{"as_of":"2026-08-08T17:26:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:0b0591569d3ca1d50ec017f75922376bfad7677e278d585200764b6b76e167d4","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":"2026-08-06T12:46:04.053951Z","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":"2026-08-08T06:32:00.761636+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/2507.21521/citation-record","integrity":"/paper/2507.21521/integrity","json":"/paper/2507.21521/citation-record.json","paper":"/paper/2507.21521"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T12:46:04.489600Z","title":"Meta-adapter: An online few-shot learner for vision-language model,","venue":null,"work_id":"b723c65b-ec95-4cc8-ae20-40afad8a4ccb","year":2023},"citing_paper":{"arxiv_id":"2507.21521","last_updated":"2025-07-29T06:08:28Z","snapshot_observed_at":"2026-08-07T02:38:12.360447Z","submitted_at":"2025-07-29T06:08:28Z","title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T12:46:00.428088Z"},"links":{"citing_paper":"/paper/2507.21521"},"observation_digest":"sha256:be3f93721548e82ec0325dabb0533d60e4c48696082849b233699c145d41de42","observation_id":"895f54b9-0a33-4d34-ade0-7f73ad130536","resolution":{"observed_at":"2026-08-06T12:46:04.492892Z","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":"2026-08-06T12:46:04.480950Z","title":"Zero-shot visual reasoning by vision- language models: Benchmarking and analysis,","venue":null,"work_id":"23e60ffd-de5b-4287-961f-11e26af45ee1","year":2024},"citing_paper":{"arxiv_id":"2507.21521","last_updated":"2025-07-29T06:08:28Z","snapshot_observed_at":"2026-08-07T02:38:12.360447Z","submitted_at":"2025-07-29T06:08:28Z","title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T12:46:00.520898Z"},"links":{"citing_paper":"/paper/2507.21521"},"observation_digest":"sha256:b209c6000a1384f9f51c88cebbfcded5ad802404278c93b24bcb6350322b88de","observation_id":"6f5bfec2-137e-4b80-9e70-047bce78e84f","resolution":{"observed_at":"2026-08-06T12:46:04.483429Z","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":"2311.17842","last_updated":"2023-12-24T03:48:40Z","snapshot_observed_at":"2026-08-07T02:37:30.672574Z","submitted_at":"2023-11-29T17:46:25Z","title":"Look Before You Leap: Unveiling the Power of GPT-4V in Robotic Vision-Language Planning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.17842","snapshot_observed_at":"2026-08-06T12:46:00.599774Z","title":"Look before you leap: Unveiling the power of gpt-4v in robotic vision-language planning,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.21521","last_updated":"2025-07-29T06:08:28Z","snapshot_observed_at":"2026-08-07T02:38:12.360447Z","submitted_at":"2025-07-29T06:08:28Z","title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T12:46:00.599774Z"},"links":{"cited_paper":"/paper/2311.17842","citing_paper":"/paper/2507.21521"},"observation_digest":"sha256:571481c750ad633c05e44d1119041c32561dc152fa33e6bf836f47cc472ccdd2","observation_id":"0a8f2789-7dd0-4c41-8128-deecbcadba68","resolution":{"observed_at":"2026-08-06T12:46:00.599774Z","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":"2026-08-06T12:46:04.471845Z","title":"Deepseek-vl: Towards real-world vision-language understanding,","venue":null,"work_id":"ffe70565-72c5-451d-b2ca-c4be0b9280a3","year":2024},"citing_paper":{"arxiv_id":"2507.21521","last_updated":"2025-07-29T06:08:28Z","snapshot_observed_at":"2026-08-07T02:38:12.360447Z","submitted_at":"2025-07-29T06:08:28Z","title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T12:46:00.653349Z"},"links":{"citing_paper":"/paper/2507.21521"},"observation_digest":"sha256:4e678f1eab76bbb802869ab632baaa91b8e85543a3cb753c4e51794dbbfeaa5b","observation_id":"5171c5e3-b410-4434-a3ab-d16bb5864cb0","resolution":{"observed_at":"2026-08-06T12:46:04.474261Z","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":"2026-08-06T12:46:04.464006Z","title":"Active learning literature survey,","venue":null,"work_id":"4faf1155-7678-4339-90bf-79ef800430d0","year":2009},"citing_paper":{"arxiv_id":"2507.21521","last_updated":"2025-07-29T06:08:28Z","snapshot_observed_at":"2026-08-07T02:38:12.360447Z","submitted_at":"2025-07-29T06:08:28Z","title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T12:46:00.708017Z"},"links":{"citing_paper":"/paper/2507.21521"},"observation_digest":"sha256:5fb25adb3548419bc47438724540557276175964c1fa61ed91d9dd8838232d0b","observation_id":"703594f3-4649-4c59-9f09-d88fea31fe12","resolution":{"observed_at":"2026-08-06T12:46:04.466507Z","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":"2026-08-06T12:46:04.453439Z","title":"A survey of deep active learning,","venue":null,"work_id":"37545321-c8e8-45c6-82e7-0f782401b999","year":2021},"citing_paper":{"arxiv_id":"2507.21521","last_updated":"2025-07-29T06:08:28Z","snapshot_observed_at":"2026-08-07T02:38:12.360447Z","submitted_at":"2025-07-29T06:08:28Z","title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T12:46:00.752091Z"},"links":{"citing_paper":"/paper/2507.21521"},"observation_digest":"sha256:28315af563d0bc6516aa97e60c618215699161d98ada32f0868de6bc16ee54fa","observation_id":"77b34589-51e1-423e-98d8-9ba0ec89e512","resolution":{"observed_at":"2026-08-06T12:46:04.459292Z","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":"2026-08-06T12:46:00.786082Z","title":"Learning transferable visual models from natural language supervision,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.21521","last_updated":"2025-07-29T06:08:28Z","snapshot_observed_at":"2026-08-07T02:38:12.360447Z","submitted_at":"2025-07-29T06:08:28Z","title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T12:46:00.786082Z"},"links":{"citing_paper":"/paper/2507.21521"},"observation_digest":"sha256:a7552eb5978e06fcf4a24d2eb9799c787cc9d763a44a5f53a35fea75ba7f3239","observation_id":"5c573b7d-4ba8-49bd-a6d7-57d8694bd04e","resolution":{"observed_at":"2026-08-06T12:46:00.786082Z","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":"2026-08-06T12:46:04.440415Z","title":"Zero-shot text-to-image generation,","venue":null,"work_id":"d1877837-119a-4764-aae4-746d4a9a8339","year":2021},"citing_paper":{"arxiv_id":"2507.21521","last_updated":"2025-07-29T06:08:28Z","snapshot_observed_at":"2026-08-07T02:38:12.360447Z","submitted_at":"2025-07-29T06:08:28Z","title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T12:46:00.917998Z"},"links":{"citing_paper":"/paper/2507.21521"},"observation_digest":"sha256:dafd5940700d3ddd35f9bdd10fe27b059d85c9f0aebae76942fc5f084326cbed","observation_id":"4c5bce9a-620c-4e7c-8753-1c04bbec5d6b","resolution":{"observed_at":"2026-08-06T12:46:04.442758Z","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":"2026-08-06T12:46:01.075977Z","title":"Flava: A foundational language and vision alignment model,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.21521","last_updated":"2025-07-29T06:08:28Z","snapshot_observed_at":"2026-08-07T02:38:12.360447Z","submitted_at":"2025-07-29T06:08:28Z","title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T12:46:01.075977Z"},"links":{"citing_paper":"/paper/2507.21521"},"observation_digest":"sha256:233dc234450fdf370ae9adf0735cf2079128e0a04cffa56ee20e51569572e14e","observation_id":"44412f6b-a8c3-4515-8763-9f85ee8d6433","resolution":{"observed_at":"2026-08-06T12:46:01.075977Z","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":"2026-08-06T12:46:04.427930Z","title":"Overconfidence is key: Verbalized uncertainty evaluation in large language and vision-language models,","venue":null,"work_id":"c67e3c47-0f2d-4d4a-aef5-9c93a4f74174","year":2024},"citing_paper":{"arxiv_id":"2507.21521","last_updated":"2025-07-29T06:08:28Z","snapshot_observed_at":"2026-08-07T02:38:12.360447Z","submitted_at":"2025-07-29T06:08:28Z","title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T12:46:01.139387Z"},"links":{"citing_paper":"/paper/2507.21521"},"observation_digest":"sha256:66705bf055c13e36e883559e94e85559a46fb1808a3de6097e6888705e3e0a11","observation_id":"d0f333ef-733a-47e2-b84b-c36eebb12e01","resolution":{"observed_at":"2026-08-06T12:46:04.430744Z","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":"2026-08-06T12:46:04.420677Z","title":"Seeing is believing: Mitigating hallu- cination in large vision-language models via clip-guided decoding,","venue":null,"work_id":"cdd5882b-749b-4422-a739-ddb49c6d8c30","year":2024},"citing_paper":{"arxiv_id":"2507.21521","last_updated":"2025-07-29T06:08:28Z","snapshot_observed_at":"2026-08-07T02:38:12.360447Z","submitted_at":"2025-07-29T06:08:28Z","title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T12:46:01.229771Z"},"links":{"citing_paper":"/paper/2507.21521"},"observation_digest":"sha256:f1e52f7b431277a34419fa803df2e1336eeda621e38cb2fd4eb59c3ed1a83945","observation_id":"add33c34-47a9-4771-9105-6468fe541e2f","resolution":{"observed_at":"2026-08-06T12:46:04.422986Z","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":"2402.00253","last_updated":"2024-05-06T01:10:01Z","snapshot_observed_at":"2026-07-06T17:23:26.913214Z","submitted_at":"2024-02-01T00:33:21Z","title":"A Survey on Hallucination in Large Vision-Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.00253","snapshot_observed_at":"2026-08-06T12:46:01.318080Z","title":"A survey on hallucination in large vision-language models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.21521","last_updated":"2025-07-29T06:08:28Z","snapshot_observed_at":"2026-08-07T02:38:12.360447Z","submitted_at":"2025-07-29T06:08:28Z","title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T12:46:01.318080Z"},"links":{"cited_paper":"/paper/2402.00253","citing_paper":"/paper/2507.21521"},"observation_digest":"sha256:7c9dda2d0f765eadc0edf1a066e2b01760bba281b58e04bd0c98379b0007a26b","observation_id":"36842fb0-a760-4726-bf19-95999ed3d287","resolution":{"observed_at":"2026-08-06T12:46:01.318080Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.05922","last_updated":"2023-09-12T02:34:06Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-09-12T02:34:06Z","title":"A Survey of Hallucination in Large Foundation Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.05922","snapshot_observed_at":"2026-08-06T12:46:01.410618Z","title":"A survey of hallucination in large foundation models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.21521","last_updated":"2025-07-29T06:08:28Z","snapshot_observed_at":"2026-08-07T02:38:12.360447Z","submitted_at":"2025-07-29T06:08:28Z","title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T12:46:01.410618Z"},"links":{"cited_paper":"/paper/2309.05922","citing_paper":"/paper/2507.21521"},"observation_digest":"sha256:bac33fc50f0c9829cffa4e732db94ddd248d4d63f1f6eab5fb42242768d4b464","observation_id":"6cfaa864-9210-46bc-b053-22768d6146d1","resolution":{"observed_at":"2026-08-06T12:46:01.410618Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.13063","last_updated":"2024-03-17T04:38:48Z","snapshot_observed_at":"2026-07-06T15:45:39.649725Z","submitted_at":"2023-06-22T17:31:44Z","title":"Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.13063","snapshot_observed_at":"2026-08-06T12:46:01.519663Z","title":"Can llms express their uncertainty? an empirical evaluation of confidence elicitation in llms,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.21521","last_updated":"2025-07-29T06:08:28Z","snapshot_observed_at":"2026-08-07T02:38:12.360447Z","submitted_at":"2025-07-29T06:08:28Z","title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T12:46:01.519663Z"},"links":{"cited_paper":"/paper/2306.13063","citing_paper":"/paper/2507.21521"},"observation_digest":"sha256:0a8b2c502a25b61659ec458e1129a2dbbe03b37cc189fb207eebfadaa7a9d043","observation_id":"ebc6c9a8-afab-49a9-9fd7-5822075c8302","resolution":{"observed_at":"2026-08-06T12:46:01.519663Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.07383","last_updated":"2023-11-13T15:08:59Z","snapshot_observed_at":"2026-07-06T16:46:38.855912Z","submitted_at":"2023-11-13T15:08:59Z","title":"LM-Polygraph: Uncertainty Estimation for Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.07383","snapshot_observed_at":"2026-08-06T12:46:01.606511Z","title":"Lm-polygraph: Uncertainty estimation for language models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.21521","last_updated":"2025-07-29T06:08:28Z","snapshot_observed_at":"2026-08-07T02:38:12.360447Z","submitted_at":"2025-07-29T06:08:28Z","title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T12:46:01.606511Z"},"links":{"cited_paper":"/paper/2311.07383","citing_paper":"/paper/2507.21521"},"observation_digest":"sha256:d23e511c96eb9de12100886964de14a4537d113f4633d9761f26be1992970d8e","observation_id":"6febb970-377e-454f-99fa-5a37365111d7","resolution":{"observed_at":"2026-08-06T12:46:01.606511Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.02904","last_updated":"2026-04-19T22:48:18Z","snapshot_observed_at":"2026-08-02T22:43:50.593390Z","submitted_at":"2024-12-03T23:14:47Z","title":"Enhancing Trust in Large Language Models via Uncertainty-Calibrated Fine-Tuning","version":2},"cited_work":{"arxiv_id":"2412.02904","doi":null,"metadata_source":"pith","pith_arxiv_id":"2412.02904","snapshot_observed_at":"2026-08-06T12:46:04.140262Z","title":"Enhancing Trust in Large Language Models via Uncertainty-Calibrated Fine-Tuning","venue":"cs.CL","work_id":"e0d776e2-19fa-4b45-949a-4669b9199131","year":2024},"citing_paper":{"arxiv_id":"2507.21521","last_updated":"2025-07-29T06:08:28Z","snapshot_observed_at":"2026-08-07T02:38:12.360447Z","submitted_at":"2025-07-29T06:08:28Z","title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T12:46:01.721794Z"},"links":{"cited_paper":"/paper/2412.02904","citing_paper":"/paper/2507.21521"},"observation_digest":"sha256:3b4c4f53af1686cf80042fec20b9b20ad8195582428f2f4096df14c0b178a258","observation_id":"006c82c8-55b7-406e-9150-46b26404a987","resolution":{"observed_at":"2026-08-06T12:46:04.143047Z","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":{"arxiv_id":"2405.02917","last_updated":"2024-05-05T12:51:38Z","snapshot_observed_at":"2026-07-06T18:09:59.472962Z","submitted_at":"2024-05-05T12:51:38Z","title":"Overconfidence is Key: Verbalized Uncertainty Evaluation in Large Language and Vision-Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.02917","snapshot_observed_at":"2026-08-06T12:46:01.828953Z","title":"Overconfidence is key: Verbalized uncertainty evaluation in large language and vision-language models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.21521","last_updated":"2025-07-29T06:08:28Z","snapshot_observed_at":"2026-08-07T02:38:12.360447Z","submitted_at":"2025-07-29T06:08:28Z","title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T12:46:01.828953Z"},"links":{"cited_paper":"/paper/2405.02917","citing_paper":"/paper/2507.21521"},"observation_digest":"sha256:abe92016f40195a6776ec450ffe2fcc919c0967933c9e934d6dfa292a8763695","observation_id":"905043ce-46ae-454c-af0d-1afa74abdabb","resolution":{"observed_at":"2026-08-06T12:46:01.828953Z","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":"2026-08-06T12:46:04.413292Z","title":"Activedc: Distribution calibration for active finetuning,","venue":null,"work_id":"5b606d41-6e63-4f6a-bc41-6dab6074fab2","year":2024},"citing_paper":{"arxiv_id":"2507.21521","last_updated":"2025-07-29T06:08:28Z","snapshot_observed_at":"2026-08-07T02:38:12.360447Z","submitted_at":"2025-07-29T06:08:28Z","title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T12:46:01.975699Z"},"links":{"citing_paper":"/paper/2507.21521"},"observation_digest":"sha256:af2d76659a9bfc5cf4da2e21ae0d06a694d279516e3b2a213e62037214b7f895","observation_id":"0d8ddea3-d535-4233-aad6-483f523fc90d","resolution":{"observed_at":"2026-08-06T12:46:04.415721Z","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":"2026-08-06T12:46:04.405454Z","title":"Active finetuning: Exploiting annotation budget in the pretraining-finetuning paradigm,","venue":null,"work_id":"7f913731-d083-4672-97b5-d82d544c991b","year":2023},"citing_paper":{"arxiv_id":"2507.21521","last_updated":"2025-07-29T06:08:28Z","snapshot_observed_at":"2026-08-07T02:38:12.360447Z","submitted_at":"2025-07-29T06:08:28Z","title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T12:46:02.101537Z"},"links":{"citing_paper":"/paper/2507.21521"},"observation_digest":"sha256:a70831786e9ccc243463ec68748f23619457449ac199533015889539a1d928ba","observation_id":"929f4a81-f33e-4734-ad6e-e293b034ede5","resolution":{"observed_at":"2026-08-06T12:46:04.408021Z","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":"2026-08-06T12:46:04.398061Z","title":"Querying easily flip-flopped samples for deep active learning,","venue":null,"work_id":"8d83f0f0-db73-4b51-ba15-2db7392a6b6d","year":2024},"citing_paper":{"arxiv_id":"2507.21521","last_updated":"2025-07-29T06:08:28Z","snapshot_observed_at":"2026-08-07T02:38:12.360447Z","submitted_at":"2025-07-29T06:08:28Z","title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T12:46:02.203329Z"},"links":{"citing_paper":"/paper/2507.21521"},"observation_digest":"sha256:abf6499df8ff29b431cb4aa433bc8b348cf37af950c6c883e7530a9572a79105","observation_id":"c409e3be-6db7-4f24-942f-ae16a7baed3d","resolution":{"observed_at":"2026-08-06T12:46:04.401049Z","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":"1708.00489","last_updated":"2018-06-01T10:17:23Z","snapshot_observed_at":"2026-07-06T05:53:39.440274Z","submitted_at":"2017-08-01T19:50:53Z","title":"Active Learning for Convolutional Neural Networks: A Core-Set Approach","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1708.00489","snapshot_observed_at":"2026-08-06T12:46:02.269459Z","title":"Active learning for convolutional neural networks: A core-set approach,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.21521","last_updated":"2025-07-29T06:08:28Z","snapshot_observed_at":"2026-08-07T02:38:12.360447Z","submitted_at":"2025-07-29T06:08:28Z","title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T12:46:02.269459Z"},"links":{"cited_paper":"/paper/1708.00489","citing_paper":"/paper/2507.21521"},"observation_digest":"sha256:47681f4d4149705a866f4ab704d680c6a39f2a09f0d2f94c41eaa65c29d9dff5","observation_id":"7d47150f-6674-4886-80c4-b9a69db3ab3f","resolution":{"observed_at":"2026-08-06T12:46:02.269459Z","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":"2026-08-06T12:46:04.390873Z","title":"Learning loss for active learning,","venue":null,"work_id":"8ab06253-f07c-4af2-a008-20ac8da7a7ff","year":2019},"citing_paper":{"arxiv_id":"2507.21521","last_updated":"2025-07-29T06:08:28Z","snapshot_observed_at":"2026-08-07T02:38:12.360447Z","submitted_at":"2025-07-29T06:08:28Z","title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T12:46:02.414325Z"},"links":{"citing_paper":"/paper/2507.21521"},"observation_digest":"sha256:1ed9c97b2c7c46f1d61e6d5aa22d5418a80af2c74358396b779d8661ac730013","observation_id":"fac3a690-69a8-4bf7-bc6d-f34d5e71705c","resolution":{"observed_at":"2026-08-06T12:46:04.393271Z","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":"2026-08-06T12:46:04.383496Z","title":"Deep active learning for image classification,","venue":null,"work_id":"9ef1183e-560b-4286-bcf3-af8b8a6eaf83","year":2017},"citing_paper":{"arxiv_id":"2507.21521","last_updated":"2025-07-29T06:08:28Z","snapshot_observed_at":"2026-08-07T02:38:12.360447Z","submitted_at":"2025-07-29T06:08:28Z","title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T12:46:02.527733Z"},"links":{"citing_paper":"/paper/2507.21521"},"observation_digest":"sha256:0e9b7d2b5d88e132f126a3e9f00cebd57b308b4b7e5e39f2f34033fa968ebfa5","observation_id":"010b959a-ef12-4ccf-b18d-143d069fdae5","resolution":{"observed_at":"2026-08-06T12:46:04.385834Z","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":"2026-08-06T12:46:04.375175Z","title":"Entropy-based active learning for object detection with progressive diversity constraint,","venue":null,"work_id":"b6052916-498b-4f45-9570-4bab3e1fa581","year":2022},"citing_paper":{"arxiv_id":"2507.21521","last_updated":"2025-07-29T06:08:28Z","snapshot_observed_at":"2026-08-07T02:38:12.360447Z","submitted_at":"2025-07-29T06:08:28Z","title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T12:46:02.632760Z"},"links":{"citing_paper":"/paper/2507.21521"},"observation_digest":"sha256:da0c92e4b1917a30aa757b7c23589323d442c8b0533908a42c348f45e0d32bc5","observation_id":"a88c5811-8018-485f-8619-626f313eb59d","resolution":{"observed_at":"2026-08-06T12:46:04.378451Z","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":"2026-08-06T12:46:04.367071Z","title":"Active learn- ing for deep object detection via probabilistic modeling,","venue":null,"work_id":"2c74f0b9-d327-4c84-9c2c-321a0b04e950","year":2021},"citing_paper":{"arxiv_id":"2507.21521","last_updated":"2025-07-29T06:08:28Z","snapshot_observed_at":"2026-08-07T02:38:12.360447Z","submitted_at":"2025-07-29T06:08:28Z","title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T12:46:02.769427Z"},"links":{"citing_paper":"/paper/2507.21521"},"observation_digest":"sha256:b940321a6430743587859f65c398bbaf70b40ccc18aca74966c8e62dc0a11299","observation_id":"f4143564-a8e0-4b82-8dac-6b359642dba7","resolution":{"observed_at":"2026-08-06T12:46:04.370100Z","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":"2026-08-06T12:46:04.359437Z","title":"Margin-based active learning for structured output spaces,","venue":null,"work_id":"e3ccc6d4-5e56-4e4d-94b7-942f91886eec","year":2006},"citing_paper":{"arxiv_id":"2507.21521","last_updated":"2025-07-29T06:08:28Z","snapshot_observed_at":"2026-08-07T02:38:12.360447Z","submitted_at":"2025-07-29T06:08:28Z","title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T12:46:02.888938Z"},"links":{"citing_paper":"/paper/2507.21521"},"observation_digest":"sha256:9217103a59f4bfb038a734a87a2d39dfa9052fcaeee055ff0efaab77409f6448","observation_id":"5e780319-5b68-4459-a1f8-943c4f5accc2","resolution":{"observed_at":"2026-08-06T12:46:04.362068Z","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":"2026-08-06T12:46:04.352352Z","title":"A survey of deep active learning for foundation models,","venue":null,"work_id":"03c16790-38e5-4f6b-85e5-664d470696ca","year":2023},"citing_paper":{"arxiv_id":"2507.21521","last_updated":"2025-07-29T06:08:28Z","snapshot_observed_at":"2026-08-07T02:38:12.360447Z","submitted_at":"2025-07-29T06:08:28Z","title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T12:46:02.967899Z"},"links":{"citing_paper":"/paper/2507.21521"},"observation_digest":"sha256:f7fe0483c89f4394bd844b75259d76db08e497515e28cfd152715c5057b504c2","observation_id":"ba949f6e-8ecb-4126-af49-d60bf7c841d7","resolution":{"observed_at":"2026-08-06T12:46:04.354717Z","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":"2026-08-06T12:46:04.344818Z","title":"Revisiting active learning in the era of vision foundation models,","venue":null,"work_id":"afb388d9-f4fb-4d0b-98da-62802b09f400","year":2024},"citing_paper":{"arxiv_id":"2507.21521","last_updated":"2025-07-29T06:08:28Z","snapshot_observed_at":"2026-08-07T02:38:12.360447Z","submitted_at":"2025-07-29T06:08:28Z","title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T12:46:03.054477Z"},"links":{"citing_paper":"/paper/2507.21521"},"observation_digest":"sha256:153a814b44f8d615186196109c30084c04cf2facaa1616479396db7d4a570ae1","observation_id":"2c745a24-c971-4772-976d-a7f332ed3309","resolution":{"observed_at":"2026-08-06T12:46:04.347176Z","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":"2202.00254","last_updated":"2022-02-08T08:01:59Z","snapshot_observed_at":"2026-08-01T10:07:11.031561Z","submitted_at":"2022-02-01T07:27:18Z","title":"Active Learning Over Multiple Domains in Natural Language Tasks","version":2},"cited_work":{"arxiv_id":"2202.00254","doi":null,"metadata_source":"pith","pith_arxiv_id":"2202.00254","snapshot_observed_at":"2026-08-06T12:46:04.118214Z","title":"Active Learning Over Multiple Domains in Natural Language Tasks","venue":"cs.CL","work_id":"1a5040b7-dd8c-4fdb-8d19-0d6e34b7795b","year":2022},"citing_paper":{"arxiv_id":"2507.21521","last_updated":"2025-07-29T06:08:28Z","snapshot_observed_at":"2026-08-07T02:38:12.360447Z","submitted_at":"2025-07-29T06:08:28Z","title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T12:46:03.187791Z"},"links":{"cited_paper":"/paper/2202.00254","citing_paper":"/paper/2507.21521"},"observation_digest":"sha256:bf63977d2946ff5607d9aede44461a0c6e79f146e9549a0769da467a915c3916","observation_id":"97410d7b-c821-486c-9265-8572cab5bb08","resolution":{"observed_at":"2026-08-06T12:46:04.120762Z","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":{"arxiv_id":"2406.09296","last_updated":"2024-06-14T04:40:09Z","snapshot_observed_at":"2026-07-06T18:30:28.421247Z","submitted_at":"2024-06-13T16:30:32Z","title":"Parameter-Efficient Active Learning for Foundational models","version":2},"cited_work":{"arxiv_id":"2406.09296","doi":null,"metadata_source":"pith","pith_arxiv_id":"2406.09296","snapshot_observed_at":"2026-08-06T12:46:04.108918Z","title":"Parameter-Efficient Active Learning for Foundational models","venue":"cs.CV","work_id":"8dc08fd0-0fdf-4ea5-90bb-6dbb1c187d61","year":2024},"citing_paper":{"arxiv_id":"2507.21521","last_updated":"2025-07-29T06:08:28Z","snapshot_observed_at":"2026-08-07T02:38:12.360447Z","submitted_at":"2025-07-29T06:08:28Z","title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T12:46:03.316825Z"},"links":{"cited_paper":"/paper/2406.09296","citing_paper":"/paper/2507.21521"},"observation_digest":"sha256:ae374db2b178c3e9b0c112f06aeb65d0c907b98fad17b26e00953076505264e7","observation_id":"a260e6ba-19d3-4079-b7fa-db6d34ea38b6","resolution":{"observed_at":"2026-08-06T12:46:04.111861Z","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":"2026-08-06T12:46:04.337819Z","title":"Source- free continual adaptive learning with limited labels on evolving data drifts,","venue":null,"work_id":"c630a3b3-9d46-451a-9eb1-5028eb8e8b3d","year":2024},"citing_paper":{"arxiv_id":"2507.21521","last_updated":"2025-07-29T06:08:28Z","snapshot_observed_at":"2026-08-07T02:38:12.360447Z","submitted_at":"2025-07-29T06:08:28Z","title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T12:46:03.438549Z"},"links":{"citing_paper":"/paper/2507.21521"},"observation_digest":"sha256:4d99a2aace66dfaae656e15877fd32c2ff252a3cb39ee553524032bd85f583a2","observation_id":"ef2c8c42-3561-4a22-b6a2-a25715d4cd49","resolution":{"observed_at":"2026-08-06T12:46:04.340125Z","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":"2026-08-06T12:46:04.329967Z","title":"Active prompt learning in vision language models,","venue":null,"work_id":"b28eec3f-e7a9-43cc-a637-bf09fa2a9b80","year":2024},"citing_paper":{"arxiv_id":"2507.21521","last_updated":"2025-07-29T06:08:28Z","snapshot_observed_at":"2026-08-07T02:38:12.360447Z","submitted_at":"2025-07-29T06:08:28Z","title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T12:46:03.604799Z"},"links":{"citing_paper":"/paper/2507.21521"},"observation_digest":"sha256:99353189da1dba4cd8d675309bcd8ee2106a57d1ff650ccf32fc9e72389a15cc","observation_id":"399d002e-f3bd-453d-8236-bf4f1023c2dd","resolution":{"observed_at":"2026-08-06T12:46:04.332860Z","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":"2026-08-06T12:46:03.759318Z","title":"Learning to prompt for vision- language models,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.21521","last_updated":"2025-07-29T06:08:28Z","snapshot_observed_at":"2026-08-07T02:38:12.360447Z","submitted_at":"2025-07-29T06:08:28Z","title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T12:46:03.759318Z"},"links":{"citing_paper":"/paper/2507.21521"},"observation_digest":"sha256:6f70742f62e54bcdf225180fc4094556913592ff967fb80eaa25dbbcb2edf426","observation_id":"9c00f7a4-76a9-49cb-be5f-56f07d81d36a","resolution":{"observed_at":"2026-08-06T12:46:03.759318Z","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":"2026-08-06T12:46:04.316790Z","title":"One-shot active learning for image segmentation via contrastive learning and diversity-based sampling,","venue":null,"work_id":"63be48c9-d70f-4aa6-b1a3-9565eea07e59","year":2022},"citing_paper":{"arxiv_id":"2507.21521","last_updated":"2025-07-29T06:08:28Z","snapshot_observed_at":"2026-08-07T02:38:12.360447Z","submitted_at":"2025-07-29T06:08:28Z","title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T12:46:03.922168Z"},"links":{"citing_paper":"/paper/2507.21521"},"observation_digest":"sha256:8926958d93181e5ea5bc9b109c2ab198cabef4692884e6abb7c5d503312db8b1","observation_id":"064d979c-6c22-4bf7-a375-e95a9f69e762","resolution":{"observed_at":"2026-08-06T12:46:04.320388Z","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":"2026-08-06T12:46:04.308435Z","title":"Few-shot object detection with foundation models,","venue":null,"work_id":"cb45ba4c-82f4-4bf0-92f9-eb4824ea5e8c","year":2024},"citing_paper":{"arxiv_id":"2507.21521","last_updated":"2025-07-29T06:08:28Z","snapshot_observed_at":"2026-08-07T02:38:12.360447Z","submitted_at":"2025-07-29T06:08:28Z","title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T12:46:03.990535Z"},"links":{"citing_paper":"/paper/2507.21521"},"observation_digest":"sha256:07d90d33f5171009e2a6d362f8f2ff4de32428089bb04990298869d0845e83d7","observation_id":"d2af5cbb-28da-4af2-961c-871ad52460ff","resolution":{"observed_at":"2026-08-06T12:46:04.311051Z","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":"2026-08-06T12:46:03.992472Z","title":"A closer look at the few-shot adaptation of large vision-language models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.21521","last_updated":"2025-07-29T06:08:28Z","snapshot_observed_at":"2026-08-07T02:38:12.360447Z","submitted_at":"2025-07-29T06:08:28Z","title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T12:46:03.992472Z"},"links":{"citing_paper":"/paper/2507.21521"},"observation_digest":"sha256:2b31325de4be99a8d1c346da26f085914ea443cb8ae4fb5efb486bf654f9d088","observation_id":"25c6cb68-7b5c-4278-ac16-a15da8ec474f","resolution":{"observed_at":"2026-08-06T12:46:03.992472Z","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":"2026-08-06T12:46:04.295100Z","title":"Parameter efficient fine-tuning via cross block orchestration for segment anything model,","venue":null,"work_id":"dec4a93e-7ca1-4961-ad4a-3ccafd0cca6c","year":2024},"citing_paper":{"arxiv_id":"2507.21521","last_updated":"2025-07-29T06:08:28Z","snapshot_observed_at":"2026-08-07T02:38:12.360447Z","submitted_at":"2025-07-29T06:08:28Z","title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T12:46:03.994477Z"},"links":{"citing_paper":"/paper/2507.21521"},"observation_digest":"sha256:fa4c90015b2576a42f2c86236762bbc9cb6a45958961d160d29dd4acb7d98e6b","observation_id":"f724db10-fde3-4ae0-8c69-e7770f394910","resolution":{"observed_at":"2026-08-06T12:46:04.297770Z","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":"2026-08-06T12:46:04.287767Z","title":"Pela: Learning parameter- efficient models with low-rank approximation,","venue":null,"work_id":"c072413b-eb60-4058-95bd-962f89883e45","year":2024},"citing_paper":{"arxiv_id":"2507.21521","last_updated":"2025-07-29T06:08:28Z","snapshot_observed_at":"2026-08-07T02:38:12.360447Z","submitted_at":"2025-07-29T06:08:28Z","title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T12:46:03.997061Z"},"links":{"citing_paper":"/paper/2507.21521"},"observation_digest":"sha256:d9d06d0402b313492c8d9f0ff882cfdb12627cdfabf18415a255e6fbb4bd5aae","observation_id":"dfcd021a-fa7e-4a50-b249-27c7d73ae5b1","resolution":{"observed_at":"2026-08-06T12:46:04.290268Z","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":"2026-08-06T12:46:04.280089Z","title":"Maple: Multi-modal prompt learning,","venue":null,"work_id":"a3cecdde-e530-4199-9ba4-af53704f6ec1","year":2023},"citing_paper":{"arxiv_id":"2507.21521","last_updated":"2025-07-29T06:08:28Z","snapshot_observed_at":"2026-08-07T02:38:12.360447Z","submitted_at":"2025-07-29T06:08:28Z","title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T12:46:03.999551Z"},"links":{"citing_paper":"/paper/2507.21521"},"observation_digest":"sha256:eb1e47a7b580cac0ffe65d77e6140395cdda81819dfe84003b8b3ab4e6f1f295","observation_id":"b637528d-9374-45b3-814d-5b1c8bc4774a","resolution":{"observed_at":"2026-08-06T12:46:04.282685Z","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":"2026-08-06T12:46:04.001769Z","title":"Conditional prompt learning for vision-language models,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.21521","last_updated":"2025-07-29T06:08:28Z","snapshot_observed_at":"2026-08-07T02:38:12.360447Z","submitted_at":"2025-07-29T06:08:28Z","title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-06T12:46:04.001769Z"},"links":{"citing_paper":"/paper/2507.21521"},"observation_digest":"sha256:b4437c98c06a34b1b5ec8bc1657195910ad3abfd7e46c512b5eecc299cab0f07","observation_id":"5e0598b4-57de-4e94-8f50-2ae0ad607d60","resolution":{"observed_at":"2026-08-06T12:46:04.001769Z","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":"2026-08-06T12:46:04.268298Z","title":"Improving model calibration with accu- racy versus uncertainty optimization,","venue":null,"work_id":"900bd283-fd9a-4308-9d0e-69b52c0e5596","year":2020},"citing_paper":{"arxiv_id":"2507.21521","last_updated":"2025-07-29T06:08:28Z","snapshot_observed_at":"2026-08-07T02:38:12.360447Z","submitted_at":"2025-07-29T06:08:28Z","title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-06T12:46:04.004168Z"},"links":{"citing_paper":"/paper/2507.21521"},"observation_digest":"sha256:eb283ee9e599d920e824f7900ec30ac16fd99d0b945639422b6ae38250e59d74","observation_id":"7554a4db-5ef4-4b4a-b766-8a8859b6aed4","resolution":{"observed_at":"2026-08-06T12:46:04.270840Z","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":"2026-08-06T12:46:04.261080Z","title":"Soft calibration objectives for neural net- works,","venue":null,"work_id":"e74ca275-e63a-47f3-9650-816cb5d95172","year":2021},"citing_paper":{"arxiv_id":"2507.21521","last_updated":"2025-07-29T06:08:28Z","snapshot_observed_at":"2026-08-07T02:38:12.360447Z","submitted_at":"2025-07-29T06:08:28Z","title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-06T12:46:04.006738Z"},"links":{"citing_paper":"/paper/2507.21521"},"observation_digest":"sha256:ab60ef7f453ea2df1e28b287491d887806a58a920629ebb9eb07dc88e62dfd83","observation_id":"c2a3d193-475a-456a-b4fa-9d569e69bf6b","resolution":{"observed_at":"2026-08-06T12:46:04.263560Z","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":"2026-08-06T12:46:04.253007Z","title":"The power of scale for parameter-efficient prompt tuning,","venue":null,"work_id":"2e149d71-a40d-4eea-b4b4-99d67bb33cc6","year":2021},"citing_paper":{"arxiv_id":"2507.21521","last_updated":"2025-07-29T06:08:28Z","snapshot_observed_at":"2026-08-07T02:38:12.360447Z","submitted_at":"2025-07-29T06:08:28Z","title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-06T12:46:04.009664Z"},"links":{"citing_paper":"/paper/2507.21521"},"observation_digest":"sha256:5fdf635c35695348a965bd5d883672c26d4a1fb8a2b20962e2a31537878b4555","observation_id":"bddf8222-c0b7-4778-aaf9-7f00430a1b8f","resolution":{"observed_at":"2026-08-06T12:46:04.255821Z","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":"2026-08-06T12:46:04.012261Z","title":"LoRA: Low-rank adaptation of large language models,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.21521","last_updated":"2025-07-29T06:08:28Z","snapshot_observed_at":"2026-08-07T02:38:12.360447Z","submitted_at":"2025-07-29T06:08:28Z","title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-06T12:46:04.012261Z"},"links":{"citing_paper":"/paper/2507.21521"},"observation_digest":"sha256:aa324b8102e479434ebd238162608ca9883b1ca50ae0293f8f174e38e177ea2b","observation_id":"0c94b7d0-e936-43c8-864f-1b5bfbbbe81e","resolution":{"observed_at":"2026-08-06T12:46:04.012261Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1906.03671","last_updated":"2020-02-24T02:14:51Z","snapshot_observed_at":"2026-07-06T07:59:03.272339Z","submitted_at":"2019-06-09T16:52:09Z","title":"Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1906.03671","snapshot_observed_at":"2026-08-06T12:46:04.014559Z","title":"Deep batch active learning by diverse, uncertain gradient lower bounds,","venue":null,"work_id":null,"year":1906},"citing_paper":{"arxiv_id":"2507.21521","last_updated":"2025-07-29T06:08:28Z","snapshot_observed_at":"2026-08-07T02:38:12.360447Z","submitted_at":"2025-07-29T06:08:28Z","title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-06T12:46:04.014559Z"},"links":{"cited_paper":"/paper/1906.03671","citing_paper":"/paper/2507.21521"},"observation_digest":"sha256:c4d0aaf86bbb50b6b3e9bc8fc3b490e6ef6f2063f30db5c94904202e4a36642a","observation_id":"d4e80636-1be6-4816-9c86-9295c73ce008","resolution":{"observed_at":"2026-08-06T12:46:04.014559Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.06873","last_updated":"2022-08-14T19:39:03Z","snapshot_observed_at":"2026-08-04T11:32:56.707013Z","submitted_at":"2021-09-13T21:09:21Z","title":"Robust Contrastive Active Learning with Feature-guided Query Strategies","version":2},"cited_work":{"arxiv_id":"2109.06873","doi":null,"metadata_source":"pith","pith_arxiv_id":"2109.06873","snapshot_observed_at":"2026-08-06T12:46:04.092749Z","title":"Robust Contrastive Active Learning with Feature-guided Query Strategies","venue":"cs.LG","work_id":"630f9dc6-46f0-451d-8534-bef3a4cbbbf5","year":2021},"citing_paper":{"arxiv_id":"2507.21521","last_updated":"2025-07-29T06:08:28Z","snapshot_observed_at":"2026-08-07T02:38:12.360447Z","submitted_at":"2025-07-29T06:08:28Z","title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-06T12:46:04.017437Z"},"links":{"cited_paper":"/paper/2109.06873","citing_paper":"/paper/2507.21521"},"observation_digest":"sha256:b6d3d2c72ec8e0af5da4ffca39c5505f9b2334afc85efe549c2bdba3e94f5349","observation_id":"bd409e3e-7045-40bc-a26b-f8ba2a15787a","resolution":{"observed_at":"2026-08-06T12:46:04.095342Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T12:46:04.020385Z","title":"On calibration of modern neural networks,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.21521","last_updated":"2025-07-29T06:08:28Z","snapshot_observed_at":"2026-08-07T02:38:12.360447Z","submitted_at":"2025-07-29T06:08:28Z","title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-06T12:46:04.020385Z"},"links":{"citing_paper":"/paper/2507.21521"},"observation_digest":"sha256:e74b9c1e606bdbac7ec4ca9dd19f5bf824198f97319719e282ba4cab376e82f4","observation_id":"2e65d409-6963-40f1-8f5d-2336bf58a853","resolution":{"observed_at":"2026-08-06T12:46:04.020385Z","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":"2026-08-06T12:46:04.233536Z","title":"Obtaining well calibrated probabilities using bayesian binning,","venue":null,"work_id":"4c48a9e7-5a2c-4904-9443-b50c52958194","year":2015},"citing_paper":{"arxiv_id":"2507.21521","last_updated":"2025-07-29T06:08:28Z","snapshot_observed_at":"2026-08-07T02:38:12.360447Z","submitted_at":"2025-07-29T06:08:28Z","title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-06T12:46:04.023124Z"},"links":{"citing_paper":"/paper/2507.21521"},"observation_digest":"sha256:ac313116989620347ba99250487f8fd48c6e5568337e933f048b9628865da4eb","observation_id":"d829a6b1-d192-45c9-83a2-8c33348dbafd","resolution":{"observed_at":"2026-08-06T12:46:04.236945Z","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":"2026-08-06T12:46:04.025094Z","title":"A mathematical theory of communication,","venue":null,"work_id":null,"year":1948},"citing_paper":{"arxiv_id":"2507.21521","last_updated":"2025-07-29T06:08:28Z","snapshot_observed_at":"2026-08-07T02:38:12.360447Z","submitted_at":"2025-07-29T06:08:28Z","title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-06T12:46:04.025094Z"},"links":{"citing_paper":"/paper/2507.21521"},"observation_digest":"sha256:93d6d710b9d1641fa33676bbde888fbc911fc953a4660e1f3b4eb421dd3acd47","observation_id":"67e5542f-aa0d-41f7-a554-10f917303ec5","resolution":{"observed_at":"2026-08-06T12:46:04.025094Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1112.5745","last_updated":"2011-12-24T17:53:19Z","snapshot_observed_at":"2026-07-06T02:40:01.191970Z","submitted_at":"2011-12-24T17:53:19Z","title":"Bayesian Active Learning for Classification and Preference Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1112.5745","snapshot_observed_at":"2026-08-06T12:46:04.027700Z","title":"Bayesian active learning for classification and preference learning,","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2507.21521","last_updated":"2025-07-29T06:08:28Z","snapshot_observed_at":"2026-08-07T02:38:12.360447Z","submitted_at":"2025-07-29T06:08:28Z","title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-06T12:46:04.027700Z"},"links":{"cited_paper":"/paper/1112.5745","citing_paper":"/paper/2507.21521"},"observation_digest":"sha256:cbdcb693b9fc0aad5cf433bc1abc99a82df82fc5d6b3ab759f1c6559baff7376","observation_id":"fb37595f-6baa-42cc-82c1-f9662eabb897","resolution":{"observed_at":"2026-08-06T12:46:04.027700Z","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":"2026-08-06T12:46:04.030346Z","title":"Deep deterministic uncertainty: A new simple baseline,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.21521","last_updated":"2025-07-29T06:08:28Z","snapshot_observed_at":"2026-08-07T02:38:12.360447Z","submitted_at":"2025-07-29T06:08:28Z","title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-06T12:46:04.030346Z"},"links":{"citing_paper":"/paper/2507.21521"},"observation_digest":"sha256:f4fc54aa4a7aca1f7dbdce7c4f4d873420e76bfea0427452d2132d8530fab1bf","observation_id":"a0a95603-d8ac-4ee1-9c2d-894521549f8e","resolution":{"observed_at":"2026-08-06T12:46:04.030346Z","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":"2026-08-06T12:46:04.217890Z","title":"Active learning for convolutional neural networks: A core-set approach,","venue":null,"work_id":"e395dbc1-2b94-42a3-b446-c6b10b0cbbae","year":2018},"citing_paper":{"arxiv_id":"2507.21521","last_updated":"2025-07-29T06:08:28Z","snapshot_observed_at":"2026-08-07T02:38:12.360447Z","submitted_at":"2025-07-29T06:08:28Z","title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-06T12:46:04.036878Z"},"links":{"citing_paper":"/paper/2507.21521"},"observation_digest":"sha256:7dcf28462bf2a62540497c1bc799cc15962367ead6a7530289071049b9b7fa9c","observation_id":"9875afff-6fa5-46d9-a6b1-fc9500f2f7cf","resolution":{"observed_at":"2026-08-06T12:46:04.220198Z","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":"2026-08-06T12:46:04.211599Z","title":"Eurosat: A novel dataset and deep learning benchmark for land use and land cover classi- fication,","venue":null,"work_id":"b0fbae21-b7e3-4fc1-9e6e-525d0b2c4628","year":2019},"citing_paper":{"arxiv_id":"2507.21521","last_updated":"2025-07-29T06:08:28Z","snapshot_observed_at":"2026-08-07T02:38:12.360447Z","submitted_at":"2025-07-29T06:08:28Z","title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-06T12:46:04.039379Z"},"links":{"citing_paper":"/paper/2507.21521"},"observation_digest":"sha256:18a896a924044eb09208ac26237fb74c52d33d78ac507cf3760f7ab58d208020","observation_id":"729f7435-8c8a-487d-b74e-c0d5c71606c4","resolution":{"observed_at":"2026-08-06T12:46:04.213894Z","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":"2026-08-06T12:46:04.204471Z","title":"One-shot learning of object cate- gories,","venue":null,"work_id":"1d6b8061-a1ea-4089-97ae-87ff465466f6","year":2006},"citing_paper":{"arxiv_id":"2507.21521","last_updated":"2025-07-29T06:08:28Z","snapshot_observed_at":"2026-08-07T02:38:12.360447Z","submitted_at":"2025-07-29T06:08:28Z","title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-06T12:46:04.042006Z"},"links":{"citing_paper":"/paper/2507.21521"},"observation_digest":"sha256:30658f893d1bdc43c1af725f1481566fabfc3ffcefeaa9c3fbfbdae3555acfd0","observation_id":"dd7f5af7-e763-4bfe-acdd-05d6f0249966","resolution":{"observed_at":"2026-08-06T12:46:04.207518Z","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":"2026-08-06T12:46:04.198628Z","title":"Describing textures in the wild,","venue":null,"work_id":"46e3556d-db72-4f0a-af41-15a31ee4174b","year":2014},"citing_paper":{"arxiv_id":"2507.21521","last_updated":"2025-07-29T06:08:28Z","snapshot_observed_at":"2026-08-07T02:38:12.360447Z","submitted_at":"2025-07-29T06:08:28Z","title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-06T12:46:04.043919Z"},"links":{"citing_paper":"/paper/2507.21521"},"observation_digest":"sha256:3c7d70028b6de0fa9aa82ecd687c24be4ac3a4a98ab6a43dc967c1ea5d40f854","observation_id":"656b094b-a9d2-4856-b230-3ba8f48d3815","resolution":{"observed_at":"2026-08-06T12:46:04.200745Z","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":"2026-08-06T12:46:04.045738Z","title":"Cats and dogs,","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2507.21521","last_updated":"2025-07-29T06:08:28Z","snapshot_observed_at":"2026-08-07T02:38:12.360447Z","submitted_at":"2025-07-29T06:08:28Z","title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-06T12:46:04.045738Z"},"links":{"citing_paper":"/paper/2507.21521"},"observation_digest":"sha256:f56c138c651c76c712b5c760506bda131e4628551a13c42b4e76cf98fc004b81","observation_id":"f07b2bba-f23a-46f7-91e6-caac1965cc93","resolution":{"observed_at":"2026-08-06T12:46:04.045738Z","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":"2026-08-06T12:46:04.048156Z","title":"Deep residual learning for image recognition,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2507.21521","last_updated":"2025-07-29T06:08:28Z","snapshot_observed_at":"2026-08-07T02:38:12.360447Z","submitted_at":"2025-07-29T06:08:28Z","title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-06T12:46:04.048156Z"},"links":{"citing_paper":"/paper/2507.21521"},"observation_digest":"sha256:70214785c6c2c0a95a59d9d9daba58defac099ce0062dc8f5c9996539466df7f","observation_id":"15013dd3-d7c7-4c34-ac22-c93465d974bd","resolution":{"observed_at":"2026-08-06T12:46:04.048156Z","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":"2026-08-06T12:46:04.049919Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.21521","last_updated":"2025-07-29T06:08:28Z","snapshot_observed_at":"2026-08-07T02:38:12.360447Z","submitted_at":"2025-07-29T06:08:28Z","title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-06T12:46:04.049919Z"},"links":{"citing_paper":"/paper/2507.21521"},"observation_digest":"sha256:c54a646bdd73048d6412038e57d88c792ba944294799cb00ff3b8eeca8b20772","observation_id":"8ebe0d23-a516-4f29-be7a-364ed709d5f6","resolution":{"observed_at":"2026-08-06T12:46:04.049919Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.13320","last_updated":"2024-08-23T18:12:12Z","snapshot_observed_at":"2026-08-04T06:37:48.182655Z","submitted_at":"2024-08-23T18:12:12Z","title":"Online Zero-Shot Classification with CLIP","version":1},"cited_work":{"arxiv_id":"2408.13320","doi":"10.48550/arxiv.2408.13320","metadata_source":"pith","pith_arxiv_id":"2408.13320","snapshot_observed_at":"2026-08-06T18:16:30.548575Z","title":"Online Zero-Shot Classification with CLIP","venue":"cs.CV","work_id":"e3756fe2-8f61-4cf6-86c9-905005589e00","year":2024},"citing_paper":{"arxiv_id":"2507.21521","last_updated":"2025-07-29T06:08:28Z","snapshot_observed_at":"2026-08-07T02:38:12.360447Z","submitted_at":"2025-07-29T06:08:28Z","title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-06T12:46:04.051838Z"},"links":{"cited_paper":"/paper/2408.13320","citing_paper":"/paper/2507.21521"},"observation_digest":"sha256:904d832185cdb91b83cc3e01436c7229ba781f39466b47a867d5e1cab50a1a02","observation_id":"946fbee6-7d35-4fb4-88ab-3849dc28b5d2","resolution":{"observed_at":"2026-08-06T12:46:04.079250Z","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":"2026-08-06T12:46:04.180401Z","title":"Low-rank few-shot adaptation of vision- language models,","venue":null,"work_id":"b15d0234-4896-4685-b956-c7aff513dac2","year":2024},"citing_paper":{"arxiv_id":"2507.21521","last_updated":"2025-07-29T06:08:28Z","snapshot_observed_at":"2026-08-07T02:38:12.360447Z","submitted_at":"2025-07-29T06:08:28Z","title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-06T12:46:04.053951Z"},"links":{"citing_paper":"/paper/2507.21521"},"observation_digest":"sha256:72e7ee0fb369b5e43b5072c4b1986fd39dc99c4e1b2eca8b58ac2c59b6f274ab","observation_id":"06d16255-03f9-4cf9-8a03-2eeae2038e9c","resolution":{"observed_at":"2026-08-06T12:46:04.183300Z","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"}}],"paper":{"arxiv_id":"2507.21521","last_updated":"2025-07-29T06:08:28Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-07T02:38:12.360447Z","submitted_at":"2025-07-29T06:08:28Z","title":"Optimizing Active Learning in Vision-Language Models via Parameter-Efficient Uncertainty Calibration"},"reference_resolution":{"displayed":60,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":21,"verified_exact":5,"verified_fuzzy":34},"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":"2026-08-08T06:32:00.761636+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 60 of 60 outbound references and 0 inbound Pith citation observations for arXiv:2507.21521."}