{"as_of":"2026-08-11T17:03:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d51030df6ad391a2bd26b94c89a017da2bde3e42bb2f4a0721fec3b6826c45c2","coverage":[{"denominator":82,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":82,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T05:57:31.405043Z","state":"measured"},{"denominator":82,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":82,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-11T06:34:44.6726+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2412.17009/citation-record","integrity":"/paper/2412.17009/integrity","json":"/paper/2412.17009/citation-record.json","paper":"/paper/2412.17009"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:57:31.000021Z","title":"Unsupervised domain clusters in pretrained language models","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.000021Z"},"links":{"citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:237e9cdc837be31d6fd1ad5f15c77ea18da0ae39fd440325e4c78f7418160a8c","observation_id":"e7c7f8b0-f5c7-4765-88ae-6790361b4b52","resolution":{"observed_at":"2026-08-11T05:57:31.000021Z","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":"2026-08-11T05:57:31.005390Z","title":"Expert gate: Lifelong learning with a network of experts","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.005390Z"},"links":{"citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:a3fe9435c66c536dd7012fd99e40540ed7494d5faf42d4f1905cf8ac5230b992","observation_id":"b4aba505-b3f9-4377-947f-7136b70c8bfb","resolution":{"observed_at":"2026-08-11T05:57:31.005390Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.09053","last_updated":"2024-10-30T01:38:27Z","snapshot_observed_at":"2026-08-09T06:32:26.933441Z","submitted_at":"2024-08-16T23:57:29Z","title":"Learning to Route for Dynamic Adapter Composition in Continual Learning with Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.09053","snapshot_observed_at":"2026-08-11T05:57:31.010226Z","title":"Learning to route for dynamic adapter composition in continual learning with language models.arXiv preprint arXiv:2408.09053, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.010226Z"},"links":{"cited_paper":"/paper/2408.09053","citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:326461630aa6a7945ed68168db8b75a4c36334ffdb21334b4a8c26ffac6f5ad3","observation_id":"d7ec4dc5-293a-4277-95b4-c03120246ab2","resolution":{"observed_at":"2026-08-11T05:57:31.010226Z","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":"2026-08-11T05:57:32.693309Z","title":"Don’t generate me: Training differentially private generative models with sinkhorn divergence.Advances in Neural Information Processing Systems, 34:12480–12492, 2021","venue":null,"work_id":"12870980-f71c-4bd5-9558-c7edf5ca31be","year":2021},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.015790Z"},"links":{"citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:30d39eb4f1a9ccbd50864a1f2313b3adb57623b9b78c7a9a1855baf15b5ea8ec","observation_id":"2c4c12a1-62fc-481f-bcef-384bb95f873e","resolution":{"observed_at":"2026-08-11T05:57:32.699451Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:57:32.676824Z","title":"Analysis of the isic image datasets: Usage, benchmarks and recommendations.Medical image analysis, 75:102305, 2022","venue":null,"work_id":"5332fa96-86f1-4dcc-9840-da6ec3ec7f14","year":2022},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.021119Z"},"links":{"citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:64e4d9974c186d49f9b28f49b886b1f33fb0796f4b2cfbe399639b0666254511","observation_id":"f5870fe4-093e-41ab-baa4-5bfff76479a5","resolution":{"observed_at":"2026-08-11T05:57:32.682101Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:57:31.025811Z","title":"Efficient lifelong learning with a-GEM","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.025811Z"},"links":{"citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:1f9dc86f4d092ad84fa56ab469d3f4e85523880cb2df9b168415d40da3ef5c05","observation_id":"b70e2dc0-fc19-4844-b174-880bc4a608da","resolution":{"observed_at":"2026-08-11T05:57:31.025811Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1902.10486","last_updated":"2019-06-04T07:59:35Z","snapshot_observed_at":"2026-08-07T08:44:38.959537Z","submitted_at":"2019-02-27T12:34:19Z","title":"On Tiny Episodic Memories in Continual Learning","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.10486","snapshot_observed_at":"2026-08-11T05:57:31.031100Z","title":"On tiny episodic memories in continual learning.arXiv preprint arXiv:1902.10486, 2019","venue":null,"work_id":null,"year":1902},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.031100Z"},"links":{"cited_paper":"/paper/1902.10486","citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:3c3753a24206991aea1c2105331369bd301b3afd39335e621fdfa469e2409eeb","observation_id":"914f8e28-f326-4f33-bddf-6f76b35e788e","resolution":{"observed_at":"2026-08-11T05:57:31.031100Z","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":"2026-08-11T05:57:32.649837Z","title":"Synthetic data in machine learning for medicine and healthcare.Nature Biomedical Engineering, 5 (6):493–497, 2021","venue":null,"work_id":"f0609781-4701-489d-a36c-c51f59bd89a2","year":2021},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.036494Z"},"links":{"citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:82118542086d49684f58a4142114ab92c6e9ef8ab7742e1d6bbd4649e94ff212","observation_id":"e8217388-3bfb-4d5b-b299-f0ccbfa88c15","resolution":{"observed_at":"2026-08-11T05:57:32.655482Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:57:32.630579Z","title":"Quac: Question answering in context","venue":null,"work_id":"34f689d6-40c1-4a40-b390-019b40cff410","year":2018},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.041118Z"},"links":{"citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:36bd505936d34c3c860738203881b6481863253d15bdcbe046eb190b238b13fe","observation_id":"7764e793-5be8-4160-925e-4e08ae5ad88a","resolution":{"observed_at":"2026-08-11T05:57:32.636267Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:57:32.612745Z","title":null,"venue":null,"work_id":"b5a81578-b3eb-4c2c-90f2-ccc07be79fe4","year":2022},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.045624Z"},"links":{"citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:1fbbf809560b6ca5fda6924db47285f65e2f2d4f4fe752e66537d5e9f8e0ac14","observation_id":"ea3dac1a-fb5c-4f69-9cdc-40ac09eaac60","resolution":{"observed_at":"2026-08-11T05:57:32.618090Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"2026-08-11T05:57:32.596024Z","title":"Disparities in dermatology ai performance on a diverse, curated clinical image set.Science advances, 8(31): eabq6147, 2022","venue":null,"work_id":"a79fcc66-ef1c-49f9-8380-a9ae19533982","year":2022},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.050202Z"},"links":{"citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:b596bbde47e64ecff71cae883b16187ee9fd748e016dc33033556bb3e3500fe8","observation_id":"6c1a8b83-66e1-4cc7-a057-e81bb29d1af3","resolution":{"observed_at":"2026-08-11T05:57:32.601558Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:57:32.580168Z","title":"A continual learning survey: Defying forgetting in classification tasks.IEEE transactions on pattern analysis and machine intelligence, 44(7):3366–3385, 2021","venue":null,"work_id":"f853886f-97db-4e3e-a860-e1c726711f7d","year":2021},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.054980Z"},"links":{"citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:b5e4e2e0d9256ee861a8a1cfd3a86a70d417820717a0bbf15863446f620ed093","observation_id":"85d737a2-4e2c-4442-bb05-d89814523d6f","resolution":{"observed_at":"2026-08-11T05:57:32.585814Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:57:32.564548Z","title":"Episodic memory in lifelong language learning.Advances in Neural Information Processing Systems, 32, 2019","venue":null,"work_id":"5ecc9693-21ef-48f8-827a-afeac10fcf59","year":2019},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.059492Z"},"links":{"citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:1ddb64be68ebd06db3c4ed3754b547abf45be5a98e0dd3f563e2b4e10d810635","observation_id":"d4456736-5eb5-41f1-b1b6-322c688050eb","resolution":{"observed_at":"2026-08-11T05:57:32.570382Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:57:31.064051Z","title":"Imagenet: A large-scale hierarchical image database","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.064051Z"},"links":{"citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:f9b7faa47b7413d91aa1cb6ecf1b169de914c7572dab626f481826ac7e9b754e","observation_id":"09aaf0cc-4c89-4e80-b66b-d570c2d0cac5","resolution":{"observed_at":"2026-08-11T05:57:31.064051Z","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":"2026-08-11T05:57:32.536129Z","title":"Continual learning beyond a single model","venue":null,"work_id":"dbda6354-eb43-48c7-9ba4-e791a67746cc","year":2023},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.068575Z"},"links":{"citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:ffc8201230f9adf377165ba0f4037c611624a4e0cac3d2a6465c42b502bac25c","observation_id":"294dee90-dea2-43d1-91f5-02e4989ec829","resolution":{"observed_at":"2026-08-11T05:57:32.541385Z","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":"2210.09929","last_updated":"2023-12-31T01:24:45Z","snapshot_observed_at":"2026-07-06T14:07:15.678393Z","submitted_at":"2022-10-18T15:20:47Z","title":"Differentially Private Diffusion Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.09929","snapshot_observed_at":"2026-08-11T05:57:31.072744Z","title":"Differentially private diffusion models.arXiv preprint arXiv:2210.09929, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.072744Z"},"links":{"cited_paper":"/paper/2210.09929","citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:9a44d58d144adc508568ecd79868f94d7957a95103c1cc44a30c3137f04ef088","observation_id":"00f13715-a822-4439-976b-dfc13e64e10c","resolution":{"observed_at":"2026-08-11T05:57:31.072744Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.11929","last_updated":"2021-06-03T13:08:56Z","snapshot_observed_at":"2026-08-10T01:12:16.468283Z","submitted_at":"2020-10-22T17:55:59Z","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.11929","snapshot_observed_at":"2026-08-11T05:57:31.077846Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale.arXiv preprint arXiv:2010.11929, 2020","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.077846Z"},"links":{"cited_paper":"/paper/2010.11929","citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:5009f62ee68e075e8da809a25a2c13fc0eb4b25f2f0fb59bb58fccb6ec890551","observation_id":"93c246cf-03b2-4de1-a8ee-65b5f732213b","resolution":{"observed_at":"2026-08-11T05:57:31.077846Z","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":"2026-08-11T05:57:32.519768Z","title":"Overcoming barriers to data sharing with medical image generation: a comprehensive evaluation.NPJ digital medicine, 4(1):141, 2021","venue":null,"work_id":"2e975eac-fe75-4647-89f3-b71de5f075da","year":2021},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.082839Z"},"links":{"citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:0c15735662f2eb3e5ba9280ab265fdc441613b95affec4c6348c19c3766877d2","observation_id":"0c704528-f45b-4450-b07d-8e4fc7d4229c","resolution":{"observed_at":"2026-08-11T05:57:32.525502Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:57:32.503681Z","title":"Now Publishers Inc., 2014","venue":null,"work_id":"73c9af25-624b-4ed5-8daa-5f0936fc1c08","year":2014},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.087933Z"},"links":{"citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:85db3fca90bd233de1f8f8effc193137dee5bd8b246d86664e85421979ad0dfd","observation_id":"9ceff1ff-27fe-48c2-a13f-985b1fa083b9","resolution":{"observed_at":"2026-08-11T05:57:32.509116Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:57:32.488119Z","title":"Calibrating noise to sensitivity in private data analysis","venue":null,"work_id":"24c01e31-7825-4a5b-9bc6-4cd89c53f700","year":2006},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.092805Z"},"links":{"citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:8111dd63968336d55a32163343252d252773161b438b20cbd4073dd76e517d5a","observation_id":"699480e2-1278-4329-b18f-8721d6806348","resolution":{"observed_at":"2026-08-11T05:57:32.493211Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:57:32.472949Z","title":null,"venue":null,"work_id":"0114519a-41c7-4421-a33c-608b8abd5e54","year":2022},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.097325Z"},"links":{"citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:ec41b257a9d791b745fc913c16fd41b1f6ed76c6b1fcae721429f41934ee62ae","observation_id":"f6fefa10-aff7-45d1-a4b2-41667d4fed0a","resolution":{"observed_at":"2026-08-11T05:57:32.478109Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:57:31.102267Z","title":"Catastrophic forgetting in connectionist networks.Trends in cognitive sciences, 3(4):128–135, 1999","venue":null,"work_id":null,"year":1999},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.102267Z"},"links":{"citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:528d63c12b9176afe211cf08225e15d68b718210173981d53ab317bd84eb2bc8","observation_id":"2b790e95-3d70-4c37-b563-28cea737157d","resolution":{"observed_at":"2026-08-11T05:57:31.102267Z","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":"2026-08-11T05:57:31.107021Z","title":"Domain adaptation for medical image analysis: a survey.IEEE Transactions on Biomedical Engineering, 69(3):1173–1185, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.107021Z"},"links":{"citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:7280681a82fc114c1def5e29397b85fd29be4fd9cfe18e4929c89985cc44a829","observation_id":"c30a9af6-d6a5-40c1-86ae-8900ca2e8612","resolution":{"observed_at":"2026-08-11T05:57:31.107021Z","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":"2026-08-11T05:57:32.433811Z","title":"Improved schemes for episodic memory-based lifelong learning.Advances in Neural Information Processing Systems, 33:1023–1035, 2020","venue":null,"work_id":"1c4d5563-5ddf-4170-a6c7-38f036710139","year":2020},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.111759Z"},"links":{"citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:96e0a229320df51bacc7d09e11eacf5b0a2eaec7007704329fd53632a26975e6","observation_id":"9e91b77e-a86e-4583-a6f8-5537b838d789","resolution":{"observed_at":"2026-08-11T05:57:32.439876Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:57:32.415951Z","title":"Dselect-k: Differentiable selection in the mixture of experts with applications to multi-task learning.Advances in Neural Information Processing Systems, 34:29335–29347, 2021","venue":null,"work_id":"cf4621b0-b716-415a-a712-d5e4a91b63a5","year":2021},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.116327Z"},"links":{"citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:8dc29d5e55c3432854c3df2cdb3a683485f266d8d53756c2466eae23c94838b6","observation_id":"51e851a1-57b8-4c1f-9f20-895925d13bd4","resolution":{"observed_at":"2026-08-11T05:57:32.421985Z","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":"2106.09685","last_updated":"2021-10-16T18:40:34Z","snapshot_observed_at":"2026-08-11T08:20:29.798517Z","submitted_at":"2021-06-17T17:37:18Z","title":"LoRA: Low-Rank Adaptation of Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.09685","snapshot_observed_at":"2026-08-11T05:57:31.121442Z","title":"Lora: Low-rank adaptation of large language models.arXiv preprint arXiv:2106.09685, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.121442Z"},"links":{"cited_paper":"/paper/2106.09685","citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:8936f1825b2ea1ecab55c8e990b9f90d10506255b773cdf6a74ecb9eaf63f09b","observation_id":"ca00f622-1e65-45c7-a57c-c4de43b6316a","resolution":{"observed_at":"2026-08-11T05:57:31.121442Z","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":"2026-08-11T05:57:32.391678Z","title":"Triviaqa: A large scale distantly supervised challenge dataset for reading comprehension","venue":null,"work_id":"e72a94fe-9ab2-43de-8f95-00dbf99d30cb","year":2017},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.126187Z"},"links":{"citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:95495d7f64df422976024005097f9cf7ab2d4a9d3d9e5a0063aba8ad4efda818","observation_id":"0656dfe3-853c-4e07-8d05-097eed025ef3","resolution":{"observed_at":"2026-08-11T05:57:32.403289Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:57:32.375218Z","title":"Early identification of patients admitted to hospital for covid-19 at risk of clinical deterioration: model development and multisite external validation study.bmj, 376, 2022","venue":null,"work_id":"32eb1aa0-8dd0-42b1-b4ec-af87df132c38","year":2022},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.130902Z"},"links":{"citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:33e2b79163756e8f99ecdc7f1cae255ef21aabf1ccb999cfb63ba43998332ced","observation_id":"b267bd63-c9ef-4846-9171-1d28ce71fd0b","resolution":{"observed_at":"2026-08-11T05:57:32.380638Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:57:31.135592Z","title":"Bert: Pre-training of deep bidirectional transformers for language understanding","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.135592Z"},"links":{"citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:1ceabf135024233375780628552b417088428e85ab0730ab85dc640968f94903","observation_id":"36f1bad6-57da-450f-a185-f0ba9e7d2592","resolution":{"observed_at":"2026-08-11T05:57:31.135592Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6980","last_updated":"2017-01-30T01:27:54Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2014-12-22T13:54:29Z","title":"Adam: A Method for Stochastic Optimization","version":9},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6980","snapshot_observed_at":"2026-08-11T05:57:31.140329Z","title":"Adam: A Method for Stochastic Optimization.arXiv Preprint arXiv:1412.6980, 2014","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.140329Z"},"links":{"cited_paper":"/paper/1412.6980","citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:7226b46c9e279fe3f8c72e778dbb31ef278edc3f079c1889df4e6dc086aae5b0","observation_id":"2056012c-820f-4649-ba85-eab43551132f","resolution":{"observed_at":"2026-08-11T05:57:31.140329Z","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":"2026-08-11T05:57:31.145173Z","title":"Rusu, Kieran Milan, John Quan, Tiago Ramalho, Agnieszka Grabska-Barwinska, Demis Hassabis, Claudia Clopath, Dharshan Kumaran, and Raia Hadsell","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.145173Z"},"links":{"citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:47029428784394e5e434d34f50efd54362f650bf0c96c7cf237748a2c644e39a","observation_id":"63a04f8c-0124-4b3c-8e6b-9e568224ff79","resolution":{"observed_at":"2026-08-11T05:57:31.145173Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.14124","last_updated":"2025-01-04T04:04:50Z","snapshot_observed_at":"2026-07-06T18:18:16.530605Z","submitted_at":"2024-05-23T02:49:57Z","title":"Mixture of Experts Meets Prompt-Based Continual Learning","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.14124","snapshot_observed_at":"2026-08-11T05:57:31.150082Z","title":"Mixture of experts meets prompt-based continual learning.arXiv preprint arXiv:2405.14124, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.150082Z"},"links":{"cited_paper":"/paper/2405.14124","citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:6f4d284fe8b6867b8157578e7425440bf7adf5980bf1fe556e94ea1b210c5398","observation_id":"c8a18f01-89e5-4b08-b39f-b946cdb53aaf","resolution":{"observed_at":"2026-08-11T05:57:31.150082Z","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":"2026-08-11T05:57:31.154927Z","title":"The power of scale for parameter-efficient prompt tuning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.154927Z"},"links":{"citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:4426ae4ea58625bb2f551e097ecd5bb453fc8ca0423aa96600e82e48d5f88c0e","observation_id":"f98b215c-432a-4681-be30-bbb5593bdada","resolution":{"observed_at":"2026-08-11T05:57:31.154927Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.16437","last_updated":"2025-02-19T14:35:07Z","snapshot_observed_at":"2026-07-06T18:35:54.300599Z","submitted_at":"2024-06-24T08:29:58Z","title":"Theory on Mixture-of-Experts in Continual Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.16437","snapshot_observed_at":"2026-08-11T05:57:31.159315Z","title":"Theory on mixture-of-experts in continual learning.arXiv preprint arXiv:2406.16437, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.159315Z"},"links":{"cited_paper":"/paper/2406.16437","citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:8b833e673eb22d88706a6ec8aa148262ff98b534db61be02db449b8a475263d5","observation_id":"bacf0a96-80fb-41d9-a915-674c43a1aa8a","resolution":{"observed_at":"2026-08-11T05:57:31.159315Z","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":"2026-08-11T05:57:32.336500Z","title":"Learn to grow: A continual structure learning framework for overcoming catastrophic forgetting","venue":null,"work_id":"cde60f7c-f4e9-492d-bba5-88174aaa244e","year":2019},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.163905Z"},"links":{"citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:577e14480a0672a51b354257ead136d9ba6bf42da21d839d440f254548ba219b","observation_id":"2816fd85-1ddf-4470-b92b-0e2227bcae64","resolution":{"observed_at":"2026-08-11T05:57:32.342404Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:57:31.168603Z","title":"Learning without forgetting.IEEE transactions on pattern analysis and machine intelligence, 40(12):2935–2947, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.168603Z"},"links":{"citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:521f25bf5f123e845be4a45e28e6a681e3cd4de58edbbf6427af4a8dc9658ee5","observation_id":"2cdfd59c-3232-471d-9d40-2c81552a4ec4","resolution":{"observed_at":"2026-08-11T05:57:31.168603Z","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":"2026-08-11T05:57:32.307237Z","title":"The clear benchmark: Continual learning on real-world imagery","venue":null,"work_id":"8ab7d57c-4575-4efb-84c4-c3ad8ed4b95f","year":2021},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.173053Z"},"links":{"citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:a2f73eb738b577e8bb45cac47195fdbb5b905a5debba1a38c3274c8933f8bb46","observation_id":"7d590c6f-db44-4d2c-9d27-54918ebd35ca","resolution":{"observed_at":"2026-08-11T05:57:32.312991Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:57:31.177422Z","title":"Core50: a new dataset and benchmark for continuous object recognition","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.177422Z"},"links":{"citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:0159540df873706f1b9f504bc14a6b161d8476ce9b0804d02cbf8acfba67e82c","observation_id":"27466e0d-d195-49c3-9bb8-94f9be8a770e","resolution":{"observed_at":"2026-08-11T05:57:31.177422Z","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":"2026-08-11T05:57:31.181897Z","title":"Gradient episodic memory for continual learning","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.181897Z"},"links":{"citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:c8af177b47324662d0ad0c5ffd1b05bb65f2e7c6438db126489fd81ce614e1c3","observation_id":"47c7291e-f369-4b26-982b-54971d62edce","resolution":{"observed_at":"2026-08-11T05:57:31.181897Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1711.05101","last_updated":"2019-01-04T21:01:49Z","snapshot_observed_at":"2026-08-09T20:34:52.923500Z","submitted_at":"2017-11-14T14:24:06Z","title":"Decoupled Weight Decay Regularization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.05101","snapshot_observed_at":"2026-08-11T05:57:31.186164Z","title":"Decoupled weight decay regularization.arXiv preprint arXiv:1711.05101, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.186164Z"},"links":{"cited_paper":"/paper/1711.05101","citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:ae0bd6cd94ef79199ee89ccc959080a1a038ae1ac9c0dc2411a64cc6abfff6c4","observation_id":"77e73637-e62c-4c3f-8a3b-132c29c9aa64","resolution":{"observed_at":"2026-08-11T05:57:31.186164Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.15759","last_updated":"2025-03-05T08:34:25Z","snapshot_observed_at":"2026-08-01T16:41:42.081136Z","submitted_at":"2023-05-25T06:18:31Z","title":"DP-LDMs: Differentially Private Latent Diffusion Models","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.15759","snapshot_observed_at":"2026-08-11T05:57:31.190933Z","title":"Differentially private latent diffusion models.arXiv preprint arXiv:2305.15759, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.190933Z"},"links":{"cited_paper":"/paper/2305.15759","citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:ab3c2b8a2b669f453d83e5176954c7cfa211625dbc1984e152143334e5b21f7d","observation_id":"fb6f1dc6-1f5b-415a-9ce1-f40354fdeadc","resolution":{"observed_at":"2026-08-11T05:57:31.190933Z","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":"2026-08-11T05:57:31.195753Z","title":"Modeling task relationships in multi-task learning with multi-gate mixture-of-experts","venue":null,"work_id":null,"year":1930},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.195753Z"},"links":{"citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:cb7b9deca001075741400a499af164f75f8d2ef6803af675ddb7295462535453","observation_id":"e09d318a-92b7-4f51-8c67-afd8e12fa27d","resolution":{"observed_at":"2026-08-11T05:57:31.195753Z","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":"2026-08-11T05:57:31.200258Z","title":"Catastrophic interference in connectionist networks: The sequential learning problem","venue":null,"work_id":null,"year":1989},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.200258Z"},"links":{"citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:2aa27e9dd464231a34f9e2f87075ce99c6ef4d70d7e2495a318459a9a88003e0","observation_id":"b4ce00fd-9b3e-4c35-9729-a86f33e806bd","resolution":{"observed_at":"2026-08-11T05:57:31.200258Z","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":"2026-08-11T05:57:32.236807Z","title":"An empirical investigation of the role of pre-training in lifelong learning.Journal of Machine Learning Research, 24(214):1–50, 2023","venue":null,"work_id":"88103ef5-5b60-47cc-bd30-70b218aa9d3c","year":2023},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.205125Z"},"links":{"citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:40ed10b8212ae783d344e5a7fac8d3a7b83ece90b1d35086cc2726f01816ba9b","observation_id":"d231e1ea-6f26-4f8e-87fe-936d1f822ffd","resolution":{"observed_at":"2026-08-11T05:57:32.243965Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:57:32.217219Z","title":"Pad-ufes-20: A skin lesion dataset composed of patient data and clinical images collected from smartphones.Data in brief, 32:106221, 2020","venue":null,"work_id":"78b6f225-2347-4ece-a2ff-e98c40f85f1b","year":2020},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.209608Z"},"links":{"citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:9f26d14a2e9aa1aba8d45cf2aea13c21121655312eaaa8b37b117624b6a58164","observation_id":"2659e6da-ac8c-4b43-9ede-0450c8a66fdf","resolution":{"observed_at":"2026-08-11T05:57:32.224125Z","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":"2405.11530","last_updated":"2024-05-19T11:55:48Z","snapshot_observed_at":"2026-08-01T15:38:47.662370Z","submitted_at":"2024-05-19T11:55:48Z","title":"Learning More Generalized Experts by Merging Experts in Mixture-of-Experts","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.11530","snapshot_observed_at":"2026-08-11T05:57:31.214178Z","title":"Learning more generalized experts by merging experts in mixture-of-experts.arXiv preprint arXiv:2405.11530, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.214178Z"},"links":{"cited_paper":"/paper/2405.11530","citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:3c4ab1497fe1422e43d5c0dc134b937533633e8a5f5bef5d7c71fc3f23a1783d","observation_id":"2b9c76ff-412c-47db-a205-38ccd8f80098","resolution":{"observed_at":"2026-08-11T05:57:31.214178Z","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":"2026-08-11T05:57:32.196456Z","title":"Moment matching for multi-source domain adaptation","venue":null,"work_id":"c3dd740b-511f-47a7-b5e9-e304d3a8c179","year":2019},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.219142Z"},"links":{"citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:1ecfa6415d247567b5e6a5575dda156e9d93a2b895fdca8fb5ee5c203f4dfc04","observation_id":"4884ffe6-2f9e-4ca4-808a-2e3aa69fc6e3","resolution":{"observed_at":"2026-08-11T05:57:32.203744Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:57:32.180022Z","title":"Can we trust deep learning based diagnosis? the impact of domain shift in chest radiograph classification","venue":null,"work_id":"daca66df-08cb-4902-87c6-2112059cd80f","year":2020},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.224841Z"},"links":{"citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:79e5141901bc81ea6fc0c14a68608c77a847b75aeaef7c1afb7d89e8779cd0cd","observation_id":"cb223e8b-26e0-4e32-a398-8010d70e1fc8","resolution":{"observed_at":"2026-08-11T05:57:32.185249Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:57:32.159950Z","title":"LFPT5: A unified framework for lifelong few-shot language learning based on prompt tuning of t5","venue":null,"work_id":"78704cc8-67fb-4240-8bf2-5fae4b3d294c","year":2022},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.229682Z"},"links":{"citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:041146496d5c7b95beea7e32050cd24aa9adcf32444b238ad445540667f1c473","observation_id":"ee4a2c01-1727-43ce-9e25-2aa7f296860d","resolution":{"observed_at":"2026-08-11T05:57:32.168116Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:57:31.234524Z","title":"Exploring the limits of transfer learning with a unified text-to-text transformer.The Journal of Machine Learning Research, 21(1):5485–5551, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.234524Z"},"links":{"citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:2b90073f3062b6c61352963d552699e7cf54121bca4f5ae001b509664dd3acd2","observation_id":"c6f45dd2-ff33-4678-9dab-c49f21d8c77a","resolution":{"observed_at":"2026-08-11T05:57:31.234524Z","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":"2026-08-11T05:57:31.239336Z","title":"Squad: 100,000+ questions for machine comprehension of text","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.239336Z"},"links":{"citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:ecfee2640df895fddc92d96af9c9b291442acd17831817cf000b9585817eaee5","observation_id":"ec8c3b1e-e913-428d-a92b-7440bdf4262e","resolution":{"observed_at":"2026-08-11T05:57:31.239336Z","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":"2026-08-11T05:57:31.244277Z","title":"High- resolution image synthesis with latent diffusion models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.244277Z"},"links":{"citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:c8d0efba6499d8c845d3f52992a4143cccb27382d84a0bdea6c3e3da48436e5c","observation_id":"3a4ed309-0ffa-4484-a6a0-b59c3917156c","resolution":{"observed_at":"2026-08-11T05:57:31.244277Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.10191","last_updated":"2024-03-19T14:09:31Z","snapshot_observed_at":"2026-07-06T17:17:31.008185Z","submitted_at":"2024-01-18T18:25:29Z","title":"Divide and not forget: Ensemble of selectively trained experts in Continual Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.10191","snapshot_observed_at":"2026-08-11T05:57:31.249346Z","title":"Divide and not forget: Ensemble of selectively trained experts in continual learning.arXiv preprint arXiv:2401.10191, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.249346Z"},"links":{"cited_paper":"/paper/2401.10191","citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:8299cfabf9261d1c5fa85e2ca51a26d3574c3e2ac40a5fc6436ca12f80640739","observation_id":"62c38501-8b31-4da3-b3b9-58bcf45bb3a9","resolution":{"observed_at":"2026-08-11T05:57:31.249346Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1701.06538","last_updated":"2017-01-23T18:10:00Z","snapshot_observed_at":"2026-08-11T16:18:55.320420Z","submitted_at":"2017-01-23T18:10:00Z","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1701.06538","snapshot_observed_at":"2026-08-11T05:57:31.253975Z","title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer.arXiv preprint arXiv:1701.06538, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.253975Z"},"links":{"cited_paper":"/paper/1701.06538","citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:d572b363f2a8af31cf8cd894700827d8a4a3e5cd999758d097a4452e9fc0dccf","observation_id":"4a7bf659-9d31-4668-a24a-30cf736bb663","resolution":{"observed_at":"2026-08-11T05:57:31.253975Z","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":"2026-08-11T05:57:31.259171Z","title":"Continual learning with deep generative replay.Advances in neural information processing systems, 30, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.259171Z"},"links":{"citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:f776378db23915ac7254ade959a450ba18338b1d07199d0dd24938df1e224980","observation_id":"577e4dfe-f952-4465-8bd5-535e77a250df","resolution":{"observed_at":"2026-08-11T05:57:31.259171Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.06027","last_updated":"2024-05-02T17:43:34Z","snapshot_observed_at":"2026-07-06T15:14:59.488000Z","submitted_at":"2023-04-12T17:59:41Z","title":"Continual Diffusion: Continual Customization of Text-to-Image Diffusion with C-LoRA","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.06027","snapshot_observed_at":"2026-08-11T05:57:31.263942Z","title":"Continual diffusion: Continual customization of text-to-image diffusion with c-lora.arXiv preprint arXiv:2304.06027, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.263942Z"},"links":{"cited_paper":"/paper/2304.06027","citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:fa6b257f0d37f8286ebf605c0fb3aef90bde8b783f3199af18e90411f6110877","observation_id":"69828bf9-b98a-4cbf-9d1e-f1f83074768a","resolution":{"observed_at":"2026-08-11T05:57:31.263942Z","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":"2026-08-11T05:57:32.097395Z","title":"Coda-prompt: Continual de- composed attention-based prompting for rehearsal-free continual learning","venue":null,"work_id":"4d828abe-761f-409b-a3d4-1618c643829a","year":2023},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.269043Z"},"links":{"citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:794f069d433eef03e946c5a69823ecf5ffe9ff55a5ecb8c794c10ade2ca57325","observation_id":"a91e4a4b-cd1c-4b2f-bdf5-185faba174ff","resolution":{"observed_at":"2026-08-11T05:57:32.103281Z","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":"2207.04354","last_updated":"2022-07-12T15:47:04Z","snapshot_observed_at":"2026-07-06T13:29:32.211007Z","submitted_at":"2022-07-10T00:48:42Z","title":"An Introduction to Lifelong Supervised Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2207.04354","snapshot_observed_at":"2026-08-11T05:57:31.274531Z","title":"An introduction to lifelong supervised learning.arXiv preprint arXiv:2207.04354, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.274531Z"},"links":{"cited_paper":"/paper/2207.04354","citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:58bd0efd39af9ee6185b7f093f3c3eb151b04a31180ded9df1f606a161455eca","observation_id":"5cdc4ca7-5f9f-4d93-ad84-976e4d51d465","resolution":{"observed_at":"2026-08-11T05:57:31.274531Z","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":"2026-08-11T05:57:32.078123Z","title":"{LAMAL}: {LA}nguage modeling is all you need for lifelong language learning","venue":null,"work_id":"7df8fe79-790e-48cc-985b-6dc92e0d1cca","year":2020},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.280356Z"},"links":{"citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:30ce479deae6fcc3ada2a1cb168aca697f23ea1dddb437b5a8ef1eb7163dee20","observation_id":"e5a88997-c146-457c-b990-179a185027d4","resolution":{"observed_at":"2026-08-11T05:57:32.083615Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:57:31.285323Z","title":"The ham10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions.Scientific data, 5(1):1–9, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.285323Z"},"links":{"citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:2a5ffcc7b8ddd45c0a99fcea56863bcbf0d1c4981d5fbeb7af9f703f714bae0e","observation_id":"955e76e9-b0c0-4b3f-9935-b67da6d15329","resolution":{"observed_at":"2026-08-11T05:57:31.285323Z","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":"2026-08-11T05:57:32.050774Z","title":null,"venue":null,"work_id":"6a5536f5-4e90-4425-8092-76d303a37a88","year":2022},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.290708Z"},"links":{"citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:420dfd8553be86e3db6ed3d5b4c728dc9d78e21eb067aa3b88624e1f20e64ce5","observation_id":"a6a23436-a6b7-4456-bd9f-ffe7227d6ec3","resolution":{"observed_at":"2026-08-11T05:57:32.056162Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"1904.07734","last_updated":"2019-04-15T12:22:36Z","snapshot_observed_at":"2026-07-06T07:46:29.188511Z","submitted_at":"2019-04-15T12:22:36Z","title":"Three scenarios for continual learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1904.07734","snapshot_observed_at":"2026-08-11T05:57:31.295563Z","title":"Three scenarios for continual learning.arXiv preprint arXiv:1904.07734, 2019","venue":null,"work_id":null,"year":1904},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.295563Z"},"links":{"cited_paper":"/paper/1904.07734","citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:16810ef38107748b3a8dcd2d8feab633481dfe02bf4ac6ca0edcf99176f21bc2","observation_id":"bb240881-11eb-43f7-87ea-4e4fb159e207","resolution":{"observed_at":"2026-08-11T05:57:31.295563Z","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":"2026-08-11T05:57:31.300522Z","title":"Visualizing data using t-sne.Journal of machine learning research, 9(11), 2008","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.300522Z"},"links":{"citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:c67bf6201b770cafe46b1186dc8efc0edf288fda8f77ccb448c74674e640ddda","observation_id":"7b5c6ec2-06a9-4b8e-8a69-580f9f4a5164","resolution":{"observed_at":"2026-08-11T05:57:31.300522Z","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":"2026-08-11T05:57:32.021941Z","title":"Development and multi-site external validation of a generalizable risk prediction model for bipolar disorder.medRxiv, pages 2023–02, 2023","venue":null,"work_id":"401c3f37-048d-4048-acbd-926ea66d4b7b","year":2023},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.305007Z"},"links":{"citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:08cba62848f50ade5435abdf8977c5749dc6bb76266ecf1d125f2d7d05e052df","observation_id":"87588a2c-8496-4e7e-99c1-39458d28e27f","resolution":{"observed_at":"2026-08-11T05:57:32.027793Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:57:31.310123Z","title":"Coscl: Cooperation of small continual learners is stronger than a big one","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.310123Z"},"links":{"citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:05bbb3ead06b961b15a4ce7b4226e04c77bcb8cab2f4d616da9e1a6cb1ee4b1d","observation_id":"37dc7dec-a101-4c57-a3fe-f8d924126516","resolution":{"observed_at":"2026-08-11T05:57:31.310123Z","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":"2026-08-11T05:57:31.987351Z","title":"Hierarchical decomposition of prompt-based continual learning: Rethinking obscured sub-optimality.Advances in Neural Information Processing Systems, 36, 2024","venue":null,"work_id":"7e6b17f2-ab5f-451f-b12b-2fd82b44bbb8","year":2024},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.314932Z"},"links":{"citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:253b0a603cf8303f14165e91752330942509256a573ea15049ade9bbec80e66e","observation_id":"778752bd-6d74-4c68-9c57-e97f616cc089","resolution":{"observed_at":"2026-08-11T05:57:31.993906Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:57:31.966102Z","title":"S-prompts learning with pre-trained transformers: An occam’s razor for domain incremental learning","venue":null,"work_id":"4d03460b-6893-4627-aafe-5bc62578a8a5","year":2022},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.319576Z"},"links":{"citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:714fd4c01df2df54b0d25578ffe787f7df1bd1b9d2f6234db7444230e1cc2566","observation_id":"ebbf925c-6fe5-49a2-bbad-6bb68f93fd31","resolution":{"observed_at":"2026-08-11T05:57:31.973117Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:57:31.324695Z","title":"Dualprompt: Complementary prompting for rehearsal-free continual learning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.324695Z"},"links":{"citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:9d302f4e7fe301908ed6eb48f7c619f05bf37c669c8479b4214c4c75ed55faf3","observation_id":"6ee5b627-a790-4114-83e2-5aaa077b34eb","resolution":{"observed_at":"2026-08-11T05:57:31.324695Z","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":"2026-08-11T05:57:31.333192Z","title":"Learning to prompt for continual learning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.333192Z"},"links":{"citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:7d02c70b24e8eba689365c5e7825b0d09fea96613af408fe71b404e6aea8d026","observation_id":"fe7ef7a3-e138-4adc-bea6-b4fd77ece1b7","resolution":{"observed_at":"2026-08-11T05:57:31.333192Z","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":"2026-08-11T05:57:31.920747Z","title":"Efficient meta lifelong-learning with limited memory","venue":null,"work_id":"f3a27b8e-ce2c-42a9-80a2-f607bec14e29","year":2020},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.338218Z"},"links":{"citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:03e7c6ff0ca4e6f481aee8f5571934451208c792c975d8e4b8bae0d01f16e531","observation_id":"62fb31f0-7e1f-457f-a215-ad13793616ab","resolution":{"observed_at":"2026-08-11T05:57:31.929497Z","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":"2304.08486","last_updated":"2023-06-26T15:47:27Z","snapshot_observed_at":"2026-07-06T15:16:38.500909Z","submitted_at":"2023-04-17T17:59:26Z","title":"BenchMD: A Benchmark for Unified Learning on Medical Images and Sensors","version":2},"cited_work":{"arxiv_id":"2304.08486","doi":null,"metadata_source":"pith","pith_arxiv_id":"2304.08486","snapshot_observed_at":"2026-08-11T05:57:31.477448Z","title":"BenchMD: A Benchmark for Unified Learning on Medical Images and Sensors","venue":"cs.CV","work_id":"f2e3cabf-a19a-48dc-9ee9-f7c68edd9e96","year":2023},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.343077Z"},"links":{"cited_paper":"/paper/2304.08486","citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:3b3f82602d69e1f112ac112e16c314488e88117e00032681e12f53db9a6baf33","observation_id":"d6575dd5-b26c-4360-afe1-b7633744bf1e","resolution":{"observed_at":"2026-08-11T05:57:31.485357Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:57:31.348280Z","title":"Boosting continual learning of vision-language models via mixture-of-experts adapters","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.348280Z"},"links":{"citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:0fae12f4fc9dae95fadab0ba003192b97533c8aa0e8fbe8244ae190054fcf723","observation_id":"33ae1996-2132-4d55-b067-3319dfaca1d2","resolution":{"observed_at":"2026-08-11T05:57:31.348280Z","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":"2026-08-11T05:57:31.357172Z","title":"Variable generalization performance of a deep learning model to detect pneumonia in chest radiographs: a cross-sectional study.PLoS medicine, 15(11):e1002683, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.357172Z"},"links":{"citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:5e6e71546c35492c3074ce49f5d55f77e62c9683f83b36929899afa4574ddd2d","observation_id":"820d1a40-6c7e-4b1f-81be-386c4b2d81a5","resolution":{"observed_at":"2026-08-11T05:57:31.357172Z","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":"2026-08-11T05:57:31.362861Z","title":"Continual learning through synaptic intelligence","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.362861Z"},"links":{"citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:8bd7311605a65d686f5b6f3283247002f9872d1a930a622080d25f3cc48c33c0","observation_id":"f3083eac-9018-4df9-94e6-eb8b7b2f644f","resolution":{"observed_at":"2026-08-11T05:57:31.362861Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.16386","last_updated":"2024-04-23T10:44:01Z","snapshot_observed_at":"2026-07-06T17:21:58.983048Z","submitted_at":"2024-01-29T18:27:52Z","title":"Continual Learning with Pre-Trained Models: A Survey","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.16386","snapshot_observed_at":"2026-08-11T05:57:31.367933Z","title":"Continual learning with pre-trained models: A survey.arXiv preprint arXiv:2401.16386, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.367933Z"},"links":{"cited_paper":"/paper/2401.16386","citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:299b26500dc9684309092d882251243c2b44946b1805e701d95f525182836751","observation_id":"e1eaa1cf-c5e1-4465-a000-e143b1a19a32","resolution":{"observed_at":"2026-08-11T05:57:31.367933Z","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":"2026-08-11T05:57:31.871801Z","title":"Mixture-of-experts with expert choice routing.Advances in Neural Information Processing Systems, 35:7103–7114, 2022","venue":null,"work_id":"67f67e21-aaeb-4ee2-b5b2-d543e2bcd17f","year":2022},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.373428Z"},"links":{"citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:6edf2267c2095a4929d09257107b19ddf7af2674a7b8961ed7a3405a49c29355","observation_id":"cdc13217-42ca-4434-bba6-2a158b922d02","resolution":{"observed_at":"2026-08-11T05:57:31.877446Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:57:31.853573Z","title":null,"venue":null,"work_id":"3264356b-3ea4-4195-b8bd-99f443480369","year":null},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.378405Z"},"links":{"citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:0296c88d4c32b821e0619666f48307d73a088e47106eadcb2ed5f4f3806d610f","observation_id":"0d3b8093-3836-4ffb-8599-a48003d1c6d6","resolution":{"observed_at":"2026-08-11T05:57:31.859336Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"2026-08-11T05:57:31.834946Z","title":null,"venue":null,"work_id":"4ee003f3-28b0-4e83-a484-282fd91f9a97","year":null},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.384141Z"},"links":{"citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:df4080f63489f8808fce4b01f08be7bf18ae5ecf96aa239fad652a1736841405","observation_id":"56c10383-b2df-48c4-aefe-99f146ccf794","resolution":{"observed_at":"2026-08-11T05:57:31.840415Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"2026-08-11T05:57:31.816583Z","title":null,"venue":null,"work_id":"4eca17bf-f7df-4e55-a6e9-339dbe8eaf5d","year":null},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.388934Z"},"links":{"citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:38d45c0f4b48b0746e45f507393937e053e28b5847ecdaa03c0d188d94a8103e","observation_id":"e88470f6-9a3d-4b99-8fab-13fe6c7621c4","resolution":{"observed_at":"2026-08-11T05:57:31.821263Z","resolver_source":"raw_fallback","status":"unresolved"},"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":"2026-08-11T05:57:31.799403Z","title":"Generate article, question and answer","venue":null,"work_id":"14b6771b-8d27-4ba5-8a6a-5ef0c2d8e9cb","year":2010},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.395067Z"},"links":{"citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:f5f52b06d218a06e9555d4410376039b8ab51d0ee305fe6d5443ee6712455ea9","observation_id":"97f84c41-11b6-4bf8-9eb6-46b25cc0d902","resolution":{"observed_at":"2026-08-11T05:57:31.804847Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:57:31.780328Z","title":"(2) In the original Generative Replay implementation, the generator is sequentially finetuned (in addition to the classifier) on each domain in the sequence","venue":null,"work_id":"eb355412-1258-40e6-8ffe-f2f6cfbe79b8","year":null},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.400133Z"},"links":{"citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:bc92e37c03ca8853ad2010b543edf6ecf05e470c74f7c164c18ced373ecbb8e6","observation_id":"524ecbb5-830f-4310-9d72-6fdd610c7775","resolution":{"observed_at":"2026-08-11T05:57:31.787122Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T05:57:31.762499Z","title":"The BERT-base architecture has 12 Transformer layers, 12 self-attention heads, and 768 hidden dimensions (110M parameters)","venue":null,"work_id":"32c52419-44b4-41a5-88b8-60f68a7a122f","year":null},"citing_paper":{"arxiv_id":"2412.17009","last_updated":"2025-08-28T17:13:51Z","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning","version":3},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-11T05:57:31.405043Z"},"links":{"citing_paper":"/paper/2412.17009"},"observation_digest":"sha256:079181cd3e7910b6bc01828596b212e87eaf93e6239533e23d9e5c5e56d3b40a","observation_id":"8a11a4e6-c5da-4e7a-9540-806eb1401470","resolution":{"observed_at":"2026-08-11T05:57:31.769064Z","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":"2412.17009","last_updated":"2025-08-28T17:13:51Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-11T05:50:35.219770Z","submitted_at":"2024-12-22T13:16:28Z","title":"Expert Routing with Synthetic Data for Continual Learning"},"reference_resolution":{"displayed":82,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":49,"verified_exact":1,"verified_fuzzy":32},"total_outbound_references":82},"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 82 of 82 outbound references and 0 inbound Pith citation observations for arXiv:2412.17009."}