{"as_of":"2026-08-21T18:43:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:4bc07846afff639ef0a8be26153f6055cea55c9c2679f7fc11b6de0ad041477a","coverage":[{"denominator":46,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":46,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T05:21:01.226786Z","state":"measured"},{"denominator":46,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":46,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-21T06:32:19.484+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/2412.17692/citation-record","integrity":"/paper/2412.17692/integrity","json":"/paper/2412.17692/citation-record.json","paper":"/paper/2412.17692"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:21:01.032401Z","title":"Attention is all you need,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.17692","last_updated":"2025-01-26T05:21:54Z","snapshot_observed_at":"2026-08-21T10:28:17.424223Z","submitted_at":"2024-12-23T16:17:46Z","title":"FedTLU: Federated Learning with Targeted Layer Updates","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-11T05:21:01.032401Z"},"links":{"citing_paper":"/paper/2412.17692"},"observation_digest":"sha256:1fbc3f8e8212978a26e63d47a9feaeb48dd51bbeed90ba73db3faccb8cf32e77","observation_id":"5ea293d5-3064-4963-9c7d-f64a33e80047","resolution":{"observed_at":"2026-08-11T05:21:01.032401Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1810.04805","last_updated":"2019-05-24T20:37:26Z","snapshot_observed_at":"2026-08-14T18:16:28.847993Z","submitted_at":"2018-10-11T00:50:01Z","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1810.04805","snapshot_observed_at":"2026-08-11T05:21:01.038646Z","title":"Bert: Pre-training of deep bidirectional transformers for language understanding,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.17692","last_updated":"2025-01-26T05:21:54Z","snapshot_observed_at":"2026-08-21T10:28:17.424223Z","submitted_at":"2024-12-23T16:17:46Z","title":"FedTLU: Federated Learning with Targeted Layer Updates","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-11T05:21:01.038646Z"},"links":{"cited_paper":"/paper/1810.04805","citing_paper":"/paper/2412.17692"},"observation_digest":"sha256:565774a5cbe5be4fceaf15b66df59dffe3ee45204927bbbaa3a98a2896202958","observation_id":"ad6955a5-3706-4ede-bd49-6aa7be9e6fd7","resolution":{"observed_at":"2026-08-11T05:21:01.038646Z","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":"2026-08-11T05:21:01.043592Z","title":"Language models are unsupervised multitask learners,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.17692","last_updated":"2025-01-26T05:21:54Z","snapshot_observed_at":"2026-08-21T10:28:17.424223Z","submitted_at":"2024-12-23T16:17:46Z","title":"FedTLU: Federated Learning with Targeted Layer Updates","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-11T05:21:01.043592Z"},"links":{"citing_paper":"/paper/2412.17692"},"observation_digest":"sha256:e861ac30a45f65e0aea65063ca60b8ac51c291c6edacae1032a4511ebe426348","observation_id":"4ad83b49-d01a-4e86-aca7-9862d5b42015","resolution":{"observed_at":"2026-08-11T05:21:01.043592Z","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":"2026-08-11T05:21:01.048626Z","title":"A survey on large language model (llm) security and privacy: The good, the bad, and the ugly,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.17692","last_updated":"2025-01-26T05:21:54Z","snapshot_observed_at":"2026-08-21T10:28:17.424223Z","submitted_at":"2024-12-23T16:17:46Z","title":"FedTLU: Federated Learning with Targeted Layer Updates","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-11T05:21:01.048626Z"},"links":{"citing_paper":"/paper/2412.17692"},"observation_digest":"sha256:5405fdc276983da4d708ee8876b2f3c978d1d3e9d033b18ab9b063ce6511bd61","observation_id":"4be2accf-d049-4b78-a432-5a78dc66a27a","resolution":{"observed_at":"2026-08-11T05:21:01.048626Z","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":"2026-08-11T05:21:01.801964Z","title":"Fedmed: A federated learning framework for language modeling,","venue":null,"work_id":"729133a6-973b-47c8-b149-4e8fcc7bd806","year":2020},"citing_paper":{"arxiv_id":"2412.17692","last_updated":"2025-01-26T05:21:54Z","snapshot_observed_at":"2026-08-21T10:28:17.424223Z","submitted_at":"2024-12-23T16:17:46Z","title":"FedTLU: Federated Learning with Targeted Layer Updates","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-11T05:21:01.053144Z"},"links":{"citing_paper":"/paper/2412.17692"},"observation_digest":"sha256:d3416cd876d3db66be38b12cd3cfa44f30a1e6c2e5f7bb4c3a2c9f949971fd94","observation_id":"d71298e8-19b9-4395-9ba4-70060a9dfb00","resolution":{"observed_at":"2026-08-11T05:21:01.806770Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T05:21:01.789492Z","title":"Scaling federated learning for fine-tuning of large language models,","venue":null,"work_id":"b7760283-63d4-458b-9972-b21d497a9dd5","year":2021},"citing_paper":{"arxiv_id":"2412.17692","last_updated":"2025-01-26T05:21:54Z","snapshot_observed_at":"2026-08-21T10:28:17.424223Z","submitted_at":"2024-12-23T16:17:46Z","title":"FedTLU: Federated Learning with Targeted Layer Updates","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-11T05:21:01.057075Z"},"links":{"citing_paper":"/paper/2412.17692"},"observation_digest":"sha256:397741a574aca666efa90e8d50e926576e3e1adab3904c1b4a6f1cb25f1f432c","observation_id":"49461bb5-4ef1-46f2-8323-6a3916ce447c","resolution":{"observed_at":"2026-08-11T05:21:01.793601Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T05:21:01.775615Z","title":"Communication-efficient learning of deep networks from decentralized data,","venue":null,"work_id":"9d77d3f5-2349-419f-a479-3e854f0592d0","year":2017},"citing_paper":{"arxiv_id":"2412.17692","last_updated":"2025-01-26T05:21:54Z","snapshot_observed_at":"2026-08-21T10:28:17.424223Z","submitted_at":"2024-12-23T16:17:46Z","title":"FedTLU: Federated Learning with Targeted Layer Updates","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-11T05:21:01.061372Z"},"links":{"citing_paper":"/paper/2412.17692"},"observation_digest":"sha256:7ba8f271ba41f044c02d6036a024017df03085f803c657ed3a0d1adf688d0bd3","observation_id":"16c65c3d-e367-4122-bf78-8bd20390fbeb","resolution":{"observed_at":"2026-08-11T05:21:01.781038Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T05:21:01.065686Z","title":"Federated optimization in heterogeneous networks,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.17692","last_updated":"2025-01-26T05:21:54Z","snapshot_observed_at":"2026-08-21T10:28:17.424223Z","submitted_at":"2024-12-23T16:17:46Z","title":"FedTLU: Federated Learning with Targeted Layer Updates","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-11T05:21:01.065686Z"},"links":{"citing_paper":"/paper/2412.17692"},"observation_digest":"sha256:f8b0e9975088ab7f95bdf063d1b5bfa14cb24e122ad882b60021829770325fb3","observation_id":"99368972-e97b-4414-9844-e0dc3c420f24","resolution":{"observed_at":"2026-08-11T05:21:01.065686Z","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":"2026-08-11T05:21:01.754361Z","title":"Preserving data privacy via fed- erated learning: Challenges and solutions,","venue":null,"work_id":"0166c292-63c8-4239-98ca-f6d9dcc5da5a","year":2020},"citing_paper":{"arxiv_id":"2412.17692","last_updated":"2025-01-26T05:21:54Z","snapshot_observed_at":"2026-08-21T10:28:17.424223Z","submitted_at":"2024-12-23T16:17:46Z","title":"FedTLU: Federated Learning with Targeted Layer Updates","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-11T05:21:01.069499Z"},"links":{"citing_paper":"/paper/2412.17692"},"observation_digest":"sha256:713e8641bbe84a0d8736067c162525324d73fbeca4536fbdfbd7dbc43dd42344","observation_id":"53d741dd-8c4e-4ca4-98b2-e4fde0f375af","resolution":{"observed_at":"2026-08-11T05:21:01.758760Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T05:21:01.741046Z","title":"Federated analytics: Opportunities and challenges,","venue":null,"work_id":"d40c174f-2dfc-4dd0-a061-a31857cf63e4","year":2021},"citing_paper":{"arxiv_id":"2412.17692","last_updated":"2025-01-26T05:21:54Z","snapshot_observed_at":"2026-08-21T10:28:17.424223Z","submitted_at":"2024-12-23T16:17:46Z","title":"FedTLU: Federated Learning with Targeted Layer Updates","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-11T05:21:01.073355Z"},"links":{"citing_paper":"/paper/2412.17692"},"observation_digest":"sha256:c894facb2f20fd3705dc87171a9b9ff52d5c5493b30f651d73edd6ef5707d114","observation_id":"a7a8f9c7-159f-4e33-8877-961f156aeb00","resolution":{"observed_at":"2026-08-11T05:21:01.745749Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T05:21:01.727957Z","title":"Generalized federated learning via sharpness aware minimization,","venue":null,"work_id":"03b90199-a97d-4f0e-9c46-364303adf175","year":2022},"citing_paper":{"arxiv_id":"2412.17692","last_updated":"2025-01-26T05:21:54Z","snapshot_observed_at":"2026-08-21T10:28:17.424223Z","submitted_at":"2024-12-23T16:17:46Z","title":"FedTLU: Federated Learning with Targeted Layer Updates","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-11T05:21:01.077281Z"},"links":{"citing_paper":"/paper/2412.17692"},"observation_digest":"sha256:a39a42c4a82bd308567853e3ab5a2170893dce78a9fda63aaa47e0678d57bb1e","observation_id":"3619617d-fa2a-471d-9553-fc34ea43cace","resolution":{"observed_at":"2026-08-11T05:21:01.732509Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T05:21:01.715159Z","title":"A survey on federated learning: The journey from centralized to distributed on-site learning and beyond,","venue":null,"work_id":"3a21a05d-4d16-4e33-b8bb-84068a6bee57","year":2020},"citing_paper":{"arxiv_id":"2412.17692","last_updated":"2025-01-26T05:21:54Z","snapshot_observed_at":"2026-08-21T10:28:17.424223Z","submitted_at":"2024-12-23T16:17:46Z","title":"FedTLU: Federated Learning with Targeted Layer Updates","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-11T05:21:01.081577Z"},"links":{"citing_paper":"/paper/2412.17692"},"observation_digest":"sha256:465a8b437b06fa973d7bb448e5799cf45c9ba5984c8499bdab58c04ae1df69d8","observation_id":"5377106d-a060-4166-8ac6-33b3ae7b2902","resolution":{"observed_at":"2026-08-11T05:21:01.719709Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T05:21:01.702335Z","title":"Internet of things intrusion detection: Centralized, on-device, or federated learning?","venue":null,"work_id":"1c9201b6-0140-4e40-9d84-71998b538651","year":2020},"citing_paper":{"arxiv_id":"2412.17692","last_updated":"2025-01-26T05:21:54Z","snapshot_observed_at":"2026-08-21T10:28:17.424223Z","submitted_at":"2024-12-23T16:17:46Z","title":"FedTLU: Federated Learning with Targeted Layer Updates","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-11T05:21:01.086158Z"},"links":{"citing_paper":"/paper/2412.17692"},"observation_digest":"sha256:e45b0d954070ac1647e810e8678579214bd7424e1b9737eff7343e15d950524e","observation_id":"33a4f534-0580-4c0a-b4a7-050af225f580","resolution":{"observed_at":"2026-08-11T05:21:01.706872Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T05:21:01.688269Z","title":"Higher order naive bayes: A novel non-iid approach to text classification,","venue":null,"work_id":"aab75598-1f25-4758-92bd-0eb10a2582b5","year":2010},"citing_paper":{"arxiv_id":"2412.17692","last_updated":"2025-01-26T05:21:54Z","snapshot_observed_at":"2026-08-21T10:28:17.424223Z","submitted_at":"2024-12-23T16:17:46Z","title":"FedTLU: Federated Learning with Targeted Layer Updates","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-11T05:21:01.090558Z"},"links":{"citing_paper":"/paper/2412.17692"},"observation_digest":"sha256:280fa440706f7103791522fce197678e5463ff968d88b23d9407f29f52691b09","observation_id":"35c6df37-473d-403e-a56c-8977b72b5b8a","resolution":{"observed_at":"2026-08-11T05:21:01.693725Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T05:21:01.674535Z","title":"Beyond iid: Non-iid thinking, informatics, and learning,","venue":null,"work_id":"6aa3c0bb-b42a-485b-8b82-842d2c9eecc0","year":2022},"citing_paper":{"arxiv_id":"2412.17692","last_updated":"2025-01-26T05:21:54Z","snapshot_observed_at":"2026-08-21T10:28:17.424223Z","submitted_at":"2024-12-23T16:17:46Z","title":"FedTLU: Federated Learning with Targeted Layer Updates","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-11T05:21:01.094440Z"},"links":{"citing_paper":"/paper/2412.17692"},"observation_digest":"sha256:69e87528cf1de56f14aab5712254c69e5659867c733cd590e530aea367ffab1e","observation_id":"eb3229da-819b-4cef-995d-5d8f1f4aa4f5","resolution":{"observed_at":"2026-08-11T05:21:01.679458Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T05:21:01.098561Z","title":"Fedbiot: Llm local fine-tuning in federated learning without full model,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.17692","last_updated":"2025-01-26T05:21:54Z","snapshot_observed_at":"2026-08-21T10:28:17.424223Z","submitted_at":"2024-12-23T16:17:46Z","title":"FedTLU: Federated Learning with Targeted Layer Updates","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-11T05:21:01.098561Z"},"links":{"citing_paper":"/paper/2412.17692"},"observation_digest":"sha256:9cc24f7685b199a8121f62a0c1c7984eb961aa7080f9ec2999598843f79e0e98","observation_id":"3199b399-cc3a-44e3-b5c7-5aa66895407f","resolution":{"observed_at":"2026-08-11T05:21:01.098561Z","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":"2026-08-11T05:21:01.653265Z","title":"Momentum-based variance reduction in non-convex sgd,","venue":null,"work_id":"e8d0a4f5-df9f-46bb-814a-76d7c08de731","year":2019},"citing_paper":{"arxiv_id":"2412.17692","last_updated":"2025-01-26T05:21:54Z","snapshot_observed_at":"2026-08-21T10:28:17.424223Z","submitted_at":"2024-12-23T16:17:46Z","title":"FedTLU: Federated Learning with Targeted Layer Updates","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-11T05:21:01.102605Z"},"links":{"citing_paper":"/paper/2412.17692"},"observation_digest":"sha256:4baae60988eb383fa96e2a29fefd3b442f81bcb3e761836d6f188fa7c30ebf32","observation_id":"b009bc3e-416f-4003-94ed-e26589bd49c5","resolution":{"observed_at":"2026-08-11T05:21:01.658310Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T05:21:01.640334Z","title":"Federated learning with proximal stochastic variance reduced gradient algorithms,","venue":null,"work_id":"e69ea923-68d3-4522-8731-1f94aaa7ad18","year":2020},"citing_paper":{"arxiv_id":"2412.17692","last_updated":"2025-01-26T05:21:54Z","snapshot_observed_at":"2026-08-21T10:28:17.424223Z","submitted_at":"2024-12-23T16:17:46Z","title":"FedTLU: Federated Learning with Targeted Layer Updates","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-11T05:21:01.106629Z"},"links":{"citing_paper":"/paper/2412.17692"},"observation_digest":"sha256:4391f29531c583c8b448666328e42725f5d7d8a5481744f9a88f652b794070de","observation_id":"6db78364-5105-410e-a64f-acdbc7f62461","resolution":{"observed_at":"2026-08-11T05:21:01.644910Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T05:21:01.110553Z","title":"Few-shot parameter-efficient fine-tuning is better and cheaper than in-context learning,","venue":null,"work_id":null,"year":1950},"citing_paper":{"arxiv_id":"2412.17692","last_updated":"2025-01-26T05:21:54Z","snapshot_observed_at":"2026-08-21T10:28:17.424223Z","submitted_at":"2024-12-23T16:17:46Z","title":"FedTLU: Federated Learning with Targeted Layer Updates","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-11T05:21:01.110553Z"},"links":{"citing_paper":"/paper/2412.17692"},"observation_digest":"sha256:3d1929161372ef3b52579e62d9aff846d589cc2a1369174f6893310735ff0b94","observation_id":"e62158d9-e90f-4171-9191-4caafc5b9db0","resolution":{"observed_at":"2026-08-11T05:21:01.110553Z","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":"2026-08-11T05:21:01.618867Z","title":"Sensitivity-aware visual parameter-efficient fine-tuning,","venue":null,"work_id":"d78a34b3-aad0-4e66-bf81-c0aca3197a67","year":2023},"citing_paper":{"arxiv_id":"2412.17692","last_updated":"2025-01-26T05:21:54Z","snapshot_observed_at":"2026-08-21T10:28:17.424223Z","submitted_at":"2024-12-23T16:17:46Z","title":"FedTLU: Federated Learning with Targeted Layer Updates","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-11T05:21:01.114967Z"},"links":{"citing_paper":"/paper/2412.17692"},"observation_digest":"sha256:b732e375cbd8802538493cd796034e5aa438d42c1bc91bc42e4b20e2027d7d3d","observation_id":"7512b539-943f-4de1-8d4c-58e201a4aa47","resolution":{"observed_at":"2026-08-11T05:21:01.623387Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T05:21:01.605859Z","title":"Ditto: Fair and robust federated learning through personalization,","venue":null,"work_id":"5b9d206b-de81-4742-8d0d-ade54b60c1b1","year":2021},"citing_paper":{"arxiv_id":"2412.17692","last_updated":"2025-01-26T05:21:54Z","snapshot_observed_at":"2026-08-21T10:28:17.424223Z","submitted_at":"2024-12-23T16:17:46Z","title":"FedTLU: Federated Learning with Targeted Layer Updates","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-11T05:21:01.119507Z"},"links":{"citing_paper":"/paper/2412.17692"},"observation_digest":"sha256:fa1a7e042994f9b5a4af6c315ae4455b55e7c3a216bba957e9fb1c6b7e98c798","observation_id":"9788690d-6f03-41d8-a949-a301b735c46d","resolution":{"observed_at":"2026-08-11T05:21:01.610548Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T05:21:01.123701Z","title":"Towards personalized federated learning,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.17692","last_updated":"2025-01-26T05:21:54Z","snapshot_observed_at":"2026-08-21T10:28:17.424223Z","submitted_at":"2024-12-23T16:17:46Z","title":"FedTLU: Federated Learning with Targeted Layer Updates","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-11T05:21:01.123701Z"},"links":{"citing_paper":"/paper/2412.17692"},"observation_digest":"sha256:2fc69692e9e812a9086b0d69740433d7e81efe6c156d9b622ad5df9e2d027175","observation_id":"0d834a56-7ebd-469c-8ff6-7dfb625a75cf","resolution":{"observed_at":"2026-08-11T05:21:01.123701Z","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":"2026-08-11T05:21:01.584094Z","title":"Personalization improves privacy-accuracy tradeoffs in federated learning,","venue":null,"work_id":"cac9b09f-1a15-4c30-8150-d0bb606eb69a","year":2022},"citing_paper":{"arxiv_id":"2412.17692","last_updated":"2025-01-26T05:21:54Z","snapshot_observed_at":"2026-08-21T10:28:17.424223Z","submitted_at":"2024-12-23T16:17:46Z","title":"FedTLU: Federated Learning with Targeted Layer Updates","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-11T05:21:01.128488Z"},"links":{"citing_paper":"/paper/2412.17692"},"observation_digest":"sha256:42b395f0a8e243b1e5ef99164ef6953dc1c60831de4c305bc1ed607d994c21c0","observation_id":"a443e960-a5c3-47b7-9b34-24041f0f1340","resolution":{"observed_at":"2026-08-11T05:21:01.588628Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T05:21:01.570266Z","title":"Local learning matters: Rethinking data heterogeneity in federated learning,","venue":null,"work_id":"8e8f4a1a-4d2c-4ba2-9745-febc4faf38f1","year":2022},"citing_paper":{"arxiv_id":"2412.17692","last_updated":"2025-01-26T05:21:54Z","snapshot_observed_at":"2026-08-21T10:28:17.424223Z","submitted_at":"2024-12-23T16:17:46Z","title":"FedTLU: Federated Learning with Targeted Layer Updates","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-11T05:21:01.133175Z"},"links":{"citing_paper":"/paper/2412.17692"},"observation_digest":"sha256:6bce49c6d769e3e40bdd3e12685ddc2fa40552434bd371cab36f8248b852037a","observation_id":"0a861da1-94ba-4e0e-b563-e2cab835f419","resolution":{"observed_at":"2026-08-11T05:21:01.574962Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T05:21:01.137949Z","title":"Heterogeneous federated learning: State-of-the-art and research challenges,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.17692","last_updated":"2025-01-26T05:21:54Z","snapshot_observed_at":"2026-08-21T10:28:17.424223Z","submitted_at":"2024-12-23T16:17:46Z","title":"FedTLU: Federated Learning with Targeted Layer Updates","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-11T05:21:01.137949Z"},"links":{"citing_paper":"/paper/2412.17692"},"observation_digest":"sha256:e60cb3a4a3a00f280ad8ea6dff28477c47b55a80735074ff3c0714a636efc761","observation_id":"04770ebe-0b9d-4208-950f-c961b5f31c60","resolution":{"observed_at":"2026-08-11T05:21:01.137949Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.18352","last_updated":"2025-06-21T23:50:22Z","snapshot_observed_at":"2026-08-16T13:06:26.219887Z","submitted_at":"2024-10-24T01:14:23Z","title":"FedBaF: Federated Learning Aggregation Biased by a Foundation Model","version":3},"cited_work":{"arxiv_id":"2410.18352","doi":null,"metadata_source":"pith","pith_arxiv_id":"2410.18352","snapshot_observed_at":"2026-08-11T05:21:01.285573Z","title":"FedBaF: Federated Learning Aggregation Biased by a Foundation Model","venue":"cs.LG","work_id":"93d3a492-6ba1-4fc2-8d59-c618ab628450","year":2024},"citing_paper":{"arxiv_id":"2412.17692","last_updated":"2025-01-26T05:21:54Z","snapshot_observed_at":"2026-08-21T10:28:17.424223Z","submitted_at":"2024-12-23T16:17:46Z","title":"FedTLU: Federated Learning with Targeted Layer Updates","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-11T05:21:01.142403Z"},"links":{"cited_paper":"/paper/2410.18352","citing_paper":"/paper/2412.17692"},"observation_digest":"sha256:7d404ba69aad300b8e4fbfea604a9ee95d5f978473e3a2a8b49538a0e1a2c100","observation_id":"50a07ce3-f86c-4591-aee4-e08fd013578f","resolution":{"observed_at":"2026-08-11T05:21:01.293144Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T05:21:01.549419Z","title":"Threats, attacks and defenses to federated learning: issues, taxonomy and perspectives,","venue":null,"work_id":"97a2ec43-9550-4008-8ab0-a7f2e405cf62","year":2022},"citing_paper":{"arxiv_id":"2412.17692","last_updated":"2025-01-26T05:21:54Z","snapshot_observed_at":"2026-08-21T10:28:17.424223Z","submitted_at":"2024-12-23T16:17:46Z","title":"FedTLU: Federated Learning with Targeted Layer Updates","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-11T05:21:01.146807Z"},"links":{"citing_paper":"/paper/2412.17692"},"observation_digest":"sha256:27a38a5533e523390fa30db999e82f74181ba73f4532756706227ba69960c021","observation_id":"9d5a07c5-2e93-41e2-ae2b-3c60a9315306","resolution":{"observed_at":"2026-08-11T05:21:01.554099Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T05:21:01.534925Z","title":"Robust federated learning with noisy and het- erogeneous clients,","venue":null,"work_id":"d5609cb8-97e5-4896-acd2-e6e006e4dd0d","year":2022},"citing_paper":{"arxiv_id":"2412.17692","last_updated":"2025-01-26T05:21:54Z","snapshot_observed_at":"2026-08-21T10:28:17.424223Z","submitted_at":"2024-12-23T16:17:46Z","title":"FedTLU: Federated Learning with Targeted Layer Updates","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-11T05:21:01.151037Z"},"links":{"citing_paper":"/paper/2412.17692"},"observation_digest":"sha256:686365e109bacd2aff0d792feeaded95ed6ff60c655a5833046bf1a2b12f6c60","observation_id":"7841d7d1-6d5b-4d06-a676-a513fb233032","resolution":{"observed_at":"2026-08-11T05:21:01.540181Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T05:21:01.520399Z","title":"Bert: Pre-training of deep bidirectional transformers for language understanding,","venue":null,"work_id":"15d00499-ed73-4811-9a54-07654a78ccea","year":2019},"citing_paper":{"arxiv_id":"2412.17692","last_updated":"2025-01-26T05:21:54Z","snapshot_observed_at":"2026-08-21T10:28:17.424223Z","submitted_at":"2024-12-23T16:17:46Z","title":"FedTLU: Federated Learning with Targeted Layer Updates","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-11T05:21:01.155221Z"},"links":{"citing_paper":"/paper/2412.17692"},"observation_digest":"sha256:e7eb314f068570760dc1db7dbbbbad08d5e156f9991339a34a4f14ae826e5b1c","observation_id":"7f7e8b7b-1f83-44b5-ab1b-e872ee7fe97b","resolution":{"observed_at":"2026-08-11T05:21:01.525437Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T05:21:01.506748Z","title":"Improved dropout for shallow and deep learning,","venue":null,"work_id":"8957d57f-55bd-44b6-8edd-4b12bb3ce91d","year":2016},"citing_paper":{"arxiv_id":"2412.17692","last_updated":"2025-01-26T05:21:54Z","snapshot_observed_at":"2026-08-21T10:28:17.424223Z","submitted_at":"2024-12-23T16:17:46Z","title":"FedTLU: Federated Learning with Targeted Layer Updates","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-11T05:21:01.159282Z"},"links":{"citing_paper":"/paper/2412.17692"},"observation_digest":"sha256:0b51c5261fde212c2b86d2967a270339a0d87f1701c99cdec64016a6a0afb03c","observation_id":"98b0feb1-f28d-46ee-94cf-d94d19d06646","resolution":{"observed_at":"2026-08-11T05:21:01.511304Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T05:21:01.492021Z","title":"Random cnn structure: tool to increase generalization ability in deep learning,","venue":null,"work_id":"1d2217ae-0a6f-4649-92b9-ba48760c858a","year":2022},"citing_paper":{"arxiv_id":"2412.17692","last_updated":"2025-01-26T05:21:54Z","snapshot_observed_at":"2026-08-21T10:28:17.424223Z","submitted_at":"2024-12-23T16:17:46Z","title":"FedTLU: Federated Learning with Targeted Layer Updates","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-11T05:21:01.163238Z"},"links":{"citing_paper":"/paper/2412.17692"},"observation_digest":"sha256:09553a714ef929b9b49204376a5494cf21f6e2c942aeb1f1dab57a6f6c8cc7c2","observation_id":"0701ff1d-3b46-4639-876a-fc888c7131c3","resolution":{"observed_at":"2026-08-11T05:21:01.497552Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T05:21:01.478719Z","title":"Layerout: Freezing layers in deep neural networks,","venue":null,"work_id":"2ce982b2-e9a6-4879-b9ae-1e30104b585e","year":2020},"citing_paper":{"arxiv_id":"2412.17692","last_updated":"2025-01-26T05:21:54Z","snapshot_observed_at":"2026-08-21T10:28:17.424223Z","submitted_at":"2024-12-23T16:17:46Z","title":"FedTLU: Federated Learning with Targeted Layer Updates","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-11T05:21:01.168452Z"},"links":{"citing_paper":"/paper/2412.17692"},"observation_digest":"sha256:79de9bf03e879414a4f7b054e934d4a1a0199bfdc0fe3b1401650cc6c5ddedb5","observation_id":"9ba035fc-8bcb-4fa7-bd5e-6d4124b27334","resolution":{"observed_at":"2026-08-11T05:21:01.482993Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T05:21:01.465917Z","title":"Transfusion: Un- derstanding transfer learning for medical imaging,","venue":null,"work_id":"f16033e3-5aea-4e61-be7a-695514d2bf51","year":2019},"citing_paper":{"arxiv_id":"2412.17692","last_updated":"2025-01-26T05:21:54Z","snapshot_observed_at":"2026-08-21T10:28:17.424223Z","submitted_at":"2024-12-23T16:17:46Z","title":"FedTLU: Federated Learning with Targeted Layer Updates","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-11T05:21:01.173160Z"},"links":{"citing_paper":"/paper/2412.17692"},"observation_digest":"sha256:ef7ff62982b06a3ea27cf8819ec71b5de4ad3de9255f174ba8beee56d0be2266","observation_id":"360fcef8-e0a8-4ecb-9222-cf7e53ff96cf","resolution":{"observed_at":"2026-08-11T05:21:01.470583Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T05:21:01.177530Z","title":"Parameter-efficient transfer learning for nlp,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.17692","last_updated":"2025-01-26T05:21:54Z","snapshot_observed_at":"2026-08-21T10:28:17.424223Z","submitted_at":"2024-12-23T16:17:46Z","title":"FedTLU: Federated Learning with Targeted Layer Updates","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-11T05:21:01.177530Z"},"links":{"citing_paper":"/paper/2412.17692"},"observation_digest":"sha256:35c3e4546a65e41b0881588eedf29ce8d6533bb734da393d3ce9cd6dcd4a565f","observation_id":"35675d9b-ff78-4c81-98e4-4f6c65ae2c89","resolution":{"observed_at":"2026-08-11T05:21:01.177530Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2110.06500","last_updated":"2022-07-14T22:14:17Z","snapshot_observed_at":"2026-08-20T02:39:21.861813Z","submitted_at":"2021-10-13T05:15:00Z","title":"Differentially Private Fine-tuning of Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.06500","snapshot_observed_at":"2026-08-11T05:21:01.181635Z","title":"Differentially private fine- tuning of language models,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.17692","last_updated":"2025-01-26T05:21:54Z","snapshot_observed_at":"2026-08-21T10:28:17.424223Z","submitted_at":"2024-12-23T16:17:46Z","title":"FedTLU: Federated Learning with Targeted Layer Updates","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-11T05:21:01.181635Z"},"links":{"cited_paper":"/paper/2110.06500","citing_paper":"/paper/2412.17692"},"observation_digest":"sha256:68bf5d0efbb8cf13b59eb4a8d0da6c7cae7101a950d7ee84127699b51ece0c1e","observation_id":"d53ea8b7-f4fd-4259-85dc-7bbcbeebc9ca","resolution":{"observed_at":"2026-08-11T05:21:01.181635Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1802.08760","last_updated":"2018-06-18T18:01:43Z","snapshot_observed_at":"2026-08-14T19:42:42.814858Z","submitted_at":"2018-02-23T23:11:07Z","title":"Sensitivity and Generalization in Neural Networks: an Empirical Study","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1802.08760","snapshot_observed_at":"2026-08-11T05:21:01.185873Z","title":"Sensitivity and generalization in neural networks: an empirical study,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.17692","last_updated":"2025-01-26T05:21:54Z","snapshot_observed_at":"2026-08-21T10:28:17.424223Z","submitted_at":"2024-12-23T16:17:46Z","title":"FedTLU: Federated Learning with Targeted Layer Updates","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-11T05:21:01.185873Z"},"links":{"cited_paper":"/paper/1802.08760","citing_paper":"/paper/2412.17692"},"observation_digest":"sha256:85fafb2335be274167cd644326e168a75201cf435f243d8520672cf70b180d7a","observation_id":"7f88d4c6-4749-4c06-b164-6bf255f4d9fd","resolution":{"observed_at":"2026-08-11T05:21:01.185873Z","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":"2026-08-11T05:21:01.442520Z","title":"Corrnet: pearson correlation based pruning for efficient convolutional neural networks,","venue":null,"work_id":"02e35d00-68d7-49d3-bffa-03fda28cf5d3","year":2022},"citing_paper":{"arxiv_id":"2412.17692","last_updated":"2025-01-26T05:21:54Z","snapshot_observed_at":"2026-08-21T10:28:17.424223Z","submitted_at":"2024-12-23T16:17:46Z","title":"FedTLU: Federated Learning with Targeted Layer Updates","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-11T05:21:01.190610Z"},"links":{"citing_paper":"/paper/2412.17692"},"observation_digest":"sha256:042f7ebf0d883db1a782dad92bf978cca4a171a75fe6b7ab75318c772911e511","observation_id":"a3a51381-d6e1-4629-9fea-537819f943d8","resolution":{"observed_at":"2026-08-11T05:21:01.448464Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T05:21:01.425853Z","title":"Scaffold: Stochastic controlled averaging for federated learn- ing,","venue":null,"work_id":"34edda31-c2ba-442d-bdfd-385e37c3f47b","year":2020},"citing_paper":{"arxiv_id":"2412.17692","last_updated":"2025-01-26T05:21:54Z","snapshot_observed_at":"2026-08-21T10:28:17.424223Z","submitted_at":"2024-12-23T16:17:46Z","title":"FedTLU: Federated Learning with Targeted Layer Updates","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-11T05:21:01.194417Z"},"links":{"citing_paper":"/paper/2412.17692"},"observation_digest":"sha256:541a619023471dc04bef55c57161c4e6ff60e6f6a5ccb7a543de09e794c3e542","observation_id":"da46f13a-6591-488e-8b3a-b4c49aebba20","resolution":{"observed_at":"2026-08-11T05:21:01.431300Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T05:21:01.198658Z","title":"Advances and open problems in federated learning,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.17692","last_updated":"2025-01-26T05:21:54Z","snapshot_observed_at":"2026-08-21T10:28:17.424223Z","submitted_at":"2024-12-23T16:17:46Z","title":"FedTLU: Federated Learning with Targeted Layer Updates","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-11T05:21:01.198658Z"},"links":{"citing_paper":"/paper/2412.17692"},"observation_digest":"sha256:b5785fd9e9057c78257d1338f4dc3b278e6d0a985ccb2870f17880631fd476ee","observation_id":"56955728-a425-4d17-8625-1c7ff49100cf","resolution":{"observed_at":"2026-08-11T05:21:01.198658Z","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":"2026-08-11T05:21:01.400991Z","title":"Fedbert: When federated learning meets pre-training,","venue":null,"work_id":"33c96367-6a32-4140-8d69-aa0b885e3131","year":2022},"citing_paper":{"arxiv_id":"2412.17692","last_updated":"2025-01-26T05:21:54Z","snapshot_observed_at":"2026-08-21T10:28:17.424223Z","submitted_at":"2024-12-23T16:17:46Z","title":"FedTLU: Federated Learning with Targeted Layer Updates","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-11T05:21:01.202826Z"},"links":{"citing_paper":"/paper/2412.17692"},"observation_digest":"sha256:4aac916837d4382bf387a34e2098bcd41cd7add434a5cc01697871515c0791ff","observation_id":"9b84a40c-d43b-47de-b6e1-a55c7cdd514a","resolution":{"observed_at":"2026-08-11T05:21:01.406977Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T05:21:01.206690Z","title":"Federated learning on non-iid data: A survey,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.17692","last_updated":"2025-01-26T05:21:54Z","snapshot_observed_at":"2026-08-21T10:28:17.424223Z","submitted_at":"2024-12-23T16:17:46Z","title":"FedTLU: Federated Learning with Targeted Layer Updates","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-11T05:21:01.206690Z"},"links":{"citing_paper":"/paper/2412.17692"},"observation_digest":"sha256:587459ea0664fefb82c8a8ddd877bcd3c0e10ec018160e7c24e81fd0d965f47e","observation_id":"688ab783-b0c0-4165-b5df-19b5e6f88325","resolution":{"observed_at":"2026-08-11T05:21:01.206690Z","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":"2026-08-11T05:21:01.375949Z","title":"Federated multi-task learning,","venue":null,"work_id":"38dd14ed-06c4-4db5-84a8-a085b14c4a5a","year":2017},"citing_paper":{"arxiv_id":"2412.17692","last_updated":"2025-01-26T05:21:54Z","snapshot_observed_at":"2026-08-21T10:28:17.424223Z","submitted_at":"2024-12-23T16:17:46Z","title":"FedTLU: Federated Learning with Targeted Layer Updates","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-11T05:21:01.210794Z"},"links":{"citing_paper":"/paper/2412.17692"},"observation_digest":"sha256:b3adf47fd9f4035730cd79653b947c8a8de88b24fe3046d44a0b6fcf415dc1a2","observation_id":"5acfd00d-2ef6-4fdc-99ab-0446a5489370","resolution":{"observed_at":"2026-08-11T05:21:01.381864Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T05:21:01.214730Z","title":"Clustered federated learning: Model-agnostic distributed multitask optimization under privacy con- straints,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.17692","last_updated":"2025-01-26T05:21:54Z","snapshot_observed_at":"2026-08-21T10:28:17.424223Z","submitted_at":"2024-12-23T16:17:46Z","title":"FedTLU: Federated Learning with Targeted Layer Updates","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-11T05:21:01.214730Z"},"links":{"citing_paper":"/paper/2412.17692"},"observation_digest":"sha256:ba2f65f2a18b983f61183ea1b0597233e2584815397ac49b49553b38fb95b402","observation_id":"724bd775-64be-4b96-a20d-d20f63dfc100","resolution":{"observed_at":"2026-08-11T05:21:01.214730Z","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":"2026-08-11T05:21:01.351360Z","title":"On the importance of single directions for generalization,","venue":null,"work_id":"95ef0429-d1e5-4b35-9294-5b1a89e0910d","year":2018},"citing_paper":{"arxiv_id":"2412.17692","last_updated":"2025-01-26T05:21:54Z","snapshot_observed_at":"2026-08-21T10:28:17.424223Z","submitted_at":"2024-12-23T16:17:46Z","title":"FedTLU: Federated Learning with Targeted Layer Updates","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-11T05:21:01.218755Z"},"links":{"citing_paper":"/paper/2412.17692"},"observation_digest":"sha256:9fd82f5baea9452dd35f1e49e362bc7f2565ed7af2671fa95af3b8bc1aba1dbd","observation_id":"5dc125c7-620c-4d14-a70e-e1cd58fae4a5","resolution":{"observed_at":"2026-08-11T05:21:01.357326Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T05:21:01.335126Z","title":"On the convergence of fedavg on non-iid data,","venue":null,"work_id":"c7773a84-749b-4e8f-8d5c-0e18d43a594a","year":2020},"citing_paper":{"arxiv_id":"2412.17692","last_updated":"2025-01-26T05:21:54Z","snapshot_observed_at":"2026-08-21T10:28:17.424223Z","submitted_at":"2024-12-23T16:17:46Z","title":"FedTLU: Federated Learning with Targeted Layer Updates","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-11T05:21:01.222899Z"},"links":{"citing_paper":"/paper/2412.17692"},"observation_digest":"sha256:83a9dc2070468a3e18facf640f0b44db53e9aac6ff8b0b6fd1b0e86baaede7cf","observation_id":"41c04659-497a-40e4-83ba-eb915a5857f4","resolution":{"observed_at":"2026-08-11T05:21:01.340874Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T05:21:01.317715Z","title":"Zico: Zero-shot nas via inverse coefficient of variation on gradients,","venue":null,"work_id":"f8e55500-a244-4cc2-9ec4-6eb3f0f84a20","year":2023},"citing_paper":{"arxiv_id":"2412.17692","last_updated":"2025-01-26T05:21:54Z","snapshot_observed_at":"2026-08-21T10:28:17.424223Z","submitted_at":"2024-12-23T16:17:46Z","title":"FedTLU: Federated Learning with Targeted Layer Updates","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-11T05:21:01.226786Z"},"links":{"citing_paper":"/paper/2412.17692"},"observation_digest":"sha256:b8c992571495d7d85d109728673ce893b060b58cc117f3557db825b9fcc54c2e","observation_id":"8a5488a4-2b6d-45a5-8846-83dfcf29b930","resolution":{"observed_at":"2026-08-11T05:21:01.324172Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2412.17692","last_updated":"2025-01-26T05:21:54Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-21T10:28:17.424223Z","submitted_at":"2024-12-23T16:17:46Z","title":"FedTLU: Federated Learning with Targeted Layer Updates"},"reference_resolution":{"displayed":46,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":15,"verified_exact":1,"verified_fuzzy":30},"total_outbound_references":46},"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":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"thesis":"As of 21 August 2026, this Paper Citation Record lists 46 of 46 outbound references and 0 inbound Pith citation observations for arXiv:2412.17692."}