{"as_of":"2026-08-09T13:56:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:483e6e38569d0a7ccbfb3adedd5503c6df4ad3dc1b95434eaadfab5400ccf945","coverage":[{"denominator":64,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":64,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-04T18:10:19.614372Z","state":"measured"},{"denominator":64,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":64,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+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/2509.10161/citation-record","integrity":"/paper/2509.10161/integrity","json":"/paper/2509.10161/citation-record.json","paper":"/paper/2509.10161"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T18:10:16.143798Z","title":"Qsgd: Communication-efficient sgd via gradient quantization and encoding.Advances in neural information processing systems, 30, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-04T18:10:16.143798Z"},"links":{"citing_paper":"/paper/2509.10161"},"observation_digest":"sha256:9fbee38aead581cf585436bbc2b8403e73a087dddd187910313445a4dde7cb18","observation_id":"cb5e1b2a-dde9-4d53-be94-7af99566f391","resolution":{"observed_at":"2026-08-04T18:10:16.143798Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"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":"2026-08-04T18:10:16.212049Z","title":"Kulkarni, and H","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-04T18:10:16.212049Z"},"links":{"cited_paper":"/paper/2006.10672","citing_paper":"/paper/2509.10161"},"observation_digest":"sha256:35056b7819f34adf12a0477f2f9c3d55c9cd2ffb6602da737b935754683f0c28","observation_id":"1b800ef2-8214-49ed-bd55-23c4fa214aab","resolution":{"observed_at":"2026-08-04T18:10:16.212049Z","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":"2026-08-04T18:10:16.274425Z","title":"Post training 4- bit quantization of convolutional networks for rapid-deployment","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-04T18:10:16.274425Z"},"links":{"citing_paper":"/paper/2509.10161"},"observation_digest":"sha256:b10e23d1abcca82634b0b4c337f50e64d015f07cc43b5e63031401c5f17e3c7e","observation_id":"291e0cc5-1fbc-496b-8835-44e2c42cebda","resolution":{"observed_at":"2026-08-04T18:10:16.274425Z","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":"2026-08-04T18:10:16.354731Z","title":"signsgd with majority vote is communication efficient and fault tolerant","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-04T18:10:16.354731Z"},"links":{"citing_paper":"/paper/2509.10161"},"observation_digest":"sha256:2a747e48de7be0114f1a52b457e62570bf903e25acf7ca8de88a34b4ee8373f1","observation_id":"983e4a74-b539-49c0-82c2-d5dc07bf6950","resolution":{"observed_at":"2026-08-04T18:10:16.354731Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2007.14390","last_updated":"2022-03-05T20:30:32Z","snapshot_observed_at":"2026-07-06T09:42:35.058716Z","submitted_at":"2020-07-28T17:59:07Z","title":"Flower: A Friendly Federated Learning Research Framework","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2007.14390","snapshot_observed_at":"2026-08-04T18:10:16.384410Z","title":"Beutel, Taner Topal, Akhil Mathur, Xinchi Qiu, Titouan Parcollet, and Nicholas D","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-04T18:10:16.384410Z"},"links":{"cited_paper":"/paper/2007.14390","citing_paper":"/paper/2509.10161"},"observation_digest":"sha256:d76722c03a0627cb205764e7bdc653afb8a4b9eff33c67c1eadc626c3c2e059c","observation_id":"d978c4f0-0881-40f6-9b9e-302b55ad8344","resolution":{"observed_at":"2026-08-04T18:10:16.384410Z","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":"2026-08-04T18:10:16.435953Z","title":"Large-scale machine learning with stochastic gradient descent","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-04T18:10:16.435953Z"},"links":{"citing_paper":"/paper/2509.10161"},"observation_digest":"sha256:2740cd24617ed3b631cf5c9bc7a1a323454f7df0b716c8bc8f9adfdabb877ff1","observation_id":"2169e796-281b-4b15-9239-1b099436e3e0","resolution":{"observed_at":"2026-08-04T18:10:16.435953Z","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":"2026-08-04T18:10:16.490165Z","title":"Adaptive federated dropout: Improving communication efficiency and generalization for federated learning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-04T18:10:16.490165Z"},"links":{"citing_paper":"/paper/2509.10161"},"observation_digest":"sha256:ecaa268c4aa64f002e0b0ac1c70bd77d55378d27bbe060f81c6c5df71a1762bc","observation_id":"bd03a2f5-fc22-4f0d-afdb-ea5fe7a39a70","resolution":{"observed_at":"2026-08-04T18:10:16.490165Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1805.06085","last_updated":"2018-07-17T07:33:19Z","snapshot_observed_at":"2026-07-06T06:39:21.688392Z","submitted_at":"2018-05-16T01:19:43Z","title":"PACT: Parameterized Clipping Activation for Quantized Neural Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1805.06085","snapshot_observed_at":"2026-08-04T18:10:16.571475Z","title":"PACT: parameterized clipping activation for quantized neural networks.CoRR, abs/1805.06085, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-04T18:10:16.571475Z"},"links":{"cited_paper":"/paper/1805.06085","citing_paper":"/paper/2509.10161"},"observation_digest":"sha256:8aceea8b1551043869b2954542442f0f27ef304ef2e6e599cfa412bf518f6f70","observation_id":"7b9f66d4-7eb7-40c6-a40d-eb58708b1eb2","resolution":{"observed_at":"2026-08-04T18:10:16.571475Z","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":"2026-08-04T18:10:16.656226Z","title":"Bina- ryconnect: Training deep neural networks with binary weights during propagations","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-04T18:10:16.656226Z"},"links":{"citing_paper":"/paper/2509.10161"},"observation_digest":"sha256:fac95ff34970e6de52700478b0440a8d4a29176b28e54296c2de303a684e4ff9","observation_id":"2c1d575a-b7bf-4309-b49d-dd72db364ef9","resolution":{"observed_at":"2026-08-04T18:10:16.656226Z","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":"2026-08-04T18:10:16.748765Z","title":"Docofl: Downlink compression for cross-device federated learning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-04T18:10:16.748765Z"},"links":{"citing_paper":"/paper/2509.10161"},"observation_digest":"sha256:f30f13ae1e6dd9ce319081263f0b316ac4b182bfbbf8b7efddbd3281a9f33540","observation_id":"c5981372-e255-4145-a9d5-721f48699a3f","resolution":{"observed_at":"2026-08-04T18:10:16.748765Z","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":"2026-08-04T18:10:16.813952Z","title":"Esser, Jeffrey L","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-04T18:10:16.813952Z"},"links":{"citing_paper":"/paper/2509.10161"},"observation_digest":"sha256:73ca97192df59e9ce0dd1b2b97bd30a3fdfed451ea6b959f149b6bda95e20ab6","observation_id":"38144c52-0dd7-49f3-b004-c24adfa0b8d0","resolution":{"observed_at":"2026-08-04T18:10:16.813952Z","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":"2026-08-04T18:10:16.871143Z","title":"Deep sparse rectifier neural networks","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-04T18:10:16.871143Z"},"links":{"citing_paper":"/paper/2509.10161"},"observation_digest":"sha256:13bc4330af49a495df356a159682e97b5382c71ca46e990e3f5d92574d842904","observation_id":"cace2071-10c7-4d29-9d32-5889fb1824d0","resolution":{"observed_at":"2026-08-04T18:10:16.871143Z","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":"2026-08-04T18:10:16.965829Z","title":"EF21- P and friends: Improved theoretical communication complexity for distributed optimization with bidirectional compression","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-04T18:10:16.965829Z"},"links":{"citing_paper":"/paper/2509.10161"},"observation_digest":"sha256:95d4e86a7630b82376bff7bf17b571f487be6d1208e9d003da896d05dfed54f8","observation_id":"999dd907-04c7-4131-8750-8fb531b0116c","resolution":{"observed_at":"2026-08-04T18:10:16.965829Z","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":"2026-08-04T18:10:17.046927Z","title":"Quantization robust federated learning for efficient inference on heterogeneous devices.Trans","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-04T18:10:17.046927Z"},"links":{"citing_paper":"/paper/2509.10161"},"observation_digest":"sha256:558e7fe06483300d9ece23e686574e407fb3896908a6e5ea09e162d18363d39d","observation_id":"0b09fe6f-b22f-4768-ac25-00d3940c0515","resolution":{"observed_at":"2026-08-04T18:10:17.046927Z","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":"2026-08-04T18:10:17.134927Z","title":"Delving deep into rectifiers: Surpassing human-level performance on imagenet classification","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-04T18:10:17.134927Z"},"links":{"citing_paper":"/paper/2509.10161"},"observation_digest":"sha256:b141b8d3d6c8fefb02452a06eed59fe2743d8fbeb18de9d7509ac6adcf5ac757","observation_id":"b23efc4b-caa6-42c4-ac3d-683a881c36e6","resolution":{"observed_at":"2026-08-04T18:10:17.134927Z","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":"2026-08-04T18:10:17.195377Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-04T18:10:17.195377Z"},"links":{"citing_paper":"/paper/2509.10161"},"observation_digest":"sha256:a8b1438baba18ab646e2ede610ded77e97fc9f37a08ac4bdecceb3800cca1d1c","observation_id":"7c7387c9-1350-43b7-bc17-0131d7e4e2f1","resolution":{"observed_at":"2026-08-04T18:10:17.195377Z","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":"2026-08-04T18:10:17.280215Z","title":"Neural networks for machine learning.Coursera video lectures, 2012","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-04T18:10:17.280215Z"},"links":{"citing_paper":"/paper/2509.10161"},"observation_digest":"sha256:82a60da8856f9a63bcef417baa682eb496c4cb49addf7da256795eb059a47393","observation_id":"4950f11c-9868-436d-b056-c4f33d820aa5","resolution":{"observed_at":"2026-08-04T18:10:17.280215Z","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":"2026-08-04T18:10:17.368624Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-04T18:10:17.368624Z"},"links":{"citing_paper":"/paper/2509.10161"},"observation_digest":"sha256:07939c53a4be5bead49a76e439734d2db382f959b5241e96081f55205d0345ce","observation_id":"715a4304-adcc-4c25-92bd-ac0b5b907a8d","resolution":{"observed_at":"2026-08-04T18:10:17.368624Z","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":"2026-08-04T18:10:17.430438Z","title":"Weinberger","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-04T18:10:17.430438Z"},"links":{"citing_paper":"/paper/2509.10161"},"observation_digest":"sha256:7ca4f966054535bdb8fb815d0b883efd0e714bed31f9e3c8415ea8e4166fe2c3","observation_id":"fd1d192d-e7bb-4652-9bf0-a0adf1ffa383","resolution":{"observed_at":"2026-08-04T18:10:17.430438Z","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":"2026-08-04T18:10:17.480452Z","title":"Fedpara: Low-rank hadamard product for communication-efficient federated learning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-04T18:10:17.480452Z"},"links":{"citing_paper":"/paper/2509.10161"},"observation_digest":"sha256:506f698e0ccd54ddd64fed9f15ce56ef0f58c778613b70e4ad3b9320b1fc906e","observation_id":"392ccd46-e491-4483-b9ce-5da79ea4e4f0","resolution":{"observed_at":"2026-08-04T18:10:17.480452Z","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":"2026-08-04T18:10:17.536223Z","title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-04T18:10:17.536223Z"},"links":{"citing_paper":"/paper/2509.10161"},"observation_digest":"sha256:ca54ceedaf0f826a829fce61f77c52abfe0a60d04e62402fa823c274dcc286a7","observation_id":"db875a93-8e0b-48fe-88b9-0a4b548b88b9","resolution":{"observed_at":"2026-08-04T18:10:17.536223Z","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":"2026-08-04T18:10:17.591537Z","title":"Sparse random networks for communication-efficient federated learning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-04T18:10:17.591537Z"},"links":{"citing_paper":"/paper/2509.10161"},"observation_digest":"sha256:ac330bf3304b99e13641b765dd58cd79e80685f60ff0561a05e1801f1b4a5235","observation_id":"b07db55e-4d74-40e5-8b8f-b5aee74785b6","resolution":{"observed_at":"2026-08-04T18:10:17.591537Z","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":"2026-08-04T18:10:17.650248Z","title":"Howard, Hartwig Adam, and Dmitry Kalenichenko","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-04T18:10:17.650248Z"},"links":{"citing_paper":"/paper/2509.10161"},"observation_digest":"sha256:724d91a8b3e089dddd1f5b968c2551b27e12d9ebde89ca1886bfe3f0c55a6027","observation_id":"24df3766-e8a6-4344-8b3e-fadf1d0fb0b2","resolution":{"observed_at":"2026-08-04T18:10:17.650248Z","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":"2026-08-04T18:10:17.689103Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-04T18:10:17.689103Z"},"links":{"citing_paper":"/paper/2509.10161"},"observation_digest":"sha256:493ed2b07d42197d3c678ee5b03ebb61b6ba92759a6e5382c051507f2c57760f","observation_id":"2a655260-0523-45f1-90bc-15bbaad4b9df","resolution":{"observed_at":"2026-08-04T18:10:17.689103Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1909.12326","last_updated":"2022-04-06T04:14:53Z","snapshot_observed_at":"2026-07-06T08:24:58.301676Z","submitted_at":"2019-09-26T18:32:33Z","title":"Model Pruning Enables Efficient Federated Learning on Edge Devices","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1909.12326","snapshot_observed_at":"2026-08-04T18:10:17.740703Z","title":"Model pruning enables efficient federated learning on edge devices.CoRR, abs/1909.12326, 2019","venue":null,"work_id":null,"year":1909},"citing_paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-04T18:10:17.740703Z"},"links":{"cited_paper":"/paper/1909.12326","citing_paper":"/paper/2509.10161"},"observation_digest":"sha256:1b836500b7d5275c2c8da751b2b968aeed2373350ef4a24d7c7e6321cf85b12f","observation_id":"75bdbc8d-5fbd-4b6f-81d9-8dab48fa55c4","resolution":{"observed_at":"2026-08-04T18:10:17.740703Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1806.08342","last_updated":"2018-06-21T17:32:46Z","snapshot_observed_at":"2026-07-06T06:46:08.396066Z","submitted_at":"2018-06-21T17:32:46Z","title":"Quantizing deep convolutional networks for efficient inference: A whitepaper","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1806.08342","snapshot_observed_at":"2026-08-04T18:10:17.830275Z","title":"Quantizing deep convolutional networks for efficient inference: A whitepaper.CoRR, abs/1806.08342, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-04T18:10:17.830275Z"},"links":{"cited_paper":"/paper/1806.08342","citing_paper":"/paper/2509.10161"},"observation_digest":"sha256:2627d51760ebf975fb603b92253aaa8bc8c4088ac2e534c52b061ee0ae5dfee8","observation_id":"0f61389d-c847-4ac2-8ec0-532e771149ea","resolution":{"observed_at":"2026-08-04T18:10:17.830275Z","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":"2026-08-04T18:10:17.914572Z","title":"Learning multiple layers of features from tiny images.Technical report, University of Toronto, 2009","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-04T18:10:17.914572Z"},"links":{"citing_paper":"/paper/2509.10161"},"observation_digest":"sha256:289292df693b60e61e59e79e58b7a6925adb47f154390b1b69fb775c5c148baa","observation_id":"1d8a3446-95a0-443c-b40e-9d051a7fc284","resolution":{"observed_at":"2026-08-04T18:10:17.914572Z","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":"2026-08-04T18:10:17.978972Z","title":"Tiny imagenet visual recognition challenge,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-04T18:10:17.978972Z"},"links":{"citing_paper":"/paper/2509.10161"},"observation_digest":"sha256:297c68eb39ccf5b1f03fd0206dbafbe8d3ca1dd2da50f190567db8495ce82057","observation_id":"5db430db-ac56-4c78-badd-7e6d50462877","resolution":{"observed_at":"2026-08-04T18:10:17.978972Z","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":"2026-08-04T18:10:18.101258Z","title":"Fedmask: Joint computation and communication-efficient personalized federated learning via heterogeneous masking","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-04T18:10:18.101258Z"},"links":{"citing_paper":"/paper/2509.10161"},"observation_digest":"sha256:19e9d9b6c11038c4f35c701c413775f32c5d76fcdaf8bd09ee2d75274aa93f68","observation_id":"eee0b4ea-2352-4170-b8a0-9578408a9a12","resolution":{"observed_at":"2026-08-04T18:10:18.101258Z","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":"2026-08-04T18:10:18.164770Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-04T18:10:18.164770Z"},"links":{"citing_paper":"/paper/2509.10161"},"observation_digest":"sha256:29c9276f0b32b6be1fa7d67968d59d785afda8d0484c9fcfdb8d5433048c48b2","observation_id":"bb457427-8dd6-47f2-b4a2-ef97c6099bab","resolution":{"observed_at":"2026-08-04T18:10:18.164770Z","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":"2026-08-04T18:10:18.213976Z","title":"Federated learning on non-iid data silos: An experimental study","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-04T18:10:18.213976Z"},"links":{"citing_paper":"/paper/2509.10161"},"observation_digest":"sha256:585f7c86e195bdd27b6c4ce95dc326e43ee72c29d46562d757203bf9403e3b58","observation_id":"d7e631ca-3cb3-426c-b99d-be2da34a800c","resolution":{"observed_at":"2026-08-04T18:10:18.213976Z","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":"2026-08-04T18:10:18.265701Z","title":"Masked random noise for communication-efficient federated learning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-04T18:10:18.265701Z"},"links":{"citing_paper":"/paper/2509.10161"},"observation_digest":"sha256:36c6fe8a7ea42e16633b966bc585e1420b98f60131a0fbc163fe7a379b25592c","observation_id":"eda039ac-ca8a-4468-8875-eaaa2f2d28b4","resolution":{"observed_at":"2026-08-04T18:10:18.265701Z","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":"2026-08-04T18:10:18.355249Z","title":"Adaptive low-precision training for embeddings in click-through rate prediction","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-04T18:10:18.355249Z"},"links":{"citing_paper":"/paper/2509.10161"},"observation_digest":"sha256:d0caf50e8e9ebd37623d80f9e7aac8dcaa65750213af6cbb5192715ef9776c4e","observation_id":"134edd7c-72b0-4531-901d-bcb728667159","resolution":{"observed_at":"2026-08-04T18:10:18.355249Z","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":"2026-08-04T18:10:18.438005Z","title":"The panaceas for improving low-rank decomposition in communication-efficient federated learning","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-04T18:10:18.438005Z"},"links":{"citing_paper":"/paper/2509.10161"},"observation_digest":"sha256:5106c5a78633433d42626ad1d13b603e0d3aa8a8b1f9d05a1d2f0fb2377b7909","observation_id":"48196ebf-d17d-4e92-9cc3-2453d1553480","resolution":{"observed_at":"2026-08-04T18:10:18.438005Z","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":"2026-08-04T18:10:18.494615Z","title":"Fedbat: Communication-efficient federated learning via learnable binarization","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-04T18:10:18.494615Z"},"links":{"citing_paper":"/paper/2509.10161"},"observation_digest":"sha256:5a9913c2ead93e2887ed6b7d47f8006e786bb9ce0aab1ef161d010cbcfcd3728","observation_id":"7d49b28f-98fc-4e0f-aa84-5ad34b1b2434","resolution":{"observed_at":"2026-08-04T18:10:18.494615Z","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":"2026-08-04T18:10:18.568167Z","title":"Towards efficient replay in federated incremental learning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-04T18:10:18.568167Z"},"links":{"citing_paper":"/paper/2509.10161"},"observation_digest":"sha256:03fc0ab61d823618839c3dd9c6221b3adf09c6d20a8b2b8f19ccd8f1be7e0059","observation_id":"85e23a75-9296-40e5-8a00-935eae19cb29","resolution":{"observed_at":"2026-08-04T18:10:18.568167Z","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":"2026-08-04T18:10:18.676434Z","title":"Re- fed+: A better replay strategy for federated incremental learning.IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-04T18:10:18.676434Z"},"links":{"citing_paper":"/paper/2509.10161"},"observation_digest":"sha256:78c6f55b37fa9b92cae25f368052f2f0fad1b4b7d0226a78c4ba6f9bf8b4742f","observation_id":"f1b86edb-1530-41a1-a0d0-928ad3fcb756","resolution":{"observed_at":"2026-08-04T18:10:18.676434Z","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":"2026-08-04T18:10:18.761460Z","title":"Unleashing the power of continual learning on non-centralized devices: A survey.IEEE Communications Surveys & Tutorials, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-04T18:10:18.761460Z"},"links":{"citing_paper":"/paper/2509.10161"},"observation_digest":"sha256:719dd162b42cb160980b8aeaaef3a42943c46d19c97016091087f065cc62ec16","observation_id":"c6e23dc2-8b25-4cc0-9b6c-c3d28019f3b4","resolution":{"observed_at":"2026-08-04T18:10:18.761460Z","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":"2026-08-04T18:10:18.817214Z","title":"FedSSI: Rehearsal-free continual federated learning with synergistic synaptic intelligence","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-04T18:10:18.817214Z"},"links":{"citing_paper":"/paper/2509.10161"},"observation_digest":"sha256:c4f04d3ee0334c7b547e301c3cf90caff26d29685e9519481ec3fa4ef98c8d5e","observation_id":"dc249d0f-0840-4ccf-baeb-c1cf24131d19","resolution":{"observed_at":"2026-08-04T18:10:18.817214Z","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":"2026-08-04T18:10:18.873723Z","title":"Personalized federated domain-incremental learning based on adaptive knowledge matching","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-04T18:10:18.873723Z"},"links":{"citing_paper":"/paper/2509.10161"},"observation_digest":"sha256:520ebe67dd489a9888c485d27d3977e92ced6e355c5141576eae25bd0a308a86","observation_id":"6ef01c59-114e-4ddd-894c-e0932407ca8d","resolution":{"observed_at":"2026-08-04T18:10:18.873723Z","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":"2026-08-04T18:10:18.958314Z","title":"Low precision local training is enough for federated learning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-04T18:10:18.958314Z"},"links":{"citing_paper":"/paper/2509.10161"},"observation_digest":"sha256:a78f1f8dce14e55a27ce4a0f5bf1f6115080d2c33bc4fe7abb0eec0b0eaee52d","observation_id":"6e1a56c6-d2ea-4973-917f-72107f483ca7","resolution":{"observed_at":"2026-08-04T18:10:18.958314Z","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":"2026-08-04T18:10:19.040634Z","title":"Communication-efficient learning of deep net- works from decentralized data","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-04T18:10:19.040634Z"},"links":{"citing_paper":"/paper/2509.10161"},"observation_digest":"sha256:5481e46dfb7715c3ec3a1b1be416e9ed34b98ccec531976b9104bed5d4ef86fb","observation_id":"f97d5a2a-a34e-46c6-8c92-efd8972c6aed","resolution":{"observed_at":"2026-08-04T18:10:19.040634Z","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":"2026-08-04T18:10:19.123203Z","title":"Up or down? adaptive rounding for post-training quantization","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-04T18:10:19.123203Z"},"links":{"citing_paper":"/paper/2509.10161"},"observation_digest":"sha256:8ade522ae9d05e29169572af13d0b7a9ea6c284cbc009452a1b67c0a5e63e952","observation_id":"352a2159-cb0c-42b8-a43c-4b1df4cf56d8","resolution":{"observed_at":"2026-08-04T18:10:19.123203Z","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":"2026-08-04T18:10:19.207819Z","title":"Reading digits in natural images with unsupervised feature learning","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-04T18:10:19.207819Z"},"links":{"citing_paper":"/paper/2509.10161"},"observation_digest":"sha256:df9373458c9d1e15e86b2c384887612742befb29945f72ed2fbaf7a290c0bfb4","observation_id":"11cf0ba2-e06d-4ef4-987a-bcdd2362dce9","resolution":{"observed_at":"2026-08-04T18:10:19.207819Z","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":"2026-08-04T18:10:19.309251Z","title":"Nguyen, Quoc Tran-Dinh, Dzung T","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-04T18:10:19.309251Z"},"links":{"citing_paper":"/paper/2509.10161"},"observation_digest":"sha256:1d1a6d399057376dde846c89bb275d22281794f52ed77100410162dce0994e3b","observation_id":"57b8dfe8-4c99-493c-8731-87f32141ab54","resolution":{"observed_at":"2026-08-04T18:10:19.309251Z","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":"2026-08-04T18:10:19.363723Z","title":"Fedaqt: Accurate quantized training with fed- erated learning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-04T18:10:19.363723Z"},"links":{"citing_paper":"/paper/2509.10161"},"observation_digest":"sha256:95158911ee423e87517c76852b430fb6d7936a77d0f87ff6a097890cfecfb7ac","observation_id":"5e39f3e7-a0e2-4b30-aa33-2cac03d7a306","resolution":{"observed_at":"2026-08-04T18:10:19.363723Z","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":"2026-08-04T18:10:19.489542Z","title":"Cocofl: Communication- and computation-aware federated learning via partial NN freezing and quantization.Trans","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-04T18:10:19.489542Z"},"links":{"citing_paper":"/paper/2509.10161"},"observation_digest":"sha256:a5022f0358245fb8ba175aef7d680ada23c876451784fa5bb71da42ba656e964","observation_id":"8d833d7c-4e47-4310-ba9b-9387a0981ce5","resolution":{"observed_at":"2026-08-04T18:10:19.489542Z","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":"2026-08-04T18:10:19.556182Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-04T18:10:19.556182Z"},"links":{"citing_paper":"/paper/2509.10161"},"observation_digest":"sha256:496137cd41e52c5b9d804d186e8d767efc69d138e2773d259dc46608a0a309e9","observation_id":"157acf93-f42e-401d-bd55-2431edb6b4c7","resolution":{"observed_at":"2026-08-04T18:10:19.556182Z","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":"2026-08-04T18:10:19.560164Z","title":"Feddq: Communication-efficient federated learning with descending quantiza- tion","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-04T18:10:19.560164Z"},"links":{"citing_paper":"/paper/2509.10161"},"observation_digest":"sha256:557a68acfb88e644c3456f9299aeaab551ef0d4c04b90ca5c138c2ac1da3c6d3","observation_id":"3e647caf-b3a1-4fc4-aca6-820daf2c2982","resolution":{"observed_at":"2026-08-04T18:10:19.560164Z","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":"2026-08-04T18:10:19.563918Z","title":"Fedpaq: A communication-efficient federated learning method with periodic averaging and quantization","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-04T18:10:19.563918Z"},"links":{"citing_paper":"/paper/2509.10161"},"observation_digest":"sha256:93d649d85a6d156b6c4043e4fb5de7d0a0392c6c93055d4f6fab75cc8349bbc7","observation_id":"3c4d4939-2f9d-4821-b662-19db44be40e2","resolution":{"observed_at":"2026-08-04T18:10:19.563918Z","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":"2026-08-04T18:10:19.567963Z","title":"Fetchsgd: Communication-efficient federated learning with sketching","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-04T18:10:19.567963Z"},"links":{"citing_paper":"/paper/2509.10161"},"observation_digest":"sha256:7dd1891afd019a8e726956b4ebfb6263313a6a5906167182656a65971cadd142","observation_id":"bca87a18-b95b-4e06-aecd-ef097c450f11","resolution":{"observed_at":"2026-08-04T18:10:19.567963Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04385","last_updated":"2022-06-09T09:55:31Z","snapshot_observed_at":"2026-07-06T13:19:00.855697Z","submitted_at":"2022-06-09T09:55:31Z","title":"HideNseek: Federated Lottery Ticket via Server-side Pruning and Sign Supermask","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.04385","snapshot_observed_at":"2026-08-04T18:10:19.571697Z","title":"Vallapuram, Pengyuan Zhou, Young D","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-04T18:10:19.571697Z"},"links":{"cited_paper":"/paper/2206.04385","citing_paper":"/paper/2509.10161"},"observation_digest":"sha256:dc74a53304aec5b090c9fc1c64f1da140e7f017b7e05cc4302d119584213af3e","observation_id":"c8cbf66c-84f4-419d-b3b8-72259f85400f","resolution":{"observed_at":"2026-08-04T18:10:19.571697Z","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":"2026-08-04T18:10:19.576232Z","title":"Error-compensated sparsification for communication-efficient decentral- ized training in edge environment.IEEE Trans","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-04T18:10:19.576232Z"},"links":{"citing_paper":"/paper/2509.10161"},"observation_digest":"sha256:725e01fd8f6454ad305f0e2218cb87c6b36bc5ffacfe66856fa5774380d63a6e","observation_id":"d77acb60-cbef-4c4a-944f-ce09103075ca","resolution":{"observed_at":"2026-08-04T18:10:19.576232Z","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":"2026-08-04T18:10:19.580440Z","title":"Dafkd: Domain-aware federated knowledge distillation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-04T18:10:19.580440Z"},"links":{"citing_paper":"/paper/2509.10161"},"observation_digest":"sha256:c77a0fe1da65c240324dd78627e25f2eb9d91ad09b3a712a5145e77f5ea2db13","observation_id":"45d03f68-f4f3-4d3d-b6cb-b34842fa5435","resolution":{"observed_at":"2026-08-04T18:10:19.580440Z","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":"2026-08-04T18:10:19.584589Z","title":"Fedcda: Federated learning with cross-rounds divergence- aware aggregation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-04T18:10:19.584589Z"},"links":{"citing_paper":"/paper/2509.10161"},"observation_digest":"sha256:b4a4ea4ddf649f41cddbab53bffbe4849ac1d4ee1447a7ebb74537142fc7ddaf","observation_id":"7c88cb22-d40d-44a8-888a-9395c278db4a","resolution":{"observed_at":"2026-08-04T18:10:19.584589Z","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":"2026-08-04T18:10:19.588434Z","title":"Fednlr: Federated learning with neuron-wise learning rates","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-04T18:10:19.588434Z"},"links":{"citing_paper":"/paper/2509.10161"},"observation_digest":"sha256:97ceae371afe1dafe7c68d3a75d91b2fd68de79e516e55d81c4cd2078fd6b1df","observation_id":"6c9c6f44-c012-494f-9881-e003d1365b80","resolution":{"observed_at":"2026-08-04T18:10:19.588434Z","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":"2026-08-04T18:10:19.592053Z","title":"Decoupling general and personalized knowl- edge in federated learning via additive and low-rank decomposition","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-04T18:10:19.592053Z"},"links":{"citing_paper":"/paper/2509.10161"},"observation_digest":"sha256:ef5aa54d4212c37077f8455ec9b7963a17d626120a1b7a5f3c3e17136af756fc","observation_id":"86e11266-f6f1-4ace-9047-118fc21fb15d","resolution":{"observed_at":"2026-08-04T18:10:19.592053Z","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":"2026-08-04T18:10:19.595783Z","title":"Bold but cautious: Unlocking the potential of personalized federated learning through cautiously aggressive collaboration","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-04T18:10:19.595783Z"},"links":{"citing_paper":"/paper/2509.10161"},"observation_digest":"sha256:77c26798905f772132790d0c6d0fc04a3707439f16e1fa1672bef5521fc8ed01","observation_id":"d102a144-03bf-4e41-817d-2a5f2e5634f1","resolution":{"observed_at":"2026-08-04T18:10:19.595783Z","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":"2026-08-04T18:10:19.599575Z","title":"pfedgf: Enabling personalized federated learning via gradient fusion","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-04T18:10:19.599575Z"},"links":{"citing_paper":"/paper/2509.10161"},"observation_digest":"sha256:87356b6b167c9fb74b8959fd74762f421db7e7ef694804bded2db0d1b0cc44f1","observation_id":"46d02ee1-7daa-448a-98f6-4956f387a9ad","resolution":{"observed_at":"2026-08-04T18:10:19.599575Z","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":"2026-08-04T18:10:19.603189Z","title":"The diversity bonus: Learning from dissimilar clients in personalized federated learning.IEEE Transactions on Neural Networks and Learning Systems, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-04T18:10:19.603189Z"},"links":{"citing_paper":"/paper/2509.10161"},"observation_digest":"sha256:e990bc02af82a32de39aeb9fb4ea82a354d2335e92ad67ed9ab2d9b53c9137b5","observation_id":"66f3c340-ee2b-48c4-8ff9-32c65490547a","resolution":{"observed_at":"2026-08-04T18:10:19.603189Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1708.07747","last_updated":"2017-09-15T21:29:49Z","snapshot_observed_at":"2026-07-06T05:56:41.814255Z","submitted_at":"2017-08-25T14:01:29Z","title":"Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1708.07747","snapshot_observed_at":"2026-08-04T18:10:19.606878Z","title":"Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms.CoRR, abs/1708.07747, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-04T18:10:19.606878Z"},"links":{"cited_paper":"/paper/1708.07747","citing_paper":"/paper/2509.10161"},"observation_digest":"sha256:648a2203b3fcb9b64965da339b20778443f5565b99bdddb2e51fa2ed624295f6","observation_id":"590959ed-c1c1-45b3-a4d5-9925f2f48a01","resolution":{"observed_at":"2026-08-04T18:10:19.606878Z","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":"2026-08-04T18:10:19.610761Z","title":"Greenewald, Trong Nghia Hoang, and Yasaman Khazaeni","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-04T18:10:19.610761Z"},"links":{"citing_paper":"/paper/2509.10161"},"observation_digest":"sha256:8280de4bc0e35a79418a507bfb0a85316b0d82ff94598ea8bb5dbfc8e2595935","observation_id":"d39daafb-f9d4-4944-82b5-b4cf28df4fa7","resolution":{"observed_at":"2026-08-04T18:10:19.610761Z","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":"2026-08-04T18:10:18.047240Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing","version":1},"reference_index":2015,"source":"pdf_text","source_observed_at":"2026-08-04T18:10:18.047240Z"},"links":{"citing_paper":"/paper/2509.10161"},"observation_digest":"sha256:2cf25158ffeccde49217cfa35c0a08f64fb145cb84550cf5e5e907634bd5ea96","observation_id":"6e13bba0-9dd4-42fb-a34a-634a6e37339d","resolution":{"observed_at":"2026-08-04T18:10:18.047240Z","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":"2026-08-04T18:10:19.614372Z","title":"His research interests include decision making, deep learning, and optimization algorithms","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing","version":1},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-04T18:10:19.614372Z"},"links":{"citing_paper":"/paper/2509.10161"},"observation_digest":"sha256:a44b9a90190273171614044c4199455992efaaada6596b9d1347a2b8e07c0d10","observation_id":"432fd320-4e32-49ce-b3e3-a9f23543e00c","resolution":{"observed_at":"2026-08-04T18:10:19.614372Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2509.10161","last_updated":"2025-09-12T11:41:06Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-09T02:11:34.255942Z","submitted_at":"2025-09-12T11:41:06Z","title":"FedBiF: Communication-Efficient Federated Learning via Bits Freezing"},"reference_resolution":{"displayed":64,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":64,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":64},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 64 of 64 outbound references and 0 inbound Pith citation observations for arXiv:2509.10161."}