{"as_of":"2026-08-08T07:19:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:342fc9a24b90d5cfdf44f6a02191cafb0be12dfab115c883d4c981deeb938c4a","coverage":[{"denominator":57,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":57,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T15:10:13.252061Z","state":"measured"},{"denominator":58,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":58,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-13T20:58:59.346867Z","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":"2026-05-13T21:03:20.317945Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2505.16149","last_updated":"2025-05-22T02:47:36Z","snapshot_observed_at":"2026-08-07T15:04:05.913617Z","submitted_at":"2025-05-22T02:47:36Z","title":"When VLMs Meet Image Classification: Test Sets Renovation via Missing Label Identification","version":1},"cited_work":{"arxiv_id":"2505.16149","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.16149","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"arXiv preprint arXiv:2505.16149 (2025)","venue":null,"work_id":"10a4804d-777f-49b1-aaf4-284ab05cde73","year":2025},"citing_paper":{"arxiv_id":"2604.03156","last_updated":"2026-06-17T05:47:04Z","snapshot_observed_at":"2026-08-02T19:28:53.956947Z","submitted_at":"2026-04-03T16:27:02Z","title":"CAMEO: A Conditional and Quality-Aware Multi-Agent Image Editing Orchestrator","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-05-13T20:58:59.346867Z"},"links":{"cited_paper":"/paper/2505.16149","citing_paper":"/paper/2604.03156"},"observation_digest":"sha256:99c0d66cecdb1388ca00bbed032c6ddef5a92540c685584b7b7b3bf5754ac299","observation_id":"25fa9c8e-96e5-49bd-84e8-18e3e5f29531","resolution":{"observed_at":"2026-05-13T21:03:20.320358Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2505.16149/citation-record","integrity":"/paper/2505.16149/integrity","json":"/paper/2505.16149/citation-record.json","paper":"/paper/2505.16149"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2204.14198","last_updated":"2022-11-15T23:07:37Z","snapshot_observed_at":"2026-07-06T13:05:12.350238Z","submitted_at":"2022-04-29T16:29:01Z","title":"Flamingo: a Visual Language Model for Few-Shot Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.14198","snapshot_observed_at":"2026-08-07T15:10:06.972843Z","title":"Flamingo: a visual language model for few-shot learning.arXiv preprint arXiv:2204.14198, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.16149","last_updated":"2025-05-22T02:47:36Z","snapshot_observed_at":"2026-08-07T15:04:05.913617Z","submitted_at":"2025-05-22T02:47:36Z","title":"When VLMs Meet Image Classification: Test Sets Renovation via Missing Label Identification","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T15:10:06.972843Z"},"links":{"cited_paper":"/paper/2204.14198","citing_paper":"/paper/2505.16149"},"observation_digest":"sha256:fa70553dd1ef2a1ce46d21b78e03273981ddea89ee02b3bb9b497326aa7502e7","observation_id":"48a3e18a-4e49-49f5-ae0b-0819e9da3985","resolution":{"observed_at":"2026-08-07T15:10:06.972843Z","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":"2026-08-07T15:10:20.338864Z","title":"Robust bi-tempered logistic loss based on Bregman divergences.Advances in Neural Information Processing Systems, 32, 2019","venue":null,"work_id":"c513cdf0-067e-4efb-8092-5adbd158d6a2","year":2019},"citing_paper":{"arxiv_id":"2505.16149","last_updated":"2025-05-22T02:47:36Z","snapshot_observed_at":"2026-08-07T15:04:05.913617Z","submitted_at":"2025-05-22T02:47:36Z","title":"When VLMs Meet Image Classification: Test Sets Renovation via Missing Label Identification","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T15:10:07.036315Z"},"links":{"citing_paper":"/paper/2505.16149"},"observation_digest":"sha256:6a6fca0dd030097b5f7271cf0e8e965d471b009b7258bc6ef869c7d64b34f65c","observation_id":"8f064ddd-9342-4f7f-b4b6-bf9ce1bd984d","resolution":{"observed_at":"2026-08-07T15:10:20.344936Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.01390","last_updated":"2023-08-07T17:53:09Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-08-02T19:10:23Z","title":"OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.01390","snapshot_observed_at":"2026-08-07T15:10:07.127399Z","title":"Openflamingo: An open-source framework for multimodal few-shot learning.arXiv preprint arXiv:2308.01390, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.16149","last_updated":"2025-05-22T02:47:36Z","snapshot_observed_at":"2026-08-07T15:04:05.913617Z","submitted_at":"2025-05-22T02:47:36Z","title":"When VLMs Meet Image Classification: Test Sets Renovation via Missing Label Identification","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T15:10:07.127399Z"},"links":{"cited_paper":"/paper/2308.01390","citing_paper":"/paper/2505.16149"},"observation_digest":"sha256:f0b4a27a37ca93068c138e05ca3d6129919de5cc6765516eb6cd0d5b743e2b09","observation_id":"6fcd7051-fdc4-4f55-ad25-778f795e80ff","resolution":{"observed_at":"2026-08-07T15:10:07.127399Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.12966","last_updated":"2023-10-13T02:41:28Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-08-24T17:59:17Z","title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.12966","snapshot_observed_at":"2026-08-07T15:10:07.196272Z","title":"Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond.arXiv preprint arXiv:2308.12966, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.16149","last_updated":"2025-05-22T02:47:36Z","snapshot_observed_at":"2026-08-07T15:04:05.913617Z","submitted_at":"2025-05-22T02:47:36Z","title":"When VLMs Meet Image Classification: Test Sets Renovation via Missing Label Identification","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T15:10:07.196272Z"},"links":{"cited_paper":"/paper/2308.12966","citing_paper":"/paper/2505.16149"},"observation_digest":"sha256:e5cf075dfd460f90f0abdbb40f24abd2a3aa586355db46160ebd2739aeda5d98","observation_id":"8a525d9e-dee7-4dad-be7e-9c06f4445167","resolution":{"observed_at":"2026-08-07T15:10:07.196272Z","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":"2026-08-07T15:10:07.274254Z","title":"Multi-label classification with partial annotations using class-aware selective loss","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.16149","last_updated":"2025-05-22T02:47:36Z","snapshot_observed_at":"2026-08-07T15:04:05.913617Z","submitted_at":"2025-05-22T02:47:36Z","title":"When VLMs Meet Image Classification: Test Sets Renovation via Missing Label Identification","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T15:10:07.274254Z"},"links":{"citing_paper":"/paper/2505.16149"},"observation_digest":"sha256:d739a0ea8fd55d0367d4c49db6f2633b90bf5c1fab95a9626ce61bced32368d4","observation_id":"961a0667-4b37-4de6-a241-c14631fe194c","resolution":{"observed_at":"2026-08-07T15:10:07.274254Z","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":"2026-08-07T15:10:20.296051Z","title":"Revolt: Collaborative crowdsourcing for labeling machine learning datasets","venue":null,"work_id":"50369f8b-5d9c-4aaa-97d1-9f07ffc6234b","year":2017},"citing_paper":{"arxiv_id":"2505.16149","last_updated":"2025-05-22T02:47:36Z","snapshot_observed_at":"2026-08-07T15:04:05.913617Z","submitted_at":"2025-05-22T02:47:36Z","title":"When VLMs Meet Image Classification: Test Sets Renovation via Missing Label Identification","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T15:10:07.387342Z"},"links":{"citing_paper":"/paper/2505.16149"},"observation_digest":"sha256:d57b5350766f59a679f019563133a86886dea5fc7110b4620ddd32389d59806c","observation_id":"0e71ad4c-169a-4845-b791-042fda023895","resolution":{"observed_at":"2026-08-07T15:10:20.312410Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:10:20.139140Z","title":"Understanding and utilizing deep neural networks trained with noisy labels","venue":null,"work_id":"b98f9767-067b-43b6-ac82-254cf989f18d","year":2019},"citing_paper":{"arxiv_id":"2505.16149","last_updated":"2025-05-22T02:47:36Z","snapshot_observed_at":"2026-08-07T15:04:05.913617Z","submitted_at":"2025-05-22T02:47:36Z","title":"When VLMs Meet Image Classification: Test Sets Renovation via Missing Label Identification","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T15:10:07.454791Z"},"links":{"citing_paper":"/paper/2505.16149"},"observation_digest":"sha256:d1378919cd788a7bec3a8774759f3e91af29a9a4793ae91b1f4692451a4e3555","observation_id":"9f06821e-0f4a-45b7-8cfb-3e51a74f7c49","resolution":{"observed_at":"2026-08-07T15:10:20.213540Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2501.17811","last_updated":"2025-01-29T18:00:19Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-01-29T18:00:19Z","title":"Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.17811","snapshot_observed_at":"2026-08-07T15:10:07.532981Z","title":"Janus-pro: Unified multimodal understanding and generation with data and model scaling.arXiv preprint arXiv:2501.17811, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.16149","last_updated":"2025-05-22T02:47:36Z","snapshot_observed_at":"2026-08-07T15:04:05.913617Z","submitted_at":"2025-05-22T02:47:36Z","title":"When VLMs Meet Image Classification: Test Sets Renovation via Missing Label Identification","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T15:10:07.532981Z"},"links":{"cited_paper":"/paper/2501.17811","citing_paper":"/paper/2505.16149"},"observation_digest":"sha256:6e93755fe98b8737e008f5bd874ed28be233f7317e18a8056848efe3707d84e9","observation_id":"6f375435-c8b1-4f53-a707-99b73eaf87fd","resolution":{"observed_at":"2026-08-07T15:10:07.532981Z","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":"2026-08-07T15:10:19.959252Z","title":"Learning with instance-dependent label noise: A sample sieve approach","venue":null,"work_id":"e4ed5f87-45b1-42ff-92f0-581e30e35f1e","year":2021},"citing_paper":{"arxiv_id":"2505.16149","last_updated":"2025-05-22T02:47:36Z","snapshot_observed_at":"2026-08-07T15:04:05.913617Z","submitted_at":"2025-05-22T02:47:36Z","title":"When VLMs Meet Image Classification: Test Sets Renovation via Missing Label Identification","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T15:10:07.619926Z"},"links":{"citing_paper":"/paper/2505.16149"},"observation_digest":"sha256:4003397c167abf654b0fa8ecf1e016ae8582ddc852bbd9d90d9a1f48f897ec23","observation_id":"6ab8e373-0174-47fa-b025-f6bb3748e6ae","resolution":{"observed_at":"2026-08-07T15:10:20.050759Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.06500","last_updated":"2023-06-15T08:00:18Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-05-11T00:38:10Z","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.06500","snapshot_observed_at":"2026-08-07T15:10:07.708958Z","title":"Instructblip: Towards general-purpose vision- language models with instruction tuning.arXiv preprint arXiv:2305.06500, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.16149","last_updated":"2025-05-22T02:47:36Z","snapshot_observed_at":"2026-08-07T15:04:05.913617Z","submitted_at":"2025-05-22T02:47:36Z","title":"When VLMs Meet Image Classification: Test Sets Renovation via Missing Label Identification","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T15:10:07.708958Z"},"links":{"cited_paper":"/paper/2305.06500","citing_paper":"/paper/2505.16149"},"observation_digest":"sha256:8e0c49e354d44588374be3905137cef9215d0af09dd8924fe45bb0dc225a6d4a","observation_id":"cd5e300b-90c8-4a31-a339-514a3398aba3","resolution":{"observed_at":"2026-08-07T15:10:07.708958Z","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":"2026-08-07T15:10:07.781082Z","title":"Imagenet: A large- scale hierarchical image database","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2505.16149","last_updated":"2025-05-22T02:47:36Z","snapshot_observed_at":"2026-08-07T15:04:05.913617Z","submitted_at":"2025-05-22T02:47:36Z","title":"When VLMs Meet Image Classification: Test Sets Renovation via Missing Label Identification","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T15:10:07.781082Z"},"links":{"citing_paper":"/paper/2505.16149"},"observation_digest":"sha256:d372a6b051cd45507dcf7ddb04c3b76325684808ad020ae6f3d929a84b267134","observation_id":"cdb43341-5072-45fb-a67f-b44b3686d445","resolution":{"observed_at":"2026-08-07T15:10:07.781082Z","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":"2026-08-07T15:10:07.867329Z","title":"Learning a deep convnet for multi-label classification with partial labels","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.16149","last_updated":"2025-05-22T02:47:36Z","snapshot_observed_at":"2026-08-07T15:04:05.913617Z","submitted_at":"2025-05-22T02:47:36Z","title":"When VLMs Meet Image Classification: Test Sets Renovation via Missing Label Identification","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T15:10:07.867329Z"},"links":{"citing_paper":"/paper/2505.16149"},"observation_digest":"sha256:690527973be581f1b71982e2de6488328d998e02d7971033050ddb680f26b679","observation_id":"3bd93e03-d636-408f-b0ce-c2fd53e0501e","resolution":{"observed_at":"2026-08-07T15:10:07.867329Z","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":"2026-08-07T15:10:19.805432Z","title":"Training deep neural-networks using a noise adapta- tion layer","venue":null,"work_id":"b4dbbaaf-defb-4000-8d12-b1074eb81cb2","year":2017},"citing_paper":{"arxiv_id":"2505.16149","last_updated":"2025-05-22T02:47:36Z","snapshot_observed_at":"2026-08-07T15:04:05.913617Z","submitted_at":"2025-05-22T02:47:36Z","title":"When VLMs Meet Image Classification: Test Sets Renovation via Missing Label Identification","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T15:10:07.975552Z"},"links":{"citing_paper":"/paper/2505.16149"},"observation_digest":"sha256:6dfa9631051efd44bb4f372b641ba788e7f92b076d6a8dd591db35a3197873b3","observation_id":"ba6c2ee2-d814-4d58-9616-e7bb6938a4f2","resolution":{"observed_at":"2026-08-07T15:10:19.845977Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:10:19.789460Z","title":"Caltech-256 object category dataset","venue":null,"work_id":"b3941650-090f-46d4-9faa-fd4725971f8e","year":2007},"citing_paper":{"arxiv_id":"2505.16149","last_updated":"2025-05-22T02:47:36Z","snapshot_observed_at":"2026-08-07T15:04:05.913617Z","submitted_at":"2025-05-22T02:47:36Z","title":"When VLMs Meet Image Classification: Test Sets Renovation via Missing Label Identification","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T15:10:08.064431Z"},"links":{"citing_paper":"/paper/2505.16149"},"observation_digest":"sha256:b601179b48eb9263709458853d7d943640694e059a1a370a660c7906b1fc4e2e","observation_id":"99aaa568-009d-4fb6-aca0-38910f54b467","resolution":{"observed_at":"2026-08-07T15:10:19.795432Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:10:08.176558Z","title":"Using trusted data to train deep networks on labels corrupted by severe noise.Advances in neural information processing systems, 31, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.16149","last_updated":"2025-05-22T02:47:36Z","snapshot_observed_at":"2026-08-07T15:04:05.913617Z","submitted_at":"2025-05-22T02:47:36Z","title":"When VLMs Meet Image Classification: Test Sets Renovation via Missing Label Identification","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T15:10:08.176558Z"},"links":{"citing_paper":"/paper/2505.16149"},"observation_digest":"sha256:808c37af72759f82969ccd72840f9e6b2d393fe1e3d72c2ed2146ecdac33dd8e","observation_id":"6f8f14ad-e6c5-4016-91cc-ca137689b0e3","resolution":{"observed_at":"2026-08-07T15:10:08.176558Z","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":"2026-08-07T15:10:19.768748Z","title":"Scaling up visual and vision-language representation learning with noisy text supervision","venue":null,"work_id":"48abbc46-cf05-4495-bf24-01a56b1d981c","year":2021},"citing_paper":{"arxiv_id":"2505.16149","last_updated":"2025-05-22T02:47:36Z","snapshot_observed_at":"2026-08-07T15:04:05.913617Z","submitted_at":"2025-05-22T02:47:36Z","title":"When VLMs Meet Image Classification: Test Sets Renovation via Missing Label Identification","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T15:10:08.280972Z"},"links":{"citing_paper":"/paper/2505.16149"},"observation_digest":"sha256:e3aea929632487311757043812dceaae8a01ceb91d66ab58bed91728a4ce5221","observation_id":"e14c9111-f0ad-46c4-84b5-050e73c2279a","resolution":{"observed_at":"2026-08-07T15:10:19.773148Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:10:19.757387Z","title":"Detecting and preventing confused labels in crowdsourced data.Proceedings of the VLDB Endowment, 13(12):2522–2535, 2020","venue":null,"work_id":"1591224c-a333-42ad-9a58-96e123ea65a6","year":2020},"citing_paper":{"arxiv_id":"2505.16149","last_updated":"2025-05-22T02:47:36Z","snapshot_observed_at":"2026-08-07T15:04:05.913617Z","submitted_at":"2025-05-22T02:47:36Z","title":"When VLMs Meet Image Classification: Test Sets Renovation via Missing Label Identification","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T15:10:08.395288Z"},"links":{"citing_paper":"/paper/2505.16149"},"observation_digest":"sha256:334966c6df699ea717cdcc396a6b083f2af44ff67207dbfac908ec094f62c6f7","observation_id":"5ee5d210-d361-499a-a95e-6714754ed563","resolution":{"observed_at":"2026-08-07T15:10:19.761199Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:10:08.510498Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2505.16149","last_updated":"2025-05-22T02:47:36Z","snapshot_observed_at":"2026-08-07T15:04:05.913617Z","submitted_at":"2025-05-22T02:47:36Z","title":"When VLMs Meet Image Classification: Test Sets Renovation via Missing Label Identification","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T15:10:08.510498Z"},"links":{"citing_paper":"/paper/2505.16149"},"observation_digest":"sha256:f0e14145b2644652cc8f1a781691ae1cb765dcd67f1b4be3817571287bb76ca1","observation_id":"9e581a3b-be4e-4344-bd85-82ad5b0d0ef6","resolution":{"observed_at":"2026-08-07T15:10:08.510498Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2111.05428","last_updated":"2021-11-09T21:37:53Z","snapshot_observed_at":"2026-08-07T23:19:59.359877Z","submitted_at":"2021-11-09T21:37:53Z","title":"Constrained Instance and Class Reweighting for Robust Learning under Label Noise","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2111.05428","snapshot_observed_at":"2026-08-07T15:10:08.626706Z","title":"Constrained instance and class reweighting for robust learning under label noise.arXiv preprint arXiv:2111.05428, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.16149","last_updated":"2025-05-22T02:47:36Z","snapshot_observed_at":"2026-08-07T15:04:05.913617Z","submitted_at":"2025-05-22T02:47:36Z","title":"When VLMs Meet Image Classification: Test Sets Renovation via Missing Label Identification","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T15:10:08.626706Z"},"links":{"cited_paper":"/paper/2111.05428","citing_paper":"/paper/2505.16149"},"observation_digest":"sha256:ca2c8e64a9cb452e03df22557d17939da12c846a82716a97f179ad9ed570eae7","observation_id":"9228a774-a58a-4557-8d3b-bfe3d2b72162","resolution":{"observed_at":"2026-08-07T15:10:08.626706Z","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":"2026-08-07T15:10:08.731369Z","title":"Gradient-based learning applied to document recognition.Proceedings of the IEEE, 86(11):2278–2324, 1998","venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2505.16149","last_updated":"2025-05-22T02:47:36Z","snapshot_observed_at":"2026-08-07T15:04:05.913617Z","submitted_at":"2025-05-22T02:47:36Z","title":"When VLMs Meet Image Classification: Test Sets Renovation via Missing Label Identification","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T15:10:08.731369Z"},"links":{"citing_paper":"/paper/2505.16149"},"observation_digest":"sha256:cc2a8346a93ca741a69a221958d8a3f6bb86e6ef8073c6d0998c3841dc69abae","observation_id":"d3845250-8d70-4512-8ccb-b3b0dbfb8561","resolution":{"observed_at":"2026-08-07T15:10:08.731369Z","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":"2026-08-07T15:10:08.846380Z","title":"Blip: Bootstrapping language- image pre-training for unified vision-language understanding and generation","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.16149","last_updated":"2025-05-22T02:47:36Z","snapshot_observed_at":"2026-08-07T15:04:05.913617Z","submitted_at":"2025-05-22T02:47:36Z","title":"When VLMs Meet Image Classification: Test Sets Renovation via Missing Label Identification","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T15:10:08.846380Z"},"links":{"citing_paper":"/paper/2505.16149"},"observation_digest":"sha256:6b61d5124ae45da5ea459220023c36cd21e0aee430eca9a1a6948e836c321d22","observation_id":"93a1c842-87b5-4a4c-aa02-4cb2260404a4","resolution":{"observed_at":"2026-08-07T15:10:08.846380Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2301.12597","last_updated":"2023-06-15T07:57:29Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-01-30T00:56:51Z","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.12597","snapshot_observed_at":"2026-08-07T15:10:08.955081Z","title":"Blip-2: Bootstrapping language- image pre-training with frozen image encoders and large language models.arXiv preprint arXiv:2301.12597, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.16149","last_updated":"2025-05-22T02:47:36Z","snapshot_observed_at":"2026-08-07T15:04:05.913617Z","submitted_at":"2025-05-22T02:47:36Z","title":"When VLMs Meet Image Classification: Test Sets Renovation via Missing Label Identification","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T15:10:08.955081Z"},"links":{"cited_paper":"/paper/2301.12597","citing_paper":"/paper/2505.16149"},"observation_digest":"sha256:163273aad414c381da878f2f1f6bb38e62bfce29af65c41b06927907841c1569","observation_id":"9564e4d9-de7d-4b9d-893d-ebfb7204a736","resolution":{"observed_at":"2026-08-07T15:10:08.955081Z","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":"2026-08-07T15:10:09.021317Z","title":"Align before fuse: Vision and language representation learning with momentum distillation.Advances in neural information processing systems, 34:9694–9705, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.16149","last_updated":"2025-05-22T02:47:36Z","snapshot_observed_at":"2026-08-07T15:04:05.913617Z","submitted_at":"2025-05-22T02:47:36Z","title":"When VLMs Meet Image Classification: Test Sets Renovation via Missing Label Identification","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T15:10:09.021317Z"},"links":{"citing_paper":"/paper/2505.16149"},"observation_digest":"sha256:2843103e7562d7ebbc77a706304f8413e5a1ce7ec53b3c313100683f143e117f","observation_id":"6a8675f7-9c6e-4fb4-840a-faf73d8de1db","resolution":{"observed_at":"2026-08-07T15:10:09.021317Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.08485","last_updated":"2023-12-11T17:46:14Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-04-17T17:59:25Z","title":"Visual Instruction Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.08485","snapshot_observed_at":"2026-08-07T15:10:09.121439Z","title":"Visual instruction tuning.arXiv preprint arXiv:2304.08485, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.16149","last_updated":"2025-05-22T02:47:36Z","snapshot_observed_at":"2026-08-07T15:04:05.913617Z","submitted_at":"2025-05-22T02:47:36Z","title":"When VLMs Meet Image Classification: Test Sets Renovation via Missing Label Identification","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T15:10:09.121439Z"},"links":{"cited_paper":"/paper/2304.08485","citing_paper":"/paper/2505.16149"},"observation_digest":"sha256:cb38669744ac9b6cfb201ca454a4bc754c0f7168c5d8ce00b962d79913b382ef","observation_id":"4f7f9a45-9155-4a8e-93dd-629543266a3c","resolution":{"observed_at":"2026-08-07T15:10:09.121439Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.11338","last_updated":"2026-04-19T00:17:32Z","snapshot_observed_at":"2026-07-06T19:03:52.342045Z","submitted_at":"2024-08-21T04:45:12Z","title":"Automatic Dataset Construction (ADC): Sample Collection, Data Curation, and Beyond","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.11338","snapshot_observed_at":"2026-08-07T15:10:09.230185Z","title":"Automatic dataset construction (adc): Sample collection, data curation, and beyond.arXiv preprint arXiv:2408.11338, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.16149","last_updated":"2025-05-22T02:47:36Z","snapshot_observed_at":"2026-08-07T15:04:05.913617Z","submitted_at":"2025-05-22T02:47:36Z","title":"When VLMs Meet Image Classification: Test Sets Renovation via Missing Label Identification","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T15:10:09.230185Z"},"links":{"cited_paper":"/paper/2408.11338","citing_paper":"/paper/2505.16149"},"observation_digest":"sha256:3f89a17e8e36ffb37e4dacbd11d7f6ef8d681a06210a38013cf5102d6ed7a459","observation_id":"b9000fca-389d-4516-b2db-3f3a74aecfce","resolution":{"observed_at":"2026-08-07T15:10:09.230185Z","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":"2026-08-07T15:10:19.712550Z","title":"Human and ai perceptual differences in image classification errors","venue":null,"work_id":"af0c1503-f4e8-4086-b554-658b3bf1afd5","year":2025},"citing_paper":{"arxiv_id":"2505.16149","last_updated":"2025-05-22T02:47:36Z","snapshot_observed_at":"2026-08-07T15:04:05.913617Z","submitted_at":"2025-05-22T02:47:36Z","title":"When VLMs Meet Image Classification: Test Sets Renovation via Missing Label Identification","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T15:10:09.318525Z"},"links":{"citing_paper":"/paper/2505.16149"},"observation_digest":"sha256:7078a415d4322740ce88e13590f118094e02f23bc71bc6676a757e72bc623c12","observation_id":"e51ac529-6a5a-4a5d-9962-6b2fe153ac0e","resolution":{"observed_at":"2026-08-07T15:10:19.716942Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:10:19.698637Z","title":"Classification with noisy labels by importance reweighting","venue":null,"work_id":"40a8e52d-d77c-4110-8fd7-8bc8b2a0d78e","year":2016},"citing_paper":{"arxiv_id":"2505.16149","last_updated":"2025-05-22T02:47:36Z","snapshot_observed_at":"2026-08-07T15:04:05.913617Z","submitted_at":"2025-05-22T02:47:36Z","title":"When VLMs Meet Image Classification: Test Sets Renovation via Missing Label Identification","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T15:10:09.425206Z"},"links":{"citing_paper":"/paper/2505.16149"},"observation_digest":"sha256:cf94cad2896ec93e29212ef4d5c096454d4f2384467968e00b12acdb6a5bc211","observation_id":"bf7f27be-965f-407e-b40d-562537f78e6c","resolution":{"observed_at":"2026-08-07T15:10:19.703561Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:10:19.684656Z","title":"Peer loss functions: Learning from noisy labels without knowing noise rates","venue":null,"work_id":"39f75204-4abf-4ed4-8044-e1aace6308d6","year":2020},"citing_paper":{"arxiv_id":"2505.16149","last_updated":"2025-05-22T02:47:36Z","snapshot_observed_at":"2026-08-07T15:04:05.913617Z","submitted_at":"2025-05-22T02:47:36Z","title":"When VLMs Meet Image Classification: Test Sets Renovation via Missing Label Identification","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T15:10:09.555204Z"},"links":{"citing_paper":"/paper/2505.16149"},"observation_digest":"sha256:31f238fff1c4ef2d209bc4c3bd25bf604d28abefc1153220d8d90be4c5451933","observation_id":"34ab41c4-67d5-4b72-b9d2-761b4500d150","resolution":{"observed_at":"2026-08-07T15:10:19.689195Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:10:19.622406Z","title":"Normalized loss functions for deep learning with noisy labels","venue":null,"work_id":"6373f4fd-f5f5-44cd-8aa6-63d87188cf52","year":2020},"citing_paper":{"arxiv_id":"2505.16149","last_updated":"2025-05-22T02:47:36Z","snapshot_observed_at":"2026-08-07T15:04:05.913617Z","submitted_at":"2025-05-22T02:47:36Z","title":"When VLMs Meet Image Classification: Test Sets Renovation via Missing Label Identification","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T15:10:09.636034Z"},"links":{"citing_paper":"/paper/2505.16149"},"observation_digest":"sha256:21f9487526a54480e2a7518fe8342ce786da7d2f30572ff0b5b11e849b85d534","observation_id":"3adf3b09-f40f-4588-a053-07031cde3b63","resolution":{"observed_at":"2026-08-07T15:10:19.676484Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2209.01314","last_updated":"2022-09-03T02:44:07Z","snapshot_observed_at":"2026-07-06T13:48:27.542590Z","submitted_at":"2022-09-03T02:44:07Z","title":"Label Structure Preserving Contrastive Embedding for Multi-Label Learning with Missing Labels","version":1},"cited_work":{"arxiv_id":"2209.01314","doi":null,"metadata_source":"pith","pith_arxiv_id":"2209.01314","snapshot_observed_at":"2026-08-07T15:10:13.706888Z","title":"Label Structure Preserving Contrastive Embedding for Multi-Label Learning with Missing Labels","venue":"cs.CV","work_id":"f868e019-0808-407c-bf84-f7a258d4a383","year":2022},"citing_paper":{"arxiv_id":"2505.16149","last_updated":"2025-05-22T02:47:36Z","snapshot_observed_at":"2026-08-07T15:04:05.913617Z","submitted_at":"2025-05-22T02:47:36Z","title":"When VLMs Meet Image Classification: Test Sets Renovation via Missing Label Identification","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T15:10:09.727733Z"},"links":{"cited_paper":"/paper/2209.01314","citing_paper":"/paper/2505.16149"},"observation_digest":"sha256:987a315a33365cd7b7be815b26a33fd44cdad615a4bdce0043882c4bc15ee5cc","observation_id":"8a11cefe-315e-4b77-9858-c95b198e69e1","resolution":{"observed_at":"2026-08-07T15:10:13.840314Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:10:19.314413Z","title":"Learning with noisy labels","venue":null,"work_id":"4f0cb311-23f7-47a2-b9eb-bf19d677c82f","year":2013},"citing_paper":{"arxiv_id":"2505.16149","last_updated":"2025-05-22T02:47:36Z","snapshot_observed_at":"2026-08-07T15:04:05.913617Z","submitted_at":"2025-05-22T02:47:36Z","title":"When VLMs Meet Image Classification: Test Sets Renovation via Missing Label Identification","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T15:10:09.877260Z"},"links":{"citing_paper":"/paper/2505.16149"},"observation_digest":"sha256:4b3eb4c7464f4a68cd35e52ac3a8f0d2029ac20477b9e723b7ac5ad1ba2f7e78","observation_id":"89187f11-ee59-42c1-bf94-e4bae83775b7","resolution":{"observed_at":"2026-08-07T15:10:19.556065Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:10:09.989225Z","title":"Confident learning: Estimating uncertainty in dataset labels.Journal of Artificial Intelligence Research, 70:1373–1411, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.16149","last_updated":"2025-05-22T02:47:36Z","snapshot_observed_at":"2026-08-07T15:04:05.913617Z","submitted_at":"2025-05-22T02:47:36Z","title":"When VLMs Meet Image Classification: Test Sets Renovation via Missing Label Identification","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T15:10:09.989225Z"},"links":{"citing_paper":"/paper/2505.16149"},"observation_digest":"sha256:cb245dfbb8e6c55d787c1f02e9b7abbfb167b3db754032211f2e52364d0fccd3","observation_id":"28cbb655-d390-46f7-a484-66fea9370ff0","resolution":{"observed_at":"2026-08-07T15:10:09.989225Z","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":"2026-08-07T15:10:18.974613Z","title":"Northcutt, Anish Athalye, and Jonas Mueller","venue":null,"work_id":"7002f500-97dc-41d2-8ae8-3688f1c22006","year":2021},"citing_paper":{"arxiv_id":"2505.16149","last_updated":"2025-05-22T02:47:36Z","snapshot_observed_at":"2026-08-07T15:04:05.913617Z","submitted_at":"2025-05-22T02:47:36Z","title":"When VLMs Meet Image Classification: Test Sets Renovation via Missing Label Identification","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T15:10:10.083742Z"},"links":{"citing_paper":"/paper/2505.16149"},"observation_digest":"sha256:1008f842abb25c428488c47f7efad7456eca017f7a3707d1ad5307b5ba9c6f9f","observation_id":"0ddd2e76-91d3-43a4-9bc2-e9d4c495ebfa","resolution":{"observed_at":"2026-08-07T15:10:19.076565Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2103.14749","last_updated":"2021-11-07T13:04:04Z","snapshot_observed_at":"2026-08-04T22:08:50.379039Z","submitted_at":"2021-03-26T21:54:36Z","title":"Pervasive Label Errors in Test Sets Destabilize Machine Learning Benchmarks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.14749","snapshot_observed_at":"2026-08-07T15:10:10.178439Z","title":"Pervasive label errors in test sets destabilize machine learning benchmarks.arXiv preprint arXiv:2103.14749, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.16149","last_updated":"2025-05-22T02:47:36Z","snapshot_observed_at":"2026-08-07T15:04:05.913617Z","submitted_at":"2025-05-22T02:47:36Z","title":"When VLMs Meet Image Classification: Test Sets Renovation via Missing Label Identification","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T15:10:10.178439Z"},"links":{"cited_paper":"/paper/2103.14749","citing_paper":"/paper/2505.16149"},"observation_digest":"sha256:21d2ad7a21039adf38ae0e976161b01cbba4b80f8957a15500b9dd9d4c82d4ab","observation_id":"44cd219f-29c8-47d5-bc64-9c0ee8395bae","resolution":{"observed_at":"2026-08-07T15:10:10.178439Z","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":"2026-08-07T15:10:10.271754Z","title":"Learning transferable visual models from natural language supervision","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.16149","last_updated":"2025-05-22T02:47:36Z","snapshot_observed_at":"2026-08-07T15:04:05.913617Z","submitted_at":"2025-05-22T02:47:36Z","title":"When VLMs Meet Image Classification: Test Sets Renovation via Missing Label Identification","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T15:10:10.271754Z"},"links":{"citing_paper":"/paper/2505.16149"},"observation_digest":"sha256:17090bf32e27de304be8cb2a15fe36affd63607dfc45c38ff691d20c1d333675","observation_id":"05353be6-f5c1-4cb9-be3e-5a211a843ae6","resolution":{"observed_at":"2026-08-07T15:10:10.271754Z","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":"2026-08-07T15:10:10.397262Z","title":"Learning from noisy labels by regularized estimation of annotator confusion","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.16149","last_updated":"2025-05-22T02:47:36Z","snapshot_observed_at":"2026-08-07T15:04:05.913617Z","submitted_at":"2025-05-22T02:47:36Z","title":"When VLMs Meet Image Classification: Test Sets Renovation via Missing Label Identification","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T15:10:10.397262Z"},"links":{"citing_paper":"/paper/2505.16149"},"observation_digest":"sha256:56a9e369ac9a98d0be7ff3f3b9e3875cfdd6a9109844eaea2df5f1361be6dbb6","observation_id":"6c2b9fe4-e065-4de5-a576-e95b1239c191","resolution":{"observed_at":"2026-08-07T15:10:10.397262Z","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":"2026-08-07T15:10:18.925554Z","title":"Policy learning using weak supervision.Advances in Neural Information Processing Systems, 34, 2021","venue":null,"work_id":"9dacb54f-e04d-49dd-8232-e8e1dd5e06e3","year":2021},"citing_paper":{"arxiv_id":"2505.16149","last_updated":"2025-05-22T02:47:36Z","snapshot_observed_at":"2026-08-07T15:04:05.913617Z","submitted_at":"2025-05-22T02:47:36Z","title":"When VLMs Meet Image Classification: Test Sets Renovation via Missing Label Identification","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T15:10:10.496241Z"},"links":{"citing_paper":"/paper/2505.16149"},"observation_digest":"sha256:e9ec677704feb68248bc0e2992b5cb9b2cc2ba6191b7f63bfff89c7ca425bb94","observation_id":"f2d29e77-6dc6-4371-b4bc-40aecf0a1dc8","resolution":{"observed_at":"2026-08-07T15:10:18.943972Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:10:18.681021Z","title":"Symmetric cross entropy for robust learning with noisy labels","venue":null,"work_id":"3baf2a9f-5335-40cb-bf64-64ca908ddff4","year":2019},"citing_paper":{"arxiv_id":"2505.16149","last_updated":"2025-05-22T02:47:36Z","snapshot_observed_at":"2026-08-07T15:04:05.913617Z","submitted_at":"2025-05-22T02:47:36Z","title":"When VLMs Meet Image Classification: Test Sets Renovation via Missing Label Identification","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T15:10:10.628669Z"},"links":{"citing_paper":"/paper/2505.16149"},"observation_digest":"sha256:7b981601b28d33bbf9ca5cb6cadbd39d5145ab180a3721a227cce00c8cae9316","observation_id":"88eda010-595e-485a-924a-af2f4f185ceb","resolution":{"observed_at":"2026-08-07T15:10:18.825424Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:10:18.532930Z","title":"Combating noisy labels by agreement: A joint training method with co-regularization","venue":null,"work_id":"4ca0b5ed-a683-4ce0-bc6a-a9db56ce1843","year":2020},"citing_paper":{"arxiv_id":"2505.16149","last_updated":"2025-05-22T02:47:36Z","snapshot_observed_at":"2026-08-07T15:04:05.913617Z","submitted_at":"2025-05-22T02:47:36Z","title":"When VLMs Meet Image Classification: Test Sets Renovation via Missing Label Identification","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T15:10:10.799805Z"},"links":{"citing_paper":"/paper/2505.16149"},"observation_digest":"sha256:a5a7d80a6c6b29b09792545c58db27ab67a7c4aadb15feb3289051a3bfb94f60","observation_id":"3e095e30-a355-46a7-9e01-f07b199fdda6","resolution":{"observed_at":"2026-08-07T15:10:18.596349Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:10:18.263779Z","title":"Open-set label noise can improve robustness against inherent label noise.Advances in Neural Information Processing Systems, 34, 2021","venue":null,"work_id":"aed83e4f-aa50-44ae-9aa8-99aac7b2f831","year":2021},"citing_paper":{"arxiv_id":"2505.16149","last_updated":"2025-05-22T02:47:36Z","snapshot_observed_at":"2026-08-07T15:04:05.913617Z","submitted_at":"2025-05-22T02:47:36Z","title":"When VLMs Meet Image Classification: Test Sets Renovation via Missing Label Identification","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T15:10:10.926462Z"},"links":{"citing_paper":"/paper/2505.16149"},"observation_digest":"sha256:220e593f5ac3603cceec3651b06dc55e15de16c2f261f79b70f679ea956f9593","observation_id":"d7fdcfb5-84f6-41d5-a145-24212c7ecde7","resolution":{"observed_at":"2026-08-07T15:10:18.373746Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:10:11.097295Z","title":"To smooth or not? when label smoothing meets noisy labels","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.16149","last_updated":"2025-05-22T02:47:36Z","snapshot_observed_at":"2026-08-07T15:04:05.913617Z","submitted_at":"2025-05-22T02:47:36Z","title":"When VLMs Meet Image Classification: Test Sets Renovation via Missing Label Identification","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T15:10:11.097295Z"},"links":{"citing_paper":"/paper/2505.16149"},"observation_digest":"sha256:a5e62241e93ea6c5c63e898348a870b2189302649728fe3958ff6d8ca0cb7005","observation_id":"d8c35e1d-5537-4855-a38f-fb810b12c63f","resolution":{"observed_at":"2026-08-07T15:10:11.097295Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2011.03687","last_updated":"2021-08-18T20:49:13Z","snapshot_observed_at":"2026-08-02T09:17:39.599426Z","submitted_at":"2020-11-07T04:31:33Z","title":"When Optimizing $f$-divergence is Robust with Label Noise","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2011.03687","snapshot_observed_at":"2026-08-07T15:10:11.195032Z","title":"When optimizing f-divergence is robust with label noise.arXiv preprint arXiv:2011.03687, 2020","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2505.16149","last_updated":"2025-05-22T02:47:36Z","snapshot_observed_at":"2026-08-07T15:04:05.913617Z","submitted_at":"2025-05-22T02:47:36Z","title":"When VLMs Meet Image Classification: Test Sets Renovation via Missing Label Identification","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T15:10:11.195032Z"},"links":{"cited_paper":"/paper/2011.03687","citing_paper":"/paper/2505.16149"},"observation_digest":"sha256:c37ff5f8cb28ff5b13c0788657e2da3b0de4c05228e2c4411ea46664f337884c","observation_id":"7369f625-704c-4374-9e58-c03f7e205b67","resolution":{"observed_at":"2026-08-07T15:10:11.195032Z","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":"2026-08-07T15:10:15.558428Z","title":"Distributionally robust post-hoc classifiers under prior shifts","venue":null,"work_id":"a65610f2-3048-4119-93e0-0c0a7b2455d1","year":2023},"citing_paper":{"arxiv_id":"2505.16149","last_updated":"2025-05-22T02:47:36Z","snapshot_observed_at":"2026-08-07T15:04:05.913617Z","submitted_at":"2025-05-22T02:47:36Z","title":"When VLMs Meet Image Classification: Test Sets Renovation via Missing Label Identification","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T15:10:11.327504Z"},"links":{"citing_paper":"/paper/2505.16149"},"observation_digest":"sha256:3ea87c651f204265378eef344a357d645c277f90100d2998b6402b14a576b270","observation_id":"6dc4ecb3-c002-4e29-82b8-8af3d825ac32","resolution":{"observed_at":"2026-08-07T15:10:17.266126Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.12088","last_updated":"2022-03-27T06:51:57Z","snapshot_observed_at":"2026-07-06T12:00:53.862881Z","submitted_at":"2021-10-22T22:42:11Z","title":"Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotations","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.12088","snapshot_observed_at":"2026-08-07T15:10:11.464051Z","title":"Learning with noisy labels revisited: A study using real-world human annotations.arXiv preprint arXiv:2110.12088, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.16149","last_updated":"2025-05-22T02:47:36Z","snapshot_observed_at":"2026-08-07T15:04:05.913617Z","submitted_at":"2025-05-22T02:47:36Z","title":"When VLMs Meet Image Classification: Test Sets Renovation via Missing Label Identification","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T15:10:11.464051Z"},"links":{"cited_paper":"/paper/2110.12088","citing_paper":"/paper/2505.16149"},"observation_digest":"sha256:6c1f778bcc68f8f3a667885d1000e1439262383fbe23809f3f942a04462cc6fb","observation_id":"fff03e6f-efb9-46e4-9917-c63d21c172e5","resolution":{"observed_at":"2026-08-07T15:10:11.464051Z","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":"2026-08-07T15:10:15.319822Z","title":"To aggregate or not? learning with separate noisy labels","venue":null,"work_id":"eac51131-cb1e-4d0b-a7e8-34c11df5544a","year":2023},"citing_paper":{"arxiv_id":"2505.16149","last_updated":"2025-05-22T02:47:36Z","snapshot_observed_at":"2026-08-07T15:04:05.913617Z","submitted_at":"2025-05-22T02:47:36Z","title":"When VLMs Meet Image Classification: Test Sets Renovation via Missing Label Identification","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T15:10:11.668401Z"},"links":{"citing_paper":"/paper/2505.16149"},"observation_digest":"sha256:16d91d55f4692a57f7b5b3e4abe3fcd6f9e405c8819b868fbaa790ff09feb4f8","observation_id":"d653ab22-961d-4229-9e83-08337bb27bba","resolution":{"observed_at":"2026-08-07T15:10:15.383805Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.12291","last_updated":"2023-03-22T03:46:51Z","snapshot_observed_at":"2026-08-05T07:35:03.548322Z","submitted_at":"2023-03-22T03:46:51Z","title":"Fairness Improves Learning from Noisily Labeled Long-Tailed Data","version":1},"cited_work":{"arxiv_id":"2303.12291","doi":null,"metadata_source":"pith","pith_arxiv_id":"2303.12291","snapshot_observed_at":"2026-08-07T15:10:13.415873Z","title":"Fairness Improves Learning from Noisily Labeled Long-Tailed Data","venue":"cs.LG","work_id":"3fe9ab11-8a93-469c-997d-722c940236ee","year":2023},"citing_paper":{"arxiv_id":"2505.16149","last_updated":"2025-05-22T02:47:36Z","snapshot_observed_at":"2026-08-07T15:04:05.913617Z","submitted_at":"2025-05-22T02:47:36Z","title":"When VLMs Meet Image Classification: Test Sets Renovation via Missing Label Identification","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-07T15:10:11.848877Z"},"links":{"cited_paper":"/paper/2303.12291","citing_paper":"/paper/2505.16149"},"observation_digest":"sha256:3f13787127edba984de8a9e7fa9b6bac068a1d8e0c89eb5c044435a68c5368e3","observation_id":"f8e74cf1-6b44-4751-9924-3ac1349b9188","resolution":{"observed_at":"2026-08-07T15:10:13.575149Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:10:15.143236Z","title":"Vision- language models are strong noisy label detectors.Advances in Neural Information Processing Systems, 37:58154–58173, 2024","venue":null,"work_id":"9324841e-0f3f-4f22-b466-abb756cd55a4","year":2024},"citing_paper":{"arxiv_id":"2505.16149","last_updated":"2025-05-22T02:47:36Z","snapshot_observed_at":"2026-08-07T15:04:05.913617Z","submitted_at":"2025-05-22T02:47:36Z","title":"When VLMs Meet Image Classification: Test Sets Renovation via Missing Label Identification","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-07T15:10:12.019987Z"},"links":{"citing_paper":"/paper/2505.16149"},"observation_digest":"sha256:c547eba804667bc3d11586a56e039a42d73824e2165887d271ddbcf024bd439e","observation_id":"c697762b-48db-4af5-9901-42f62a742f56","resolution":{"observed_at":"2026-08-07T15:10:15.219455Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:10:14.854112Z","title":"iclip: Bridging image classification and contrastive language-image pre-training for visual recognition","venue":null,"work_id":"e8804bd8-3c7f-4f22-ab2a-aac63f283a92","year":2023},"citing_paper":{"arxiv_id":"2505.16149","last_updated":"2025-05-22T02:47:36Z","snapshot_observed_at":"2026-08-07T15:04:05.913617Z","submitted_at":"2025-05-22T02:47:36Z","title":"When VLMs Meet Image Classification: Test Sets Renovation via Missing Label Identification","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-07T15:10:12.144349Z"},"links":{"citing_paper":"/paper/2505.16149"},"observation_digest":"sha256:5ee2f95a5cc3ab116d0cc7b7d98690f25d129f7d72ba286fd7945ebc52994f5d","observation_id":"d8f9f345-fe27-45d3-a83d-0439145e011d","resolution":{"observed_at":"2026-08-07T15:10:14.965188Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.13848","last_updated":"2024-10-17T17:58:37Z","snapshot_observed_at":"2026-08-03T03:16:45.693966Z","submitted_at":"2024-10-17T17:58:37Z","title":"Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.13848","snapshot_observed_at":"2026-08-07T15:10:12.279954Z","title":"Janus: Decoupling visual encoding for unified multimodal understanding and generation.arXiv preprint arXiv:2410.13848, 2024","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.16149","last_updated":"2025-05-22T02:47:36Z","snapshot_observed_at":"2026-08-07T15:04:05.913617Z","submitted_at":"2025-05-22T02:47:36Z","title":"When VLMs Meet Image Classification: Test Sets Renovation via Missing Label Identification","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-07T15:10:12.279954Z"},"links":{"cited_paper":"/paper/2410.13848","citing_paper":"/paper/2505.16149"},"observation_digest":"sha256:e9716667cd23b2467c64cecf1d20d8dfb347152b27ee135853ed61967f5efe95","observation_id":"b2176df7-c402-4bce-838f-a6d5b1dccc79","resolution":{"observed_at":"2026-08-07T15:10:12.279954Z","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":"2026-08-07T15:10:14.638668Z","title":"Are anchor points really indispensable in label-noise learning?Advances in Neural Information Processing Systems, 32, 2019","venue":null,"work_id":"1a908217-1c99-4ca1-84c2-f3153b31bd3b","year":2019},"citing_paper":{"arxiv_id":"2505.16149","last_updated":"2025-05-22T02:47:36Z","snapshot_observed_at":"2026-08-07T15:04:05.913617Z","submitted_at":"2025-05-22T02:47:36Z","title":"When VLMs Meet Image Classification: Test Sets Renovation via Missing Label Identification","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-07T15:10:12.467084Z"},"links":{"citing_paper":"/paper/2505.16149"},"observation_digest":"sha256:94afc2b12c70add100e0ebfc9ec41162441046a75f575c1ccb9309ed5867c5f4","observation_id":"bfd973bd-80f8-46f0-929f-3f0b1bf6c901","resolution":{"observed_at":"2026-08-07T15:10:14.755349Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2111.07783","last_updated":"2021-11-09T17:15:38Z","snapshot_observed_at":"2026-07-06T12:08:35.761426Z","submitted_at":"2021-11-09T17:15:38Z","title":"FILIP: Fine-grained Interactive Language-Image Pre-Training","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2111.07783","snapshot_observed_at":"2026-08-07T15:10:12.558456Z","title":"Filip: Fine-grained interactive language-image pre-training.arXiv preprint arXiv:2111.07783, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.16149","last_updated":"2025-05-22T02:47:36Z","snapshot_observed_at":"2026-08-07T15:04:05.913617Z","submitted_at":"2025-05-22T02:47:36Z","title":"When VLMs Meet Image Classification: Test Sets Renovation via Missing Label Identification","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-07T15:10:12.558456Z"},"links":{"cited_paper":"/paper/2111.07783","citing_paper":"/paper/2505.16149"},"observation_digest":"sha256:8263340f21de6860cba9c2685a2149b68593e73492bc931fa7eff8bb613310dc","observation_id":"6335e2a4-9f40-4714-829a-2ea7718e1101","resolution":{"observed_at":"2026-08-07T15:10:12.558456Z","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":"2026-08-07T15:10:14.453957Z","title":"How does disagreement help generalization against label corruption? InInternational Conference on Machine Learning, pages 7164–7173","venue":null,"work_id":"4d8fef63-38db-4b31-9cf9-96d7183aea1d","year":2019},"citing_paper":{"arxiv_id":"2505.16149","last_updated":"2025-05-22T02:47:36Z","snapshot_observed_at":"2026-08-07T15:04:05.913617Z","submitted_at":"2025-05-22T02:47:36Z","title":"When VLMs Meet Image Classification: Test Sets Renovation via Missing Label Identification","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-07T15:10:12.598796Z"},"links":{"citing_paper":"/paper/2505.16149"},"observation_digest":"sha256:c2d278fbfdb27adbc1172d3abafd3f931a784546d4d17cf94a64a173767cc2b5","observation_id":"b523da12-5eab-408b-a5d4-b53a5275c552","resolution":{"observed_at":"2026-08-07T15:10:14.523290Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:10:12.697369Z","title":"Lit: Zero-shot transfer with locked-image text tuning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.16149","last_updated":"2025-05-22T02:47:36Z","snapshot_observed_at":"2026-08-07T15:04:05.913617Z","submitted_at":"2025-05-22T02:47:36Z","title":"When VLMs Meet Image Classification: Test Sets Renovation via Missing Label Identification","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-07T15:10:12.697369Z"},"links":{"citing_paper":"/paper/2505.16149"},"observation_digest":"sha256:b530182be09e26827d4eb4e81029d384afd91f788407dce9cf4a8172ce60876d","observation_id":"60d5cab3-2639-4515-9a3d-aef77bfe0040","resolution":{"observed_at":"2026-08-07T15:10:12.697369Z","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":"2026-08-07T15:10:14.276401Z","title":"Learning in imperfect environment: Multi-label classification with long-tailed distribution and partial labels","venue":null,"work_id":"af4dcdd6-92f5-49b9-8bbb-c55e48624fc5","year":2023},"citing_paper":{"arxiv_id":"2505.16149","last_updated":"2025-05-22T02:47:36Z","snapshot_observed_at":"2026-08-07T15:04:05.913617Z","submitted_at":"2025-05-22T02:47:36Z","title":"When VLMs Meet Image Classification: Test Sets Renovation via Missing Label Identification","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-07T15:10:12.839082Z"},"links":{"citing_paper":"/paper/2505.16149"},"observation_digest":"sha256:e347e104fd65d9f547e852c17704c407a4557516dc9d69eb6026e21df2839303","observation_id":"01dd9641-0e53-4b4a-ac50-2471b1ef8c2f","resolution":{"observed_at":"2026-08-07T15:10:14.361480Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:10:12.961360Z","title":"Conditional prompt learning for vision-language models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.16149","last_updated":"2025-05-22T02:47:36Z","snapshot_observed_at":"2026-08-07T15:04:05.913617Z","submitted_at":"2025-05-22T02:47:36Z","title":"When VLMs Meet Image Classification: Test Sets Renovation via Missing Label Identification","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-07T15:10:12.961360Z"},"links":{"citing_paper":"/paper/2505.16149"},"observation_digest":"sha256:2abb597959c281bd5b43f36383593b3f0529e2db987365b02223849dfd56d81c","observation_id":"70761e1b-5107-4bcc-b438-6409042976df","resolution":{"observed_at":"2026-08-07T15:10:12.961360Z","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":"2026-08-07T15:10:14.066872Z","title":"Clusterability as an alternative to anchor points when learning with noisy labels","venue":null,"work_id":"9b7aa9df-86f8-4bb7-8c1c-8469610da633","year":2021},"citing_paper":{"arxiv_id":"2505.16149","last_updated":"2025-05-22T02:47:36Z","snapshot_observed_at":"2026-08-07T15:04:05.913617Z","submitted_at":"2025-05-22T02:47:36Z","title":"When VLMs Meet Image Classification: Test Sets Renovation via Missing Label Identification","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-07T15:10:13.127295Z"},"links":{"citing_paper":"/paper/2505.16149"},"observation_digest":"sha256:a9382dd28d402f3a48d7f4e25e32b5636007f60e57c65c9415727803ea7d68f9","observation_id":"f68fd159-20da-4ed9-9f3c-3b13c6306094","resolution":{"observed_at":"2026-08-07T15:10:14.149868Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2311.11202","last_updated":"2024-03-24T22:02:47Z","snapshot_observed_at":"2026-07-06T16:49:33.776407Z","submitted_at":"2023-11-19T02:34:12Z","title":"Unmasking and Improving Data Credibility: A Study with Datasets for Training Harmless Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.11202","snapshot_observed_at":"2026-08-07T15:10:13.252061Z","title":"Unmasking and improving data credibility: A study with datasets for training harmless language models.arXiv preprint arXiv:2311.11202, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.16149","last_updated":"2025-05-22T02:47:36Z","snapshot_observed_at":"2026-08-07T15:04:05.913617Z","submitted_at":"2025-05-22T02:47:36Z","title":"When VLMs Meet Image Classification: Test Sets Renovation via Missing Label Identification","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-07T15:10:13.252061Z"},"links":{"cited_paper":"/paper/2311.11202","citing_paper":"/paper/2505.16149"},"observation_digest":"sha256:f2fc4d35d5b8edbdfadf824624eaf5996c9bd2e3199f266f12c49244e8baf1da","observation_id":"72d5a0e0-35b0-49dd-8837-17c29dd6b31c","resolution":{"observed_at":"2026-08-07T15:10:13.252061Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2505.16149","last_updated":"2025-05-22T02:47:36Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-07T15:04:05.913617Z","submitted_at":"2025-05-22T02:47:36Z","title":"When VLMs Meet Image Classification: Test Sets Renovation via Missing Label Identification"},"reference_resolution":{"displayed":57,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":29,"verified_exact":2,"verified_fuzzy":26},"total_outbound_references":57},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 57 of 57 outbound references and 1 inbound Pith citation observation for arXiv:2505.16149."}