{"as_of":"2026-08-04T23:29:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:7469c47e07310d112953b4bdc07d357d463038464bb32826520392cc2ff60f75","coverage":[{"denominator":65,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":65,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-10T04:44:46.383126Z","state":"measured"},{"denominator":65,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":65,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-04T06:34:03.388597+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/2604.18842/citation-record","integrity":"/paper/2604.18842/integrity","json":"/paper/2604.18842/citation-record.json","paper":"/paper/2604.18842"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Zero-shot sparse mixture of low-rank experts construction from pre- trained foundation models","venue":null,"work_id":"7b34e74b-e22f-492c-a678-b8de3dda6bb9","year":2025},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:a2451e1df36b099679e1dba3aee9650f1888070d587f9a3d8a966cf179786c91","observation_id":"6ad25bad-63b5-4d56-a9d1-588a8cdd0164","resolution":{"observed_at":"2026-05-22T02:34:32.796628Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Large-scale object detection in the wild with imbalanced data distribution, and multi-labels","venue":null,"work_id":"a2962fe5-858f-472e-a491-d6863e51d92d","year":2024},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:d7b46e69782d24d13beecdc5b95f3baa0427b96567c43484385f0a9dfee469c5","observation_id":"a32d70cd-121f-4b82-957b-cb418204a810","resolution":{"observed_at":"2026-05-22T02:34:32.793344Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Learning heterogeneous mixture of scene experts for large-scale neural radiance fields","venue":null,"work_id":"f659e44b-dace-4e3f-be1f-b4d8c2bf7bc5","year":2025},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:3f0690ecfb9ef4bccf118667707f492b9df808e59071352fd15327dd8d0b3f63","observation_id":"db227370-aff5-4437-bf5c-390e9323ce8c","resolution":{"observed_at":"2026-05-22T02:34:32.799947Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Sparse mixture-of-experts are domain generalizable learners","venue":null,"work_id":"1ef4e1fa-c5e8-4947-91de-74bb1f8c61e2","year":2023},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:fcd085f76ab4d12fc4fb7976b4e55a31b10eb1c454b23eca57f94525f454924f","observation_id":"99f14c2b-ae96-4aa7-88bd-5b09471850f4","resolution":{"observed_at":"2026-05-22T02:34:32.805031Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Setformer is what you need for vision and language","venue":null,"work_id":"77f12879-877a-49f6-afac-4d646d92f443","year":2024},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:dd5f423fc8d399312940a2996730270ce51df2cb807e37fb2722611a3c5805b6","observation_id":"6ec88ae9-31f7-4a87-b050-3e1c8451d68e","resolution":{"observed_at":"2026-05-22T02:34:32.799180Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Learning general and specific embedding with transformer for few-shot object detection","venue":null,"work_id":"3e0db57b-a3ee-4ea1-8f13-8b34694c3cd5","year":2025},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:e6323d9bd95ee6ec939b019d0863535adceaa8271addf2db1ad6e65abd1415f6","observation_id":"b9ee69eb-8ab5-41a2-93cb-e6317eba06ab","resolution":{"observed_at":"2026-05-22T02:34:32.806449Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Microsoft coco: Common objects in context","venue":null,"work_id":"ef0aac3e-d211-4747-a8d7-aef8e7665474","year":2014},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:2a08d68416b848958155b04e59fb75539bd571b9f2f96bda679c328bac2e740f","observation_id":"cbe823b0-2fe7-4c25-992b-8135a03545ff","resolution":{"observed_at":"2026-05-22T02:34:32.812090Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Cross-domain weakly-supervised object detection through progressive domain adapta- tion","venue":null,"work_id":"786c5ec3-d790-486a-83e6-603d0ee15a50","year":2018},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:7bc640cfeca32c0670e3fbf6eb9ff5190ca61c60e748ef986f112928ce22eb29","observation_id":"325786aa-de03-4b2a-a188-3b21eb42f7b6","resolution":{"observed_at":"2026-05-22T02:34:32.815356Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Efficient parametrization of multi-domain deep neural networks","venue":null,"work_id":"3ab37485-959d-4eec-b322-5646815d9ad1","year":2018},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:88e050703eb49077d14a5117b954df5ec591d8a5e549959e9953e6c9ed4f0636","observation_id":"ce1e2c1c-5706-448c-bee7-dd7050330476","resolution":{"observed_at":"2026-05-22T02:34:32.809273Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Damex: Dataset-aware mixture- of-experts for visual understanding of mixture-of-datasets","venue":null,"work_id":"28c4c2c6-db03-429b-8c4e-a9773aa1dc36","year":2024},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:4fb303313c7746ff496b3d0269ae443fab9e38c39ece76bb6992d3d2b36158ad","observation_id":"721cf479-7680-4728-b7c4-4a8345cd25e4","resolution":{"observed_at":"2026-05-22T02:34:32.786196Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Simple multi-dataset detection","venue":null,"work_id":"94e480e8-418c-4d83-a9bd-396b4f43c44b","year":2022},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:a29db6d52410d1c3db9954b6628f3a43827190aed94ec5c83757bebe0d53a0f8","observation_id":"3721a61a-8f91-43c7-b2ed-785acfe82592","resolution":{"observed_at":"2026-05-22T02:34:32.781872Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Towards universal object detection by domain attention","venue":null,"work_id":"5b142975-55d5-4502-a4c4-545d9b39140d","year":2019},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:93b853f63fad63d227018dd9c77781fedbbe4362c3467fe4cef2a8e8d11a8ea1","observation_id":"aa1f1ab3-2ae8-47f3-84b5-161588190a40","resolution":{"observed_at":"2026-05-22T02:34:32.781202Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Detection hub: Unifying object detection datasets via query adaptation on language embedding","venue":null,"work_id":"1f871076-f586-4d44-867d-cb0aceff3d67","year":2023},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:da10a75d24f83226484492affa862cc990cebab4093afcf025df6fd936ebe2d3","observation_id":"257d7eeb-df60-49c6-9edf-71373554fa83","resolution":{"observed_at":"2026-05-22T02:34:32.752614Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Multi-dataset, multitask learning of egocentric vision tasks","venue":null,"work_id":"66691df5-0590-49b6-9c61-e7853da9bf68","year":2022},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:2c5aeaec536e4e46d5bdcfd6338acee482a4e48c2d93b78fe6c1d81a87fd4663","observation_id":"77256ac4-8359-42a2-ab22-4108cadc2ec6","resolution":{"observed_at":"2026-05-22T02:34:32.686012Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Plain-det: A plain multi-dataset object detector","venue":null,"work_id":"4d582823-8a68-4dd1-9e6c-5bcd33ef8b65","year":2024},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:6d0928f8b29a836f19afc3a400d03b04685ae7237a92a32bce34ee1af1de5aec","observation_id":"f3513801-bb1f-467a-b1bd-9d418e67dd06","resolution":{"observed_at":"2026-05-22T02:34:32.675250Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer","venue":null,"work_id":"85ad6eca-3297-4577-a6e6-4e82b806177f","year":2017},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:e7c4bb46a19a8339300a0d96edc77d84724e8801b3575bbce8db90315e7de2bd","observation_id":"f2c52820-da6b-41e1-9bb2-01a10a6de8e0","resolution":{"observed_at":"2026-05-22T02:34:32.731853Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Remoe: Fully differentiable mixture-of- experts with relu routing","venue":null,"work_id":"02ea8e1a-9404-44a6-b49d-f3707e489daa","year":2025},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:96affabe9aaa48b3923c818c475c0b63711fa751a62874c70d2d436941796421","observation_id":"4948a7f9-c4e0-453f-9e1b-6ccddbeae36d","resolution":{"observed_at":"2026-05-22T02:34:32.702952Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Mergeme: Model merging techniques for homogeneous and heterogeneous moes","venue":null,"work_id":"c5cd8f60-577d-4c0e-9181-2835317a1ccd","year":2025},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:a4f4b6e5f23217deb5677ffcf1cc33201e26d7170ead7cd70777179b9253f53a","observation_id":"b011d169-0d30-40cb-baf1-191fa6b508e1","resolution":{"observed_at":"2026-05-22T02:34:32.673200Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Mocae: Mixture of calibrated experts significantly improves object detection","venue":null,"work_id":"dc3f8475-b520-499c-8688-09837304d543","year":2024},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:8dd9afb281ce2d5662dcd3b2a49b904e88e8c9057fc3190ba8092f7e61ed22b0","observation_id":"1f10ebe5-c5a0-4d97-be39-29d82718be30","resolution":{"observed_at":"2026-05-22T02:34:32.772201Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-07-05T02:00:37.681631Z","title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","venue":null,"work_id":"8b984fb3-6f4d-4a9e-acbb-a3d4124f8c1e","year":2022},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:d9167f01f24a6567927d0ff828905241ca6312ce580c44b2858bfba7dff6793f","observation_id":"3a822ced-d81d-4058-99ec-aab9f7939638","resolution":{"observed_at":"2026-05-22T02:34:32.685768Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Deepseekmoe: Towards ultimate expert specialization in mixture-of-experts language models","venue":null,"work_id":"5f33baa2-089e-4037-8cbb-2d10b4bd9f10","year":2024},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:64495aad6a9e215dd7be351f6740d30a4858a2099eeb71d6060093d50f32a138","observation_id":"303aaa31-492f-4875-b291-100ad221fc7b","resolution":{"observed_at":"2026-05-22T02:34:32.759957Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Multilinear mixture of experts: Scalable expert specialization through factorization","venue":null,"work_id":"f9c287e1-a844-4bda-8da0-d63180c26233","year":2024},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:01bdabde202a75d09acbaa16addb21d0e91e7dbde6596ede164af683270f780f","observation_id":"2451a8db-9f46-4d6b-8b98-26527a126e6c","resolution":{"observed_at":"2026-05-22T02:34:32.635747Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2506.14038","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-04T14:59:55.369015Z","title":"Load balancing mixture of experts with similarity preserving routers","venue":null,"work_id":"b66b5907-56d6-44a5-bda9-bce51b076b17","year":2025},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:6873b79558e485a6b20c5735964beea5b8127cb4a70ae4c675ff7b74fc65a31e","observation_id":"b5f95fa8-e254-4d92-93b1-d65e5b6965f2","resolution":{"observed_at":"2026-05-10T11:50:21.266871Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Uni-moe: Scaling unified multimodal llms with mixture of experts","venue":null,"work_id":"964efba7-240c-4ac8-83e0-3d7d840f9333","year":2025},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:eac6675910aa6d24237584ea705ec52dadd79305fbf690c111ab21ab45b89e31","observation_id":"2914106e-8134-437e-a933-ca2c6983b8a5","resolution":{"observed_at":"2026-05-22T02:34:32.768959Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Buffer overflow in mixture of experts","venue":null,"work_id":"657ff51c-8a0f-4579-b355-d3444cd24938","year":2024},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:5ccfd71e81e45b5689203d2eb25353a1113cdcf96a3882f82c3f2808264f2b82","observation_id":"74f20259-c46d-4be0-a1a2-8db234cc451b","resolution":{"observed_at":"2026-05-22T02:34:32.756825Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Harder tasks need more experts: Dynamic routing in moe models","venue":null,"work_id":"2ef3fac2-53cc-460b-92a5-e86997932a1a","year":2024},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:d32ddb144f401737f13a3fa101c9efb811ed92a854c7ea29fa705691100292a7","observation_id":"d2a84be3-e972-403f-890a-5b5b51157df1","resolution":{"observed_at":"2026-05-22T02:34:32.680248Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Machine learning in compiler optimization","venue":null,"work_id":"650aa95a-5b82-4544-91d3-511a5d1857b5","year":1901},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:1ef2f575dc81f6f083c8cfb17d9a4dccf0a32aa32f521255e5ca56eecdd3a4e0","observation_id":"ed5d8151-9b50-4fed-9f6a-a03b79149f7d","resolution":{"observed_at":"2026-05-22T02:34:32.716499Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Machine-learning-based self-optimizing compiler heuristics","venue":null,"work_id":"33c50005-4226-47cc-a2dd-4be459f93c16","year":2022},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:e80b95a5312f90dbbe1ca2fee34dacf792beafc783ac4666357b8c234d63e298","observation_id":"701cd51e-8f5f-4563-8e37-87431d4285ef","resolution":{"observed_at":"2026-05-22T02:34:32.651180Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Improved deterministic distributed matching via rounding","venue":null,"work_id":"d00ebe89-9190-4ffb-b503-de02b2b5a065","year":2020},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:5499a90d91837fcb7eed23a0548b3e14c1e90ef785961b9567700e4ad1d116a5","observation_id":"da53f31c-c77a-4b92-b42c-880706f8473d","resolution":{"observed_at":"2026-05-22T02:34:32.765821Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Hierarchical clustering via spreading metrics","venue":null,"work_id":"55a145e3-05cd-4ad0-83fc-f4a13df10d45","year":2017},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:66d9b4724b95f0dadee3e7864c805d7aed3857cc44a6ef9eeceb7d97e7802c9a","observation_id":"4e7e68a3-965f-447a-9919-f9207ceeabaa","resolution":{"observed_at":"2026-05-22T02:34:32.775333Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Dynamic algorithms for packing-covering lps via multiplicative weight updates","venue":null,"work_id":"acc010b1-b932-4f47-a3f7-2efc3343b439","year":2023},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:df2afeed76e5188a3bf1fb8b1f3ebcb9113e947240329fa8664e7d2a5c5c8725","observation_id":"3d4b1485-5f82-4480-aba3-4d20ad9c9990","resolution":{"observed_at":"2026-05-22T02:34:32.747365Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Base layers: Simplifying training of large, sparse models","venue":null,"work_id":"8566e260-f8c3-42ac-b5a9-0d28a9c569d1","year":2021},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:f6848d7946ca9b9dbc2e8b4449ebe425b25f944bceb3d02c1b42ad4bb801a029","observation_id":"bda63494-4191-49bd-8870-3f169142f57c","resolution":{"observed_at":"2026-05-22T02:34:32.710004Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Unified scaling laws for routed language models","venue":null,"work_id":"91289f15-1649-4d3d-ba76-121e6019b4dc","year":2022},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:be6dc77325bac22f8a3be2a7be9fe17b5e860d1b998d68851dd9b21075c3e069","observation_id":"bb425d88-10a6-49a2-bb01-83448b1b6780","resolution":{"observed_at":"2026-05-22T02:34:32.743960Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Sparsity-constrained optimal transport","venue":null,"work_id":"5b85ccef-bce1-4f2d-bbd4-c2128a5befd4","year":2022},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:4df72b1361f2fc6b7526966dca7d8335eb8137384a9438db6cd1f7ab0bf9ceb2","observation_id":"18a46503-c115-43a1-92a1-c54b4f0f8857","resolution":{"observed_at":"2026-05-22T02:34:32.749311Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Dino: Detr with improved denoising anchor boxes for end-to-end object detection","venue":null,"work_id":"ee1e74f9-de30-4d64-acd1-c3b8cc58ec76","year":2023},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:14b61d770e055865525d68e8e5652351cf409fbcb3c673b0368d6c7457d86388","observation_id":"521342f2-7a92-4d71-9245-6102703766b5","resolution":{"observed_at":"2026-05-22T02:34:32.659896Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"From sparse to soft mixtures of experts","venue":null,"work_id":"67147212-feed-4963-aaa1-27aa91515041","year":2024},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:8527443d8a1cfb512c10ab2f2b852efcc189a8f3e4484d1d02cf6ea1f59fc5e9","observation_id":"abd5aed1-04ca-430e-a810-41e9b9badd99","resolution":{"observed_at":"2026-05-22T02:34:32.759111Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Moe++: Accelerating mixture- of-experts methods with zero-computation experts","venue":null,"work_id":"d3497cef-27bc-46b6-92f0-011af349a3a1","year":2025},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:5f604f0dfab99e8921028c90e5f4fbe18aa1e8e75e769d10712b115945d1d3f0","observation_id":"91cfecda-41d6-4dc0-a7e8-e93b84152123","resolution":{"observed_at":"2026-05-22T02:34:32.666632Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Scaling vision with sparse mixture of experts","venue":null,"work_id":"727e029e-4343-48c8-9f55-ac1e6026046f","year":2021},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:076c90c2d16992c6c0edf2b3d847b5428cd9abee68885a0a2af76b4d6f18c681","observation_id":"92a3a9d2-4a78-4cab-94c5-7b0e19a06b1a","resolution":{"observed_at":"2026-05-22T02:34:32.699609Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Grounding dino: Marrying dino with grounded pre-training for open-set object detection","venue":null,"work_id":"ce3b4bf5-557f-4569-b150-e8244fcd5908","year":2024},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:9bbfa2f0690486375541601dcff80e0c5170da0bd3ec0a6d6e3d3302cd7963cb","observation_id":"0836ffa5-6306-489b-a697-87228cb06005","resolution":{"observed_at":"2026-05-22T02:34:32.740758Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Multi-source and multi- target domain adaptation based on dynamic generator with attention","venue":null,"work_id":"ad8bddd3-1890-49f2-b384-72e72fdf6518","year":2024},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:208be00b187ccde401621793e673a8bc6776161fcaf13898b346a5de3f6a753e","observation_id":"d8a95417-118f-49c9-8c90-7ccb6aadb80b","resolution":{"observed_at":"2026-05-22T02:34:32.753500Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Generalizing to new tasks via one-shot compositional subgoals","venue":null,"work_id":"60315e75-bb67-4c30-90bc-7485988ca165","year":2024},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:703054e187c0075c0d32cca2b71f89cd90bfb35d2dde17de5d99bf88ed8406bb","observation_id":"4c458e31-b133-4687-9d25-13d5d8c942db","resolution":{"observed_at":"2026-05-22T02:34:32.727772Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Omnivore: A single model for many visual modalities","venue":null,"work_id":"135a6786-e879-450d-8ae5-34a11bc18d88","year":2022},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:10ebc3d4a31891f977937a1f3044a963aeba491c9461e9bae4884961bbf2e1fe","observation_id":"84992ce6-18dd-4389-b3ce-53fa65bf5a64","resolution":{"observed_at":"2026-05-22T02:34:32.636033Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Detecting 11k classes: Large scale object detection without fine-grained bounding boxes","venue":null,"work_id":"3ddf3234-3587-4abb-978c-3a4a455a03a0","year":2019},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:a2348442a6169472ae6311bcdd787ebbb3088edbe5dc728d2571e094aedd7725","observation_id":"4c1eb527-5a85-4d64-ac2f-a0f4b414267e","resolution":{"observed_at":"2026-05-22T02:34:32.706475Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Glam: Efficient scaling of language models with mixture-of-experts","venue":null,"work_id":"9643e25d-580f-44f1-9300-d45afaee1f8d","year":2022},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:1027cdcf06e02c03c2663cee034bcf2a0e594a0fa3caa54c1227adbfb876e9c5","observation_id":"18247942-7fc5-4529-a539-112dd1e264a6","resolution":{"observed_at":"2026-05-22T02:34:32.696160Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Mixture-of-experts with expert choice routing","venue":null,"work_id":"239b2712-a175-489c-8575-efab8b1c85dd","year":2022},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:b99be67f9d3195c04baa1de1bbf0e639fd8d8f4c48fda23605eddc0748d7b9ea","observation_id":"573ce47c-a557-4355-999b-e3a6d67e73c6","resolution":{"observed_at":"2026-05-22T02:34:32.726768Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Scaling laws for fine-grained mixture of experts","venue":null,"work_id":"50387f8c-532c-4c88-bafa-eaa4c51d8d69","year":2024},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:6481f31cba3ad46bc781a85764babfc513b061d1b09498a30028b95255bea3a8","observation_id":"6a7de3d9-6e04-427f-9597-b2b27d7cc1f3","resolution":{"observed_at":"2026-05-22T02:34:32.762873Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.04088","last_updated":"2024-01-08T18:47:34Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-01-08T18:47:34Z","title":"Mixtral of Experts","version":1},"cited_work":{"arxiv_id":"2401.04088","doi":"10.48550/arxiv.2401.04088","metadata_source":"pith","pith_arxiv_id":"2401.04088","snapshot_observed_at":"2026-07-11T03:27:47.028679Z","title":"Mixtral of Experts","venue":"cs.LG","work_id":"0de8c352-9daa-4e1e-8c7b-3d0dec69f369","year":2024},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"cited_paper":"/paper/2401.04088","citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:e2b9884a1d3c2b082c5d82aead4a032354afba8bb5b1a8c49d559ba1e6ac0fd1","observation_id":"3f373fe5-e3f0-42a2-9651-7b7bc14bc17b","resolution":{"observed_at":"2026-05-10T11:50:21.263231Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-07-09T08:48:39.110013+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-09T08:48:39.110013+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Continuous action reinforcement learning from a mixture of interpretable experts","venue":null,"work_id":"539808b0-88fc-461d-99db-df691ad5cb08","year":2022},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:d87e274d83cf7225df0d5734ff7f55b19f0a1ae62d91560640d338bfb1d4ead9","observation_id":"b34ffed2-5fda-47cf-86f0-3b2a7972f008","resolution":{"observed_at":"2026-05-22T02:34:32.713362Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"On the representation collapse of sparse mixture of experts","venue":null,"work_id":"d12a0426-3ec8-4c5d-a928-bda3f2c6288f","year":2022},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:5cae699bdd94e97691a8debc6228633e3a8ad939f8cf6ae90327e60ca449f56d","observation_id":"b2d6bd86-68ea-4897-a97a-6ece0a90e420","resolution":{"observed_at":"2026-05-22T02:34:32.668340Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Regularized box- simplex games and dynamic decremental bipartite matching","venue":null,"work_id":"38aa401b-1519-43ec-a8cb-f60e33e8c9fc","year":2022},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:c0717d5279eee65ea0259ce4591ade3af7858423505a6a5bade4d63c674013f6","observation_id":"8e73edd7-80e4-4b8c-9899-a28c7fcb2470","resolution":{"observed_at":"2026-05-22T02:34:32.692430Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"An approximation algorithm for the generalized assignment problem","venue":null,"work_id":"d453c6a5-3e58-42bf-b624-7151f8821e5d","year":1993},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:9181996e3d90ec033913296731b53df0b0f69d1b725315a5a0da2dd855acdde0","observation_id":"5324c6b8-b666-4183-9f27-5a335fc8a7a3","resolution":{"observed_at":"2026-05-22T02:34:32.765605Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Deterministic decre- mental reachability, scc, and shortest paths via directed expanders and congestion balancing","venue":null,"work_id":"8a838280-fd27-4f61-a7ba-006b83c575c1","year":2020},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:aeced5f56bc29210a60bdc5475572a7abd2e0ad9a29cfe959ec197125c7fb62a","observation_id":"c92bb1c5-a43d-450e-8a3f-934988892b70","resolution":{"observed_at":"2026-05-22T02:34:32.742772Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Path finding methods for linear programming: Solving linear programs in o (vrank) iterations and faster algorithms for maximum flow","venue":null,"work_id":"7b26162d-65e7-4ba8-ad5c-583ca911fe70","year":2014},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:6bc27d79ef79a4691f8cbfa8c7b76e20ff33fb905a70cf9be6655ec3d308d822","observation_id":"e6ac0391-af58-4e20-bf72-f61b223b7af5","resolution":{"observed_at":"2026-05-22T02:34:32.720035Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Entropy regularization and faster decremental matching in general graphs","venue":null,"work_id":"e9814c67-3dfd-4369-b6a0-7fcd66ddc66f","year":2025},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:17d53f02e5c97b6b8047151b7182e81699ba7726049ebb69a60003f53ff519dd","observation_id":"5bd65bd6-0d04-4561-8ce7-dd1743654350","resolution":{"observed_at":"2026-05-22T02:34:32.750533Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Lvis: A dataset for large vocabu- lary instance segmentation","venue":null,"work_id":"ba02faef-bc44-4874-9715-979e10c8adab","year":2019},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:98098b644ef7890217180658898adfa7f491e9d915dfdaaa5a5dde15e8605a30","observation_id":"27a3c306-a5ab-4d44-a343-f77a8acb8985","resolution":{"observed_at":"2026-05-22T02:34:32.652835Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"The pascal visual object classes challenge: A retrospec- tive","venue":null,"work_id":"ded3d26a-fc2a-4ba5-8da6-302b49e314e8","year":2015},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:3c7b38f7253e26b2658bfcf1c6ac41233848b9929ec8a877ca8b1a617c3dbabe","observation_id":"9425d425-1150-4c48-9789-4859d4d4c566","resolution":{"observed_at":"2026-05-22T02:34:32.713907Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Wider face: A face detection benchmark","venue":null,"work_id":"ca1aa524-ea26-454f-b4c5-3ed9287f115c","year":2016},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:91ec8bcac1770ae8bac24c102409e7965c7a4f5a448aceb220d326892c618845","observation_id":"e4de1739-af3c-4698-8b15-7aec4ca9ad78","resolution":{"observed_at":"2026-05-22T02:34:32.762422Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Deep lesion graphs in the wild: relationship learning and organization of significant radiology image findings in a diverse large- scale lesion database","venue":null,"work_id":"211b912c-71da-45d9-a874-3c0f85825ba8","year":2018},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:7fe2ca5c64c371ae047e3c691e72d47180e9e100125f1a20c0b8d2884e80401f","observation_id":"fc2e4088-6b09-4ece-a545-c40776e334a5","resolution":{"observed_at":"2026-05-22T02:34:32.622142Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"kitchen-object-detection dataset","venue":null,"work_id":"fe79482d-9a34-4216-8853-3450fdf00ee9","year":2022},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:09f2ccdb5ce67e1d6f0ba6df4b3c170ac8f13f8098b921c3252e8e0c75bf33be","observation_id":"93d89964-59ae-4a73-9a2f-32370f8a9ffb","resolution":{"observed_at":"2026-05-22T02:34:32.735378Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Dota: A large-scale dataset for object detection in aerial images","venue":null,"work_id":"c43bc39d-4306-4156-a379-d4590a977b08","year":2018},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:7fd11e9bbc46ea0b7cd3d01c87d47e10c0804781ebaedc55fdbb29dd8637a21c","observation_id":"7fd47a91-25bf-49d7-9aa1-c96cb19c0621","resolution":{"observed_at":"2026-05-22T02:34:32.730502Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Vision-based traffic sign detection and analysis for intelligent driver assistance systems: Perspectives and survey","venue":null,"work_id":"e3d2cd3e-064f-412a-80b4-bcc033541c92","year":2012},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:f8f61e2e38fea63c4c9d0815d75fea12022332a26e517dc10065d90ce432d2d1","observation_id":"f6b43479-f2d5-41ff-a4d7-ca89dd0e44d2","resolution":{"observed_at":"2026-05-22T02:34:32.738983Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Are we ready for autonomous driving? the kitti vision benchmark suite","venue":null,"work_id":"ec0ea016-52c2-4772-ad97-57379c64f4fa","year":2012},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:0402833aca8c43c515b7baf4f35a6054645e6308f6b4642d9fb85899cf9ca03f","observation_id":"70f53ca1-d3dd-48ae-8066-af481b0cc53a","resolution":{"observed_at":"2026-05-22T02:34:32.756218Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"k-means++: The advantages of careful seeding","venue":null,"work_id":"10211925-ebff-41f8-9c32-2c15d8c4ed81","year":2007},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:0b91c884aae433d4840492cfc832ffe11edd51e480fdbacc9c2f4384a527feac","observation_id":"16f18b7e-1ccc-42fa-a8c9-daf3ccda6b87","resolution":{"observed_at":"2026-05-22T02:34:32.654090Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Objects365: A large-scale, high-quality dataset for object detection","venue":null,"work_id":"25267294-35ff-4ba7-9886-60595f7052e2","year":2019},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:fd14d7876272f16a803ff68487762dbd166cc2c2c2d38b79b326626214055060","observation_id":"d30effad-c830-483d-b053-349b14cb571b","resolution":{"observed_at":"2026-05-22T02:34:32.689327Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+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":"2026-06-05T21:23:00.469572Z","title":"Unbiased scene graph generation from biased training","venue":null,"work_id":"ede73e79-fc1b-45e7-b650-c5607c8c846d","year":2020},"citing_paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-05-10T04:44:46.383126Z"},"links":{"citing_paper":"/paper/2604.18842"},"observation_digest":"sha256:86d2d0d98e08132f41fedb51fdc6a3bf1cc864e5f1c0590d729f7218043e9bee","observation_id":"cc7c4e16-89d8-45ea-be3e-07030cd891e2","resolution":{"observed_at":"2026-05-22T02:34:32.737409Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2604.18842","last_updated":"2026-04-20T21:09:34Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T23:05:35.374092Z","submitted_at":"2026-04-20T21:09:34Z","title":"Multi-Domain Learning with Global Expert Mapping"},"reference_resolution":{"displayed":65,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":2,"verified_fuzzy":63},"total_outbound_references":65},"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":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"thesis":"As of 4 August 2026, this Paper Citation Record lists 65 of 65 outbound references and 0 inbound Pith citation observations for arXiv:2604.18842."}