{"as_of":"2026-08-11T08:46:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d7eaa3ea4fc51c515e00bfee56a57e55c9d8915d6082a5bcfce158a67864c14e","coverage":[{"denominator":42,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":42,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-09T19:54:41.688032Z","state":"measured"},{"denominator":42,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":42,"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/2502.00206/citation-record","integrity":"/paper/2502.00206/integrity","json":"/paper/2502.00206/citation-record.json","paper":"/paper/2502.00206"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"1904.01197","last_updated":"2019-04-02T03:47:28Z","snapshot_observed_at":"2026-07-06T07:43:14.473925Z","submitted_at":"2019-04-02T03:47:28Z","title":"Nested Dithered Quantization for Communication Reduction in Distributed Training","version":1},"cited_work":{"arxiv_id":"1904.01197","doi":null,"metadata_source":"pith","pith_arxiv_id":"1904.01197","snapshot_observed_at":"2026-08-09T19:54:41.896300Z","title":"Nested Dithered Quantization for Communication Reduction in Distributed Training","venue":"cs.DC","work_id":"b8caf9ac-d6d4-4359-849c-26e0a74a7f51","year":2019},"citing_paper":{"arxiv_id":"2502.00206","last_updated":"2025-01-31T22:48:43Z","snapshot_observed_at":"2026-08-09T19:46:34.246723Z","submitted_at":"2025-01-31T22:48:43Z","title":"BICompFL: Stochastic Federated Learning with Bi-Directional Compression","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-09T19:54:41.524085Z"},"links":{"cited_paper":"/paper/1904.01197","citing_paper":"/paper/2502.00206"},"observation_digest":"sha256:3cc6ec3ffa313983d639b069c774804c25decd762bd4e0fdce9e5fb421aefc6d","observation_id":"768df459-a206-4ef4-91ba-d6f34ce29326","resolution":{"observed_at":"2026-08-09T19:54:41.900896Z","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":"2026-08-09T19:54:42.334508Z","title":"QSGD : Communication-efficient SGD via gradient quantization and encoding","venue":null,"work_id":"41639611-c5fd-4148-bd63-134a10bbbb50","year":2017},"citing_paper":{"arxiv_id":"2502.00206","last_updated":"2025-01-31T22:48:43Z","snapshot_observed_at":"2026-08-09T19:46:34.246723Z","submitted_at":"2025-01-31T22:48:43Z","title":"BICompFL: Stochastic Federated Learning with Bi-Directional Compression","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-09T19:54:41.530003Z"},"links":{"citing_paper":"/paper/2502.00206"},"observation_digest":"sha256:8fae5ca7fb5f858f5b0bb04ebb850e46bb5dc127a833b1f42a313dff29c1dc39","observation_id":"bbbbf099-919c-4f76-8dd7-f6eb6a346417","resolution":{"observed_at":"2026-08-09T19:54:42.338757Z","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":"2006.10672","last_updated":"2020-10-07T01:15:06Z","snapshot_observed_at":"2026-08-09T02:11:01.681294Z","submitted_at":"2020-06-18T16:55:20Z","title":"Federated Learning With Quantized Global Model Updates","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.10672","snapshot_observed_at":"2026-08-09T19:54:41.534388Z","title":"Kulkarni, and H","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2502.00206","last_updated":"2025-01-31T22:48:43Z","snapshot_observed_at":"2026-08-09T19:46:34.246723Z","submitted_at":"2025-01-31T22:48:43Z","title":"BICompFL: Stochastic Federated Learning with Bi-Directional Compression","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-09T19:54:41.534388Z"},"links":{"cited_paper":"/paper/2006.10672","citing_paper":"/paper/2502.00206"},"observation_digest":"sha256:57efa16552d8812dd313fe34ed0a5f51c01d3c2beb1301cc24eb0b688cee7703","observation_id":"c0544a38-da4b-4933-876a-86df72b4880f","resolution":{"observed_at":"2026-08-09T19:54:41.534388Z","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":"2026-08-09T19:54:42.321616Z","title":"The sample size required in importance sampling","venue":null,"work_id":"594d5235-b050-4c77-b857-aeed25a2c92a","year":2018},"citing_paper":{"arxiv_id":"2502.00206","last_updated":"2025-01-31T22:48:43Z","snapshot_observed_at":"2026-08-09T19:46:34.246723Z","submitted_at":"2025-01-31T22:48:43Z","title":"BICompFL: Stochastic Federated Learning with Bi-Directional Compression","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-09T19:54:41.539850Z"},"links":{"citing_paper":"/paper/2502.00206"},"observation_digest":"sha256:814c00414e7d47818bed44026237e3a5432ebca0f7d719b2d09e93ba476c09be","observation_id":"7eedc403-1290-4b6a-8395-c447b44200e7","resolution":{"observed_at":"2026-08-09T19:54:42.326498Z","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":"2402.11857","last_updated":"2024-02-19T05:59:09Z","snapshot_observed_at":"2026-07-06T17:32:02.824244Z","submitted_at":"2024-02-19T05:59:09Z","title":"Communication-Efficient Distributed Learning with Local Immediate Error Compensation","version":1},"cited_work":{"arxiv_id":"2402.11857","doi":null,"metadata_source":"pith","pith_arxiv_id":"2402.11857","snapshot_observed_at":"2026-08-09T19:54:41.867427Z","title":"Communication-Efficient Distributed Learning with Local Immediate Error Compensation","venue":"cs.LG","work_id":"f98025af-327f-4db0-b00c-15eb4a557070","year":2024},"citing_paper":{"arxiv_id":"2502.00206","last_updated":"2025-01-31T22:48:43Z","snapshot_observed_at":"2026-08-09T19:46:34.246723Z","submitted_at":"2025-01-31T22:48:43Z","title":"BICompFL: Stochastic Federated Learning with Bi-Directional Compression","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-09T19:54:41.544135Z"},"links":{"cited_paper":"/paper/2402.11857","citing_paper":"/paper/2502.00206"},"observation_digest":"sha256:d2aa79cc70adc1d78245f250c1cd2974c89a22a2c233c504b95a648d34e4f9fb","observation_id":"e591b6f1-2103-41dd-905c-0a5e1eb3bf8c","resolution":{"observed_at":"2026-08-09T19:54:41.873974Z","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":"2026-08-09T19:54:42.302358Z","title":"Elements of information theory","venue":null,"work_id":"898a006d-b98e-488e-9ed0-7b7a8856bf51","year":2006},"citing_paper":{"arxiv_id":"2502.00206","last_updated":"2025-01-31T22:48:43Z","snapshot_observed_at":"2026-08-09T19:46:34.246723Z","submitted_at":"2025-01-31T22:48:43Z","title":"BICompFL: Stochastic Federated Learning with Bi-Directional Compression","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-09T19:54:41.548947Z"},"links":{"citing_paper":"/paper/2502.00206"},"observation_digest":"sha256:9fa0160947eb72fe610ddbca47cbd036260d64b52cae30466115fb43f533f6bc","observation_id":"4b20f330-b052-41d9-a8f2-527845e7351a","resolution":{"observed_at":"2026-08-09T19:54:42.307945Z","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":"2026-08-09T19:54:42.280663Z","title":"DoCoFL : Downlink compression for cross-device federated learning","venue":null,"work_id":"12939880-d2d1-4f9a-a003-374783a35164","year":2023},"citing_paper":{"arxiv_id":"2502.00206","last_updated":"2025-01-31T22:48:43Z","snapshot_observed_at":"2026-08-09T19:46:34.246723Z","submitted_at":"2025-01-31T22:48:43Z","title":"BICompFL: Stochastic Federated Learning with Bi-Directional Compression","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-09T19:54:41.553337Z"},"links":{"citing_paper":"/paper/2502.00206"},"observation_digest":"sha256:cf931449661f96bbc00530db03f026da5f1059cc5822c28cd234b0d254290bd5","observation_id":"1744da45-9161-4912-9f98-9a5d7a5643b0","resolution":{"observed_at":"2026-08-09T19:54:42.290468Z","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":"2026-08-09T19:54:41.557577Z","title":"The lottery ticket hypothesis: Finding sparse, trainable neural networks","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2502.00206","last_updated":"2025-01-31T22:48:43Z","snapshot_observed_at":"2026-08-09T19:46:34.246723Z","submitted_at":"2025-01-31T22:48:43Z","title":"BICompFL: Stochastic Federated Learning with Bi-Directional Compression","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-09T19:54:41.557577Z"},"links":{"citing_paper":"/paper/2502.00206"},"observation_digest":"sha256:07edc398c133decf497d1de080268243e91cef1b7bd1319fdfde2eea17849d75","observation_id":"5c4da31c-cee0-48a7-90e6-46be2e9fb03d","resolution":{"observed_at":"2026-08-09T19:54:41.557577Z","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":"2026-08-09T19:54:42.256323Z","title":"vqSGD : Vector quantized stochastic gradient descent","venue":null,"work_id":"2851e9e9-c01d-40bc-a865-0e4954dde7d3","year":2021},"citing_paper":{"arxiv_id":"2502.00206","last_updated":"2025-01-31T22:48:43Z","snapshot_observed_at":"2026-08-09T19:46:34.246723Z","submitted_at":"2025-01-31T22:48:43Z","title":"BICompFL: Stochastic Federated Learning with Bi-Directional Compression","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-09T19:54:41.561959Z"},"links":{"citing_paper":"/paper/2502.00206"},"observation_digest":"sha256:cd095fb8c9df153e867067d11b834b1911417add7c47599c8abae9608a08050e","observation_id":"9438079b-ffd7-40ba-923f-591e66a144ac","resolution":{"observed_at":"2026-08-09T19:54:42.261319Z","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":"2026-08-09T19:54:42.242703Z","title":"EF21-P and friends: Improved theoretical communication complexity for distributed optimization with bidirectional compression","venue":null,"work_id":"e98f748d-1323-4b36-827e-ed7fbd4d396f","year":2023},"citing_paper":{"arxiv_id":"2502.00206","last_updated":"2025-01-31T22:48:43Z","snapshot_observed_at":"2026-08-09T19:46:34.246723Z","submitted_at":"2025-01-31T22:48:43Z","title":"BICompFL: Stochastic Federated Learning with Bi-Directional Compression","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-09T19:54:41.566297Z"},"links":{"citing_paper":"/paper/2502.00206"},"observation_digest":"sha256:830fb1bcf10143a1ee6edc400aff5da68874f5a6f5df7fb8fe065c48c20c36a5","observation_id":"ddc12b13-deed-43bf-a068-eebd9bbbfc0b","resolution":{"observed_at":"2026-08-09T19:54:42.247352Z","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":"2402.06412","last_updated":"2024-11-02T18:54:03Z","snapshot_observed_at":"2026-08-07T04:04:18.626026Z","submitted_at":"2024-02-09T13:58:33Z","title":"Improving the Worst-Case Bidirectional Communication Complexity for Nonconvex Distributed Optimization under Function Similarity","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.06412","snapshot_observed_at":"2026-08-09T19:54:41.570533Z","title":"Improving the worst-case bidirectional communication complexity for nonconvex distributed optimization under function similarity","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.00206","last_updated":"2025-01-31T22:48:43Z","snapshot_observed_at":"2026-08-09T19:46:34.246723Z","submitted_at":"2025-01-31T22:48:43Z","title":"BICompFL: Stochastic Federated Learning with Bi-Directional Compression","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-09T19:54:41.570533Z"},"links":{"cited_paper":"/paper/2402.06412","citing_paper":"/paper/2502.00206"},"observation_digest":"sha256:d34e228c01fe6a53c91b7ee13b79b88d1e8adf205c5aaffca4845c66bf37e2d5","observation_id":"d642548d-837f-453f-8cae-b46953b186fd","resolution":{"observed_at":"2026-08-09T19:54:41.570533Z","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":"2026-08-09T19:54:42.229677Z","title":"Minimal random code learning: Getting bits back from compressed model parameters","venue":null,"work_id":"f101842a-026e-4dfc-95f0-13731ebddca8","year":2019},"citing_paper":{"arxiv_id":"2502.00206","last_updated":"2025-01-31T22:48:43Z","snapshot_observed_at":"2026-08-09T19:46:34.246723Z","submitted_at":"2025-01-31T22:48:43Z","title":"BICompFL: Stochastic Federated Learning with Bi-Directional Compression","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-09T19:54:41.574516Z"},"links":{"citing_paper":"/paper/2502.00206"},"observation_digest":"sha256:6dbe8572baa37c28d3f003929ded728a76f87b70bd79eff0499728888606723c","observation_id":"1197d661-33d5-4340-8e74-75aed0018dbb","resolution":{"observed_at":"2026-08-09T19:54:42.234124Z","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":"2026-08-09T19:54:42.217201Z","title":"Natural compression for distributed deep learning","venue":null,"work_id":"a1e3c84e-5835-4173-8a98-af33be371837","year":2022},"citing_paper":{"arxiv_id":"2502.00206","last_updated":"2025-01-31T22:48:43Z","snapshot_observed_at":"2026-08-09T19:46:34.246723Z","submitted_at":"2025-01-31T22:48:43Z","title":"BICompFL: Stochastic Federated Learning with Bi-Directional Compression","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-09T19:54:41.577453Z"},"links":{"citing_paper":"/paper/2502.00206"},"observation_digest":"sha256:b7a598fe52b46b79ccfd5a19c932a36ae4815f458abfa10ccccd3c7f825cf6d8","observation_id":"c8eb371a-1159-43f6-9484-d9a5d40b5d50","resolution":{"observed_at":"2026-08-09T19:54:42.221432Z","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":"2026-08-09T19:54:42.202975Z","title":"Lower bounds and nearly optimal algorithms in distributed learning with communication compression","venue":null,"work_id":"8fe344df-305b-4924-a026-101f16f2976d","year":2022},"citing_paper":{"arxiv_id":"2502.00206","last_updated":"2025-01-31T22:48:43Z","snapshot_observed_at":"2026-08-09T19:46:34.246723Z","submitted_at":"2025-01-31T22:48:43Z","title":"BICompFL: Stochastic Federated Learning with Bi-Directional Compression","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-09T19:54:41.580323Z"},"links":{"citing_paper":"/paper/2502.00206"},"observation_digest":"sha256:88471e2caa325a38319d6acb088dc04f51efb0127dea31a190b8d0685ecb94bb","observation_id":"c1421abc-9761-4978-a8dc-cf534f98849c","resolution":{"observed_at":"2026-08-09T19:54:42.207805Z","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":"2026-08-09T19:54:42.189085Z","title":"Sparse random networks for communication-efficient federated learning","venue":null,"work_id":"7f390e05-30d8-4d6d-9bbc-d2b7ae465f64","year":2023},"citing_paper":{"arxiv_id":"2502.00206","last_updated":"2025-01-31T22:48:43Z","snapshot_observed_at":"2026-08-09T19:46:34.246723Z","submitted_at":"2025-01-31T22:48:43Z","title":"BICompFL: Stochastic Federated Learning with Bi-Directional Compression","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-09T19:54:41.583587Z"},"links":{"citing_paper":"/paper/2502.00206"},"observation_digest":"sha256:b751aa025446aed1a0f7d15879ebb235d8b90c577993535f2a0aa5aca9736cca","observation_id":"dbca338a-e874-4d10-9f08-8b671357e528","resolution":{"observed_at":"2026-08-09T19:54:42.193740Z","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":"2026-08-09T19:54:42.173404Z","title":"Adaptive compression in federated learning via side information","venue":null,"work_id":"8721b552-902d-4c8e-94b2-f8b99396f267","year":2024},"citing_paper":{"arxiv_id":"2502.00206","last_updated":"2025-01-31T22:48:43Z","snapshot_observed_at":"2026-08-09T19:46:34.246723Z","submitted_at":"2025-01-31T22:48:43Z","title":"BICompFL: Stochastic Federated Learning with Bi-Directional Compression","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-09T19:54:41.587072Z"},"links":{"citing_paper":"/paper/2502.00206"},"observation_digest":"sha256:7fef37660def8390683ee6f485c032a0362b1b1d79bbdd92f5449514bdcbf8a8","observation_id":"3d83b14e-be02-437e-8b1f-63d83bd34f47","resolution":{"observed_at":"2026-08-09T19:54:42.177996Z","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":"2026-08-09T19:54:42.158524Z","title":"Error feedback fixes SignSGD and other gradient compression schemes","venue":null,"work_id":"2e4a7e21-7046-42a8-ab41-878cb0b14e71","year":2019},"citing_paper":{"arxiv_id":"2502.00206","last_updated":"2025-01-31T22:48:43Z","snapshot_observed_at":"2026-08-09T19:46:34.246723Z","submitted_at":"2025-01-31T22:48:43Z","title":"BICompFL: Stochastic Federated Learning with Bi-Directional Compression","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-09T19:54:41.590705Z"},"links":{"citing_paper":"/paper/2502.00206"},"observation_digest":"sha256:f1ff00876ddbba51185e6e7bd0ef279ce8dee69929e31175c0ef6037f6d8bcbd","observation_id":"3a3cb79c-e132-4227-bf0e-1a5454dd274d","resolution":{"observed_at":"2026-08-09T19:54:42.163882Z","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":"2026-08-09T19:54:41.593996Z","title":"Adam: A method for stochastic optimization","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2502.00206","last_updated":"2025-01-31T22:48:43Z","snapshot_observed_at":"2026-08-09T19:46:34.246723Z","submitted_at":"2025-01-31T22:48:43Z","title":"BICompFL: Stochastic Federated Learning with Bi-Directional Compression","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-09T19:54:41.593996Z"},"links":{"citing_paper":"/paper/2502.00206"},"observation_digest":"sha256:59a5d2bf1bca09fc80bfe07e84c8fe352830db0a6969e0a72873ffc71c78e5f0","observation_id":"edad39fd-e353-4b65-9a5f-ac233568b08d","resolution":{"observed_at":"2026-08-09T19:54:41.593996Z","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":"2026-08-09T19:54:41.597375Z","title":"Lecun, L","venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2502.00206","last_updated":"2025-01-31T22:48:43Z","snapshot_observed_at":"2026-08-09T19:46:34.246723Z","submitted_at":"2025-01-31T22:48:43Z","title":"BICompFL: Stochastic Federated Learning with Bi-Directional Compression","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-09T19:54:41.597375Z"},"links":{"citing_paper":"/paper/2502.00206"},"observation_digest":"sha256:5f04a7cd10e0adec8391031bf8794da45e065ed8042e29228847f8307a3ffbcb","observation_id":"40288b40-a1c6-4297-b25c-300e14b04928","resolution":{"observed_at":"2026-08-09T19:54:41.597375Z","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":"2026-08-09T19:54:42.131413Z","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","venue":null,"work_id":"f9541936-f718-4e7c-b534-95b8106b4bee","year":2017},"citing_paper":{"arxiv_id":"2502.00206","last_updated":"2025-01-31T22:48:43Z","snapshot_observed_at":"2026-08-09T19:46:34.246723Z","submitted_at":"2025-01-31T22:48:43Z","title":"BICompFL: Stochastic Federated Learning with Bi-Directional Compression","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-09T19:54:41.601021Z"},"links":{"citing_paper":"/paper/2502.00206"},"observation_digest":"sha256:dbc99f6adbd751078fe0a6af7e092bb19916a851bf1504749e2f848873a02813","observation_id":"a0d13c6c-7aaa-45d2-99f7-0960ee97c418","resolution":{"observed_at":"2026-08-09T19:54:42.136283Z","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":"2006.14591","last_updated":"2022-06-19T15:40:37Z","snapshot_observed_at":"2026-07-06T09:32:48.916535Z","submitted_at":"2020-06-25T17:37:45Z","title":"Bidirectional compression in heterogeneous settings for distributed or federated learning with partial participation: tight convergence guarantees","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.14591","snapshot_observed_at":"2026-08-09T19:54:41.604681Z","title":"Bidirectional compression in heterogeneous settings for distributed or federated learning with partial participation: tight convergence guarantees","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2502.00206","last_updated":"2025-01-31T22:48:43Z","snapshot_observed_at":"2026-08-09T19:46:34.246723Z","submitted_at":"2025-01-31T22:48:43Z","title":"BICompFL: Stochastic Federated Learning with Bi-Directional Compression","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-09T19:54:41.604681Z"},"links":{"cited_paper":"/paper/2006.14591","citing_paper":"/paper/2502.00206"},"observation_digest":"sha256:b2d3d4bc8737a7344c414a524a27a464e724baabf1a73387ab6d5c9670df14ad","observation_id":"3f2e247e-b4ff-40a3-b8e9-d6907decc848","resolution":{"observed_at":"2026-08-09T19:54:41.604681Z","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":"2026-08-09T19:54:42.119771Z","title":"Preserved central model for faster bidirectional compression in distributed settings","venue":null,"work_id":"d94df496-9bf4-48c8-a559-0d6da8976a13","year":2021},"citing_paper":{"arxiv_id":"2502.00206","last_updated":"2025-01-31T22:48:43Z","snapshot_observed_at":"2026-08-09T19:46:34.246723Z","submitted_at":"2025-01-31T22:48:43Z","title":"BICompFL: Stochastic Federated Learning with Bi-Directional Compression","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-09T19:54:41.609333Z"},"links":{"citing_paper":"/paper/2502.00206"},"observation_digest":"sha256:beb6ca72463e948471ec28db8e0bc9c9f5cc166e445807f6598b5bccffe079c6","observation_id":"5609cb75-25e5-4179-8e30-b573419491b1","resolution":{"observed_at":"2026-08-09T19:54:42.124185Z","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":"2026-08-09T19:54:42.105703Z","title":"What's hidden in a randomly weighted neural network? In IEEE/CVF conference on computer vision and pattern recognition, pp.\\ 11893--11902, 2020","venue":null,"work_id":"1885d923-a3fe-42e6-90b9-d551f6e24f30","year":2020},"citing_paper":{"arxiv_id":"2502.00206","last_updated":"2025-01-31T22:48:43Z","snapshot_observed_at":"2026-08-09T19:46:34.246723Z","submitted_at":"2025-01-31T22:48:43Z","title":"BICompFL: Stochastic Federated Learning with Bi-Directional Compression","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-09T19:54:41.612993Z"},"links":{"citing_paper":"/paper/2502.00206"},"observation_digest":"sha256:5d4b066891addd58b110ddc1c1a5754bc6cf5b8ea018e1b2b34f5e43a9917562","observation_id":"5d15b3da-97d1-4827-8e3e-dac0f17246d3","resolution":{"observed_at":"2026-08-09T19:54:42.110706Z","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":"2026-08-09T19:54:42.092608Z","title":"Ef21: A new, simpler, theoretically better, and practically faster error feedback","venue":null,"work_id":"e365cec4-4dc2-4e26-a98e-4d3ccfc049ea","year":2021},"citing_paper":{"arxiv_id":"2502.00206","last_updated":"2025-01-31T22:48:43Z","snapshot_observed_at":"2026-08-09T19:46:34.246723Z","submitted_at":"2025-01-31T22:48:43Z","title":"BICompFL: Stochastic Federated Learning with Bi-Directional Compression","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-09T19:54:41.617180Z"},"links":{"citing_paper":"/paper/2502.00206"},"observation_digest":"sha256:b3677460d845ad0dfd34532c789e79bdd9193835eae13d603aac2b21438c873f","observation_id":"305c1acf-06ae-4e86-bd4e-e1a8382940ff","resolution":{"observed_at":"2026-08-09T19:54:42.096697Z","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":"2026-08-09T19:54:42.079750Z","title":"1-bit stochastic gradient descent and its application to data-parallel distributed training of speech DNNs","venue":null,"work_id":"ef6c2544-ade1-4c29-8700-9ba1fa2867cc","year":2014},"citing_paper":{"arxiv_id":"2502.00206","last_updated":"2025-01-31T22:48:43Z","snapshot_observed_at":"2026-08-09T19:46:34.246723Z","submitted_at":"2025-01-31T22:48:43Z","title":"BICompFL: Stochastic Federated Learning with Bi-Directional Compression","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-09T19:54:41.621624Z"},"links":{"citing_paper":"/paper/2502.00206"},"observation_digest":"sha256:14efd3d00fa811ea81e07c39b78a6a6d7017ad08137b0ddfd9a90c874db12e24","observation_id":"c9c3d054-2705-4f05-8da5-e0a8708a2630","resolution":{"observed_at":"2026-08-09T19:54:42.084260Z","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":"2026-08-09T19:54:42.068608Z","title":"A distributed synchronous SGD algorithm with global top-k sparsification for low bandwidth networks","venue":null,"work_id":"0aebdaac-6f0c-4c2c-98c5-64d4337e92a8","year":2019},"citing_paper":{"arxiv_id":"2502.00206","last_updated":"2025-01-31T22:48:43Z","snapshot_observed_at":"2026-08-09T19:46:34.246723Z","submitted_at":"2025-01-31T22:48:43Z","title":"BICompFL: Stochastic Federated Learning with Bi-Directional Compression","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-09T19:54:41.625697Z"},"links":{"citing_paper":"/paper/2502.00206"},"observation_digest":"sha256:58ceb1e4b2719f7de7b7b73e5aa65f5daa54b2154139a822950ccf2cad753d97","observation_id":"6daea999-c4c3-49d8-a233-e43fc25bc246","resolution":{"observed_at":"2026-08-09T19:54:42.072635Z","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":"2026-08-09T19:54:42.056252Z","title":"Importance sampling: Applications in communications and detection","venue":null,"work_id":"56ec5e49-1f63-47cd-8139-a38a46f7b2b9","year":2002},"citing_paper":{"arxiv_id":"2502.00206","last_updated":"2025-01-31T22:48:43Z","snapshot_observed_at":"2026-08-09T19:46:34.246723Z","submitted_at":"2025-01-31T22:48:43Z","title":"BICompFL: Stochastic Federated Learning with Bi-Directional Compression","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-09T19:54:41.629456Z"},"links":{"citing_paper":"/paper/2502.00206"},"observation_digest":"sha256:1f6bbe90ce59a1c5ea63bc85218f4e529ed4c39e274aa170cae1cf68101f84e7","observation_id":"ad57469a-3441-448d-90fe-a7ec5795a9fc","resolution":{"observed_at":"2026-08-09T19:54:42.060812Z","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":"2026-08-09T19:54:42.044974Z","title":"Sparsified SGD with memory","venue":null,"work_id":"e2011cf6-6181-4c03-9dea-bc142b36cccc","year":2018},"citing_paper":{"arxiv_id":"2502.00206","last_updated":"2025-01-31T22:48:43Z","snapshot_observed_at":"2026-08-09T19:46:34.246723Z","submitted_at":"2025-01-31T22:48:43Z","title":"BICompFL: Stochastic Federated Learning with Bi-Directional Compression","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-09T19:54:41.633587Z"},"links":{"citing_paper":"/paper/2502.00206"},"observation_digest":"sha256:4ab68966ccefd7b2b5448a81985407c020247b04c45bc748863345f1f974e97b","observation_id":"90fa7a00-b238-42e0-a83e-151e7e478d68","resolution":{"observed_at":"2026-08-09T19:54:42.048638Z","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":"2026-08-09T19:54:42.033828Z","title":"Doublesqueeze: Parallel stochastic gradient descent with double-pass error-compensated compression","venue":null,"work_id":"6445356b-3896-4cf6-bfe6-faefafd08ac4","year":2019},"citing_paper":{"arxiv_id":"2502.00206","last_updated":"2025-01-31T22:48:43Z","snapshot_observed_at":"2026-08-09T19:46:34.246723Z","submitted_at":"2025-01-31T22:48:43Z","title":"BICompFL: Stochastic Federated Learning with Bi-Directional Compression","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-09T19:54:41.637466Z"},"links":{"citing_paper":"/paper/2502.00206"},"observation_digest":"sha256:36e8c6efe49d70cdb68297bc91df02e38658ef1cdc59a57985f0fba018931c10","observation_id":"5973b717-b063-4588-b39c-0eb13fd9a874","resolution":{"observed_at":"2026-08-09T19:54:42.038213Z","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":"2026-08-09T19:54:42.021990Z","title":"DP - REC : Private & communication-efficient federated learning, 2022","venue":null,"work_id":"a6d4f3e0-28d6-4cf5-a22c-e77445e48a2d","year":2022},"citing_paper":{"arxiv_id":"2502.00206","last_updated":"2025-01-31T22:48:43Z","snapshot_observed_at":"2026-08-09T19:46:34.246723Z","submitted_at":"2025-01-31T22:48:43Z","title":"BICompFL: Stochastic Federated Learning with Bi-Directional Compression","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-09T19:54:41.641433Z"},"links":{"citing_paper":"/paper/2502.00206"},"observation_digest":"sha256:03f85aafb9687402f00dfcf3513e0b7e5547b89348466f3bffde7e0f1049eccc","observation_id":"194fa0e1-b08d-4a3a-8510-20524fb40901","resolution":{"observed_at":"2026-08-09T19:54:42.026587Z","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":"2026-08-09T19:54:42.008572Z","title":"2Direction: theoretically faster distributed training with bidirectional communication compression","venue":null,"work_id":"f80282bd-b663-4404-9bda-70096dc8cef6","year":2023},"citing_paper":{"arxiv_id":"2502.00206","last_updated":"2025-01-31T22:48:43Z","snapshot_observed_at":"2026-08-09T19:46:34.246723Z","submitted_at":"2025-01-31T22:48:43Z","title":"BICompFL: Stochastic Federated Learning with Bi-Directional Compression","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-09T19:54:41.645137Z"},"links":{"citing_paper":"/paper/2502.00206"},"observation_digest":"sha256:e17446c648777528c1eba2d3351846a713c79c26dbc68ccb8f49c75d92d93594","observation_id":"bc4e7ecd-bf57-4652-9ce9-f7f9b54647c3","resolution":{"observed_at":"2026-08-09T19:54:42.014188Z","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":"2026-08-09T19:54:41.996101Z","title":"QLSD: quantised langevin stochastic dynamics for bayesian federated learning","venue":null,"work_id":"502dfe6f-c4cd-4ca8-a9b1-f12433e21b17","year":2022},"citing_paper":{"arxiv_id":"2502.00206","last_updated":"2025-01-31T22:48:43Z","snapshot_observed_at":"2026-08-09T19:46:34.246723Z","submitted_at":"2025-01-31T22:48:43Z","title":"BICompFL: Stochastic Federated Learning with Bi-Directional Compression","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-09T19:54:41.648757Z"},"links":{"citing_paper":"/paper/2502.00206"},"observation_digest":"sha256:50d88f39c6ef546c7facabae35f29a352fdbf21f2740718e88eeae1b04c2b9ec","observation_id":"d62d2772-81c6-478e-ad22-220571b9d692","resolution":{"observed_at":"2026-08-09T19:54:42.000723Z","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":"2026-08-09T19:54:41.652442Z","title":"Gradient sparsification for communication-efficient distributed optimization","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2502.00206","last_updated":"2025-01-31T22:48:43Z","snapshot_observed_at":"2026-08-09T19:46:34.246723Z","submitted_at":"2025-01-31T22:48:43Z","title":"BICompFL: Stochastic Federated Learning with Bi-Directional Compression","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-09T19:54:41.652442Z"},"links":{"citing_paper":"/paper/2502.00206"},"observation_digest":"sha256:903bc6a3df1e8f3f4126235b99fd9983584bdc73cfa07c553c4032cf4a2044d1","observation_id":"89cce0e1-7dc3-47ab-a84a-5768325f172d","resolution":{"observed_at":"2026-08-09T19:54:41.652442Z","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":"2026-08-09T19:54:41.973028Z","title":"Multi-armed bandits with self-information rewards","venue":null,"work_id":"d20fbff5-529c-4091-bfbe-f9541a3988d2","year":2023},"citing_paper":{"arxiv_id":"2502.00206","last_updated":"2025-01-31T22:48:43Z","snapshot_observed_at":"2026-08-09T19:46:34.246723Z","submitted_at":"2025-01-31T22:48:43Z","title":"BICompFL: Stochastic Federated Learning with Bi-Directional Compression","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-09T19:54:41.656142Z"},"links":{"citing_paper":"/paper/2502.00206"},"observation_digest":"sha256:6b5f83fcdf68cc6c211bee455a9ae677b150e6b0acc6172dcad422f71c792c90","observation_id":"3a44b7c4-1df1-429a-aa2f-42bc71a9c06a","resolution":{"observed_at":"2026-08-09T19:54:41.977716Z","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":"2026-08-09T19:54:41.659830Z","title":"A survey on federated learning: challenges and applications","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.00206","last_updated":"2025-01-31T22:48:43Z","snapshot_observed_at":"2026-08-09T19:46:34.246723Z","submitted_at":"2025-01-31T22:48:43Z","title":"BICompFL: Stochastic Federated Learning with Bi-Directional Compression","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-09T19:54:41.659830Z"},"links":{"citing_paper":"/paper/2502.00206"},"observation_digest":"sha256:9863fb31bff532d7c8c66ecb03194bb7cb767f47ce7e562bd9b80cc9d4506a97","observation_id":"9180f107-4964-42f2-a330-3ee6e4d22e9f","resolution":{"observed_at":"2026-08-09T19:54:41.659830Z","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":"2026-08-09T19:54:41.954166Z","title":"TernGrad : Ternary gradients to reduce communication in distributed deep learning","venue":null,"work_id":"063c6a21-be79-418a-805e-bb37d71c68db","year":2017},"citing_paper":{"arxiv_id":"2502.00206","last_updated":"2025-01-31T22:48:43Z","snapshot_observed_at":"2026-08-09T19:46:34.246723Z","submitted_at":"2025-01-31T22:48:43Z","title":"BICompFL: Stochastic Federated Learning with Bi-Directional Compression","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-09T19:54:41.664403Z"},"links":{"citing_paper":"/paper/2502.00206"},"observation_digest":"sha256:1caf7d96fd3924b7b18feada4f3f7294106ff8a6e19d7d10dbfc47aebf04db9e","observation_id":"d22ba350-2a1a-47de-8d5e-75edd641c414","resolution":{"observed_at":"2026-08-09T19:54:41.958484Z","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":"2026-08-09T19:54:41.940961Z","title":"Cser: Communication-efficient sgd with error reset","venue":null,"work_id":"1288e089-c0e9-41e4-9d25-92ee77435634","year":2020},"citing_paper":{"arxiv_id":"2502.00206","last_updated":"2025-01-31T22:48:43Z","snapshot_observed_at":"2026-08-09T19:46:34.246723Z","submitted_at":"2025-01-31T22:48:43Z","title":"BICompFL: Stochastic Federated Learning with Bi-Directional Compression","version":1},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-09T19:54:41.668174Z"},"links":{"citing_paper":"/paper/2502.00206"},"observation_digest":"sha256:4e0fb753bef53e5323890eb534ea436186cc32d8cd4f7d27aa6ed4e5d843350b","observation_id":"5662cd5f-1937-4186-a87f-236f7c198526","resolution":{"observed_at":"2026-08-09T19:54:41.944787Z","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":"2026-08-09T19:54:41.930862Z","title":"A survey on federated learning","venue":null,"work_id":"78e951a3-85b1-4be3-9a21-e842f28168fd","year":2021},"citing_paper":{"arxiv_id":"2502.00206","last_updated":"2025-01-31T22:48:43Z","snapshot_observed_at":"2026-08-09T19:46:34.246723Z","submitted_at":"2025-01-31T22:48:43Z","title":"BICompFL: Stochastic Federated Learning with Bi-Directional Compression","version":1},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-09T19:54:41.671779Z"},"links":{"citing_paper":"/paper/2502.00206"},"observation_digest":"sha256:bdb01f8698d427631cd46663ad0c09624016656d87386edb36ff3b6242a6a7c3","observation_id":"0a7a07b8-690f-4cc1-b1b2-722a7c2000b8","resolution":{"observed_at":"2026-08-09T19:54:41.934256Z","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":"2026-08-09T19:54:41.920666Z","title":"Communication-efficient distributed blockwise momentum SGD with error-feedback","venue":null,"work_id":"29a0bec3-c6bd-4f7a-925a-ce73b5274071","year":2019},"citing_paper":{"arxiv_id":"2502.00206","last_updated":"2025-01-31T22:48:43Z","snapshot_observed_at":"2026-08-09T19:46:34.246723Z","submitted_at":"2025-01-31T22:48:43Z","title":"BICompFL: Stochastic Federated Learning with Bi-Directional Compression","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-09T19:54:41.675401Z"},"links":{"citing_paper":"/paper/2502.00206"},"observation_digest":"sha256:94786a36daff2f4ed01b5fa63a07453cee11a7a9c6065fc6306c20796efc1c6d","observation_id":"34985e4d-e2a7-42e7-a58b-594356912909","resolution":{"observed_at":"2026-08-09T19:54:41.924237Z","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":"2026-08-09T19:54:41.679052Z","title":"@esa (Ref","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.00206","last_updated":"2025-01-31T22:48:43Z","snapshot_observed_at":"2026-08-09T19:46:34.246723Z","submitted_at":"2025-01-31T22:48:43Z","title":"BICompFL: Stochastic Federated Learning with Bi-Directional Compression","version":1},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-09T19:54:41.679052Z"},"links":{"citing_paper":"/paper/2502.00206"},"observation_digest":"sha256:eb7166de88ba39cc023067631d03cc1771ebca3def8f3201ffd78a54e8fc52d1","observation_id":"22c68df7-9592-445c-84bd-66b5758b4926","resolution":{"observed_at":"2026-08-09T19:54:41.679052Z","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":"2026-08-09T19:54:41.683927Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.00206","last_updated":"2025-01-31T22:48:43Z","snapshot_observed_at":"2026-08-09T19:46:34.246723Z","submitted_at":"2025-01-31T22:48:43Z","title":"BICompFL: Stochastic Federated Learning with Bi-Directional Compression","version":1},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-09T19:54:41.683927Z"},"links":{"citing_paper":"/paper/2502.00206"},"observation_digest":"sha256:39ed18a2b36d8e1554cc0d54d80a7ffd565e7217d554dc4a9bcd964a73f36eb4","observation_id":"f0abb1d8-6c9c-498c-ac14-47320f2148bc","resolution":{"observed_at":"2026-08-09T19:54:41.683927Z","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":"2026-08-09T19:54:41.688032Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.00206","last_updated":"2025-01-31T22:48:43Z","snapshot_observed_at":"2026-08-09T19:46:34.246723Z","submitted_at":"2025-01-31T22:48:43Z","title":"BICompFL: Stochastic Federated Learning with Bi-Directional Compression","version":1},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-09T19:54:41.688032Z"},"links":{"citing_paper":"/paper/2502.00206"},"observation_digest":"sha256:1270e1f5c066af6b66f0d8d1c818559cb0ab2f6ff84ae3df4a63dc7fb214db89","observation_id":"cdc28e84-3747-4859-ba53-63dfce5dd274","resolution":{"observed_at":"2026-08-09T19:54:41.688032Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2502.00206","last_updated":"2025-01-31T22:48:43Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-09T19:46:34.246723Z","submitted_at":"2025-01-31T22:48:43Z","title":"BICompFL: Stochastic Federated Learning with Bi-Directional Compression"},"reference_resolution":{"displayed":42,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":11,"verified_exact":2,"verified_fuzzy":29},"total_outbound_references":42},"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 11 August 2026, this Paper Citation Record lists 42 of 42 outbound references and 0 inbound Pith citation observations for arXiv:2502.00206."}