{"as_of":"2026-08-13T20:27:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f15a13ca0e1596e01e898e8ab538c0c3816ae347cf222255554ed6bb92aa4e62","coverage":[{"denominator":66,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":66,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T16:52:27.844180Z","state":"measured"},{"denominator":66,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":66,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-13T06:32:02.005865+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2411.13136/citation-record","integrity":"/paper/2411.13136/integrity","json":"/paper/2411.13136/citation-record.json","paper":"/paper/2411.13136"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T16:52:28.605108Z","title":"Align your prompts: Test-time prompting with distribution align- ment for zero-shot generalization","venue":null,"work_id":"5cb3bb6c-4958-4705-b46a-7d0eeaf71c7f","year":2024},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.601767Z"},"links":{"citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:d2a40e623dd9b018282fb7f6f76708b92c8fc4f8866d0ae0efa7d49e51cf716f","observation_id":"a67bfdc0-bb18-47cf-b57c-f74cd3ee028e","resolution":{"observed_at":"2026-08-12T16:52:28.609305Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.08774","last_updated":"2024-03-04T06:01:33Z","snapshot_observed_at":"2026-08-07T07:30:12.213965Z","submitted_at":"2023-03-15T17:15:04Z","title":"GPT-4 Technical Report","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.08774","snapshot_observed_at":"2026-08-12T16:52:27.606350Z","title":"Gpt-4 technical report","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.606350Z"},"links":{"cited_paper":"/paper/2303.08774","citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:16afaaa1d5423cb96c2889c5e402c700813332fa89bf0b755dddf7d0e1c44921","observation_id":"518df696-ba5f-48be-82fe-8123e754af2d","resolution":{"observed_at":"2026-08-12T16:52:27.606350Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2204.01691","last_updated":"2022-08-16T16:06:33Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2022-04-04T17:57:11Z","title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.01691","snapshot_observed_at":"2026-08-12T16:52:27.610565Z","title":"Do as i can, not as i say: Grounding language in robotic affordances","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.610565Z"},"links":{"cited_paper":"/paper/2204.01691","citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:0227879ef3e498b03af9bdab2287227ad4c6f230ffa74e56fc1e163580075c2a","observation_id":"651d3ff6-fbbf-44bb-9dc3-3c9d669a8112","resolution":{"observed_at":"2026-08-12T16:52:27.610565Z","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":"2026-08-12T16:52:28.594497Z","title":"Agreement-on-the-line: Predicting the performance of neural networks under distribution shift","venue":null,"work_id":"a7e13ee8-e8f5-4afe-891d-ec0b7871ff6d","year":null},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.615177Z"},"links":{"citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:efecffbe35016b092be38501ac2498b582c61003302d3b1045c96bb225f801b0","observation_id":"6a910d48-3f98-4d7b-ae50-3cabe55e4bc7","resolution":{"observed_at":"2026-08-12T16:52:28.598294Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2203.17274","last_updated":"2022-06-03T17:52:04Z","snapshot_observed_at":"2026-08-13T16:10:42.555436Z","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":"2026-08-12T16:52:27.619224Z","title":"Exploring visual prompts for adapting large- scale models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.619224Z"},"links":{"cited_paper":"/paper/2203.17274","citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:3d5c9f06dcac0894fa7088456ecce24f5fc4f59904a46710624195933f19295d","observation_id":"8d7aa66b-5300-4825-8282-f41aa7eb22ca","resolution":{"observed_at":"2026-08-12T16:52:27.619224Z","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":"2026-08-12T16:52:27.623476Z","title":"Food-101–mining discriminative components with random forests","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.623476Z"},"links":{"citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:308c9ff6231725b3d8a0d2738b235babc280a1be928d94801e4578dd9c856491","observation_id":"b26e17d1-b382-418a-9f38-0b174356dffd","resolution":{"observed_at":"2026-08-12T16:52:27.623476Z","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":"2026-08-12T16:52:28.577129Z","title":"Describing textures in the wild","venue":null,"work_id":"3750e528-eef7-4335-ad9a-b870e9642286","year":2014},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.627220Z"},"links":{"citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:3667ffc9dcf4430aef2bf5c9893ab4e9daa2bba39642259af6cced6abbbe4f4e","observation_id":"574c6f45-62c4-4bf5-8e74-ce4e1fea7467","resolution":{"observed_at":"2026-08-12T16:52:28.580641Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T16:52:28.565803Z","title":"Reliable evalua- tion of adversarial robustness with an ensemble of diverse parameter-free attacks","venue":null,"work_id":"54cd5dd3-88fc-46ae-b730-d741be022012","year":2020},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.631175Z"},"links":{"citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:3f391f124be9b221878bb0667c4c6119cfaf82bec7f6cd8c992b2501015a74b1","observation_id":"6ee214d9-ad4f-401e-b09c-3c6bdd443200","resolution":{"observed_at":"2026-08-12T16:52:28.569826Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T16:52:28.554378Z","title":"Boosting adversarial at- tacks with momentum","venue":null,"work_id":"c0a11312-337a-48a5-be21-28e5f647b33e","year":2018},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.634997Z"},"links":{"citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:16e439839d5c21c551b25cec41cda48f367351a4b015754e0dfb801e489015db","observation_id":"0b4d5f23-90b0-4e33-a785-5a265b30c801","resolution":{"observed_at":"2026-08-12T16:52:28.558233Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T16:52:27.638672Z","title":"One perturbation is enough: On generating universal adversarial perturbations against vision- language pre-training models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.638672Z"},"links":{"citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:b3039f1680169cf3c969b6e82f0774f63ddca67bc3279d8a77ca0cd1c47de9b0","observation_id":"81fd44ab-0bef-4235-a7bd-c303fa34ffcf","resolution":{"observed_at":"2026-08-12T16:52:27.638672Z","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":"2026-08-12T16:52:28.542883Z","title":"Learning gener- ative visual models from few training examples: An incre- mental bayesian approach tested on 101 object categories","venue":null,"work_id":"2d0045e0-a49c-4df4-8f5e-673268caf228","year":2004},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.642731Z"},"links":{"citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:40a971f66719a9695ee0df681ba3ce023a345c57a0dbc20f8c3ab3977956569f","observation_id":"349303b4-a001-43b0-9ebe-95f81653ba83","resolution":{"observed_at":"2026-08-12T16:52:28.546801Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T16:52:28.531676Z","title":"Large-scale adversarial training for vision- and-language representation learning","venue":null,"work_id":"e24123bc-7929-43eb-ba56-389c803feda8","year":2020},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.646496Z"},"links":{"citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:4e8b38d81f41a638376538eb7364cc7a92fa976f40d4c132fc8d5539115a64e2","observation_id":"78b00c95-053d-41f0-a8ca-e158440afe2f","resolution":{"observed_at":"2026-08-12T16:52:28.535430Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.04913","last_updated":"2023-12-08T09:08:50Z","snapshot_observed_at":"2026-08-13T05:07:22.505099Z","submitted_at":"2023-12-08T09:08:50Z","title":"SA-Attack: Improving Adversarial Transferability of Vision-Language Pre-training Models via Self-Augmentation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.04913","snapshot_observed_at":"2026-08-12T16:52:27.650257Z","title":"Sa-attack: Improving adversar- ial transferability of vision-language pre-training models via self-augmentation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.650257Z"},"links":{"cited_paper":"/paper/2312.04913","citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:999302993a04a3233313651a75fef757db85cd85f03a45eaf9a620e43381946b","observation_id":"8dedbda0-6fba-4535-acf3-d9cf26e09085","resolution":{"observed_at":"2026-08-12T16:52:27.650257Z","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":"2026-08-12T16:52:28.520004Z","title":"Eurosat: A novel dataset and deep learning benchmark for land use and land cover classification","venue":null,"work_id":"276423c1-5fe7-4852-8f68-ab697cb8f882","year":2019},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.654463Z"},"links":{"citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:51681e3c0e69bd368d2ec760893579f67a910781ffc9873da0bd8b940df83fb7","observation_id":"13ec3537-cef7-4828-bd1d-65f5b106dadb","resolution":{"observed_at":"2026-08-12T16:52:28.524362Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T16:52:28.508580Z","title":"A visual–language foundation model for pathology image analysis using medical twitter","venue":null,"work_id":"41f4bcb0-7e14-4653-bb35-66ebbad3a80b","year":2023},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.658077Z"},"links":{"citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:9d9e9228014f02c2391608f5dcdd6ce2450ef024fd091717f8cb198590afb821","observation_id":"29a8e459-3192-42de-b62e-bbf335eb3ab5","resolution":{"observed_at":"2026-08-12T16:52:28.512561Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T16:52:27.661569Z","title":"Scaling up visual and vision-language representation learning with noisy text supervision","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.661569Z"},"links":{"citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:e32fdf5ab68d12ebd960b113fa6acaffc7fc8d9f8ac2b84bd1db2ccbe002235e","observation_id":"0fcf6700-6d89-424a-a80b-78b7c1792702","resolution":{"observed_at":"2026-08-12T16:52:27.661569Z","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":"2026-08-12T16:52:28.490531Z","title":"Simple but effective: Clip embed- dings for embodied ai","venue":null,"work_id":"ce449a29-0954-4535-8856-8aa86ee65f5d","year":2022},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.665179Z"},"links":{"citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:8d11376fa2b2a776014e7ef1a0842897865ee829574d5588d499d67ac45b4cf0","observation_id":"3e864907-8af8-4236-930d-fe36aa388c06","resolution":{"observed_at":"2026-08-12T16:52:28.494306Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T16:52:28.479823Z","title":"Maple: Multi-modal prompt learning","venue":null,"work_id":"44f2e7e9-c9b3-48e7-be45-f865524aae17","year":2023},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.668740Z"},"links":{"citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:f768a7dc35f28835fae653d09e3154d26bf9c25fcd21b09b59955e302b8f7d3f","observation_id":"e4c18c12-1230-482f-b5fb-de29ca7e3b9d","resolution":{"observed_at":"2026-08-12T16:52:28.483450Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T16:52:28.469322Z","title":"Test-time adaptation induces stronger accuracy and agreement-on-the-line","venue":null,"work_id":"3f48c852-4bfd-43ac-b2ce-10291a276a95","year":null},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.672211Z"},"links":{"citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:a47790bd1eae6d244c510410bf30816cf6fdb8e3f75745d094fa290f920917dc","observation_id":"3af7214f-5933-4239-84e5-58bef45385b5","resolution":{"observed_at":"2026-08-12T16:52:28.473031Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2010.01950","last_updated":"2021-02-19T15:42:38Z","snapshot_observed_at":"2026-08-12T09:04:06.209594Z","submitted_at":"2020-09-24T01:34:42Z","title":"Torchattacks: A PyTorch Repository for Adversarial Attacks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.01950","snapshot_observed_at":"2026-08-12T16:52:27.676168Z","title":"Torchattacks: A pytorch repository for adversar- ial attacks","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.676168Z"},"links":{"cited_paper":"/paper/2010.01950","citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:d4e85531b8c6af9985eb718850c2fccb7daaa8f2aa7db0499ef46d0f0ef1b1d2","observation_id":"4b90cd3b-b27b-416b-bb0e-734cc5e92eb6","resolution":{"observed_at":"2026-08-12T16:52:27.676168Z","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":"2026-08-12T16:52:28.457398Z","title":"3d object representations for fine-grained categorization","venue":null,"work_id":"09750e6e-d2e1-41d0-a7b5-5dc2de497b0a","year":2013},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.680010Z"},"links":{"citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:66af11c035ae36b7ab46ae23d16deb0563f0fedc5d0f9a4f7995ebb03f976d6a","observation_id":"da76e5b1-5d8c-4c01-884f-4b77136b21bb","resolution":{"observed_at":"2026-08-12T16:52:28.461508Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T16:52:28.445310Z","title":"One prompt word is enough to boost adversarial robustness for pre-trained vision-language models","venue":null,"work_id":"d5346297-0ff4-46df-bca4-7a1da97d0313","year":2024},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.683433Z"},"links":{"citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:b5108b992e0ba21e621152aab5b4bf282eab60817143c93af3708f852c5c9bbf","observation_id":"c39837d6-b2f8-4a78-8c6f-b82a8e18a410","resolution":{"observed_at":"2026-08-12T16:52:28.449188Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T16:52:28.433186Z","title":"Set-level guidance at- tack: Boosting adversarial transferability of vision-language pre-training models","venue":null,"work_id":"61d5c5ae-0dc0-44ff-be37-d4a9ecc5efbc","year":2023},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.687095Z"},"links":{"citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:03757fe7b8efa120a6a7e1dc39cd979acb4ae19116878bcdb5392e5887acbe10","observation_id":"0a9c9bd7-3b95-4b63-9e85-4fa6c0761bb3","resolution":{"observed_at":"2026-08-12T16:52:28.437381Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T16:52:28.420535Z","title":"Imbalanced gradients: a sub- tle cause of overestimated adversarial robustness","venue":null,"work_id":"ff6d3d3c-52d1-488d-8ad9-39841a776fab","year":2024},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.690518Z"},"links":{"citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:836d624203e86e813094ad55cdf91cc6d5ebfe602dc71e1d49b17a31aa41ebcc","observation_id":"3c92c15d-06cd-4cef-bc1c-e32fe4662192","resolution":{"observed_at":"2026-08-12T16:52:28.425163Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T16:52:28.409189Z","title":"Towards deep learning models resistant to adversarial attacks","venue":null,"work_id":"3643a0e4-af31-428f-9813-1fba2146bc9d","year":2018},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.694002Z"},"links":{"citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:f8ff69e98f76c57345558c03665f2992519c76fd29e3114b3324da5d7c64ea48","observation_id":"dde244a9-6eb2-41f6-957f-c4d04065347b","resolution":{"observed_at":"2026-08-12T16:52:28.413171Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1306.5151","last_updated":"2013-06-21T14:31:57Z","snapshot_observed_at":"2026-08-12T17:35:23.022229Z","submitted_at":"2013-06-21T14:31:57Z","title":"Fine-Grained Visual Classification of Aircraft","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1306.5151","snapshot_observed_at":"2026-08-12T16:52:27.697455Z","title":"Fine-grained visual classi- fication of aircraft","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.697455Z"},"links":{"cited_paper":"/paper/1306.5151","citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:b381d43daca0c5c93c16081a3164e73337e88b9fe8fda20c998b10103de05e25","observation_id":"976d04d3-ca59-4659-86a6-534baca1fdb4","resolution":{"observed_at":"2026-08-12T16:52:27.697455Z","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":"2026-08-12T16:52:28.398048Z","title":"Understanding zero-shot adversarial robust- ness for large-scale models","venue":null,"work_id":"6096681e-aa5a-4400-8d34-3c5b581a9604","year":2023},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.701377Z"},"links":{"citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:afbd3920dafd5214b8be843d4b1880ba33bd470265c9b78be82d2a7a963f940e","observation_id":"d48d05f9-ef81-4059-8835-d8954c02519c","resolution":{"observed_at":"2026-08-12T16:52:28.401839Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2006.10963","last_updated":"2021-01-14T21:11:06Z","snapshot_observed_at":"2026-08-06T05:58:45.817385Z","submitted_at":"2020-06-19T05:08:43Z","title":"Evaluating Prediction-Time Batch Normalization for Robustness under Covariate Shift","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.10963","snapshot_observed_at":"2026-08-12T16:52:27.705166Z","title":"Evaluating prediction-time batch normalization for robust- ness under covariate shift","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.705166Z"},"links":{"cited_paper":"/paper/2006.10963","citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:9e41b85bc89f00289002a7da49f6f6a137debe6a64de0f85d5fad9b7e239e8e9","observation_id":"734dd0c1-8ae3-4277-9553-56e12181d32a","resolution":{"observed_at":"2026-08-12T16:52:27.705166Z","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":"2026-08-12T16:52:27.709031Z","title":"Automated flower classification over a large number of classes","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.709031Z"},"links":{"citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:4b7adb6bb356dc8b7b50a365b60f3d4b28a127688abe06e1be36f78ec3b5fe8b","observation_id":"74803c23-95d0-424b-988a-2fbcaf4b4bbe","resolution":{"observed_at":"2026-08-12T16:52:27.709031Z","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":"2026-08-12T16:52:28.381349Z","title":"Efficient test- 9 time model adaptation without forgetting","venue":null,"work_id":"80025c28-da0b-4084-bdda-80f0cc7aeeab","year":2022},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.712504Z"},"links":{"citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:6014ee2da25c2f0daf7a6ee1218eca347e3ec2e71f980818b1eb10c3960c3259","observation_id":"5cbe0811-ccd0-43d1-8bcc-a57544227ace","resolution":{"observed_at":"2026-08-12T16:52:28.384878Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T16:52:28.370390Z","title":"Cats and dogs","venue":null,"work_id":"7ef012a0-2788-41fe-8544-72e3ba0ccd87","year":2012},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.715803Z"},"links":{"citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:340c6bd3391dc727159eab3a1794e682ca200f41d0c8509e8ffeab6a0e0c9c66","observation_id":"3a57427d-82db-4c47-bbc7-9c72bd868fa5","resolution":{"observed_at":"2026-08-12T16:52:28.374117Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T16:52:28.359536Z","title":"On the rela- tionship between generalization and robustness to adversar- ial examples","venue":null,"work_id":"fd3e2fba-08b9-4b18-9427-c3c999a110c4","year":2021},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.719415Z"},"links":{"citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:9e636fb4f794faa4f6638125acd76297b922f1b13af57df352f9ecd5b29dd342","observation_id":"22cdc8ba-4300-4ff0-b6e3-6315966857c4","resolution":{"observed_at":"2026-08-12T16:52:28.363427Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T16:52:28.348247Z","title":"Learn- ing transferable visual models from natural language super- vision","venue":null,"work_id":"e2626cec-676f-4476-8f4f-a780fa15791e","year":2021},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.723200Z"},"links":{"citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:af14acc230394832a8cd695cfcfab601ea7d66a84a6771de31fd000f8d153a8b","observation_id":"43604da4-d9d7-4a04-8996-552f49b19418","resolution":{"observed_at":"2026-08-12T16:52:28.352421Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T16:52:27.726821Z","title":"Imagenet large scale visual recognition challenge","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.726821Z"},"links":{"citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:959b8ad0053ad173ec967029f9a7f4f7cf620fe25bb33ab91158e32217e56349","observation_id":"f548a372-ab7e-4317-999b-1e0273013abe","resolution":{"observed_at":"2026-08-12T16:52:27.726821Z","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":"2026-08-12T16:52:28.331125Z","title":"Robust CLIP: Unsupervised ad- versarial fine-tuning of vision embeddings for robust large vision-language models","venue":null,"work_id":"0411ec92-7839-4fb5-b040-fe6f537fb1af","year":2024},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.730286Z"},"links":{"citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:a67c6b59eae3e04093b1e1cdf9884ae66a1ab12089e8faf34ad5450ddad67c50","observation_id":"b6504b37-73b6-46fd-9f79-2056d1ff285d","resolution":{"observed_at":"2026-08-12T16:52:28.334837Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T16:52:28.320207Z","title":"Improving robustness against common corruptions by covariate shift adaptation","venue":null,"work_id":"dee30fa0-0681-4212-9b6a-4b8d4dca8edd","year":2020},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.733729Z"},"links":{"citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:ae8be75f7cea028b75af6c9db014d0cd90943720ba40bfbb5d9b2a9827f4fa4e","observation_id":"d46bad2f-ee0e-4dee-8d29-f05fa39cb2e1","resolution":{"observed_at":"2026-08-12T16:52:28.323880Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2004.08900","last_updated":"2020-04-19T16:28:35Z","snapshot_observed_at":"2026-08-11T03:08:37.055470Z","submitted_at":"2020-04-19T16:28:35Z","title":"The Cost of Training NLP Models: A Concise Overview","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2004.08900","snapshot_observed_at":"2026-08-12T16:52:27.737116Z","title":"The cost of training nlp models: A concise overview","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.737116Z"},"links":{"cited_paper":"/paper/2004.08900","citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:853b4eb1a0a2f47a85b33108db383aa120af2bed0edd3bf4aefb1fe6fc431436","observation_id":"2e7e8c93-0ad0-4efb-a9c7-d2dd199e27eb","resolution":{"observed_at":"2026-08-12T16:52:27.737116Z","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":"2026-08-12T16:52:27.740725Z","title":"Cliport: What and where pathways for robotic manipulation","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.740725Z"},"links":{"citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:05a72fe064ec458c9ec95d1a2caa1195dc3ffcb2c052c220f562dbcb84d2d886","observation_id":"73432cff-c52a-4268-abfe-7a665328ef6f","resolution":{"observed_at":"2026-08-12T16:52:27.740725Z","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":"2026-08-12T16:52:28.303309Z","title":"Test- time prompt tuning for zero-shot generalization in vision- language models","venue":null,"work_id":"80d9b257-b812-44b3-9491-0d3703ce3212","year":2022},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.744135Z"},"links":{"citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:4462c5b88acb4b63fe0d718ef4856073ef8ae1d908f6fefa6d26c7964f14657b","observation_id":"c18ba89a-0142-4ea8-9d00-a3b4c0d57d9c","resolution":{"observed_at":"2026-08-12T16:52:28.307010Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1212.0402","last_updated":"2012-12-03T14:45:31Z","snapshot_observed_at":"2026-08-12T17:34:19.526460Z","submitted_at":"2012-12-03T14:45:31Z","title":"UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1212.0402","snapshot_observed_at":"2026-08-12T16:52:27.747523Z","title":"Ucf101: A dataset of 101 human actions classes from videos in the wild","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.747523Z"},"links":{"cited_paper":"/paper/1212.0402","citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:d4701b44a7993167470d81fd0ec0522021a19cb82b6232bdef003ba73dbdc7fc","observation_id":"83f64589-886e-4de6-8068-7227558c7434","resolution":{"observed_at":"2026-08-12T16:52:27.747523Z","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":"2026-08-12T16:52:28.292715Z","title":"Disentan- gling adversarial robustness and generalization","venue":null,"work_id":"8560401f-99dc-4e0b-b61c-f106e53fb36a","year":null},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.751187Z"},"links":{"citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:ada979fc1d42cdd8d13f510d831babfdf88e5a0b1fc8c7c8fb983a1a6a0c38f8","observation_id":"334da2de-a4af-4867-b6f3-d7a060623bf1","resolution":{"observed_at":"2026-08-12T16:52:28.296181Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T16:52:28.282605Z","title":"Is robustness the cost of accuracy?– a comprehensive study on the robustness of 18 deep image classification models","venue":null,"work_id":"9c25ab75-42a7-438d-a19b-14efa2e9c668","year":2018},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.754913Z"},"links":{"citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:e5a1c3ed7a9d4938d2547a4a10052d77e72cecefc16d690d92cb671bbc9ecf61","observation_id":"f1640690-67b7-4b13-8c26-549577e77a2f","resolution":{"observed_at":"2026-08-12T16:52:28.286114Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T16:52:28.271543Z","title":"In- triguing properties of neural networks","venue":null,"work_id":"a94390c6-5475-4250-8aef-2e868da81c6d","year":2013},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.758345Z"},"links":{"citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:3c7abc666b41008b4405cfd031b20536c80c94b81f153bb04e816cd27d50b949","observation_id":"07564bcb-9fd9-4ca7-8d0b-933c46156d7d","resolution":{"observed_at":"2026-08-12T16:52:28.275668Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.11805","last_updated":"2025-05-09T21:04:06Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-12-19T02:39:27Z","title":"Gemini: A Family of Highly Capable Multimodal Models","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.11805","snapshot_observed_at":"2026-08-12T16:52:27.762038Z","title":"Gemini: a family of highly capable multimodal models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.762038Z"},"links":{"cited_paper":"/paper/2312.11805","citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:54068bae8e8e30d3b39986717bff647daa16576f5463d76692faf479afca95c0","observation_id":"48bfb5d2-56e9-4f83-9a16-a975a45e32c1","resolution":{"observed_at":"2026-08-12T16:52:27.762038Z","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":"2026-08-12T16:52:28.260489Z","title":"Tent: Fully test-time adaptation by entropy minimization","venue":null,"work_id":"aeb7e91f-8587-40c6-a6da-e4706db30a9d","year":2021},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.766504Z"},"links":{"citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:0b3b8519749455689fe653b0e3b40b1e866ddf4bc2b1a4179565c0669a37c8e7","observation_id":"618d51b5-ad1a-4909-a400-6fb13dbb1db5","resolution":{"observed_at":"2026-08-12T16:52:28.264209Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T16:52:28.248918Z","title":"Trans- ferable multimodal attack on vision-language pre-training models","venue":null,"work_id":"d75dfcea-a64f-47a1-aba9-b3dd3c07db50","year":2024},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.770075Z"},"links":{"citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:5b1acf585fcb4bb08e3f1228f7ca724bff6d5b0643c28bdd32950a68fa94a4c5","observation_id":"cf0df288-2cfd-4897-b477-f59e7b92bad2","resolution":{"observed_at":"2026-08-12T16:52:28.253088Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T16:52:28.236955Z","title":"Con- tinual test-time domain adaptation","venue":null,"work_id":"4d60d96f-6e7d-46ce-9858-113ca33e2805","year":2022},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.773702Z"},"links":{"citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:175d5b426123e912e56ead9148f59d2838f2a64978e6f95f6dfeaf25a585f5d5","observation_id":"2d5725b6-8f42-461b-a86e-79dea12622ed","resolution":{"observed_at":"2026-08-12T16:52:28.240908Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T16:52:28.225849Z","title":"Pre- trained model guided fine-tuning for zero-shot adversarial robustness","venue":null,"work_id":"5863965c-3b48-450a-8cb0-6b101c1a02a5","year":2024},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.777170Z"},"links":{"citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:91add8ba285d9587e158f1a2b7d5f45713e91b79deb66e602c950ec97fa5bf95","observation_id":"2899b49b-91f6-4f65-bd82-ddeb0104ea37","resolution":{"observed_at":"2026-08-12T16:52:28.229558Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T16:52:28.214326Z","title":"AdvQDet: Detecting query-based adversarial attacks with adversarial contrastive prompt tun- ing","venue":null,"work_id":"d1e110a5-165e-4439-9838-19a78167e17c","year":2024},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.781771Z"},"links":{"citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:ad13617212d5d073d19642a00af6c85aa7fdb77f5709f6c934ddf5a03180da4a","observation_id":"f06f41c9-ff90-41e2-8a1d-6b9953080415","resolution":{"observed_at":"2026-08-12T16:52:28.218578Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T16:52:28.200912Z","title":"Medclip: Contrastive learning from unpaired medical images and text","venue":null,"work_id":"00544a30-4a50-4147-8e46-9d6f93901713","year":2022},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.785590Z"},"links":{"citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:b40e159e6e1e7b5e4ddaf02aa27471bff49b9411cb849f13311c3dc470f7d406","observation_id":"86fbb80f-6ce3-4d11-bcd3-d281eb6728d3","resolution":{"observed_at":"2026-08-12T16:52:28.205260Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T16:52:28.189238Z","title":"Re- visiting adversarial training at scale","venue":null,"work_id":"6f266d7f-5e09-40f4-b7f5-f7aff4b54a92","year":2024},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.789220Z"},"links":{"citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:e40b73673f480966979c8801095c00d85122a7663b558cc54bed786a6c8f3ec0","observation_id":"117c918d-4b18-4815-89c3-eae9ef280c0f","resolution":{"observed_at":"2026-08-12T16:52:28.193167Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T16:52:28.177280Z","title":"Sun database: Large-scale scene recognition from abbey to zoo","venue":null,"work_id":"9562c4a7-0abb-4e63-85c6-d95c3fefe6d1","year":2010},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.793107Z"},"links":{"citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:c8e8c34e35f20d2bf63d2bd0ea4243e7224371fcd6f114d225b01d2c5cd8b4bf","observation_id":"66b99564-25ac-4121-9163-a1c9f6bc6e50","resolution":{"observed_at":"2026-08-12T16:52:28.181483Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T16:52:27.796630Z","title":"Improving transferabil- ity of adversarial examples with input diversity","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.796630Z"},"links":{"citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:e04b7e6da42602235ae5b2aa7cf4a553ed65c9bc2ec2fd28052f6f45fcb1c99b","observation_id":"87066be0-5bbd-4476-855d-100b52867a59","resolution":{"observed_at":"2026-08-12T16:52:27.796630Z","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":"2026-08-12T16:52:28.158968Z","title":"Vlattack: Multimodal adversarial attacks on vision-language tasks via pre-trained models","venue":null,"work_id":"7d8a76cd-672a-414f-809f-9b3564fa7b69","year":2023},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.800248Z"},"links":{"citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:04ba2e4720ff0e7a8b1c645ea84948188f0c641fc581fc4935bd338b3e148a67","observation_id":"0ac438f1-2d45-48fe-8d75-4735f07aee6b","resolution":{"observed_at":"2026-08-12T16:52:28.162796Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T16:52:27.803912Z","title":"Multi-event video-text retrieval","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.803912Z"},"links":{"citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:fb5d2f452c3944e1e789e7a968ea2b889c821e34984966eb795fae84691f2486","observation_id":"7cea113f-6024-46a9-a37e-e4887bd8ab9a","resolution":{"observed_at":"2026-08-12T16:52:27.803912Z","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":"2026-08-12T16:52:28.138637Z","title":"Theoretically principled trade-off between robustness and accuracy","venue":null,"work_id":"9c72196d-8040-4755-b2e8-b3bbf0406cee","year":2019},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.807451Z"},"links":{"citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:f111c949841f650d50b0aedb09607f2ddfed26a94152437f2e401a6bdfd2b97e","observation_id":"5383218d-6c5f-4f8c-8ece-fb10d5f9bc6a","resolution":{"observed_at":"2026-08-12T16:52:28.142508Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T16:52:27.810981Z","title":"Towards adversarial attack on vision-language pre-training models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.810981Z"},"links":{"citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:dfbfcb9e6987ed3dd5498bb814722be5cf72b13dd74d03845a772855253de4e1","observation_id":"802eae0a-60d1-478d-8b34-e4e9474bbb6a","resolution":{"observed_at":"2026-08-12T16:52:27.810981Z","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":"2026-08-12T16:52:28.119909Z","title":"Adversarial prompt tuning for vision-language models","venue":null,"work_id":"119251f2-c0da-4381-875e-05599245b8f1","year":2024},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.814964Z"},"links":{"citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:97ae3838e034fafa0886ca204896c675d0d7da30fd0da4a343cedbf643e0992f","observation_id":"6b4c7f66-c410-4302-965e-e9ee826b538d","resolution":{"observed_at":"2026-08-12T16:52:28.123706Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T16:52:28.109289Z","title":"Memo: Test time robustness via adaptation and augmentation","venue":null,"work_id":"bd048be0-c1e5-4f1c-9c2c-6cac63db300d","year":2022},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.818545Z"},"links":{"citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:a1b85628323622771ab3a0073dc33f1d1d3266d1e3125cf8340adc3d57dc3061","observation_id":"85d99722-1b83-4ef8-a023-84616393d9c7","resolution":{"observed_at":"2026-08-12T16:52:28.112918Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T16:52:28.097574Z","title":"Univer- sal adversarial perturbations for vision-language pre-trained models","venue":null,"work_id":"79215db6-6610-43aa-8858-0f9d92697351","year":2024},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.822479Z"},"links":{"citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:8f5c94b2a2a7d0aea771d60d5e8aeb5dca0342a20e3adda2480cf235ed163ba7","observation_id":"5025364b-d97a-40f5-ba13-f1dd194f1ff8","resolution":{"observed_at":"2026-08-12T16:52:28.101759Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T16:52:28.086951Z","title":"On evaluating adversarial robustness of large vision-language models","venue":null,"work_id":"01286f4f-809b-4aa9-b6f6-ebd550496928","year":2024},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.825958Z"},"links":{"citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:7490e25195eb2aba13e8ed59d15cdc0dc673e00b27c919ac758927138859ec62","observation_id":"ceaf71e2-0ea8-4b4e-b96c-804f7497a86a","resolution":{"observed_at":"2026-08-12T16:52:28.090659Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T16:52:28.074902Z","title":"Conditional prompt learning for vision-language models","venue":null,"work_id":"c4a03033-ef68-453d-8582-e4b3508ab96d","year":2022},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.829420Z"},"links":{"citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:fceb656075b4e3cb8ffd8b49e103be53c08108524804e9efb1538749d61280c7","observation_id":"a4ac5ca2-dc9a-45f2-9ed8-158319245599","resolution":{"observed_at":"2026-08-12T16:52:28.079185Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T16:52:27.833011Z","title":"Learning to prompt for vision-language models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.833011Z"},"links":{"citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:76861cfab90e55e7248c66ccd349d59dc5a94cf96bbdef9cf4bd333e142b8047","observation_id":"54589e70-1270-4b66-9757-a3dc569a3c6d","resolution":{"observed_at":"2026-08-12T16:52:27.833011Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.19287","last_updated":"2024-11-12T10:48:21Z","snapshot_observed_at":"2026-08-13T19:14:38.705895Z","submitted_at":"2024-04-30T06:34:21Z","title":"Revisiting the Adversarial Robustness of Vision Language Models: a Multimodal Perspective","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.19287","snapshot_observed_at":"2026-08-12T16:52:27.836524Z","title":"Revisiting the adversarial robustness of vision language models: a multimodal perspective","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.836524Z"},"links":{"cited_paper":"/paper/2404.19287","citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:1f5e842cbd8d2fa611f4ec0a7986ad5520174f73075ff0f179fbff995a9ea8f9","observation_id":"6f453f80-fa02-48b3-b641-d3932e2de760","resolution":{"observed_at":"2026-08-12T16:52:27.836524Z","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":"2026-08-12T16:52:28.056892Z","title":"Few-shot adversarial prompt learning on vision-language models","venue":null,"work_id":"e027517a-da35-4056-ab6b-42e675baa28b","year":2024},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.840353Z"},"links":{"citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:9ce412de6837924b7a0d0c637345c839b1c7d189e14318cb53844e7dd8d4185e","observation_id":"2364e03f-d124-460b-a650-99d3b036c607","resolution":{"observed_at":"2026-08-12T16:52:28.060689Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T16:52:28.044101Z","title":"Advclip: Downstream-agnostic adversarial examples in multimodal contrastive learning","venue":null,"work_id":"b55e0e9e-4835-4aa2-ae00-9708c3665a2a","year":2023},"citing_paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-12T16:52:27.844180Z"},"links":{"citing_paper":"/paper/2411.13136"},"observation_digest":"sha256:3e8990a426a3c5b9eb627268068758bb2e4090ff3456d70afebaa1dd53086d9d","observation_id":"e3a2ccde-b8ee-493e-9b63-d4179845281a","resolution":{"observed_at":"2026-08-12T16:52:28.049547Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2411.13136","last_updated":"2024-11-20T08:58:59Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-12T21:46:04.963008Z","submitted_at":"2024-11-20T08:58:59Z","title":"TAPT: Test-Time Adversarial Prompt Tuning for Robust Inference in Vision-Language Models"},"reference_resolution":{"displayed":66,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":21,"verified_exact":0,"verified_fuzzy":45},"total_outbound_references":66},"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":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 66 of 66 outbound references and 0 inbound Pith citation observations for arXiv:2411.13136."}