{"as_of":"2026-08-10T11:44:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d41e6f5aa82ba943260af30e9d819e187d2399bb7881635c4c118f3601ade7d1","coverage":[{"denominator":51,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":51,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-27T20:09:00.056162Z","state":"measured"},{"denominator":51,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":51,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+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/2606.09907/citation-record","integrity":"/paper/2606.09907/integrity","json":"/paper/2606.09907/citation-record.json","paper":"/paper/2606.09907"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T20:09:00.056162Z","title":"Multimodal machine learning: A survey and taxonomy,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2606.09907","last_updated":"2026-06-06T07:50:41Z","snapshot_observed_at":"2026-08-10T08:27:52.621037Z","submitted_at":"2026-06-06T07:50:41Z","title":"LongMoE: Longitudinal Multimodal Learning via Trajectory-Aware Mixture-of-Experts","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-06-27T20:09:00.056162Z"},"links":{"citing_paper":"/paper/2606.09907"},"observation_digest":"sha256:08a5ec079cacc843b77e624f0f613cc95a9953418acd94551eaeda41f0f03394","observation_id":"131fe14b-534f-4c33-8594-80ca3ac589d8","resolution":{"observed_at":"2026-06-27T20:09:00.056162Z","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":"2026-06-27T20:09:00.056162Z","title":"MultiBench: Multiscale benchmarks for multimodal representation learning,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2606.09907","last_updated":"2026-06-06T07:50:41Z","snapshot_observed_at":"2026-08-10T08:27:52.621037Z","submitted_at":"2026-06-06T07:50:41Z","title":"LongMoE: Longitudinal Multimodal Learning via Trajectory-Aware Mixture-of-Experts","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-06-27T20:09:00.056162Z"},"links":{"citing_paper":"/paper/2606.09907"},"observation_digest":"sha256:bc86ace86720212802865421b3a90909195795b6ee5faeff46ff71ed4f923105","observation_id":"19fb260e-bcde-4f87-87ab-7df29c7f6785","resolution":{"observed_at":"2026-06-27T20:09:00.056162Z","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":"2026-06-27T20:09:00.056162Z","title":"Multi-task learning in heterogeneous feature spaces,","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2606.09907","last_updated":"2026-06-06T07:50:41Z","snapshot_observed_at":"2026-08-10T08:27:52.621037Z","submitted_at":"2026-06-06T07:50:41Z","title":"LongMoE: Longitudinal Multimodal Learning via Trajectory-Aware Mixture-of-Experts","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-06-27T20:09:00.056162Z"},"links":{"citing_paper":"/paper/2606.09907"},"observation_digest":"sha256:f271177eea229400973e517db292b27ac9bf0f79567d350cb70ef56669c45fdf","observation_id":"fb37971a-a0a3-44e4-afe1-e5f5b29b17ae","resolution":{"observed_at":"2026-06-27T20:09:00.056162Z","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":"2026-06-27T20:09:00.056162Z","title":"Biomarker modeling of Alzheimer’s disease,","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2606.09907","last_updated":"2026-06-06T07:50:41Z","snapshot_observed_at":"2026-08-10T08:27:52.621037Z","submitted_at":"2026-06-06T07:50:41Z","title":"LongMoE: Longitudinal Multimodal Learning via Trajectory-Aware Mixture-of-Experts","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-06-27T20:09:00.056162Z"},"links":{"citing_paper":"/paper/2606.09907"},"observation_digest":"sha256:a3c36c96d556134448de9ff63cd79f2741f44f5f995328fd773e5077a45c6123","observation_id":"87d64372-1f6c-4aaa-9435-37fe4945e9e0","resolution":{"observed_at":"2026-06-27T20:09:00.056162Z","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":"2026-06-27T20:09:00.056162Z","title":"Neuroimaging biomarkers for Alzheimer’s disease,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2606.09907","last_updated":"2026-06-06T07:50:41Z","snapshot_observed_at":"2026-08-10T08:27:52.621037Z","submitted_at":"2026-06-06T07:50:41Z","title":"LongMoE: Longitudinal Multimodal Learning via Trajectory-Aware Mixture-of-Experts","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-06-27T20:09:00.056162Z"},"links":{"citing_paper":"/paper/2606.09907"},"observation_digest":"sha256:1f64ac9a9dcf8dbbe6f62673e502fc7affc20ee60b93f7d91b64bb67e46820b8","observation_id":"6b68ba7c-5dd1-422e-a1a9-6066209d1078","resolution":{"observed_at":"2026-06-27T20:09:00.056162Z","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":"2026-06-27T20:09:00.056162Z","title":"Genet- ics, transcriptomics, and proteomics of Alzheimer’s disease,","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2606.09907","last_updated":"2026-06-06T07:50:41Z","snapshot_observed_at":"2026-08-10T08:27:52.621037Z","submitted_at":"2026-06-06T07:50:41Z","title":"LongMoE: Longitudinal Multimodal Learning via Trajectory-Aware Mixture-of-Experts","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-06-27T20:09:00.056162Z"},"links":{"citing_paper":"/paper/2606.09907"},"observation_digest":"sha256:6e447d7fe4d086966620510ae0926acaa76b67da06cf9f5df36d84ddf02f9b9f","observation_id":"04f22112-50a7-42a5-8190-30ee32708929","resolution":{"observed_at":"2026-06-27T20:09:00.056162Z","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":"2026-06-27T20:09:00.056162Z","title":"Flex-MoE: Modeling arbitrary modality combination via the flexible mixture-of-experts,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.09907","last_updated":"2026-06-06T07:50:41Z","snapshot_observed_at":"2026-08-10T08:27:52.621037Z","submitted_at":"2026-06-06T07:50:41Z","title":"LongMoE: Longitudinal Multimodal Learning via Trajectory-Aware Mixture-of-Experts","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-06-27T20:09:00.056162Z"},"links":{"citing_paper":"/paper/2606.09907"},"observation_digest":"sha256:f188b2f3f13a9a2d0c1b7900ab5069f8f0486b1ab5a125a86201d6d105f2ce03","observation_id":"6c40930f-2808-4610-b32e-7e3e91e6a57e","resolution":{"observed_at":"2026-06-27T20:09:00.056162Z","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":"2026-06-27T20:09:00.056162Z","title":"FuseMoE: Mixture-of-experts transformers for fleximodal fusion,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.09907","last_updated":"2026-06-06T07:50:41Z","snapshot_observed_at":"2026-08-10T08:27:52.621037Z","submitted_at":"2026-06-06T07:50:41Z","title":"LongMoE: Longitudinal Multimodal Learning via Trajectory-Aware Mixture-of-Experts","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-06-27T20:09:00.056162Z"},"links":{"citing_paper":"/paper/2606.09907"},"observation_digest":"sha256:1984f7944610f7abc8d0c56e21a958bb0687d0ad10beef439a84ca8d77aa8e20","observation_id":"e0a056e4-35b7-4044-b70c-63982dcfb4cc","resolution":{"observed_at":"2026-06-27T20:09:00.056162Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.02425","last_updated":"2022-08-04T07:23:42Z","snapshot_observed_at":"2026-07-06T13:17:44.718595Z","submitted_at":"2022-06-06T08:41:56Z","title":"mmFormer: Multimodal Medical Transformer for Incomplete Multimodal Learning of Brain Tumor Segmentation","version":2},"cited_work":{"arxiv_id":"2206.02425","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2206.02425","snapshot_observed_at":"2026-07-02T20:47:23.017461Z","title":"mmformer: Multimodal medical transformer for incomplete multimodal learning of brain tumor segmentation","venue":null,"work_id":"23ef5ce9-f14a-41a6-94f3-07d1e09f71eb","year":2022},"citing_paper":{"arxiv_id":"2606.09907","last_updated":"2026-06-06T07:50:41Z","snapshot_observed_at":"2026-08-10T08:27:52.621037Z","submitted_at":"2026-06-06T07:50:41Z","title":"LongMoE: Longitudinal Multimodal Learning via Trajectory-Aware Mixture-of-Experts","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-06-27T20:09:00.056162Z"},"links":{"cited_paper":"/paper/2206.02425","citing_paper":"/paper/2606.09907"},"observation_digest":"sha256:58317c426167dbf2dc4f6c91fa2cb94ec965080901a03c04876aca017af42ae6","observation_id":"86210516-12da-40ec-a956-612d7b9fc7e3","resolution":{"observed_at":"2026-07-02T20:47:23.019027Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-06-27T20:09:00.056162Z","title":"Multi-modal learning with missing modality via shared-specific feature modelling,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.09907","last_updated":"2026-06-06T07:50:41Z","snapshot_observed_at":"2026-08-10T08:27:52.621037Z","submitted_at":"2026-06-06T07:50:41Z","title":"LongMoE: Longitudinal Multimodal Learning via Trajectory-Aware Mixture-of-Experts","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-06-27T20:09:00.056162Z"},"links":{"citing_paper":"/paper/2606.09907"},"observation_digest":"sha256:621b4391b63aa3af07470c8a6f7151075448667c0d88f4816629f78320ab2cb4","observation_id":"c08484f3-9a6c-460d-9b19-812feb1cb318","resolution":{"observed_at":"2026-06-27T20:09:00.056162Z","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":"2026-06-27T20:09:00.056162Z","title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2606.09907","last_updated":"2026-06-06T07:50:41Z","snapshot_observed_at":"2026-08-10T08:27:52.621037Z","submitted_at":"2026-06-06T07:50:41Z","title":"LongMoE: Longitudinal Multimodal Learning via Trajectory-Aware Mixture-of-Experts","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-06-27T20:09:00.056162Z"},"links":{"citing_paper":"/paper/2606.09907"},"observation_digest":"sha256:53750111f14bcf40921bc0bfdf9875257084c88158e6a59598acf47463d6a156","observation_id":"4a292e43-1bf3-4778-96ca-adb181edc037","resolution":{"observed_at":"2026-06-27T20:09:00.056162Z","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":"2026-06-27T20:09:00.056162Z","title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.09907","last_updated":"2026-06-06T07:50:41Z","snapshot_observed_at":"2026-08-10T08:27:52.621037Z","submitted_at":"2026-06-06T07:50:41Z","title":"LongMoE: Longitudinal Multimodal Learning via Trajectory-Aware Mixture-of-Experts","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-06-27T20:09:00.056162Z"},"links":{"citing_paper":"/paper/2606.09907"},"observation_digest":"sha256:bc8567b6e44d0c6d02945f269662bdd52b34322755e5d8c36e44cabbf433460a","observation_id":"47c04294-58da-41ef-8a4e-278b75a9697f","resolution":{"observed_at":"2026-06-27T20:09:00.056162Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.04088","last_updated":"2024-01-08T18:47:34Z","snapshot_observed_at":"2026-08-08T06:16:25.839566Z","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":"2026-08-05T02:28:24.338817Z","title":"Mixtral of Experts","venue":"cs.LG","work_id":"0de8c352-9daa-4e1e-8c7b-3d0dec69f369","year":2024},"citing_paper":{"arxiv_id":"2606.09907","last_updated":"2026-06-06T07:50:41Z","snapshot_observed_at":"2026-08-10T08:27:52.621037Z","submitted_at":"2026-06-06T07:50:41Z","title":"LongMoE: Longitudinal Multimodal Learning via Trajectory-Aware Mixture-of-Experts","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-06-27T20:09:00.056162Z"},"links":{"cited_paper":"/paper/2401.04088","citing_paper":"/paper/2606.09907"},"observation_digest":"sha256:5abb44ac80f7d5d014a21daa9379dfb600adbb9bcf7cbadc8bb3504096779cbf","observation_id":"92836396-853e-47ff-b9b3-7c7424252d7e","resolution":{"observed_at":"2026-07-02T20:47:23.021440Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-08T21:08:09.485243+00:00","source":"crossref_status_cache"},{"observed_at":"2026-08-08T21:08:09.485243+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-06-27T20:09:00.056162Z","title":"Multimodal contrastive learning with LiMoE: The language-image mixture of experts,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.09907","last_updated":"2026-06-06T07:50:41Z","snapshot_observed_at":"2026-08-10T08:27:52.621037Z","submitted_at":"2026-06-06T07:50:41Z","title":"LongMoE: Longitudinal Multimodal Learning via Trajectory-Aware Mixture-of-Experts","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-06-27T20:09:00.056162Z"},"links":{"citing_paper":"/paper/2606.09907"},"observation_digest":"sha256:840be0327edc0811dc0bb92f5903336cc1db248b749a3acdb4f3769d4907c23c","observation_id":"6558ae68-f53b-4990-be5b-c9c94a18dbce","resolution":{"observed_at":"2026-06-27T20:09:00.056162Z","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":"2026-06-27T20:09:00.056162Z","title":"Sparse MoE as a new treatment: Addressing forgetting, fitting, and learning issues in multi-modal multi-task learning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.09907","last_updated":"2026-06-06T07:50:41Z","snapshot_observed_at":"2026-08-10T08:27:52.621037Z","submitted_at":"2026-06-06T07:50:41Z","title":"LongMoE: Longitudinal Multimodal Learning via Trajectory-Aware Mixture-of-Experts","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-06-27T20:09:00.056162Z"},"links":{"citing_paper":"/paper/2606.09907"},"observation_digest":"sha256:85561c48d800202e78edd464c44fcf9c8741ac52d84c33788856eeab5cc8c452","observation_id":"131867d2-4b29-4852-b87e-69c1c6faf968","resolution":{"observed_at":"2026-06-27T20:09:00.056162Z","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":"2026-06-27T20:09:00.056162Z","title":"Tensor fusion network for multimodal sentiment analysis,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2606.09907","last_updated":"2026-06-06T07:50:41Z","snapshot_observed_at":"2026-08-10T08:27:52.621037Z","submitted_at":"2026-06-06T07:50:41Z","title":"LongMoE: Longitudinal Multimodal Learning via Trajectory-Aware Mixture-of-Experts","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-06-27T20:09:00.056162Z"},"links":{"citing_paper":"/paper/2606.09907"},"observation_digest":"sha256:05ae7f632956166b6af68528c86348933dcaf1a0853580ac3d43d5aa0e3ed5c0","observation_id":"96f9dc40-4355-4123-8bca-c1828fadf758","resolution":{"observed_at":"2026-06-27T20:09:00.056162Z","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":"2026-06-27T20:09:00.056162Z","title":"Multimodal transformer for unaligned multimodal language sequences,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2606.09907","last_updated":"2026-06-06T07:50:41Z","snapshot_observed_at":"2026-08-10T08:27:52.621037Z","submitted_at":"2026-06-06T07:50:41Z","title":"LongMoE: Longitudinal Multimodal Learning via Trajectory-Aware Mixture-of-Experts","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-06-27T20:09:00.056162Z"},"links":{"citing_paper":"/paper/2606.09907"},"observation_digest":"sha256:a82f24a1f17a452b84f64557116b037c179c22b78474d4276a0ce6d5e2d42389","observation_id":"1e8a08bf-457e-4568-abb9-325ffa17d4a5","resolution":{"observed_at":"2026-06-27T20:09:00.056162Z","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":"2026-06-27T20:09:00.056162Z","title":"Integrating multimodal information in large pretrained transformers,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2606.09907","last_updated":"2026-06-06T07:50:41Z","snapshot_observed_at":"2026-08-10T08:27:52.621037Z","submitted_at":"2026-06-06T07:50:41Z","title":"LongMoE: Longitudinal Multimodal Learning via Trajectory-Aware Mixture-of-Experts","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-06-27T20:09:00.056162Z"},"links":{"citing_paper":"/paper/2606.09907"},"observation_digest":"sha256:740aa890ab9736c28d3c70f81824c6746c56c60d5510104a5bb217d28fd0badd","observation_id":"26a9c99b-782b-4d91-8710-36d0e92e5dcf","resolution":{"observed_at":"2026-06-27T20:09:00.056162Z","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":"2026-06-27T20:09:00.056162Z","title":"Predicting Alzheimer’s disease progression using multi-modal deep learning approach,","venue":null,"work_id":null,"year":1952},"citing_paper":{"arxiv_id":"2606.09907","last_updated":"2026-06-06T07:50:41Z","snapshot_observed_at":"2026-08-10T08:27:52.621037Z","submitted_at":"2026-06-06T07:50:41Z","title":"LongMoE: Longitudinal Multimodal Learning via Trajectory-Aware Mixture-of-Experts","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-06-27T20:09:00.056162Z"},"links":{"citing_paper":"/paper/2606.09907"},"observation_digest":"sha256:01bbba2bcb8a24973b3653957281f72a78a7b4cf7c5d2d8db1948036e8021d06","observation_id":"2d1461a5-0a4e-4367-90fd-36456f9377b9","resolution":{"observed_at":"2026-06-27T20:09:00.056162Z","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":"2026-06-27T20:09:00.056162Z","title":"Multimodal deep learning models for early detection of Alzheimer’s disease stage,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2606.09907","last_updated":"2026-06-06T07:50:41Z","snapshot_observed_at":"2026-08-10T08:27:52.621037Z","submitted_at":"2026-06-06T07:50:41Z","title":"LongMoE: Longitudinal Multimodal Learning via Trajectory-Aware Mixture-of-Experts","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-06-27T20:09:00.056162Z"},"links":{"citing_paper":"/paper/2606.09907"},"observation_digest":"sha256:ac56ff00cff58deefb065b157877743cd4fdd64ee3af5425f417009c3c012406","observation_id":"058bf726-0fae-45d8-b817-6ccb5c6e8247","resolution":{"observed_at":"2026-06-27T20:09:00.056162Z","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":"2026-06-27T20:09:00.056162Z","title":"Machine learning with multi- modal neuroimaging data to classify stages of Alzheimer’s disease: A systematic review and meta-analysis,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.09907","last_updated":"2026-06-06T07:50:41Z","snapshot_observed_at":"2026-08-10T08:27:52.621037Z","submitted_at":"2026-06-06T07:50:41Z","title":"LongMoE: Longitudinal Multimodal Learning via Trajectory-Aware Mixture-of-Experts","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-06-27T20:09:00.056162Z"},"links":{"citing_paper":"/paper/2606.09907"},"observation_digest":"sha256:ab661af085357628a04fed6b697301c8dd13a9fd174bc241198c8336cd1de69e","observation_id":"49c1a0f5-8762-410d-a3b2-1309741fba03","resolution":{"observed_at":"2026-06-27T20:09:00.056162Z","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":"2026-06-27T20:09:00.056162Z","title":"Attention is all you need,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2606.09907","last_updated":"2026-06-06T07:50:41Z","snapshot_observed_at":"2026-08-10T08:27:52.621037Z","submitted_at":"2026-06-06T07:50:41Z","title":"LongMoE: Longitudinal Multimodal Learning via Trajectory-Aware Mixture-of-Experts","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-06-27T20:09:00.056162Z"},"links":{"citing_paper":"/paper/2606.09907"},"observation_digest":"sha256:837f5fc517171a44f649d06613ea56c269b4c95d9d773d022626998e5a464940","observation_id":"1baed7b2-d0c1-41ca-8440-6f2b0aadc222","resolution":{"observed_at":"2026-06-27T20:09:00.056162Z","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":"2026-06-27T20:09:00.056162Z","title":"BERT: Pre-training of deep bidirectional transformers for language understanding,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2606.09907","last_updated":"2026-06-06T07:50:41Z","snapshot_observed_at":"2026-08-10T08:27:52.621037Z","submitted_at":"2026-06-06T07:50:41Z","title":"LongMoE: Longitudinal Multimodal Learning via Trajectory-Aware Mixture-of-Experts","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-06-27T20:09:00.056162Z"},"links":{"citing_paper":"/paper/2606.09907"},"observation_digest":"sha256:f9d6a78276e4976f73962f8f73bedaf8ed2b709ee899e44ffdf0aa018da95b0f","observation_id":"a5abc184-dff0-4b49-bccb-ea46d681d0be","resolution":{"observed_at":"2026-06-27T20:09:00.056162Z","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":"2026-06-27T20:09:00.056162Z","title":"The Alzheimer’s Disease Neuroimaging Initiative: Progress report and future plans,","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2606.09907","last_updated":"2026-06-06T07:50:41Z","snapshot_observed_at":"2026-08-10T08:27:52.621037Z","submitted_at":"2026-06-06T07:50:41Z","title":"LongMoE: Longitudinal Multimodal Learning via Trajectory-Aware Mixture-of-Experts","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-06-27T20:09:00.056162Z"},"links":{"citing_paper":"/paper/2606.09907"},"observation_digest":"sha256:7ccc4a20d42da4c6b446b542c0666c9408adbf554882d05a3bf5ff98931bccec","observation_id":"084bda31-316b-473c-816c-75d7afa03ab4","resolution":{"observed_at":"2026-06-27T20:09:00.056162Z","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":"2026-06-27T20:09:00.056162Z","title":"OASIS-3: Longitudinal neuroimaging, clinical, and cognitive dataset for normal aging and Alzheimer’s disease,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2606.09907","last_updated":"2026-06-06T07:50:41Z","snapshot_observed_at":"2026-08-10T08:27:52.621037Z","submitted_at":"2026-06-06T07:50:41Z","title":"LongMoE: Longitudinal Multimodal Learning via Trajectory-Aware Mixture-of-Experts","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-06-27T20:09:00.056162Z"},"links":{"citing_paper":"/paper/2606.09907"},"observation_digest":"sha256:7954f8a5c15d6e031975b733c4940758c32945140fd0f2366674cb74c3f5af16","observation_id":"e376d674-e1a1-4eb3-b504-fd473e2a1320","resolution":{"observed_at":"2026-06-27T20:09:00.056162Z","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":"2026-06-27T20:09:00.056162Z","title":"A., and Mark, R","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.09907","last_updated":"2026-06-06T07:50:41Z","snapshot_observed_at":"2026-08-10T08:27:52.621037Z","submitted_at":"2026-06-06T07:50:41Z","title":"LongMoE: Longitudinal Multimodal Learning via Trajectory-Aware Mixture-of-Experts","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-06-27T20:09:00.056162Z"},"links":{"citing_paper":"/paper/2606.09907"},"observation_digest":"sha256:2ae42dc847f76c9a2537d4cbfa2d32da24955e2e2be41956b5ba88805c83e7dd","observation_id":"a19192cf-be7e-44e3-9622-3f46f440abb8","resolution":{"observed_at":"2026-06-27T20:09:00.056162Z","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":"2026-06-27T20:09:00.056162Z","title":"MUSE: Multi-atlas region segmentation utilizing ensem- bles of registration algorithms and parameters, and locally optimal atlas selection,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2606.09907","last_updated":"2026-06-06T07:50:41Z","snapshot_observed_at":"2026-08-10T08:27:52.621037Z","submitted_at":"2026-06-06T07:50:41Z","title":"LongMoE: Longitudinal Multimodal Learning via Trajectory-Aware Mixture-of-Experts","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-06-27T20:09:00.056162Z"},"links":{"citing_paper":"/paper/2606.09907"},"observation_digest":"sha256:9d96b053730311287bb9c6bb6a7da486766bbed3751ebbd26d0093c8b6ed0dca","observation_id":"8d293926-7193-4fdd-8478-bdda89e98fc4","resolution":{"observed_at":"2026-06-27T20:09:00.056162Z","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":"2026-06-27T20:09:00.056162Z","title":"DRAMMS: Deformable registration via attribute matching and mutual-saliency weighting,","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2606.09907","last_updated":"2026-06-06T07:50:41Z","snapshot_observed_at":"2026-08-10T08:27:52.621037Z","submitted_at":"2026-06-06T07:50:41Z","title":"LongMoE: Longitudinal Multimodal Learning via Trajectory-Aware Mixture-of-Experts","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-06-27T20:09:00.056162Z"},"links":{"citing_paper":"/paper/2606.09907"},"observation_digest":"sha256:b54d20f5c32f2a98adb087806c129f8eca053e49a06e0ded08f670022c618603","observation_id":"fa4c3386-525d-4dfb-8805-a58d9ff8ab4d","resolution":{"observed_at":"2026-06-27T20:09:00.056162Z","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":"2026-06-27T20:09:00.056162Z","title":"Decoupled weight decay regularization,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2606.09907","last_updated":"2026-06-06T07:50:41Z","snapshot_observed_at":"2026-08-10T08:27:52.621037Z","submitted_at":"2026-06-06T07:50:41Z","title":"LongMoE: Longitudinal Multimodal Learning via Trajectory-Aware Mixture-of-Experts","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-06-27T20:09:00.056162Z"},"links":{"citing_paper":"/paper/2606.09907"},"observation_digest":"sha256:8b913f3c66cae9800a70802510e8734917f82e5bc2b3a45fd4b272e7525bd6b5","observation_id":"992f100e-e476-4b66-a3a0-4fe455498ad6","resolution":{"observed_at":"2026-06-27T20:09:00.056162Z","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":"2026-06-27T20:09:00.056162Z","title":"PyTorch: An imperative style, high-performance deep learning library,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2606.09907","last_updated":"2026-06-06T07:50:41Z","snapshot_observed_at":"2026-08-10T08:27:52.621037Z","submitted_at":"2026-06-06T07:50:41Z","title":"LongMoE: Longitudinal Multimodal Learning via Trajectory-Aware Mixture-of-Experts","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-06-27T20:09:00.056162Z"},"links":{"citing_paper":"/paper/2606.09907"},"observation_digest":"sha256:12eebbb6f49cf889c2fae3946eb281a8c4ce0edf25bee4acd04808832507b52d","observation_id":"64fcd7e2-19e0-459e-8dd7-72191e605824","resolution":{"observed_at":"2026-06-27T20:09:00.056162Z","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":"2026-06-27T20:09:00.056162Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2606.09907","last_updated":"2026-06-06T07:50:41Z","snapshot_observed_at":"2026-08-10T08:27:52.621037Z","submitted_at":"2026-06-06T07:50:41Z","title":"LongMoE: Longitudinal Multimodal Learning via Trajectory-Aware Mixture-of-Experts","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-06-27T20:09:00.056162Z"},"links":{"citing_paper":"/paper/2606.09907"},"observation_digest":"sha256:19d9630d82d086609eca83350e631f1b43df7b0f4ada4ec3f761b87c154529b2","observation_id":"e8d9e4e1-8791-47ce-91aa-00bc8343ee58","resolution":{"observed_at":"2026-06-27T20:09:00.056162Z","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":"2026-06-27T20:09:00.056162Z","title":"Scaling vision with sparse mixture of experts,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2606.09907","last_updated":"2026-06-06T07:50:41Z","snapshot_observed_at":"2026-08-10T08:27:52.621037Z","submitted_at":"2026-06-06T07:50:41Z","title":"LongMoE: Longitudinal Multimodal Learning via Trajectory-Aware Mixture-of-Experts","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-06-27T20:09:00.056162Z"},"links":{"citing_paper":"/paper/2606.09907"},"observation_digest":"sha256:b827e7e39b666d3fabac9cb9fdb5fd34e1b708be26700c913de32096d5342723","observation_id":"c6a6d48a-f6f1-4f4e-9cee-3f36e47bf6b6","resolution":{"observed_at":"2026-06-27T20:09:00.056162Z","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":"2026-06-27T20:09:00.056162Z","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":"2606.09907","last_updated":"2026-06-06T07:50:41Z","snapshot_observed_at":"2026-08-10T08:27:52.621037Z","submitted_at":"2026-06-06T07:50:41Z","title":"LongMoE: Longitudinal Multimodal Learning via Trajectory-Aware Mixture-of-Experts","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-06-27T20:09:00.056162Z"},"links":{"citing_paper":"/paper/2606.09907"},"observation_digest":"sha256:c098859b07af5737fd0878e28e41ce0654e3c171b540265e190c1836c2cef707","observation_id":"bb7a572a-3088-44ce-a575-a84f390ba343","resolution":{"observed_at":"2026-06-27T20:09:00.056162Z","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":"2026-06-27T20:09:00.056162Z","title":"Mod-Squad: Designing mixtures of experts as modular multi-task learners,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.09907","last_updated":"2026-06-06T07:50:41Z","snapshot_observed_at":"2026-08-10T08:27:52.621037Z","submitted_at":"2026-06-06T07:50:41Z","title":"LongMoE: Longitudinal Multimodal Learning via Trajectory-Aware Mixture-of-Experts","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-06-27T20:09:00.056162Z"},"links":{"citing_paper":"/paper/2606.09907"},"observation_digest":"sha256:8b4012f0e361c3ca2a4ac2e0b65f69844553e0716e9ffafcb35c64693598eb98","observation_id":"0988738e-05ab-469f-9349-50beffb90dd3","resolution":{"observed_at":"2026-06-27T20:09:00.056162Z","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":"2026-06-27T20:09:00.056162Z","title":"Mixture-of-experts with expert choice routing,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.09907","last_updated":"2026-06-06T07:50:41Z","snapshot_observed_at":"2026-08-10T08:27:52.621037Z","submitted_at":"2026-06-06T07:50:41Z","title":"LongMoE: Longitudinal Multimodal Learning via Trajectory-Aware Mixture-of-Experts","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-06-27T20:09:00.056162Z"},"links":{"citing_paper":"/paper/2606.09907"},"observation_digest":"sha256:93b3b66063a39de8994893f148fdc8a9075edb2eadac4a61fbbae2b57428c512","observation_id":"d6ce22da-db12-43e9-a964-b49faf7fffd6","resolution":{"observed_at":"2026-06-27T20:09:00.056162Z","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":"2026-06-27T20:09:00.056162Z","title":"DSelect-k: Differentiable selection in the mixture of experts with applications to multi-task learning,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2606.09907","last_updated":"2026-06-06T07:50:41Z","snapshot_observed_at":"2026-08-10T08:27:52.621037Z","submitted_at":"2026-06-06T07:50:41Z","title":"LongMoE: Longitudinal Multimodal Learning via Trajectory-Aware Mixture-of-Experts","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-06-27T20:09:00.056162Z"},"links":{"citing_paper":"/paper/2606.09907"},"observation_digest":"sha256:92fd2d482f801aafde338e33b870b9db20edd73cf2875b124c6e55aa6f827b93","observation_id":"3b0f9f46-2575-4698-ae31-a868f26ec837","resolution":{"observed_at":"2026-06-27T20:09:00.056162Z","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":"2026-06-27T20:09:00.056162Z","title":"Long short-term memory,","venue":null,"work_id":null,"year":1997},"citing_paper":{"arxiv_id":"2606.09907","last_updated":"2026-06-06T07:50:41Z","snapshot_observed_at":"2026-08-10T08:27:52.621037Z","submitted_at":"2026-06-06T07:50:41Z","title":"LongMoE: Longitudinal Multimodal Learning via Trajectory-Aware Mixture-of-Experts","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-06-27T20:09:00.056162Z"},"links":{"citing_paper":"/paper/2606.09907"},"observation_digest":"sha256:6194cda3e5b7bc88066d74968cca6a92bedad1804eadf9d2b4fd8f477e55c39f","observation_id":"492cde35-0345-4202-b1e9-977a82d3a50d","resolution":{"observed_at":"2026-06-27T20:09:00.056162Z","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":"2026-06-27T20:09:00.056162Z","title":"Learning phrase representations using RNN encoder–decoder for statistical machine translation,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2606.09907","last_updated":"2026-06-06T07:50:41Z","snapshot_observed_at":"2026-08-10T08:27:52.621037Z","submitted_at":"2026-06-06T07:50:41Z","title":"LongMoE: Longitudinal Multimodal Learning via Trajectory-Aware Mixture-of-Experts","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-06-27T20:09:00.056162Z"},"links":{"citing_paper":"/paper/2606.09907"},"observation_digest":"sha256:961de0a344192e0b23afaa5467f56646f739594a19039fc7702a5f5cd66932ff","observation_id":"95142d43-41b9-4bd8-a888-b9bcb50fe203","resolution":{"observed_at":"2026-06-27T20:09:00.056162Z","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":"2026-06-27T20:09:00.056162Z","title":"RETAIN: An inter- pretable predictive model for healthcare using reverse time attention mechanism,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2606.09907","last_updated":"2026-06-06T07:50:41Z","snapshot_observed_at":"2026-08-10T08:27:52.621037Z","submitted_at":"2026-06-06T07:50:41Z","title":"LongMoE: Longitudinal Multimodal Learning via Trajectory-Aware Mixture-of-Experts","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-06-27T20:09:00.056162Z"},"links":{"citing_paper":"/paper/2606.09907"},"observation_digest":"sha256:1d5b5720e13621b1be5048eb6d842d7998fea8b8820ed74fe288b49e77e279ee","observation_id":"ff8271ed-afd1-41ac-86c3-1fd518923cca","resolution":{"observed_at":"2026-06-27T20:09:00.056162Z","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":"2026-06-27T20:09:00.056162Z","title":"Set functions for time series,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2606.09907","last_updated":"2026-06-06T07:50:41Z","snapshot_observed_at":"2026-08-10T08:27:52.621037Z","submitted_at":"2026-06-06T07:50:41Z","title":"LongMoE: Longitudinal Multimodal Learning via Trajectory-Aware Mixture-of-Experts","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-06-27T20:09:00.056162Z"},"links":{"citing_paper":"/paper/2606.09907"},"observation_digest":"sha256:b034455f4656a5af2a194dd9f517d15c15ee224b95b9559698257db1c3f76b29","observation_id":"d4ebea39-6e0f-45f1-9201-73f9eab4d186","resolution":{"observed_at":"2026-06-27T20:09:00.056162Z","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":"2026-06-27T20:09:00.056162Z","title":"Multi-time attention networks for irregularly sampled time series,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2606.09907","last_updated":"2026-06-06T07:50:41Z","snapshot_observed_at":"2026-08-10T08:27:52.621037Z","submitted_at":"2026-06-06T07:50:41Z","title":"LongMoE: Longitudinal Multimodal Learning via Trajectory-Aware Mixture-of-Experts","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-06-27T20:09:00.056162Z"},"links":{"citing_paper":"/paper/2606.09907"},"observation_digest":"sha256:420b0e22a0140df00c60e4ba8d7a65ff64beaf3963ab505882d29fdc1764c468","observation_id":"9bb7d2de-38f1-4afb-b6f1-de44d864fc52","resolution":{"observed_at":"2026-06-27T20:09:00.056162Z","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":"2026-06-27T20:09:00.056162Z","title":"Hierarchical mixtures of experts and the EM algorithm,","venue":null,"work_id":null,"year":1994},"citing_paper":{"arxiv_id":"2606.09907","last_updated":"2026-06-06T07:50:41Z","snapshot_observed_at":"2026-08-10T08:27:52.621037Z","submitted_at":"2026-06-06T07:50:41Z","title":"LongMoE: Longitudinal Multimodal Learning via Trajectory-Aware Mixture-of-Experts","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-06-27T20:09:00.056162Z"},"links":{"citing_paper":"/paper/2606.09907"},"observation_digest":"sha256:6f651c7062a20a5399aa4c1b189c134ef3943f5ca479b0ff1c482e3e902986cf","observation_id":"ad9deba1-ee30-443b-84d6-48c894fbf8f8","resolution":{"observed_at":"2026-06-27T20:09:00.056162Z","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":"2026-06-27T20:09:00.056162Z","title":"A., Jordan, M","venue":null,"work_id":null,"year":1991},"citing_paper":{"arxiv_id":"2606.09907","last_updated":"2026-06-06T07:50:41Z","snapshot_observed_at":"2026-08-10T08:27:52.621037Z","submitted_at":"2026-06-06T07:50:41Z","title":"LongMoE: Longitudinal Multimodal Learning via Trajectory-Aware Mixture-of-Experts","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-06-27T20:09:00.056162Z"},"links":{"citing_paper":"/paper/2606.09907"},"observation_digest":"sha256:7d1906bee845de39d825dc9ba7ec7a42e4b55c9e0ee0fd173ae938c31f1027d9","observation_id":"8a0777f2-949d-4de4-aa36-0080f48e3ba6","resolution":{"observed_at":"2026-06-27T20:09:00.056162Z","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":"2026-06-27T20:09:00.056162Z","title":"TimesNet: Temporal 2D-variation modeling for general time series analysis","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.09907","last_updated":"2026-06-06T07:50:41Z","snapshot_observed_at":"2026-08-10T08:27:52.621037Z","submitted_at":"2026-06-06T07:50:41Z","title":"LongMoE: Longitudinal Multimodal Learning via Trajectory-Aware Mixture-of-Experts","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-06-27T20:09:00.056162Z"},"links":{"citing_paper":"/paper/2606.09907"},"observation_digest":"sha256:f91a163907f4135b674c36b94adc7669e6c4a40e7174012f250eb49138e068fe","observation_id":"cfd176d9-28e6-4ea5-a54c-b85f70874ad6","resolution":{"observed_at":"2026-06-27T20:09:00.056162Z","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":"2026-06-27T20:09:00.056162Z","title":"FEDformer: Frequency enhanced de- composed transformer for long-term series forecasting","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.09907","last_updated":"2026-06-06T07:50:41Z","snapshot_observed_at":"2026-08-10T08:27:52.621037Z","submitted_at":"2026-06-06T07:50:41Z","title":"LongMoE: Longitudinal Multimodal Learning via Trajectory-Aware Mixture-of-Experts","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-06-27T20:09:00.056162Z"},"links":{"citing_paper":"/paper/2606.09907"},"observation_digest":"sha256:3cbafbd3716ff963fe864b1fb341a1241d9437cd14de2feed61da82f3a15d020","observation_id":"920c4613-4fd0-4d0e-98b3-cad55ec98053","resolution":{"observed_at":"2026-06-27T20:09:00.056162Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1909.02950","last_updated":"2020-11-12T03:08:28Z","snapshot_observed_at":"2026-08-10T08:27:19.772782Z","submitted_at":"2019-09-06T14:59:18Z","title":"Supervised Multimodal Bitransformers for Classifying Images and Text","version":2},"cited_work":{"arxiv_id":"1909.02950","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1909.02950","snapshot_observed_at":"2026-07-02T20:47:23.022501Z","title":"digital","venue":null,"work_id":"f1465369-c0c9-4f98-ace0-efadd9d87805","year":1909},"citing_paper":{"arxiv_id":"2606.09907","last_updated":"2026-06-06T07:50:41Z","snapshot_observed_at":"2026-08-10T08:27:52.621037Z","submitted_at":"2026-06-06T07:50:41Z","title":"LongMoE: Longitudinal Multimodal Learning via Trajectory-Aware Mixture-of-Experts","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-06-27T20:09:00.056162Z"},"links":{"cited_paper":"/paper/1909.02950","citing_paper":"/paper/2606.09907"},"observation_digest":"sha256:25ab2c9f632bf4b89c606282bc59ff4f447dadb3ad55f2e5f62ce637e240598c","observation_id":"73cbfa37-0a9a-4f64-9e0d-89a60603d956","resolution":{"observed_at":"2026-07-02T20:47:23.025038Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-06-27T20:09:00.056162Z","title":"Reformer: The efficient transformer,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2606.09907","last_updated":"2026-06-06T07:50:41Z","snapshot_observed_at":"2026-08-10T08:27:52.621037Z","submitted_at":"2026-06-06T07:50:41Z","title":"LongMoE: Longitudinal Multimodal Learning via Trajectory-Aware Mixture-of-Experts","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-06-27T20:09:00.056162Z"},"links":{"citing_paper":"/paper/2606.09907"},"observation_digest":"sha256:250ad3d8218b21d9adbcedf637d1ee04464bb24f4689509058d96752ecc5dc23","observation_id":"dfacea1b-3156-46f7-8b06-0e067924c518","resolution":{"observed_at":"2026-06-27T20:09:00.056162Z","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":"2026-06-27T20:09:00.056162Z","title":null,"venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2606.09907","last_updated":"2026-06-06T07:50:41Z","snapshot_observed_at":"2026-08-10T08:27:52.621037Z","submitted_at":"2026-06-06T07:50:41Z","title":"LongMoE: Longitudinal Multimodal Learning via Trajectory-Aware Mixture-of-Experts","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-06-27T20:09:00.056162Z"},"links":{"citing_paper":"/paper/2606.09907"},"observation_digest":"sha256:5f5fcd4529de1022c62aa9d392d45cb704876aadbd874a42f7df15a400b552c9","observation_id":"d1917d8f-a64d-420e-a190-e9c546ef8dc7","resolution":{"observed_at":"2026-06-27T20:09:00.056162Z","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":"2026-06-27T20:09:00.056162Z","title":"Multilayer feedforward networks are universal approximators,","venue":null,"work_id":null,"year":1989},"citing_paper":{"arxiv_id":"2606.09907","last_updated":"2026-06-06T07:50:41Z","snapshot_observed_at":"2026-08-10T08:27:52.621037Z","submitted_at":"2026-06-06T07:50:41Z","title":"LongMoE: Longitudinal Multimodal Learning via Trajectory-Aware Mixture-of-Experts","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-06-27T20:09:00.056162Z"},"links":{"citing_paper":"/paper/2606.09907"},"observation_digest":"sha256:146636554cabbb7a3f886bdad29f9ad5f4b4b944666f6da82542cbf8aef4c073","observation_id":"78834cb5-621d-4e9c-8242-42eed17a4cae","resolution":{"observed_at":"2026-06-27T20:09:00.056162Z","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":"2026-06-27T20:09:00.056162Z","title":"Optimization methods for large-scale machine learning,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2606.09907","last_updated":"2026-06-06T07:50:41Z","snapshot_observed_at":"2026-08-10T08:27:52.621037Z","submitted_at":"2026-06-06T07:50:41Z","title":"LongMoE: Longitudinal Multimodal Learning via Trajectory-Aware Mixture-of-Experts","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-06-27T20:09:00.056162Z"},"links":{"citing_paper":"/paper/2606.09907"},"observation_digest":"sha256:aa33a68b483f38cb30bf42667ac63700a6c9668f2bb376130d88ae03e3e27cda","observation_id":"af6f21ed-28a1-40bc-8be0-d17dd08f57c6","resolution":{"observed_at":"2026-06-27T20:09:00.056162Z","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":"2026-06-27T20:09:00.056162Z","title":"Are transformers universal approximators of sequence-to-sequence functions?","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2606.09907","last_updated":"2026-06-06T07:50:41Z","snapshot_observed_at":"2026-08-10T08:27:52.621037Z","submitted_at":"2026-06-06T07:50:41Z","title":"LongMoE: Longitudinal Multimodal Learning via Trajectory-Aware Mixture-of-Experts","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-06-27T20:09:00.056162Z"},"links":{"citing_paper":"/paper/2606.09907"},"observation_digest":"sha256:98c8f030f05ad73d4dbf02e653a34e45758091b0e1a43c18cca512cc2d2260b9","observation_id":"d2703fd3-2c77-4279-9bbd-e46425a84294","resolution":{"observed_at":"2026-06-27T20:09:00.056162Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2606.09907","last_updated":"2026-06-06T07:50:41Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-10T08:27:52.621037Z","submitted_at":"2026-06-06T07:50:41Z","title":"LongMoE: Longitudinal Multimodal Learning via Trajectory-Aware Mixture-of-Experts"},"reference_resolution":{"displayed":51,"state_counts":{"malformed_identifier":1,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":47,"verified_exact":2,"verified_fuzzy":0},"total_outbound_references":51},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 51 of 51 outbound references and 0 inbound Pith citation observations for arXiv:2606.09907."}