{"as_of":"2026-08-09T23:32:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:b7ea2b9f4af4056ec7e85e0685c038d6cb85d1e595c2f57520ff827cf803cb26","coverage":[{"denominator":60,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":60,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-16T15:22:35.204623Z","state":"measured"},{"denominator":60,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":60,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+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/2601.09746/citation-record","integrity":"/paper/2601.09746/integrity","json":"/paper/2601.09746/citation-record.json","paper":"/paper/2601.09746"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"LLM2Vec: Large language models are secretly powerful text encoders","venue":null,"work_id":"faf8b0a7-0e60-4446-87e9-0dfa65108471","year":2024},"citing_paper":{"arxiv_id":"2601.09746","last_updated":"2026-01-11T20:36:47Z","snapshot_observed_at":"2026-08-09T00:07:01.447972Z","submitted_at":"2026-01-11T20:36:47Z","title":"Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD Concepts","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-16T15:22:35.204623Z"},"links":{"citing_paper":"/paper/2601.09746"},"observation_digest":"sha256:6e99e4c1695c91f1376ba3c207ca1fb6b00158c7a414a3ff9db12609627826c1","observation_id":"6e2e8eea-796d-4368-8b41-c56caa12cd8a","resolution":{"observed_at":"2026-05-16T15:23:02.162468Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Internvl: Scal- ing up vision foundation models and aligning for generic visual-linguistic tasks","venue":null,"work_id":"a65d7d03-3db3-48db-b4d0-a931d46b670d","year":2024},"citing_paper":{"arxiv_id":"2601.09746","last_updated":"2026-01-11T20:36:47Z","snapshot_observed_at":"2026-08-09T00:07:01.447972Z","submitted_at":"2026-01-11T20:36:47Z","title":"Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD Concepts","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-16T15:22:35.204623Z"},"links":{"citing_paper":"/paper/2601.09746"},"observation_digest":"sha256:d4cc916cbdbe8483f1c4f4d827c885d4b103b67d48f7d75c6f3808d59d6f7855","observation_id":"f9dccdfe-4216-49d4-b713-44424d83a2f5","resolution":{"observed_at":"2026-05-16T15:23:02.237918Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Reproducible scaling laws for contrastive language-image learning","venue":null,"work_id":"579af6a2-c392-4162-88b0-c6ca171da500","year":2023},"citing_paper":{"arxiv_id":"2601.09746","last_updated":"2026-01-11T20:36:47Z","snapshot_observed_at":"2026-08-09T00:07:01.447972Z","submitted_at":"2026-01-11T20:36:47Z","title":"Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD Concepts","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-16T15:22:35.204623Z"},"links":{"citing_paper":"/paper/2601.09746"},"observation_digest":"sha256:2eadb198c10186261ae242e78f0a40cc76cc8e13d21cbe8019b86aa55d56c562","observation_id":"2625b4d0-cc90-4148-a31f-a0ea6ef61f4e","resolution":{"observed_at":"2026-05-16T15:23:02.160199Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"The case for human–AI interaction as system 0 thinking.Nature Human Behaviour, 8(10):1829–1830","venue":null,"work_id":"2134e4e5-9d9f-4583-a981-9757daf7f77e","year":2024},"citing_paper":{"arxiv_id":"2601.09746","last_updated":"2026-01-11T20:36:47Z","snapshot_observed_at":"2026-08-09T00:07:01.447972Z","submitted_at":"2026-01-11T20:36:47Z","title":"Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD Concepts","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-16T15:22:35.204623Z"},"links":{"citing_paper":"/paper/2601.09746"},"observation_digest":"sha256:1358db9d00bc958e8dd41ea2c233af73f8f8cdae25ff3d3e1b23f8771d268513","observation_id":"63c6293e-a0b7-4621-a8f9-3708d5a9b720","resolution":{"observed_at":"2026-05-16T15:23:02.183516Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Distribution-aware prompt tuning for vision-language models","venue":null,"work_id":"132c3291-bc62-4ae7-9c5c-15461c403279","year":2023},"citing_paper":{"arxiv_id":"2601.09746","last_updated":"2026-01-11T20:36:47Z","snapshot_observed_at":"2026-08-09T00:07:01.447972Z","submitted_at":"2026-01-11T20:36:47Z","title":"Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD Concepts","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-16T15:22:35.204623Z"},"links":{"citing_paper":"/paper/2601.09746"},"observation_digest":"sha256:f5d2adae9f376b74cf79dd1e9280dfe108defe72942a7178c36618ef81523b80","observation_id":"d6ccb2da-6fd5-4311-b054-f2591cca8b8b","resolution":{"observed_at":"2026-05-16T15:23:02.202066Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Exploring large language models for multi-modal out-of-distribution detection","venue":null,"work_id":"5a028a81-925c-419d-9d7d-fe311daf2cda","year":2023},"citing_paper":{"arxiv_id":"2601.09746","last_updated":"2026-01-11T20:36:47Z","snapshot_observed_at":"2026-08-09T00:07:01.447972Z","submitted_at":"2026-01-11T20:36:47Z","title":"Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD Concepts","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-16T15:22:35.204623Z"},"links":{"citing_paper":"/paper/2601.09746"},"observation_digest":"sha256:a312b04855681bf64757322ad7bd4d507c35e2c618167e69a067453f6cc6ab8c","observation_id":"257b2f58-219b-4707-8850-d367bebea814","resolution":{"observed_at":"2026-05-16T15:23:02.146846Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Qlora: Efficient finetuning of quan- tized llms","venue":null,"work_id":"7dd44b8d-4ec5-47e1-a592-dbdacb588413","year":2023},"citing_paper":{"arxiv_id":"2601.09746","last_updated":"2026-01-11T20:36:47Z","snapshot_observed_at":"2026-08-09T00:07:01.447972Z","submitted_at":"2026-01-11T20:36:47Z","title":"Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD Concepts","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-16T15:22:35.204623Z"},"links":{"citing_paper":"/paper/2601.09746"},"observation_digest":"sha256:dba2c69b9e6e92777c1c9b66740ef271d3b8eae1d605d3434bbe74d4500eb658","observation_id":"9d979047-2322-4bb7-8839-c9ef64d7f547","resolution":{"observed_at":"2026-05-16T15:23:02.176299Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Unveiling encoder- free vision-language models","venue":null,"work_id":"5f510408-962e-49c8-abc7-b8966b8a8b89","year":2024},"citing_paper":{"arxiv_id":"2601.09746","last_updated":"2026-01-11T20:36:47Z","snapshot_observed_at":"2026-08-09T00:07:01.447972Z","submitted_at":"2026-01-11T20:36:47Z","title":"Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD Concepts","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-16T15:22:35.204623Z"},"links":{"citing_paper":"/paper/2601.09746"},"observation_digest":"sha256:4560071737d93d6ec191118ced62915ba6fe98b2f79e4293b71bc956b880821c","observation_id":"6e9e945e-d466-4e30-900a-527bf5e2e8ab","resolution":{"observed_at":"2026-05-16T15:23:02.221369Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"A survey on in-context learning","venue":null,"work_id":"e295e93c-4e2c-4f27-bd55-38632cb95d14","year":null},"citing_paper":{"arxiv_id":"2601.09746","last_updated":"2026-01-11T20:36:47Z","snapshot_observed_at":"2026-08-09T00:07:01.447972Z","submitted_at":"2026-01-11T20:36:47Z","title":"Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD Concepts","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-16T15:22:35.204623Z"},"links":{"citing_paper":"/paper/2601.09746"},"observation_digest":"sha256:300efc89eef63fee082a09db6c1339a09ba80945c4154c7330ebb54022933051","observation_id":"cf1a2418-de86-4ba0-8669-0e3b96c97e46","resolution":{"observed_at":"2026-05-16T15:23:02.225202Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"CCG: Rare-label prediction via neu- ral SEM–driven causal game","venue":null,"work_id":"7a73ecbf-e015-4195-a21d-edf0bf160503","year":2025},"citing_paper":{"arxiv_id":"2601.09746","last_updated":"2026-01-11T20:36:47Z","snapshot_observed_at":"2026-08-09T00:07:01.447972Z","submitted_at":"2026-01-11T20:36:47Z","title":"Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD Concepts","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-16T15:22:35.204623Z"},"links":{"citing_paper":"/paper/2601.09746"},"observation_digest":"sha256:417aa075d9f6bc0ee2b6929cf107da259395bff43fe5f4f6a43fcc5ce55f6796","observation_id":"49cf2a4c-a816-4917-8eec-e74ed2fddbd5","resolution":{"observed_at":"2026-05-16T15:23:02.231394Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.04544","last_updated":"2025-03-25T14:34:04Z","snapshot_observed_at":"2026-08-09T19:43:52.666104Z","submitted_at":"2021-10-09T11:39:30Z","title":"CLIP-Adapter: Better Vision-Language Models with Feature Adapters","version":2},"cited_work":{"arxiv_id":"2110.04544","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2110.04544","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Clip-adapter: Better vision-language models with feature adapters","venue":null,"work_id":"27d73cce-f5b6-4e7e-9173-584dd7fb6cfc","year":2021},"citing_paper":{"arxiv_id":"2601.09746","last_updated":"2026-01-11T20:36:47Z","snapshot_observed_at":"2026-08-09T00:07:01.447972Z","submitted_at":"2026-01-11T20:36:47Z","title":"Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD Concepts","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-16T15:22:35.204623Z"},"links":{"cited_paper":"/paper/2110.04544","citing_paper":"/paper/2601.09746"},"observation_digest":"sha256:23e20b5ad387fd96c95397d27e4cf7686df9c55f7a0ebc5a0597a22ac6e1e1c4","observation_id":"79b66bf9-aea1-449c-a6a8-283d765ac7da","resolution":{"observed_at":"2026-05-16T15:23:01.918374Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Context encoders as a simple but powerful extension of word2vec","venue":null,"work_id":"f5273f08-d925-4bd3-af5a-60f5d64571f9","year":2017},"citing_paper":{"arxiv_id":"2601.09746","last_updated":"2026-01-11T20:36:47Z","snapshot_observed_at":"2026-08-09T00:07:01.447972Z","submitted_at":"2026-01-11T20:36:47Z","title":"Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD Concepts","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-16T15:22:35.204623Z"},"links":{"citing_paper":"/paper/2601.09746"},"observation_digest":"sha256:59062fb17a6a9b595e3b75f95f158de43d1e2dc3d89b1fef1821978be2af4b9a","observation_id":"9e9ee1ad-8538-4d75-91e2-90463c4fe7e7","resolution":{"observed_at":"2026-05-16T15:23:02.169067Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Parameter-efficient transfer learning for nlp","venue":null,"work_id":"c19675b6-2d59-4f24-a3f1-983fe481d0c3","year":2019},"citing_paper":{"arxiv_id":"2601.09746","last_updated":"2026-01-11T20:36:47Z","snapshot_observed_at":"2026-08-09T00:07:01.447972Z","submitted_at":"2026-01-11T20:36:47Z","title":"Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD Concepts","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-16T15:22:35.204623Z"},"links":{"citing_paper":"/paper/2601.09746"},"observation_digest":"sha256:7f814d96522c63e76749d393f5ff6662ef88b261cc7f8ae5e8a451d86badaa17","observation_id":"04da7ef7-adc0-4e5b-89f2-8e6e719e4568","resolution":{"observed_at":"2026-05-16T15:23:02.114136Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen","venue":null,"work_id":"2e1f96e8-8a9b-43bb-88f9-0c13291b290b","year":2021},"citing_paper":{"arxiv_id":"2601.09746","last_updated":"2026-01-11T20:36:47Z","snapshot_observed_at":"2026-08-09T00:07:01.447972Z","submitted_at":"2026-01-11T20:36:47Z","title":"Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD Concepts","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-16T15:22:35.204623Z"},"links":{"citing_paper":"/paper/2601.09746"},"observation_digest":"sha256:fcf9d99f0d6cf03991d362261a1400991a0c083ddd4c67f5d5338f97cde3aad3","observation_id":"a837ee34-0ce5-4739-9a53-b10d092220de","resolution":{"observed_at":"2026-05-16T15:23:02.106109Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Le, Yunhsuan Sung, Zhen Li, and Tom Duerig","venue":null,"work_id":"c87e1fb1-3cab-4e3d-af2f-bc02cf664f98","year":2021},"citing_paper":{"arxiv_id":"2601.09746","last_updated":"2026-01-11T20:36:47Z","snapshot_observed_at":"2026-08-09T00:07:01.447972Z","submitted_at":"2026-01-11T20:36:47Z","title":"Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD Concepts","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-16T15:22:35.204623Z"},"links":{"citing_paper":"/paper/2601.09746"},"observation_digest":"sha256:33c84987a22eaef5b8dcd25867abde24be9702ade6cd4399cda3c7bca5e5c0a5","observation_id":"26eb4722-f348-41fb-854e-57eb76abc5fc","resolution":{"observed_at":"2026-05-16T15:23:02.164577Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Visual prompt tuning","venue":null,"work_id":"94cb8735-b780-4dc7-833c-6928dddeaa83","year":2022},"citing_paper":{"arxiv_id":"2601.09746","last_updated":"2026-01-11T20:36:47Z","snapshot_observed_at":"2026-08-09T00:07:01.447972Z","submitted_at":"2026-01-11T20:36:47Z","title":"Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD Concepts","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-05-16T15:22:35.204623Z"},"links":{"citing_paper":"/paper/2601.09746"},"observation_digest":"sha256:e3539f66a07ffafe7a8506b3973272d9118be2b3cdc9b6cde9a9b857d99531fb","observation_id":"a0799031-45bf-4fea-8320-390d1c515b57","resolution":{"observed_at":"2026-05-16T15:23:02.187398Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"The power of scale for parameter-efficient prompt tuning","venue":null,"work_id":"6863a42d-4944-4b86-a4fe-2456aeaacdf2","year":null},"citing_paper":{"arxiv_id":"2601.09746","last_updated":"2026-01-11T20:36:47Z","snapshot_observed_at":"2026-08-09T00:07:01.447972Z","submitted_at":"2026-01-11T20:36:47Z","title":"Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD Concepts","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-05-16T15:22:35.204623Z"},"links":{"citing_paper":"/paper/2601.09746"},"observation_digest":"sha256:ef1d6536fd7c7ea98d57ade1bab6369c650a00c912824fc437f1ca1a9db74d0a","observation_id":"9d9c9612-ab6a-4208-baca-d581988adfac","resolution":{"observed_at":"2026-05-16T15:23:02.155114Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Selvaraju, Akhilesh Deepak Gotmare, Shafiq Joty, Caiming Xiong, and Steven Hoi","venue":null,"work_id":"d41d1d44-5fbc-4626-8e98-8deef3819c3c","year":2021},"citing_paper":{"arxiv_id":"2601.09746","last_updated":"2026-01-11T20:36:47Z","snapshot_observed_at":"2026-08-09T00:07:01.447972Z","submitted_at":"2026-01-11T20:36:47Z","title":"Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD Concepts","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-16T15:22:35.204623Z"},"links":{"citing_paper":"/paper/2601.09746"},"observation_digest":"sha256:0ac1c7c7243f7ec4d7fe13ced885b89ac8508827f2607389cae3fb3fdd881cf3","observation_id":"25ddff94-c141-471b-b667-30a76b843910","resolution":{"observed_at":"2026-05-16T15:23:02.151824Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and gener- ation","venue":null,"work_id":"15987664-be1b-4a2f-a956-a6bbb781ba02","year":2022},"citing_paper":{"arxiv_id":"2601.09746","last_updated":"2026-01-11T20:36:47Z","snapshot_observed_at":"2026-08-09T00:07:01.447972Z","submitted_at":"2026-01-11T20:36:47Z","title":"Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD Concepts","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-05-16T15:22:35.204623Z"},"links":{"citing_paper":"/paper/2601.09746"},"observation_digest":"sha256:eb4130e2281b2ec341a18b556dd5fdef37b379d43d01134857712beb54687a4b","observation_id":"a234a039-e5c2-4529-b392-2acbb3cb2782","resolution":{"observed_at":"2026-05-16T15:23:02.166991Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Im- proving the accuracy of diabetes diagnosis applica- tions through a hybrid feature selection algorithm","venue":null,"work_id":"16d165cb-9e5d-48c9-94eb-5b79a02f8060","year":2021},"citing_paper":{"arxiv_id":"2601.09746","last_updated":"2026-01-11T20:36:47Z","snapshot_observed_at":"2026-08-09T00:07:01.447972Z","submitted_at":"2026-01-11T20:36:47Z","title":"Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD Concepts","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-05-16T15:22:35.204623Z"},"links":{"citing_paper":"/paper/2601.09746"},"observation_digest":"sha256:5cd55f50718dda1b4638b47ec49acc58a30b83171d571760b62ad38d5ef25b04","observation_id":"f3f66739-32c3-40c4-9d61-120ff9c0a6a5","resolution":{"observed_at":"2026-05-16T15:23:02.227264Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Distilling large vision- language model with out-of-distribution generalizabil- ity","venue":null,"work_id":"ad53f800-14a5-4d2c-b142-96f5a8c58df4","year":2023},"citing_paper":{"arxiv_id":"2601.09746","last_updated":"2026-01-11T20:36:47Z","snapshot_observed_at":"2026-08-09T00:07:01.447972Z","submitted_at":"2026-01-11T20:36:47Z","title":"Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD Concepts","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-05-16T15:22:35.204623Z"},"links":{"citing_paper":"/paper/2601.09746"},"observation_digest":"sha256:d51f472d363e9148a49361f617836be58a3c6680358cf4b6ed182de4a65579c0","observation_id":"bf90cc97-045a-4fc4-aaa5-f04c88504b7f","resolution":{"observed_at":"2026-05-16T15:23:02.213259Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Visual instruction tuning","venue":null,"work_id":"50bceeea-34f8-4702-ab5a-3c0ffb1c7f7f","year":2023},"citing_paper":{"arxiv_id":"2601.09746","last_updated":"2026-01-11T20:36:47Z","snapshot_observed_at":"2026-08-09T00:07:01.447972Z","submitted_at":"2026-01-11T20:36:47Z","title":"Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD Concepts","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-05-16T15:22:35.204623Z"},"links":{"citing_paper":"/paper/2601.09746"},"observation_digest":"sha256:bb2d0b914f36e8b34c5c2f0d078f95578c639dc0d8a136e57719251253dedd84","observation_id":"7438f7ed-ab49-4ccc-8498-bdba14221b51","resolution":{"observed_at":"2026-05-16T15:23:02.233863Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Towards out-of- distribution generalization: A survey","venue":null,"work_id":"ac3dac7c-24d8-4dc3-a4df-eee5c7bd9937","year":2023},"citing_paper":{"arxiv_id":"2601.09746","last_updated":"2026-01-11T20:36:47Z","snapshot_observed_at":"2026-08-09T00:07:01.447972Z","submitted_at":"2026-01-11T20:36:47Z","title":"Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD Concepts","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-05-16T15:22:35.204623Z"},"links":{"citing_paper":"/paper/2601.09746"},"observation_digest":"sha256:9e5f05589433606f7b7f182dbdb217b233edecd1b0f9b3c80f86137036459ae5","observation_id":"e49a8ce3-205e-423d-9617-af4cc9560d9e","resolution":{"observed_at":"2026-05-16T15:23:02.140067Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Mta: Multimodal task alignment for bev perception and captioning","venue":null,"work_id":"72acf88a-7a31-4d77-8d55-2daa791cd361","year":2024},"citing_paper":{"arxiv_id":"2601.09746","last_updated":"2026-01-11T20:36:47Z","snapshot_observed_at":"2026-08-09T00:07:01.447972Z","submitted_at":"2026-01-11T20:36:47Z","title":"Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD Concepts","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-05-16T15:22:35.204623Z"},"links":{"citing_paper":"/paper/2601.09746"},"observation_digest":"sha256:13e788308b1bfa059d41679cb463fd5fa4e5ca9124faf484d2d04dae325e7ea3","observation_id":"02ed595e-a873-4df2-939d-7ee5bd7494bf","resolution":{"observed_at":"2026-05-16T15:23:02.235802Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Adavit: Adaptive vision transformers for efficient im- age recognition","venue":null,"work_id":"fb672a3e-02a6-4157-8291-f9695fab30b1","year":2021},"citing_paper":{"arxiv_id":"2601.09746","last_updated":"2026-01-11T20:36:47Z","snapshot_observed_at":"2026-08-09T00:07:01.447972Z","submitted_at":"2026-01-11T20:36:47Z","title":"Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD Concepts","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-05-16T15:22:35.204623Z"},"links":{"citing_paper":"/paper/2601.09746"},"observation_digest":"sha256:cb0ac3c5df3d21f2b1ae9679966ff4c68358f086cd04dfa34db4999e768f5a03","observation_id":"319281f6-18a9-4905-a809-97a9dad03e86","resolution":{"observed_at":"2026-05-16T15:23:02.142076Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Gpt-4 technical report","venue":null,"work_id":"bc108e20-4aef-4f72-9fcd-fb04d1d9fa6e","year":2024},"citing_paper":{"arxiv_id":"2601.09746","last_updated":"2026-01-11T20:36:47Z","snapshot_observed_at":"2026-08-09T00:07:01.447972Z","submitted_at":"2026-01-11T20:36:47Z","title":"Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD Concepts","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-05-16T15:22:35.204623Z"},"links":{"citing_paper":"/paper/2601.09746"},"observation_digest":"sha256:27ac7517e1a4decdd6b3882fbd0b2bc6a33e8f4936f2d549143871cbdfc51fb0","observation_id":"fa0187ce-612a-49f1-a773-60a40df87bff","resolution":{"observed_at":"2026-05-16T15:23:02.195528Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Learning to name classes for vision and language models","venue":null,"work_id":"25c322cc-0ae0-4653-8e66-08251df6d6ca","year":2023},"citing_paper":{"arxiv_id":"2601.09746","last_updated":"2026-01-11T20:36:47Z","snapshot_observed_at":"2026-08-09T00:07:01.447972Z","submitted_at":"2026-01-11T20:36:47Z","title":"Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD Concepts","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-05-16T15:22:35.204623Z"},"links":{"citing_paper":"/paper/2601.09746"},"observation_digest":"sha256:9b529cff78d88b042a89bae8c341d789b6d6c2a000494d67b710db5af8ee2ab3","observation_id":"e4f31901-0797-487f-bf9c-47885f306fcb","resolution":{"observed_at":"2026-05-16T15:23:02.191774Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Qwen2.5 technical report","venue":null,"work_id":"98583742-61fd-4050-b697-33cf54dce973","year":2025},"citing_paper":{"arxiv_id":"2601.09746","last_updated":"2026-01-11T20:36:47Z","snapshot_observed_at":"2026-08-09T00:07:01.447972Z","submitted_at":"2026-01-11T20:36:47Z","title":"Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD Concepts","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-05-16T15:22:35.204623Z"},"links":{"citing_paper":"/paper/2601.09746"},"observation_digest":"sha256:f8ae3dc0dca38b774a0349f8a72d2ac52791d3f27ad6aa36046b9e7370a90786","observation_id":"69c75c70-5b9f-4017-90f4-ba4379241e43","resolution":{"observed_at":"2026-05-16T15:23:02.200110Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Learning trans- ferable visual models from natural language supervi- sion","venue":null,"work_id":"bdabaf66-b251-455c-847d-01d6edc112b0","year":2021},"citing_paper":{"arxiv_id":"2601.09746","last_updated":"2026-01-11T20:36:47Z","snapshot_observed_at":"2026-08-09T00:07:01.447972Z","submitted_at":"2026-01-11T20:36:47Z","title":"Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD Concepts","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-05-16T15:22:35.204623Z"},"links":{"citing_paper":"/paper/2601.09746"},"observation_digest":"sha256:9602b02e94baef5d34c542d499fabddf4a539b123bd759d5432035864152b8d7","observation_id":"8dabe4dd-b48f-4faa-801b-0b1625355c06","resolution":{"observed_at":"2026-05-16T15:23:02.181160Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Denseclip: Language-guided dense predic- tion with context-aware prompting","venue":null,"work_id":"a551f80d-f1ad-4b09-8426-eb7ebcfeb1b3","year":2022},"citing_paper":{"arxiv_id":"2601.09746","last_updated":"2026-01-11T20:36:47Z","snapshot_observed_at":"2026-08-09T00:07:01.447972Z","submitted_at":"2026-01-11T20:36:47Z","title":"Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD Concepts","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-05-16T15:22:35.204623Z"},"links":{"citing_paper":"/paper/2601.09746"},"observation_digest":"sha256:91b8a0deb5ce05788a0c80c91e99ab7169f7b1da7c6d7ff03bcb169514b49365","observation_id":"4f7305a4-c1fd-465a-8a1c-e3a24711e567","resolution":{"observed_at":"2026-05-16T15:23:02.135258Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Laion-400m: Open dataset of clip-filtered 400 million image-text pairs","venue":null,"work_id":"20829007-a8f9-4c59-9466-524fcd14504a","year":2021},"citing_paper":{"arxiv_id":"2601.09746","last_updated":"2026-01-11T20:36:47Z","snapshot_observed_at":"2026-08-09T00:07:01.447972Z","submitted_at":"2026-01-11T20:36:47Z","title":"Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD Concepts","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-05-16T15:22:35.204623Z"},"links":{"citing_paper":"/paper/2601.09746"},"observation_digest":"sha256:80f2a4e54db413c0caccd343ccd826a2248f581ead8bd3ff316fcb29afed9ef1","observation_id":"7fd63346-fd2d-4f8e-a88f-04c1838fb438","resolution":{"observed_at":"2026-05-16T15:23:02.122480Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2107.06383","last_updated":"2021-07-13T20:48:12Z","snapshot_observed_at":"2026-08-07T22:40:13.912253Z","submitted_at":"2021-07-13T20:48:12Z","title":"How Much Can CLIP Benefit Vision-and-Language Tasks?","version":1},"cited_work":{"arxiv_id":"2107.06383","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2107.06383","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"How much can clip benefit vision-and-language tasks?","venue":null,"work_id":"3b4c7819-6f34-4c2d-91df-038dc5d7c576","year":2021},"citing_paper":{"arxiv_id":"2601.09746","last_updated":"2026-01-11T20:36:47Z","snapshot_observed_at":"2026-08-09T00:07:01.447972Z","submitted_at":"2026-01-11T20:36:47Z","title":"Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD Concepts","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-05-16T15:22:35.204623Z"},"links":{"cited_paper":"/paper/2107.06383","citing_paper":"/paper/2601.09746"},"observation_digest":"sha256:3ac990621bff0bf5cb5f9685b2871c87fc08dbc72011a4aadea72c152830cf0f","observation_id":"9cb8275f-7210-4586-be21-74a5ec661e98","resolution":{"observed_at":"2026-05-16T15:23:01.929185Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Human cognition involves the dynamic integra- tion of neural activity and neuromodulatory systems","venue":null,"work_id":"9d274533-c4f6-403c-8b05-db8f8c858a8e","year":2019},"citing_paper":{"arxiv_id":"2601.09746","last_updated":"2026-01-11T20:36:47Z","snapshot_observed_at":"2026-08-09T00:07:01.447972Z","submitted_at":"2026-01-11T20:36:47Z","title":"Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD Concepts","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-05-16T15:22:35.204623Z"},"links":{"citing_paper":"/paper/2601.09746"},"observation_digest":"sha256:13e2a3a132b13640985423e72de5bfeced2beb22363a0069cba35df44d5a6dee","observation_id":"fee90444-f746-4360-9516-5637674c66d9","resolution":{"observed_at":"2026-05-16T15:23:02.208855Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Fastcontext: Han- dling out-of-vocabulary words using the word struc- ture and context","venue":null,"work_id":"0c98046b-f51f-428d-b454-dd7aaf001f87","year":2022},"citing_paper":{"arxiv_id":"2601.09746","last_updated":"2026-01-11T20:36:47Z","snapshot_observed_at":"2026-08-09T00:07:01.447972Z","submitted_at":"2026-01-11T20:36:47Z","title":"Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD Concepts","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-05-16T15:22:35.204623Z"},"links":{"citing_paper":"/paper/2601.09746"},"observation_digest":"sha256:2fc7c49eeb612f46379427cacbd2c59c26f8df72f8d51d58b2b9c011a92f5f95","observation_id":"6be28f29-d68b-4b44-bb08-a10e6866eb9c","resolution":{"observed_at":"2026-05-16T15:23:02.124981Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Out- of-distribution generalization via composition: a lens through induction heads in transformers","venue":null,"work_id":"58dfe0fd-44e6-4e33-954e-467b0373e5be","year":2024},"citing_paper":{"arxiv_id":"2601.09746","last_updated":"2026-01-11T20:36:47Z","snapshot_observed_at":"2026-08-09T00:07:01.447972Z","submitted_at":"2026-01-11T20:36:47Z","title":"Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD Concepts","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-05-16T15:22:35.204623Z"},"links":{"citing_paper":"/paper/2601.09746"},"observation_digest":"sha256:3f5c9e0c6be24997d41b763d4edcfb2f63a54d472a010cbb8e7e0d01c4dc6b51","observation_id":"9e484187-8709-43c2-912e-49e09c7063bc","resolution":{"observed_at":"2026-05-16T15:23:02.149394Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Robust fine-tuning of vision-language models for domain generalization","venue":null,"work_id":"d47b0d5d-205e-4a12-a77f-eb8a248d5176","year":null},"citing_paper":{"arxiv_id":"2601.09746","last_updated":"2026-01-11T20:36:47Z","snapshot_observed_at":"2026-08-09T00:07:01.447972Z","submitted_at":"2026-01-11T20:36:47Z","title":"Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD Concepts","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-05-16T15:22:35.204623Z"},"links":{"citing_paper":"/paper/2601.09746"},"observation_digest":"sha256:f2a243c3e9242aea5acfd442213368ad3eef47819d08056bb7a6ec8d1d33c665","observation_id":"48a14aa2-1f7e-46a0-b231-8db2ce0c06d4","resolution":{"observed_at":"2026-05-16T15:23:02.108774Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Zhao, Kelvin Guu, Adams Wei Yu, Brian Lester, Nan Du, An- drew M","venue":null,"work_id":"5b39d7f7-1389-463b-bd24-3a7274806751","year":2022},"citing_paper":{"arxiv_id":"2601.09746","last_updated":"2026-01-11T20:36:47Z","snapshot_observed_at":"2026-08-09T00:07:01.447972Z","submitted_at":"2026-01-11T20:36:47Z","title":"Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD Concepts","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-05-16T15:22:35.204623Z"},"links":{"citing_paper":"/paper/2601.09746"},"observation_digest":"sha256:67147943aca7e822dbc8fe1b100720abdaf4026e6d8548e6a6ac68053a9c6755","observation_id":"62ae0c1b-07b1-4d74-9084-2639f6e6cefc","resolution":{"observed_at":"2026-05-16T15:23:02.129644Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Robust fine-tuning of zero-shot models","venue":null,"work_id":"61329bde-518f-433d-8914-9c613566c14f","year":2022},"citing_paper":{"arxiv_id":"2601.09746","last_updated":"2026-01-11T20:36:47Z","snapshot_observed_at":"2026-08-09T00:07:01.447972Z","submitted_at":"2026-01-11T20:36:47Z","title":"Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD Concepts","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-05-16T15:22:35.204623Z"},"links":{"citing_paper":"/paper/2601.09746"},"observation_digest":"sha256:1c5744ad91421543fe555fe396d4d689b35457d9773ae5fcc67467fa16bd0831","observation_id":"463e5967-0bc5-42ac-8d88-5f63a3352982","resolution":{"observed_at":"2026-05-16T15:23:02.110969Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Cascade prompt learning for vision-language model adaptation","venue":null,"work_id":"736e48ea-745f-4912-a0d6-78f523576f95","year":2024},"citing_paper":{"arxiv_id":"2601.09746","last_updated":"2026-01-11T20:36:47Z","snapshot_observed_at":"2026-08-09T00:07:01.447972Z","submitted_at":"2026-01-11T20:36:47Z","title":"Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD Concepts","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-05-16T15:22:35.204623Z"},"links":{"citing_paper":"/paper/2601.09746"},"observation_digest":"sha256:5d66fb0c6c79fd18c957e1a667670f4701c817009922c1850a0ff8acf124ccc2","observation_id":"12c317bc-ab5d-40b4-bb6f-a0289a0bf8f1","resolution":{"observed_at":"2026-05-16T15:23:02.223189Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Depthssc: Monocular 3d seman- tic scene completion via depth-spatial alignment and voxel adaptation","venue":null,"work_id":"091a7fbd-d5a1-443e-b674-b3e7eaa216a3","year":2024},"citing_paper":{"arxiv_id":"2601.09746","last_updated":"2026-01-11T20:36:47Z","snapshot_observed_at":"2026-08-09T00:07:01.447972Z","submitted_at":"2026-01-11T20:36:47Z","title":"Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD Concepts","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-05-16T15:22:35.204623Z"},"links":{"citing_paper":"/paper/2601.09746"},"observation_digest":"sha256:d30d3dbbb61c21960af24ac2cc95f61e1ca52bc78bd9abe416124cefa1b0b544","observation_id":"714903af-a364-443b-8b14-2d5f3516e4c3","resolution":{"observed_at":"2026-05-16T15:23:02.229235Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Task residual for tuning vision-language models","venue":null,"work_id":"8125ef44-8cce-43a8-b70d-607ddcc745a1","year":2023},"citing_paper":{"arxiv_id":"2601.09746","last_updated":"2026-01-11T20:36:47Z","snapshot_observed_at":"2026-08-09T00:07:01.447972Z","submitted_at":"2026-01-11T20:36:47Z","title":"Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD Concepts","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-05-16T15:22:35.204623Z"},"links":{"citing_paper":"/paper/2601.09746"},"observation_digest":"sha256:91c1353f797a2d9e4d2b16ae75c839b7ebb6b86b53c70644bdbe8ff2cec0243a","observation_id":"347de740-0014-46fb-8e63-e9f9f6c57bb9","resolution":{"observed_at":"2026-05-16T15:23:02.215296Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Boosting vision-language models with transduction","venue":null,"work_id":"c70bc199-671b-486b-9618-76fa523404e9","year":null},"citing_paper":{"arxiv_id":"2601.09746","last_updated":"2026-01-11T20:36:47Z","snapshot_observed_at":"2026-08-09T00:07:01.447972Z","submitted_at":"2026-01-11T20:36:47Z","title":"Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD Concepts","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-05-16T15:22:35.204623Z"},"links":{"citing_paper":"/paper/2601.09746"},"observation_digest":"sha256:d6ba56a2fa815ff9d6b3f406ef787b1bcce7076f34da1bb2a311049561dcfde3","observation_id":"a70f43dc-d0f5-482a-a52c-a29a323c0a31","resolution":{"observed_at":"2026-05-16T15:23:02.171330Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"MAT-agent: Adaptive multi- agent training optimization","venue":null,"work_id":"ac512687-5ee4-45ea-89ce-ad4c36eb43b6","year":2025},"citing_paper":{"arxiv_id":"2601.09746","last_updated":"2026-01-11T20:36:47Z","snapshot_observed_at":"2026-08-09T00:07:01.447972Z","submitted_at":"2026-01-11T20:36:47Z","title":"Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD Concepts","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-05-16T15:22:35.204623Z"},"links":{"citing_paper":"/paper/2601.09746"},"observation_digest":"sha256:2f7cf739bed9f6637b35db6667eec6ac1aac36962b9377677458dcefa0e8ba78","observation_id":"d5a116c5-5593-46cc-8db3-daaac8cb9b06","resolution":{"observed_at":"2026-05-16T15:23:02.132287Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"CF-VLM: Counterfactual vision- language fine-tuning","venue":null,"work_id":"1fed36c9-da31-467d-bc69-6b0122013259","year":null},"citing_paper":{"arxiv_id":"2601.09746","last_updated":"2026-01-11T20:36:47Z","snapshot_observed_at":"2026-08-09T00:07:01.447972Z","submitted_at":"2026-01-11T20:36:47Z","title":"Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD Concepts","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-05-16T15:22:35.204623Z"},"links":{"citing_paper":"/paper/2601.09746"},"observation_digest":"sha256:993887ae6be17287e09bfc4737a875070ee7e19ae7ab3e3cf5c99dbb025f3aee","observation_id":"f388a372-2a37-44ce-9fa0-d3c2736ca977","resolution":{"observed_at":"2026-05-16T15:23:02.204078Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Mm-cot:a benchmark for probing visual chain- of-thought reasoning in multimodal models","venue":null,"work_id":"4a7a99bb-ca0d-492f-86ab-4220d130d30c","year":2025},"citing_paper":{"arxiv_id":"2601.09746","last_updated":"2026-01-11T20:36:47Z","snapshot_observed_at":"2026-08-09T00:07:01.447972Z","submitted_at":"2026-01-11T20:36:47Z","title":"Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD Concepts","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-05-16T15:22:35.204623Z"},"links":{"citing_paper":"/paper/2601.09746"},"observation_digest":"sha256:b1af7713781988a902d7576079bf91c37742f4acb3a1c53178b67494965e65de","observation_id":"0c8288ed-62a0-41a8-90bb-5117b52ca4e4","resolution":{"observed_at":"2026-05-16T15:23:02.144630Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Top-down semantic refinement for image captioning","venue":null,"work_id":"607ac0c4-1485-4ce9-acbb-007feb6d12a6","year":2025},"citing_paper":{"arxiv_id":"2601.09746","last_updated":"2026-01-11T20:36:47Z","snapshot_observed_at":"2026-08-09T00:07:01.447972Z","submitted_at":"2026-01-11T20:36:47Z","title":"Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD Concepts","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-05-16T15:22:35.204623Z"},"links":{"citing_paper":"/paper/2601.09746"},"observation_digest":"sha256:f228abb72c968f92d8132330fc1a8fa979162f36d64da06aa54da44e62a148f3","observation_id":"6a5b94a0-cc9a-4c77-87a4-9c0ab7dc7edf","resolution":{"observed_at":"2026-05-16T15:23:02.189353Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Learning dynamics of vlm finetuning","venue":null,"work_id":"28c6061f-dfa3-4abc-8d64-ceecd6625298","year":2025},"citing_paper":{"arxiv_id":"2601.09746","last_updated":"2026-01-11T20:36:47Z","snapshot_observed_at":"2026-08-09T00:07:01.447972Z","submitted_at":"2026-01-11T20:36:47Z","title":"Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD Concepts","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-05-16T15:22:35.204623Z"},"links":{"citing_paper":"/paper/2601.09746"},"observation_digest":"sha256:83acd8919d54074a95aacd7b8701209ee030f23e955979edc3ba304cc0a2233d","observation_id":"6f0ab9c0-3e40-41a8-bf3b-b08e17ab58cf","resolution":{"observed_at":"2026-05-16T15:23:02.210861Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Failure-driven workflow refinement","venue":null,"work_id":"88fc2afd-697a-4e18-81cd-777ba5100ce6","year":2025},"citing_paper":{"arxiv_id":"2601.09746","last_updated":"2026-01-11T20:36:47Z","snapshot_observed_at":"2026-08-09T00:07:01.447972Z","submitted_at":"2026-01-11T20:36:47Z","title":"Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD Concepts","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-05-16T15:22:35.204623Z"},"links":{"citing_paper":"/paper/2601.09746"},"observation_digest":"sha256:0d38b40f5075929f9a80076d59a4150f21d3af40e73e95791752a69313d0d847","observation_id":"4a42b339-502e-48e2-85c3-4580f322ecea","resolution":{"observed_at":"2026-05-16T15:23:02.127166Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Drdiff: Dynamic routing diffusion with hierarchical attention for breaking the efficiency- quality trade-off","venue":null,"work_id":"d4bca824-bd92-4314-9548-504538a32a50","year":2025},"citing_paper":{"arxiv_id":"2601.09746","last_updated":"2026-01-11T20:36:47Z","snapshot_observed_at":"2026-08-09T00:07:01.447972Z","submitted_at":"2026-01-11T20:36:47Z","title":"Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD Concepts","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-05-16T15:22:35.204623Z"},"links":{"citing_paper":"/paper/2601.09746"},"observation_digest":"sha256:05bcecac11dfa175a0dba8c0e96604c057e45b02999478834cb68ec44d02f2b0","observation_id":"b95129dc-d585-4487-b910-99d39ad44881","resolution":{"observed_at":"2026-05-16T15:23:02.219455Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Osc: Cognitive orchestration through dynamic knowledge alignment in multi-agent llm col- laboration","venue":null,"work_id":"37b47e0f-1c75-4592-bfa1-9bccbb1a587e","year":2025},"citing_paper":{"arxiv_id":"2601.09746","last_updated":"2026-01-11T20:36:47Z","snapshot_observed_at":"2026-08-09T00:07:01.447972Z","submitted_at":"2026-01-11T20:36:47Z","title":"Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD Concepts","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-05-16T15:22:35.204623Z"},"links":{"citing_paper":"/paper/2601.09746"},"observation_digest":"sha256:5c17a5ca7df037aff4e97f6e3b511b79ba32c27da5480576f8a16d1a28231a66","observation_id":"11ca9b48-397a-42ab-88cb-e323c5253417","resolution":{"observed_at":"2026-05-16T15:23:02.197878Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Kolmogorov-arnold fourier networks","venue":null,"work_id":"d3f4ac30-1820-4aa8-b6c2-f3cabbcdbe17","year":2025},"citing_paper":{"arxiv_id":"2601.09746","last_updated":"2026-01-11T20:36:47Z","snapshot_observed_at":"2026-08-09T00:07:01.447972Z","submitted_at":"2026-01-11T20:36:47Z","title":"Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD Concepts","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-05-16T15:22:35.204623Z"},"links":{"citing_paper":"/paper/2601.09746"},"observation_digest":"sha256:dfd850dca71b23d9333cf67dc339d9f842d9031dce4836539025cf0135adcd03","observation_id":"2a008d58-cdfd-4f16-b677-416dabbe0816","resolution":{"observed_at":"2026-05-16T15:23:02.173626Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"GAM-agent: Game-theoretic and uncertainty- aware collaboration for complex visual reasoning","venue":null,"work_id":"ee0f7d45-43af-43b6-a4e5-c5478718a71b","year":2025},"citing_paper":{"arxiv_id":"2601.09746","last_updated":"2026-01-11T20:36:47Z","snapshot_observed_at":"2026-08-09T00:07:01.447972Z","submitted_at":"2026-01-11T20:36:47Z","title":"Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD Concepts","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-05-16T15:22:35.204623Z"},"links":{"citing_paper":"/paper/2601.09746"},"observation_digest":"sha256:04c031308b7fcf7fcdcad986b88bd779505342dd57eeb0764ca5267ed3cda9db","observation_id":"83d5bc85-bab5-40dd-82ea-bff7f9105299","resolution":{"observed_at":"2026-05-16T15:23:02.185506Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Tri-MARF: A tri-modal multi-agent re- sponsive framework for comprehensive 3d object an- notation","venue":null,"work_id":"f5d2e416-89c4-4920-a429-41359fe65021","year":2025},"citing_paper":{"arxiv_id":"2601.09746","last_updated":"2026-01-11T20:36:47Z","snapshot_observed_at":"2026-08-09T00:07:01.447972Z","submitted_at":"2026-01-11T20:36:47Z","title":"Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD Concepts","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-05-16T15:22:35.204623Z"},"links":{"citing_paper":"/paper/2601.09746"},"observation_digest":"sha256:b6286b50ad37e39465d916184ea77de5f86042ebe7cd54249b50c319b9ef474e","observation_id":"42282af2-1042-48d8-8c6b-48bf4143c132","resolution":{"observed_at":"2026-05-16T15:23:02.116732Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Hybridtoken-vlm: Hybrid token compression for vision-language models","venue":null,"work_id":"e66e9dc6-c005-44ff-a676-eff528858dc5","year":2025},"citing_paper":{"arxiv_id":"2601.09746","last_updated":"2026-01-11T20:36:47Z","snapshot_observed_at":"2026-08-09T00:07:01.447972Z","submitted_at":"2026-01-11T20:36:47Z","title":"Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD Concepts","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-05-16T15:22:35.204623Z"},"links":{"citing_paper":"/paper/2601.09746"},"observation_digest":"sha256:68c3bf3c935bee636b43483c392768afb5596785e3c4499cb4d03025a31d9c3e","observation_id":"cc800b2d-9b27-419a-bab8-bad389be027b","resolution":{"observed_at":"2026-05-16T15:23:02.137597Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"KABB: Knowledge-aware bayesian bandits for dynamic expert coordination in multi-agent systems","venue":null,"work_id":"43e280d6-cd80-4650-a8f3-313641a05668","year":2025},"citing_paper":{"arxiv_id":"2601.09746","last_updated":"2026-01-11T20:36:47Z","snapshot_observed_at":"2026-08-09T00:07:01.447972Z","submitted_at":"2026-01-11T20:36:47Z","title":"Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD Concepts","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-05-16T15:22:35.204623Z"},"links":{"citing_paper":"/paper/2601.09746"},"observation_digest":"sha256:4aeb3c12f80fcadde5279e548116cc777d9c60499c224551a049d87eae06ffd6","observation_id":"e09a9218-b6d6-40f8-8ad0-ba479042c690","resolution":{"observed_at":"2026-05-16T15:23:02.217384Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Llm-cas: Dynamic neuron perturbation for real-time hallucination correction","venue":null,"work_id":"109144bd-1ddf-4379-89a5-bf5b6e8dc8c3","year":2025},"citing_paper":{"arxiv_id":"2601.09746","last_updated":"2026-01-11T20:36:47Z","snapshot_observed_at":"2026-08-09T00:07:01.447972Z","submitted_at":"2026-01-11T20:36:47Z","title":"Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD Concepts","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-05-16T15:22:35.204623Z"},"links":{"citing_paper":"/paper/2601.09746"},"observation_digest":"sha256:9159d98265e5f2c9ec99dd506bcea6c530f2e33d94766d33f418146fbcd53e23","observation_id":"280f4ccb-04bd-4f7f-b8a7-09a3de7e1aae","resolution":{"observed_at":"2026-05-16T15:23:02.206492Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Llava-read: Enhanc- ing reading ability of multimodal language models","venue":null,"work_id":"01e837cf-bf05-4c63-a3df-108084f8cb59","year":null},"citing_paper":{"arxiv_id":"2601.09746","last_updated":"2026-01-11T20:36:47Z","snapshot_observed_at":"2026-08-09T00:07:01.447972Z","submitted_at":"2026-01-11T20:36:47Z","title":"Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD Concepts","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-05-16T15:22:35.204623Z"},"links":{"citing_paper":"/paper/2601.09746"},"observation_digest":"sha256:369b5792d490f4b7a295aa9bc808ef20440cdb08715b75c1028f3ceae4725c39","observation_id":"2d2c9a1f-aa02-467c-9b45-7b8e37db11c3","resolution":{"observed_at":"2026-05-16T15:23:02.157841Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Learn- ing from models beyond fine-tuning.Nature Machine Intelligence, 7(1):6–17","venue":null,"work_id":"f1f2a492-ec4d-4db4-befe-c7d7a16c0be4","year":2025},"citing_paper":{"arxiv_id":"2601.09746","last_updated":"2026-01-11T20:36:47Z","snapshot_observed_at":"2026-08-09T00:07:01.447972Z","submitted_at":"2026-01-11T20:36:47Z","title":"Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD Concepts","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-05-16T15:22:35.204623Z"},"links":{"citing_paper":"/paper/2601.09746"},"observation_digest":"sha256:8550eb38bd2d451a8dfa2e9d12dd30bcbe8fbcfee20d01437cff5d2761e70877","observation_id":"4affe112-4d36-48b9-a74f-722dffdac858","resolution":{"observed_at":"2026-05-16T15:23:02.120013Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Conditional prompt learning for vision- language models","venue":null,"work_id":"8b9f77e0-8527-4415-96e3-3c8af53e16a5","year":2022},"citing_paper":{"arxiv_id":"2601.09746","last_updated":"2026-01-11T20:36:47Z","snapshot_observed_at":"2026-08-09T00:07:01.447972Z","submitted_at":"2026-01-11T20:36:47Z","title":"Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD Concepts","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-05-16T15:22:35.204623Z"},"links":{"citing_paper":"/paper/2601.09746"},"observation_digest":"sha256:6c9c05a0f1ecd7a977391a3ef062a95c09fa374cdac69db153376e8619f6ca5c","observation_id":"664360d9-6296-44ce-aefd-770229c79ca8","resolution":{"observed_at":"2026-05-16T15:23:02.178620Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Learning to prompt for vision-language models.International Journal of Computer Vision, 130(9):2337–2348","venue":null,"work_id":"61f951f1-e6c8-4cb5-98f6-f6f5c1badf1a","year":2022},"citing_paper":{"arxiv_id":"2601.09746","last_updated":"2026-01-11T20:36:47Z","snapshot_observed_at":"2026-08-09T00:07:01.447972Z","submitted_at":"2026-01-11T20:36:47Z","title":"Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD Concepts","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-05-16T15:22:35.204623Z"},"links":{"citing_paper":"/paper/2601.09746"},"observation_digest":"sha256:8871e2f08be1c4ff5fd97fcb10b03b589153c53444e533ad43cc76f0893b8f32","observation_id":"82042918-f9c9-4587-a4ac-c07b8b1d34db","resolution":{"observed_at":"2026-05-16T15:23:02.193665Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2601.09746","last_updated":"2026-01-11T20:36:47Z","latest_version":1,"primary_category":"cs.MA","snapshot_observed_at":"2026-08-09T00:07:01.447972Z","submitted_at":"2026-01-11T20:36:47Z","title":"Multi-Agent Cooperative Learning for Robust Vision-Language Alignment under OOD Concepts"},"reference_resolution":{"displayed":60,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":2,"verified_fuzzy":58},"total_outbound_references":60},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 60 of 60 outbound references and 0 inbound Pith citation observations for arXiv:2601.09746."}