{"as_of":"2026-08-22T06:10:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:081be00a8329f8208e3ffa2a8d28381e95961f440f23178b8f5ae9fa08fc073a","coverage":[{"denominator":62,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":62,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-04T14:42:49.120675Z","state":"measured"},{"denominator":62,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":62,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-21T06:32:19.484+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/2509.24181/citation-record","integrity":"/paper/2509.24181/integrity","json":"/paper/2509.24181/citation-record.json","paper":"/paper/2509.24181"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T14:42:42.517293Z","title":"Contextual diversity for active learning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.24181","last_updated":"2026-07-05T11:12:50Z","snapshot_observed_at":"2026-08-13T17:57:32.754748Z","submitted_at":"2025-09-29T02:03:44Z","title":"Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-04T14:42:42.517293Z"},"links":{"citing_paper":"/paper/2509.24181"},"observation_digest":"sha256:888ad1cf98c3a35fecfeb1e8fcb41c1e23532ab51e1a6109a7386c5614679ff9","observation_id":"5d9fca05-8cac-4c49-b6f2-9b5439cf31fd","resolution":{"observed_at":"2026-08-04T14:42:42.517293Z","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":"2026-08-04T14:42:42.641333Z","title":"Active learning: A sur- vey","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2509.24181","last_updated":"2026-07-05T11:12:50Z","snapshot_observed_at":"2026-08-13T17:57:32.754748Z","submitted_at":"2025-09-29T02:03:44Z","title":"Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-04T14:42:42.641333Z"},"links":{"citing_paper":"/paper/2509.24181"},"observation_digest":"sha256:0c86d3e9beedc58b833362b48bf596212927e4a1818689e3559c0b8e40ef4df2","observation_id":"0fcf2c1c-d43e-4bc3-82a2-2589802f3c95","resolution":{"observed_at":"2026-08-04T14:42:42.641333Z","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":"2026-08-20T07:10:23.511589Z","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":"2026-08-04T14:42:42.765444Z","title":"Deep batch active learning by diverse, uncertain gradient lower bounds.arXiv preprint arXiv:1906.03671, 2019","venue":null,"work_id":null,"year":1906},"citing_paper":{"arxiv_id":"2509.24181","last_updated":"2026-07-05T11:12:50Z","snapshot_observed_at":"2026-08-13T17:57:32.754748Z","submitted_at":"2025-09-29T02:03:44Z","title":"Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-04T14:42:42.765444Z"},"links":{"cited_paper":"/paper/1906.03671","citing_paper":"/paper/2509.24181"},"observation_digest":"sha256:b747600a615a13fe21b50989c4e0e4ce748a60aee6b0db39ca99b02a8fde8b66","observation_id":"9ed2f804-3d7f-4442-8498-fcd951770181","resolution":{"observed_at":"2026-08-04T14:42:42.765444Z","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":"2026-08-04T14:42:42.864611Z","title":"Training con- nectionist networks with queries and selective sampling.Ad- vances in neural information processing systems, 2, 1989","venue":null,"work_id":null,"year":1989},"citing_paper":{"arxiv_id":"2509.24181","last_updated":"2026-07-05T11:12:50Z","snapshot_observed_at":"2026-08-13T17:57:32.754748Z","submitted_at":"2025-09-29T02:03:44Z","title":"Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-04T14:42:42.864611Z"},"links":{"citing_paper":"/paper/2509.24181"},"observation_digest":"sha256:f5e1f4c734ea992a72bcfc013774d906888647f6ddd7e98480044d51b200cae2","observation_id":"3409703b-4eb8-4db1-a067-0ac07c0836c8","resolution":{"observed_at":"2026-08-04T14:42:42.864611Z","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":"2026-08-04T14:42:43.034689Z","title":"Gener- alized coverage for more robust low-budget active learning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.24181","last_updated":"2026-07-05T11:12:50Z","snapshot_observed_at":"2026-08-13T17:57:32.754748Z","submitted_at":"2025-09-29T02:03:44Z","title":"Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-04T14:42:43.034689Z"},"links":{"citing_paper":"/paper/2509.24181"},"observation_digest":"sha256:6df3fddfd6e15d8b707acd8dfc01233e5816deca32bcf8a0a7e4583b48728673","observation_id":"d9671458-467c-4374-bdf3-81926cdcc1c7","resolution":{"observed_at":"2026-08-04T14:42:43.034689Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.20644","last_updated":"2025-02-27T17:33:30Z","snapshot_observed_at":"2026-08-11T06:41:16.065004Z","submitted_at":"2024-12-30T01:33:42Z","title":"Uncertainty Herding: One Active Learning Method for All Label Budgets","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.20644","snapshot_observed_at":"2026-08-04T14:42:43.176932Z","title":"Uncertainty herding: One active learning method for all label budgets.arXiv preprint arXiv:2412.20644, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.24181","last_updated":"2026-07-05T11:12:50Z","snapshot_observed_at":"2026-08-13T17:57:32.754748Z","submitted_at":"2025-09-29T02:03:44Z","title":"Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-04T14:42:43.176932Z"},"links":{"cited_paper":"/paper/2412.20644","citing_paper":"/paper/2509.24181"},"observation_digest":"sha256:46b8aa0362938d09f61e72ede913137f1300681e611d17c1fd4a8d6278f054f6","observation_id":"20c908a5-9942-4ef8-9004-1e944a2e5348","resolution":{"observed_at":"2026-08-04T14:42:43.176932Z","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":"2026-08-04T14:42:43.296324Z","title":"Mar- gin based active learning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.24181","last_updated":"2026-07-05T11:12:50Z","snapshot_observed_at":"2026-08-13T17:57:32.754748Z","submitted_at":"2025-09-29T02:03:44Z","title":"Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-04T14:42:43.296324Z"},"links":{"citing_paper":"/paper/2509.24181"},"observation_digest":"sha256:dca1976705b70fc670a3ab2cc370d5724b92e94c8c131e8b840c2338676da8a8","observation_id":"b5387214-6ffa-40f2-8c61-dbc616547d11","resolution":{"observed_at":"2026-08-04T14:42:43.296324Z","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":"2026-08-04T14:42:43.371015Z","title":"Food-101–mining discriminative components with random forests","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2509.24181","last_updated":"2026-07-05T11:12:50Z","snapshot_observed_at":"2026-08-13T17:57:32.754748Z","submitted_at":"2025-09-29T02:03:44Z","title":"Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-04T14:42:43.371015Z"},"links":{"citing_paper":"/paper/2509.24181"},"observation_digest":"sha256:ec3c1c0e387e69ded5e0e4059710ee8804abc7dd8ad2c4b0d0c4d13e26f7d611","observation_id":"75879d30-4850-49fa-9606-e6099e44fbd6","resolution":{"observed_at":"2026-08-04T14:42:43.371015Z","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":"2026-08-04T14:42:43.442187Z","title":"Se- quential graph convolutional network for active learning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.24181","last_updated":"2026-07-05T11:12:50Z","snapshot_observed_at":"2026-08-13T17:57:32.754748Z","submitted_at":"2025-09-29T02:03:44Z","title":"Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-04T14:42:43.442187Z"},"links":{"citing_paper":"/paper/2509.24181"},"observation_digest":"sha256:34ccb300cc8678d966437fe1418164a517978f9f7579317f626df9c64d78b573","observation_id":"1323c0d8-3a94-4b35-99d3-a7244719342c","resolution":{"observed_at":"2026-08-04T14:42:43.442187Z","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":"2026-08-04T14:42:43.513911Z","title":"Emerg- ing properties in self-supervised vision transformers","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.24181","last_updated":"2026-07-05T11:12:50Z","snapshot_observed_at":"2026-08-13T17:57:32.754748Z","submitted_at":"2025-09-29T02:03:44Z","title":"Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-04T14:42:43.513911Z"},"links":{"citing_paper":"/paper/2509.24181"},"observation_digest":"sha256:f398e6274def1ef7172f225e2fe2dc7d98d280a216bce7f9633ba892cf55d37a","observation_id":"1999b55c-c947-4cc6-afc7-fc782dfccf38","resolution":{"observed_at":"2026-08-04T14:42:43.513911Z","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":"2026-08-04T14:42:43.581158Z","title":"Debiased active learning with variational gradient rectifier","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.24181","last_updated":"2026-07-05T11:12:50Z","snapshot_observed_at":"2026-08-13T17:57:32.754748Z","submitted_at":"2025-09-29T02:03:44Z","title":"Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-04T14:42:43.581158Z"},"links":{"citing_paper":"/paper/2509.24181"},"observation_digest":"sha256:abc4d9600509eb71e74695d8a3b7b6fdb1b5f74407888fa822e15274b0a52fce","observation_id":"50460da3-f901-4620-8df9-da0b8b2edbd6","resolution":{"observed_at":"2026-08-04T14:42:43.581158Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2202.03822","last_updated":"2022-02-08T12:35:58Z","snapshot_observed_at":"2026-08-16T17:22:50.863487Z","submitted_at":"2022-02-08T12:35:58Z","title":"A Novel Plug-in Module for Fine-Grained Visual Classification","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.03822","snapshot_observed_at":"2026-08-04T14:42:43.663716Z","title":"A novel plug-in module for fine-grained visual classification","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.24181","last_updated":"2026-07-05T11:12:50Z","snapshot_observed_at":"2026-08-13T17:57:32.754748Z","submitted_at":"2025-09-29T02:03:44Z","title":"Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-04T14:42:43.663716Z"},"links":{"cited_paper":"/paper/2202.03822","citing_paper":"/paper/2509.24181"},"observation_digest":"sha256:2bf7d593fb60d1cd9b7b6ec484b9c13e935752f7410cb59003b512d71f086f7f","observation_id":"7aac1372-db5b-4936-beee-44f02e580812","resolution":{"observed_at":"2026-08-04T14:42:43.663716Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.11929","last_updated":"2021-06-03T13:08:56Z","snapshot_observed_at":"2026-08-16T09:25:53.087782Z","submitted_at":"2020-10-22T17:55:59Z","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.11929","snapshot_observed_at":"2026-08-04T14:42:43.732412Z","title":"An image is worth 16x16 words: Trans- formers for image recognition at scale.arXiv preprint arXiv:2010.11929, 2020","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2509.24181","last_updated":"2026-07-05T11:12:50Z","snapshot_observed_at":"2026-08-13T17:57:32.754748Z","submitted_at":"2025-09-29T02:03:44Z","title":"Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-04T14:42:43.732412Z"},"links":{"cited_paper":"/paper/2010.11929","citing_paper":"/paper/2509.24181"},"observation_digest":"sha256:169a2c493250bee33b701247b33d2a1f7b1d6e4d7fb8b0851c9d90f2e65ccc81","observation_id":"6283265f-08f5-4f8b-ab71-3b670ee3bc5f","resolution":{"observed_at":"2026-08-04T14:42:43.732412Z","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":"2026-08-04T14:42:43.816374Z","title":"Patchup: A feature-space block-level regularization technique for convo- lutional neural networks","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.24181","last_updated":"2026-07-05T11:12:50Z","snapshot_observed_at":"2026-08-13T17:57:32.754748Z","submitted_at":"2025-09-29T02:03:44Z","title":"Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-04T14:42:43.816374Z"},"links":{"citing_paper":"/paper/2509.24181"},"observation_digest":"sha256:a71848a2e5333ed58960e9f39399bc80691e6db2746c24adff684157a9548ef0","observation_id":"00a5443d-1b82-482c-9675-2953348152fb","resolution":{"observed_at":"2026-08-04T14:42:43.816374Z","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":"2026-08-04T14:42:43.898878Z","title":"Learning gener- ative visual models from few training examples: An incre- mental bayesian approach tested on 101 object categories","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2509.24181","last_updated":"2026-07-05T11:12:50Z","snapshot_observed_at":"2026-08-13T17:57:32.754748Z","submitted_at":"2025-09-29T02:03:44Z","title":"Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-04T14:42:43.898878Z"},"links":{"citing_paper":"/paper/2509.24181"},"observation_digest":"sha256:f991d16eb1bb87bd96c5094ce9640815a55c2cbdb3dbaf57e516156529d6f2f9","observation_id":"03e6e8fb-5b81-4572-a360-3e19bd7c92f5","resolution":{"observed_at":"2026-08-04T14:42:43.898878Z","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":"2026-08-04T14:42:43.979900Z","title":"Deep bayesian active learning with image data","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.24181","last_updated":"2026-07-05T11:12:50Z","snapshot_observed_at":"2026-08-13T17:57:32.754748Z","submitted_at":"2025-09-29T02:03:44Z","title":"Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-04T14:42:43.979900Z"},"links":{"citing_paper":"/paper/2509.24181"},"observation_digest":"sha256:f8c0562a4ad3cc07d72bc70782720dd96d9b26a9466f034afe85c18248c7dbd2","observation_id":"1bb19a6c-9e33-4f50-ac61-ab2e4d2868f3","resolution":{"observed_at":"2026-08-04T14:42:43.979900Z","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":"2026-08-04T14:42:44.035172Z","title":"Feature mixing-based active learn- ing for multi-label text classification","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.24181","last_updated":"2026-07-05T11:12:50Z","snapshot_observed_at":"2026-08-13T17:57:32.754748Z","submitted_at":"2025-09-29T02:03:44Z","title":"Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-04T14:42:44.035172Z"},"links":{"citing_paper":"/paper/2509.24181"},"observation_digest":"sha256:9ebfe0b699c5cb7db54e2a89c01f541138f32e4889d4026c31a252db66e44ce2","observation_id":"5ac1c673-802d-4a2e-9c27-229a7b2d1a00","resolution":{"observed_at":"2026-08-04T14:42:44.035172Z","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":"2026-08-04T14:42:44.110934Z","title":"Balque: Batch active learning by querying unstable examples with calibrated confidence.Pattern Recognition, 151:110385,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.24181","last_updated":"2026-07-05T11:12:50Z","snapshot_observed_at":"2026-08-13T17:57:32.754748Z","submitted_at":"2025-09-29T02:03:44Z","title":"Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-04T14:42:44.110934Z"},"links":{"citing_paper":"/paper/2509.24181"},"observation_digest":"sha256:5cedbda70fc309b0859d4d829b9554c6348e91810e87b7589dd7a4fb76e8ea8e","observation_id":"6729ff1e-561c-4568-87e3-bd297f136a9f","resolution":{"observed_at":"2026-08-04T14:42:44.110934Z","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":"2026-08-04T14:42:44.185332Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2509.24181","last_updated":"2026-07-05T11:12:50Z","snapshot_observed_at":"2026-08-13T17:57:32.754748Z","submitted_at":"2025-09-29T02:03:44Z","title":"Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-04T14:42:44.185332Z"},"links":{"citing_paper":"/paper/2509.24181"},"observation_digest":"sha256:a34db1ac76da3c113b1ac1b0d1acb725d6b5177e594a6a2c38c047b23754fb74","observation_id":"6ac2d818-2e9a-48e4-84cd-d47d60238dc6","resolution":{"observed_at":"2026-08-04T14:42:44.185332Z","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":"2026-08-04T14:42:44.263272Z","title":"Multi-class active learning for image classification","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2509.24181","last_updated":"2026-07-05T11:12:50Z","snapshot_observed_at":"2026-08-13T17:57:32.754748Z","submitted_at":"2025-09-29T02:03:44Z","title":"Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-04T14:42:44.263272Z"},"links":{"citing_paper":"/paper/2509.24181"},"observation_digest":"sha256:acc30ba77d61296db5c16c6fc4dfabbfbbe7bc6c3909f349a75b20b6c51ac3a2","observation_id":"dbce74b2-a530-4190-b551-902b58ace101","resolution":{"observed_at":"2026-08-04T14:42:44.263272Z","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":"2026-08-04T14:42:44.410683Z","title":"Novel dataset for fine-grained image categorization: Stanford dogs","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2509.24181","last_updated":"2026-07-05T11:12:50Z","snapshot_observed_at":"2026-08-13T17:57:32.754748Z","submitted_at":"2025-09-29T02:03:44Z","title":"Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-04T14:42:44.410683Z"},"links":{"citing_paper":"/paper/2509.24181"},"observation_digest":"sha256:f2f9ba420afd5089194fbb1147d8e61eca76fca7c2a18ee32e2441c6fb196d16","observation_id":"27e517c3-6e99-46c2-bb4f-d30690aa3150","resolution":{"observed_at":"2026-08-04T14:42:44.410683Z","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":"2026-08-04T14:42:44.461858Z","title":"Task-aware variational adversarial active learning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.24181","last_updated":"2026-07-05T11:12:50Z","snapshot_observed_at":"2026-08-13T17:57:32.754748Z","submitted_at":"2025-09-29T02:03:44Z","title":"Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-04T14:42:44.461858Z"},"links":{"citing_paper":"/paper/2509.24181"},"observation_digest":"sha256:bd50994d8a6bff0249394dc333be4c95374a573343928babb817feefcafde5ee","observation_id":"3e9feb82-ef7f-4fce-bea1-d21fd368c885","resolution":{"observed_at":"2026-08-04T14:42:44.461858Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6980","last_updated":"2017-01-30T01:27:54Z","snapshot_observed_at":"2026-08-17T19:26:44.032537Z","submitted_at":"2014-12-22T13:54:29Z","title":"Adam: A Method for Stochastic Optimization","version":9},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6980","snapshot_observed_at":"2026-08-04T14:42:44.557442Z","title":"Adam: A method for stochastic optimization.arXiv preprint arXiv:1412.6980,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.24181","last_updated":"2026-07-05T11:12:50Z","snapshot_observed_at":"2026-08-13T17:57:32.754748Z","submitted_at":"2025-09-29T02:03:44Z","title":"Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-04T14:42:44.557442Z"},"links":{"cited_paper":"/paper/1412.6980","citing_paper":"/paper/2509.24181"},"observation_digest":"sha256:748d52976460280d21dc8138a4cd6e95e914b0d52cc6edaed20d50a715b69212","observation_id":"3076b66e-605d-4440-8316-69f47222ad52","resolution":{"observed_at":"2026-08-04T14:42:44.557442Z","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":"2026-08-04T14:42:44.715322Z","title":"Learning active learning from data.Advances in neural in- formation processing systems, 30, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2509.24181","last_updated":"2026-07-05T11:12:50Z","snapshot_observed_at":"2026-08-13T17:57:32.754748Z","submitted_at":"2025-09-29T02:03:44Z","title":"Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-04T14:42:44.715322Z"},"links":{"citing_paper":"/paper/2509.24181"},"observation_digest":"sha256:34d6018631043e63e0da68e6ad8068f946e8e7f50ca2c07226407817945cb92a","observation_id":"f85ddc72-2449-4ac8-a43e-003cb3976870","resolution":{"observed_at":"2026-08-04T14:42:44.715322Z","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":"2026-08-04T14:42:44.858078Z","title":"Tidal: Learning training dynamics for active learning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.24181","last_updated":"2026-07-05T11:12:50Z","snapshot_observed_at":"2026-08-13T17:57:32.754748Z","submitted_at":"2025-09-29T02:03:44Z","title":"Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-04T14:42:44.858078Z"},"links":{"citing_paper":"/paper/2509.24181"},"observation_digest":"sha256:44efe6471b9134c7a782614bea7b47ffa4d62aa33d1c3cc97c71dfce82e6e12f","observation_id":"80d48a31-8c3c-4965-befc-d51a04fe6676","resolution":{"observed_at":"2026-08-04T14:42:44.858078Z","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":"2026-08-04T14:42:45.037621Z","title":"A survey on deep active learning: Recent advances and new frontiers.IEEE Trans- actions on Neural Networks and Learning Systems, 36(4): 5879–5899, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.24181","last_updated":"2026-07-05T11:12:50Z","snapshot_observed_at":"2026-08-13T17:57:32.754748Z","submitted_at":"2025-09-29T02:03:44Z","title":"Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-04T14:42:45.037621Z"},"links":{"citing_paper":"/paper/2509.24181"},"observation_digest":"sha256:6f18a8b3983b64554ef448c5186d552d2bffbeeefd9d563b7d4815bfad97a2cc","observation_id":"8629be9d-4a18-43fd-9016-106e60a638b0","resolution":{"observed_at":"2026-08-04T14:42:45.037621Z","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":"2026-08-04T14:42:45.097758Z","title":"Deep active 9 learning with noise stability","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.24181","last_updated":"2026-07-05T11:12:50Z","snapshot_observed_at":"2026-08-13T17:57:32.754748Z","submitted_at":"2025-09-29T02:03:44Z","title":"Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-04T14:42:45.097758Z"},"links":{"citing_paper":"/paper/2509.24181"},"observation_digest":"sha256:3c1577abf61d72ca43814dc8fe7b675831e889f985c777930650214d4a53f4cc","observation_id":"c3400389-7b18-4ffd-8bd6-9b6df77efb22","resolution":{"observed_at":"2026-08-04T14:42:45.097758Z","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":"2026-08-04T14:42:45.254005Z","title":"A survey on active deep learning: From model driven to data driven.ACM Computing Surveys (CSUR), 54(10s): 1–34, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.24181","last_updated":"2026-07-05T11:12:50Z","snapshot_observed_at":"2026-08-13T17:57:32.754748Z","submitted_at":"2025-09-29T02:03:44Z","title":"Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-04T14:42:45.254005Z"},"links":{"citing_paper":"/paper/2509.24181"},"observation_digest":"sha256:7bcc39eea5b342a2eb3873252c8d788f15a235d481d97abc8678591695e279a1","observation_id":"03d3b315-1b01-4545-af35-48032cf111a4","resolution":{"observed_at":"2026-08-04T14:42:45.254005Z","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":"2026-08-04T14:42:45.356054Z","title":"Influence selection for active learning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.24181","last_updated":"2026-07-05T11:12:50Z","snapshot_observed_at":"2026-08-13T17:57:32.754748Z","submitted_at":"2025-09-29T02:03:44Z","title":"Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-04T14:42:45.356054Z"},"links":{"citing_paper":"/paper/2509.24181"},"observation_digest":"sha256:820a5591f4389e11067e9041fa321f4d4b207ab658c520390c38a76677aca151","observation_id":"f2277591-12fc-4191-b05e-be78b77124ed","resolution":{"observed_at":"2026-08-04T14:42:45.356054Z","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":"2026-08-04T14:42:45.438422Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.24181","last_updated":"2026-07-05T11:12:50Z","snapshot_observed_at":"2026-08-13T17:57:32.754748Z","submitted_at":"2025-09-29T02:03:44Z","title":"Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-04T14:42:45.438422Z"},"links":{"citing_paper":"/paper/2509.24181"},"observation_digest":"sha256:581a7269b9cb5a2d875634dd1c3d5f9d510a13496cf3444ffb40f78b90a42c8e","observation_id":"ef98ac93-b964-4f8b-8eb7-564628c3e026","resolution":{"observed_at":"2026-08-04T14:42:45.438422Z","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":"2026-08-04T14:42:45.504432Z","title":"Visualizing data using t-sne.Journal of machine learning research, 9 (Nov):2579–2605, 2008","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2509.24181","last_updated":"2026-07-05T11:12:50Z","snapshot_observed_at":"2026-08-13T17:57:32.754748Z","submitted_at":"2025-09-29T02:03:44Z","title":"Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-04T14:42:45.504432Z"},"links":{"citing_paper":"/paper/2509.24181"},"observation_digest":"sha256:8a79159b8330dd880800d369fcca9b82ba1234ccbfb423b2bd2b75337cac70a0","observation_id":"383ae97a-24d7-4e76-85ce-0d0e567b803c","resolution":{"observed_at":"2026-08-04T14:42:45.504432Z","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":"2026-08-04T14:42:45.640562Z","title":"Instance-wise supervision- level optimization in active learning","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.24181","last_updated":"2026-07-05T11:12:50Z","snapshot_observed_at":"2026-08-13T17:57:32.754748Z","submitted_at":"2025-09-29T02:03:44Z","title":"Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-04T14:42:45.640562Z"},"links":{"citing_paper":"/paper/2509.24181"},"observation_digest":"sha256:d8161fcd0449170b881e6a3d6ef15f05b495c329af2d9784782b26b981fa3bb3","observation_id":"e33392e4-66ea-4616-96df-a9d52f7171fa","resolution":{"observed_at":"2026-08-04T14:42:45.640562Z","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":"2026-08-04T14:42:45.720345Z","title":"Deep deterministic un- certainty: A new simple baseline","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.24181","last_updated":"2026-07-05T11:12:50Z","snapshot_observed_at":"2026-08-13T17:57:32.754748Z","submitted_at":"2025-09-29T02:03:44Z","title":"Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-04T14:42:45.720345Z"},"links":{"citing_paper":"/paper/2509.24181"},"observation_digest":"sha256:d2f4ef95a87a5fca7e836b0adaaa43afd80473c271dc265be7c989fbd5011b0d","observation_id":"ee091e78-70dc-45ed-9bd8-49546993ecaa","resolution":{"observed_at":"2026-08-04T14:42:45.720345Z","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":"2026-08-04T14:42:45.776387Z","title":"Automated flower classification over a large number of classes","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2509.24181","last_updated":"2026-07-05T11:12:50Z","snapshot_observed_at":"2026-08-13T17:57:32.754748Z","submitted_at":"2025-09-29T02:03:44Z","title":"Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-04T14:42:45.776387Z"},"links":{"citing_paper":"/paper/2509.24181"},"observation_digest":"sha256:c327a5cee99a89bbaabb8c231d50a35f10de89fcf395700641c57401bda5beee","observation_id":"35516a73-1ed3-4bba-9e94-8cd185c50363","resolution":{"observed_at":"2026-08-04T14:42:45.776387Z","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":"2026-08-04T14:42:45.859131Z","title":"Cats and dogs","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2509.24181","last_updated":"2026-07-05T11:12:50Z","snapshot_observed_at":"2026-08-13T17:57:32.754748Z","submitted_at":"2025-09-29T02:03:44Z","title":"Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-04T14:42:45.859131Z"},"links":{"citing_paper":"/paper/2509.24181"},"observation_digest":"sha256:7f5149038b2892ad6c95d6373aab50776f00bfd11e88c1233dc5af9177f59adb","observation_id":"82e29597-f7f5-44f6-9a42-7882bfe41f42","resolution":{"observed_at":"2026-08-04T14:42:45.859131Z","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":"2026-08-04T14:42:45.918770Z","title":"Active learning by feature mixing","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.24181","last_updated":"2026-07-05T11:12:50Z","snapshot_observed_at":"2026-08-13T17:57:32.754748Z","submitted_at":"2025-09-29T02:03:44Z","title":"Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-04T14:42:45.918770Z"},"links":{"citing_paper":"/paper/2509.24181"},"observation_digest":"sha256:bb7703e34eaad254ebcef94b607ae4871f26edb192e5340f77681c40ca82e25c","observation_id":"193fc627-3cb5-4137-a19a-f40251563dff","resolution":{"observed_at":"2026-08-04T14:42:45.918770Z","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":"2026-08-04T14:42:45.977596Z","title":"Automatic differentiation in pytorch","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2509.24181","last_updated":"2026-07-05T11:12:50Z","snapshot_observed_at":"2026-08-13T17:57:32.754748Z","submitted_at":"2025-09-29T02:03:44Z","title":"Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-04T14:42:45.977596Z"},"links":{"citing_paper":"/paper/2509.24181"},"observation_digest":"sha256:50f0e08dbbff62470659b4a74d145c2c520066f0e7bfcd73ec80ecc2f09e1e17","observation_id":"d82309e7-8ecb-4f02-b924-8e91219ec1ee","resolution":{"observed_at":"2026-08-04T14:42:45.977596Z","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":"2026-08-04T14:42:46.068866Z","title":"A survey of deep active learning.ACM computing surveys (CSUR), 54(9):1–40, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.24181","last_updated":"2026-07-05T11:12:50Z","snapshot_observed_at":"2026-08-13T17:57:32.754748Z","submitted_at":"2025-09-29T02:03:44Z","title":"Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-04T14:42:46.068866Z"},"links":{"citing_paper":"/paper/2509.24181"},"observation_digest":"sha256:caabcbe92fdad579c80728e67792b0e1350022451ca5ef8dece49ce320e5fb70","observation_id":"a7896192-3104-4c9c-b3a3-700a7dffa4f6","resolution":{"observed_at":"2026-08-04T14:42:46.068866Z","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":"2026-08-04T14:42:46.147768Z","title":"Margin-based active learning for structured output spaces","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2509.24181","last_updated":"2026-07-05T11:12:50Z","snapshot_observed_at":"2026-08-13T17:57:32.754748Z","submitted_at":"2025-09-29T02:03:44Z","title":"Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-04T14:42:46.147768Z"},"links":{"citing_paper":"/paper/2509.24181"},"observation_digest":"sha256:830228cd56c677c82356ebe22af478ad86fcb07632d110c60fd1c7d3bd0382fc","observation_id":"df2be9ca-494b-4fe4-876d-da62aa921c44","resolution":{"observed_at":"2026-08-04T14:42:46.147768Z","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":"2026-08-04T14:42:46.302878Z","title":"Active learning for vision- language models","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.24181","last_updated":"2026-07-05T11:12:50Z","snapshot_observed_at":"2026-08-13T17:57:32.754748Z","submitted_at":"2025-09-29T02:03:44Z","title":"Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-04T14:42:46.302878Z"},"links":{"citing_paper":"/paper/2509.24181"},"observation_digest":"sha256:eb4e5946ba9047f00da5e810f99ce141c6f07c9076d8ed50c5690e90502e51b5","observation_id":"73982cde-93a6-4f36-943c-43c8751d2395","resolution":{"observed_at":"2026-08-04T14:42:46.302878Z","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":"2026-08-04T14:42:46.407329Z","title":"Entropic open-set active learning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.24181","last_updated":"2026-07-05T11:12:50Z","snapshot_observed_at":"2026-08-13T17:57:32.754748Z","submitted_at":"2025-09-29T02:03:44Z","title":"Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-04T14:42:46.407329Z"},"links":{"citing_paper":"/paper/2509.24181"},"observation_digest":"sha256:7a7c286f53a3395ac18b89b1f81f12d6a33810f41954fe1cde0bbd74b86dc028","observation_id":"542989a5-a50e-4a88-8089-9238317c1ad7","resolution":{"observed_at":"2026-08-04T14:42:46.407329Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1708.00489","last_updated":"2018-06-01T10:17:23Z","snapshot_observed_at":"2026-08-16T13:51:24.988660Z","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":"2026-08-04T14:42:46.466934Z","title":"Active learning for convolu- tional neural networks: A core-set approach.arXiv preprint arXiv:1708.00489, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2509.24181","last_updated":"2026-07-05T11:12:50Z","snapshot_observed_at":"2026-08-13T17:57:32.754748Z","submitted_at":"2025-09-29T02:03:44Z","title":"Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-04T14:42:46.466934Z"},"links":{"cited_paper":"/paper/1708.00489","citing_paper":"/paper/2509.24181"},"observation_digest":"sha256:256da959a84d0419a879cc251b1d3bddfdf9c81c0b0b6d6419c5eeaacb020b03","observation_id":"6c279991-e123-4da5-bdde-a6313ba94a05","resolution":{"observed_at":"2026-08-04T14:42:46.466934Z","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":"2026-08-04T14:42:46.532909Z","title":"Active learning literature survey","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2509.24181","last_updated":"2026-07-05T11:12:50Z","snapshot_observed_at":"2026-08-13T17:57:32.754748Z","submitted_at":"2025-09-29T02:03:44Z","title":"Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-04T14:42:46.532909Z"},"links":{"citing_paper":"/paper/2509.24181"},"observation_digest":"sha256:858116f0973217c6ab9560cd0dfa16ce201f01ac67b3e035f8e292c54d757041","observation_id":"b82db62f-e905-4136-a6a0-d3369dae5f30","resolution":{"observed_at":"2026-08-04T14:42:46.532909Z","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":"2026-08-04T14:42:46.591588Z","title":"Vari- ational adversarial active learning","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.24181","last_updated":"2026-07-05T11:12:50Z","snapshot_observed_at":"2026-08-13T17:57:32.754748Z","submitted_at":"2025-09-29T02:03:44Z","title":"Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-04T14:42:46.591588Z"},"links":{"citing_paper":"/paper/2509.24181"},"observation_digest":"sha256:7b590dd94f105c91754c8b26eb3c1c6d29fb12f57b0473bd87eda925c533bbb5","observation_id":"fa006f24-76a8-4bc6-bd5d-736dfcdd04cd","resolution":{"observed_at":"2026-08-04T14:42:46.591588Z","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":"2026-08-04T14:42:46.647150Z","title":"The caltech-ucsd birds-200-2011 dataset","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2509.24181","last_updated":"2026-07-05T11:12:50Z","snapshot_observed_at":"2026-08-13T17:57:32.754748Z","submitted_at":"2025-09-29T02:03:44Z","title":"Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-04T14:42:46.647150Z"},"links":{"citing_paper":"/paper/2509.24181"},"observation_digest":"sha256:d776bd881d29b3fa701451229b5c7d6c6c3e429697cc28d2b35ef8b69ca5939f","observation_id":"d6d5dd41-4992-430c-8778-4e11e5c3203e","resolution":{"observed_at":"2026-08-04T14:42:46.647150Z","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":"2026-08-04T14:42:46.734734Z","title":"Mul- tiple instance differentiation learning for active object detec- tion.IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(10):12133–12147, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.24181","last_updated":"2026-07-05T11:12:50Z","snapshot_observed_at":"2026-08-13T17:57:32.754748Z","submitted_at":"2025-09-29T02:03:44Z","title":"Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-04T14:42:46.734734Z"},"links":{"citing_paper":"/paper/2509.24181"},"observation_digest":"sha256:b64b088c557f7efe76660c3ae350314abacdcd3f8a8045e239bedafc01c0bff1","observation_id":"e5a0e7f6-1bd6-4b59-ba50-35d94c40d6e9","resolution":{"observed_at":"2026-08-04T14:42:46.734734Z","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":"2026-08-04T14:42:46.894463Z","title":"A survey of dataset refinement for problems in com- puter vision datasets.ACM computing surveys, 56(7):1–34,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.24181","last_updated":"2026-07-05T11:12:50Z","snapshot_observed_at":"2026-08-13T17:57:32.754748Z","submitted_at":"2025-09-29T02:03:44Z","title":"Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-04T14:42:46.894463Z"},"links":{"citing_paper":"/paper/2509.24181"},"observation_digest":"sha256:469e754559dbfb1871fb8410d046a8065aa3f8d1ed30deea6901c29378825b32","observation_id":"135490e9-d26a-411b-b0f3-7cfd7d91c26e","resolution":{"observed_at":"2026-08-04T14:42:46.894463Z","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":"2026-08-04T14:42:46.996930Z","title":"A new active labeling method for deep learning","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2509.24181","last_updated":"2026-07-05T11:12:50Z","snapshot_observed_at":"2026-08-13T17:57:32.754748Z","submitted_at":"2025-09-29T02:03:44Z","title":"Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification","version":2},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-04T14:42:46.996930Z"},"links":{"citing_paper":"/paper/2509.24181"},"observation_digest":"sha256:5ff0207be3f184101e68007863e43ec6bce29dbbd51a3242be895aa17c8a9c43","observation_id":"49c16ea2-667f-451d-91cf-23395b27e71a","resolution":{"observed_at":"2026-08-04T14:42:46.996930Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2105.14559","last_updated":"2023-04-15T05:45:25Z","snapshot_observed_at":"2026-08-21T22:06:26.448703Z","submitted_at":"2021-05-30T14:49:10Z","title":"Active Learning in Bayesian Neural Networks with Balanced Entropy Learning Principle","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2105.14559","snapshot_observed_at":"2026-08-04T14:42:47.119056Z","title":"Active learning in bayesian neural networks with balanced entropy learning principle.arXiv preprint arXiv:2105.14559, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.24181","last_updated":"2026-07-05T11:12:50Z","snapshot_observed_at":"2026-08-13T17:57:32.754748Z","submitted_at":"2025-09-29T02:03:44Z","title":"Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-04T14:42:47.119056Z"},"links":{"cited_paper":"/paper/2105.14559","citing_paper":"/paper/2509.24181"},"observation_digest":"sha256:45b21681c33ecf3abc8d6d2a66304c048c16a72bddb493ac18b8c06ad1972ead","observation_id":"2cd018cb-636e-4284-99cd-f48a1cdb6827","resolution":{"observed_at":"2026-08-04T14:42:47.119056Z","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":"2026-08-04T14:42:47.250745Z","title":"Covid-al: The diagnosis of covid-19 with deep ac- tive learning.Medical Image Analysis, 68:101913, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.24181","last_updated":"2026-07-05T11:12:50Z","snapshot_observed_at":"2026-08-13T17:57:32.754748Z","submitted_at":"2025-09-29T02:03:44Z","title":"Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification","version":2},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-04T14:42:47.250745Z"},"links":{"citing_paper":"/paper/2509.24181"},"observation_digest":"sha256:8ce0475fe838797c269f0a95d6df8ef531c7e45dcf57545a51e0d74150df06fb","observation_id":"8634dd5d-791c-4ded-a487-98413dcc6612","resolution":{"observed_at":"2026-08-04T14:42:47.250745Z","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":"2026-08-04T14:42:47.414376Z","title":"Active learning for domain adaptation: An energy-based approach","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.24181","last_updated":"2026-07-05T11:12:50Z","snapshot_observed_at":"2026-08-13T17:57:32.754748Z","submitted_at":"2025-09-29T02:03:44Z","title":"Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification","version":2},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-04T14:42:47.414376Z"},"links":{"citing_paper":"/paper/2509.24181"},"observation_digest":"sha256:9f3e63543eb82a581cfa1389556ceecfebbc3e4cf1b67bdad045e66979067587","observation_id":"7bbaf4a0-71ac-4fc6-9141-b8a8bfd7e76a","resolution":{"observed_at":"2026-08-04T14:42:47.414376Z","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":"2026-08-04T14:42:47.584200Z","title":"Active finetuning: Exploiting an- notation budget in the pretraining-finetuning paradigm","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.24181","last_updated":"2026-07-05T11:12:50Z","snapshot_observed_at":"2026-08-13T17:57:32.754748Z","submitted_at":"2025-09-29T02:03:44Z","title":"Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification","version":2},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-04T14:42:47.584200Z"},"links":{"citing_paper":"/paper/2509.24181"},"observation_digest":"sha256:588629b9bd6fb4da63f24925ed846c24f80bb9bfb227a9e7a2bcf508fa177d52","observation_id":"9c6a8c25-0f83-4211-9703-c42fdc74381f","resolution":{"observed_at":"2026-08-04T14:42:47.584200Z","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":"2026-08-04T14:42:47.688980Z","title":"Active learning through a covering lens.Ad- vances in Neural Information Processing Systems, 35: 22354–22367, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.24181","last_updated":"2026-07-05T11:12:50Z","snapshot_observed_at":"2026-08-13T17:57:32.754748Z","submitted_at":"2025-09-29T02:03:44Z","title":"Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification","version":2},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-04T14:42:47.688980Z"},"links":{"citing_paper":"/paper/2509.24181"},"observation_digest":"sha256:3cb8b367a1d06c092645942e7a3fee2e3cb2888a46bee207ee8e2e3d4d309fab","observation_id":"0dd4556b-d73c-4c5a-b6be-06a18370b3af","resolution":{"observed_at":"2026-08-04T14:42:47.688980Z","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":"2026-08-04T14:42:47.811125Z","title":"Learning loss for ac- tive learning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.24181","last_updated":"2026-07-05T11:12:50Z","snapshot_observed_at":"2026-08-13T17:57:32.754748Z","submitted_at":"2025-09-29T02:03:44Z","title":"Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification","version":2},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-04T14:42:47.811125Z"},"links":{"citing_paper":"/paper/2509.24181"},"observation_digest":"sha256:d556cd86da85f0a056db059eedfab541e66937b596a18719df4706f1e9ae10a1","observation_id":"f6e974d1-b82a-4afd-9861-4b9b652cfd43","resolution":{"observed_at":"2026-08-04T14:42:47.811125Z","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":"2026-08-04T14:42:47.924196Z","title":"Data- centric artificial intelligence: A survey.ACM Computing Surveys, 57(5):1–42, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.24181","last_updated":"2026-07-05T11:12:50Z","snapshot_observed_at":"2026-08-13T17:57:32.754748Z","submitted_at":"2025-09-29T02:03:44Z","title":"Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification","version":2},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-04T14:42:47.924196Z"},"links":{"citing_paper":"/paper/2509.24181"},"observation_digest":"sha256:da972785802082b5fe7d40776f1048322106c1f94a49a42f7bb86ff4b34e5f1c","observation_id":"e3ebc114-4889-4107-b210-e65ee2912b5c","resolution":{"observed_at":"2026-08-04T14:42:47.924196Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.13450","last_updated":"2022-07-19T15:31:09Z","snapshot_observed_at":"2026-08-21T15:45:32.864264Z","submitted_at":"2022-03-25T05:17:24Z","title":"A Comparative Survey of Deep Active Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.13450","snapshot_observed_at":"2026-08-04T14:42:48.064775Z","title":"A compar- ative survey of deep active learning.arXiv preprint arXiv:2203.13450, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.24181","last_updated":"2026-07-05T11:12:50Z","snapshot_observed_at":"2026-08-13T17:57:32.754748Z","submitted_at":"2025-09-29T02:03:44Z","title":"Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification","version":2},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-04T14:42:48.064775Z"},"links":{"cited_paper":"/paper/2203.13450","citing_paper":"/paper/2509.24181"},"observation_digest":"sha256:71ba2c1abaa2990f17b92b1f1a456289ea8f40d056bbee3481c3654de30390cc","observation_id":"1b8815ab-332c-4f60-9dc4-71b7be4a66c0","resolution":{"observed_at":"2026-08-04T14:42:48.064775Z","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":"2026-08-04T14:42:48.202917Z","title":"State-relabeling adversar- ial active learning","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.24181","last_updated":"2026-07-05T11:12:50Z","snapshot_observed_at":"2026-08-13T17:57:32.754748Z","submitted_at":"2025-09-29T02:03:44Z","title":"Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification","version":2},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-04T14:42:48.202917Z"},"links":{"citing_paper":"/paper/2509.24181"},"observation_digest":"sha256:287691ffe622704fc8cd4c99700b59bc7e676593cdd60c37d1ec7840cfede1d7","observation_id":"5bfda398-4144-43ff-8158-c24562e750cb","resolution":{"observed_at":"2026-08-04T14:42:48.202917Z","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":"2026-08-04T14:42:48.403349Z","title":"Downstream-pretext domain knowledge traceback for active learning.IEEE Transactions on Multi- media, 26:10585–10596, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.24181","last_updated":"2026-07-05T11:12:50Z","snapshot_observed_at":"2026-08-13T17:57:32.754748Z","submitted_at":"2025-09-29T02:03:44Z","title":"Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification","version":2},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-04T14:42:48.403349Z"},"links":{"citing_paper":"/paper/2509.24181"},"observation_digest":"sha256:20027d1a4005b9860334bd43d5815a93c9dc2d492b3867ffa38d8ce9e6327421","observation_id":"2c2419dc-105f-4c4c-8dd3-09be6d9e246c","resolution":{"observed_at":"2026-08-04T14:42:48.403349Z","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":"2026-08-04T14:42:48.569892Z","title":"Employing feature mixture for active learning of object detection.Neurocomputing, 594:127883, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.24181","last_updated":"2026-07-05T11:12:50Z","snapshot_observed_at":"2026-08-13T17:57:32.754748Z","submitted_at":"2025-09-29T02:03:44Z","title":"Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification","version":2},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-04T14:42:48.569892Z"},"links":{"citing_paper":"/paper/2509.24181"},"observation_digest":"sha256:cd7c138798bfe87bccd73a9fe446540a03bd662c13c2166c4a6d3dd1d8fcc42e","observation_id":"c6ba1a6c-c48d-428c-bd01-5986f3c758c0","resolution":{"observed_at":"2026-08-04T14:42:48.569892Z","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":"2026-08-04T14:42:48.767193Z","title":"Multi-granularity archaeological dating of chinese bronze dings based on a knowledge-guided re- lation graph","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.24181","last_updated":"2026-07-05T11:12:50Z","snapshot_observed_at":"2026-08-13T17:57:32.754748Z","submitted_at":"2025-09-29T02:03:44Z","title":"Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification","version":2},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-04T14:42:48.767193Z"},"links":{"citing_paper":"/paper/2509.24181"},"observation_digest":"sha256:2cb994b0fca2b2ad327d3a8a0b2edb161a8665173e28f9dd2af329c3980973b9","observation_id":"a38656ec-8c25-4667-9005-601c78ca51bb","resolution":{"observed_at":"2026-08-04T14:42:48.767193Z","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":"2026-08-04T14:42:48.938949Z","title":"Rethinking epis- temic and aleatoric uncertainty for active open-set annota- tion: An energy-based approach","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.24181","last_updated":"2026-07-05T11:12:50Z","snapshot_observed_at":"2026-08-13T17:57:32.754748Z","submitted_at":"2025-09-29T02:03:44Z","title":"Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification","version":2},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-04T14:42:48.938949Z"},"links":{"citing_paper":"/paper/2509.24181"},"observation_digest":"sha256:99a16ba845f797521448b5f33be4eb8e27a86fd49f164564733e33c960dfadb7","observation_id":"b7c1b0c2-588e-4d78-a181-d7b80c582567","resolution":{"observed_at":"2026-08-04T14:42:48.938949Z","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":"2026-08-04T14:42:49.120675Z","title":"w/o Weighted","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.24181","last_updated":"2026-07-05T11:12:50Z","snapshot_observed_at":"2026-08-13T17:57:32.754748Z","submitted_at":"2025-09-29T02:03:44Z","title":"Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification","version":2},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-04T14:42:49.120675Z"},"links":{"citing_paper":"/paper/2509.24181"},"observation_digest":"sha256:fc345d1aae877e9f6c6744308832bab00a2404e93d5c445221b369d8febbe251","observation_id":"0b4b5011-8bbe-4bed-a54e-c69609cef991","resolution":{"observed_at":"2026-08-04T14:42:49.120675Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2509.24181","last_updated":"2026-07-05T11:12:50Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-13T17:57:32.754748Z","submitted_at":"2025-09-29T02:03:44Z","title":"Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification"},"reference_resolution":{"displayed":62,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":62,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":62},"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":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"thesis":"As of 22 August 2026, this Paper Citation Record lists 62 of 62 outbound references and 0 inbound Pith citation observations for arXiv:2509.24181."}