{"as_of":"2026-08-12T19:26:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:5ad0a528a00fa7871d3bb06fbcc3b8ed270b74d5daa811eb5f8e357c171e8ae6","coverage":[{"denominator":61,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":61,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T23:21:16.912001Z","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":"2026-08-12T06:34:41.77262+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-04T14:42:43.176932Z","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":[{"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":"2026-08-10T12:54:24.176748Z","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":"sha256:10ce1300170281065397ff8e1820eb7e29d6a3fa263b9f51db2cbab5a987b442","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"}}],"links":{"evidence":"/evidence","html":"/paper/2412.20644/citation-record","integrity":"/paper/2412.20644/integrity","json":"/paper/2412.20644/citation-record.json","paper":"/paper/2412.20644"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T23:21:17.689197Z","title":"Active distance-based clustering using k-medoids","venue":null,"work_id":"210eb384-6547-468f-9f1b-e744ba52637a","year":2016},"citing_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},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-10T23:21:16.640878Z"},"links":{"citing_paper":"/paper/2412.20644"},"observation_digest":"sha256:90c94eff8bc5739da0afffa265a1feaaeba4f87db5abfbc5147f2831a662124b","observation_id":"7d050665-9d97-4fd8-a6a7-61db7b1eaab7","resolution":{"observed_at":"2026-08-10T23:21:17.694051Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T23:21:17.675974Z","title":"On warm-starting neural network training","venue":null,"work_id":"70ef590a-25f4-4850-99a5-d98518bc93d8","year":2020},"citing_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},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-10T23:21:16.645803Z"},"links":{"citing_paper":"/paper/2412.20644"},"observation_digest":"sha256:605dd5f0f8894c639d81b7a16493d8cdc64486e7159916d4323da39e37b84813","observation_id":"13a44511-d4f1-4577-936b-2fef89684d8f","resolution":{"observed_at":"2026-08-10T23:21:17.680318Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T23:21:17.662382Z","title":"Gone fishing: Neural active learning with fisher embeddings","venue":null,"work_id":"09b8f29f-8c99-4e18-9d84-8e844ffeea0e","year":2021},"citing_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},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-10T23:21:16.650560Z"},"links":{"citing_paper":"/paper/2412.20644"},"observation_digest":"sha256:c726b085ef74a9ca5b7e01d415b4643228dfd397539123311b4b29f14e7fd35d","observation_id":"de59d67d-efad-43b7-8598-17ffe72e468d","resolution":{"observed_at":"2026-08-10T23:21:17.666902Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T23:21:17.648979Z","title":"Deep batch active learning by diverse, uncertain gradient lower bounds","venue":null,"work_id":"26291698-cca2-46b1-bd7e-71664abeebc2","year":2020},"citing_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},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-10T23:21:16.656060Z"},"links":{"citing_paper":"/paper/2412.20644"},"observation_digest":"sha256:f191be9b43b3d6f000e770cc367f114a5afe10af1e66819d74179fea1b912d23","observation_id":"12390363-223c-435c-a847-68983b543385","resolution":{"observed_at":"2026-08-10T23:21:17.653183Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T23:21:17.636280Z","title":"Generalized coverage for more robust low-budget active learning","venue":null,"work_id":"3f035164-c439-4d04-a3d5-c3f712241ccb","year":2024},"citing_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},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-10T23:21:16.659946Z"},"links":{"citing_paper":"/paper/2412.20644"},"observation_digest":"sha256:2c70044e0ea6355344974af017231fcdfdae6510d34acc0c9742cca1684d76b3","observation_id":"77560e95-3062-4202-877d-11ba81527a22","resolution":{"observed_at":"2026-08-10T23:21:17.641071Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T23:21:17.622452Z","title":"Batch active learning using determinantal point processes","venue":null,"work_id":"812c7221-9a15-4c93-852f-4330ba8fedb8","year":2019},"citing_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},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-10T23:21:16.664808Z"},"links":{"citing_paper":"/paper/2412.20644"},"observation_digest":"sha256:37fd9e8da1855ecc8e67c6f8bb1e04092b739b2003a882b843f997a9c4da783a","observation_id":"a3ea6b28-7c0a-4c13-85bb-89b88b1d44d9","resolution":{"observed_at":"2026-08-10T23:21:17.627428Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T23:21:16.670364Z","title":"Emerging properties in self-supervised vision transformers","venue":null,"work_id":null,"year":2021},"citing_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},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-10T23:21:16.670364Z"},"links":{"citing_paper":"/paper/2412.20644"},"observation_digest":"sha256:5f09f2208b92d1b11a0a1c0b4c26f71f38696da921f97c435105ebc710308592","observation_id":"23ec4721-bf77-4f75-b073-6b25f77b44fa","resolution":{"observed_at":"2026-08-10T23:21:16.670364Z","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":"2026-08-10T23:21:16.674070Z","title":"A simple framework for contrastive learning of visual representations","venue":null,"work_id":null,"year":2020},"citing_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},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-10T23:21:16.674070Z"},"links":{"citing_paper":"/paper/2412.20644"},"observation_digest":"sha256:52475cdc5b539942b1bd97f8ba5980e90f4e16392dae4a7cc74241c3c6e4d628","observation_id":"84ffd254-6c76-470a-ab92-95b8bc4e55cd","resolution":{"observed_at":"2026-08-10T23:21:16.674070Z","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":"2026-08-10T23:21:17.591974Z","title":"A closer look at few-shot classification","venue":null,"work_id":"8c7c1f53-b778-4272-a64d-80d4635f72da","year":2019},"citing_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},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-10T23:21:16.677782Z"},"links":{"citing_paper":"/paper/2412.20644"},"observation_digest":"sha256:86dbe2c118e6143b4321009f0d99bca8f2d105f8562d97ef9fc0cb363dce2828","observation_id":"3b7090d2-eb97-4bee-9ef4-3f28f1a04716","resolution":{"observed_at":"2026-08-10T23:21:17.596426Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T23:21:17.578341Z","title":"Super-samples from kernel herding","venue":null,"work_id":"d8c8d27a-cb8e-4903-b68d-a1b5386ba478","year":2010},"citing_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},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-10T23:21:16.681820Z"},"links":{"citing_paper":"/paper/2412.20644"},"observation_digest":"sha256:451a159d9ffc707daa3957747d76cf99dc5c2fdbd6c063e333edeca32a042eda","observation_id":"c700458b-7b24-4eb5-837b-1b6501b95dc2","resolution":{"observed_at":"2026-08-10T23:21:17.582771Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T23:21:17.565463Z","title":"On the mathematical foundations of learning","venue":null,"work_id":"7208f160-83f2-4d9c-b6fa-0de062331035","year":2001},"citing_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},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-10T23:21:16.685871Z"},"links":{"citing_paper":"/paper/2412.20644"},"observation_digest":"sha256:d7ed25c30393a7112077074bf16453f43ad792ccb5be9d33b11813d042cc9999","observation_id":"068a1c07-cc29-4c95-b5fd-a771c92c3997","resolution":{"observed_at":"2026-08-10T23:21:17.569851Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T23:21:16.690354Z","title":"ImageNet : A large-scale hierarchical image database","venue":null,"work_id":null,"year":2009},"citing_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},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-10T23:21:16.690354Z"},"links":{"citing_paper":"/paper/2412.20644"},"observation_digest":"sha256:910dfc9f2487aa4e07872fb9e99e1ceb59e4cf17105ea758f8d785290371c0e5","observation_id":"d68214c4-afa4-4474-b496-511eb2afe199","resolution":{"observed_at":"2026-08-10T23:21:16.690354Z","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":"2026-08-10T23:21:17.541611Z","title":"Dual strategy active learning","venue":null,"work_id":"c8241851-71a1-4458-a15e-a65ac53e094a","year":2007},"citing_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},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-10T23:21:16.694290Z"},"links":{"citing_paper":"/paper/2412.20644"},"observation_digest":"sha256:170b384b11f1690d8ab7ca9a57c573cd18a0f3bda01e864456a3b0c3a247f129","observation_id":"655837aa-fc67-4898-81e2-3f17be991d47","resolution":{"observed_at":"2026-08-10T23:21:17.546694Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T23:21:17.528706Z","title":"Bridging diversity and uncertainty in active learning with self-supervised pre-training","venue":null,"work_id":"a505fe88-e42b-4858-abed-1f83fdcb9382","year":2024},"citing_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},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-10T23:21:16.698118Z"},"links":{"citing_paper":"/paper/2412.20644"},"observation_digest":"sha256:bc99318bc36084a33b772ebd426cd9c760fc049a3f5721b06e9aa609cab9b68a","observation_id":"c8979c04-bf49-4523-af46-2ad92bbffad8","resolution":{"observed_at":"2026-08-10T23:21:17.532944Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T23:21:17.515853Z","title":"Selecting influential examples: Active learning with expected model output changes","venue":null,"work_id":"d29853a0-802d-4f69-8b50-ffbbfe61731c","year":2014},"citing_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},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-10T23:21:16.701947Z"},"links":{"citing_paper":"/paper/2412.20644"},"observation_digest":"sha256:fb5ed3f6626292e7b48d0cf2cd534e1d39f82fe411c35c3ebee1ca75b4c3e8b5","observation_id":"f743f2a4-6912-4e7c-a1a5-2839000f44d1","resolution":{"observed_at":"2026-08-10T23:21:17.520266Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T23:21:17.502116Z","title":"Deep bayesian active learning with image data","venue":null,"work_id":"ad724986-6768-4061-9153-1cfb4790d655","year":2017},"citing_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},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-10T23:21:16.705976Z"},"links":{"citing_paper":"/paper/2412.20644"},"observation_digest":"sha256:2676f5837fca9ebebf8799ebb8cfc4816b3d987943fcf015be5fa6682f992377","observation_id":"2e95d956-34f6-4538-98f6-04fa3ba9af73","resolution":{"observed_at":"2026-08-10T23:21:17.506815Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T23:21:17.486754Z","title":"Unraveling meta-learning: Understanding feature representations for few-shot tasks","venue":null,"work_id":"6eb5c78d-1bad-46e9-a56e-3bdf3a45ba49","year":2020},"citing_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},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-10T23:21:16.709988Z"},"links":{"citing_paper":"/paper/2412.20644"},"observation_digest":"sha256:a9c276236965b956ce910b80c77726eb05b881f8ad553e0764084405fcf1fcb1","observation_id":"9a10f11d-82a3-47e0-9816-81adbbde6e47","resolution":{"observed_at":"2026-08-10T23:21:17.492583Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T23:21:17.472588Z","title":"On calibration of modern neural networks","venue":null,"work_id":"987e6ef4-25a3-4ca6-bc69-dd96c52bcdea","year":2017},"citing_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},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-10T23:21:16.713865Z"},"links":{"citing_paper":"/paper/2412.20644"},"observation_digest":"sha256:3daeffad52a13ce3b912382a826e6482bd152b7deb9ea189377833c56b4af6db","observation_id":"b7aa4aef-9414-4f38-a09c-d29351f3adfa","resolution":{"observed_at":"2026-08-10T23:21:17.476839Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T23:21:17.459570Z","title":"Optimistic active-learning using mutual information","venue":null,"work_id":"a7483d4e-5541-4c00-bac8-70e2621c7a6f","year":2007},"citing_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},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-10T23:21:16.717410Z"},"links":{"citing_paper":"/paper/2412.20644"},"observation_digest":"sha256:b848b939ada87e35acbbb2b8442dadd1ac1f3cfcbe798f2a77f6be5760a87a31","observation_id":"b079f236-66a6-41b1-bf25-7f0236d6c7fc","resolution":{"observed_at":"2026-08-10T23:21:17.463807Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T23:21:17.446183Z","title":"How to select which active learning strategy is best suited for your specific problem and budget","venue":null,"work_id":"630133fa-ff6f-4ddd-b654-0f6915184e1b","year":2024},"citing_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},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-10T23:21:16.721548Z"},"links":{"citing_paper":"/paper/2412.20644"},"observation_digest":"sha256:51be146a1da07366d98f390087e06cdde535bcc003419b123540b7576cec96a6","observation_id":"c8cd9555-0a5d-4f35-862b-11cd7ab9071c","resolution":{"observed_at":"2026-08-10T23:21:17.450449Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T23:21:17.430723Z","title":"Active learning on a budget: Opposite strategies suit high and low budgets","venue":null,"work_id":"44afdb15-70e1-4410-a7e2-ceb96cc9a575","year":2022},"citing_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},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-10T23:21:16.725522Z"},"links":{"citing_paper":"/paper/2412.20644"},"observation_digest":"sha256:0bf137f6a2c297930fd66697e89bbcf1d714f8ea95da4d6fdfd71b9f57fed5a5","observation_id":"0d32646a-2d19-4963-a131-881483e15f21","resolution":{"observed_at":"2026-08-10T23:21:17.436230Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T23:21:16.729326Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_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},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-10T23:21:16.729326Z"},"links":{"citing_paper":"/paper/2412.20644"},"observation_digest":"sha256:627ef975cdf0b15684dea7e94585407fa8ce14802fa1c51de053e6fb8e7354a2","observation_id":"a1c411e7-5c33-40cb-8132-044dbfe9d431","resolution":{"observed_at":"2026-08-10T23:21:16.729326Z","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":"2026-08-10T23:21:17.408929Z","title":"Active and continuous exploration with deep neural networks and expected model output changes","venue":null,"work_id":"ec61cbdd-298e-43d3-a9df-46d46ec15958","year":2016},"citing_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},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-10T23:21:16.733460Z"},"links":{"citing_paper":"/paper/2412.20644"},"observation_digest":"sha256:dc4d36024b6b4d033c374f7d250d9d7eea75054b4e6e7a3168493ba6d0ee5f8d","observation_id":"a69de62c-160f-478c-8b70-a9667adee754","resolution":{"observed_at":"2026-08-10T23:21:17.413578Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T23:21:17.395729Z","title":"a ding, Erik Rodner, Alexander Freytag, Oliver Mothes, Bj \\","venue":null,"work_id":"2f6f3aa2-47e3-4ea9-b98a-ccb3bb10e4aa","year":2018},"citing_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},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-10T23:21:16.737727Z"},"links":{"citing_paper":"/paper/2412.20644"},"observation_digest":"sha256:9c02165644ab4f7593f3bfa228a10a9dece75d47b976ede89e97aac31a84dbec","observation_id":"a320727c-4661-4676-a500-d4ccc3f1638d","resolution":{"observed_at":"2026-08-10T23:21:17.399745Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T23:21:17.383406Z","title":"Finding groups in data: an introduction to cluster analysis","venue":null,"work_id":"0a517a0b-1db9-4a9b-b57e-014d61833e07","year":2009},"citing_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},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-10T23:21:16.741722Z"},"links":{"citing_paper":"/paper/2412.20644"},"observation_digest":"sha256:e041332bfbc21820515b7d67731568a470f0b782b90dc8f9eae57b8dc3830773","observation_id":"14c4f997-7e5c-4dbc-a22f-b14eae2c7ecb","resolution":{"observed_at":"2026-08-10T23:21:17.388041Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T23:21:17.370318Z","title":"Batchbald: Efficient and diverse batch acquisition for deep bayesian active learning","venue":null,"work_id":"8c828e54-1f8f-4567-b308-be724fc2809f","year":2019},"citing_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},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-10T23:21:16.745622Z"},"links":{"citing_paper":"/paper/2412.20644"},"observation_digest":"sha256:b547660a91cb19faabecc40827f64050deff8e8caf2ce0444f06b855ef23f28d","observation_id":"674b360c-c89f-43e4-9a81-18eb3ea1d90d","resolution":{"observed_at":"2026-08-10T23:21:17.374457Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T23:21:16.749127Z","title":"Learning multiple layers of features from tiny images, 2009","venue":null,"work_id":null,"year":2009},"citing_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},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-10T23:21:16.749127Z"},"links":{"citing_paper":"/paper/2412.20644"},"observation_digest":"sha256:9caf3c2bb0a3c8826707189f7dcabe96265b16197c587232341d07e4f5308a83","observation_id":"971bc1f1-a9d9-4322-b1d6-d177a934829d","resolution":{"observed_at":"2026-08-10T23:21:16.749127Z","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":"2026-08-10T23:21:17.350500Z","title":"Cifar-100 (canadian institute for advanced research)","venue":null,"work_id":"cfa421b6-aa07-462e-a10e-1eae02b71165","year":null},"citing_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},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-10T23:21:16.754385Z"},"links":{"citing_paper":"/paper/2412.20644"},"observation_digest":"sha256:b1a6f71712197e26d6fcb642a6e1c83c15bae7ac513ecb77418d5a270d4cca31","observation_id":"4da97789-3ffe-4347-ae0a-45213d20472d","resolution":{"observed_at":"2026-08-10T23:21:17.354915Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T23:21:17.336182Z","title":"Tidal: Learning training dynamics for active learning","venue":null,"work_id":"a7c59402-19be-4dc9-ad67-5a19715a7256","year":2023},"citing_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},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-10T23:21:16.758190Z"},"links":{"citing_paper":"/paper/2412.20644"},"observation_digest":"sha256:e297d77279cdf83e5e783ea90b07f0b74438645bc57fc9952186b7e49a49664e","observation_id":"75426e4b-4c76-4e1d-98d9-e93382e9ca97","resolution":{"observed_at":"2026-08-10T23:21:17.341369Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T23:21:17.323790Z","title":"Heterogeneous uncertainty sampling for supervised learning","venue":null,"work_id":"93e13b8b-7df2-4701-8a36-51e3179926f1","year":1994},"citing_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},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-10T23:21:16.762473Z"},"links":{"citing_paper":"/paper/2412.20644"},"observation_digest":"sha256:a64cd1f20d111c5608f24b1a6b9bdc027664b1524b6d40f47fc5fdde9a60f858","observation_id":"243a7d48-2e77-4f63-821a-9195b58f7f61","resolution":{"observed_at":"2026-08-10T23:21:17.328228Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T23:21:17.311077Z","title":"A sequential algorithm for training text classifiers","venue":null,"work_id":"46317834-9d5a-47c9-a34c-1919c1f94a3d","year":1994},"citing_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},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-10T23:21:16.766898Z"},"links":{"citing_paper":"/paper/2412.20644"},"observation_digest":"sha256:a801d2ce445ec45dc1355acd74c4cb93ffa3430d19c002e6e427c919add61819","observation_id":"b46282ae-ea6e-45f7-aef2-018680d2327e","resolution":{"observed_at":"2026-08-10T23:21:17.315263Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T23:21:17.298707Z","title":"Low budget active learning via wasserstein distance: An integer programming approach","venue":null,"work_id":"f4c5155e-885a-4723-8590-f19457b6b49f","year":2022},"citing_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},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-10T23:21:16.771059Z"},"links":{"citing_paper":"/paper/2412.20644"},"observation_digest":"sha256:9b5719e67854307ea6e2925491884151af34a5f5ca7e06418128647eadde768d","observation_id":"9b3b70e5-5e42-4920-84af-227d5a2833b7","resolution":{"observed_at":"2026-08-10T23:21:17.302861Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T23:21:17.285379Z","title":"Tiny imagenet, 2017","venue":null,"work_id":"9b715dc4-b69d-4b38-a16d-17739d4b6cf7","year":2017},"citing_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},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-10T23:21:16.775113Z"},"links":{"citing_paper":"/paper/2412.20644"},"observation_digest":"sha256:959dcdd3845fa49ec1b266b9f3f63b42f83a1a3a517bffd23d0fdc3a1f871dee","observation_id":"94b19791-3a1f-4681-822c-8063f41de324","resolution":{"observed_at":"2026-08-10T23:21:17.290197Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T23:21:17.272747Z","title":"Making look-ahead active learning strategies feasible with neural tangent kernels","venue":null,"work_id":"db17730a-061f-40f0-8b5b-f5b17fdec304","year":2022},"citing_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},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-10T23:21:16.779451Z"},"links":{"citing_paper":"/paper/2412.20644"},"observation_digest":"sha256:0b938f544f4f7ea7f5118dcaddad80b934655fa94e3088b3f7533f903e6637c3","observation_id":"9a562a29-2025-42e8-a3ab-42a69143857d","resolution":{"observed_at":"2026-08-10T23:21:17.277077Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T23:21:17.258770Z","title":"Obtaining well calibrated probabilities using bayesian binning","venue":null,"work_id":"b8b5b0d1-2011-4544-8aae-24672a534a6a","year":2015},"citing_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},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-10T23:21:16.784266Z"},"links":{"citing_paper":"/paper/2412.20644"},"observation_digest":"sha256:aeca492031dbdde6112ffbd5ad0b0bf976f28293b96db8ecf6b185d4fe318277","observation_id":"2490e6a6-7242-4a9f-88e1-8ceb8c9deefa","resolution":{"observed_at":"2026-08-10T23:21:17.263638Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T23:21:17.245624Z","title":null,"venue":null,"work_id":"8915a9cc-d358-4cd0-8a07-7df635b321a9","year":1978},"citing_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},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-10T23:21:16.789858Z"},"links":{"citing_paper":"/paper/2412.20644"},"observation_digest":"sha256:c6616611f65b445a4bf08cc6233d686b599f3dad436902eeb49670c3070a1cc7","observation_id":"7de586eb-6b65-4f33-ace8-e1def6a80e41","resolution":{"observed_at":"2026-08-10T23:21:17.249984Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T23:21:17.232519Z","title":"Active learning using pre-clustering","venue":null,"work_id":"f0da1642-cbde-40b2-9ae4-b2f17407231d","year":2004},"citing_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},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-10T23:21:16.794513Z"},"links":{"citing_paper":"/paper/2412.20644"},"observation_digest":"sha256:b3a084c66ef4e80e81e592366222504042993041fee4c57bc88e7cffc811b936","observation_id":"ab59a75a-a32a-4726-8062-ed8d4c5436b8","resolution":{"observed_at":"2026-08-10T23:21:17.237144Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T23:21:17.218959Z","title":"Active learning by feature mixing","venue":null,"work_id":"c0ea772f-5e2e-400e-8df7-c7d3c87b6daa","year":2022},"citing_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},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-10T23:21:16.798897Z"},"links":{"citing_paper":"/paper/2412.20644"},"observation_digest":"sha256:2e6757e041397e5a833618a3335c9c7b8d408165eaa12670970b1c2bed5fb1b4","observation_id":"682b0415-75e9-4b80-8a97-26aa6ace9504","resolution":{"observed_at":"2026-08-10T23:21:17.223625Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T23:21:17.205881Z","title":"Moment matching for multi-source domain adaptation","venue":null,"work_id":"cf542b9f-bdea-4d0f-9257-4dfe620a4b87","year":2019},"citing_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},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-10T23:21:16.805157Z"},"links":{"citing_paper":"/paper/2412.20644"},"observation_digest":"sha256:dbb4cb935beb66101f4d8b00f81f5591e62442b4f2bec8073a041b0ab422f457","observation_id":"69b14f2c-0ff7-44e4-92bf-faae3885ef09","resolution":{"observed_at":"2026-08-10T23:21:17.210772Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T23:21:17.192889Z","title":"Toward optimal active learning through monte carlo estimation of error reduction","venue":null,"work_id":"da074960-a2e5-4a72-846c-b2d41e2c6951","year":2001},"citing_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},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-10T23:21:16.809215Z"},"links":{"citing_paper":"/paper/2412.20644"},"observation_digest":"sha256:8eb4c719abe6e2d7655db5bc58cffeefffd9a351673e9cc381d285e169b7c429","observation_id":"1b730019-d875-41a1-83d6-e7ed98e8b174","resolution":{"observed_at":"2026-08-10T23:21:17.197022Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T23:21:16.813056Z","title":"Active hidden M arkov models for information extraction","venue":null,"work_id":null,"year":2001},"citing_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},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-10T23:21:16.813056Z"},"links":{"citing_paper":"/paper/2412.20644"},"observation_digest":"sha256:0ce08103b2a626501d6782b196cb6bf6fade83f32b372a859188b97f1139879a","observation_id":"7bd52421-5781-4fa6-a76d-7b913e17f2ed","resolution":{"observed_at":"2026-08-10T23:21:16.813056Z","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":"2026-08-10T23:21:17.172707Z","title":"Fast k-medoids clustering in R ust and P ython","venue":null,"work_id":"4f2fd442-536a-419e-8aa6-a452575b39f1","year":2022},"citing_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},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-10T23:21:16.818269Z"},"links":{"citing_paper":"/paper/2412.20644"},"observation_digest":"sha256:f38fc5a15fb1b8e2d542eb400ce94f0dbfb072afe0314d7900e3411a3b925f45","observation_id":"47755168-ca39-4f02-97fa-8e5cd5a4ecd5","resolution":{"observed_at":"2026-08-10T23:21:17.177243Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T23:21:17.159771Z","title":"Faster k-medoids clustering: improving the PAM , CLARA , and CLARANS algorithms","venue":null,"work_id":"85034703-521e-440c-a5c2-992c988d007a","year":2019},"citing_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},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-10T23:21:16.822808Z"},"links":{"citing_paper":"/paper/2412.20644"},"observation_digest":"sha256:e1a615fda0afd3e01d782dbf2178e575abc873929745568a001d9fcd6cdb8072","observation_id":"331e5f30-92ab-4c49-88ba-7daf9a7ce13c","resolution":{"observed_at":"2026-08-10T23:21:17.164123Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T23:21:17.147189Z","title":"Fast and eager k-medoids clustering: O(k) runtime improvement of the PAM , CLARA , and CLARANS algorithms","venue":null,"work_id":"dc434456-eb18-44ef-8045-2c85032388f1","year":2021},"citing_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},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-10T23:21:16.827366Z"},"links":{"citing_paper":"/paper/2412.20644"},"observation_digest":"sha256:eb2082b936238093745b343d7972867d2ec6214366855e84958e2d411be6e1fa","observation_id":"5a6f219a-159a-482c-a452-cb2dc82321d5","resolution":{"observed_at":"2026-08-10T23:21:17.151650Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T23:21:16.831908Z","title":"Active learning for convolutional neural networks: A core-set approach","venue":null,"work_id":null,"year":2018},"citing_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},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-10T23:21:16.831908Z"},"links":{"citing_paper":"/paper/2412.20644"},"observation_digest":"sha256:bc6c1717f10377dd24c6d685ffd9c90821d57efd0e4be1db22652bc3b4cb047b","observation_id":"bbf353fb-19bc-4298-8ea1-7469de7cd0f5","resolution":{"observed_at":"2026-08-10T23:21:16.831908Z","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":"2026-08-10T23:21:16.836975Z","title":"Active learning literature survey","venue":null,"work_id":null,"year":2009},"citing_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},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-10T23:21:16.836975Z"},"links":{"citing_paper":"/paper/2412.20644"},"observation_digest":"sha256:c7961cd2862e811b3e1ab7dd3161593d114c21607868dac44dd2a29c8e521d72","observation_id":"71a0d320-713e-4723-98dc-6085daac9615","resolution":{"observed_at":"2026-08-10T23:21:16.836975Z","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":"2026-08-10T23:21:17.116671Z","title":"An analysis of active learning strategies for sequence labeling tasks","venue":null,"work_id":"5d590f05-66ce-4902-999f-59fce3e58e06","year":2008},"citing_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},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-10T23:21:16.846481Z"},"links":{"citing_paper":"/paper/2412.20644"},"observation_digest":"sha256:612ce04de98fd2d0f87edfff29ebc1f8426da01febedcfd01ecdbd93f966eb12","observation_id":"31087ca1-e8a4-4992-863d-e4d5bfc888a9","resolution":{"observed_at":"2026-08-10T23:21:17.122264Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T23:21:17.102909Z","title":"Multiple-instance active learning","venue":null,"work_id":"e09970e8-e536-41c4-aa93-9a45a6025302","year":2007},"citing_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},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-10T23:21:16.850973Z"},"links":{"citing_paper":"/paper/2412.20644"},"observation_digest":"sha256:a891ec5dd3746773ee5ca468e486d0f6d095020a80f53760a4862b1cdebec303","observation_id":"028ccee3-ba9e-4164-8caf-294f09da3925","resolution":{"observed_at":"2026-08-10T23:21:17.107675Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T23:21:16.854740Z","title":"Training data-efficient image transformers & distillation through attention","venue":null,"work_id":null,"year":2021},"citing_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},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-10T23:21:16.854740Z"},"links":{"citing_paper":"/paper/2412.20644"},"observation_digest":"sha256:b6e4aad3ea91def7b30d5a5e69d05ba6c25a54494ab59576c7d83cc7eb3c7499","observation_id":"cae86cb2-2ae9-4d9e-89ce-e70843f822e8","resolution":{"observed_at":"2026-08-10T23:21:16.854740Z","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":"2026-08-10T23:21:17.080442Z","title":"Active clustering of biological sequences","venue":null,"work_id":"2c7dd3e2-35a3-4fed-bc7e-352e40025a72","year":2012},"citing_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},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-10T23:21:16.859316Z"},"links":{"citing_paper":"/paper/2412.20644"},"observation_digest":"sha256:9f4e72d2e20d16c1970d298b037d04105ea56424ec1c618a983718b88a34f222","observation_id":"03047b06-817e-436c-b7a1-fe68ff694f7c","resolution":{"observed_at":"2026-08-10T23:21:17.086222Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T23:21:16.863796Z","title":"A new active labeling method for deep learning","venue":null,"work_id":null,"year":2014},"citing_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},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-10T23:21:16.863796Z"},"links":{"citing_paper":"/paper/2412.20644"},"observation_digest":"sha256:70e30c0be1fe4e4c69682bfc34a96de40ba47e24c90460945458b228d942011c","observation_id":"bf70c465-987c-40f4-9f60-7e52b474d846","resolution":{"observed_at":"2026-08-10T23:21:16.863796Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1911.04623","last_updated":"2019-11-16T00:35:54Z","snapshot_observed_at":"2026-08-11T17:03:10.222098Z","submitted_at":"2019-11-12T00:44:10Z","title":"SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1911.04623","snapshot_observed_at":"2026-08-10T23:21:16.868105Z","title":"Weinberger, and Laurens van der Maaten","venue":null,"work_id":null,"year":1911},"citing_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},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-10T23:21:16.868105Z"},"links":{"cited_paper":"/paper/1911.04623","citing_paper":"/paper/2412.20644"},"observation_digest":"sha256:75e855ea12274ed960b5c0048fa8a3ebf4c995a2a9017db62cd05ae7d697a073","observation_id":"94923c48-3f84-4f4b-8bf5-93af0b744d89","resolution":{"observed_at":"2026-08-10T23:21:16.868105Z","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":"2026-08-10T23:21:17.057181Z","title":"Active finetuning: Exploiting annotation budget in the pretraining-finetuning paradigm","venue":null,"work_id":"ce3b6964-66ff-4bf6-bfb8-ca6bbbc5cbd9","year":2023},"citing_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},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-10T23:21:16.872746Z"},"links":{"citing_paper":"/paper/2412.20644"},"observation_digest":"sha256:21f46546fcafe58aba466276bff7d7ab5a941a5cbf37e910fcfd6320fe3aab54","observation_id":"4dcb2504-5e58-4820-9cd4-cb6e02eac296","resolution":{"observed_at":"2026-08-10T23:21:17.062496Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T23:21:17.043841Z","title":"Representative sampling for text classification using support vector machines","venue":null,"work_id":"b4cec481-a723-4183-af3f-06e94cd8e7e0","year":2003},"citing_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},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-08-10T23:21:16.877220Z"},"links":{"citing_paper":"/paper/2412.20644"},"observation_digest":"sha256:a9ffb07b87d8a0df72ea161404f4458bc590aa2cea565e7fab913a52be4b0842","observation_id":"a55c9cf7-3f68-4d0c-b70b-ad76eaa13064","resolution":{"observed_at":"2026-08-10T23:21:17.048539Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T23:21:16.881111Z","title":"Active learning through a covering lens","venue":null,"work_id":null,"year":2022},"citing_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},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-08-10T23:21:16.881111Z"},"links":{"citing_paper":"/paper/2412.20644"},"observation_digest":"sha256:69cbd9203866f4ff27554da89c6b0aa7c636064249bc13737e2bcdca7e6e8cd9","observation_id":"5429a32d-0264-4339-82bc-ae4f93509e69","resolution":{"observed_at":"2026-08-10T23:21:16.881111Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1901.05954","last_updated":"2019-01-17T18:56:50Z","snapshot_observed_at":"2026-07-06T07:27:23.918977Z","submitted_at":"2019-01-17T18:56:50Z","title":"Diverse mini-batch Active Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1901.05954","snapshot_observed_at":"2026-08-10T23:21:16.884841Z","title":"Diverse mini-batch active learning","venue":null,"work_id":null,"year":1901},"citing_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},"reference_index":56,"source":"arxiv_source","source_observed_at":"2026-08-10T23:21:16.884841Z"},"links":{"cited_paper":"/paper/1901.05954","citing_paper":"/paper/2412.20644"},"observation_digest":"sha256:c4914294b15a3f9f5b87139594da3212d9e5b21185de0b59bfd6528d5d83031f","observation_id":"d6472a4a-3f92-4587-85ed-508c8b545b28","resolution":{"observed_at":"2026-08-10T23:21:16.884841Z","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":"2026-08-10T23:21:17.017901Z","title":"Combining active learning and semi-supervised learning using gaussian fields and harmonic functions","venue":null,"work_id":"3e3767f6-c8a3-48dd-b65b-cbe03dd0447a","year":2003},"citing_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},"reference_index":57,"source":"arxiv_source","source_observed_at":"2026-08-10T23:21:16.889768Z"},"links":{"citing_paper":"/paper/2412.20644"},"observation_digest":"sha256:06490f6e735d20c6fc6cdc15a1bbfb68e8ea3fbd881ef7f4345d228f7385d1bb","observation_id":"48e296e6-e9b0-44c5-a7d1-059beadc3694","resolution":{"observed_at":"2026-08-10T23:21:17.024802Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-10T23:21:16.894202Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_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},"reference_index":58,"source":"arxiv_source","source_observed_at":"2026-08-10T23:21:16.894202Z"},"links":{"citing_paper":"/paper/2412.20644"},"observation_digest":"sha256:8f37b1acadc9aefd885d3d34877c9234e3ee4dad2a90eed131df6286524a816b","observation_id":"f01c8b46-f3ca-4c6b-8357-4f9da931764e","resolution":{"observed_at":"2026-08-10T23:21:16.894202Z","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":"2026-08-10T23:21:16.899572Z","title":"@esa (Ref","venue":null,"work_id":null,"year":null},"citing_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},"reference_index":59,"source":"arxiv_source","source_observed_at":"2026-08-10T23:21:16.899572Z"},"links":{"citing_paper":"/paper/2412.20644"},"observation_digest":"sha256:fb948cc897bdbcda9ebaab123cb2d57eb48a99c146279765b8ca171170cf8e50","observation_id":"7b725627-d515-4386-840f-b57a646780b6","resolution":{"observed_at":"2026-08-10T23:21:16.899572Z","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":"2026-08-10T23:21:16.905178Z","title":null,"venue":null,"work_id":null,"year":null},"citing_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},"reference_index":60,"source":"arxiv_source","source_observed_at":"2026-08-10T23:21:16.905178Z"},"links":{"citing_paper":"/paper/2412.20644"},"observation_digest":"sha256:8955dac3c14681addb997e260206d26e12ab6657504ece124dea81fdc5981b86","observation_id":"8584b0fc-4a04-4591-95c1-eddbaa689e7e","resolution":{"observed_at":"2026-08-10T23:21:16.905178Z","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":"2026-08-10T23:21:16.912001Z","title":null,"venue":null,"work_id":null,"year":null},"citing_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},"reference_index":61,"source":"arxiv_source","source_observed_at":"2026-08-10T23:21:16.912001Z"},"links":{"citing_paper":"/paper/2412.20644"},"observation_digest":"sha256:b2875b5ca2cec269032691b88f212e41c793dc7ea27c03457c329e96670b7f27","observation_id":"1c13b8dd-c5ff-4f99-9fea-2158c5c107ce","resolution":{"observed_at":"2026-08-10T23:21:16.912001Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2412.20644","last_updated":"2025-02-27T17:33:30Z","latest_version":2,"primary_category":"cs.LG","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"},"reference_resolution":{"displayed":61,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":18,"verified_exact":0,"verified_fuzzy":43},"total_outbound_references":61},"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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 61 of 61 outbound references and 1 inbound Pith citation observation for arXiv:2412.20644."}