{"as_of":"2026-08-22T00:01:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d27fd258c71df765365a8d42c9358281f9c1af2aa4369cb675143b5cb891c2d7","coverage":[{"denominator":81,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":81,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T17:59:15.852142Z","state":"measured"},{"denominator":82,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":82,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-21T06:32:19.484+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":"2026-08-06T21:07:43.908675Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-06T21:07:44.721535Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"cited_work":{"arxiv_id":"2412.08341","doi":null,"metadata_source":"pith","pith_arxiv_id":"2412.08341","snapshot_observed_at":"2026-08-06T21:07:44.721535Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","venue":"cs.CV","work_id":"c6f85d67-8ec0-4bfa-bf9c-6683c64b1a64","year":2024},"citing_paper":{"arxiv_id":"2507.00992","last_updated":"2025-07-02T04:08:46Z","snapshot_observed_at":"2026-08-14T13:40:26.950589Z","submitted_at":"2025-07-01T17:42:19Z","title":"UniGlyph: Unified Segmentation-Conditioned Diffusion for Precise Visual Text Synthesis","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T21:07:43.908675Z"},"links":{"cited_paper":"/paper/2412.08341","citing_paper":"/paper/2507.00992"},"observation_digest":"sha256:fd303df20cf38502881b282e7392e161e54125318d33e1df34e32925daf90627","observation_id":"519f8f0f-4074-489d-83ea-7cf3c4ee0af7","resolution":{"observed_at":"2026-08-06T21:07:44.729047Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2412.08341/citation-record","integrity":"/paper/2412.08341/integrity","json":"/paper/2412.08341/citation-record.json","paper":"/paper/2412.08341"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2012.13255","last_updated":"2020-12-22T07:42:30Z","snapshot_observed_at":"2026-08-18T15:17:24.628404Z","submitted_at":"2020-12-22T07:42:30Z","title":"Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2012.13255","snapshot_observed_at":"2026-08-11T17:59:15.452404Z","title":"In- trinsic dimensionality explains the effectiveness of language model fine-tuning","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.452404Z"},"links":{"cited_paper":"/paper/2012.13255","citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:f52514f43b591d48c251c99de844654c4ee91e4425bdd7563ca3a4e75fe018c3","observation_id":"6e664dac-3d25-4d43-9123-91ac1cf699f0","resolution":{"observed_at":"2026-08-11T17:59:15.452404Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1612.03801","last_updated":"2016-12-13T12:19:48Z","snapshot_observed_at":"2026-08-14T21:25:55.714417Z","submitted_at":"2016-12-12T17:32:49Z","title":"DeepMind Lab","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1612.03801","snapshot_observed_at":"2026-08-11T17:59:15.458254Z","title":"Deepmind lab","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.458254Z"},"links":{"cited_paper":"/paper/1612.03801","citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:236cac8f9a4b68e0f1e69eace685a7f517df6f0682feb7f9c3baeb7209862fc1","observation_id":"4ab27bef-0275-4cc8-a395-71fe2031dc29","resolution":{"observed_at":"2026-08-11T17:59:15.458254Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.07967","last_updated":"2023-10-16T15:52:20Z","snapshot_observed_at":"2026-08-16T20:00:55.703702Z","submitted_at":"2023-06-13T17:59:32Z","title":"One-for-All: Generalized LoRA for Parameter-Efficient Fine-tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.07967","snapshot_observed_at":"2026-08-11T17:59:15.463193Z","title":"One-for-all: Generalized lora for parameter- efficient fine-tuning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.463193Z"},"links":{"cited_paper":"/paper/2306.07967","citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:deee19f3d089c10fac2bbcb447fdeb69855684a0c315ec540f92f37ea5117ea1","observation_id":"11d51109-2b75-41e7-a8ef-1704610f2d22","resolution":{"observed_at":"2026-08-11T17:59:15.463193Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2208.07463","last_updated":"2024-04-12T04:48:48Z","snapshot_observed_at":"2026-08-16T16:39:02.351862Z","submitted_at":"2022-08-15T22:51:23Z","title":"Conv-Adapter: Exploring Parameter Efficient Transfer Learning for ConvNets","version":4},"cited_work":{"arxiv_id":"2208.07463","doi":null,"metadata_source":"pith","pith_arxiv_id":"2208.07463","snapshot_observed_at":"2026-08-11T17:59:16.255229Z","title":"Conv-Adapter: Exploring Parameter Efficient Transfer Learning for ConvNets","venue":"cs.CV","work_id":"79239f71-7532-4bc7-9b76-7fc713640299","year":2022},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.468112Z"},"links":{"cited_paper":"/paper/2208.07463","citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:4b6ac57409deb4bd0558df0f7c39d880ca7f746bdeb2df25d2659e126dfca89f","observation_id":"8695a79d-4cc9-479a-8809-3cae22053283","resolution":{"observed_at":"2026-08-11T17:59:16.260448Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T17:59:15.474026Z","title":"Adaptformer: Adapting vision transformers for scalable visual recogni- tion","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.474026Z"},"links":{"citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:ad5b82f2b631b5ba33c87af9c459d12865a749207c2dc6bc0c3e7d25e526468c","observation_id":"ff9cc4b0-121d-450c-99b3-87ac501de290","resolution":{"observed_at":"2026-08-11T17:59:15.474026Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.02057","last_updated":"2021-08-16T17:40:21Z","snapshot_observed_at":"2026-08-21T12:16:24.984776Z","submitted_at":"2021-04-05T17:59:40Z","title":"An Empirical Study of Training Self-Supervised Vision Transformers","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.02057","snapshot_observed_at":"2026-08-11T17:59:15.478948Z","title":"An empirical study of training self-supervised vision transformers","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.478948Z"},"links":{"cited_paper":"/paper/2104.02057","citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:4eb834f1cbe6dee3dff240b51806b19adef47afff7a39b3d8589cd4062c723e4","observation_id":"01b5b844-ef0d-4366-a92c-b6ccc0bd9ae4","resolution":{"observed_at":"2026-08-11T17:59:15.478948Z","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":"2026-08-11T17:59:17.154274Z","title":"Remote sens- ing image scene classification: Benchmark and state of the art","venue":null,"work_id":"3c0b3b6f-a9a8-44cb-8653-6474224293f2","year":2017},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.484375Z"},"links":{"citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:50c8406ff245c7b1983b5051e278a0f8f39cf5d95b2a9f0ebf3a4739f02d268b","observation_id":"fa848fcd-d12f-4b26-9d1f-af961ee1f832","resolution":{"observed_at":"2026-08-11T17:59:17.159327Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2010.12821","last_updated":"2020-10-24T07:43:00Z","snapshot_observed_at":"2026-08-20T18:20:08.121742Z","submitted_at":"2020-10-24T07:43:00Z","title":"Rethinking embedding coupling in pre-trained language models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.12821","snapshot_observed_at":"2026-08-11T17:59:15.489019Z","title":"Rethinking embedding coupling in pre-trained language models","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.489019Z"},"links":{"cited_paper":"/paper/2010.12821","citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:bfecfda6d51258f3dff4f2ebd640ec3ec64f345b29e8e1e5c53209fec6ec765a","observation_id":"4674ec86-2a96-4724-a196-c675d9eb021d","resolution":{"observed_at":"2026-08-11T17:59:15.489019Z","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":"2026-08-11T17:59:17.138898Z","title":"Describing textures in the wild","venue":null,"work_id":"2aca3ff5-4f26-44ec-b3f3-4dddf7729634","year":2014},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.493991Z"},"links":{"citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:34f9bfc83d573949fe31a22f2918df6900227aef9999df17ce8dc3358f105287","observation_id":"558d62d5-cd8c-407b-8aa8-f3f9509272f8","resolution":{"observed_at":"2026-08-11T17:59:17.143814Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T17:59:17.123174Z","title":"Imagenet: A large-scale hierarchical image database","venue":null,"work_id":"834c4df4-eab4-474a-a8ac-be78d2e4edbf","year":2009},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.498589Z"},"links":{"citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:75146408e258831cf36a8582e45156e02ab127cee749d68a4a0dab4bd1114fd6","observation_id":"1ca176f7-76ea-43ab-9d4f-b9a25b7d87ec","resolution":{"observed_at":"2026-08-11T17:59:17.128626Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T17:59:17.108408Z","title":"Acnet: Strengthening the kernel skeletons for powerful cnn via asymmetric convolution blocks","venue":null,"work_id":"cef2bf7c-0e4a-4ff0-8abd-634e7cfdc78a","year":1911},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.503500Z"},"links":{"citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:6e4bef920528e55850fa2b7d3f80358f4f9fafb5b6b9a6c39ce3f61b56160cde","observation_id":"eb4142b5-09cc-48f1-b005-3fa2070961ea","resolution":{"observed_at":"2026-08-11T17:59:17.113176Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2105.01883","last_updated":"2022-03-30T13:36:31Z","snapshot_observed_at":"2026-08-21T09:57:20.406010Z","submitted_at":"2021-05-05T06:17:40Z","title":"RepMLP: Re-parameterizing Convolutions into Fully-connected Layers for Image Recognition","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2105.01883","snapshot_observed_at":"2026-08-11T17:59:15.508228Z","title":"Repmlp: Re- parameterizing convolutions into fully-connected layers for image recognition","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.508228Z"},"links":{"cited_paper":"/paper/2105.01883","citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:73bbc7d9a2c187df2e85d8ac91dab89bcc21b2d567b3615a8bfa02c3fbdede62","observation_id":"35ba3834-4d92-4999-95d3-79ef9d627409","resolution":{"observed_at":"2026-08-11T17:59:15.508228Z","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":"2026-08-11T17:59:17.093460Z","title":"Diverse branch block: Building a convolution as an inception-like unit","venue":null,"work_id":"5657f985-78cd-4812-83c1-cbfbed6a7f99","year":2021},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.512919Z"},"links":{"citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:7dca8f03ed40add0afa86b9731502d1314fbf91888e52c48bf5f245072d05b27","observation_id":"4f6e395e-1087-43b8-afe2-da5abd71869d","resolution":{"observed_at":"2026-08-11T17:59:17.098266Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T17:59:17.078750Z","title":"Repvgg: Making vgg-style convnets great again","venue":null,"work_id":"c1575761-af8c-4b5e-b34f-994518e6c951","year":2021},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.517390Z"},"links":{"citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:d02238cb908c25a5509a10e593dd0fbae48aa987a58469c3890b2344635c3bfe","observation_id":"7ab871a2-94e1-41a3-82b1-1344cf608ad8","resolution":{"observed_at":"2026-08-11T17:59:17.083313Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T17:59:17.063277Z","title":"Repmlpnet: Hierarchical vi- sion mlp with re-parameterized locality","venue":null,"work_id":"e9e89b0c-4ed3-4678-a49d-eed9e8df7206","year":2022},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.521976Z"},"links":{"citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:a6526c843b5cee034d315c7f3935a8e5664e71d8627316e0d62a3805a374e7ec","observation_id":"675b65ad-5136-4be2-991b-1dcdeb8b2ff0","resolution":{"observed_at":"2026-08-11T17:59:17.068493Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T17:59:17.048191Z","title":"Effi- cient adaptation of large vision transformer via adapter re- composing","venue":null,"work_id":"8d49c5d3-1c42-4194-8aeb-d66a6879081f","year":2024},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.526545Z"},"links":{"citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:803df2597e8f6bf4c05780ffedf88b984c8f8a4cd36d7fe3e87ad0a8963550bf","observation_id":"ad89e490-c3f5-405c-87f6-853e43195c70","resolution":{"observed_at":"2026-08-11T17:59:17.053154Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T17:59:17.033876Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale","venue":null,"work_id":"0344046a-10e0-4981-bf78-76d134021ca8","year":2021},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.530986Z"},"links":{"citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:11878e04f5b8f25bf0331b44e328c30fd4b2090b0314d9a3a60c02ab3331a7ac","observation_id":"3c324e1d-8dc8-4458-b3d7-da118f6b3d01","resolution":{"observed_at":"2026-08-11T17:59:17.038377Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T17:59:17.018816Z","title":"One-shot learning of object categories","venue":null,"work_id":"ca8eec02-4319-46c5-a199-2fb5fd2dfba9","year":2006},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.535156Z"},"links":{"citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:e6807656b0c1ce3b58b21803c84a4bec0315ccbc9ce59997fcbeab51400692a4","observation_id":"981ece85-833b-4341-8346-14480bea05d7","resolution":{"observed_at":"2026-08-11T17:59:17.023787Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T17:59:17.001188Z","title":"Fine-grained car detection for visual census estimation","venue":null,"work_id":"d1a5c65e-99c2-4de8-a143-0d2148b960e3","year":2017},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.539668Z"},"links":{"citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:eb73f73cfaf3fd54f7c809859755e0a46a4c1e77c41cdc691f4557b7512be1da","observation_id":"097f144c-fb45-4c40-a3f7-5789ba68e68d","resolution":{"observed_at":"2026-08-11T17:59:17.007164Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T17:59:16.983699Z","title":"Vision meets robotics: The kitti dataset","venue":null,"work_id":"c290025f-1332-4bb9-a512-9df1ae21069a","year":2013},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.543960Z"},"links":{"citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:3c497d15d075e851c1a15ee8f28ff47106699c36cd74d24b3cf0017aa0962c9b","observation_id":"785d848b-4fe9-4910-9efc-49eea11483fc","resolution":{"observed_at":"2026-08-11T17:59:16.989134Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T17:59:16.967242Z","title":"Kaggle diabetic retinopathy detection compe- tition report","venue":null,"work_id":"1ce312b9-173f-4fbd-a244-e7732220200f","year":2015},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.548068Z"},"links":{"citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:8f7cc76b6269e79912070f4284858f5b1e3206656529b0ef25f062c2b2da5e15","observation_id":"39f290f0-d332-4d81-a4d3-eba53ddfea01","resolution":{"observed_at":"2026-08-11T17:59:16.972839Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T17:59:16.950028Z","title":"Deep residual learning for image recognition","venue":null,"work_id":"068ff2c6-c3a2-4a74-9ec0-38689a478a6e","year":2016},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.552124Z"},"links":{"citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:7d45708100b86d863d5cdd00b203dd37bb1d6fdde070836446a4dd8b519df23b","observation_id":"fffa2c1e-5235-46c9-85bf-ce8ce001bfdf","resolution":{"observed_at":"2026-08-11T17:59:16.954575Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T17:59:16.932836Z","title":"Momentum contrast for unsupervised visual rep- resentation learning","venue":null,"work_id":"ac71d0e4-f8f5-4e13-8251-5a3eb5f9ec14","year":2020},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.556298Z"},"links":{"citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:85af791c38250d145576ad23a021a9e4d166048e646c86daf57d43766d2e8ceb","observation_id":"91dd390f-1966-46f8-8d23-7d01826c15c7","resolution":{"observed_at":"2026-08-11T17:59:16.938113Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2111.06377","last_updated":"2021-12-19T19:23:25Z","snapshot_observed_at":"2026-08-17T17:58:26.288570Z","submitted_at":"2021-11-11T18:46:40Z","title":"Masked Autoencoders Are Scalable Vision Learners","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2111.06377","snapshot_observed_at":"2026-08-11T17:59:15.560502Z","title":"Masked autoencoders are scalable vision learners","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.560502Z"},"links":{"cited_paper":"/paper/2111.06377","citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:31889f5a85d990e4832aea55b70d245416bf63c8fa8f61a7e1767b99ca4c7f14","observation_id":"629d94f7-f354-4e11-bf27-4658d9cae41b","resolution":{"observed_at":"2026-08-11T17:59:15.560502Z","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":"2026-08-11T17:59:16.916698Z","title":"Eurosat: A novel dataset and deep learning benchmark for land use and land cover classification","venue":null,"work_id":"f595db47-e8a5-4b73-aa84-e4948dc2da04","year":2019},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.564913Z"},"links":{"citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:55e66090375653901f9be914fc880e2cb863a7460af1274975f83c8a65f01770","observation_id":"c0906478-be43-40b1-8152-db77536a4dc5","resolution":{"observed_at":"2026-08-11T17:59:16.921280Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T17:59:16.900956Z","title":"Compacter: Effi- cient low-rank hypercomplex adapter layers","venue":null,"work_id":"18dc44c6-c633-4f98-b965-5ce635ed6946","year":2021},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.569230Z"},"links":{"citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:4ea9e68f17c10d1364769e0565726ff58ac1eba5d5694bd96fa1f3ea0661d735","observation_id":"9e1951a7-67b8-47ae-bf5e-0a56ec830cd5","resolution":{"observed_at":"2026-08-11T17:59:16.905708Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T17:59:16.885549Z","title":"Parameter-efficient transfer learning for nlp","venue":null,"work_id":"db71b053-48a8-45e8-be64-5c4f34e7f73a","year":2019},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.573507Z"},"links":{"citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:6bee32b94b59d43713b7384ead8640b9bcc8668ec12b15bd29a4d4c9d37b51a3","observation_id":"b2a50d71-ff7e-4031-9769-dd8ad54003be","resolution":{"observed_at":"2026-08-11T17:59:16.890185Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2106.09685","last_updated":"2021-10-16T18:40:34Z","snapshot_observed_at":"2026-08-20T11:47:17.477107Z","submitted_at":"2021-06-17T17:37:18Z","title":"LoRA: Low-Rank Adaptation of Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.09685","snapshot_observed_at":"2026-08-11T17:59:15.577427Z","title":"Lora: Low-rank adaptation of large language models","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.577427Z"},"links":{"cited_paper":"/paper/2106.09685","citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:b048a01d554b5a7d7d5d796e00a48fdc1be64918a1ee3a0fcb423ead28588f3f","observation_id":"cd846ffe-7100-463d-9c94-0e1774b8638c","resolution":{"observed_at":"2026-08-11T17:59:15.577427Z","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":"2026-08-11T17:59:16.869126Z","title":"Visual prompt tuning","venue":null,"work_id":"02ce30e4-90cd-4878-acd4-44d8c935c94d","year":2022},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.581751Z"},"links":{"citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:775b1785d0846a0ec498f30233c97562dd525302b30195f3d020a8e309850331","observation_id":"1ce50cc2-7327-4816-9b1a-2a5dd2d167dc","resolution":{"observed_at":"2026-08-11T17:59:16.874208Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T17:59:16.852350Z","title":"Res- tuning: A flexible and efficient tuning paradigm via unbind- ing tuner from backbone","venue":null,"work_id":"01777634-e53e-4a88-b387-800ac31f606b","year":2023},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.585738Z"},"links":{"citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:632cbf05ebaa153fd9ad0f6568c28962a76b384aae6652d0df22c08f9df0feb7","observation_id":"56e9a360-373a-4544-b0cf-0a7cd82e8214","resolution":{"observed_at":"2026-08-11T17:59:16.858026Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2207.07039","last_updated":"2022-08-09T10:40:06Z","snapshot_observed_at":"2026-08-18T23:56:57.045777Z","submitted_at":"2022-07-14T16:32:28Z","title":"Convolutional Bypasses Are Better Vision Transformer Adapters","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2207.07039","snapshot_observed_at":"2026-08-11T17:59:15.590307Z","title":"Convolutional bypasses are better vision transformer adapters","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.590307Z"},"links":{"cited_paper":"/paper/2207.07039","citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:1f4435a5a681562a51879fbeb240a9fecbe279713fbda895ce59ea0803d53af6","observation_id":"dca5d446-25ce-42b7-b254-e312ea94abd1","resolution":{"observed_at":"2026-08-11T17:59:15.590307Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:59:15.595423Z","title":"Clevr: A diagnostic dataset for compositional language and elementary visual reasoning","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.595423Z"},"links":{"citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:5e43e7d835d9f2f1a6350e525f72c1ce58a7afa973096aeada9a71fd2548b682","observation_id":"edee4438-64f9-4fa3-9325-455635dd74dc","resolution":{"observed_at":"2026-08-11T17:59:15.595423Z","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":"2026-08-11T17:59:16.823264Z","title":"Novel dataset for fine-grained image categorization: Stanford dogs","venue":null,"work_id":"b9e61169-6eb8-4a16-ab95-51288d9d7a37","year":2011},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.600004Z"},"links":{"citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:5550e80f472ae0faa4e1019a3f95d0c31a86e5297c48b9a30924933143480a97","observation_id":"c305a098-a490-4dc6-8c10-6272e5c3f5b2","resolution":{"observed_at":"2026-08-11T17:59:16.829081Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T17:59:16.806020Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":"9bd3ec3a-74e7-42d8-b0d8-36946fe10c1a","year":2009},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.604942Z"},"links":{"citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:d79e40201df1273372208a7080dcf3e8184bb39b73038d76bc97a546d7ae4e68","observation_id":"9b018d63-f997-4b0c-9b12-b1000b877a7c","resolution":{"observed_at":"2026-08-11T17:59:16.811708Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T17:59:16.789683Z","title":"Hmdb: a large video database for human motion recognition","venue":null,"work_id":"0d1c333a-9f87-4a77-ba84-95917b147f23","year":2011},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.610350Z"},"links":{"citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:ed1fcf0d89268e335c87a359cc8bb0c58f9d5e21682d929baea1dcbb14e8bf99","observation_id":"dcda7cfe-f371-49a5-b84a-61aa930375d5","resolution":{"observed_at":"2026-08-11T17:59:16.794939Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T17:59:16.773441Z","title":"Learn- ing methods for generic object recognition with invari- ance to pose and lighting","venue":null,"work_id":"382e9611-2113-4e39-a2e3-b403d5f8b447","year":2004},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.615374Z"},"links":{"citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:957064e281e2908ffd85cd95b9b9990adbebdd14f0ecce1fb4c27b9bb88355e3","observation_id":"28d2e093-4074-4398-9bb2-2634b127a29e","resolution":{"observed_at":"2026-08-11T17:59:16.778600Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T17:59:16.757663Z","title":"The power of scale for parameter-efficient prompt tuning","venue":null,"work_id":"7b938d95-7ebe-4046-b281-da8997fadf79","year":2021},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.621158Z"},"links":{"citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:2df8c28e90fccc99f127867a2c571901ab92111e46827db8fc4200fb6e5a8826","observation_id":"089a532c-a6cc-4226-a200-54c1c9be91c6","resolution":{"observed_at":"2026-08-11T17:59:16.762637Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1804.08838","last_updated":"2018-04-24T04:29:10Z","snapshot_observed_at":"2026-08-14T19:22:43.852228Z","submitted_at":"2018-04-24T04:29:10Z","title":"Measuring the Intrinsic Dimension of Objective Landscapes","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1804.08838","snapshot_observed_at":"2026-08-11T17:59:15.626951Z","title":"Measuring the intrinsic dimension of objective landscapes","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.626951Z"},"links":{"cited_paper":"/paper/1804.08838","citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:545c877fbc20ab32d877674d1afc44c1880b785916522a566d7532758a9525c0","observation_id":"5540cee6-56d0-42c8-b50c-9aa278579d43","resolution":{"observed_at":"2026-08-11T17:59:15.626951Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2101.00190","last_updated":"2021-01-01T08:00:36Z","snapshot_observed_at":"2026-08-21T16:24:51.670091Z","submitted_at":"2021-01-01T08:00:36Z","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2101.00190","snapshot_observed_at":"2026-08-11T17:59:15.633496Z","title":"Prefix-tuning: Optimiz- ing continuous prompts for generation","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.633496Z"},"links":{"cited_paper":"/paper/2101.00190","citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:d817bff4be0375c1425c63e3a1dd711bb32aef7cb8c6d14889462ef330944a0a","observation_id":"a1e3b14a-56ea-45ba-b50e-1fd31922f71a","resolution":{"observed_at":"2026-08-11T17:59:15.633496Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2107.08391","last_updated":"2022-03-17T06:59:03Z","snapshot_observed_at":"2026-08-16T18:09:18.638258Z","submitted_at":"2021-07-18T08:56:34Z","title":"AS-MLP: An Axial Shifted MLP Architecture for Vision","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2107.08391","snapshot_observed_at":"2026-08-11T17:59:15.639436Z","title":"As- mlp: An axial shifted mlp architecture for vision","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.639436Z"},"links":{"cited_paper":"/paper/2107.08391","citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:b8c72de25713ab183749059565d3cd169ebed73c06c2cc1497c66dc55473998c","observation_id":"11c2351d-9ce3-4fda-bb57-0878e70f518c","resolution":{"observed_at":"2026-08-11T17:59:15.639436Z","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":"2026-08-11T17:59:16.740132Z","title":"Scaling & shifting your features: A new baseline for efficient model tuning","venue":null,"work_id":"55d4056e-c09c-4e1c-9ddf-5e6378843a66","year":2022},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.645326Z"},"links":{"citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:91cda6d60eecbff5338004dd9716dbdba9a75328f4657ed3b23c730d7d982c44","observation_id":"c06139de-90f4-42f4-82e5-025025e385b9","resolution":{"observed_at":"2026-08-11T17:59:16.745992Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T17:59:16.723998Z","title":"Pre-train, prompt, and predict: A systematic survey of prompting methods in nat- ural language processing","venue":null,"work_id":"5ed968e0-c3a7-4e6c-b152-9145a4358805","year":2023},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.651049Z"},"links":{"citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:2c5d259f09c1ebeb0b975c378dea0e01d815fa2bdabb4d0119739bd1c2cd602d","observation_id":"8bc0ee52-6236-47b3-9b7e-e333dbd55a01","resolution":{"observed_at":"2026-08-11T17:59:16.728699Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T17:59:16.709240Z","title":"Swin transformer: Hierarchical vision transformer using shifted windows","venue":null,"work_id":"5a5548e6-818c-4590-ae8b-decca65c8223","year":2021},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.656944Z"},"links":{"citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:a280ed955e33916751bd0b14081e8252945c16e91dae81fc877a954ca209ecf1","observation_id":"173c2418-9c9e-47d2-9dc2-2a3656ee7c77","resolution":{"observed_at":"2026-08-11T17:59:16.713825Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T17:59:16.693348Z","title":"Swin transformer v2: Scaling up capacity and resolution","venue":null,"work_id":"56d03573-930b-4e4f-9d74-0b43cf85b0ca","year":2022},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.662171Z"},"links":{"citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:f610998c1131bdbb5e2ff95ee21af2e03d171d57fb00251d7b915441ddb0735d","observation_id":"e2ed28a8-192b-4121-8137-a5b3141d7215","resolution":{"observed_at":"2026-08-11T17:59:16.698248Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T17:59:16.676967Z","title":"A convnet for the 2020s","venue":null,"work_id":"4c2c43f3-24a8-4287-89d5-2bbcc531402f","year":2022},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.667266Z"},"links":{"citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:06db4ab6391baa4fade69fbd92d0c967db1c869501ab6e545b25774dc824e6ae","observation_id":"27d89c97-2674-42e4-903c-ebf13fe348fd","resolution":{"observed_at":"2026-08-11T17:59:16.682241Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T17:59:16.656143Z","title":"Decoupled weight decay regularization","venue":null,"work_id":"4f579d9a-7fbd-43cf-8783-bdfe9af56b11","year":2017},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.672282Z"},"links":{"citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:c849c5edfd8915c30420ea81b9d0048a0a98714d13000143c2cea59e46389c69","observation_id":"92c34ea8-61aa-4a58-8506-8d323df1c812","resolution":{"observed_at":"2026-08-11T17:59:16.661065Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2302.08106","last_updated":"2023-03-21T02:51:27Z","snapshot_observed_at":"2026-08-16T15:54:58.333296Z","submitted_at":"2023-02-16T06:14:15Z","title":"Towards Efficient Visual Adaption via Structural Re-parameterization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.08106","snapshot_observed_at":"2026-08-11T17:59:15.677554Z","title":"Towards efficient visual adaption via structural re-parameterization","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.677554Z"},"links":{"cited_paper":"/paper/2302.08106","citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:1e9af7ecfc8736b139cdd32fab7a43567dea6f9f605eb8ab0fba123a21885901","observation_id":"f11b0a61-66ec-42c9-a0e9-2e384c08b83d","resolution":{"observed_at":"2026-08-11T17:59:15.677554Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:59:15.683092Z","title":"dsprites: Disentanglement testing sprites dataset,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.683092Z"},"links":{"citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:81f50b651dae87c4d5533aef657639730cbdf2c6432563a6f081eb3e357237b7","observation_id":"f2e5bf39-01d1-4c65-a717-e1e56b9c9b85","resolution":{"observed_at":"2026-08-11T17:59:15.683092Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.02887","last_updated":"2024-02-05T10:55:47Z","snapshot_observed_at":"2026-08-20T05:42:11.673960Z","submitted_at":"2024-02-05T10:55:47Z","title":"Time-, Memory- and Parameter-Efficient Visual Adaptation","version":1},"cited_work":{"arxiv_id":"2402.02887","doi":null,"metadata_source":"pith","pith_arxiv_id":"2402.02887","snapshot_observed_at":"2026-08-11T17:59:16.078101Z","title":"Time-, Memory- and Parameter-Efficient Visual Adaptation","venue":"cs.CV","work_id":"182fe92f-d7cd-4067-bb27-645b27df6ef8","year":2024},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.688744Z"},"links":{"cited_paper":"/paper/2402.02887","citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:d6d7b1bb221f0a96cea290c48d164f06f348659bc82b90b7794e8484028079f6","observation_id":"6ab37b4a-d64a-4f46-8be5-86794d2e1110","resolution":{"observed_at":"2026-08-11T17:59:16.083395Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T17:59:16.629474Z","title":"Reading digits in natural images with unsupervised feature learning","venue":null,"work_id":"b98f51f1-11ce-4f3f-8ea1-c8981145d101","year":2011},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.693418Z"},"links":{"citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:40a902681ed702707fe131047dcd58083e4834681a34923f2da79941c3fa201f","observation_id":"2370cfd7-d674-4b77-8127-7f393d9f4d08","resolution":{"observed_at":"2026-08-11T17:59:16.634615Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T17:59:16.613801Z","title":"Automated flower classification over a large number of classes","venue":null,"work_id":"0ffef0aa-9eb2-4edf-92ec-36c143420065","year":2008},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.697867Z"},"links":{"citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:63ff991c2ac500ddc3e9247edb81914cab865df73869e1d85bdcee86392fa24f","observation_id":"328ddb23-d0e5-4e25-95aa-926cf69b95e8","resolution":{"observed_at":"2026-08-11T17:59:16.619546Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T17:59:16.596544Z","title":"Automated flower classification over a large number of classes","venue":null,"work_id":"6f121b9a-5381-4ca3-85dc-b75b8224befb","year":2008},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.702489Z"},"links":{"citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:8bfb8740759a48d7ddbe824bdf0c5bedd8e15c9c79ab2bfd05b18450ec5c9fb3","observation_id":"0dcf479b-5272-4b42-8d55-29ec0ccc2f83","resolution":{"observed_at":"2026-08-11T17:59:16.602790Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T17:59:16.577201Z","title":"Cats and dogs","venue":null,"work_id":"a1d6137f-f006-44c5-8693-6d0e23de16c2","year":2012},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.707281Z"},"links":{"citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:0d87c104f9b0c80786a728dae7a9cf222f053cece1a998c8b9a62ab1cc73a7de","observation_id":"3152d619-2bd9-4fc9-9379-6ae70365ad70","resolution":{"observed_at":"2026-08-11T17:59:16.582833Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2005.00247","last_updated":"2021-01-26T12:54:33Z","snapshot_observed_at":"2026-08-18T15:11:44.299970Z","submitted_at":"2020-05-01T07:03:42Z","title":"AdapterFusion: Non-Destructive Task Composition for Transfer Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.00247","snapshot_observed_at":"2026-08-11T17:59:15.712516Z","title":"Adapterfusion: Non- destructive task composition for transfer learning","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.712516Z"},"links":{"cited_paper":"/paper/2005.00247","citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:eacc84a12155ab1a7dd63414d07bd7685d4e93aaa2bd2a9256640a9712d0df09","observation_id":"ff68636d-6fb2-45a3-80b1-fc5b1a783508","resolution":{"observed_at":"2026-08-11T17:59:15.712516Z","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":"2026-08-11T17:59:16.559862Z","title":"Imagenet-21k pretraining for the masses","venue":null,"work_id":"a7492ec0-0c3f-47f4-8d5b-fc6cd6e4ccd3","year":2021},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.718066Z"},"links":{"citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:8bafbe13611dec90a3fe145554f241a14abffd7ba4e516ee90c6c1b94e2c65ef","observation_id":"1c868861-0965-4e30-8623-ec6f0bbc37a0","resolution":{"observed_at":"2026-08-11T17:59:16.565296Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2010.11918","last_updated":"2021-10-05T18:37:04Z","snapshot_observed_at":"2026-08-20T10:43:54.102245Z","submitted_at":"2020-10-22T17:49:42Z","title":"AdapterDrop: On the Efficiency of Adapters in Transformers","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.11918","snapshot_observed_at":"2026-08-11T17:59:15.722924Z","title":"Adapterdrop: On the efficiency of adapters in transformers","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.722924Z"},"links":{"cited_paper":"/paper/2010.11918","citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:69836ed199e517f10364318c72ffd09fb68ec5c5ca0d3eb6da0396e4c32965e2","observation_id":"e335093f-77eb-4729-b13e-aa0affd30345","resolution":{"observed_at":"2026-08-11T17:59:15.722924Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.15980","last_updated":"2020-11-07T05:33:35Z","snapshot_observed_at":"2026-08-16T19:09:26.533311Z","submitted_at":"2020-10-29T22:54:00Z","title":"AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.15980","snapshot_observed_at":"2026-08-11T17:59:15.729243Z","title":"Autoprompt: Eliciting knowl- edge from language models with automatically generated prompts","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.729243Z"},"links":{"cited_paper":"/paper/2010.15980","citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:601d0a20dc5579bd7306a764e9c69edd76de78435c58f267e9eac7da56c76721","observation_id":"15a8362b-d8f4-4a12-be1f-c68d25e5b21e","resolution":{"observed_at":"2026-08-11T17:59:15.729243Z","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":"2026-08-11T17:59:16.543224Z","title":"Dropout: a simple way to prevent neural networks from overfitting","venue":null,"work_id":"1e555bf0-bf44-423e-9db9-48451699dd7c","year":1929},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.734672Z"},"links":{"citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:a9d6fad93d3f9048b98290a183facc7e7c0050bb82e58404d8e36aad9b0811c7","observation_id":"f7da9432-2148-49c6-8aa6-00cc97308899","resolution":{"observed_at":"2026-08-11T17:59:16.548462Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T17:59:16.526153Z","title":"Lst: Lad- der side-tuning for parameter and memory efficient trans- fer learning","venue":null,"work_id":"c0b18682-bec0-40e1-a6b7-a7de5ed77151","year":2022},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.739975Z"},"links":{"citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:a075eb1e01d5d9346b8219a4c6ff27b85d96f30fb3319ad5140d813c99822492","observation_id":"99949a2a-8f3c-4ff1-9f0b-063b247416ed","resolution":{"observed_at":"2026-08-11T17:59:16.532049Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2105.01601","last_updated":"2021-06-11T09:36:50Z","snapshot_observed_at":"2026-08-20T13:50:07.095032Z","submitted_at":"2021-05-04T16:17:21Z","title":"MLP-Mixer: An all-MLP Architecture for Vision","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2105.01601","snapshot_observed_at":"2026-08-11T17:59:15.744703Z","title":"Mlp-mixer: An all-mlp architecture for vision","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.744703Z"},"links":{"cited_paper":"/paper/2105.01601","citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:1236b6de4f31dfef2ba281ec8c2d53178367199349aa08b85f7b8e9d86a4e71b","observation_id":"cefcc746-cada-43a7-b3c0-6257b017d033","resolution":{"observed_at":"2026-08-11T17:59:15.744703Z","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":"2026-08-11T17:59:16.509203Z","title":"Videomae: Masked autoencoders are data-efficient learners for self-supervised video pre-training","venue":null,"work_id":"cf5f628d-cf6c-4caa-bb10-dc36f17221f4","year":2022},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.750655Z"},"links":{"citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:ecb4f3309131e57949f533d3e6868056d55256ae121a020d579c1032238d05af","observation_id":"889f3bcf-f342-48be-9d90-57807271e37c","resolution":{"observed_at":"2026-08-11T17:59:16.514211Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T17:59:16.493964Z","title":"Training data-efficient image transformers & distillation through at- tention","venue":null,"work_id":"10907b3b-f3b6-4b10-bffb-0845ffdf2f72","year":2021},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.755564Z"},"links":{"citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:12db60a8847718ed34574eada14d69fd426e9959f8aacb0ac1d540dd33756b58","observation_id":"76f1448f-605d-459f-ae9e-c1e31ba34d3b","resolution":{"observed_at":"2026-08-11T17:59:16.498861Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T17:59:15.760583Z","title":"Visualizing data using t-sne","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.760583Z"},"links":{"citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:5411a3245950454ceb47b73e5c0a85aa8dcf5492ba8505302045776a3e2f7aa1","observation_id":"43e537e2-ebda-4948-bef8-293db35c33e5","resolution":{"observed_at":"2026-08-11T17:59:15.760583Z","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":"2026-08-11T17:59:16.467930Z","title":"Building a bird recognition app and large scale dataset with citizen scientists: The fine print in fine-grained dataset collection","venue":null,"work_id":"42bf8526-1a38-4167-b7c0-0fbfdfb69cd6","year":null},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.765672Z"},"links":{"citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:482b20d697247c49dc0b9d3fb90162720d0439d8698de6d89a1fa271457ce1ce","observation_id":"4a0118cb-c0d2-4cb4-9350-276caf613e95","resolution":{"observed_at":"2026-08-11T17:59:16.472940Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T17:59:15.771496Z","title":"Attention is all you need","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.771496Z"},"links":{"citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:0f4d289b96ce3aef77123100932ca5325d3a7fe76d3bb38389cfbd8ef4c59bc7","observation_id":"000ab995-e4ef-4df4-8a83-2e2d045abdd1","resolution":{"observed_at":"2026-08-11T17:59:15.771496Z","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":"2026-08-11T17:59:16.441959Z","title":"Rotation equivariant cnns for digital pathology","venue":null,"work_id":"422ceb3c-a62b-48b5-8f40-5fe87e691e10","year":2018},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.776845Z"},"links":{"citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:b18fc5c578339cf12ef42726531e40c90f955409a05acb3b4e8e2a221d607c34","observation_id":"47ed83b1-3b04-4fcd-bd2d-36ecee1bc630","resolution":{"observed_at":"2026-08-11T17:59:16.446982Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T17:59:16.426213Z","title":"The caltech-ucsd birds-200-2011 dataset","venue":null,"work_id":"141ba90f-9785-42fb-b0e8-ce8b1c22743b","year":2011},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.782995Z"},"links":{"citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:51db1c53587de90ca7d4b2e87eb2e63d9038a74473b82e61675c57fc7202f598","observation_id":"c2536ddd-2fc8-4ea5-ac68-a1b8f2c18447","resolution":{"observed_at":"2026-08-11T17:59:16.430868Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2002.06715","last_updated":"2020-02-20T03:38:44Z","snapshot_observed_at":"2026-08-20T06:13:33.239348Z","submitted_at":"2020-02-17T00:00:59Z","title":"BatchEnsemble: An Alternative Approach to Efficient Ensemble and Lifelong Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.06715","snapshot_observed_at":"2026-08-11T17:59:15.788752Z","title":"Batchensemble: an alternative approach to efficient ensemble and lifelong learning","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.788752Z"},"links":{"cited_paper":"/paper/2002.06715","citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:c6332ec4454c11181402e727c67b250886bffbeea3802ffebf55da720fa06381","observation_id":"a718869f-de8b-4fd1-8d24-d73faf318fda","resolution":{"observed_at":"2026-08-11T17:59:15.788752Z","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":"2026-08-11T17:59:16.411158Z","title":"Sun database: Large-scale scene recognition from abbey to zoo","venue":null,"work_id":"ab765d21-be6c-4fb6-9b9a-9ac08a9b5013","year":2010},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.794267Z"},"links":{"citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:ba5459aac7d0935e1e29c33e30120406af1454dc6b288e864524907b32f3d4d6","observation_id":"34e65d68-8fe8-495f-9e8c-8dbdf7d1f22a","resolution":{"observed_at":"2026-08-11T17:59:16.416019Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2311.15010","last_updated":"2023-11-30T14:57:30Z","snapshot_observed_at":"2026-08-19T05:29:36.545750Z","submitted_at":"2023-11-25T12:33:54Z","title":"Adapter is All You Need for Tuning Visual Tasks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.15010","snapshot_observed_at":"2026-08-11T17:59:15.799186Z","title":"Adapter is all you need for tuning visual tasks","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.799186Z"},"links":{"cited_paper":"/paper/2311.15010","citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:76f09770e5d5ef5583e241b9f9f505926d12436bf8dec9402113facb6ba929ec","observation_id":"7c0dc4b0-6d1f-4d42-8c5a-9ed45d5b9ba3","resolution":{"observed_at":"2026-08-11T17:59:15.799186Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1706.00388","last_updated":"2018-01-26T14:08:57Z","snapshot_observed_at":"2026-08-14T20:56:39.203017Z","submitted_at":"2017-06-01T17:02:11Z","title":"DiracNets: Training Very Deep Neural Networks Without Skip-Connections","version":2},"cited_work":{"arxiv_id":"1706.00388","doi":null,"metadata_source":"pith","pith_arxiv_id":"1706.00388","snapshot_observed_at":"2026-08-11T17:59:15.957669Z","title":"DiracNets: Training Very Deep Neural Networks Without Skip-Connections","venue":"cs.CV","work_id":"9b20c787-a604-4e58-b3e2-b02515e8169a","year":2017},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.804132Z"},"links":{"cited_paper":"/paper/1706.00388","citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:fb4fbbef222584938a45130316ab065a76f3868095ab7f499f7e84e6ebe252cf","observation_id":"bb3d538e-c251-454b-af49-738e671a6a7a","resolution":{"observed_at":"2026-08-11T17:59:15.965201Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T17:59:16.395806Z","title":"Bitfit: Simple parameter-efficient fine-tuning for transformer-based masked language-models","venue":null,"work_id":"b26fc7a8-dcb7-4b95-82b8-388524c8b036","year":2022},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.809337Z"},"links":{"citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:0939c3ed85d2cd13ec26599cd35f1d479ae55b87874f29a2b19bcc3ff1c6a60e","observation_id":"c617ce40-28db-4237-867b-dd659f60de5d","resolution":{"observed_at":"2026-08-11T17:59:16.400701Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1910.04867","last_updated":"2020-02-21T13:36:15Z","snapshot_observed_at":"2026-08-09T06:48:42.729935Z","submitted_at":"2019-10-01T17:06:29Z","title":"A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.04867","snapshot_observed_at":"2026-08-11T17:59:15.814734Z","title":"A large-scale study of representation learning with the visual task adaptation benchmark","venue":null,"work_id":null,"year":1910},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.814734Z"},"links":{"cited_paper":"/paper/1910.04867","citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:093335d2f3c118765bee2343368abb6f885952ce87c815dc9bf2ba7fe08475a2","observation_id":"27e5cf9f-baf2-4982-9166-ada862c9a230","resolution":{"observed_at":"2026-08-11T17:59:15.814734Z","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":"2026-08-11T17:59:16.380234Z","title":"Scaling vision transformers","venue":null,"work_id":"a4fae661-563c-4342-8f82-82b1576764a4","year":2022},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.819843Z"},"links":{"citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:01706097f2894718d7258210c93c70a2d1d6bb8d45c0d7dd0e1ac684590bead9","observation_id":"b65c9371-e074-463c-a4a4-cef492c7a8b4","resolution":{"observed_at":"2026-08-11T17:59:16.385007Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2102.08597","last_updated":"2021-02-17T06:16:58Z","snapshot_observed_at":"2026-08-16T18:45:01.445829Z","submitted_at":"2021-02-17T06:16:58Z","title":"Beyond Fully-Connected Layers with Quaternions: Parameterization of Hypercomplex Multiplications with $1/n$ Parameters","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2102.08597","snapshot_observed_at":"2026-08-11T17:59:15.824792Z","title":"Beyond fully-connected layers with quaternions: Parameterization of hypercom- plex multiplications with 1/n parameters","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.824792Z"},"links":{"cited_paper":"/paper/2102.08597","citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:14d1d1678c5b945b4381a4814ae9e9fa64d4bca4ec15797c94c3af1b2b7d7db9","observation_id":"fa9b415d-773c-4cb5-a481-f7312189e689","resolution":{"observed_at":"2026-08-11T17:59:15.824792Z","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":"2026-08-11T17:59:16.364150Z","title":"Adaptive budget allocation for parameter-efficient fine- tuning","venue":null,"work_id":"67358b66-b754-4421-9521-87b9ad8022d0","year":2023},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.829961Z"},"links":{"citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:9b864b4de8e929fea9a911d85a726ad31528b0b0ba0b5d96bc83429cb4dd319e","observation_id":"ba1d6aa7-ac52-433d-bfa1-f55e1fae399d","resolution":{"observed_at":"2026-08-11T17:59:16.369514Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2006.05987","last_updated":"2021-03-11T17:22:50Z","snapshot_observed_at":"2026-08-13T22:28:03.255826Z","submitted_at":"2020-06-10T17:57:03Z","title":"Revisiting Few-sample BERT Fine-tuning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.05987","snapshot_observed_at":"2026-08-11T17:59:15.834049Z","title":"Revisiting few-sample bert fine- tuning","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.834049Z"},"links":{"cited_paper":"/paper/2006.05987","citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:67c89ecf85deae3ddebdf95136255bafb2ff1c713d6f0435fdd55561f37197ca","observation_id":"f618d415-bf43-4314-b509-6ae59ad03f79","resolution":{"observed_at":"2026-08-11T17:59:15.834049Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04673","last_updated":"2022-06-14T12:15:55Z","snapshot_observed_at":"2026-08-18T15:12:07.105904Z","submitted_at":"2022-06-09T17:59:58Z","title":"Neural Prompt Search","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.04673","snapshot_observed_at":"2026-08-11T17:59:15.838420Z","title":"Neural prompt search","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.838420Z"},"links":{"cited_paper":"/paper/2206.04673","citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:3593945351ef2325828f22eb80195ab995eea536421723f6fc507aa994db0819","observation_id":"bd4a546c-da8d-4595-ac13-31dd01c16cb8","resolution":{"observed_at":"2026-08-11T17:59:15.838420Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T17:59:15.843109Z","title":"Rethinking semantic segmen- tation from a sequence-to-sequence perspective with trans- formers","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.843109Z"},"links":{"citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:6a952a6546125c81e1bb4f81a6e92f4e14f20d53a17e52797582390d5abcd5ab","observation_id":"a0e7e1c8-6bd5-4491-9385-69aa0f90c83a","resolution":{"observed_at":"2026-08-11T17:59:15.843109Z","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":"2026-08-11T17:59:16.338618Z","title":"Convolution meets lora: Parameter efficient finetuning for segment anything model","venue":null,"work_id":"b7168bdf-698e-405b-a4bf-346d324ea86e","year":2024},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.847846Z"},"links":{"citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:32be28ae80bc50d8df2eba8899a70b3357777e3c551aff61389a7d5e030f094a","observation_id":"76c82519-e998-464c-9fb2-1bc60c1d0a59","resolution":{"observed_at":"2026-08-11T17:59:16.343793Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T17:59:16.322205Z","title":"Group Mean","venue":null,"work_id":"4f82c0e0-aec0-4fcd-b6c5-b6e1c3619f0d","year":2019},"citing_paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-11T17:59:15.852142Z"},"links":{"citing_paper":"/paper/2412.08341"},"observation_digest":"sha256:49fde536de08565747a3930a5247bfe7cdfd32eaa8c9b0743d4d591e71d29190","observation_id":"437da8bf-e347-4ec2-b726-0c4e75bcd7dc","resolution":{"observed_at":"2026-08-11T17:59:16.327052Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2412.08341","last_updated":"2024-12-11T12:31:30Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-17T10:57:42.676537Z","submitted_at":"2024-12-11T12:31:30Z","title":"ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts"},"reference_resolution":{"displayed":81,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":29,"verified_exact":3,"verified_fuzzy":48},"total_outbound_references":81},"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":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"thesis":"As of 22 August 2026, this Paper Citation Record lists 81 of 81 outbound references and 1 inbound Pith citation observation for arXiv:2412.08341."}