{"as_of":"2026-08-20T11:18:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:834c9afd36bbc5cfc61a9d4b0c8db6fe741c101298c6fcae4218be101084ce82","coverage":[{"denominator":43,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":43,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T04:51:52.390069Z","state":"measured"},{"denominator":43,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":43,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-20T06:33:59.587034+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/2508.02978/citation-record","integrity":"/paper/2508.02978/integrity","json":"/paper/2508.02978/citation-record.json","paper":"/paper/2508.02978"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T04:51:58.941149Z","title":"MT- LoRA: Low-rank adaptation approach for efficient multi- task learning","venue":null,"work_id":"acc285b4-57a0-49f6-92b8-13031a424eeb","year":2024},"citing_paper":{"arxiv_id":"2508.02978","last_updated":"2025-08-05T01:04:32Z","snapshot_observed_at":"2026-08-18T11:43:48.197239Z","submitted_at":"2025-08-05T01:04:32Z","title":"Separating Shared and Domain-Specific LoRAs for Multi-Domain Learning","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T04:51:49.174806Z"},"links":{"citing_paper":"/paper/2508.02978"},"observation_digest":"sha256:2fd6b191ff225b38f5dd8604b51fa389d84107f7523e39c001ccf5a3bf2afb3f","observation_id":"cbd238f6-0221-4ecc-be28-52996de6124f","resolution":{"observed_at":"2026-08-06T04:51:59.011333Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2009.09796","last_updated":"2020-09-10T19:31:04Z","snapshot_observed_at":"2026-08-09T08:30:49.737024Z","submitted_at":"2020-09-10T19:31:04Z","title":"Multi-Task Learning with Deep Neural Networks: A Survey","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2009.09796","snapshot_observed_at":"2026-08-06T04:51:49.277546Z","title":"Multi-task learning with deep neural networks: A survey","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2508.02978","last_updated":"2025-08-05T01:04:32Z","snapshot_observed_at":"2026-08-18T11:43:48.197239Z","submitted_at":"2025-08-05T01:04:32Z","title":"Separating Shared and Domain-Specific LoRAs for Multi-Domain Learning","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T04:51:49.277546Z"},"links":{"cited_paper":"/paper/2009.09796","citing_paper":"/paper/2508.02978"},"observation_digest":"sha256:9b90f2530a52c6fcbf7a303338e80732200df858e7ba1bd7faba1864adf1b20e","observation_id":"689f34fc-d8fa-45aa-a146-9388ef3c2ab2","resolution":{"observed_at":"2026-08-06T04:51:49.277546Z","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":"2026-08-06T04:51:58.754580Z","title":"QLoRA: Efficient finetuning of quantized llms","venue":null,"work_id":"4377b932-9431-4160-ad88-d623593d97ba","year":2023},"citing_paper":{"arxiv_id":"2508.02978","last_updated":"2025-08-05T01:04:32Z","snapshot_observed_at":"2026-08-18T11:43:48.197239Z","submitted_at":"2025-08-05T01:04:32Z","title":"Separating Shared and Domain-Specific LoRAs for Multi-Domain Learning","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T04:51:49.324895Z"},"links":{"citing_paper":"/paper/2508.02978"},"observation_digest":"sha256:0bd7f0077ec9f91345b8755c92fd6ef5f45eef7a68667c8e2b730faebb436cf1","observation_id":"ffd3a88c-e16b-43df-9f98-c04a83e52085","resolution":{"observed_at":"2026-08-06T04:51:58.830205Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T04:51:58.525349Z","title":"BERT: Pre-training of deep bidirectional trans- formers for language understanding","venue":null,"work_id":"835dc4c0-3980-4d79-89a8-3eaa18884d56","year":2019},"citing_paper":{"arxiv_id":"2508.02978","last_updated":"2025-08-05T01:04:32Z","snapshot_observed_at":"2026-08-18T11:43:48.197239Z","submitted_at":"2025-08-05T01:04:32Z","title":"Separating Shared and Domain-Specific LoRAs for Multi-Domain Learning","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T04:51:49.412818Z"},"links":{"citing_paper":"/paper/2508.02978"},"observation_digest":"sha256:75e6bb402667fe24683e094b545ce379b816827bc1cde41870769d71a4605445","observation_id":"0342470e-cbfa-4ed2-8d1f-5419737eb2a4","resolution":{"observed_at":"2026-08-06T04:51:58.614512Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T04:51:58.349693Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale","venue":null,"work_id":"cfd08edb-99d5-45a4-8271-3e1391b9a53a","year":2021},"citing_paper":{"arxiv_id":"2508.02978","last_updated":"2025-08-05T01:04:32Z","snapshot_observed_at":"2026-08-18T11:43:48.197239Z","submitted_at":"2025-08-05T01:04:32Z","title":"Separating Shared and Domain-Specific LoRAs for Multi-Domain Learning","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T04:51:49.519791Z"},"links":{"citing_paper":"/paper/2508.02978"},"observation_digest":"sha256:834d930a9e4d12d1548a24cb69bdd28204896d3789aca6d13abf72b1b061a5f3","observation_id":"99ad3ebf-cdce-4826-ab16-8abf8fbe161a","resolution":{"observed_at":"2026-08-06T04:51:58.425082Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T04:51:58.118021Z","title":"Omnivore: A sin- gle model for many visual modalities","venue":null,"work_id":"ad931ec0-47d0-48e2-87f3-abb88a4c86f6","year":2022},"citing_paper":{"arxiv_id":"2508.02978","last_updated":"2025-08-05T01:04:32Z","snapshot_observed_at":"2026-08-18T11:43:48.197239Z","submitted_at":"2025-08-05T01:04:32Z","title":"Separating Shared and Domain-Specific LoRAs for Multi-Domain Learning","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T04:51:49.598533Z"},"links":{"citing_paper":"/paper/2508.02978"},"observation_digest":"sha256:c77fe0567e818b4ec6b4429ad476ab24e4bd7d8154488d45a8fbf0659ef4baee","observation_id":"d02a173c-fcff-400c-a402-54514778c786","resolution":{"observed_at":"2026-08-06T04:51:58.247567Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T04:51:57.895949Z","title":"Parameter-efficient fine-tuning for large models: A comprehensive survey","venue":null,"work_id":"d71ec8b2-39eb-47a6-b2c1-ad19f5265edb","year":2024},"citing_paper":{"arxiv_id":"2508.02978","last_updated":"2025-08-05T01:04:32Z","snapshot_observed_at":"2026-08-18T11:43:48.197239Z","submitted_at":"2025-08-05T01:04:32Z","title":"Separating Shared and Domain-Specific LoRAs for Multi-Domain Learning","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T04:51:49.666128Z"},"links":{"citing_paper":"/paper/2508.02978"},"observation_digest":"sha256:2df7f8d70a42354bb633fd8274f8e1de5de9fe0625ec94b064445d0ff78bdb03","observation_id":"944b0a5e-96ad-41bf-82a7-62429a489a99","resolution":{"observed_at":"2026-08-06T04:51:58.027116Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T04:51:49.766283Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2508.02978","last_updated":"2025-08-05T01:04:32Z","snapshot_observed_at":"2026-08-18T11:43:48.197239Z","submitted_at":"2025-08-05T01:04:32Z","title":"Separating Shared and Domain-Specific LoRAs for Multi-Domain Learning","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T04:51:49.766283Z"},"links":{"citing_paper":"/paper/2508.02978"},"observation_digest":"sha256:ff6e4d9025d7ccc7fd3e32c6e8a5c1e5ddc17cec6976328e7bb57990213c4c00","observation_id":"2ef26e3c-2d04-4b9c-946f-e92ea82887cb","resolution":{"observed_at":"2026-08-06T04:51:49.766283Z","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":"2026-08-06T04:51:57.700748Z","title":"Parameter-efficient transfer learning for NLP","venue":null,"work_id":"b497329d-9b56-49cc-8a00-cfb77803a4b1","year":null},"citing_paper":{"arxiv_id":"2508.02978","last_updated":"2025-08-05T01:04:32Z","snapshot_observed_at":"2026-08-18T11:43:48.197239Z","submitted_at":"2025-08-05T01:04:32Z","title":"Separating Shared and Domain-Specific LoRAs for Multi-Domain Learning","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T04:51:49.831718Z"},"links":{"citing_paper":"/paper/2508.02978"},"observation_digest":"sha256:2c310786a683572bc8a82797680f224ad3bfa7ff2d560f379195c178660a95c3","observation_id":"42a52814-50b2-448b-a98b-176f61922dff","resolution":{"observed_at":"2026-08-06T04:51:57.784891Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T04:51:57.501699Z","title":"LoRA: Low-rank adaptation of large language models","venue":null,"work_id":"c800d87d-fd08-49f7-9447-1f2dabac442b","year":2022},"citing_paper":{"arxiv_id":"2508.02978","last_updated":"2025-08-05T01:04:32Z","snapshot_observed_at":"2026-08-18T11:43:48.197239Z","submitted_at":"2025-08-05T01:04:32Z","title":"Separating Shared and Domain-Specific LoRAs for Multi-Domain Learning","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T04:51:49.935132Z"},"links":{"citing_paper":"/paper/2508.02978"},"observation_digest":"sha256:5d01a2265eb3f7899a0ed1c72c084b485369eb60a83ba9aece6fd8e03b01d17c","observation_id":"895a8b4f-1ea3-4c49-aa60-94fb9f8a5a69","resolution":{"observed_at":"2026-08-06T04:51:57.564498Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T04:51:57.352728Z","title":"Parameter-efficient Multi- task Fine-tuning for Transformers via Shared Hypernet- works","venue":null,"work_id":"f43ff248-94e0-40ee-be70-a9dca9c38faa","year":2021},"citing_paper":{"arxiv_id":"2508.02978","last_updated":"2025-08-05T01:04:32Z","snapshot_observed_at":"2026-08-18T11:43:48.197239Z","submitted_at":"2025-08-05T01:04:32Z","title":"Separating Shared and Domain-Specific LoRAs for Multi-Domain Learning","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T04:51:50.006612Z"},"links":{"citing_paper":"/paper/2508.02978"},"observation_digest":"sha256:1aa05b3f5f5326ccbf73e36baa3b3f9de680dcf04954958f888152613517e615","observation_id":"a4e7779d-091c-46cb-baa4-09578933de03","resolution":{"observed_at":"2026-08-06T04:51:57.445917Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1705.06950","last_updated":"2017-05-19T12:07:01Z","snapshot_observed_at":"2026-08-15T11:35:18.832923Z","submitted_at":"2017-05-19T12:07:01Z","title":"The Kinetics Human Action Video Dataset","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1705.06950","snapshot_observed_at":"2026-08-06T04:51:50.100456Z","title":"The kinetics human action video dataset","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2508.02978","last_updated":"2025-08-05T01:04:32Z","snapshot_observed_at":"2026-08-18T11:43:48.197239Z","submitted_at":"2025-08-05T01:04:32Z","title":"Separating Shared and Domain-Specific LoRAs for Multi-Domain Learning","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T04:51:50.100456Z"},"links":{"cited_paper":"/paper/1705.06950","citing_paper":"/paper/2508.02978"},"observation_digest":"sha256:d34e3e1081806a61cc1fcd00c388edf267ed668f46010c3bc5554b5b4b35a09b","observation_id":"3ebb7966-4a42-4007-8800-963357463d57","resolution":{"observed_at":"2026-08-06T04:51:50.100456Z","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":"2026-08-06T04:51:57.202996Z","title":"Human action recognition and predic- tion: A survey","venue":null,"work_id":"18a0d9a4-a36c-43dc-aab2-03658a0a937b","year":2022},"citing_paper":{"arxiv_id":"2508.02978","last_updated":"2025-08-05T01:04:32Z","snapshot_observed_at":"2026-08-18T11:43:48.197239Z","submitted_at":"2025-08-05T01:04:32Z","title":"Separating Shared and Domain-Specific LoRAs for Multi-Domain Learning","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T04:51:50.185018Z"},"links":{"citing_paper":"/paper/2508.02978"},"observation_digest":"sha256:b848938c4e6097c6923bf49ece7c81bcc5038059c9741f5dca485fcc89d1fdb4","observation_id":"0ae3f84d-04e8-4d82-b79e-cc87081436ee","resolution":{"observed_at":"2026-08-06T04:51:57.233032Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T04:51:57.017054Z","title":"Poggio, and Thomas Serre","venue":null,"work_id":"3a371a01-ceb9-4eab-8976-606c00e7fdc0","year":2011},"citing_paper":{"arxiv_id":"2508.02978","last_updated":"2025-08-05T01:04:32Z","snapshot_observed_at":"2026-08-18T11:43:48.197239Z","submitted_at":"2025-08-05T01:04:32Z","title":"Separating Shared and Domain-Specific LoRAs for Multi-Domain Learning","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T04:51:50.253605Z"},"links":{"citing_paper":"/paper/2508.02978"},"observation_digest":"sha256:30955464e1b68b335919d4499e134fb2bf9c53cfe049fb49d336b108d8a99c37","observation_id":"8e0b9f3c-f8d4-4b25-be0c-474751efeff9","resolution":{"observed_at":"2026-08-06T04:51:57.109339Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T04:51:56.841747Z","title":"Efficient multi-domain learning by covariance normalization","venue":null,"work_id":"a56d984e-708b-4966-bf0c-9dfd8e468440","year":2019},"citing_paper":{"arxiv_id":"2508.02978","last_updated":"2025-08-05T01:04:32Z","snapshot_observed_at":"2026-08-18T11:43:48.197239Z","submitted_at":"2025-08-05T01:04:32Z","title":"Separating Shared and Domain-Specific LoRAs for Multi-Domain Learning","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T04:51:50.330127Z"},"links":{"citing_paper":"/paper/2508.02978"},"observation_digest":"sha256:c34ab3e2ef0e16895402b28c5557418c6f3927b7f3738f02278160b7cdf1d930","observation_id":"06097439-4ca9-4ffe-bf06-13a7e55dc89b","resolution":{"observed_at":"2026-08-06T04:51:56.900828Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T04:51:56.660631Z","title":"REPAIR: Removing repre- sentation bias by dataset resampling","venue":null,"work_id":"b201beea-cc44-4128-b4d6-decc090b1ad4","year":2019},"citing_paper":{"arxiv_id":"2508.02978","last_updated":"2025-08-05T01:04:32Z","snapshot_observed_at":"2026-08-18T11:43:48.197239Z","submitted_at":"2025-08-05T01:04:32Z","title":"Separating Shared and Domain-Specific LoRAs for Multi-Domain Learning","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T04:51:50.408850Z"},"links":{"citing_paper":"/paper/2508.02978"},"observation_digest":"sha256:1bd09ef0b3cebef64ed94394282f79f9c9eedf951f1e0227a60e4de8e5aa9a34","observation_id":"d9527c21-a666-4ef5-a40c-5f7b3bf4d57e","resolution":{"observed_at":"2026-08-06T04:51:56.739057Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T04:51:56.477612Z","title":"RESOUND: To- wards Action Recognition Without Representation Bias","venue":null,"work_id":"f103fdd7-d9da-456b-b25a-9eba8058dcc6","year":2018},"citing_paper":{"arxiv_id":"2508.02978","last_updated":"2025-08-05T01:04:32Z","snapshot_observed_at":"2026-08-18T11:43:48.197239Z","submitted_at":"2025-08-05T01:04:32Z","title":"Separating Shared and Domain-Specific LoRAs for Multi-Domain Learning","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T04:51:50.465764Z"},"links":{"citing_paper":"/paper/2508.02978"},"observation_digest":"sha256:5a9f4731f7a979e0af962d961bdc8bb7a929fa2c033d27010d16c9bf3266df4b","observation_id":"d008149c-7eeb-4489-a60b-2b20039252de","resolution":{"observed_at":"2026-08-06T04:51:56.551926Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T04:51:56.316002Z","title":"Multi-dataset Training of Transformers for Robust Action Recognition","venue":null,"work_id":"00e08cc3-58cb-4701-9a75-76c059dc16bb","year":2022},"citing_paper":{"arxiv_id":"2508.02978","last_updated":"2025-08-05T01:04:32Z","snapshot_observed_at":"2026-08-18T11:43:48.197239Z","submitted_at":"2025-08-05T01:04:32Z","title":"Separating Shared and Domain-Specific LoRAs for Multi-Domain Learning","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T04:51:50.528346Z"},"links":{"citing_paper":"/paper/2508.02978"},"observation_digest":"sha256:91c4b5174cc9595df79da3e0bf183a56beeac9bc792eb9976e4788fe9537869f","observation_id":"72a628a0-c4e3-4115-94a5-9036d26ab035","resolution":{"observed_at":"2026-08-06T04:51:56.358225Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T04:51:56.130662Z","title":"PolyViT: Co-training vision transformers on images, videos and audio","venue":null,"work_id":"4f1cc23f-bf2a-4a2a-9aa7-ab62a8d3d678","year":null},"citing_paper":{"arxiv_id":"2508.02978","last_updated":"2025-08-05T01:04:32Z","snapshot_observed_at":"2026-08-18T11:43:48.197239Z","submitted_at":"2025-08-05T01:04:32Z","title":"Separating Shared and Domain-Specific LoRAs for Multi-Domain Learning","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T04:51:50.615485Z"},"links":{"citing_paper":"/paper/2508.02978"},"observation_digest":"sha256:c7877ce847727cbf770b209ab98d87a438c0e35e08d0fecd740fadda149185bd","observation_id":"17da5dcf-d249-4693-b3e8-36f54d58c123","resolution":{"observed_at":"2026-08-06T04:51:56.242711Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T04:51:55.967440Z","title":"Polyhistor: Parameter-Efficient Multi-Task Adaptation for Dense Vision Tasks","venue":null,"work_id":"4c10e2be-9329-4c35-b34e-78490d8985f7","year":2022},"citing_paper":{"arxiv_id":"2508.02978","last_updated":"2025-08-05T01:04:32Z","snapshot_observed_at":"2026-08-18T11:43:48.197239Z","submitted_at":"2025-08-05T01:04:32Z","title":"Separating Shared and Domain-Specific LoRAs for Multi-Domain Learning","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T04:51:50.676116Z"},"links":{"citing_paper":"/paper/2508.02978"},"observation_digest":"sha256:ffbb640625989c9afcd5fa102aeb5e92be02d9879e228e7991c6d2696b79c8f9","observation_id":"6ba998cd-0026-49be-bd4c-51ab5a185b57","resolution":{"observed_at":"2026-08-06T04:51:56.046671Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T04:51:55.794545Z","title":"Decoupled weight de- cay regularization","venue":null,"work_id":"02885fa3-6964-4603-bd46-d1d265fa9dd4","year":2019},"citing_paper":{"arxiv_id":"2508.02978","last_updated":"2025-08-05T01:04:32Z","snapshot_observed_at":"2026-08-18T11:43:48.197239Z","submitted_at":"2025-08-05T01:04:32Z","title":"Separating Shared and Domain-Specific LoRAs for Multi-Domain Learning","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T04:51:50.740068Z"},"links":{"citing_paper":"/paper/2508.02978"},"observation_digest":"sha256:db12d82b1e7517b2282c487c1adff6f5efe980013b7175c4c9f5f4f6663677d2","observation_id":"b3c93f7d-9cd9-48d6-af96-3dee9c373a4c","resolution":{"observed_at":"2026-08-06T04:51:55.856061Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T04:51:50.827693Z","title":"Learning transferable visual models from natural language supervision","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.02978","last_updated":"2025-08-05T01:04:32Z","snapshot_observed_at":"2026-08-18T11:43:48.197239Z","submitted_at":"2025-08-05T01:04:32Z","title":"Separating Shared and Domain-Specific LoRAs for Multi-Domain Learning","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T04:51:50.827693Z"},"links":{"citing_paper":"/paper/2508.02978"},"observation_digest":"sha256:49cb577051ab2f6649d9ad626986eb746f40fc7bf86188ec711a0fa5ff95fc7c","observation_id":"d7d4c076-73b3-4641-a8fd-5807771cc532","resolution":{"observed_at":"2026-08-06T04:51:50.827693Z","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":"2026-08-06T04:51:55.632624Z","title":"Learning multiple visual domains with residual adapters","venue":null,"work_id":"8cb4963a-a6f0-4e5e-8158-3c06fe7f607c","year":2017},"citing_paper":{"arxiv_id":"2508.02978","last_updated":"2025-08-05T01:04:32Z","snapshot_observed_at":"2026-08-18T11:43:48.197239Z","submitted_at":"2025-08-05T01:04:32Z","title":"Separating Shared and Domain-Specific LoRAs for Multi-Domain Learning","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T04:51:50.878857Z"},"links":{"citing_paper":"/paper/2508.02978"},"observation_digest":"sha256:57bccade88f51c52269024977d786b530267165edaecfd0a14ec7c9803e3de05","observation_id":"94ac5601-d187-4f77-a12f-d3a31c80969c","resolution":{"observed_at":"2026-08-06T04:51:55.714391Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T04:51:55.483587Z","title":"Efficient parametrization of multi-domain deep neural net- works","venue":null,"work_id":"c4498360-8b82-41f6-9b5c-20a0fbf7747b","year":2018},"citing_paper":{"arxiv_id":"2508.02978","last_updated":"2025-08-05T01:04:32Z","snapshot_observed_at":"2026-08-18T11:43:48.197239Z","submitted_at":"2025-08-05T01:04:32Z","title":"Separating Shared and Domain-Specific LoRAs for Multi-Domain Learning","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T04:51:50.973414Z"},"links":{"citing_paper":"/paper/2508.02978"},"observation_digest":"sha256:9c984e8bf87bc57432ff46936caa1c66ed9beeb5c7fcff46bbc1c54c79289905","observation_id":"2e7243bb-80a8-4033-b5fd-d59b7565e6c7","resolution":{"observed_at":"2026-08-06T04:51:55.556921Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T04:51:55.318390Z","title":"Imagenet-21k pretraining for the masses","venue":null,"work_id":"97c1e76b-883e-4ff2-8300-c01ae24430a6","year":2021},"citing_paper":{"arxiv_id":"2508.02978","last_updated":"2025-08-05T01:04:32Z","snapshot_observed_at":"2026-08-18T11:43:48.197239Z","submitted_at":"2025-08-05T01:04:32Z","title":"Separating Shared and Domain-Specific LoRAs for Multi-Domain Learning","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T04:51:51.044400Z"},"links":{"citing_paper":"/paper/2508.02978"},"observation_digest":"sha256:10dda649522d826300cb76cd0d965c3cd6994ccc4a40a6c6feee6ec6af68b95c","observation_id":"8ab3cbd3-ad19-4fac-b752-58a335a66251","resolution":{"observed_at":"2026-08-06T04:51:55.378224Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T04:51:51.085998Z","title":"High-resolution image synthesis with latent diffusion models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.02978","last_updated":"2025-08-05T01:04:32Z","snapshot_observed_at":"2026-08-18T11:43:48.197239Z","submitted_at":"2025-08-05T01:04:32Z","title":"Separating Shared and Domain-Specific LoRAs for Multi-Domain Learning","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T04:51:51.085998Z"},"links":{"citing_paper":"/paper/2508.02978"},"observation_digest":"sha256:4ce7719703cba88dde1c0a3226469665cce5906862ab23e5045ee7795cf11f00","observation_id":"fe3e0498-2857-4d05-9b32-edb9ee97b96c","resolution":{"observed_at":"2026-08-06T04:51:51.085998Z","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":"2026-08-06T04:51:55.161275Z","title":"Johansen, Sergio Escalera, Kamal Nasrollahi, Thomas B","venue":null,"work_id":"d021e3ec-7776-4b84-9441-13a317bd7a86","year":2023},"citing_paper":{"arxiv_id":"2508.02978","last_updated":"2025-08-05T01:04:32Z","snapshot_observed_at":"2026-08-18T11:43:48.197239Z","submitted_at":"2025-08-05T01:04:32Z","title":"Separating Shared and Domain-Specific LoRAs for Multi-Domain Learning","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T04:51:51.142881Z"},"links":{"citing_paper":"/paper/2508.02978"},"observation_digest":"sha256:6449212ae36e849c75d21ced8b10921bea81eccb2f541560454328deae15df52","observation_id":"72e6dfcd-95a1-44d2-8c8c-d93207434f06","resolution":{"observed_at":"2026-08-06T04:51:55.232187Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1212.0402","last_updated":"2012-12-03T14:45:31Z","snapshot_observed_at":"2026-08-16T21:21:44.768787Z","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":"2026-08-06T04:51:51.257729Z","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":"2508.02978","last_updated":"2025-08-05T01:04:32Z","snapshot_observed_at":"2026-08-18T11:43:48.197239Z","submitted_at":"2025-08-05T01:04:32Z","title":"Separating Shared and Domain-Specific LoRAs for Multi-Domain Learning","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T04:51:51.257729Z"},"links":{"cited_paper":"/paper/1212.0402","citing_paper":"/paper/2508.02978"},"observation_digest":"sha256:83d82572c929faf6ce530c935f3ea77faa193e988d659440148f6e7e3ef47955","observation_id":"c8d4f36d-4a32-44b0-99ea-282810f56188","resolution":{"observed_at":"2026-08-06T04:51:51.257729Z","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":"2026-08-06T04:51:54.944833Z","title":"VL-Adapter: Parameter-efficient transfer learning for vision-and-language tasks","venue":null,"work_id":"a0514372-125a-48d4-bd0f-3dc68d54b73a","year":2022},"citing_paper":{"arxiv_id":"2508.02978","last_updated":"2025-08-05T01:04:32Z","snapshot_observed_at":"2026-08-18T11:43:48.197239Z","submitted_at":"2025-08-05T01:04:32Z","title":"Separating Shared and Domain-Specific LoRAs for Multi-Domain Learning","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T04:51:51.321871Z"},"links":{"citing_paper":"/paper/2508.02978"},"observation_digest":"sha256:a6fb0c165cb02f1c9b193b32b8987e79552d3a6ccde91a13e73463c4228e7eeb","observation_id":"c8bcc86c-fea3-46e7-ab4d-2d4163821636","resolution":{"observed_at":"2026-08-06T04:51:55.075190Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T04:51:54.765975Z","title":null,"venue":null,"work_id":"6e00d645-da45-4cc5-9e32-6101c13c2092","year":2011},"citing_paper":{"arxiv_id":"2508.02978","last_updated":"2025-08-05T01:04:32Z","snapshot_observed_at":"2026-08-18T11:43:48.197239Z","submitted_at":"2025-08-05T01:04:32Z","title":"Separating Shared and Domain-Specific LoRAs for Multi-Domain Learning","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T04:51:51.409931Z"},"links":{"citing_paper":"/paper/2508.02978"},"observation_digest":"sha256:33ddf3f5b8e25e3381a90e7e90f97d85090a86b35c8535f93c9892d5a2996553","observation_id":"facd8571-3cd1-40d5-9d0d-90d5a828aa4c","resolution":{"observed_at":"2026-08-06T04:51:54.827666Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2209.05700","last_updated":"2022-09-13T02:57:05Z","snapshot_observed_at":"2026-08-19T17:19:41.877999Z","submitted_at":"2022-09-13T02:57:05Z","title":"Vision Transformers for Action Recognition: A Survey","version":1},"cited_work":{"arxiv_id":"2209.05700","doi":null,"metadata_source":"pith","pith_arxiv_id":"2209.05700","snapshot_observed_at":"2026-08-06T04:51:52.698618Z","title":"Vision Transformers for Action Recognition: A Survey","venue":"cs.CV","work_id":"5f6c5883-760e-4d1a-824b-5d37e23b82c5","year":2022},"citing_paper":{"arxiv_id":"2508.02978","last_updated":"2025-08-05T01:04:32Z","snapshot_observed_at":"2026-08-18T11:43:48.197239Z","submitted_at":"2025-08-05T01:04:32Z","title":"Separating Shared and Domain-Specific LoRAs for Multi-Domain Learning","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T04:51:51.487411Z"},"links":{"cited_paper":"/paper/2209.05700","citing_paper":"/paper/2508.02978"},"observation_digest":"sha256:b7bc3e44d8c1254e15f231d8bd8e0a4ed2033b1a7c42ace705d9b9d8dc8a30b1","observation_id":"bf98a876-2d0f-47ef-9c13-77dbf4196918","resolution":{"observed_at":"2026-08-06T04:51:52.766835Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T04:51:54.568974Z","title":"Multi-task learning for dense prediction tasks: A survey","venue":null,"work_id":"83d0c5bb-01fa-4cc5-8468-e10ac9e50eba","year":2022},"citing_paper":{"arxiv_id":"2508.02978","last_updated":"2025-08-05T01:04:32Z","snapshot_observed_at":"2026-08-18T11:43:48.197239Z","submitted_at":"2025-08-05T01:04:32Z","title":"Separating Shared and Domain-Specific LoRAs for Multi-Domain Learning","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T04:51:51.589714Z"},"links":{"citing_paper":"/paper/2508.02978"},"observation_digest":"sha256:3417e3f323d883dbf67892ce36db689cc2be8aaf1558c129e565cab5519f6190","observation_id":"f267c686-820a-4e38-9fe9-b328c82e9989","resolution":{"observed_at":"2026-08-06T04:51:54.682432Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T04:51:54.327927Z","title":"Interpretable image recognition by constructing transparent embedding space","venue":null,"work_id":"7b16f706-b1e9-4553-9663-8b49048f69f8","year":2021},"citing_paper":{"arxiv_id":"2508.02978","last_updated":"2025-08-05T01:04:32Z","snapshot_observed_at":"2026-08-18T11:43:48.197239Z","submitted_at":"2025-08-05T01:04:32Z","title":"Separating Shared and Domain-Specific LoRAs for Multi-Domain Learning","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T04:51:51.656423Z"},"links":{"citing_paper":"/paper/2508.02978"},"observation_digest":"sha256:0188c47d6ae7062a401e320ba97ee8ab21c31b6e895d01f8832d9d88309b5217","observation_id":"bd4d3c28-ac4f-4345-9ced-f163a46d39af","resolution":{"observed_at":"2026-08-06T04:51:54.438471Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T04:51:54.132549Z","title":"Mimetics: To- wards understanding human actions out of context","venue":null,"work_id":"f96a47d6-9dde-4c30-a74e-f37af89455a4","year":2021},"citing_paper":{"arxiv_id":"2508.02978","last_updated":"2025-08-05T01:04:32Z","snapshot_observed_at":"2026-08-18T11:43:48.197239Z","submitted_at":"2025-08-05T01:04:32Z","title":"Separating Shared and Domain-Specific LoRAs for Multi-Domain Learning","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T04:51:51.720308Z"},"links":{"citing_paper":"/paper/2508.02978"},"observation_digest":"sha256:bbda97b9c1fe379c4770feb5a27cb3332ba1f26c14986062905370789fa2aaa1","observation_id":"244523c9-a70a-41ec-b2d6-169024253c31","resolution":{"observed_at":"2026-08-06T04:51:54.260653Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.15116","last_updated":"2024-02-23T06:04:23Z","snapshot_observed_at":"2026-08-18T11:43:13.450548Z","submitted_at":"2024-02-23T06:04:23Z","title":"Large Multimodal Agents: A Survey","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.15116","snapshot_observed_at":"2026-08-06T04:51:51.808479Z","title":"Large multimodal agents: A survey","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.02978","last_updated":"2025-08-05T01:04:32Z","snapshot_observed_at":"2026-08-18T11:43:48.197239Z","submitted_at":"2025-08-05T01:04:32Z","title":"Separating Shared and Domain-Specific LoRAs for Multi-Domain Learning","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T04:51:51.808479Z"},"links":{"cited_paper":"/paper/2402.15116","citing_paper":"/paper/2508.02978"},"observation_digest":"sha256:8d1a72a84b0dff3c12d557edc15666f70ec641a13719cf0ed4a0ac3b607ada99","observation_id":"6c79fc6c-5692-48db-a413-ec83758c0a2a","resolution":{"observed_at":"2026-08-06T04:51:51.808479Z","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":"2026-08-06T04:51:53.962458Z","title":"VMT-Adapter: Parameter-Efficient Transfer Learning for Multi-Task Dense Scene Understanding","venue":null,"work_id":"7ccc86bb-1a65-438e-bc9b-0b7a2a889695","year":2024},"citing_paper":{"arxiv_id":"2508.02978","last_updated":"2025-08-05T01:04:32Z","snapshot_observed_at":"2026-08-18T11:43:48.197239Z","submitted_at":"2025-08-05T01:04:32Z","title":"Separating Shared and Domain-Specific LoRAs for Multi-Domain Learning","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T04:51:51.901369Z"},"links":{"citing_paper":"/paper/2508.02978"},"observation_digest":"sha256:7bc41266a4a7bc52892f38b2835e5009aee9a2e2480d36d22d1a6ebdd589aa78","observation_id":"9e1e3c63-9270-4f8e-879e-2b3ed80ca6cb","resolution":{"observed_at":"2026-08-06T04:51:54.031724Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T04:51:51.966116Z","title":"Parameter-efficient fine- tuning for pre-trained vision models: A survey","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.02978","last_updated":"2025-08-05T01:04:32Z","snapshot_observed_at":"2026-08-18T11:43:48.197239Z","submitted_at":"2025-08-05T01:04:32Z","title":"Separating Shared and Domain-Specific LoRAs for Multi-Domain Learning","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T04:51:51.966116Z"},"links":{"citing_paper":"/paper/2508.02978"},"observation_digest":"sha256:d53be72befa88d518254f2bfa00f37333b90292c50786171f167718f14c17f9d","observation_id":"6b503157-d550-402c-b0e0-b66ecc803d41","resolution":{"observed_at":"2026-08-06T04:51:51.966116Z","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":"2026-08-06T04:51:53.771469Z","title":"A survey of efficient fine- tuning methods for Vision-Language Models — Prompt and Adapter","venue":null,"work_id":"de67d796-9ae7-4fa6-8c7c-27998272990a","year":2024},"citing_paper":{"arxiv_id":"2508.02978","last_updated":"2025-08-05T01:04:32Z","snapshot_observed_at":"2026-08-18T11:43:48.197239Z","submitted_at":"2025-08-05T01:04:32Z","title":"Separating Shared and Domain-Specific LoRAs for Multi-Domain Learning","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T04:51:52.032857Z"},"links":{"citing_paper":"/paper/2508.02978"},"observation_digest":"sha256:b9822dfcecc9c2018647ec17bd34fda890eaeb071a54bb316055af7d70df057a","observation_id":"3296a260-b09c-41d7-a95e-2273c5a01e06","resolution":{"observed_at":"2026-08-06T04:51:53.837288Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T04:51:53.563914Z","title":null,"venue":null,"work_id":"3349ba0d-c6de-4296-b03a-9c7c56ffffeb","year":2023},"citing_paper":{"arxiv_id":"2508.02978","last_updated":"2025-08-05T01:04:32Z","snapshot_observed_at":"2026-08-18T11:43:48.197239Z","submitted_at":"2025-08-05T01:04:32Z","title":"Separating Shared and Domain-Specific LoRAs for Multi-Domain Learning","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T04:51:52.115718Z"},"links":{"citing_paper":"/paper/2508.02978"},"observation_digest":"sha256:580f2a85668d6bee8906b160472cb91d224f7052cc6b2b984af89c23514bb49f","observation_id":"171c0a52-60cd-43ed-80e4-ee69401f85c8","resolution":{"observed_at":"2026-08-06T04:51:53.642647Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T04:51:53.368297Z","title":"Tensors for Data Processing: Theory, Methods, and Applications","venue":null,"work_id":"f5859c00-f074-4a4e-911d-14841cb190b0","year":null},"citing_paper":{"arxiv_id":"2508.02978","last_updated":"2025-08-05T01:04:32Z","snapshot_observed_at":"2026-08-18T11:43:48.197239Z","submitted_at":"2025-08-05T01:04:32Z","title":"Separating Shared and Domain-Specific LoRAs for Multi-Domain Learning","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-06T04:51:52.203368Z"},"links":{"citing_paper":"/paper/2508.02978"},"observation_digest":"sha256:986808749a141f6faf23f57f15af1fc3cf1dc241978eb49cc5f96f81e5d8c6b5","observation_id":"a1056671-317b-48a9-a34a-efaa50c6c5d7","resolution":{"observed_at":"2026-08-06T04:51:53.450658Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T04:51:53.247204Z","title":"LLaMA-adapter: Efficient fine-tuning of large language models with zero- initialized attention","venue":null,"work_id":"3b7634ec-d730-4072-9090-472ac15d85dc","year":2024},"citing_paper":{"arxiv_id":"2508.02978","last_updated":"2025-08-05T01:04:32Z","snapshot_observed_at":"2026-08-18T11:43:48.197239Z","submitted_at":"2025-08-05T01:04:32Z","title":"Separating Shared and Domain-Specific LoRAs for Multi-Domain Learning","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-06T04:51:52.270271Z"},"links":{"citing_paper":"/paper/2508.02978"},"observation_digest":"sha256:5e775a0089ffbb1d1838cfa54fa340513cc5405e22a5ecc9d25fb502ef3999b9","observation_id":"f9af3a86-9f77-4fde-b079-e14932a7953f","resolution":{"observed_at":"2026-08-06T04:51:53.314893Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T04:51:53.086777Z","title":"A survey on multi-task learning","venue":null,"work_id":"8efe5e86-9c1b-427f-bd21-c9bbe952b548","year":2022},"citing_paper":{"arxiv_id":"2508.02978","last_updated":"2025-08-05T01:04:32Z","snapshot_observed_at":"2026-08-18T11:43:48.197239Z","submitted_at":"2025-08-05T01:04:32Z","title":"Separating Shared and Domain-Specific LoRAs for Multi-Domain Learning","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-06T04:51:52.311850Z"},"links":{"citing_paper":"/paper/2508.02978"},"observation_digest":"sha256:7096c5b6c34d8a73be1476aa5846870d0103b4556b20d2613179018e79996f16","observation_id":"65374403-ef63-4862-b601-21a777136b89","resolution":{"observed_at":"2026-08-06T04:51:53.172115Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-06T04:51:52.888062Z","title":"Sim- ple multi-dataset detection","venue":null,"work_id":"f468b636-dca5-4174-bf05-5f30417fd7c8","year":2022},"citing_paper":{"arxiv_id":"2508.02978","last_updated":"2025-08-05T01:04:32Z","snapshot_observed_at":"2026-08-18T11:43:48.197239Z","submitted_at":"2025-08-05T01:04:32Z","title":"Separating Shared and Domain-Specific LoRAs for Multi-Domain Learning","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-06T04:51:52.390069Z"},"links":{"citing_paper":"/paper/2508.02978"},"observation_digest":"sha256:b12b62005e4fd5014d0bb6583eba6663366031301e000eddfb01aeac4ab407b5","observation_id":"20890385-00f7-46fa-a2de-8973e4f1bf9c","resolution":{"observed_at":"2026-08-06T04:51:52.979007Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2508.02978","last_updated":"2025-08-05T01:04:32Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-18T11:43:48.197239Z","submitted_at":"2025-08-05T01:04:32Z","title":"Separating Shared and Domain-Specific LoRAs for Multi-Domain Learning"},"reference_resolution":{"displayed":43,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":10,"verified_exact":1,"verified_fuzzy":32},"total_outbound_references":43},"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":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"thesis":"As of 20 August 2026, this Paper Citation Record lists 43 of 43 outbound references and 0 inbound Pith citation observations for arXiv:2508.02978."}