{"as_of":"2026-08-08T09:57:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d1e5e440312d55a1feaffdbe64a8799cd22e668eba696ce260070f17c7af2485","coverage":[{"denominator":11,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":11,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T13:33:45.476302Z","state":"measured"},{"denominator":11,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":11,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+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/2505.21695/citation-record","integrity":"/paper/2505.21695/integrity","json":"/paper/2505.21695/citation-record.json","paper":"/paper/2505.21695"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:33:48.020548Z","title":"Federated learning based on dynamic regularization","venue":null,"work_id":"a2c7830e-4488-420a-9ca9-450f8e57e791","year":2021},"citing_paper":{"arxiv_id":"2505.21695","last_updated":"2025-05-27T19:32:00Z","snapshot_observed_at":"2026-08-07T13:22:33.320698Z","submitted_at":"2025-05-27T19:32:00Z","title":"AMSFL: Adaptive Multi-Step Federated Learning via Gradient Difference-Based Error Modeling","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T13:33:44.101610Z"},"links":{"citing_paper":"/paper/2505.21695"},"observation_digest":"sha256:12f1372459f7c96c12ab2fa404c4e2c39f6ed93149d422dd96e046d331745b02","observation_id":"3d426f83-44cf-4676-b1f9-970b8a6438ea","resolution":{"observed_at":"2026-08-07T13:33:48.169060Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:33:47.753309Z","title":"Altomare, D","venue":null,"work_id":"da4cd844-a7f9-4f48-ac7d-5f55940867c1","year":2024},"citing_paper":{"arxiv_id":"2505.21695","last_updated":"2025-05-27T19:32:00Z","snapshot_observed_at":"2026-08-07T13:22:33.320698Z","submitted_at":"2025-05-27T19:32:00Z","title":"AMSFL: Adaptive Multi-Step Federated Learning via Gradient Difference-Based Error Modeling","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T13:33:44.215700Z"},"links":{"citing_paper":"/paper/2505.21695"},"observation_digest":"sha256:8362caba657d9bf80ad27d726e50b027152c0a6bb0c8d7aa8b8cc81eb303166d","observation_id":"efc10033-cb09-4afd-87db-95b2b3a0fb76","resolution":{"observed_at":"2026-08-07T13:33:47.864545Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:33:47.543455Z","title":"Scaffold: Stochastic controlled averaging for federated learning","venue":null,"work_id":"cd9257f6-caf0-4cfc-9afd-09ff2eeac13d","year":2020},"citing_paper":{"arxiv_id":"2505.21695","last_updated":"2025-05-27T19:32:00Z","snapshot_observed_at":"2026-08-07T13:22:33.320698Z","submitted_at":"2025-05-27T19:32:00Z","title":"AMSFL: Adaptive Multi-Step Federated Learning via Gradient Difference-Based Error Modeling","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T13:33:44.310977Z"},"links":{"citing_paper":"/paper/2505.21695"},"observation_digest":"sha256:3ad213d1004aab14c0563dede7075cb4129763d02b6cd294b740293b8bf2a922","observation_id":"597c7514-d8da-4e1d-8a8a-cdd5eaace9a7","resolution":{"observed_at":"2026-08-07T13:33:47.655653Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:33:47.308225Z","title":"Mime: Mimicking centralised stochastic algorithms in federated learning","venue":null,"work_id":"b2461982-462c-4b8c-8114-e88c4eead0c1","year":2021},"citing_paper":{"arxiv_id":"2505.21695","last_updated":"2025-05-27T19:32:00Z","snapshot_observed_at":"2026-08-07T13:22:33.320698Z","submitted_at":"2025-05-27T19:32:00Z","title":"AMSFL: Adaptive Multi-Step Federated Learning via Gradient Difference-Based Error Modeling","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T13:33:44.455739Z"},"links":{"citing_paper":"/paper/2505.21695"},"observation_digest":"sha256:d18939f78dbc09b34df0ce7cf5436bd2e71cee3f1b7a6f580a75fdcd3e73782a","observation_id":"ea009d4a-af5a-472e-89e9-cfdfedbb4d7a","resolution":{"observed_at":"2026-08-07T13:33:47.394017Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:33:47.095472Z","title":"Federated optimization in heterogeneous networks","venue":null,"work_id":"bdc40b1f-d16d-4048-8f67-68bbe9194db2","year":2020},"citing_paper":{"arxiv_id":"2505.21695","last_updated":"2025-05-27T19:32:00Z","snapshot_observed_at":"2026-08-07T13:22:33.320698Z","submitted_at":"2025-05-27T19:32:00Z","title":"AMSFL: Adaptive Multi-Step Federated Learning via Gradient Difference-Based Error Modeling","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T13:33:44.653433Z"},"links":{"citing_paper":"/paper/2505.21695"},"observation_digest":"sha256:f95a07840dcdf3171350bdf395c426e024188e08fd11c521d35a21fd357935c1","observation_id":"d7bb0bd7-0871-4395-8997-605b7a952cf9","resolution":{"observed_at":"2026-08-07T13:33:47.197235Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:33:46.897541Z","title":"Communication- efficient learning of deep networks from decentralized data","venue":null,"work_id":"01b621fb-2494-4456-a9b2-7192bb48c400","year":2017},"citing_paper":{"arxiv_id":"2505.21695","last_updated":"2025-05-27T19:32:00Z","snapshot_observed_at":"2026-08-07T13:22:33.320698Z","submitted_at":"2025-05-27T19:32:00Z","title":"AMSFL: Adaptive Multi-Step Federated Learning via Gradient Difference-Based Error Modeling","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T13:33:44.860120Z"},"links":{"citing_paper":"/paper/2505.21695"},"observation_digest":"sha256:eb32c002e368ed350a112d1ff158103ccad8831d33702cb98f4ed0f3ff3e07a8","observation_id":"d85b1577-254f-4e91-9801-5790e294130c","resolution":{"observed_at":"2026-08-07T13:33:46.994217Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:33:46.620477Z","title":"Communication-efficient distributed optimization using an approximate newton-type method","venue":null,"work_id":"4d8feec6-7f8c-4652-a7a9-1307d4a23233","year":2014},"citing_paper":{"arxiv_id":"2505.21695","last_updated":"2025-05-27T19:32:00Z","snapshot_observed_at":"2026-08-07T13:22:33.320698Z","submitted_at":"2025-05-27T19:32:00Z","title":"AMSFL: Adaptive Multi-Step Federated Learning via Gradient Difference-Based Error Modeling","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T13:33:44.980860Z"},"links":{"citing_paper":"/paper/2505.21695"},"observation_digest":"sha256:2bbee92355c4524c1b4c410e5d3565f9661d375263b0c10dcc3832fc74386e11","observation_id":"d2b4cb94-f8e3-467b-a5b4-d0dea15da7d9","resolution":{"observed_at":"2026-08-07T13:33:46.732727Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:33:46.364802Z","title":"Local sgd converges fast and communicates little","venue":null,"work_id":"6d32bda0-1aa9-4d5f-b33f-69333c3f4ffe","year":2019},"citing_paper":{"arxiv_id":"2505.21695","last_updated":"2025-05-27T19:32:00Z","snapshot_observed_at":"2026-08-07T13:22:33.320698Z","submitted_at":"2025-05-27T19:32:00Z","title":"AMSFL: Adaptive Multi-Step Federated Learning via Gradient Difference-Based Error Modeling","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T13:33:45.065023Z"},"links":{"citing_paper":"/paper/2505.21695"},"observation_digest":"sha256:054f5eef3c0bca06949b5a19cbf531807a8560ed82343cbf6289e03db7f75b5f","observation_id":"8a3fa52a-50a4-4497-a5fc-11bac956e5c8","resolution":{"observed_at":"2026-08-07T13:33:46.499566Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:33:46.058613Z","title":"Tackling the objective inconsistency problem in heterogeneous federated optimization","venue":null,"work_id":"e12c3a4e-b160-4ceb-8b0d-786aabdf614b","year":2020},"citing_paper":{"arxiv_id":"2505.21695","last_updated":"2025-05-27T19:32:00Z","snapshot_observed_at":"2026-08-07T13:22:33.320698Z","submitted_at":"2025-05-27T19:32:00Z","title":"AMSFL: Adaptive Multi-Step Federated Learning via Gradient Difference-Based Error Modeling","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T13:33:45.210175Z"},"links":{"citing_paper":"/paper/2505.21695"},"observation_digest":"sha256:eab808b2bd0cfc33ebfc10ddd27c4458051414a8fc3d6f5d0fcb985e2574633d","observation_id":"6def3558-bc92-49c0-aa78-2b647b9c80be","resolution":{"observed_at":"2026-08-07T13:33:46.256725Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:33:45.863711Z","title":"Op- timizing federated learning on non-iid data with reinforcement learning","venue":null,"work_id":"8e7cf76f-dff7-4e78-a6ca-2b34efeb2649","year":2020},"citing_paper":{"arxiv_id":"2505.21695","last_updated":"2025-05-27T19:32:00Z","snapshot_observed_at":"2026-08-07T13:22:33.320698Z","submitted_at":"2025-05-27T19:32:00Z","title":"AMSFL: Adaptive Multi-Step Federated Learning via Gradient Difference-Based Error Modeling","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T13:33:45.350499Z"},"links":{"citing_paper":"/paper/2505.21695"},"observation_digest":"sha256:a6010c3efca8afdee69b55b2e20c617872ed1d8ddd8435591121fc65ffac7522","observation_id":"b28cc6b1-45ab-420a-8edd-8c287d6a4213","resolution":{"observed_at":"2026-08-07T13:33:45.944794Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-07T13:33:45.626620Z","title":"Disco: Distributed optimization for self-concordant empirical loss","venue":null,"work_id":"b4c5f084-a8b5-4203-8303-862c1dea4519","year":2015},"citing_paper":{"arxiv_id":"2505.21695","last_updated":"2025-05-27T19:32:00Z","snapshot_observed_at":"2026-08-07T13:22:33.320698Z","submitted_at":"2025-05-27T19:32:00Z","title":"AMSFL: Adaptive Multi-Step Federated Learning via Gradient Difference-Based Error Modeling","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T13:33:45.476302Z"},"links":{"citing_paper":"/paper/2505.21695"},"observation_digest":"sha256:7e27b604a4f384b2ff4b326d8a3e921fbb0553a01e781e35c3bdc6d3cfa15b12","observation_id":"8a21d11b-82a2-45af-aa31-0a44b2533e8d","resolution":{"observed_at":"2026-08-07T13:33:45.716503Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2505.21695","last_updated":"2025-05-27T19:32:00Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T13:22:33.320698Z","submitted_at":"2025-05-27T19:32:00Z","title":"AMSFL: Adaptive Multi-Step Federated Learning via Gradient Difference-Based Error Modeling"},"reference_resolution":{"displayed":11,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":11},"total_outbound_references":11},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 11 of 11 outbound references and 0 inbound Pith citation observations for arXiv:2505.21695."}