Order Guarantees of Stochastic Gradient Descent in Non-Convex Optimization","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-14T12:38:57.545530Z"},"links":{"cited_paper":"/paper/1705.10412","citing_paper":"/paper/1908.07023"},"observation_digest":"sha256:a3b2fd411c985bab664306ed93cb652a5e7b0258399cadc422a12b13258f292d","observation_id":"afaad788-92c5-4a26-940c-5baac79ad298","resolution":{"observed_at":"2026-08-14T12:38:57.545530Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:38:58.143361Z","title":"Escaping from saddle pointsonline stochastic gradient for tensor decompositio n,","venue":null,"work_id":"c61a9e39-3d6b-4a2a-b24d-8fd3bc422ce1","year":2015},"citing_paper":{"arxiv_id":"1908.07023","last_updated":"2019-08-19T18:56:40Z","snapshot_observed_at":"2026-08-16T16:26:24.233008Z","submitted_at":"2019-08-19T18:56:40Z","title":"Second-Order Guarantees of Stochastic Gradient Descent in Non-Convex Optimization","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-14T12:38:57.550997Z"},"links":{"citing_paper":"/paper/1908.07023"},"observation_digest":"sha256:262c9a5ddd708626d75c7b006c3c66d489590eaefc3e4ef615681de942c22966","observation_id":"9e903345-de89-4eed-8e72-ce78a1b34e4c","resolution":{"observed_at":"2026-08-14T12:38:58.148641Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1902.04811","last_updated":"2019-09-04T03:26:59Z","snapshot_observed_at":"2026-08-16T03:16:43.775672Z","submitted_at":"2019-02-13T09:44:02Z","title":"On Nonconvex Optimization for Machine Learning: Gradients, Stochasticity, and Saddle Points","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.04811","snapshot_observed_at":"2026-08-14T12:38:57.556595Z","title":"Stochas- tic gradient descent escapes saddle points efficiently,","venue":null,"work_id":null,"year":1902},"citing_paper":{"arxiv_id":"1908.07023","last_updated":"2019-08-19T18:56:40Z","snapshot_observed_at":"2026-08-16T16:26:24.233008Z","submitted_at":"2019-08-19T18:56:40Z","title":"Second-Order Guarantees of Stochastic Gradient Descent in Non-Convex Optimization","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-14T12:38:57.556595Z"},"links":{"cited_paper":"/paper/1902.04811","citing_paper":"/paper/1908.07023"},"observation_digest":"sha256:93f0a493c92fc8c0119f4528d60c519e07202269edc9087bdffb56a57d58107b","observation_id":"225efb58-aadc-4cae-98ad-130710dfabd3","resolution":{"observed_at":"2026-08-14T12:38:57.556595Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1907.01848","last_updated":"2019-07-03T11:06:11Z","snapshot_observed_at":"2026-08-15T23:56:31.655626Z","submitted_at":"2019-07-03T11:06:11Z","title":"Distributed Learning in Non-Convex Environments -- Part I: Agreement at a Linear Rate","version":1},"cited_work":{"arxiv_id":"1907.01848","doi":null,"metadata_source":"pith","pith_arxiv_id":"1907.01848","snapshot_observed_at":"2026-08-14T12:38:57.852701Z","title":"Distributed Learning in Non-Convex Environments -- Part I: Agreement at a Linear Rate","venue":"math.OC","work_id":"9cdc6cc1-e71d-4cce-bb07-dafa79d5fe1b","year":2019},"citing_paper":{"arxiv_id":"1908.07023","last_updated":"2019-08-19T18:56:40Z","snapshot_observed_at":"2026-08-16T16:26:24.233008Z","submitted_at":"2019-08-19T18:56:40Z","title":"Second-Order Guarantees of Stochastic Gradient Descent in Non-Convex Optimization","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-14T12:38:57.562112Z"},"links":{"cited_paper":"/paper/1907.01848","citing_paper":"/paper/1908.07023"},"observation_digest":"sha256:0a561668d408bdde30b225c671f6d5b08db743ff59ecf776849a8f6ae958bbeb","observation_id":"2a641101-e745-4204-8a10-d0e4a85eae9d","resolution":{"observed_at":"2026-08-14T12:38:57.858068Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1907.01849","last_updated":"2019-07-03T11:06:43Z","snapshot_observed_at":"2026-08-11T08:42:58.759366Z","submitted_at":"2019-07-03T11:06:43Z","title":"Distributed Learning in Non-Convex Environments -- Part II: Polynomial Escape from Saddle-Points","version":1},"cited_work":{"arxiv_id":"1907.01849","doi":null,"metadata_source":"pith","pith_arxiv_id":"1907.01849","snapshot_observed_at":"2026-08-14T12:38:57.831183Z","title":"Distributed Learning in Non-Convex Environments -- Part II: Polynomial Escape from Saddle-Points","venue":"cs.MA","work_id":"c2ce354b-abb5-4223-83a2-e20c3dad7eb6","year":2019},"citing_paper":{"arxiv_id":"1908.07023","last_updated":"2019-08-19T18:56:40Z","snapshot_observed_at":"2026-08-16T16:26:24.233008Z","submitted_at":"2019-08-19T18:56:40Z","title":"Second-Order Guarantees of Stochastic Gradient Descent in Non-Convex Optimization","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-14T12:38:57.567840Z"},"links":{"cited_paper":"/paper/1907.01849","citing_paper":"/paper/1908.07023"},"observation_digest":"sha256:9007d561c44de911f9c578b6a41b8a7fc541d5252d93176aa20f83008c23d630","observation_id":"0685eacb-e7e5-4049-baaa-dd1c8d2a990d","resolution":{"observed_at":"2026-08-14T12:38:57.836541Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:38:58.126952Z","title":"Nesterov, Introductory Lectures on Convex Programming V olume I: Basic Course , Springer, 1998","venue":null,"work_id":"8c80d66f-c729-4658-b523-212c2fd72279","year":1998},"citing_paper":{"arxiv_id":"1908.07023","last_updated":"2019-08-19T18:56:40Z","snapshot_observed_at":"2026-08-16T16:26:24.233008Z","submitted_at":"2019-08-19T18:56:40Z","title":"Second-Order Guarantees of Stochastic Gradient Descent in Non-Convex Optimization","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-14T12:38:57.573304Z"},"links":{"citing_paper":"/paper/1908.07023"},"observation_digest":"sha256:1f2e7dd11222641156caa5c1428587020e8e669cc57aaca098ab840eb8abc339","observation_id":"05a00bb6-f2c2-423e-8504-80f62e64e523","resolution":{"observed_at":"2026-08-14T12:38:58.132514Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:38:58.108272Z","title":"Gradient convergence in gradient methods with errors,","venue":null,"work_id":"a96edc8e-08e0-4abb-9fdb-fdebc3b086ca","year":2000},"citing_paper":{"arxiv_id":"1908.07023","last_updated":"2019-08-19T18:56:40Z","snapshot_observed_at":"2026-08-16T16:26:24.233008Z","submitted_at":"2019-08-19T18:56:40Z","title":"Second-Order Guarantees of Stochastic Gradient Descent in Non-Convex Optimization","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-14T12:38:57.578282Z"},"links":{"citing_paper":"/paper/1908.07023"},"observation_digest":"sha256:9178626518ef7c40bc25a99db341304b957d4db5c7157792e8efc7020ca41dd6","observation_id":"daaa2bd9-9690-487a-a62e-5b86e9207e98","resolution":{"observed_at":"2026-08-14T12:38:58.113798Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:38:57.583333Z","title":"Stochastic variance reduction for nonconvex optimization,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.07023","last_updated":"2019-08-19T18:56:40Z","snapshot_observed_at":"2026-08-16T16:26:24.233008Z","submitted_at":"2019-08-19T18:56:40Z","title":"Second-Order Guarantees of Stochastic Gradient Descent in Non-Convex Optimization","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-14T12:38:57.583333Z"},"links":{"citing_paper":"/paper/1908.07023"},"observation_digest":"sha256:3460ae96ba613c9e1666d1f84a83f57574eccfc420545db27e1f31edc13965b1","observation_id":"8259aab6-0a18-4ea9-998e-5e52ead4fd43","resolution":{"observed_at":"2026-08-14T12:38:57.583333Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1709.03384","last_updated":"2020-05-30T14:57:50Z","snapshot_observed_at":"2026-08-15T21:50:39.931164Z","submitted_at":"2017-09-11T14:05:55Z","title":"Ghost Penalties in Nonconvex Constrained Optimization: Diminishing Stepsizes and Iteration Complexity","version":3},"cited_work":{"arxiv_id":"1709.03384","doi":null,"metadata_source":"pith","pith_arxiv_id":"1709.03384","snapshot_observed_at":"2026-08-14T12:38:57.806557Z","title":"Ghost Penalties in Nonconvex Constrained Optimization: Diminishing Stepsizes and Iteration Complexity","venue":"math.OC","work_id":"1256c069-7c6f-4da9-82a1-90d916176b15","year":2017},"citing_paper":{"arxiv_id":"1908.07023","last_updated":"2019-08-19T18:56:40Z","snapshot_observed_at":"2026-08-16T16:26:24.233008Z","submitted_at":"2019-08-19T18:56:40Z","title":"Second-Order Guarantees of Stochastic Gradient Descent in Non-Convex Optimization","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-14T12:38:57.588833Z"},"links":{"cited_paper":"/paper/1709.03384","citing_paper":"/paper/1908.07023"},"observation_digest":"sha256:941c0077ef51ee55533af2d976c7929d00991fc20dd0baba2143d3057b7ed348","observation_id":"3e940f5d-0b60-472a-ab28-e8631f7b3bae","resolution":{"observed_at":"2026-08-14T12:38:57.813743Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:38:57.593920Z","title":"Non-convex optimization for machin e learning,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.07023","last_updated":"2019-08-19T18:56:40Z","snapshot_observed_at":"2026-08-16T16:26:24.233008Z","submitted_at":"2019-08-19T18:56:40Z","title":"Second-Order Guarantees of Stochastic Gradient Descent in Non-Convex Optimization","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-14T12:38:57.593920Z"},"links":{"citing_paper":"/paper/1908.07023"},"observation_digest":"sha256:83ba0993a22a67793bbb5493ac770e309af8ea5bb36744e32b68d52c92fbe86c","observation_id":"eeb2449a-aecc-4e2f-86bf-9833363d9952","resolution":{"observed_at":"2026-08-14T12:38:57.593920Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:38:57.598727Z","title":"The Loss Surfaces of Multilayer Networks,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"1908.07023","last_updated":"2019-08-19T18:56:40Z","snapshot_observed_at":"2026-08-16T16:26:24.233008Z","submitted_at":"2019-08-19T18:56:40Z","title":"Second-Order Guarantees of Stochastic Gradient Descent in Non-Convex Optimization","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-14T12:38:57.598727Z"},"links":{"citing_paper":"/paper/1908.07023"},"observation_digest":"sha256:8c5668b3c4216daafe38729d5a544ffe48c76f5a1246a0ae3991a50c278039dd","observation_id":"b0048097-5447-4794-a77d-8c7e471b7fe8","resolution":{"observed_at":"2026-08-14T12:38:57.598727Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:38:58.057685Z","title":"Deep learning without poor local minima ,","venue":null,"work_id":"34f217ec-853d-4ecf-8d1f-7c796c7ce557","year":2016},"citing_paper":{"arxiv_id":"1908.07023","last_updated":"2019-08-19T18:56:40Z","snapshot_observed_at":"2026-08-16T16:26:24.233008Z","submitted_at":"2019-08-19T18:56:40Z","title":"Second-Order Guarantees of Stochastic Gradient Descent in Non-Convex Optimization","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-14T12:38:57.604523Z"},"links":{"citing_paper":"/paper/1908.07023"},"observation_digest":"sha256:fe56fead525a88afcb1553031712ec9d711c769cd1a7e03835f7d062fd8f517b","observation_id":"23dacbb6-aa1a-4499-9a96-0a80418f8519","resolution":{"observed_at":"2026-08-14T12:38:58.062989Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:38:58.042268Z","title":"Matrix completion has no spur ious local minimum,","venue":null,"work_id":"951ec04f-3b31-4e15-8680-1787d6f528e5","year":2016},"citing_paper":{"arxiv_id":"1908.07023","last_updated":"2019-08-19T18:56:40Z","snapshot_observed_at":"2026-08-16T16:26:24.233008Z","submitted_at":"2019-08-19T18:56:40Z","title":"Second-Order Guarantees of Stochastic Gradient Descent in Non-Convex Optimization","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-14T12:38:57.609797Z"},"links":{"citing_paper":"/paper/1908.07023"},"observation_digest":"sha256:c30027aa95cf67d97922d799866f663d8e7f0b2db4b9518c19d87c5f2eefa218","observation_id":"5b2f9233-fbce-4df5-a08b-54690ac1f820","resolution":{"observed_at":"2026-08-14T12:38:58.047060Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:38:58.025920Z","title":"Global o ptimality of local search for low rank matrix recovery,","venue":null,"work_id":"eb1db028-6efa-46cb-8962-57547b243e0d","year":2016},"citing_paper":{"arxiv_id":"1908.07023","last_updated":"2019-08-19T18:56:40Z","snapshot_observed_at":"2026-08-16T16:26:24.233008Z","submitted_at":"2019-08-19T18:56:40Z","title":"Second-Order Guarantees of Stochastic Gradient Descent in Non-Convex Optimization","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-14T12:38:57.614781Z"},"links":{"citing_paper":"/paper/1908.07023"},"observation_digest":"sha256:1808cb16f53a55ee8f9c27d8ba444e3edc540f02aee5a8a83d38b1c943b6662b","observation_id":"236c8887-6a5a-4d0b-b086-1ae3415bf549","resolution":{"observed_at":"2026-08-14T12:38:58.031637Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:38:57.619640Z","title":"Cubic regularization of n ewton method and its global performance,","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"1908.07023","last_updated":"2019-08-19T18:56:40Z","snapshot_observed_at":"2026-08-16T16:26:24.233008Z","submitted_at":"2019-08-19T18:56:40Z","title":"Second-Order Guarantees of Stochastic Gradient Descent in Non-Convex Optimization","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-14T12:38:57.619640Z"},"links":{"citing_paper":"/paper/1908.07023"},"observation_digest":"sha256:9b286406b4fa683d1383c3906b7dc86212da1272735ad7d1489b032828edcbba","observation_id":"f30c2a85-ba54-4d12-ae36-0b7158154b12","resolution":{"observed_at":"2026-08-14T12:38:57.619640Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:38:57.998945Z","title":"A trust regi on algorithm with a worst-case iteration complexity of o(ǫ− 3/ 2) for nonconvex optimization,","venue":null,"work_id":"13a3f6ba-0cf1-4a50-8930-fdff2393e809","year":2017},"citing_paper":{"arxiv_id":"1908.07023","last_updated":"2019-08-19T18:56:40Z","snapshot_observed_at":"2026-08-16T16:26:24.233008Z","submitted_at":"2019-08-19T18:56:40Z","title":"Second-Order Guarantees of Stochastic Gradient Descent in Non-Convex Optimization","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-14T12:38:57.624425Z"},"links":{"citing_paper":"/paper/1908.07023"},"observation_digest":"sha256:c1ca469489880a3d62146b3f998afdfab5a3030eabd1521b2a24da037357a9af","observation_id":"6b7f75cd-1e5c-447d-a186-95d85379a8d5","resolution":{"observed_at":"2026-08-14T12:38:58.004243Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:38:57.629224Z","title":"SPIDER: Near-opt imal non- convex optimization via stochastic path-integrated differential estimator,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.07023","last_updated":"2019-08-19T18:56:40Z","snapshot_observed_at":"2026-08-16T16:26:24.233008Z","submitted_at":"2019-08-19T18:56:40Z","title":"Second-Order Guarantees of Stochastic Gradient Descent in Non-Convex Optimization","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-14T12:38:57.629224Z"},"links":{"citing_paper":"/paper/1908.07023"},"observation_digest":"sha256:61c1f3b78c5b1d082e279798e3076a6492d155b09a903be5f5456772e6690797","observation_id":"3b5df49c-18d5-43a7-a38b-da615bef6100","resolution":{"observed_at":"2026-08-14T12:38:57.629224Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:38:57.633787Z","title":"NEON2: Finding local minima via first-order oracles,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.07023","last_updated":"2019-08-19T18:56:40Z","snapshot_observed_at":"2026-08-16T16:26:24.233008Z","submitted_at":"2019-08-19T18:56:40Z","title":"Second-Order Guarantees of Stochastic Gradient Descent in Non-Convex Optimization","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-14T12:38:57.633787Z"},"links":{"citing_paper":"/paper/1908.07023"},"observation_digest":"sha256:b26f93a964c0f062fcae8d118b12898de3d41d3e6930b55382e369ce2e58ae2b","observation_id":"2b68105e-a54c-4980-b146-0771999afc8d","resolution":{"observed_at":"2026-08-14T12:38:57.633787Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:38:57.638390Z","title":"Natasha 2: Faster non-convex optimizat ion than SGD,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.07023","last_updated":"2019-08-19T18:56:40Z","snapshot_observed_at":"2026-08-16T16:26:24.233008Z","submitted_at":"2019-08-19T18:56:40Z","title":"Second-Order Guarantees of Stochastic Gradient Descent in Non-Convex Optimization","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-14T12:38:57.638390Z"},"links":{"citing_paper":"/paper/1908.07023"},"observation_digest":"sha256:755255fbd0b845d2a177f457a06230cdfa452f34b360457998fa270d365164cb","observation_id":"44f9e851-c255-4e21-80d7-ec4cbdb56df5","resolution":{"observed_at":"2026-08-14T12:38:57.638390Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:38:57.643356Z","title":"Gra dient descent only converges to minimizers,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"1908.07023","last_updated":"2019-08-19T18:56:40Z","snapshot_observed_at":"2026-08-16T16:26:24.233008Z","submitted_at":"2019-08-19T18:56:40Z","title":"Second-Order Guarantees of Stochastic Gradient Descent in Non-Convex Optimization","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-14T12:38:57.643356Z"},"links":{"citing_paper":"/paper/1908.07023"},"observation_digest":"sha256:1b082850d6aece3ce3bba7b591aaa8240622d5c05ced109b38bdf0b013d6a2e4","observation_id":"763e2391-7027-4ca1-ad84-b062ca77d603","resolution":{"observed_at":"2026-08-14T12:38:57.643356Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1809.08694","last_updated":"2020-05-25T16:53:35Z","snapshot_observed_at":"2026-08-14T18:24:41.972871Z","submitted_at":"2018-09-23T23:06:39Z","title":"Second-order Guarantees of Distributed Gradient Algorithms","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1809.08694","snapshot_observed_at":"2026-08-14T12:38:57.648461Z","title":"Second-o rder guaran- tees of distributed gradient algorithms,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.07023","last_updated":"2019-08-19T18:56:40Z","snapshot_observed_at":"2026-08-16T16:26:24.233008Z","submitted_at":"2019-08-19T18:56:40Z","title":"Second-Order Guarantees of Stochastic Gradient Descent in Non-Convex Optimization","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-14T12:38:57.648461Z"},"links":{"cited_paper":"/paper/1809.08694","citing_paper":"/paper/1908.07023"},"observation_digest":"sha256:b1c10fbdaf46f735cb0d572057584ee185092a466ae43a66e1d3029bae969a49","observation_id":"31cc347c-8c22-4ec3-b6ef-c574a1e0cc8a","resolution":{"observed_at":"2026-08-14T12:38:57.648461Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:38:57.653942Z","title":"How to escape saddle points efficiently,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.07023","last_updated":"2019-08-19T18:56:40Z","snapshot_observed_at":"2026-08-16T16:26:24.233008Z","submitted_at":"2019-08-19T18:56:40Z","title":"Second-Order Guarantees of Stochastic Gradient Descent in Non-Convex Optimization","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-14T12:38:57.653942Z"},"links":{"citing_paper":"/paper/1908.07023"},"observation_digest":"sha256:7143b630c2b3fe57e474f6d9673743b4eaaa19a83c85bc1e99a9396918a15da3","observation_id":"4ca6569c-5e64-42d8-86f3-72ddf0b4ee31","resolution":{"observed_at":"2026-08-14T12:38:57.653942Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:38:57.930979Z","title":"Accelerated gr adient descent escapes saddle points faster than gradient descent,","venue":null,"work_id":"4efe80ef-16d7-4876-a17d-59f99d597d50","year":2018},"citing_paper":{"arxiv_id":"1908.07023","last_updated":"2019-08-19T18:56:40Z","snapshot_observed_at":"2026-08-16T16:26:24.233008Z","submitted_at":"2019-08-19T18:56:40Z","title":"Second-Order Guarantees of Stochastic Gradient Descent in Non-Convex Optimization","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-14T12:38:57.658446Z"},"links":{"citing_paper":"/paper/1908.07023"},"observation_digest":"sha256:3652e93a3bf25e89807465737534a27109f36b14aee4d82428120113380bd764","observation_id":"8cd5fca3-cd97-4a72-a48d-aa73224bb56a","resolution":{"observed_at":"2026-08-14T12:38:57.936819Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:38:57.663150Z","title":"Recursive stochastic algori thms for global optimization in Rd,","venue":null,"work_id":null,"year":1991},"citing_paper":{"arxiv_id":"1908.07023","last_updated":"2019-08-19T18:56:40Z","snapshot_observed_at":"2026-08-16T16:26:24.233008Z","submitted_at":"2019-08-19T18:56:40Z","title":"Second-Order Guarantees of Stochastic Gradient Descent in Non-Convex Optimization","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-14T12:38:57.663150Z"},"links":{"citing_paper":"/paper/1908.07023"},"observation_digest":"sha256:b35a7a967f57083478c17ee6791c50f336387c0ade34767e33e372815ee11469","observation_id":"608c1dc5-8dd5-4073-854b-d01fb25c979a","resolution":{"observed_at":"2026-08-14T12:38:57.663150Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.07258","last_updated":"2019-03-18T05:16:37Z","snapshot_observed_at":"2026-08-14T17:00:57.527974Z","submitted_at":"2019-03-18T05:16:37Z","title":"Annealing for Distributed Global Optimization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.07258","snapshot_observed_at":"2026-08-14T12:38:57.667814Z","title":"Anneali ng for distributed global optimization,","venue":null,"work_id":null,"year":1903},"citing_paper":{"arxiv_id":"1908.07023","last_updated":"2019-08-19T18:56:40Z","snapshot_observed_at":"2026-08-16T16:26:24.233008Z","submitted_at":"2019-08-19T18:56:40Z","title":"Second-Order Guarantees of Stochastic Gradient Descent in Non-Convex Optimization","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-14T12:38:57.667814Z"},"links":{"cited_paper":"/paper/1903.07258","citing_paper":"/paper/1908.07023"},"observation_digest":"sha256:076ec0513f46315d37599b426f86529dda18cb23f6309e0e3cabb4123170f813","observation_id":"28bf37f6-5a63-4742-9772-aae4abec551d","resolution":{"observed_at":"2026-08-14T12:38:57.667814Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1803.05999","last_updated":"2018-09-16T16:18:17Z","snapshot_observed_at":"2026-08-15T14:26:26.608743Z","submitted_at":"2018-03-15T20:48:06Z","title":"Escaping Saddles with Stochastic Gradients","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1803.05999","snapshot_observed_at":"2026-08-14T12:38:57.672603Z","title":"Esc aping saddles with stochastic gradients,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"1908.07023","last_updated":"2019-08-19T18:56:40Z","snapshot_observed_at":"2026-08-16T16:26:24.233008Z","submitted_at":"2019-08-19T18:56:40Z","title":"Second-Order Guarantees of Stochastic Gradient Descent in Non-Convex Optimization","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-14T12:38:57.672603Z"},"links":{"cited_paper":"/paper/1803.05999","citing_paper":"/paper/1908.07023"},"observation_digest":"sha256:bba2d734d61eb3b2306b42aa45afc3faa856a6d2dc0cdf20f2c9e674c5a97acb","observation_id":"65e65c4c-2ff0-45b2-a8c4-e01cd5d7bacd","resolution":{"observed_at":"2026-08-14T12:38:57.672603Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1902.00247","last_updated":"2019-06-04T12:23:24Z","snapshot_observed_at":"2026-08-14T17:22:30.779148Z","submitted_at":"2019-02-01T09:35:27Z","title":"Sharp Analysis for Nonconvex SGD Escaping from Saddle Points","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.00247","snapshot_observed_at":"2026-08-14T12:38:57.677397Z","title":"Sharp analysis for nonconv ex sgd escaping from saddle points,","venue":null,"work_id":null,"year":1902},"citing_paper":{"arxiv_id":"1908.07023","last_updated":"2019-08-19T18:56:40Z","snapshot_observed_at":"2026-08-16T16:26:24.233008Z","submitted_at":"2019-08-19T18:56:40Z","title":"Second-Order Guarantees of Stochastic Gradient Descent in Non-Convex Optimization","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-14T12:38:57.677397Z"},"links":{"cited_paper":"/paper/1902.00247","citing_paper":"/paper/1908.07023"},"observation_digest":"sha256:7f23df8a81c937a2c2655463ea17acac6d0cb79d60bd218bae5c0bee8212a8dd","observation_id":"37c587e2-a5ef-4239-b9eb-c95e4b85096e","resolution":{"observed_at":"2026-08-14T12:38:57.677397Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1905.00529","last_updated":"2019-05-01T23:44:26Z","snapshot_observed_at":"2026-08-14T16:38:31.508331Z","submitted_at":"2019-05-01T23:44:26Z","title":"Stabilized SVRG: Simple Variance Reduction for Nonconvex Optimization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1905.00529","snapshot_observed_at":"2026-08-14T12:38:57.682441Z","title":"Stabilized SVRG: Simpl e variance reduction for nonconvex optimization,","venue":null,"work_id":null,"year":1905},"citing_paper":{"arxiv_id":"1908.07023","last_updated":"2019-08-19T18:56:40Z","snapshot_observed_at":"2026-08-16T16:26:24.233008Z","submitted_at":"2019-08-19T18:56:40Z","title":"Second-Order Guarantees of Stochastic Gradient Descent in Non-Convex Optimization","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-14T12:38:57.682441Z"},"links":{"cited_paper":"/paper/1905.00529","citing_paper":"/paper/1908.07023"},"observation_digest":"sha256:0df91b35f71ba2a45a88161f178cdb872251b075639a0abf8b58fd634e39d2c0","observation_id":"add5bab4-93c1-4189-8355-7b6546356889","resolution":{"observed_at":"2026-08-14T12:38:57.682441Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T12:38:57.904465Z","title":"Distributed Pareto optimizati on via diffusion strategies,","venue":null,"work_id":"bb86b061-0485-4f63-a823-e195746862e5","year":2013},"citing_paper":{"arxiv_id":"1908.07023","last_updated":"2019-08-19T18:56:40Z","snapshot_observed_at":"2026-08-16T16:26:24.233008Z","submitted_at":"2019-08-19T18:56:40Z","title":"Second-Order Guarantees of Stochastic Gradient Descent in Non-Convex Optimization","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-14T12:38:57.687348Z"},"links":{"citing_paper":"/paper/1908.07023"},"observation_digest":"sha256:559be26056bd77066c2a5af8bdd8fa808484f6e100d2f0242ac937ca80ae23ef","observation_id":"92c09af5-6139-4463-ab19-fd92e0aa1b9f","resolution":{"observed_at":"2026-08-14T12:38:57.909701Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"1908.07023","last_updated":"2019-08-19T18:56:40Z","latest_version":1,"primary_category":"math.OC","snapshot_observed_at":"2026-08-16T16:26:24.233008Z","submitted_at":"2019-08-19T18:56:40Z","title":"Second-Order Guarantees of Stochastic Gradient Descent in Non-Convex Optimization"},"reference_resolution":{"displayed":33,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":20,"verified_exact":3,"verified_fuzzy":10},"total_outbound_references":33},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 33 of 33 outbound references and 0 inbound Pith citation observations for arXiv:1908.07023."}