{"as_of":"2026-08-10T06:08:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:59b7374bf7278282b53a69ce42a3cf7d98588e051f9887c90e0aee91a964797d","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":40,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":40,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":40,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":40,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-09T17:23:25.342323Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-04T00:49:19.216124Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2203.17274","last_updated":"2022-06-03T17:52:04Z","snapshot_observed_at":"2026-07-06T12:55:27.843060Z","submitted_at":"2022-03-31T17:59:30Z","title":"Exploring Visual Prompts for Adapting Large-Scale Models","version":2},"cited_work":{"arxiv_id":"2203.17274","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2203.17274","snapshot_observed_at":"2026-07-04T00:49:19.216124Z","title":"Visual prompting: Modifying pixel space to adapt pre-trained models","venue":null,"work_id":"da285965-ebf5-410b-beaf-17ba49e67f3d","year":2022},"citing_paper":{"arxiv_id":"2402.07927","last_updated":"2025-03-16T06:23:34Z","snapshot_observed_at":"2026-08-05T17:55:26.008016Z","submitted_at":"2024-02-05T19:49:13Z","title":"A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-12T21:52:09.938550Z"},"links":{"cited_paper":"/paper/2203.17274","citing_paper":"/paper/2402.07927"},"observation_digest":"sha256:e0f6af7cb85adc1eed36b95623e9c1c171fd905d6f3aab0602a91ee59493faee","observation_id":"755e325f-8756-4f26-80a1-c00a64f254ca","resolution":{"observed_at":"2026-05-12T21:52:10.367192Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2203.17274","last_updated":"2022-06-03T17:52:04Z","snapshot_observed_at":"2026-07-06T12:55:27.843060Z","submitted_at":"2022-03-31T17:59:30Z","title":"Exploring Visual Prompts for Adapting Large-Scale Models","version":2},"cited_work":{"arxiv_id":"2203.17274","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2203.17274","snapshot_observed_at":"2026-07-04T00:49:19.216124Z","title":"Visual prompting: Modifying pixel space to adapt pre-trained models","venue":null,"work_id":"da285965-ebf5-410b-beaf-17ba49e67f3d","year":2022},"citing_paper":{"arxiv_id":"2402.10380","last_updated":"2024-02-16T00:25:24Z","snapshot_observed_at":"2026-07-06T17:30:56.216307Z","submitted_at":"2024-02-16T00:25:24Z","title":"Subgraph-level Universal Prompt Tuning","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-24T03:37:59.957481Z"},"links":{"cited_paper":"/paper/2203.17274","citing_paper":"/paper/2402.10380"},"observation_digest":"sha256:a721df97d76a6c9977cbbc3ba0002c2fdc4d5fe8deffb14e03bd694bbf0d0ad3","observation_id":"22f8bcea-76f0-4749-9573-44fb78f5fbc3","resolution":{"observed_at":"2026-05-24T03:38:50.032879Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2203.17274","last_updated":"2022-06-03T17:52:04Z","snapshot_observed_at":"2026-07-06T12:55:27.843060Z","submitted_at":"2022-03-31T17:59:30Z","title":"Exploring Visual Prompts for Adapting Large-Scale Models","version":2},"cited_work":{"arxiv_id":"2203.17274","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2203.17274","snapshot_observed_at":"2026-07-04T00:49:19.216124Z","title":"Visual prompting: Modifying pixel space to adapt pre-trained models","venue":null,"work_id":"da285965-ebf5-410b-beaf-17ba49e67f3d","year":2022},"citing_paper":{"arxiv_id":"2407.17491","last_updated":"2026-04-03T23:10:26Z","snapshot_observed_at":"2026-08-02T18:34:18.562354Z","submitted_at":"2024-07-04T02:35:00Z","title":"Robust Adaptation of Foundation Models with Black-Box Visual Prompting","version":4},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-23T23:23:03.562550Z"},"links":{"cited_paper":"/paper/2203.17274","citing_paper":"/paper/2407.17491"},"observation_digest":"sha256:d01376d8a2c21775d40fcd48bdae976ca5d04fde50c6d6af3e0ac7fd7dfafddc","observation_id":"fcea3cc7-99b8-40a1-b527-79e7f7f54ad0","resolution":{"observed_at":"2026-05-23T23:23:36.348169Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2203.17274","last_updated":"2022-06-03T17:52:04Z","snapshot_observed_at":"2026-07-06T12:55:27.843060Z","submitted_at":"2022-03-31T17:59:30Z","title":"Exploring Visual Prompts for Adapting Large-Scale Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.17274","snapshot_observed_at":"2026-08-09T17:23:25.342323Z","title":"Exploring visual prompts for adapting large-scale models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.00896","last_updated":"2025-04-12T02:16:47Z","snapshot_observed_at":"2026-08-09T17:15:51.791206Z","submitted_at":"2025-02-02T20:10:48Z","title":"LoR-VP: Low-Rank Visual Prompting for Efficient Vision Model Adaptation","version":3},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-09T17:23:25.342323Z"},"links":{"cited_paper":"/paper/2203.17274","citing_paper":"/paper/2502.00896"},"observation_digest":"sha256:e9a3abd93995a9819d143fe59fa0d302543f433067fcd6dbff2b66f94a694a67","observation_id":"509017f4-7d0c-47fd-8829-f6d09806e771","resolution":{"observed_at":"2026-08-09T17:23:25.342323Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.17274","last_updated":"2022-06-03T17:52:04Z","snapshot_observed_at":"2026-07-06T12:55:27.843060Z","submitted_at":"2022-03-31T17:59:30Z","title":"Exploring Visual Prompts for Adapting Large-Scale Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.17274","snapshot_observed_at":"2026-08-08T13:30:03.452514Z","title":"Exploring visual prompts for adapting large-scale models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.07231","last_updated":"2025-02-11T03:46:35Z","snapshot_observed_at":"2026-08-08T13:22:19.556282Z","submitted_at":"2025-02-11T03:46:35Z","title":"Revisiting the Auxiliary Data in Backdoor Purification","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-08T13:30:03.452514Z"},"links":{"cited_paper":"/paper/2203.17274","citing_paper":"/paper/2502.07231"},"observation_digest":"sha256:c4332d8a226344def90685837b82eb1b41568e90bd376c2d4e9f7b54944bbb22","observation_id":"daa4f87e-5307-4586-b804-5939b38108c3","resolution":{"observed_at":"2026-08-08T13:30:03.452514Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.17274","last_updated":"2022-06-03T17:52:04Z","snapshot_observed_at":"2026-07-06T12:55:27.843060Z","submitted_at":"2022-03-31T17:59:30Z","title":"Exploring Visual Prompts for Adapting Large-Scale Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.17274","snapshot_observed_at":"2026-08-07T15:27:21.565626Z","title":"Exploring visual prompts for adapting large- scale models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.15123","last_updated":"2025-08-24T14:40:35Z","snapshot_observed_at":"2026-08-09T16:58:46.218963Z","submitted_at":"2025-05-21T05:16:45Z","title":"Seeing the Trees for the Forest: Rethinking Weakly-Supervised Medical Visual Grounding","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T15:27:21.565626Z"},"links":{"cited_paper":"/paper/2203.17274","citing_paper":"/paper/2505.15123"},"observation_digest":"sha256:5ee5e580fff0aa3dcec4308aff23328892858cd32f2002a68483738ec8a9c00a","observation_id":"a3177020-49a8-40e6-b885-eefd51385243","resolution":{"observed_at":"2026-08-07T15:27:21.565626Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.17274","last_updated":"2022-06-03T17:52:04Z","snapshot_observed_at":"2026-07-06T12:55:27.843060Z","submitted_at":"2022-03-31T17:59:30Z","title":"Exploring Visual Prompts for Adapting Large-Scale Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.17274","snapshot_observed_at":"2026-08-07T14:29:37.658386Z","title":"Exploring visual prompts for adapting large-scale models,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.18770","last_updated":"2025-05-24T16:20:06Z","snapshot_observed_at":"2026-08-07T14:23:43.806027Z","submitted_at":"2025-05-24T16:20:06Z","title":"Dual-Path Stable Soft Prompt Generation for Domain Generalization","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-07T14:29:37.658386Z"},"links":{"cited_paper":"/paper/2203.17274","citing_paper":"/paper/2505.18770"},"observation_digest":"sha256:b94c694f37bec9135acdbb674668e9ed6c172c69b7b7f2b25cf22b02a630f661","observation_id":"b2f9bdee-b5ef-488f-a24b-645e8e0715c4","resolution":{"observed_at":"2026-08-07T14:29:37.658386Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.17274","last_updated":"2022-06-03T17:52:04Z","snapshot_observed_at":"2026-07-06T12:55:27.843060Z","submitted_at":"2022-03-31T17:59:30Z","title":"Exploring Visual Prompts for Adapting Large-Scale Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.17274","snapshot_observed_at":"2026-08-07T13:58:03.278749Z","title":"Exploring visual prompts for adapting large- scale models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.20513","last_updated":"2025-05-26T20:26:16Z","snapshot_observed_at":"2026-08-07T13:50:45.184432Z","submitted_at":"2025-05-26T20:26:16Z","title":"MetaWriter: Personalized Handwritten Text Recognition Using Meta-Learned Prompt Tuning","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T13:58:03.278749Z"},"links":{"cited_paper":"/paper/2203.17274","citing_paper":"/paper/2505.20513"},"observation_digest":"sha256:df66b49837ffe23f0fbd803bc98d6e4ec5530fc41abf2bab6c3c762888aa752e","observation_id":"f41d087e-c57c-4113-99e1-ae1913b0af76","resolution":{"observed_at":"2026-08-07T13:58:03.278749Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.17274","last_updated":"2022-06-03T17:52:04Z","snapshot_observed_at":"2026-07-06T12:55:27.843060Z","submitted_at":"2022-03-31T17:59:30Z","title":"Exploring Visual Prompts for Adapting Large-Scale Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.17274","snapshot_observed_at":"2026-08-07T12:09:48.866213Z","title":"Bahng, A","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.00620","last_updated":"2025-05-31T16:15:04Z","snapshot_observed_at":"2026-08-09T10:56:18.617995Z","submitted_at":"2025-05-31T16:15:04Z","title":"Model Reprogramming Demystified: A Neural Tangent Kernel Perspective","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-07T12:09:48.866213Z"},"links":{"cited_paper":"/paper/2203.17274","citing_paper":"/paper/2506.00620"},"observation_digest":"sha256:942ef971175de630830ef503d907a700cc0c53647485c6526dfa5685ceded75c","observation_id":"ef5adab9-0979-4da1-a0f1-c8cbb3a616de","resolution":{"observed_at":"2026-08-07T12:09:48.866213Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.17274","last_updated":"2022-06-03T17:52:04Z","snapshot_observed_at":"2026-07-06T12:55:27.843060Z","submitted_at":"2022-03-31T17:59:30Z","title":"Exploring Visual Prompts for Adapting Large-Scale Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.17274","snapshot_observed_at":"2026-08-07T05:52:38.655882Z","title":"Exploring visual prompts for adapting large-scale models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.06823","last_updated":"2025-06-07T14:56:32Z","snapshot_observed_at":"2026-08-08T14:52:29.864984Z","submitted_at":"2025-06-07T14:56:32Z","title":"Exploring Visual Prompting: Robustness Inheritance and Beyond","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-07T05:52:38.655882Z"},"links":{"cited_paper":"/paper/2203.17274","citing_paper":"/paper/2506.06823"},"observation_digest":"sha256:0a4ef3a1c9e0dc50ee543682b821894f7e50cd6959762f03e1707e2eba5524ff","observation_id":"0a91bcad-9e1b-4a6a-8e5e-861009a9bf32","resolution":{"observed_at":"2026-08-07T05:52:38.655882Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.17274","last_updated":"2022-06-03T17:52:04Z","snapshot_observed_at":"2026-07-06T12:55:27.843060Z","submitted_at":"2022-03-31T17:59:30Z","title":"Exploring Visual Prompts for Adapting Large-Scale Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.17274","snapshot_observed_at":"2026-08-07T05:40:28.964278Z","title":"Exploring visual prompts for adapting large-scale models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.07484","last_updated":"2025-06-09T07:04:47Z","snapshot_observed_at":"2026-08-07T05:30:08.010657Z","submitted_at":"2025-06-09T07:04:47Z","title":"CoCoA-Mix: Confusion-and-Confidence-Aware Mixture Model for Context Optimization","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-07T05:40:28.964278Z"},"links":{"cited_paper":"/paper/2203.17274","citing_paper":"/paper/2506.07484"},"observation_digest":"sha256:734ffa35da7c44e09ac8e09711775f94210385b823e220985d078797213f65d7","observation_id":"355dc0b5-766f-4a70-8abe-601b140d994b","resolution":{"observed_at":"2026-08-07T05:40:28.964278Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.17274","last_updated":"2022-06-03T17:52:04Z","snapshot_observed_at":"2026-07-06T12:55:27.843060Z","submitted_at":"2022-03-31T17:59:30Z","title":"Exploring Visual Prompts for Adapting Large-Scale Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.17274","snapshot_observed_at":"2026-08-07T00:14:15.210742Z","title":"Bahng, A","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.14727","last_updated":"2025-07-04T20:27:52Z","snapshot_observed_at":"2026-08-08T23:40:41.478391Z","submitted_at":"2025-06-17T17:06:43Z","title":"Casper: Inferring Diverse Intents for Assistive Teleoperation with Vision Language Models","version":2},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-07T00:14:15.210742Z"},"links":{"cited_paper":"/paper/2203.17274","citing_paper":"/paper/2506.14727"},"observation_digest":"sha256:e1f47893cfdb13bb4b291b6bdad7a37fe86eccc38e100b1469c6c084de99e207","observation_id":"f059a6d5-a6e6-4e84-a65e-8b9f95e79385","resolution":{"observed_at":"2026-08-07T00:14:15.210742Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.17274","last_updated":"2022-06-03T17:52:04Z","snapshot_observed_at":"2026-07-06T12:55:27.843060Z","submitted_at":"2022-03-31T17:59:30Z","title":"Exploring Visual Prompts for Adapting Large-Scale Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.17274","snapshot_observed_at":"2026-08-06T23:20:44.918777Z","title":"Ex- ploring visual prompts for adapting large-scale models,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.18504","last_updated":"2025-06-30T05:24:22Z","snapshot_observed_at":"2026-08-08T10:23:10.135024Z","submitted_at":"2025-06-23T10:56:37Z","title":"Generalizing vision-language models to novel domains: A comprehensive survey","version":2},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-06T23:20:44.918777Z"},"links":{"cited_paper":"/paper/2203.17274","citing_paper":"/paper/2506.18504"},"observation_digest":"sha256:d084ae21ca6629cabbeb7195ac8c02359135a0cc3a417b0b9a8317c7e314eb54","observation_id":"4201aed3-822e-4e97-8a35-cf388bf94315","resolution":{"observed_at":"2026-08-06T23:20:44.918777Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.17274","last_updated":"2022-06-03T17:52:04Z","snapshot_observed_at":"2026-07-06T12:55:27.843060Z","submitted_at":"2022-03-31T17:59:30Z","title":"Exploring Visual Prompts for Adapting Large-Scale Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.17274","snapshot_observed_at":"2026-08-06T21:37:03.071096Z","title":"Exploring visual prompts for adapting large- scale models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.23785","last_updated":"2025-06-30T12:27:35Z","snapshot_observed_at":"2026-08-06T23:32:11.173462Z","submitted_at":"2025-06-30T12:27:35Z","title":"Visual Textualization for Image Prompted Object Detection","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T21:37:03.071096Z"},"links":{"cited_paper":"/paper/2203.17274","citing_paper":"/paper/2506.23785"},"observation_digest":"sha256:1106a81374ec2c346f1e2d3e761bd9efe9e2ed6debb3cb78b607c0f34da3b838","observation_id":"a8a31ae4-53dd-4930-936c-bc8d7851bbba","resolution":{"observed_at":"2026-08-06T21:37:03.071096Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.17274","last_updated":"2022-06-03T17:52:04Z","snapshot_observed_at":"2026-07-06T12:55:27.843060Z","submitted_at":"2022-03-31T17:59:30Z","title":"Exploring Visual Prompts for Adapting Large-Scale Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.17274","snapshot_observed_at":"2026-08-06T18:37:35.090755Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.07796","last_updated":"2025-07-10T14:23:15Z","snapshot_observed_at":"2026-08-07T20:53:46.671274Z","submitted_at":"2025-07-10T14:23:15Z","title":"Visual Instance-aware Prompt Tuning","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T18:37:35.090755Z"},"links":{"cited_paper":"/paper/2203.17274","citing_paper":"/paper/2507.07796"},"observation_digest":"sha256:41d1bdab118a3310280cd0b70f15ab2eac6198ff4067ee06c95434eb56001a6f","observation_id":"f44d106a-f5ca-47ae-bd2e-9146376fb124","resolution":{"observed_at":"2026-08-06T18:37:35.090755Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.17274","last_updated":"2022-06-03T17:52:04Z","snapshot_observed_at":"2026-07-06T12:55:27.843060Z","submitted_at":"2022-03-31T17:59:30Z","title":"Exploring Visual Prompts for Adapting Large-Scale Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.17274","snapshot_observed_at":"2026-08-06T15:34:44.361412Z","title":"Exploring visual prompts for adapting large- scale models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.15569","last_updated":"2025-07-21T12:50:49Z","snapshot_observed_at":"2026-08-09T12:39:27.106704Z","submitted_at":"2025-07-21T12:50:49Z","title":"DynImg: Key Frames with Visual Prompts are Good Representation for Multi-Modal Video Understanding","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T15:34:44.361412Z"},"links":{"cited_paper":"/paper/2203.17274","citing_paper":"/paper/2507.15569"},"observation_digest":"sha256:0b68092a1d15c0a4bfb66f2bf0a2280e9b11be8b014b232191553061a1bcb0c8","observation_id":"a810cc3f-b520-4e8b-837c-051629199850","resolution":{"observed_at":"2026-08-06T15:34:44.361412Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.17274","last_updated":"2022-06-03T17:52:04Z","snapshot_observed_at":"2026-07-06T12:55:27.843060Z","submitted_at":"2022-03-31T17:59:30Z","title":"Exploring Visual Prompts for Adapting Large-Scale Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.17274","snapshot_observed_at":"2026-08-06T14:44:24.547505Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.18243","last_updated":"2025-07-24T09:32:53Z","snapshot_observed_at":"2026-08-10T00:46:08.190244Z","submitted_at":"2025-07-24T09:32:53Z","title":"DepthDark: Robust Monocular Depth Estimation for Low-Light Environments","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T14:44:24.547505Z"},"links":{"cited_paper":"/paper/2203.17274","citing_paper":"/paper/2507.18243"},"observation_digest":"sha256:0586e88f1ce908d858784534b0db2445ffb46826e804cd76ec050d70ada03f48","observation_id":"d48289a5-6a7c-46c4-803c-462a4ce5110f","resolution":{"observed_at":"2026-08-06T14:44:24.547505Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.17274","last_updated":"2022-06-03T17:52:04Z","snapshot_observed_at":"2026-07-06T12:55:27.843060Z","submitted_at":"2022-03-31T17:59:30Z","title":"Exploring Visual Prompts for Adapting Large-Scale Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.17274","snapshot_observed_at":"2026-08-06T12:42:01.672805Z","title":"Visual prompting: Modifying pixel space to adapt pre-trained models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.21588","last_updated":"2025-07-29T08:42:36Z","snapshot_observed_at":"2026-08-09T10:08:56.325837Z","submitted_at":"2025-07-29T08:42:36Z","title":"Progressive Homeostatic and Plastic Prompt Tuning for Audio-Visual Multi-Task Incremental Learning","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T12:42:01.672805Z"},"links":{"cited_paper":"/paper/2203.17274","citing_paper":"/paper/2507.21588"},"observation_digest":"sha256:e091f0da2a77116c357d74b283085c3eccd6c0150f1437c29e0cacb48929a59e","observation_id":"535c30e0-6bf9-4295-9d97-e9e7b4d222eb","resolution":{"observed_at":"2026-08-06T12:42:01.672805Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.17274","last_updated":"2022-06-03T17:52:04Z","snapshot_observed_at":"2026-07-06T12:55:27.843060Z","submitted_at":"2022-03-31T17:59:30Z","title":"Exploring Visual Prompts for Adapting Large-Scale Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.17274","snapshot_observed_at":"2026-08-06T05:32:05.603281Z","title":"Explor- ing visual prompts for adapting large-scale models,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.01584","last_updated":"2025-08-03T04:38:50Z","snapshot_observed_at":"2026-08-09T22:07:30.119807Z","submitted_at":"2025-08-03T04:38:50Z","title":"Twistronics and moir\\'e superlattice physics in 2D transition metal dichalcogenides","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-06T05:32:05.603281Z"},"links":{"cited_paper":"/paper/2203.17274","citing_paper":"/paper/2508.01584"},"observation_digest":"sha256:0cbffc874678776fc465e603b2c8819b448104c910e15f8a8ea6455e79fa0ece","observation_id":"94857fbf-9c66-4aef-9382-bfa295a1ce11","resolution":{"observed_at":"2026-08-06T05:32:05.603281Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.17274","last_updated":"2022-06-03T17:52:04Z","snapshot_observed_at":"2026-07-06T12:55:27.843060Z","submitted_at":"2022-03-31T17:59:30Z","title":"Exploring Visual Prompts for Adapting Large-Scale Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.17274","snapshot_observed_at":"2026-08-05T21:01:26.913858Z","title":"Exploring visual prompts for adapting large- scale models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.10065","last_updated":"2025-08-13T08:05:47Z","snapshot_observed_at":"2026-08-08T04:37:03.833237Z","submitted_at":"2025-08-13T08:05:47Z","title":"Invisible Watermarks, Visible Gains: Steering Machine Unlearning with Bi-Level Watermarking Design","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-05T21:01:26.913858Z"},"links":{"cited_paper":"/paper/2203.17274","citing_paper":"/paper/2508.10065"},"observation_digest":"sha256:5d404949dc34cfe77b166acb410a4570d98cbeba0906e1dd89d6bd31a4543bb8","observation_id":"7148a55f-e9ee-4945-82d2-a17bde025b00","resolution":{"observed_at":"2026-08-05T21:01:26.913858Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.17274","last_updated":"2022-06-03T17:52:04Z","snapshot_observed_at":"2026-07-06T12:55:27.843060Z","submitted_at":"2022-03-31T17:59:30Z","title":"Exploring Visual Prompts for Adapting Large-Scale Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.17274","snapshot_observed_at":"2026-08-05T18:45:08.262623Z","title":"Bahng, A","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.14191","last_updated":"2025-08-19T18:33:03Z","snapshot_observed_at":"2026-08-07T10:36:41.020025Z","submitted_at":"2025-08-19T18:33:03Z","title":"Polarization-Resolved Chlorophyll Imaging for Non-Invasive Plant Tissue Assessment Using a Silicon-Rich Nitride Metalens Array","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-05T18:45:08.262623Z"},"links":{"cited_paper":"/paper/2203.17274","citing_paper":"/paper/2508.14191"},"observation_digest":"sha256:3c4773c58aa1f0b3da9f71efdada709532c2a8e9c5bc1a925b0abf106d1f71d4","observation_id":"d6ee39eb-6a72-406f-b9a7-db5ef07de65b","resolution":{"observed_at":"2026-08-05T18:45:08.262623Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.17274","last_updated":"2022-06-03T17:52:04Z","snapshot_observed_at":"2026-07-06T12:55:27.843060Z","submitted_at":"2022-03-31T17:59:30Z","title":"Exploring Visual Prompts for Adapting Large-Scale Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.17274","snapshot_observed_at":"2026-08-05T18:48:34.686795Z","title":"Bahng, A","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.14197","last_updated":"2025-08-19T18:43:14Z","snapshot_observed_at":"2026-08-09T01:33:11.103215Z","submitted_at":"2025-08-19T18:43:14Z","title":"CLIPSym: Delving into Symmetry Detection with CLIP","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-05T18:48:34.686795Z"},"links":{"cited_paper":"/paper/2203.17274","citing_paper":"/paper/2508.14197"},"observation_digest":"sha256:62c67bd1a2e2976675a78f0f0353bb8b8d08983b7f451f3f47ec4aae7ac0b288","observation_id":"f707f0b5-ef9f-4cda-befb-c3de0ebc6f3d","resolution":{"observed_at":"2026-08-05T18:48:34.686795Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.17274","last_updated":"2022-06-03T17:52:04Z","snapshot_observed_at":"2026-07-06T12:55:27.843060Z","submitted_at":"2022-03-31T17:59:30Z","title":"Exploring Visual Prompts for Adapting Large-Scale Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.17274","snapshot_observed_at":"2026-08-05T13:45:43.985537Z","title":"Explor- ing visual prompts for adapting large-scale models,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.00374","last_updated":"2025-08-30T06:02:21Z","snapshot_observed_at":"2026-08-05T13:45:20.748062Z","submitted_at":"2025-08-30T06:02:21Z","title":"Adaptive Point-Prompt Tuning: Fine-Tuning Heterogeneous Foundation Models for 3D Point Cloud Analysis","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-05T13:45:43.985537Z"},"links":{"cited_paper":"/paper/2203.17274","citing_paper":"/paper/2509.00374"},"observation_digest":"sha256:b6e1c296d2c10d35ae903a9f77c4663a44b5cf40a2586e9c8d74c69c5f920c98","observation_id":"a5d17cd1-77ae-4eec-b466-b453eb082bc1","resolution":{"observed_at":"2026-08-05T13:45:43.985537Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.17274","last_updated":"2022-06-03T17:52:04Z","snapshot_observed_at":"2026-07-06T12:55:27.843060Z","submitted_at":"2022-03-31T17:59:30Z","title":"Exploring Visual Prompts for Adapting Large-Scale Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.17274","snapshot_observed_at":"2026-08-05T10:55:55.673736Z","title":"Exploring Visual Prompts for Adapting Large-Scale Models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.03494","last_updated":"2025-09-06T16:31:33Z","snapshot_observed_at":"2026-08-09T16:30:12.385435Z","submitted_at":"2025-09-03T17:23:24Z","title":"Parameter-Efficient Adaptation of mPLUG-Owl2 via Pixel-Level Visual Prompts for NR-IQA","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-05T10:55:55.673736Z"},"links":{"cited_paper":"/paper/2203.17274","citing_paper":"/paper/2509.03494"},"observation_digest":"sha256:33234a33d61cf1ba26a84ccc4f5f28f5105d0eef74f90dea78f71b5508a42d7b","observation_id":"241f9d26-79d5-4ac8-af64-68c4e92693a7","resolution":{"observed_at":"2026-08-05T10:55:55.673736Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.17274","last_updated":"2022-06-03T17:52:04Z","snapshot_observed_at":"2026-07-06T12:55:27.843060Z","submitted_at":"2022-03-31T17:59:30Z","title":"Exploring Visual Prompts for Adapting Large-Scale Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.17274","snapshot_observed_at":"2026-08-05T05:21:30.834999Z","title":"Explor- ing visual prompts for adapting large-scale models,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.05635","last_updated":"2025-09-06T07:41:47Z","snapshot_observed_at":"2026-08-05T05:21:29.230518Z","submitted_at":"2025-09-06T07:41:47Z","title":"Few-Shot Query Intent Detection via Relation-Aware Prompt Learning","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-05T05:21:30.834999Z"},"links":{"cited_paper":"/paper/2203.17274","citing_paper":"/paper/2509.05635"},"observation_digest":"sha256:454ae54392ad42593854359cb50175832c56b04f06138b7656d5ab4f63cbf045","observation_id":"1128d73f-a5d9-4deb-8e6a-35935c20d013","resolution":{"observed_at":"2026-08-05T05:21:30.834999Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.17274","last_updated":"2022-06-03T17:52:04Z","snapshot_observed_at":"2026-07-06T12:55:27.843060Z","submitted_at":"2022-03-31T17:59:30Z","title":"Exploring Visual Prompts for Adapting Large-Scale Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.17274","snapshot_observed_at":"2026-08-05T04:50:27.627722Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.05949","last_updated":"2025-09-07T07:07:59Z","snapshot_observed_at":"2026-08-09T22:37:59.836106Z","submitted_at":"2025-09-07T07:07:59Z","title":"AttriPrompt: Dynamic Prompt Composition Learning for CLIP","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-05T04:50:27.627722Z"},"links":{"cited_paper":"/paper/2203.17274","citing_paper":"/paper/2509.05949"},"observation_digest":"sha256:f2fb5e43641e6148bbc9388de49569e1259f374bb52a5699255d43649c29666b","observation_id":"d1f09176-d956-4c63-863b-08ddb346d4e6","resolution":{"observed_at":"2026-08-05T04:50:27.627722Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.17274","last_updated":"2022-06-03T17:52:04Z","snapshot_observed_at":"2026-07-06T12:55:27.843060Z","submitted_at":"2022-03-31T17:59:30Z","title":"Exploring Visual Prompts for Adapting Large-Scale Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.17274","snapshot_observed_at":"2026-08-04T12:41:48.171666Z","title":"Exploring visual prompts for adapting large-scale models.arXiv preprint arXiv:2203.17274, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2510.02913","last_updated":"2026-07-25T20:08:20Z","snapshot_observed_at":"2026-08-09T15:56:09.091026Z","submitted_at":"2025-10-03T11:36:02Z","title":"Improving Adversarial Robustness of Zero-Shot CLIP with Confidence-Aware Weighting","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-04T12:41:48.171666Z"},"links":{"cited_paper":"/paper/2203.17274","citing_paper":"/paper/2510.02913"},"observation_digest":"sha256:6ec32f222be61969d6dfd9fcba8cc8dfc88164dd833b2e202fa66fdf5e403661","observation_id":"48c90f39-0524-4b32-a760-c8df16b39471","resolution":{"observed_at":"2026-08-04T12:41:48.171666Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.17274","last_updated":"2022-06-03T17:52:04Z","snapshot_observed_at":"2026-07-06T12:55:27.843060Z","submitted_at":"2022-03-31T17:59:30Z","title":"Exploring Visual Prompts for Adapting Large-Scale Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.17274","snapshot_observed_at":"2026-08-02T21:07:44.774219Z","title":"arXiv preprint arXiv:2203.17274 (2022)","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2602.21397","last_updated":"2026-07-01T05:08:00Z","snapshot_observed_at":"2026-08-02T21:07:43.675064Z","submitted_at":"2026-02-24T22:00:34Z","title":"MMLoP: Multi-Modal Low-Rank Prompting for Efficient Vision-Language Adaptation","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-02T21:07:44.774219Z"},"links":{"cited_paper":"/paper/2203.17274","citing_paper":"/paper/2602.21397"},"observation_digest":"sha256:01cbefb52bdbad93f1185455216676ffdaba95e600b557debc161a5dc06ca14d","observation_id":"092ca34d-4bbb-4d74-a258-365ccec9222e","resolution":{"observed_at":"2026-08-02T21:07:44.774219Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.17274","last_updated":"2022-06-03T17:52:04Z","snapshot_observed_at":"2026-07-06T12:55:27.843060Z","submitted_at":"2022-03-31T17:59:30Z","title":"Exploring Visual Prompts for Adapting Large-Scale Models","version":2},"cited_work":{"arxiv_id":"2203.17274","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2203.17274","snapshot_observed_at":"2026-07-04T00:49:19.216124Z","title":"Visual prompting: Modifying pixel space to adapt pre-trained models","venue":null,"work_id":"da285965-ebf5-410b-beaf-17ba49e67f3d","year":2022},"citing_paper":{"arxiv_id":"2604.06440","last_updated":"2026-04-07T20:28:24Z","snapshot_observed_at":"2026-08-04T19:54:31.349994Z","submitted_at":"2026-04-07T20:28:24Z","title":"Visual prompting reimagined: The power of the Activation Prompts","version":1},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-05-10T18:52:10.770345Z"},"links":{"cited_paper":"/paper/2203.17274","citing_paper":"/paper/2604.06440"},"observation_digest":"sha256:0c8f74d3dcfdbe53edbf508685a4094902ab261a7698997812353a124cdbfda0","observation_id":"7971877d-d16b-49bd-a150-b07fa417ab01","resolution":{"observed_at":"2026-05-10T23:45:53.794408Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2203.17274","last_updated":"2022-06-03T17:52:04Z","snapshot_observed_at":"2026-07-06T12:55:27.843060Z","submitted_at":"2022-03-31T17:59:30Z","title":"Exploring Visual Prompts for Adapting Large-Scale Models","version":2},"cited_work":{"arxiv_id":"2203.17274","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2203.17274","snapshot_observed_at":"2026-07-04T00:49:19.216124Z","title":"Visual prompting: Modifying pixel space to adapt pre-trained models","venue":null,"work_id":"da285965-ebf5-410b-beaf-17ba49e67f3d","year":2022},"citing_paper":{"arxiv_id":"2605.00906","last_updated":"2026-04-29T02:54:33Z","snapshot_observed_at":"2026-08-03T01:43:45.088258Z","submitted_at":"2026-04-29T02:54:33Z","title":"Generalized Category Discovery under Domain Shifts: From Vision to Vision-Language Models","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-05-09T20:20:20.864444Z"},"links":{"cited_paper":"/paper/2203.17274","citing_paper":"/paper/2605.00906"},"observation_digest":"sha256:92981357d0d0d1cc1852b6151a2d3b04f21c6691f9991cc7f9a60ad94ab634c5","observation_id":"201de585-a328-4a43-9536-40209c69348f","resolution":{"observed_at":"2026-05-11T15:16:11.008917Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2203.17274","last_updated":"2022-06-03T17:52:04Z","snapshot_observed_at":"2026-07-06T12:55:27.843060Z","submitted_at":"2022-03-31T17:59:30Z","title":"Exploring Visual Prompts for Adapting Large-Scale Models","version":2},"cited_work":{"arxiv_id":"2203.17274","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2203.17274","snapshot_observed_at":"2026-07-04T00:49:19.216124Z","title":"Visual prompting: Modifying pixel space to adapt pre-trained models","venue":null,"work_id":"da285965-ebf5-410b-beaf-17ba49e67f3d","year":2022},"citing_paper":{"arxiv_id":"2605.05910","last_updated":"2026-05-07T09:20:42Z","snapshot_observed_at":"2026-08-02T15:46:22.431560Z","submitted_at":"2026-05-07T09:20:42Z","title":"Plug-and-play Class-aware Knowledge Injection for Prompt Learning with Visual-Language Model","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-09T15:52:06.698536Z"},"links":{"cited_paper":"/paper/2203.17274","citing_paper":"/paper/2605.05910"},"observation_digest":"sha256:1b2d2f80875f41c2041c6a3c83c9e17b38efe7e8fd38ffce7e19912cad1996e3","observation_id":"ec967b38-6f25-4f53-bf50-3cf01355e7cf","resolution":{"observed_at":"2026-05-11T16:36:09.441123Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2203.17274","last_updated":"2022-06-03T17:52:04Z","snapshot_observed_at":"2026-07-06T12:55:27.843060Z","submitted_at":"2022-03-31T17:59:30Z","title":"Exploring Visual Prompts for Adapting Large-Scale Models","version":2},"cited_work":{"arxiv_id":"2203.17274","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2203.17274","snapshot_observed_at":"2026-07-04T00:49:19.216124Z","title":"Visual prompting: Modifying pixel space to adapt pre-trained models","venue":null,"work_id":"da285965-ebf5-410b-beaf-17ba49e67f3d","year":2022},"citing_paper":{"arxiv_id":"2605.08273","last_updated":"2026-05-08T03:45:51Z","snapshot_observed_at":"2026-08-05T12:51:37.154487Z","submitted_at":"2026-05-08T03:45:51Z","title":"Efficient Prompt Learning for Traffic Forecasting","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-12T01:20:37.192907Z"},"links":{"cited_paper":"/paper/2203.17274","citing_paper":"/paper/2605.08273"},"observation_digest":"sha256:a7ce31a4427d151d28be5a7e37ca9573504abb30bd3327e19eb9a1418ad634f0","observation_id":"76d31edb-a4dc-4c31-a012-6a4a56115b0a","resolution":{"observed_at":"2026-05-12T08:06:26.680493Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2203.17274","last_updated":"2022-06-03T17:52:04Z","snapshot_observed_at":"2026-07-06T12:55:27.843060Z","submitted_at":"2022-03-31T17:59:30Z","title":"Exploring Visual Prompts for Adapting Large-Scale Models","version":2},"cited_work":{"arxiv_id":"2203.17274","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2203.17274","snapshot_observed_at":"2026-07-04T00:49:19.216124Z","title":"Visual prompting: Modifying pixel space to adapt pre-trained models","venue":null,"work_id":"da285965-ebf5-410b-beaf-17ba49e67f3d","year":2022},"citing_paper":{"arxiv_id":"2605.10130","last_updated":"2026-05-11T07:41:37Z","snapshot_observed_at":"2026-07-06T23:22:08.560919Z","submitted_at":"2026-05-11T07:41:37Z","title":"Thermal-Det: Language-Guided Cross-Modal Distillation for Open-Vocabulary Thermal Object Detection","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-12T03:25:13.709254Z"},"links":{"cited_paper":"/paper/2203.17274","citing_paper":"/paper/2605.10130"},"observation_digest":"sha256:3b546e5bf0928e12738bc0f82d59416a76521f1cfd180995d345beb6a90c1750","observation_id":"49a774fc-4d22-4a12-8921-c6917544589a","resolution":{"observed_at":"2026-05-12T03:26:19.261914Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2203.17274","last_updated":"2022-06-03T17:52:04Z","snapshot_observed_at":"2026-07-06T12:55:27.843060Z","submitted_at":"2022-03-31T17:59:30Z","title":"Exploring Visual Prompts for Adapting Large-Scale Models","version":2},"cited_work":{"arxiv_id":"2203.17274","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2203.17274","snapshot_observed_at":"2026-07-04T00:49:19.216124Z","title":"Visual prompting: Modifying pixel space to adapt pre-trained models","venue":null,"work_id":"da285965-ebf5-410b-beaf-17ba49e67f3d","year":2022},"citing_paper":{"arxiv_id":"2605.17577","last_updated":"2026-05-17T18:07:08Z","snapshot_observed_at":"2026-08-03T01:04:57.342492Z","submitted_at":"2026-05-17T18:07:08Z","title":"TAME: Test-Time Adversarial Prompt Tuning via Mixture-of-Experts for Vision-Language Models","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-05-20T14:20:49.278545Z"},"links":{"cited_paper":"/paper/2203.17274","citing_paper":"/paper/2605.17577"},"observation_digest":"sha256:5ca6785736c84b26df721d8a8e20dfbb8d76a32cae7b45384a5ec4d459eff713","observation_id":"fb7d82dc-8cbe-4dba-aa84-4215614ca838","resolution":{"observed_at":"2026-05-20T14:23:21.477774Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2203.17274","last_updated":"2022-06-03T17:52:04Z","snapshot_observed_at":"2026-07-06T12:55:27.843060Z","submitted_at":"2022-03-31T17:59:30Z","title":"Exploring Visual Prompts for Adapting Large-Scale Models","version":2},"cited_work":{"arxiv_id":"2203.17274","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2203.17274","snapshot_observed_at":"2026-07-04T00:49:19.216124Z","title":"Visual prompting: Modifying pixel space to adapt pre-trained models","venue":null,"work_id":"da285965-ebf5-410b-beaf-17ba49e67f3d","year":2022},"citing_paper":{"arxiv_id":"2605.31246","last_updated":"2026-05-29T12:46:15Z","snapshot_observed_at":"2026-07-06T23:40:27.543522Z","submitted_at":"2026-05-29T12:46:15Z","title":"BadBone: Backdoor Attacks Against Backbone Models in Visual Prompt Learning","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-06-28T21:52:23.150188Z"},"links":{"cited_paper":"/paper/2203.17274","citing_paper":"/paper/2605.31246"},"observation_digest":"sha256:5b66148b02bebfee6f9ac5759d6e8237c1d5a17e109f614f1dbe7548f295d1fe","observation_id":"05ef2002-a4ca-4796-933e-7f588ddeefca","resolution":{"observed_at":"2026-07-01T19:56:11.303547Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2203.17274","last_updated":"2022-06-03T17:52:04Z","snapshot_observed_at":"2026-07-06T12:55:27.843060Z","submitted_at":"2022-03-31T17:59:30Z","title":"Exploring Visual Prompts for Adapting Large-Scale Models","version":2},"cited_work":{"arxiv_id":"2203.17274","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2203.17274","snapshot_observed_at":"2026-07-04T00:49:19.216124Z","title":"Visual prompting: Modifying pixel space to adapt pre-trained models","venue":null,"work_id":"da285965-ebf5-410b-beaf-17ba49e67f3d","year":2022},"citing_paper":{"arxiv_id":"2606.00776","last_updated":"2026-05-30T15:44:36Z","snapshot_observed_at":"2026-07-06T23:41:24.911421Z","submitted_at":"2026-05-30T15:44:36Z","title":"Latent Diffusion Pretraining for Crystal Property Prediction","version":1},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-06-28T19:30:38.954152Z"},"links":{"cited_paper":"/paper/2203.17274","citing_paper":"/paper/2606.00776"},"observation_digest":"sha256:fbdf79194a74a57e47b2c7b3607556c81223dc29572dd614d9af5c4a4e05850c","observation_id":"f0cfe145-e2b6-4d75-98ab-eca2f337e9dc","resolution":{"observed_at":"2026-06-28T19:32:34.856001Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2203.17274","last_updated":"2022-06-03T17:52:04Z","snapshot_observed_at":"2026-07-06T12:55:27.843060Z","submitted_at":"2022-03-31T17:59:30Z","title":"Exploring Visual Prompts for Adapting Large-Scale Models","version":2},"cited_work":{"arxiv_id":"2203.17274","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2203.17274","snapshot_observed_at":"2026-07-04T00:49:19.216124Z","title":"Visual prompting: Modifying pixel space to adapt pre-trained models","venue":null,"work_id":"da285965-ebf5-410b-beaf-17ba49e67f3d","year":2022},"citing_paper":{"arxiv_id":"2606.11854","last_updated":"2026-06-10T09:30:37Z","snapshot_observed_at":"2026-08-01T08:16:13.928240Z","submitted_at":"2026-06-10T09:30:37Z","title":"Fine-tuning Multi-modal LLMs with ART: Art-based Reinforcement Training","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-06-27T10:30:51.490047Z"},"links":{"cited_paper":"/paper/2203.17274","citing_paper":"/paper/2606.11854"},"observation_digest":"sha256:f9cda286ac5b36e678cadc38ca5abb4d48732e2a68e76c9cd8dfea09374a440a","observation_id":"718df71c-c640-413d-8ccd-de9d456989a1","resolution":{"observed_at":"2026-07-03T09:07:48.149675Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2203.17274","last_updated":"2022-06-03T17:52:04Z","snapshot_observed_at":"2026-07-06T12:55:27.843060Z","submitted_at":"2022-03-31T17:59:30Z","title":"Exploring Visual Prompts for Adapting Large-Scale Models","version":2},"cited_work":{"arxiv_id":"2203.17274","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2203.17274","snapshot_observed_at":"2026-07-04T00:49:19.216124Z","title":"Visual prompting: Modifying pixel space to adapt pre-trained models","venue":null,"work_id":"da285965-ebf5-410b-beaf-17ba49e67f3d","year":2022},"citing_paper":{"arxiv_id":"2606.19584","last_updated":"2026-06-17T20:39:04Z","snapshot_observed_at":"2026-08-09T11:39:14.249967Z","submitted_at":"2026-06-17T20:39:04Z","title":"Language-Instructed Vision Embeddings for Controllable and Generalizable Perception","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-06-26T20:54:48.203293Z"},"links":{"cited_paper":"/paper/2203.17274","citing_paper":"/paper/2606.19584"},"observation_digest":"sha256:f33ec2cd8fd991263a20d2be4ae163c1ff1482984e6d9accbb703d93ed1775e6","observation_id":"b409a6b4-2b1c-469c-a19c-41e9306614ba","resolution":{"observed_at":"2026-07-04T00:49:19.219783Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2203.17274","last_updated":"2022-06-03T17:52:04Z","snapshot_observed_at":"2026-07-06T12:55:27.843060Z","submitted_at":"2022-03-31T17:59:30Z","title":"Exploring Visual Prompts for Adapting Large-Scale Models","version":2},"cited_work":{"arxiv_id":"2203.17274","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2203.17274","snapshot_observed_at":"2026-07-04T00:49:19.216124Z","title":"Visual prompting: Modifying pixel space to adapt pre-trained models","venue":null,"work_id":"da285965-ebf5-410b-beaf-17ba49e67f3d","year":2022},"citing_paper":{"arxiv_id":"2606.29600","last_updated":"2026-06-28T20:54:18Z","snapshot_observed_at":"2026-08-06T23:46:32.815062Z","submitted_at":"2026-06-28T20:54:18Z","title":"One Scene, Two Depths: Probing Geometric Ambiguity in Monocular Foundation Models","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-06-30T06:58:28.215741Z"},"links":{"cited_paper":"/paper/2203.17274","citing_paper":"/paper/2606.29600"},"observation_digest":"sha256:6fc29a74c1883776d0d9e0456c9912d6f48261f98eab55eb4a32257cf8002e5e","observation_id":"6ff0bf58-5ded-477b-9455-b7faf87feed8","resolution":{"observed_at":"2026-06-30T07:04:21.640534Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2203.17274","last_updated":"2022-06-03T17:52:04Z","snapshot_observed_at":"2026-07-06T12:55:27.843060Z","submitted_at":"2022-03-31T17:59:30Z","title":"Exploring Visual Prompts for Adapting Large-Scale Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.17274","snapshot_observed_at":"2026-08-01T02:13:12.362932Z","title":"Exploring visual prompts for adapting large-scale models.arXiv preprint arXiv:2203.17274, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.25537","last_updated":"2026-07-28T10:18:58Z","snapshot_observed_at":"2026-08-08T23:11:18.983142Z","submitted_at":"2026-07-28T10:18:58Z","title":"Visual prompt engineering for video models","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-01T02:13:12.362932Z"},"links":{"cited_paper":"/paper/2203.17274","citing_paper":"/paper/2607.25537"},"observation_digest":"sha256:bd2a818f0cf38ad4139f165b96fd0cf6504592ff959614bfbd11f3a12f340a80","observation_id":"085e645b-ba73-4dbc-98ac-2d97d35e2bfc","resolution":{"observed_at":"2026-08-01T02:13:12.362932Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2203.17274/citation-record","integrity":"/paper/2203.17274/integrity","json":"/paper/2203.17274/citation-record.json","paper":"/paper/2203.17274"},"outbound":[],"paper":{"arxiv_id":"2203.17274","last_updated":"2022-06-03T17:52:04Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T12:55:27.843060Z","submitted_at":"2022-03-31T17:59:30Z","title":"Exploring Visual Prompts for Adapting Large-Scale Models"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 40 inbound Pith citation observations for arXiv:2203.17274."}