{"as_of":"2026-08-09T04:50:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:477cecb5f18a9b0a3a0a94015b162ff60e2d3f38b43c49b99ad4fe72a2e5cc0e","coverage":[{"denominator":29,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":29,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-08T15:45:46.182206Z","state":"measured"},{"denominator":30,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":30,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-01T16:41:37.241236Z","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":[{"citation":{"cited_paper":{"arxiv_id":"2502.06355","last_updated":"2025-07-08T21:12:11Z","snapshot_observed_at":"2026-08-08T15:40:21.853004Z","submitted_at":"2025-02-10T11:10:41Z","title":"Fine-tuning Multimodal Transformers on Edge: A Parallel Split Learning Approach","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.06355","snapshot_observed_at":"2026-08-01T16:41:37.241236Z","title":"arXiv preprint arXiv:2502.06355 (2025)","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.17913","last_updated":"2026-07-20T13:08:41Z","snapshot_observed_at":"2026-08-05T06:43:05.293637Z","submitted_at":"2026-07-20T13:08:41Z","title":"AutoEncoder-Compressed Parallel Split Learning for Pre-trained Model Fine-Tuning","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-01T16:41:37.241236Z"},"links":{"cited_paper":"/paper/2502.06355","citing_paper":"/paper/2607.17913"},"observation_digest":"sha256:d8ffb8e5de34718c125905bc5262719a9e23f841beaf6a936bfe0865ebdc9e28","observation_id":"aebefd0f-aadf-4d82-8629-9886ad8242a6","resolution":{"observed_at":"2026-08-01T16:41:37.241236Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2502.06355/citation-record","integrity":"/paper/2502.06355/integrity","json":"/paper/2502.06355/citation-record.json","paper":"/paper/2502.06355"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T15:45:46.507368Z","title":"Vatt: Transformers for multimodal self-supervised learning from raw video, audio and text,","venue":null,"work_id":"b4c05cd9-381c-4436-a158-5ca8f4dad2ae","year":2021},"citing_paper":{"arxiv_id":"2502.06355","last_updated":"2025-07-08T21:12:11Z","snapshot_observed_at":"2026-08-08T15:40:21.853004Z","submitted_at":"2025-02-10T11:10:41Z","title":"Fine-tuning Multimodal Transformers on Edge: A Parallel Split Learning Approach","version":3},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-08T15:45:46.074894Z"},"links":{"citing_paper":"/paper/2502.06355"},"observation_digest":"sha256:ad45142d3c32b88deb9c3cedaf0a72eca08c2fbb740b727578f0b64bf67ad7a5","observation_id":"047863be-79c3-4071-8719-f096f8fb55be","resolution":{"observed_at":"2026-08-08T15:45:46.511457Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T15:45:46.454734Z","title":"Imagebind: One embedding space to bind them all,","venue":null,"work_id":"c2286267-6c00-472f-b965-eb10505ec4a9","year":2023},"citing_paper":{"arxiv_id":"2502.06355","last_updated":"2025-07-08T21:12:11Z","snapshot_observed_at":"2026-08-08T15:40:21.853004Z","submitted_at":"2025-02-10T11:10:41Z","title":"Fine-tuning Multimodal Transformers on Edge: A Parallel Split Learning Approach","version":3},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-08T15:45:46.099243Z"},"links":{"citing_paper":"/paper/2502.06355"},"observation_digest":"sha256:399b5d097d942e892ab2d7d1803df0f0ccd4bb20274eaac77ac2928cfe55fa88","observation_id":"b481ac32-0527-466c-bfb5-1ec656a21d18","resolution":{"observed_at":"2026-08-08T15:45:46.458426Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T15:45:46.444028Z","title":"Dis- tributed learning of deep neural network over multiple agents,","venue":null,"work_id":"4621e624-71b5-475c-9bd0-7d854e12f6f2","year":2018},"citing_paper":{"arxiv_id":"2502.06355","last_updated":"2025-07-08T21:12:11Z","snapshot_observed_at":"2026-08-08T15:40:21.853004Z","submitted_at":"2025-02-10T11:10:41Z","title":"Fine-tuning Multimodal Transformers on Edge: A Parallel Split Learning Approach","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-08T15:45:46.106043Z"},"links":{"citing_paper":"/paper/2502.06355"},"observation_digest":"sha256:40fd9973ca41cdf4f58146c9fabf17d9875e8909803b6c853f94e7631a125bbd","observation_id":"e69c759e-9c45-43be-b0f2-2f2826b2543d","resolution":{"observed_at":"2026-08-08T15:45:46.447966Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T15:45:46.422079Z","title":"Parameter- efficient transfer learning for nlp","venue":null,"work_id":"b58c239d-835b-47a7-b123-7cb7b5a3f994","year":2019},"citing_paper":{"arxiv_id":"2502.06355","last_updated":"2025-07-08T21:12:11Z","snapshot_observed_at":"2026-08-08T15:40:21.853004Z","submitted_at":"2025-02-10T11:10:41Z","title":"Fine-tuning Multimodal Transformers on Edge: A Parallel Split Learning Approach","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-08T15:45:46.112255Z"},"links":{"citing_paper":"/paper/2502.06355"},"observation_digest":"sha256:036da57edce28a1bd894c1ac31cc381816fa22eceb48c4b342c1aa369f1b7d44","observation_id":"afc58a40-9189-4937-859e-37974fad4339","resolution":{"observed_at":"2026-08-08T15:45:46.425705Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.10185","last_updated":"2024-03-26T13:11:07Z","snapshot_observed_at":"2026-07-06T16:08:08.552117Z","submitted_at":"2023-08-20T07:26:51Z","title":"ViT-Lens: Initiating Omni-Modal Exploration through 3D Insights","version":2},"cited_work":{"arxiv_id":"2308.10185","doi":null,"metadata_source":"pith","pith_arxiv_id":"2308.10185","snapshot_observed_at":"2026-08-08T15:45:46.263912Z","title":"ViT-Lens: Initiating Omni-Modal Exploration through 3D Insights","venue":"cs.CV","work_id":"2532c526-e6f9-4f0a-ae2e-4a7f6d613dba","year":2023},"citing_paper":{"arxiv_id":"2502.06355","last_updated":"2025-07-08T21:12:11Z","snapshot_observed_at":"2026-08-08T15:40:21.853004Z","submitted_at":"2025-02-10T11:10:41Z","title":"Fine-tuning Multimodal Transformers on Edge: A Parallel Split Learning Approach","version":3},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-08T15:45:46.119825Z"},"links":{"cited_paper":"/paper/2308.10185","citing_paper":"/paper/2502.06355"},"observation_digest":"sha256:b7cd417c80917fc57fbea222893e397204768617deb6e5dbb0df10707e5b4e0d","observation_id":"d384fa3a-feb2-4ae9-b880-3e2ffc2774d7","resolution":{"observed_at":"2026-08-08T15:45:46.270073Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T15:45:46.123879Z","title":"Federated learning on non-iid data silos: An experimental study,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.06355","last_updated":"2025-07-08T21:12:11Z","snapshot_observed_at":"2026-08-08T15:40:21.853004Z","submitted_at":"2025-02-10T11:10:41Z","title":"Fine-tuning Multimodal Transformers on Edge: A Parallel Split Learning Approach","version":3},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-08T15:45:46.123879Z"},"links":{"citing_paper":"/paper/2502.06355"},"observation_digest":"sha256:c29308da1624f22f4d4b6c262ab692392d2539a7a11b175341a92923a3fbe343","observation_id":"c5538d8b-5472-42ba-9f67-dc161476ce5d","resolution":{"observed_at":"2026-08-08T15:45:46.123879Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T15:45:46.392371Z","title":"Microsoft coco: Common objects in con- text","venue":null,"work_id":"b936c9a8-ec5d-4223-a7e8-258b7046043f","year":2014},"citing_paper":{"arxiv_id":"2502.06355","last_updated":"2025-07-08T21:12:11Z","snapshot_observed_at":"2026-08-08T15:40:21.853004Z","submitted_at":"2025-02-10T11:10:41Z","title":"Fine-tuning Multimodal Transformers on Edge: A Parallel Split Learning Approach","version":3},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-08T15:45:46.127552Z"},"links":{"citing_paper":"/paper/2502.06355"},"observation_digest":"sha256:0eeba391e967ce4c92a4caf4635be2cd1a34ac6b3c2f25846e5d55422caab3f6","observation_id":"88d47e6a-9630-4a15-87ed-9c1a425d8649","resolution":{"observed_at":"2026-08-08T15:45:46.396507Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2302.13485","last_updated":"2023-07-09T12:36:50Z","snapshot_observed_at":"2026-07-06T14:56:04.791076Z","submitted_at":"2023-02-27T02:49:06Z","title":"FedCLIP: Fast Generalization and Personalization for CLIP in Federated Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.13485","snapshot_observed_at":"2026-08-08T15:45:46.135137Z","title":"Fedclip: Fast generalization and personalization for clip in feder- ated learning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.06355","last_updated":"2025-07-08T21:12:11Z","snapshot_observed_at":"2026-08-08T15:40:21.853004Z","submitted_at":"2025-02-10T11:10:41Z","title":"Fine-tuning Multimodal Transformers on Edge: A Parallel Split Learning Approach","version":3},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-08T15:45:46.135137Z"},"links":{"cited_paper":"/paper/2302.13485","citing_paper":"/paper/2502.06355"},"observation_digest":"sha256:50262f8b75956239b815d231f365ad80de848580077e8de13f0bac48bc31381b","observation_id":"6e99a235-226d-40a1-9f01-331a6e6b765e","resolution":{"observed_at":"2026-08-08T15:45:46.135137Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T15:45:46.370886Z","title":"Scalable aggregated split learning for data-driven edge intelligence on internet-of-things","venue":null,"work_id":"8607ec41-b1f9-4730-b2e7-cff17a00301e","year":2023},"citing_paper":{"arxiv_id":"2502.06355","last_updated":"2025-07-08T21:12:11Z","snapshot_observed_at":"2026-08-08T15:40:21.853004Z","submitted_at":"2025-02-10T11:10:41Z","title":"Fine-tuning Multimodal Transformers on Edge: A Parallel Split Learning Approach","version":3},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-08T15:45:46.139246Z"},"links":{"citing_paper":"/paper/2502.06355"},"observation_digest":"sha256:41b559c3381250d8733b96061323fb7c33877d762bdea2a6a4b5845a81b5ae03","observation_id":"ff2e8f44-388b-4317-aab3-d1c0534f33e9","resolution":{"observed_at":"2026-08-08T15:45:46.374599Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T15:45:46.360479Z","title":"Communication-Efficient Learning of Deep Networks from De- centralized Data","venue":null,"work_id":"04c9c0f7-74d0-4882-8fef-cc43c28c829f","year":2017},"citing_paper":{"arxiv_id":"2502.06355","last_updated":"2025-07-08T21:12:11Z","snapshot_observed_at":"2026-08-08T15:40:21.853004Z","submitted_at":"2025-02-10T11:10:41Z","title":"Fine-tuning Multimodal Transformers on Edge: A Parallel Split Learning Approach","version":3},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-08T15:45:46.143029Z"},"links":{"citing_paper":"/paper/2502.06355"},"observation_digest":"sha256:55837f4e5f50d30d2cd597a97537559e1a19ad35f134b836eebfc7f8a2393450","observation_id":"76c39fa3-52d1-4317-b6f7-97b9a3ded190","resolution":{"observed_at":"2026-08-08T15:45:46.364187Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T15:45:46.349456Z","title":"Mix2sfl: Two-way mixup for scalable, accurate, and communication-efficient split federated learning","venue":null,"work_id":"52c5ba22-d7d2-4170-af6d-77db3be23207","year":2023},"citing_paper":{"arxiv_id":"2502.06355","last_updated":"2025-07-08T21:12:11Z","snapshot_observed_at":"2026-08-08T15:40:21.853004Z","submitted_at":"2025-02-10T11:10:41Z","title":"Fine-tuning Multimodal Transformers on Edge: A Parallel Split Learning Approach","version":3},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-08T15:45:46.146614Z"},"links":{"citing_paper":"/paper/2502.06355"},"observation_digest":"sha256:f3792447b1bc48d0a9d557a801bc9494d6dbca2197b6aefbe85d5a9a1d61bfb2","observation_id":"88096161-94a3-4b34-b601-c554372c80c6","resolution":{"observed_at":"2026-08-08T15:45:46.353629Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T15:45:46.338111Z","title":"Server-side local gradient averaging and learning rate acceleration for scalable split learning,","venue":null,"work_id":"c81848c2-967e-4e60-b328-68bbc9ca7fbe","year":2021},"citing_paper":{"arxiv_id":"2502.06355","last_updated":"2025-07-08T21:12:11Z","snapshot_observed_at":"2026-08-08T15:40:21.853004Z","submitted_at":"2025-02-10T11:10:41Z","title":"Fine-tuning Multimodal Transformers on Edge: A Parallel Split Learning Approach","version":3},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-08T15:45:46.150833Z"},"links":{"citing_paper":"/paper/2502.06355"},"observation_digest":"sha256:f151e8c1e2b60442421df3abca47c3e05a713c7c6752ae97bca0e5a395f4ebe7","observation_id":"bc431f59-4408-4cbf-afad-156d1ee9d040","resolution":{"observed_at":"2026-08-08T15:45:46.341856Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T15:45:46.328820Z","title":"Flickr30k entities: Collecting region-to-phrase corre- spondences for richer image-to-sentence models","venue":null,"work_id":"6a946aec-96dc-43f9-841e-b714ed085c45","year":2015},"citing_paper":{"arxiv_id":"2502.06355","last_updated":"2025-07-08T21:12:11Z","snapshot_observed_at":"2026-08-08T15:40:21.853004Z","submitted_at":"2025-02-10T11:10:41Z","title":"Fine-tuning Multimodal Transformers on Edge: A Parallel Split Learning Approach","version":3},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-08T15:45:46.154589Z"},"links":{"citing_paper":"/paper/2502.06355"},"observation_digest":"sha256:6af83d8564f39301d4f0dff7bef84b796bfc914d526773275f8cda5e0d2f7d44","observation_id":"867ab09c-342e-4aff-97cd-37ca8eb9c915","resolution":{"observed_at":"2026-08-08T15:45:46.331970Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T15:45:46.319396Z","title":"Learning transferable visual models from natural language supervision,","venue":null,"work_id":"106ea443-091a-4ccf-9759-6635a8423e97","year":2021},"citing_paper":{"arxiv_id":"2502.06355","last_updated":"2025-07-08T21:12:11Z","snapshot_observed_at":"2026-08-08T15:40:21.853004Z","submitted_at":"2025-02-10T11:10:41Z","title":"Fine-tuning Multimodal Transformers on Edge: A Parallel Split Learning Approach","version":3},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-08T15:45:46.162140Z"},"links":{"citing_paper":"/paper/2502.06355"},"observation_digest":"sha256:d12dd979f99a21eb87db6ca21f5125077fa761de1c61228130ced5314fea7446","observation_id":"e9e6aa05-c7d5-4b4c-b220-c5a596f52fd3","resolution":{"observed_at":"2026-08-08T15:45:46.322614Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T15:45:46.309718Z","title":"Exploring models and data for image question answering","venue":null,"work_id":"9dec5fe2-886e-4044-8f97-934ad4af741e","year":2015},"citing_paper":{"arxiv_id":"2502.06355","last_updated":"2025-07-08T21:12:11Z","snapshot_observed_at":"2026-08-08T15:40:21.853004Z","submitted_at":"2025-02-10T11:10:41Z","title":"Fine-tuning Multimodal Transformers on Edge: A Parallel Split Learning Approach","version":3},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-08T15:45:46.166079Z"},"links":{"citing_paper":"/paper/2502.06355"},"observation_digest":"sha256:ff432bf3054fa698653f819e171e88414f9a7883e2cf8bc072263bca51f0cb5a","observation_id":"c6e27adf-2f4b-4aed-96c9-94f094e9df24","resolution":{"observed_at":"2026-08-08T15:45:46.312961Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1212.0402","last_updated":"2012-12-03T14:45:31Z","snapshot_observed_at":"2026-07-06T03:01:10.229407Z","submitted_at":"2012-12-03T14:45:31Z","title":"UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1212.0402","snapshot_observed_at":"2026-08-08T15:45:46.169912Z","title":"Ucf101: A dataset of 101 human actions classes from videos in the wild","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2502.06355","last_updated":"2025-07-08T21:12:11Z","snapshot_observed_at":"2026-08-08T15:40:21.853004Z","submitted_at":"2025-02-10T11:10:41Z","title":"Fine-tuning Multimodal Transformers on Edge: A Parallel Split Learning Approach","version":3},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-08T15:45:46.169912Z"},"links":{"cited_paper":"/paper/1212.0402","citing_paper":"/paper/2502.06355"},"observation_digest":"sha256:b61f5a4c98980b49f52bdafc27c5e7a9826d9b4f7eed580400f6d44a42837eb7","observation_id":"068d5ab2-9a8a-42b7-95a8-03906bba3f95","resolution":{"observed_at":"2026-08-08T15:45:46.169912Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.07735","last_updated":"2024-03-31T11:35:46Z","snapshot_observed_at":"2026-08-08T16:25:29.798085Z","submitted_at":"2023-04-16T09:25:24Z","title":"Permutation Equivariance of Transformers and Its Applications","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.07735","snapshot_observed_at":"2026-08-08T15:45:46.177880Z","title":"Shuffled trans- former for privacy-preserving split learning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.06355","last_updated":"2025-07-08T21:12:11Z","snapshot_observed_at":"2026-08-08T15:40:21.853004Z","submitted_at":"2025-02-10T11:10:41Z","title":"Fine-tuning Multimodal Transformers on Edge: A Parallel Split Learning Approach","version":3},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-08T15:45:46.177880Z"},"links":{"cited_paper":"/paper/2304.07735","citing_paper":"/paper/2502.06355"},"observation_digest":"sha256:d98d35d25f42a631cc496ab410eb2b031ffaf15c3cb8246b67bfba84baa12cb8","observation_id":"7ed6be78-5418-4f27-896b-ac766681927e","resolution":{"observed_at":"2026-08-08T15:45:46.177880Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.10802","last_updated":"2023-07-20T12:10:29Z","snapshot_observed_at":"2026-07-06T15:56:25.975005Z","submitted_at":"2023-07-20T12:10:29Z","title":"Meta-Transformer: A Unified Framework for Multimodal Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.10802","snapshot_observed_at":"2026-08-08T15:45:46.182206Z","title":"Meta-transformer: A unified framework for multimodal learning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.06355","last_updated":"2025-07-08T21:12:11Z","snapshot_observed_at":"2026-08-08T15:40:21.853004Z","submitted_at":"2025-02-10T11:10:41Z","title":"Fine-tuning Multimodal Transformers on Edge: A Parallel Split Learning Approach","version":3},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-08T15:45:46.182206Z"},"links":{"cited_paper":"/paper/2307.10802","citing_paper":"/paper/2502.06355"},"observation_digest":"sha256:dcc98049b7e8eb70abf148a674f09a1e3a8fdab55647f366cda93d24d80c8869","observation_id":"b28a1464-fd51-485c-b3ce-5993f5cd603c","resolution":{"observed_at":"2026-08-08T15:45:46.182206Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T15:45:46.299164Z","title":"Cross-media learning for image sentiment analysis in the wild","venue":null,"work_id":"428c886c-fd57-42ce-a0af-4df1168f3a30","year":2017},"citing_paper":{"arxiv_id":"2502.06355","last_updated":"2025-07-08T21:12:11Z","snapshot_observed_at":"2026-08-08T15:40:21.853004Z","submitted_at":"2025-02-10T11:10:41Z","title":"Fine-tuning Multimodal Transformers on Edge: A Parallel Split Learning Approach","version":3},"reference_index":2012,"source":"pdf_text","source_observed_at":"2026-08-08T15:45:46.174092Z"},"links":{"citing_paper":"/paper/2502.06355"},"observation_digest":"sha256:dc8b729d30cd775a6f4bbd2be19cbe0f9ea9659f8b8b174dff367114acfadbe9","observation_id":"b2faa4c5-5bf5-4e57-9a74-ab440ff1a163","resolution":{"observed_at":"2026-08-08T15:45:46.302732Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T15:45:46.381924Z","title":"Efficient par- allel split learning over resource-constrained wireless edge net- works","venue":null,"work_id":"6100f784-21ba-41b0-88b0-3b2f82f49f94","year":2024},"citing_paper":{"arxiv_id":"2502.06355","last_updated":"2025-07-08T21:12:11Z","snapshot_observed_at":"2026-08-08T15:40:21.853004Z","submitted_at":"2025-02-10T11:10:41Z","title":"Fine-tuning Multimodal Transformers on Edge: A Parallel Split Learning Approach","version":3},"reference_index":2014,"source":"pdf_text","source_observed_at":"2026-08-08T15:45:46.131345Z"},"links":{"citing_paper":"/paper/2502.06355"},"observation_digest":"sha256:25151fbbec3cf1571fc074a82273615f81b0e235c0f475e13cdecf0aca14ac06","observation_id":"203b684d-ddf3-4051-9698-06c6b2d55a2d","resolution":{"observed_at":"2026-08-08T15:45:46.385583Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1810.02508","last_updated":"2019-06-04T12:33:49Z","snapshot_observed_at":"2026-07-06T07:06:12.726165Z","submitted_at":"2018-10-05T03:50:24Z","title":"MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1810.02508","snapshot_observed_at":"2026-08-08T15:45:46.158254Z","title":"Meld: A multimodal multi-party dataset for emotion recognition in conversations","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2502.06355","last_updated":"2025-07-08T21:12:11Z","snapshot_observed_at":"2026-08-08T15:40:21.853004Z","submitted_at":"2025-02-10T11:10:41Z","title":"Fine-tuning Multimodal Transformers on Edge: A Parallel Split Learning Approach","version":3},"reference_index":2015,"source":"pdf_text","source_observed_at":"2026-08-08T15:45:46.158254Z"},"links":{"cited_paper":"/paper/1810.02508","citing_paper":"/paper/2502.06355"},"observation_digest":"sha256:1e8f39b697ed297303209454327380220cf9661b500d3d10a002d718332bbe49","observation_id":"476a4860-d038-4dbb-988b-e16c8978d0a9","resolution":{"observed_at":"2026-08-08T15:45:46.158254Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T15:45:46.485449Z","title":"The iot breaches your household again","venue":null,"work_id":"59a6ad44-8f08-4249-88f4-62988cc80b17","year":2024},"citing_paper":{"arxiv_id":"2502.06355","last_updated":"2025-07-08T21:12:11Z","snapshot_observed_at":"2026-08-08T15:40:21.853004Z","submitted_at":"2025-02-10T11:10:41Z","title":"Fine-tuning Multimodal Transformers on Edge: A Parallel Split Learning Approach","version":3},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-08T15:45:46.083782Z"},"links":{"citing_paper":"/paper/2502.06355"},"observation_digest":"sha256:4f533f751f81b2ad3a5e5cba5af5d63cc2c1904ede06e07f7c5cadb821a87ad4","observation_id":"1919314f-7d34-4b0e-90b4-2d8e4a4a7660","resolution":{"observed_at":"2026-08-08T15:45:46.488910Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T15:45:46.432682Z","title":"Accelerating federated learning with split learning on locally generated losses","venue":null,"work_id":"ed61f41c-8388-4fba-93ec-f9cfbe31f7b3","year":2021},"citing_paper":{"arxiv_id":"2502.06355","last_updated":"2025-07-08T21:12:11Z","snapshot_observed_at":"2026-08-08T15:40:21.853004Z","submitted_at":"2025-02-10T11:10:41Z","title":"Fine-tuning Multimodal Transformers on Edge: A Parallel Split Learning Approach","version":3},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-08T15:45:46.109116Z"},"links":{"citing_paper":"/paper/2502.06355"},"observation_digest":"sha256:0f52d327c157638bf73c98772da9d9860af32bdbebc460e5d2ce622997735459","observation_id":"fb285ac0-c69a-48ed-af88-c8e18d841bb3","resolution":{"observed_at":"2026-08-08T15:45:46.436925Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T15:45:46.410064Z","title":"Privacy-sensitive parallel split learning","venue":null,"work_id":"04744624-498d-4284-b7e3-0cd5612f4a90","year":2020},"citing_paper":{"arxiv_id":"2502.06355","last_updated":"2025-07-08T21:12:11Z","snapshot_observed_at":"2026-08-08T15:40:21.853004Z","submitted_at":"2025-02-10T11:10:41Z","title":"Fine-tuning Multimodal Transformers on Edge: A Parallel Split Learning Approach","version":3},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-08T15:45:46.115887Z"},"links":{"citing_paper":"/paper/2502.06355"},"observation_digest":"sha256:211937ac6abdf130c9002742045d692915e1ab89288d673b234f209ceb996524","observation_id":"b61cd8e7-21e4-460c-8769-d1045fc486f5","resolution":{"observed_at":"2026-08-08T15:45:46.414118Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T15:45:46.475375Z","title":"Multi-modal align- ment using representation codebook,","venue":null,"work_id":"86124231-f31c-4f91-9bc3-3bf9a735999a","year":2022},"citing_paper":{"arxiv_id":"2502.06355","last_updated":"2025-07-08T21:12:11Z","snapshot_observed_at":"2026-08-08T15:40:21.853004Z","submitted_at":"2025-02-10T11:10:41Z","title":"Fine-tuning Multimodal Transformers on Edge: A Parallel Split Learning Approach","version":3},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-08T15:45:46.091790Z"},"links":{"citing_paper":"/paper/2502.06355"},"observation_digest":"sha256:3c6e9f6f291a015fef01a602e62344875aa95331fdd155d255993bcf80f700cd","observation_id":"a2c380c3-b741-4d10-88a1-fe7d9271c522","resolution":{"observed_at":"2026-08-08T15:45:46.478560Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T15:45:46.495854Z","title":"Look, listen and learn","venue":null,"work_id":"4ed3ccdb-72bf-410c-8f5d-a8c89414fa48","year":2017},"citing_paper":{"arxiv_id":"2502.06355","last_updated":"2025-07-08T21:12:11Z","snapshot_observed_at":"2026-08-08T15:40:21.853004Z","submitted_at":"2025-02-10T11:10:41Z","title":"Fine-tuning Multimodal Transformers on Edge: A Parallel Split Learning Approach","version":3},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-08T15:45:46.079585Z"},"links":{"citing_paper":"/paper/2502.06355"},"observation_digest":"sha256:cf5a668655ebf80681b4f393c8656a0bdef59ae5237e039dc5d4fb44da8e5e64","observation_id":"b483d407-0919-4b42-840a-94bbdca68a30","resolution":{"observed_at":"2026-08-08T15:45:46.499614Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T15:45:46.465414Z","title":"Split learn- ing of multi-modal medical image classification","venue":null,"work_id":"f039a951-8203-43b7-8a6c-d6ebded4ce16","year":2024},"citing_paper":{"arxiv_id":"2502.06355","last_updated":"2025-07-08T21:12:11Z","snapshot_observed_at":"2026-08-08T15:40:21.853004Z","submitted_at":"2025-02-10T11:10:41Z","title":"Fine-tuning Multimodal Transformers on Edge: A Parallel Split Learning Approach","version":3},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-08T15:45:46.095406Z"},"links":{"citing_paper":"/paper/2502.06355"},"observation_digest":"sha256:cdf7ac83fb0c92945ce50eecc2057adc15a77c4e223ec0a265abd7b61b8aae7d","observation_id":"46967e75-311e-4564-ac23-cebf4f614e40","resolution":{"observed_at":"2026-08-08T15:45:46.468989Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2104.01778","last_updated":"2021-07-08T20:16:28Z","snapshot_observed_at":"2026-08-08T11:33:21.735489Z","submitted_at":"2021-04-05T05:26:29Z","title":"AST: Audio Spectrogram Transformer","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.01778","snapshot_observed_at":"2026-08-08T15:45:46.102491Z","title":"Ast: Audio spectrogram transformer","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.06355","last_updated":"2025-07-08T21:12:11Z","snapshot_observed_at":"2026-08-08T15:40:21.853004Z","submitted_at":"2025-02-10T11:10:41Z","title":"Fine-tuning Multimodal Transformers on Edge: A Parallel Split Learning Approach","version":3},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-08T15:45:46.102491Z"},"links":{"cited_paper":"/paper/2104.01778","citing_paper":"/paper/2502.06355"},"observation_digest":"sha256:75e7f50d4f8f3b46da72f1fb90afdb2980c99138feb1e0d7d1abbc07a699ee11","observation_id":"01a0685b-d2c9-4e6d-8743-21b5b06fdc70","resolution":{"observed_at":"2026-08-08T15:45:46.102491Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.11929","last_updated":"2021-06-03T13:08:56Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2020-10-22T17:55:59Z","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.11929","snapshot_observed_at":"2026-08-08T15:45:46.087545Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.06355","last_updated":"2025-07-08T21:12:11Z","snapshot_observed_at":"2026-08-08T15:40:21.853004Z","submitted_at":"2025-02-10T11:10:41Z","title":"Fine-tuning Multimodal Transformers on Edge: A Parallel Split Learning Approach","version":3},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-08T15:45:46.087545Z"},"links":{"cited_paper":"/paper/2010.11929","citing_paper":"/paper/2502.06355"},"observation_digest":"sha256:c9035a75426f42fec69f131803c7ff97e9a246ade0fc68f76856f9eb60abd4a1","observation_id":"633f2018-36aa-45ce-90cd-b1a626ebee3a","resolution":{"observed_at":"2026-08-08T15:45:46.087545Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2502.06355","last_updated":"2025-07-08T21:12:11Z","latest_version":3,"primary_category":"cs.DC","snapshot_observed_at":"2026-08-08T15:40:21.853004Z","submitted_at":"2025-02-10T11:10:41Z","title":"Fine-tuning Multimodal Transformers on Edge: A Parallel Split Learning Approach"},"reference_resolution":{"displayed":29,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":8,"verified_exact":1,"verified_fuzzy":20},"total_outbound_references":29},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 29 of 29 outbound references and 1 inbound Pith citation observation for arXiv:2502.06355."}