{"as_of":"2026-08-12T04:17:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:fa130a3eddd84830521a421b7a7d6f6ad5c554bd50cfe7afea8c7f3804e4eebf","coverage":[{"denominator":47,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":47,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T15:46:47.779439Z","state":"measured"},{"denominator":47,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":47,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-11T06:34:44.6726+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/2501.13790/citation-record","integrity":"/paper/2501.13790/integrity","json":"/paper/2501.13790/citation-record.json","paper":"/paper/2501.13790"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T15:46:48.492519Z","title":"Communication complexity of distributed convex learning and optimization","venue":null,"work_id":"76c86e07-a932-4c1d-8a2d-def997e57218","year":2015},"citing_paper":{"arxiv_id":"2501.13790","last_updated":"2025-05-07T15:34:15Z","snapshot_observed_at":"2026-08-11T18:53:52.974479Z","submitted_at":"2025-01-23T16:09:26Z","title":"Local Steps Speed Up Local GD for Heterogeneous Distributed Logistic Regression","version":2},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-10T15:46:47.547875Z"},"links":{"citing_paper":"/paper/2501.13790"},"observation_digest":"sha256:2a506fa7e0e7f43daa882a1c0a37e4b661019537935fdbffe8cb239a4ab996e6","observation_id":"a37cd258-0359-4903-94ac-22a3b6a7f09f","resolution":{"observed_at":"2026-08-10T15:46:48.497755Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T15:46:48.476275Z","title":"Adaptivity of averaged stochastic gradient descent to local strong convexity for logistic regression","venue":null,"work_id":"c85e678b-5b95-4d81-915c-4346b348617f","year":2014},"citing_paper":{"arxiv_id":"2501.13790","last_updated":"2025-05-07T15:34:15Z","snapshot_observed_at":"2026-08-11T18:53:52.974479Z","submitted_at":"2025-01-23T16:09:26Z","title":"Local Steps Speed Up Local GD for Heterogeneous Distributed Logistic Regression","version":2},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-10T15:46:47.553915Z"},"links":{"citing_paper":"/paper/2501.13790"},"observation_digest":"sha256:ebab23533756836886fd43a1f1122eb0280121e2de38d8f911c44a75e0d3f4eb","observation_id":"14e2327a-b59b-46a0-a82d-b70593fb9fc1","resolution":{"observed_at":"2026-08-10T15:46:48.481154Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T15:46:48.460588Z","title":"Distributed learning, communication complexity and privacy","venue":null,"work_id":"588e7464-734f-47cf-95ae-2d02e4904e6c","year":2012},"citing_paper":{"arxiv_id":"2501.13790","last_updated":"2025-05-07T15:34:15Z","snapshot_observed_at":"2026-08-11T18:53:52.974479Z","submitted_at":"2025-01-23T16:09:26Z","title":"Local Steps Speed Up Local GD for Heterogeneous Distributed Logistic Regression","version":2},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-10T15:46:47.559373Z"},"links":{"citing_paper":"/paper/2501.13790"},"observation_digest":"sha256:16da3f9347d929f6efd99a056eee513a3b980fe28238ccb6f262d2e0eaf17f2d","observation_id":"7995ca07-4999-47ab-9ebe-20f901db577e","resolution":{"observed_at":"2026-08-10T15:46:48.465943Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T15:46:48.443366Z","title":"Gradient descent on neural networks typically occurs at the edge of stability","venue":null,"work_id":"f0eac7db-8ab5-44d8-9ffc-3224162d217e","year":2021},"citing_paper":{"arxiv_id":"2501.13790","last_updated":"2025-05-07T15:34:15Z","snapshot_observed_at":"2026-08-11T18:53:52.974479Z","submitted_at":"2025-01-23T16:09:26Z","title":"Local Steps Speed Up Local GD for Heterogeneous Distributed Logistic Regression","version":2},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-10T15:46:47.566003Z"},"links":{"citing_paper":"/paper/2501.13790"},"observation_digest":"sha256:a40e7b084017d3c2f1a5ece90bfa0bdd47136613c4e255809b9aee3971eca60d","observation_id":"c6b5e213-be08-4ffe-ace2-cf483f29e582","resolution":{"observed_at":"2026-08-10T15:46:48.448354Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T15:46:48.428284Z","title":"Optimal distributed online prediction using mini-batches","venue":null,"work_id":"18fe1b5a-307b-4b78-b13d-41b0df574914","year":2012},"citing_paper":{"arxiv_id":"2501.13790","last_updated":"2025-05-07T15:34:15Z","snapshot_observed_at":"2026-08-11T18:53:52.974479Z","submitted_at":"2025-01-23T16:09:26Z","title":"Local Steps Speed Up Local GD for Heterogeneous Distributed Logistic Regression","version":2},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-10T15:46:47.571559Z"},"links":{"citing_paper":"/paper/2501.13790"},"observation_digest":"sha256:64dd95f71d2748d9b3215e4bf08da0554f1edeb0e4ca0cfc09557221144f754b","observation_id":"5f460f20-dc5c-4b94-8209-12d2be8c0ff0","resolution":{"observed_at":"2026-08-10T15:46:48.433228Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T15:46:47.576742Z","title":"Optimal stochastic approximation algorithms for strongly convex stochastic composite optimization i: A generic algorithmic framework","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2501.13790","last_updated":"2025-05-07T15:34:15Z","snapshot_observed_at":"2026-08-11T18:53:52.974479Z","submitted_at":"2025-01-23T16:09:26Z","title":"Local Steps Speed Up Local GD for Heterogeneous Distributed Logistic Regression","version":2},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-10T15:46:47.576742Z"},"links":{"citing_paper":"/paper/2501.13790"},"observation_digest":"sha256:a8d9b72fa8cfa758a044a62673f7b4633b3b58e068b06e4ff7c0cb6efd047482","observation_id":"1464e2d9-3b0d-4262-9578-506d6912199c","resolution":{"observed_at":"2026-08-10T15:46:47.576742Z","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":"2026-08-10T15:46:48.401695Z","title":"Sharp bounds for federated averaging (local sgd) and continuous perspective","venue":null,"work_id":"1a2b55fe-0884-4579-9570-f801c6438249","year":2022},"citing_paper":{"arxiv_id":"2501.13790","last_updated":"2025-05-07T15:34:15Z","snapshot_observed_at":"2026-08-11T18:53:52.974479Z","submitted_at":"2025-01-23T16:09:26Z","title":"Local Steps Speed Up Local GD for Heterogeneous Distributed Logistic Regression","version":2},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-10T15:46:47.582207Z"},"links":{"citing_paper":"/paper/2501.13790"},"observation_digest":"sha256:ed73b1affba4946cc0fe13ecb7bddb9780adcf302b38b8fd86283812d23f5200","observation_id":"72110b65-9ec8-4a0b-8045-b9ec7801e4ee","resolution":{"observed_at":"2026-08-10T15:46:48.407281Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T15:46:48.385190Z","title":"Characterizing implicit bias in terms of optimization geometry","venue":null,"work_id":"e6f38102-545d-41f7-82bd-0f2a2677d78f","year":2018},"citing_paper":{"arxiv_id":"2501.13790","last_updated":"2025-05-07T15:34:15Z","snapshot_observed_at":"2026-08-11T18:53:52.974479Z","submitted_at":"2025-01-23T16:09:26Z","title":"Local Steps Speed Up Local GD for Heterogeneous Distributed Logistic Regression","version":2},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-10T15:46:47.587445Z"},"links":{"citing_paper":"/paper/2501.13790"},"observation_digest":"sha256:b1a7a311d7a781733960c728fbee664fad36cdf9087ebb118b6cc7d8dd85b713","observation_id":"9775e904-e1c6-49cf-933b-fa760af9f3db","resolution":{"observed_at":"2026-08-10T15:46:48.390148Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1910.14425","last_updated":"2019-12-06T21:16:41Z","snapshot_observed_at":"2026-07-30T21:49:53.494348Z","submitted_at":"2019-10-31T12:52:55Z","title":"On the Convergence of Local Descent Methods in Federated Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.14425","snapshot_observed_at":"2026-08-10T15:46:47.592529Z","title":"On the convergence of local descent methods in federated learning","venue":null,"work_id":null,"year":1910},"citing_paper":{"arxiv_id":"2501.13790","last_updated":"2025-05-07T15:34:15Z","snapshot_observed_at":"2026-08-11T18:53:52.974479Z","submitted_at":"2025-01-23T16:09:26Z","title":"Local Steps Speed Up Local GD for Heterogeneous Distributed Logistic Regression","version":2},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-10T15:46:47.592529Z"},"links":{"cited_paper":"/paper/1910.14425","citing_paper":"/paper/2501.13790"},"observation_digest":"sha256:91d862430213a22214aec5a5a1fbf9913aeef1e25ea0869c67ed504778c27928","observation_id":"5735e215-e8a2-4bc7-b6c9-ab02ee3637a4","resolution":{"observed_at":"2026-08-10T15:46:47.592529Z","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":"2026-08-10T15:46:47.598119Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2501.13790","last_updated":"2025-05-07T15:34:15Z","snapshot_observed_at":"2026-08-11T18:53:52.974479Z","submitted_at":"2025-01-23T16:09:26Z","title":"Local Steps Speed Up Local GD for Heterogeneous Distributed Logistic Regression","version":2},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-10T15:46:47.598119Z"},"links":{"citing_paper":"/paper/2501.13790"},"observation_digest":"sha256:cdcfdc3ed81978662123c8f388b7aadd51532bc00910a5cf1974ee8ad502433a","observation_id":"f899152c-e320-4cce-96d6-28bf9fec06b1","resolution":{"observed_at":"2026-08-10T15:46:47.598119Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1803.07300","last_updated":"2019-06-08T13:57:05Z","snapshot_observed_at":"2026-08-10T12:34:19.641462Z","submitted_at":"2018-03-20T08:47:27Z","title":"Risk and parameter convergence of logistic regression","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1803.07300","snapshot_observed_at":"2026-08-10T15:46:47.602767Z","title":"Risk and parameter convergence of logistic regression","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2501.13790","last_updated":"2025-05-07T15:34:15Z","snapshot_observed_at":"2026-08-11T18:53:52.974479Z","submitted_at":"2025-01-23T16:09:26Z","title":"Local Steps Speed Up Local GD for Heterogeneous Distributed Logistic Regression","version":2},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-10T15:46:47.602767Z"},"links":{"cited_paper":"/paper/1803.07300","citing_paper":"/paper/2501.13790"},"observation_digest":"sha256:1214245486e8313bf7148c358043e3d378964a4dd2f1e3302b40e92d355f9f3e","observation_id":"b2c9ffab-6320-4584-a086-e916b71a501e","resolution":{"observed_at":"2026-08-10T15:46:47.602767Z","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":"2026-08-10T15:46:48.360237Z","title":"Fast margin maximization via dual acceleration","venue":null,"work_id":"7dea4ecb-3200-4813-9eff-40a0cc89bdfe","year":2021},"citing_paper":{"arxiv_id":"2501.13790","last_updated":"2025-05-07T15:34:15Z","snapshot_observed_at":"2026-08-11T18:53:52.974479Z","submitted_at":"2025-01-23T16:09:26Z","title":"Local Steps Speed Up Local GD for Heterogeneous Distributed Logistic Regression","version":2},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-10T15:46:47.607982Z"},"links":{"citing_paper":"/paper/2501.13790"},"observation_digest":"sha256:cac5c253501807f026e67baae9c1866bbedfd24462b07cbf35bb3e718b4bdf50","observation_id":"242c0e72-40cd-49f0-a785-47ef71b66b3e","resolution":{"observed_at":"2026-08-10T15:46:48.365136Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1912.04977","last_updated":"2021-03-09T03:03:49Z","snapshot_observed_at":"2026-08-06T02:25:34.414976Z","submitted_at":"2019-12-10T20:55:41Z","title":"Advances and Open Problems in Federated Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1912.04977","snapshot_observed_at":"2026-08-10T15:46:47.612502Z","title":"Advances and open problems in federated learning","venue":null,"work_id":null,"year":1912},"citing_paper":{"arxiv_id":"2501.13790","last_updated":"2025-05-07T15:34:15Z","snapshot_observed_at":"2026-08-11T18:53:52.974479Z","submitted_at":"2025-01-23T16:09:26Z","title":"Local Steps Speed Up Local GD for Heterogeneous Distributed Logistic Regression","version":2},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-10T15:46:47.612502Z"},"links":{"cited_paper":"/paper/1912.04977","citing_paper":"/paper/2501.13790"},"observation_digest":"sha256:f1aaa290703e9cf34585b4db4e37e33933f4c1ac0eec54b2593d23e44b48de77","observation_id":"3a99c2c4-1754-4a19-adb6-94d178ce570e","resolution":{"observed_at":"2026-08-10T15:46:47.612502Z","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":"2026-08-10T15:46:47.617690Z","title":"Advances and open problems in federated learning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.13790","last_updated":"2025-05-07T15:34:15Z","snapshot_observed_at":"2026-08-11T18:53:52.974479Z","submitted_at":"2025-01-23T16:09:26Z","title":"Local Steps Speed Up Local GD for Heterogeneous Distributed Logistic Regression","version":2},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-10T15:46:47.617690Z"},"links":{"citing_paper":"/paper/2501.13790"},"observation_digest":"sha256:111bd9df31f81c48695b8e05ec51738962ad0c4f2f418dff31144b4478d36bf1","observation_id":"6b6cf274-2572-496d-bf60-7e666961a3d0","resolution":{"observed_at":"2026-08-10T15:46:47.617690Z","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":"2026-08-10T15:46:47.622481Z","title":"Scaffold: Stochastic controlled averaging for federated learning","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2501.13790","last_updated":"2025-05-07T15:34:15Z","snapshot_observed_at":"2026-08-11T18:53:52.974479Z","submitted_at":"2025-01-23T16:09:26Z","title":"Local Steps Speed Up Local GD for Heterogeneous Distributed Logistic Regression","version":2},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-10T15:46:47.622481Z"},"links":{"citing_paper":"/paper/2501.13790"},"observation_digest":"sha256:a5073c3c0c1365f3f1befa23ef5f830f42ed25b6895c6bdb49c13c547f9d760d","observation_id":"69e8a5cd-4fa6-47a3-a9fc-f8fb23fe347d","resolution":{"observed_at":"2026-08-10T15:46:47.622481Z","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":"2026-08-10T15:46:48.320914Z","title":"Tighter theory for local sgd on identical and heterogeneous data","venue":null,"work_id":"c4212901-6ac5-41ae-9b9b-5a4615fd4e95","year":2020},"citing_paper":{"arxiv_id":"2501.13790","last_updated":"2025-05-07T15:34:15Z","snapshot_observed_at":"2026-08-11T18:53:52.974479Z","submitted_at":"2025-01-23T16:09:26Z","title":"Local Steps Speed Up Local GD for Heterogeneous Distributed Logistic Regression","version":2},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-10T15:46:47.627218Z"},"links":{"citing_paper":"/paper/2501.13790"},"observation_digest":"sha256:80a90098ef05b5682e567341f62f71bfddc9734ba564dca7f1310e3106ef7e38","observation_id":"8ac92962-002d-49d2-8b24-a9656cc158c8","resolution":{"observed_at":"2026-08-10T15:46:48.327498Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T15:46:48.305751Z","title":"A unified theory of decentralized sgd with changing topology and local updates","venue":null,"work_id":"a9004425-1516-4416-bb44-2d5868d936d1","year":2020},"citing_paper":{"arxiv_id":"2501.13790","last_updated":"2025-05-07T15:34:15Z","snapshot_observed_at":"2026-08-11T18:53:52.974479Z","submitted_at":"2025-01-23T16:09:26Z","title":"Local Steps Speed Up Local GD for Heterogeneous Distributed Logistic Regression","version":2},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-10T15:46:47.632412Z"},"links":{"citing_paper":"/paper/2501.13790"},"observation_digest":"sha256:57b5499c3606ea23babac5caab00a5e5fdd1518015beee18e46841c51aec1704","observation_id":"cfcc2ec2-8ecb-48bb-9d7d-a24906acdd30","resolution":{"observed_at":"2026-08-10T15:46:48.310600Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2304.04169","last_updated":"2025-01-18T20:58:21Z","snapshot_observed_at":"2026-07-06T15:13:44.440390Z","submitted_at":"2023-04-09T06:10:49Z","title":"SLowcal-SGD: Slow Query Points Improve Local-SGD for Stochastic Convex Optimization","version":2},"cited_work":{"arxiv_id":"2304.04169","doi":null,"metadata_source":"pith","pith_arxiv_id":"2304.04169","snapshot_observed_at":"2026-08-10T15:46:47.881798Z","title":"SLowcal-SGD: Slow Query Points Improve Local-SGD for Stochastic Convex Optimization","venue":"cs.LG","work_id":"5e89c082-c8ed-46ff-a779-84136373c177","year":2023},"citing_paper":{"arxiv_id":"2501.13790","last_updated":"2025-05-07T15:34:15Z","snapshot_observed_at":"2026-08-11T18:53:52.974479Z","submitted_at":"2025-01-23T16:09:26Z","title":"Local Steps Speed Up Local GD for Heterogeneous Distributed Logistic Regression","version":2},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-10T15:46:47.637050Z"},"links":{"cited_paper":"/paper/2304.04169","citing_paper":"/paper/2501.13790"},"observation_digest":"sha256:176a8b6566f171ec3e0da3c7c76e718e8f32a1bc42d4a5cc9bdb6b6e68322f77","observation_id":"dc729fa8-7f92-4226-a8fc-6e9231dcd9d0","resolution":{"observed_at":"2026-08-10T15:46:47.889279Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T15:46:48.290249Z","title":"Don't use large mini-batches, use local sgd","venue":null,"work_id":"2aa6f3a8-f0bd-4745-a7bb-3fbb968772cb","year":2019},"citing_paper":{"arxiv_id":"2501.13790","last_updated":"2025-05-07T15:34:15Z","snapshot_observed_at":"2026-08-11T18:53:52.974479Z","submitted_at":"2025-01-23T16:09:26Z","title":"Local Steps Speed Up Local GD for Heterogeneous Distributed Logistic Regression","version":2},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-10T15:46:47.642171Z"},"links":{"citing_paper":"/paper/2501.13790"},"observation_digest":"sha256:d594ada6b9c9bdb0f82a1a8cead60f35fd0f2d926a8b8a81e50d8e25eda8ad85","observation_id":"3f0cec6c-dcf2-4ebd-85d7-d1072a72e2b6","resolution":{"observed_at":"2026-08-10T15:46:48.295099Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T15:46:48.274519Z","title":"Efficient large-scale distributed training of conditional maximum entropy models","venue":null,"work_id":"02a7c53b-edbe-4146-a5fd-536c8f414e7b","year":2009},"citing_paper":{"arxiv_id":"2501.13790","last_updated":"2025-05-07T15:34:15Z","snapshot_observed_at":"2026-08-11T18:53:52.974479Z","submitted_at":"2025-01-23T16:09:26Z","title":"Local Steps Speed Up Local GD for Heterogeneous Distributed Logistic Regression","version":2},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-10T15:46:47.647041Z"},"links":{"citing_paper":"/paper/2501.13790"},"observation_digest":"sha256:ac4068c9919f08e4ab90515baa8b15ea0a4c3d71cd2cece1454724af92b5f267","observation_id":"aa8eaeea-d511-4d82-bf74-fb571c48af1b","resolution":{"observed_at":"2026-08-10T15:46:48.279589Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T15:46:48.258831Z","title":"Distributed training strategies for the structured perceptron","venue":null,"work_id":"9921c1a1-8e92-464a-8568-66c797c041d6","year":2010},"citing_paper":{"arxiv_id":"2501.13790","last_updated":"2025-05-07T15:34:15Z","snapshot_observed_at":"2026-08-11T18:53:52.974479Z","submitted_at":"2025-01-23T16:09:26Z","title":"Local Steps Speed Up Local GD for Heterogeneous Distributed Logistic Regression","version":2},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-10T15:46:47.651852Z"},"links":{"citing_paper":"/paper/2501.13790"},"observation_digest":"sha256:d0551b60821eb050a9b2a362502b22cf201c90b374a7fed4c2287ef1f61307b7","observation_id":"96cd270d-3102-41be-a050-7891f00f85a0","resolution":{"observed_at":"2026-08-10T15:46:48.264210Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T15:46:47.656728Z","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2501.13790","last_updated":"2025-05-07T15:34:15Z","snapshot_observed_at":"2026-08-11T18:53:52.974479Z","submitted_at":"2025-01-23T16:09:26Z","title":"Local Steps Speed Up Local GD for Heterogeneous Distributed Logistic Regression","version":2},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-10T15:46:47.656728Z"},"links":{"citing_paper":"/paper/2501.13790"},"observation_digest":"sha256:64458342a9b984572287b331afc09ca78ef93bc12c478483ab44991e328e4b25","observation_id":"20ae09e3-7989-40c6-a7e7-f26d405b2170","resolution":{"observed_at":"2026-08-10T15:46:47.656728Z","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":"2026-08-10T15:46:48.233024Z","title":"Proximal and federated random reshuffling","venue":null,"work_id":"96be3289-44d0-424c-9696-da817c695154","year":2022},"citing_paper":{"arxiv_id":"2501.13790","last_updated":"2025-05-07T15:34:15Z","snapshot_observed_at":"2026-08-11T18:53:52.974479Z","submitted_at":"2025-01-23T16:09:26Z","title":"Local Steps Speed Up Local GD for Heterogeneous Distributed Logistic Regression","version":2},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-10T15:46:47.661732Z"},"links":{"citing_paper":"/paper/2501.13790"},"observation_digest":"sha256:797fc23431ffe22a371d60d0ffe4b43f29dd4f8cc10f445a08ecbea94e6a39ee","observation_id":"64a299ee-01aa-440a-8d6b-69a7f7df0c93","resolution":{"observed_at":"2026-08-10T15:46:48.239008Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T15:46:48.217432Z","title":"Stochastic gradient descent on separable data: Exact convergence with a fixed learning rate","venue":null,"work_id":"b71eb7ef-ac89-4ba8-980b-76163ea3d06c","year":2019},"citing_paper":{"arxiv_id":"2501.13790","last_updated":"2025-05-07T15:34:15Z","snapshot_observed_at":"2026-08-11T18:53:52.974479Z","submitted_at":"2025-01-23T16:09:26Z","title":"Local Steps Speed Up Local GD for Heterogeneous Distributed Logistic Regression","version":2},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-10T15:46:47.667587Z"},"links":{"citing_paper":"/paper/2501.13790"},"observation_digest":"sha256:d5e28ae0e79b650969bb312b7c2284414b30742d462e8363d2128f210de14910","observation_id":"4ee241fb-8002-4e79-9b36-030cd3ccccd8","resolution":{"observed_at":"2026-08-10T15:46:48.222332Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T15:46:47.672305Z","title":"Introductory lectures on convex optimization: A basic course, volume 87","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2501.13790","last_updated":"2025-05-07T15:34:15Z","snapshot_observed_at":"2026-08-11T18:53:52.974479Z","submitted_at":"2025-01-23T16:09:26Z","title":"Local Steps Speed Up Local GD for Heterogeneous Distributed Logistic Regression","version":2},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-10T15:46:47.672305Z"},"links":{"citing_paper":"/paper/2501.13790"},"observation_digest":"sha256:efadc261ef2748bb27e4edf3e21c759ea0f98bb254563e0a77478c6902a3e11a","observation_id":"974679a0-77bd-401d-8225-5c21af772912","resolution":{"observed_at":"2026-08-10T15:46:47.672305Z","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":"2026-08-10T15:46:48.191837Z","title":"A minimizer far, far away, 2024","venue":null,"work_id":"f40ed645-70da-419e-9706-2cf5ad9ca0b7","year":2024},"citing_paper":{"arxiv_id":"2501.13790","last_updated":"2025-05-07T15:34:15Z","snapshot_observed_at":"2026-08-11T18:53:52.974479Z","submitted_at":"2025-01-23T16:09:26Z","title":"Local Steps Speed Up Local GD for Heterogeneous Distributed Logistic Regression","version":2},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-10T15:46:47.677037Z"},"links":{"citing_paper":"/paper/2501.13790"},"observation_digest":"sha256:27998a1b21ec789f0e714bf5d1ff0bb47c6a3297e395edc203e3c6c5c24109aa","observation_id":"bfe2ed56-1f9b-4ae9-9c98-8d512f74c33e","resolution":{"observed_at":"2026-08-10T15:46:48.196880Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T15:46:48.175071Z","title":"On the still unreasonable effectiveness of federated averaging for heterogeneous distributed learning","venue":null,"work_id":"ad112a53-2fd7-40d3-a574-1cbe7aa74608","year":2023},"citing_paper":{"arxiv_id":"2501.13790","last_updated":"2025-05-07T15:34:15Z","snapshot_observed_at":"2026-08-11T18:53:52.974479Z","submitted_at":"2025-01-23T16:09:26Z","title":"Local Steps Speed Up Local GD for Heterogeneous Distributed Logistic Regression","version":2},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-10T15:46:47.682248Z"},"links":{"citing_paper":"/paper/2501.13790"},"observation_digest":"sha256:eb076ec33ed29a996f9d957fa3099a5c5baebc0a0c7e181f5789a1286655d62a","observation_id":"25efdabe-0ee7-4f86-9977-fd8b358108a6","resolution":{"observed_at":"2026-08-10T15:46:48.180318Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T15:46:48.158324Z","title":"The limits and potentials of local sgd for distributed heterogeneous learning with intermittent communication","venue":null,"work_id":"33be37f2-8a76-4bfc-b891-2c7a13f1d12a","year":2024},"citing_paper":{"arxiv_id":"2501.13790","last_updated":"2025-05-07T15:34:15Z","snapshot_observed_at":"2026-08-11T18:53:52.974479Z","submitted_at":"2025-01-23T16:09:26Z","title":"Local Steps Speed Up Local GD for Heterogeneous Distributed Logistic Regression","version":2},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-10T15:46:47.687037Z"},"links":{"citing_paper":"/paper/2501.13790"},"observation_digest":"sha256:1ce6a3aa17f882c63690506937c81d75bb122ab80f9b619c5ad71e44283dc43f","observation_id":"10bbef97-0329-4b30-b7dc-b2e5323eb478","resolution":{"observed_at":"2026-08-10T15:46:48.163374Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T15:46:48.141118Z","title":"Distributed stochastic optimization and learning","venue":null,"work_id":"834f88a5-be08-4f26-9491-8ef8aefd48ca","year":2014},"citing_paper":{"arxiv_id":"2501.13790","last_updated":"2025-05-07T15:34:15Z","snapshot_observed_at":"2026-08-11T18:53:52.974479Z","submitted_at":"2025-01-23T16:09:26Z","title":"Local Steps Speed Up Local GD for Heterogeneous Distributed Logistic Regression","version":2},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-10T15:46:47.691757Z"},"links":{"citing_paper":"/paper/2501.13790"},"observation_digest":"sha256:57124bae9f2e0d9a3b1d0ff0cda6ba208cf4be7b6f54347ab68cb540c5786693","observation_id":"f9867f78-3f7c-4625-b054-5fa0441dbce3","resolution":{"observed_at":"2026-08-10T15:46:48.147628Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T15:46:48.125835Z","title":"The implicit bias of gradient descent on separable data","venue":null,"work_id":"f6fd169e-30cd-4786-b168-5922795467e9","year":2018},"citing_paper":{"arxiv_id":"2501.13790","last_updated":"2025-05-07T15:34:15Z","snapshot_observed_at":"2026-08-11T18:53:52.974479Z","submitted_at":"2025-01-23T16:09:26Z","title":"Local Steps Speed Up Local GD for Heterogeneous Distributed Logistic Regression","version":2},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-10T15:46:47.696254Z"},"links":{"citing_paper":"/paper/2501.13790"},"observation_digest":"sha256:0a2fff5ca6f4b72941da94decf944279df928673f56cdb9c0bd7dd091b72f11d","observation_id":"564d3391-36df-4ad6-89ea-b3bdd871161c","resolution":{"observed_at":"2026-08-10T15:46:48.130857Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1805.09767","last_updated":"2019-05-03T12:58:04Z","snapshot_observed_at":"2026-07-06T06:41:03.009337Z","submitted_at":"2018-05-24T16:38:51Z","title":"Local SGD Converges Fast and Communicates Little","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1805.09767","snapshot_observed_at":"2026-08-10T15:46:47.700925Z","title":"Local sgd converges fast and communicates little","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2501.13790","last_updated":"2025-05-07T15:34:15Z","snapshot_observed_at":"2026-08-11T18:53:52.974479Z","submitted_at":"2025-01-23T16:09:26Z","title":"Local Steps Speed Up Local GD for Heterogeneous Distributed Logistic Regression","version":2},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-10T15:46:47.700925Z"},"links":{"cited_paper":"/paper/1805.09767","citing_paper":"/paper/2501.13790"},"observation_digest":"sha256:59cd2902ced97fd254caf73ff8256fcd778a8d6ceadbd82172a3289c46a6cbda","observation_id":"f323f905-a048-488b-bfd0-aa2ff7383e44","resolution":{"observed_at":"2026-08-10T15:46:47.700925Z","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":"2026-08-10T15:46:48.110039Z","title":"Local sgd converges fast and communicates little","venue":null,"work_id":"3520232d-6ef8-449e-bfbe-b7fa50607e6a","year":2019},"citing_paper":{"arxiv_id":"2501.13790","last_updated":"2025-05-07T15:34:15Z","snapshot_observed_at":"2026-08-11T18:53:52.974479Z","submitted_at":"2025-01-23T16:09:26Z","title":"Local Steps Speed Up Local GD for Heterogeneous Distributed Logistic Regression","version":2},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-10T15:46:47.705844Z"},"links":{"citing_paper":"/paper/2501.13790"},"observation_digest":"sha256:041a0e82da56438a19021596d59d35f8fb46dbefd73bff93733cd2c1144e7053","observation_id":"464b7f8b-05a1-4998-8e1a-153c4fc2915b","resolution":{"observed_at":"2026-08-10T15:46:48.115350Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2107.06917","last_updated":"2021-07-14T18:09:08Z","snapshot_observed_at":"2026-07-31T18:13:22.254060Z","submitted_at":"2021-07-14T18:09:08Z","title":"A Field Guide to Federated Optimization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2107.06917","snapshot_observed_at":"2026-08-10T15:46:47.710477Z","title":"A field guide to federated optimization","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.13790","last_updated":"2025-05-07T15:34:15Z","snapshot_observed_at":"2026-08-11T18:53:52.974479Z","submitted_at":"2025-01-23T16:09:26Z","title":"Local Steps Speed Up Local GD for Heterogeneous Distributed Logistic Regression","version":2},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-10T15:46:47.710477Z"},"links":{"cited_paper":"/paper/2107.06917","citing_paper":"/paper/2501.13790"},"observation_digest":"sha256:2891a1926abb52f7b7f7c1321b7ab77254b726eae4815ace19a1b1cd3f07ada3","observation_id":"7a377e9c-0abb-4518-8895-df6bdfd23892","resolution":{"observed_at":"2026-08-10T15:46:47.710477Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04723","last_updated":"2022-06-09T18:25:25Z","snapshot_observed_at":"2026-08-06T18:33:38.685868Z","submitted_at":"2022-06-09T18:25:25Z","title":"On the Unreasonable Effectiveness of Federated Averaging with Heterogeneous Data","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.04723","snapshot_observed_at":"2026-08-10T15:46:47.715859Z","title":"On the unreasonable effectiveness of federated averaging with heterogeneous data","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.13790","last_updated":"2025-05-07T15:34:15Z","snapshot_observed_at":"2026-08-11T18:53:52.974479Z","submitted_at":"2025-01-23T16:09:26Z","title":"Local Steps Speed Up Local GD for Heterogeneous Distributed Logistic Regression","version":2},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-10T15:46:47.715859Z"},"links":{"cited_paper":"/paper/2206.04723","citing_paper":"/paper/2501.13790"},"observation_digest":"sha256:f2d053bf5e7fcce05fa4e93e94e355d55622d3aa8152cca556fd722336fabf5d","observation_id":"17fcfc90-36da-4d52-a850-ee1730236330","resolution":{"observed_at":"2026-08-10T15:46:47.715859Z","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":"2026-08-10T15:46:48.093834Z","title":"Is local sgd better than minibatch sgd? In International Conference on Machine Learning, pp.\\ 10334--10343","venue":null,"work_id":"288eed29-4e80-4451-988d-c51ae3e6bbc0","year":2020},"citing_paper":{"arxiv_id":"2501.13790","last_updated":"2025-05-07T15:34:15Z","snapshot_observed_at":"2026-08-11T18:53:52.974479Z","submitted_at":"2025-01-23T16:09:26Z","title":"Local Steps Speed Up Local GD for Heterogeneous Distributed Logistic Regression","version":2},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-10T15:46:47.720585Z"},"links":{"citing_paper":"/paper/2501.13790"},"observation_digest":"sha256:61540d9972898604df810d1fdb49ac040d17ae3ad8bcdbbc32a078c05e6e6b0e","observation_id":"13d71d0d-e820-4a32-9a49-338c6da5da02","resolution":{"observed_at":"2026-08-10T15:46:48.098901Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T15:46:47.726644Z","title":"Graph oracle models, lower bounds, and gaps for parallel stochastic optimization","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2501.13790","last_updated":"2025-05-07T15:34:15Z","snapshot_observed_at":"2026-08-11T18:53:52.974479Z","submitted_at":"2025-01-23T16:09:26Z","title":"Local Steps Speed Up Local GD for Heterogeneous Distributed Logistic Regression","version":2},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-10T15:46:47.726644Z"},"links":{"citing_paper":"/paper/2501.13790"},"observation_digest":"sha256:029fc424430acf5471ea2feed59bb14ce79dfd604ee2a1675455f603d46adae6","observation_id":"b1f52b1e-22fb-49fd-973e-1aae0fdfd9cb","resolution":{"observed_at":"2026-08-10T15:46:47.726644Z","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":"2026-08-10T15:46:48.064955Z","title":"Minibatch vs local sgd for heterogeneous distributed learning","venue":null,"work_id":"596daf98-dcd2-43b6-a47d-c93782166ecb","year":2020},"citing_paper":{"arxiv_id":"2501.13790","last_updated":"2025-05-07T15:34:15Z","snapshot_observed_at":"2026-08-11T18:53:52.974479Z","submitted_at":"2025-01-23T16:09:26Z","title":"Local Steps Speed Up Local GD for Heterogeneous Distributed Logistic Regression","version":2},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-10T15:46:47.731134Z"},"links":{"citing_paper":"/paper/2501.13790"},"observation_digest":"sha256:5384a62a13bc76d6195b243c4aab23fa655effd32f758b1ab7e5727abeeae2e2","observation_id":"cf8eb43e-7e2d-4ed7-86dc-ce8eec676e01","resolution":{"observed_at":"2026-08-10T15:46:48.070822Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T15:46:48.047587Z","title":"The min-max complexity of distributed stochastic convex optimization with intermittent communication","venue":null,"work_id":"b00ec9b8-4e2f-4f99-a68d-9adb12737bcd","year":2021},"citing_paper":{"arxiv_id":"2501.13790","last_updated":"2025-05-07T15:34:15Z","snapshot_observed_at":"2026-08-11T18:53:52.974479Z","submitted_at":"2025-01-23T16:09:26Z","title":"Local Steps Speed Up Local GD for Heterogeneous Distributed Logistic Regression","version":2},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-10T15:46:47.735592Z"},"links":{"citing_paper":"/paper/2501.13790"},"observation_digest":"sha256:10a492257ce7b47bf49bcf5dd815715072b6fbde5a36abfa978cd87850f83b51","observation_id":"21cd2931-a870-434a-9d94-9675a0976255","resolution":{"observed_at":"2026-08-10T15:46:48.053068Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.15926","last_updated":"2024-06-10T03:32:05Z","snapshot_observed_at":"2026-08-06T03:14:08.878665Z","submitted_at":"2024-02-24T23:10:28Z","title":"Large Stepsize Gradient Descent for Logistic Loss: Non-Monotonicity of the Loss Improves Optimization Efficiency","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.15926","snapshot_observed_at":"2026-08-10T15:46:47.740292Z","title":"Large stepsize gradient descent for logistic loss: Non-monotonicity of the loss improves optimization efficiency","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.13790","last_updated":"2025-05-07T15:34:15Z","snapshot_observed_at":"2026-08-11T18:53:52.974479Z","submitted_at":"2025-01-23T16:09:26Z","title":"Local Steps Speed Up Local GD for Heterogeneous Distributed Logistic Regression","version":2},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-10T15:46:47.740292Z"},"links":{"cited_paper":"/paper/2402.15926","citing_paper":"/paper/2501.13790"},"observation_digest":"sha256:ad8ee6fc72da9e15733e03779b1c1bd11c9509df6a6c8cd7dcee490482c7b9a4","observation_id":"5f3e58ba-060e-4578-9d32-bba7b4217b6c","resolution":{"observed_at":"2026-08-10T15:46:47.740292Z","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":"2026-08-10T15:46:48.031871Z","title":"Implicit bias of gradient descent for logistic regression at the edge of stability","venue":null,"work_id":"2454370b-83e9-4ed6-abf1-eed61ea19ca5","year":2024},"citing_paper":{"arxiv_id":"2501.13790","last_updated":"2025-05-07T15:34:15Z","snapshot_observed_at":"2026-08-11T18:53:52.974479Z","submitted_at":"2025-01-23T16:09:26Z","title":"Local Steps Speed Up Local GD for Heterogeneous Distributed Logistic Regression","version":2},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-10T15:46:47.745231Z"},"links":{"citing_paper":"/paper/2501.13790"},"observation_digest":"sha256:e3f5bc73ec08625c9748ffb820e55cd68b29aab258b5db8035d2db4a8004aec9","observation_id":"77fe3839-79f6-4fc3-afc3-78cd4a5a9f29","resolution":{"observed_at":"2026-08-10T15:46:48.037192Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T15:46:48.016229Z","title":"Federated accelerated stochastic gradient descent","venue":null,"work_id":"c94495aa-409e-48ee-9380-33efe2c6c43b","year":2020},"citing_paper":{"arxiv_id":"2501.13790","last_updated":"2025-05-07T15:34:15Z","snapshot_observed_at":"2026-08-11T18:53:52.974479Z","submitted_at":"2025-01-23T16:09:26Z","title":"Local Steps Speed Up Local GD for Heterogeneous Distributed Logistic Regression","version":2},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-10T15:46:47.749965Z"},"links":{"citing_paper":"/paper/2501.13790"},"observation_digest":"sha256:23a10f342c5021f151309f8cf13d8cf985d8fb062ece2841b6836c401592c9dd","observation_id":"52e2efb2-1d9f-4873-bd65-a3dec788e6e9","resolution":{"observed_at":"2026-08-10T15:46:48.021582Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T15:46:47.999996Z","title":"Information-theoretic lower bounds for distributed statistical estimation with communication constraints","venue":null,"work_id":"57920db0-0eb8-4832-96e0-d1967cfa2adb","year":2013},"citing_paper":{"arxiv_id":"2501.13790","last_updated":"2025-05-07T15:34:15Z","snapshot_observed_at":"2026-08-11T18:53:52.974479Z","submitted_at":"2025-01-23T16:09:26Z","title":"Local Steps Speed Up Local GD for Heterogeneous Distributed Logistic Regression","version":2},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-10T15:46:47.754451Z"},"links":{"citing_paper":"/paper/2501.13790"},"observation_digest":"sha256:b5ade95ce90f7b879ec4b856d7458ca48aacca8ee621a0caa8d65ba406f24484","observation_id":"4b77c0b8-8d0c-4336-8b34-b57cdf1cc861","resolution":{"observed_at":"2026-08-10T15:46:48.005323Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T15:46:47.758944Z","title":"Parallelized stochastic gradient descent","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2501.13790","last_updated":"2025-05-07T15:34:15Z","snapshot_observed_at":"2026-08-11T18:53:52.974479Z","submitted_at":"2025-01-23T16:09:26Z","title":"Local Steps Speed Up Local GD for Heterogeneous Distributed Logistic Regression","version":2},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-10T15:46:47.758944Z"},"links":{"citing_paper":"/paper/2501.13790"},"observation_digest":"sha256:558a07eba39987eea60c24ea5b7389928d7679924e8e8b84c71eafe2d7d8ea91","observation_id":"ab1d4959-65a6-4dc9-a913-ee131a5b127e","resolution":{"observed_at":"2026-08-10T15:46:47.758944Z","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":"2026-08-10T15:46:47.764016Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.13790","last_updated":"2025-05-07T15:34:15Z","snapshot_observed_at":"2026-08-11T18:53:52.974479Z","submitted_at":"2025-01-23T16:09:26Z","title":"Local Steps Speed Up Local GD for Heterogeneous Distributed Logistic Regression","version":2},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-10T15:46:47.764016Z"},"links":{"citing_paper":"/paper/2501.13790"},"observation_digest":"sha256:6bc024b569090c31ac2e2a495f06931eb4f0ce145ca7cb3fdadf3e2cc198edb4","observation_id":"2850221d-1a0f-49c3-b126-61a33c5ac142","resolution":{"observed_at":"2026-08-10T15:46:47.764016Z","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":"2026-08-10T15:46:47.769809Z","title":"@esa (Ref","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.13790","last_updated":"2025-05-07T15:34:15Z","snapshot_observed_at":"2026-08-11T18:53:52.974479Z","submitted_at":"2025-01-23T16:09:26Z","title":"Local Steps Speed Up Local GD for Heterogeneous Distributed Logistic Regression","version":2},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-10T15:46:47.769809Z"},"links":{"citing_paper":"/paper/2501.13790"},"observation_digest":"sha256:3fdf89f85af4ccb3bd06123b3bbecde98ff13b568e898d88058a06f5845c07cb","observation_id":"ab9a25ce-ec6d-44ad-8bbf-1353bd0d166e","resolution":{"observed_at":"2026-08-10T15:46:47.769809Z","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":"2026-08-10T15:46:47.774739Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.13790","last_updated":"2025-05-07T15:34:15Z","snapshot_observed_at":"2026-08-11T18:53:52.974479Z","submitted_at":"2025-01-23T16:09:26Z","title":"Local Steps Speed Up Local GD for Heterogeneous Distributed Logistic Regression","version":2},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-10T15:46:47.774739Z"},"links":{"citing_paper":"/paper/2501.13790"},"observation_digest":"sha256:fe42e58fdcabb527f7748afb38ceb5da705d6895fe29fd12fe8cad4829c7787a","observation_id":"9ba25018-7fca-4301-b6f8-80f5a964ad88","resolution":{"observed_at":"2026-08-10T15:46:47.774739Z","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":"2026-08-10T15:46:47.779439Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.13790","last_updated":"2025-05-07T15:34:15Z","snapshot_observed_at":"2026-08-11T18:53:52.974479Z","submitted_at":"2025-01-23T16:09:26Z","title":"Local Steps Speed Up Local GD for Heterogeneous Distributed Logistic Regression","version":2},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-10T15:46:47.779439Z"},"links":{"citing_paper":"/paper/2501.13790"},"observation_digest":"sha256:2f29fca90da683263066e8307a0bdc0e418a9188619d2b2688289f060a62b7b6","observation_id":"c3b30e2b-313e-4239-83d7-e625c6d3e92a","resolution":{"observed_at":"2026-08-10T15:46:47.779439Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2501.13790","last_updated":"2025-05-07T15:34:15Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-11T18:53:52.974479Z","submitted_at":"2025-01-23T16:09:26Z","title":"Local Steps Speed Up Local GD for Heterogeneous Distributed Logistic Regression"},"reference_resolution":{"displayed":47,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":19,"verified_exact":1,"verified_fuzzy":27},"total_outbound_references":47},"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":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 47 of 47 outbound references and 0 inbound Pith citation observations for arXiv:2501.13790."}