{"as_of":"2026-08-11T19:40:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:065d02ad2181e10b03f52d233e5cbe64fed0646b7cc014c84c5222bdfb591da6","coverage":[{"denominator":17,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":17,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T14:26:58.213488Z","state":"measured"},{"denominator":20,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":20,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-11T06:34:44.6726+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-22T13:54:38.393967Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-22T13:54:52.951106Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2501.15356","last_updated":"2025-03-13T19:12:47Z","snapshot_observed_at":"2026-08-10T22:26:19.085532Z","submitted_at":"2025-01-26T01:08:01Z","title":"Federated Class-Incremental Learning: A Hybrid Approach Using Latent Exemplars and Data-Free Techniques to Address Local and Global Forgetting","version":3},"cited_work":{"arxiv_id":"2501.15356","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2501.15356","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Federated class- incremental learning: A hybrid approach using latent exemplars and data-free techniques to address local and global forgetting","venue":null,"work_id":"b5d46a0d-cd27-4d26-b64f-174c9f1be588","year":2025},"citing_paper":{"arxiv_id":"2505.12318","last_updated":"2026-04-09T20:36:53Z","snapshot_observed_at":"2026-08-02T11:54:02.140047Z","submitted_at":"2025-05-18T09:19:13Z","title":"Task-agnostic Low-rank Residual Adaptation for Efficient Federated Continual Fine-Tuning","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-05-22T13:54:38.393967Z"},"links":{"cited_paper":"/paper/2501.15356","citing_paper":"/paper/2505.12318"},"observation_digest":"sha256:7a0f9bc69a8c880e4ca3535c2285dac5c3c67c5c616e021ffe08bb469dd813fb","observation_id":"7f62b513-7482-422f-a0b9-3266459451ec","resolution":{"observed_at":"2026-05-22T13:54:52.954222Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2501.15356","last_updated":"2025-03-13T19:12:47Z","snapshot_observed_at":"2026-08-10T22:26:19.085532Z","submitted_at":"2025-01-26T01:08:01Z","title":"Federated Class-Incremental Learning: A Hybrid Approach Using Latent Exemplars and Data-Free Techniques to Address Local and Global Forgetting","version":3},"cited_work":{"arxiv_id":"2501.15356","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2501.15356","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Federated class- incremental learning: A hybrid approach using latent exemplars and data-free techniques to address local and global forgetting","venue":null,"work_id":"b5d46a0d-cd27-4d26-b64f-174c9f1be588","year":2025},"citing_paper":{"arxiv_id":"2512.03537","last_updated":"2026-04-03T06:15:30Z","snapshot_observed_at":"2026-08-11T03:48:26.410270Z","submitted_at":"2025-12-03T07:57:48Z","title":"Pushing the Limits of Distillation-Based Continual Learning via Classifier-Proximal Lightweight Plugins","version":3},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-05-17T01:50:47.258991Z"},"links":{"cited_paper":"/paper/2501.15356","citing_paper":"/paper/2512.03537"},"observation_digest":"sha256:0893358c514f7920d356a88ad22680b02007cf3cc81a2c9525cfca4727259acf","observation_id":"e735d90f-aff9-471c-b5d5-65b17c910857","resolution":{"observed_at":"2026-05-17T01:51:25.573510Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2501.15356","last_updated":"2025-03-13T19:12:47Z","snapshot_observed_at":"2026-08-10T22:26:19.085532Z","submitted_at":"2025-01-26T01:08:01Z","title":"Federated Class-Incremental Learning: A Hybrid Approach Using Latent Exemplars and Data-Free Techniques to Address Local and Global Forgetting","version":3},"cited_work":{"arxiv_id":"2501.15356","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2501.15356","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Federated class- incremental learning: A hybrid approach using latent exemplars and data-free techniques to address local and global forgetting","venue":null,"work_id":"b5d46a0d-cd27-4d26-b64f-174c9f1be588","year":2025},"citing_paper":{"arxiv_id":"2604.08617","last_updated":"2026-04-09T06:17:27Z","snapshot_observed_at":"2026-07-06T22:57:40.773778Z","submitted_at":"2026-04-09T06:17:27Z","title":"From Selection to Scheduling: Federated Geometry-Aware Correction Makes Exemplar Replay Work Better under Continual Dynamic Heterogeneity","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-05-10T17:07:07.598981Z"},"links":{"cited_paper":"/paper/2501.15356","citing_paper":"/paper/2604.08617"},"observation_digest":"sha256:d8729c620ab20b023bb4c41b05b9736533f7b71acc5fe8cee9c07448f12e585c","observation_id":"b7dd9b24-40c5-4ec2-9fd0-7cbb37b97e7a","resolution":{"observed_at":"2026-05-11T07:35:57.466263Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2501.15356/citation-record","integrity":"/paper/2501.15356/integrity","json":"/paper/2501.15356/citation-record.json","paper":"/paper/2501.15356"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T14:26:58.407706Z","title":"Podnet: Pooled outputs distillation for small-tasks incremental learning","venue":null,"work_id":"e350b817-4186-4646-ac05-62e714721f7e","year":2020},"citing_paper":{"arxiv_id":"2501.15356","last_updated":"2025-03-13T19:12:47Z","snapshot_observed_at":"2026-08-10T22:26:19.085532Z","submitted_at":"2025-01-26T01:08:01Z","title":"Federated Class-Incremental Learning: A Hybrid Approach Using Latent Exemplars and Data-Free Techniques to Address Local and Global Forgetting","version":3},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-10T14:26:58.156543Z"},"links":{"citing_paper":"/paper/2501.15356"},"observation_digest":"sha256:355402af5ac947a88bae70d30b9fb528d60b0e3aa4e8f386b2854948dad8cba6","observation_id":"408e6af8-4c63-4170-9862-a6fe2fbd15d4","resolution":{"observed_at":"2026-08-10T14:26:58.411723Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1312.6114","last_updated":"2022-12-10T21:04:00Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2013-12-20T20:58:10Z","title":"Auto-Encoding Variational Bayes","version":11},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1312.6114","snapshot_observed_at":"2026-08-10T14:26:58.160703Z","title":"Auto-encoding variational bayes","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2501.15356","last_updated":"2025-03-13T19:12:47Z","snapshot_observed_at":"2026-08-10T22:26:19.085532Z","submitted_at":"2025-01-26T01:08:01Z","title":"Federated Class-Incremental Learning: A Hybrid Approach Using Latent Exemplars and Data-Free Techniques to Address Local and Global Forgetting","version":3},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-10T14:26:58.160703Z"},"links":{"cited_paper":"/paper/1312.6114","citing_paper":"/paper/2501.15356"},"observation_digest":"sha256:f0ab7031c3fb6c5527d2bfb23c61eb69acf3282970fa2e519ecb40ec9a8c0176","observation_id":"ce614c16-6920-475e-b5d4-2b2b03cf35c1","resolution":{"observed_at":"2026-08-10T14:26:58.160703Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2108.06910","last_updated":"2021-08-16T05:57:01Z","snapshot_observed_at":"2026-07-06T11:38:32.437113Z","submitted_at":"2021-08-16T05:57:01Z","title":"A Novel Attribute Reconstruction Attack in Federated Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.06910","snapshot_observed_at":"2026-08-10T14:26:58.172889Z","title":"Adaptive aggregation networks for class-incremental learning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.15356","last_updated":"2025-03-13T19:12:47Z","snapshot_observed_at":"2026-08-10T22:26:19.085532Z","submitted_at":"2025-01-26T01:08:01Z","title":"Federated Class-Incremental Learning: A Hybrid Approach Using Latent Exemplars and Data-Free Techniques to Address Local and Global Forgetting","version":3},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-10T14:26:58.172889Z"},"links":{"cited_paper":"/paper/2108.06910","citing_paper":"/paper/2501.15356"},"observation_digest":"sha256:ddd5bf2e7b7b2670744e222aec9b5e7fa47a6467900b130a7abc8def81cacc3e","observation_id":"a0c84919-6199-42fb-9c97-6f5d05343440","resolution":{"observed_at":"2026-08-10T14:26:58.172889Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.15277","last_updated":"2022-10-11T14:57:02Z","snapshot_observed_at":"2026-08-10T22:27:05.419432Z","submitted_at":"2020-10-28T23:28:15Z","title":"Class-incremental learning: survey and performance evaluation on image classification","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.15277","snapshot_observed_at":"2026-08-10T14:26:58.177057Z","title":"Class-incremental learning: Survey and performance evaluation on image classifica- tion","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2501.15356","last_updated":"2025-03-13T19:12:47Z","snapshot_observed_at":"2026-08-10T22:26:19.085532Z","submitted_at":"2025-01-26T01:08:01Z","title":"Federated Class-Incremental Learning: A Hybrid Approach Using Latent Exemplars and Data-Free Techniques to Address Local and Global Forgetting","version":3},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-10T14:26:58.177057Z"},"links":{"cited_paper":"/paper/2010.15277","citing_paper":"/paper/2501.15356"},"observation_digest":"sha256:887f4b43ebe568fbb53a46ef7406504e93cbcf5b4199f89e7e1f67aaa5452eec","observation_id":"707c56e3-b4d0-4e63-81ed-1488a849f533","resolution":{"observed_at":"2026-08-10T14:26:58.177057Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1911.02054","last_updated":"2025-08-24T12:07:07Z","snapshot_observed_at":"2026-08-03T05:02:32.419407Z","submitted_at":"2019-11-05T19:45:49Z","title":"Federated Adversarial Domain Adaptation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1911.02054","snapshot_observed_at":"2026-08-10T14:26:58.181535Z","title":"Federated adversarial domain adaptation","venue":null,"work_id":null,"year":1911},"citing_paper":{"arxiv_id":"2501.15356","last_updated":"2025-03-13T19:12:47Z","snapshot_observed_at":"2026-08-10T22:26:19.085532Z","submitted_at":"2025-01-26T01:08:01Z","title":"Federated Class-Incremental Learning: A Hybrid Approach Using Latent Exemplars and Data-Free Techniques to Address Local and Global Forgetting","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-10T14:26:58.181535Z"},"links":{"cited_paper":"/paper/1911.02054","citing_paper":"/paper/2501.15356"},"observation_digest":"sha256:bc9adb825452881ec7bc9673ff08f3a268794a2a309df53a1a6f0cdf1a7454e7","observation_id":"34272ef0-5070-4ffe-b132-5f1d9c854dda","resolution":{"observed_at":"2026-08-10T14:26:58.181535Z","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":"2026-08-10T14:26:58.383014Z","title":"Asynchronous federated continual learning","venue":null,"work_id":"588b9aab-3f7d-44a6-b986-3ada8296efca","year":2025},"citing_paper":{"arxiv_id":"2501.15356","last_updated":"2025-03-13T19:12:47Z","snapshot_observed_at":"2026-08-10T22:26:19.085532Z","submitted_at":"2025-01-26T01:08:01Z","title":"Federated Class-Incremental Learning: A Hybrid Approach Using Latent Exemplars and Data-Free Techniques to Address Local and Global Forgetting","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-10T14:26:58.189903Z"},"links":{"citing_paper":"/paper/2501.15356"},"observation_digest":"sha256:dd30baf8b790de37cf600cef659dbc7502a2c9e6168d7e110dc9261aac4f3083","observation_id":"1bfb1a22-6c5b-485f-a868-df7edb24d1de","resolution":{"observed_at":"2026-08-10T14:26:58.386631Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1910.07796","last_updated":"2019-10-17T09:53:16Z","snapshot_observed_at":"2026-08-10T22:27:44.765465Z","submitted_at":"2019-10-17T09:53:16Z","title":"Overcoming Forgetting in Federated Learning on Non-IID Data","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.07796","snapshot_observed_at":"2026-08-10T14:26:58.193625Z","title":"Overcoming forgetting in federated learning on non-iid data","venue":null,"work_id":null,"year":1910},"citing_paper":{"arxiv_id":"2501.15356","last_updated":"2025-03-13T19:12:47Z","snapshot_observed_at":"2026-08-10T22:26:19.085532Z","submitted_at":"2025-01-26T01:08:01Z","title":"Federated Class-Incremental Learning: A Hybrid Approach Using Latent Exemplars and Data-Free Techniques to Address Local and Global Forgetting","version":3},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-10T14:26:58.193625Z"},"links":{"cited_paper":"/paper/1910.07796","citing_paper":"/paper/2501.15356"},"observation_digest":"sha256:e966dc4f9057079fa2d40342077406e8ffed1576b18f82bfac1d7700486103c4","observation_id":"a3a3e999-81de-4e0b-ae44-de10a09df137","resolution":{"observed_at":"2026-08-10T14:26:58.193625Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2202.05411","last_updated":"2023-06-07T05:00:32Z","snapshot_observed_at":"2026-08-10T06:31:32.614760Z","submitted_at":"2022-02-11T02:20:43Z","title":"Incremental Learning of Structured Memory via Closed-Loop Transcription","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.05411","snapshot_observed_at":"2026-08-10T14:26:58.197620Z","title":"Incremental learning of structured memory via closed-loop transcription","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.15356","last_updated":"2025-03-13T19:12:47Z","snapshot_observed_at":"2026-08-10T22:26:19.085532Z","submitted_at":"2025-01-26T01:08:01Z","title":"Federated Class-Incremental Learning: A Hybrid Approach Using Latent Exemplars and Data-Free Techniques to Address Local and Global Forgetting","version":3},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-10T14:26:58.197620Z"},"links":{"cited_paper":"/paper/2202.05411","citing_paper":"/paper/2501.15356"},"observation_digest":"sha256:cfde47540ea4ed7e03a9ae2e96d95933a4062ae05060d2ad47c7162cb3093d5a","observation_id":"308af70e-fd95-4058-aa36-f066f27a2820","resolution":{"observed_at":"2026-08-10T14:26:58.197620Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2002.06440","last_updated":"2020-02-15T20:09:24Z","snapshot_observed_at":"2026-08-06T14:46:34.371139Z","submitted_at":"2020-02-15T20:09:24Z","title":"Federated Learning with Matched Averaging","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.06440","snapshot_observed_at":"2026-08-10T14:26:58.202046Z","title":"Federated learning with matched averaging","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2501.15356","last_updated":"2025-03-13T19:12:47Z","snapshot_observed_at":"2026-08-10T22:26:19.085532Z","submitted_at":"2025-01-26T01:08:01Z","title":"Federated Class-Incremental Learning: A Hybrid Approach Using Latent Exemplars and Data-Free Techniques to Address Local and Global Forgetting","version":3},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-10T14:26:58.202046Z"},"links":{"cited_paper":"/paper/2002.06440","citing_paper":"/paper/2501.15356"},"observation_digest":"sha256:95f8d661745129315c6ef3173608f3e4b86abbe66993ab712e200d697d5bbd05","observation_id":"7b803aba-39fd-425b-a138-c150450a570a","resolution":{"observed_at":"2026-08-10T14:26:58.202046Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2101.11203","last_updated":"2021-05-04T03:30:18Z","snapshot_observed_at":"2026-08-06T02:17:42.050470Z","submitted_at":"2021-01-27T04:38:27Z","title":"Achieving Linear Speedup with Partial Worker Participation in Non-IID Federated Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2101.11203","snapshot_observed_at":"2026-08-10T14:26:58.206084Z","title":"Achieving linear speedup with partial worker participation in non-iid federated learning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.15356","last_updated":"2025-03-13T19:12:47Z","snapshot_observed_at":"2026-08-10T22:26:19.085532Z","submitted_at":"2025-01-26T01:08:01Z","title":"Federated Class-Incremental Learning: A Hybrid Approach Using Latent Exemplars and Data-Free Techniques to Address Local and Global Forgetting","version":3},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-10T14:26:58.206084Z"},"links":{"cited_paper":"/paper/2101.11203","citing_paper":"/paper/2501.15356"},"observation_digest":"sha256:39219eaf71d6815025a952c5456ed2d4334cc65c0d5e61b3228e6a71134ecf3d","observation_id":"4cc61204-e322-4d55-82b4-35bb6989f207","resolution":{"observed_at":"2026-08-10T14:26:58.206084Z","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":"2026-08-10T14:26:58.371713Z","title":"Fine-tuning global model via data-free knowledge distillation for non-iid federated learning","venue":null,"work_id":"08862f26-ae8b-4914-957c-4bb6fd56bab5","year":2025},"citing_paper":{"arxiv_id":"2501.15356","last_updated":"2025-03-13T19:12:47Z","snapshot_observed_at":"2026-08-10T22:26:19.085532Z","submitted_at":"2025-01-26T01:08:01Z","title":"Federated Class-Incremental Learning: A Hybrid Approach Using Latent Exemplars and Data-Free Techniques to Address Local and Global Forgetting","version":3},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-10T14:26:58.210140Z"},"links":{"citing_paper":"/paper/2501.15356"},"observation_digest":"sha256:6a3ed206dd6102fbea499ed366b56a1a899836c191cbd6ffc7d13c4fa3330970","observation_id":"f2ac55dc-5412-4946-8431-9b5e0d67784d","resolution":{"observed_at":"2026-08-10T14:26:58.375603Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1610.05492","last_updated":"2017-10-30T20:52:14Z","snapshot_observed_at":"2026-07-06T05:15:00.158639Z","submitted_at":"2016-10-18T09:11:51Z","title":"Federated Learning: Strategies for Improving Communication Efficiency","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1610.05492","snapshot_observed_at":"2026-08-10T14:26:58.164451Z","title":"Federated learning: Strategies for improving communication efficiency","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.15356","last_updated":"2025-03-13T19:12:47Z","snapshot_observed_at":"2026-08-10T22:26:19.085532Z","submitted_at":"2025-01-26T01:08:01Z","title":"Federated Class-Incremental Learning: A Hybrid Approach Using Latent Exemplars and Data-Free Techniques to Address Local and Global Forgetting","version":3},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-10T14:26:58.164451Z"},"links":{"cited_paper":"/paper/1610.05492","citing_paper":"/paper/2501.15356"},"observation_digest":"sha256:5f0fe761fa395e26d08a922a58c310d0afc025bcf55dcd31fe33f7fe27a0b7b4","observation_id":"a7dfc4fd-7f5f-4c10-8d9b-fc641ef46699","resolution":{"observed_at":"2026-08-10T14:26:58.164451Z","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":"2026-08-10T14:26:58.394278Z","title":"icarl: Incremental classifier and representation learning","venue":null,"work_id":"d6c61645-1c9e-440e-a8c4-eefcc20f7510","year":2001},"citing_paper":{"arxiv_id":"2501.15356","last_updated":"2025-03-13T19:12:47Z","snapshot_observed_at":"2026-08-10T22:26:19.085532Z","submitted_at":"2025-01-26T01:08:01Z","title":"Federated Class-Incremental Learning: A Hybrid Approach Using Latent Exemplars and Data-Free Techniques to Address Local and Global Forgetting","version":3},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-10T14:26:58.185992Z"},"links":{"citing_paper":"/paper/2501.15356"},"observation_digest":"sha256:9ebb6c326bf43af5f794dd74793b6b719d42d7176b5649be0d648bc30765be14","observation_id":"bdc47177-e3d0-40bb-9a09-6774ff64d30c","resolution":{"observed_at":"2026-08-10T14:26:58.399554Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2102.07623","last_updated":"2021-05-11T14:21:00Z","snapshot_observed_at":"2026-08-09T15:59:31.104495Z","submitted_at":"2021-02-15T16:04:10Z","title":"FedBN: Federated Learning on Non-IID Features via Local Batch Normalization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2102.07623","snapshot_observed_at":"2026-08-10T14:26:58.168874Z","title":"Fedbn: Federated learning on non-iid features via local batch normalization","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.15356","last_updated":"2025-03-13T19:12:47Z","snapshot_observed_at":"2026-08-10T22:26:19.085532Z","submitted_at":"2025-01-26T01:08:01Z","title":"Federated Class-Incremental Learning: A Hybrid Approach Using Latent Exemplars and Data-Free Techniques to Address Local and Global Forgetting","version":3},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-10T14:26:58.168874Z"},"links":{"cited_paper":"/paper/2102.07623","citing_paper":"/paper/2501.15356"},"observation_digest":"sha256:3951960e480dcd43f6cfcb70433e3a043fae7cdadaefa3b95ce9a16ddc5a9cb5","observation_id":"c05912a0-6f3d-4dde-9d24-62783789e7ce","resolution":{"observed_at":"2026-08-10T14:26:58.168874Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.00497","last_updated":"2023-07-17T19:16:24Z","snapshot_observed_at":"2026-08-07T11:56:06.833202Z","submitted_at":"2023-07-02T07:06:45Z","title":"Don't Memorize; Mimic The Past: Federated Class Incremental Learning Without Episodic Memory","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.00497","snapshot_observed_at":"2026-08-10T14:26:58.148077Z","title":"Don’t memorize; mimic the past: Federated class incremental learning without episodic memory","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.15356","last_updated":"2025-03-13T19:12:47Z","snapshot_observed_at":"2026-08-10T22:26:19.085532Z","submitted_at":"2025-01-26T01:08:01Z","title":"Federated Class-Incremental Learning: A Hybrid Approach Using Latent Exemplars and Data-Free Techniques to Address Local and Global Forgetting","version":3},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-10T14:26:58.148077Z"},"links":{"cited_paper":"/paper/2307.00497","citing_paper":"/paper/2501.15356"},"observation_digest":"sha256:52fdbffc8e4cf1339549269c1e53dcbeea3d231138802e91635e45eb94aa264a","observation_id":"2b664953-d285-4a21-9aa7-a214b6ba254a","resolution":{"observed_at":"2026-08-10T14:26:58.148077Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2007.14612","last_updated":"2021-03-04T06:09:13Z","snapshot_observed_at":"2026-08-06T11:40:45.883446Z","submitted_at":"2020-07-29T05:31:58Z","title":"Clarinet: A One-step Approach Towards Budget-friendly Unsupervised Domain Adaptation","version":2},"cited_work":{"arxiv_id":"2007.14612","doi":null,"metadata_source":"pith","pith_arxiv_id":"2007.14612","snapshot_observed_at":"2026-08-10T14:26:58.243942Z","title":"Clarinet: A One-step Approach Towards Budget-friendly Unsupervised Domain Adaptation","venue":"cs.LG","work_id":"566fe53b-8399-415c-ae64-d0bfba575042","year":2020},"citing_paper":{"arxiv_id":"2501.15356","last_updated":"2025-03-13T19:12:47Z","snapshot_observed_at":"2026-08-10T22:26:19.085532Z","submitted_at":"2025-01-26T01:08:01Z","title":"Federated Class-Incremental Learning: A Hybrid Approach Using Latent Exemplars and Data-Free Techniques to Address Local and Global Forgetting","version":3},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-10T14:26:58.213488Z"},"links":{"cited_paper":"/paper/2007.14612","citing_paper":"/paper/2501.15356"},"observation_digest":"sha256:8160d700d2b17958856b6bfaf15e84f9fe6de396e10ec93692421aa1db03d3ba","observation_id":"e82513fe-0694-42c7-a121-31bae19dc2bf","resolution":{"observed_at":"2026-08-10T14:26:58.250090Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T14:26:58.419324Z","title":"A data-free approach to mitigate catastrophic forgetting in federated class incremental learning for vision tasks","venue":null,"work_id":"e88ec586-6ea5-42cc-a2f5-f99be2204dd5","year":2025},"citing_paper":{"arxiv_id":"2501.15356","last_updated":"2025-03-13T19:12:47Z","snapshot_observed_at":"2026-08-10T22:26:19.085532Z","submitted_at":"2025-01-26T01:08:01Z","title":"Federated Class-Incremental Learning: A Hybrid Approach Using Latent Exemplars and Data-Free Techniques to Address Local and Global Forgetting","version":3},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-10T14:26:58.152767Z"},"links":{"citing_paper":"/paper/2501.15356"},"observation_digest":"sha256:097c80b73cc7c13fa4a59530d3c61e9492895ccad6e669199f712a0e0b889983","observation_id":"6eb4e71e-94fd-497d-b46c-71e5105db0e2","resolution":{"observed_at":"2026-08-10T14:26:58.423023Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2501.15356","last_updated":"2025-03-13T19:12:47Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-10T22:26:19.085532Z","submitted_at":"2025-01-26T01:08:01Z","title":"Federated Class-Incremental Learning: A Hybrid Approach Using Latent Exemplars and Data-Free Techniques to Address Local and Global Forgetting"},"reference_resolution":{"displayed":17,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":11,"verified_exact":0,"verified_fuzzy":5},"total_outbound_references":17},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"thesis":"As of 11 August 2026, this Paper Citation Record lists 17 of 17 outbound references and 3 inbound Pith citation observations for arXiv:2501.15356."}