{"as_of":"2026-08-22T03:52:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:116defa22012d8e9a40c0a9384b136feeadf6d8397938f2b3672dc90540fadcb","coverage":[{"denominator":33,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":33,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T23:34:35.364842Z","state":"measured"},{"denominator":33,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":33,"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/2505.04375/citation-record","integrity":"/paper/2505.04375/integrity","json":"/paper/2505.04375/citation-record.json","paper":"/paper/2505.04375"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T23:34:35.835398Z","title":"One-peace: Exploring one general representation model toward unlimited modalities, 2023","venue":null,"work_id":"de5f52e5-06ad-4c11-ac16-6caa8b80a8d2","year":2023},"citing_paper":{"arxiv_id":"2505.04375","last_updated":"2025-05-07T12:53:13Z","snapshot_observed_at":"2026-08-17T23:48:00.705474Z","submitted_at":"2025-05-07T12:53:13Z","title":"Balancing Accuracy, Calibration, and Efficiency in Active Learning with Vision Transformers Under Label Noise","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T23:34:35.222845Z"},"links":{"citing_paper":"/paper/2505.04375"},"observation_digest":"sha256:3021d805ee4aed9c0337acea5063bab6ae6243bbbaf53ad66bb3640a32368116","observation_id":"1f4e102e-b132-402e-84fb-6be78b7d560f","resolution":{"observed_at":"2026-08-15T23:34:35.839745Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T23:34:35.820634Z","title":"Omnivec: Learning robust representations with cross-modal sharing","venue":null,"work_id":"b267b514-60cc-4beb-b32c-219296c38ac8","year":2024},"citing_paper":{"arxiv_id":"2505.04375","last_updated":"2025-05-07T12:53:13Z","snapshot_observed_at":"2026-08-17T23:48:00.705474Z","submitted_at":"2025-05-07T12:53:13Z","title":"Balancing Accuracy, Calibration, and Efficiency in Active Learning with Vision Transformers Under Label Noise","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T23:34:35.228345Z"},"links":{"citing_paper":"/paper/2505.04375"},"observation_digest":"sha256:1fb9923bf0b55f05ef98f4d0affaefb256249e9b94facdbcda490025f46245b5","observation_id":"6f581d37-58a4-43ba-8e2c-8f5ce18e1b5b","resolution":{"observed_at":"2026-08-15T23:34:35.825535Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T23:34:35.806741Z","title":null,"venue":null,"work_id":"afb03983-4786-4884-b8fa-d25ccbc7a93c","year":2023},"citing_paper":{"arxiv_id":"2505.04375","last_updated":"2025-05-07T12:53:13Z","snapshot_observed_at":"2026-08-17T23:48:00.705474Z","submitted_at":"2025-05-07T12:53:13Z","title":"Balancing Accuracy, Calibration, and Efficiency in Active Learning with Vision Transformers Under Label Noise","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T23:34:35.233010Z"},"links":{"citing_paper":"/paper/2505.04375"},"observation_digest":"sha256:19d82609f9451f6d038dd0a3e1e06f4dace18eae3e5bafabfcd1ca5b8d5b7e06","observation_id":"9648d05a-bb6f-4566-bb91-628837c5777e","resolution":{"observed_at":"2026-08-15T23:34:35.811106Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T23:34:35.792523Z","title":"Berg, Wan-Yen Lo, Piotr Dollár, and Ross Girshick","venue":null,"work_id":"3c36845f-0ee9-47aa-88d7-7b47d6edecb7","year":2023},"citing_paper":{"arxiv_id":"2505.04375","last_updated":"2025-05-07T12:53:13Z","snapshot_observed_at":"2026-08-17T23:48:00.705474Z","submitted_at":"2025-05-07T12:53:13Z","title":"Balancing Accuracy, Calibration, and Efficiency in Active Learning with Vision Transformers Under Label Noise","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T23:34:35.237423Z"},"links":{"citing_paper":"/paper/2505.04375"},"observation_digest":"sha256:f191ef7aedead3cf6afa8d408796e1f2f5cf3d58f9e6929777c1ae45f21554fb","observation_id":"9ab9c358-ae9b-4bb1-a806-484c4452ce6f","resolution":{"observed_at":"2026-08-15T23:34:35.797090Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T23:34:35.241769Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.04375","last_updated":"2025-05-07T12:53:13Z","snapshot_observed_at":"2026-08-17T23:48:00.705474Z","submitted_at":"2025-05-07T12:53:13Z","title":"Balancing Accuracy, Calibration, and Efficiency in Active Learning with Vision Transformers Under Label Noise","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T23:34:35.241769Z"},"links":{"citing_paper":"/paper/2505.04375"},"observation_digest":"sha256:77708c4f0773d0259cf990ee1f90f12797731b80b23521a590c781529032f671","observation_id":"5abf69b4-5866-4dae-ae4d-f6e44f65f494","resolution":{"observed_at":"2026-08-15T23:34:35.241769Z","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":"2026-08-15T23:34:35.768982Z","title":"LeCun and Y","venue":null,"work_id":"b04fcfb0-098c-4c1e-b42a-d763329ec236","year":1998},"citing_paper":{"arxiv_id":"2505.04375","last_updated":"2025-05-07T12:53:13Z","snapshot_observed_at":"2026-08-17T23:48:00.705474Z","submitted_at":"2025-05-07T12:53:13Z","title":"Balancing Accuracy, Calibration, and Efficiency in Active Learning with Vision Transformers Under Label Noise","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T23:34:35.246118Z"},"links":{"citing_paper":"/paper/2505.04375"},"observation_digest":"sha256:668119a5b6396aaee949ef9c1308de79303c50fc4ccae84c680c4118fc35ea09","observation_id":"0a9450fa-6492-47ae-9d7e-ff669e187b0f","resolution":{"observed_at":"2026-08-15T23:34:35.773535Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T23:34:35.754503Z","title":null,"venue":null,"work_id":"d2d20fab-16b8-4ac9-be83-427fdd611b22","year":2020},"citing_paper":{"arxiv_id":"2505.04375","last_updated":"2025-05-07T12:53:13Z","snapshot_observed_at":"2026-08-17T23:48:00.705474Z","submitted_at":"2025-05-07T12:53:13Z","title":"Balancing Accuracy, Calibration, and Efficiency in Active Learning with Vision Transformers Under Label Noise","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T23:34:35.250967Z"},"links":{"citing_paper":"/paper/2505.04375"},"observation_digest":"sha256:9e790f608932e08289865a7d276f2ea40f815b54849e00ebc0c0c63a8d1652f9","observation_id":"82977dd0-253b-42f6-85e8-82e80ef303ef","resolution":{"observed_at":"2026-08-15T23:34:35.759154Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T23:34:35.740198Z","title":"Cordeiro and G","venue":null,"work_id":"829bb0be-2c42-402d-a556-fa8835a418a4","year":2020},"citing_paper":{"arxiv_id":"2505.04375","last_updated":"2025-05-07T12:53:13Z","snapshot_observed_at":"2026-08-17T23:48:00.705474Z","submitted_at":"2025-05-07T12:53:13Z","title":"Balancing Accuracy, Calibration, and Efficiency in Active Learning with Vision Transformers Under Label Noise","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T23:34:35.255219Z"},"links":{"citing_paper":"/paper/2505.04375"},"observation_digest":"sha256:6e0da3e2aa2b9e7b28ee89ce1c325384a9cf14ea054ca65a6833a97f52f819db","observation_id":"19caa90c-8d1d-4e22-bb32-5bc4a9692bb9","resolution":{"observed_at":"2026-08-15T23:34:35.744672Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2302.11075","last_updated":"2023-09-19T19:13:07Z","snapshot_observed_at":"2026-08-20T01:22:34.823359Z","submitted_at":"2023-02-22T00:27:39Z","title":"Deep Active Learning in the Presence of Label Noise: A Survey","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.11075","snapshot_observed_at":"2026-08-15T23:34:35.259300Z","title":"Mots’oehli and K","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.04375","last_updated":"2025-05-07T12:53:13Z","snapshot_observed_at":"2026-08-17T23:48:00.705474Z","submitted_at":"2025-05-07T12:53:13Z","title":"Balancing Accuracy, Calibration, and Efficiency in Active Learning with Vision Transformers Under Label Noise","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T23:34:35.259300Z"},"links":{"cited_paper":"/paper/2302.11075","citing_paper":"/paper/2505.04375"},"observation_digest":"sha256:c7537f46b46b89df47dada9a6897975949a3f832ae09b180758630e372ec7843","observation_id":"51bc5c31-f75e-4d79-b9c9-748640a438a3","resolution":{"observed_at":"2026-08-15T23:34:35.259300Z","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":"2026-08-15T23:34:35.726131Z","title":"On the interdependence between data selection and architecture optimization in deep active learning","venue":null,"work_id":"6a19b383-5b5e-4056-b102-817738033bd6","year":2024},"citing_paper":{"arxiv_id":"2505.04375","last_updated":"2025-05-07T12:53:13Z","snapshot_observed_at":"2026-08-17T23:48:00.705474Z","submitted_at":"2025-05-07T12:53:13Z","title":"Balancing Accuracy, Calibration, and Efficiency in Active Learning with Vision Transformers Under Label Noise","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T23:34:35.264214Z"},"links":{"citing_paper":"/paper/2505.04375"},"observation_digest":"sha256:b34c893f3812372b4042df5da5c41d305ec7dadd9a0030e97848c63c86c78b71","observation_id":"01f06668-54ba-4765-8823-dd97ca65788c","resolution":{"observed_at":"2026-08-15T23:34:35.730686Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T23:34:35.710592Z","title":"An empirical study on the efficacy of deep active learning for image classification, 2022","venue":null,"work_id":"87d8f634-0d45-4cf3-b368-d149dbe089bc","year":2022},"citing_paper":{"arxiv_id":"2505.04375","last_updated":"2025-05-07T12:53:13Z","snapshot_observed_at":"2026-08-17T23:48:00.705474Z","submitted_at":"2025-05-07T12:53:13Z","title":"Balancing Accuracy, Calibration, and Efficiency in Active Learning with Vision Transformers Under Label Noise","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T23:34:35.268432Z"},"links":{"citing_paper":"/paper/2505.04375"},"observation_digest":"sha256:994602f3cd3ff921c9bdf1c83fd292ec6e91e105a09fda9f831d51f2e5708da0","observation_id":"3fa2609f-9eff-4538-a1a6-a53978695b39","resolution":{"observed_at":"2026-08-15T23:34:35.715715Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T23:34:35.694066Z","title":"Deep active learning: A reality check, 2024","venue":null,"work_id":"478f827e-a470-42a8-8604-d6fc95470e4c","year":2024},"citing_paper":{"arxiv_id":"2505.04375","last_updated":"2025-05-07T12:53:13Z","snapshot_observed_at":"2026-08-17T23:48:00.705474Z","submitted_at":"2025-05-07T12:53:13Z","title":"Balancing Accuracy, Calibration, and Efficiency in Active Learning with Vision Transformers Under Label Noise","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T23:34:35.272601Z"},"links":{"citing_paper":"/paper/2505.04375"},"observation_digest":"sha256:35d1ea8fc9cfb3ca3ba49430fee0bb13be8c1d33b67807bc0c18340b0d89e40b","observation_id":"362e6c7b-04c3-4f2f-aba6-8647374b76b9","resolution":{"observed_at":"2026-08-15T23:34:35.698782Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2411.05939","last_updated":"2024-11-08T19:59:40Z","snapshot_observed_at":"2026-08-17T22:15:18.887257Z","submitted_at":"2024-11-08T19:59:40Z","title":"GCI-ViTAL: Gradual Confidence Improvement with Vision Transformers for Active Learning on Label Noise","version":1},"cited_work":{"arxiv_id":"2411.05939","doi":null,"metadata_source":"pith","pith_arxiv_id":"2411.05939","snapshot_observed_at":"2026-08-15T23:34:35.437841Z","title":"GCI-ViTAL: Gradual Confidence Improvement with Vision Transformers for Active Learning on Label Noise","venue":"cs.CV","work_id":"72905f0a-7a38-4479-b4a5-ef5c62baec51","year":2024},"citing_paper":{"arxiv_id":"2505.04375","last_updated":"2025-05-07T12:53:13Z","snapshot_observed_at":"2026-08-17T23:48:00.705474Z","submitted_at":"2025-05-07T12:53:13Z","title":"Balancing Accuracy, Calibration, and Efficiency in Active Learning with Vision Transformers Under Label Noise","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T23:34:35.276673Z"},"links":{"cited_paper":"/paper/2411.05939","citing_paper":"/paper/2505.04375"},"observation_digest":"sha256:18c1701d1083a007bdd6a2296b5eccc6455a450d53a4779d1c08f3ac426e6c1b","observation_id":"7c19990a-cb5e-4dda-b5ee-2033fc77df29","resolution":{"observed_at":"2026-08-15T23:34:35.442624Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T23:34:35.679372Z","title":"Kolesnikov, A","venue":null,"work_id":"214b4abd-f129-41c4-8482-a28a2e2630ce","year":2021},"citing_paper":{"arxiv_id":"2505.04375","last_updated":"2025-05-07T12:53:13Z","snapshot_observed_at":"2026-08-17T23:48:00.705474Z","submitted_at":"2025-05-07T12:53:13Z","title":"Balancing Accuracy, Calibration, and Efficiency in Active Learning with Vision Transformers Under Label Noise","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T23:34:35.281379Z"},"links":{"citing_paper":"/paper/2505.04375"},"observation_digest":"sha256:773ee8e192663fb6e6f43bc1b8012532aa7d527fe2b390dc1a40a142c691057d","observation_id":"9f4c02ab-270a-4448-be6d-4a45284388f6","resolution":{"observed_at":"2026-08-15T23:34:35.683800Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T23:34:35.664410Z","title":"Swin transformer: Hierarchical vision transformer using shifted windows","venue":null,"work_id":"601e40bf-2307-4532-b4e3-c753d5a8df09","year":2021},"citing_paper":{"arxiv_id":"2505.04375","last_updated":"2025-05-07T12:53:13Z","snapshot_observed_at":"2026-08-17T23:48:00.705474Z","submitted_at":"2025-05-07T12:53:13Z","title":"Balancing Accuracy, Calibration, and Efficiency in Active Learning with Vision Transformers Under Label Noise","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T23:34:35.285595Z"},"links":{"citing_paper":"/paper/2505.04375"},"observation_digest":"sha256:de14522bde90c1eb63513a4c2a4603f6b204a6149417b24c94d064d6943507b2","observation_id":"5584cb34-e241-4078-9801-fe3a6924406d","resolution":{"observed_at":"2026-08-15T23:34:35.669302Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T23:34:35.650337Z","title":null,"venue":null,"work_id":"4316f113-bf00-4a04-a159-31720036bb5d","year":1950},"citing_paper":{"arxiv_id":"2505.04375","last_updated":"2025-05-07T12:53:13Z","snapshot_observed_at":"2026-08-17T23:48:00.705474Z","submitted_at":"2025-05-07T12:53:13Z","title":"Balancing Accuracy, Calibration, and Efficiency in Active Learning with Vision Transformers Under Label Noise","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T23:34:35.290835Z"},"links":{"citing_paper":"/paper/2505.04375"},"observation_digest":"sha256:a41e9fd440c5d0e06a3ccd8371c4300e63be2a4f72a120b7a0803befcb2d9d78","observation_id":"bef62f4d-0199-4697-8620-166bd7f375f5","resolution":{"observed_at":"2026-08-15T23:34:35.654677Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T23:34:35.636675Z","title":null,"venue":null,"work_id":"9ff3c7af-8ac0-4725-a7e1-64626a6e6135","year":2012},"citing_paper":{"arxiv_id":"2505.04375","last_updated":"2025-05-07T12:53:13Z","snapshot_observed_at":"2026-08-17T23:48:00.705474Z","submitted_at":"2025-05-07T12:53:13Z","title":"Balancing Accuracy, Calibration, and Efficiency in Active Learning with Vision Transformers Under Label Noise","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T23:34:35.295004Z"},"links":{"citing_paper":"/paper/2505.04375"},"observation_digest":"sha256:0f60e67b25eaf59b8c1fe67b8578878c263ec13cf1f7a60edcab688fbb4f1604","observation_id":"e941f5d1-ac8e-4bcd-939a-f45386a3b5d4","resolution":{"observed_at":"2026-08-15T23:34:35.641058Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T23:34:35.299826Z","title":"Going deeper with convolutions","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2505.04375","last_updated":"2025-05-07T12:53:13Z","snapshot_observed_at":"2026-08-17T23:48:00.705474Z","submitted_at":"2025-05-07T12:53:13Z","title":"Balancing Accuracy, Calibration, and Efficiency in Active Learning with Vision Transformers Under Label Noise","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T23:34:35.299826Z"},"links":{"citing_paper":"/paper/2505.04375"},"observation_digest":"sha256:ab2cbba1506577d4a8201b33a31759b37392f84df2fa3f31c287c688e29de007","observation_id":"41665ca0-6242-4d28-8550-c9adc3189a33","resolution":{"observed_at":"2026-08-15T23:34:35.299826Z","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":"2026-08-15T23:34:35.304550Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.04375","last_updated":"2025-05-07T12:53:13Z","snapshot_observed_at":"2026-08-17T23:48:00.705474Z","submitted_at":"2025-05-07T12:53:13Z","title":"Balancing Accuracy, Calibration, and Efficiency in Active Learning with Vision Transformers Under Label Noise","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T23:34:35.304550Z"},"links":{"citing_paper":"/paper/2505.04375"},"observation_digest":"sha256:a5f6b6747de2c3644e0889bd52d338a70a5aa5dfdd4f78d48d94e89f9c109880","observation_id":"c27a065b-5338-4641-a199-d508d5ea90e7","resolution":{"observed_at":"2026-08-15T23:34:35.304550Z","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":"2026-08-15T23:34:35.308908Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2505.04375","last_updated":"2025-05-07T12:53:13Z","snapshot_observed_at":"2026-08-17T23:48:00.705474Z","submitted_at":"2025-05-07T12:53:13Z","title":"Balancing Accuracy, Calibration, and Efficiency in Active Learning with Vision Transformers Under Label Noise","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T23:34:35.308908Z"},"links":{"citing_paper":"/paper/2505.04375"},"observation_digest":"sha256:f63c261302d830f668462bb3d9674503bc1b316b828897618800e2dd61bc0d8d","observation_id":"c91eb4a3-b087-4185-b730-2b6979a1c183","resolution":{"observed_at":"2026-08-15T23:34:35.308908Z","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":"2026-08-15T23:34:35.313289Z","title":"Imagenet: A large-scale hierarchical image database","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2505.04375","last_updated":"2025-05-07T12:53:13Z","snapshot_observed_at":"2026-08-17T23:48:00.705474Z","submitted_at":"2025-05-07T12:53:13Z","title":"Balancing Accuracy, Calibration, and Efficiency in Active Learning with Vision Transformers Under Label Noise","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T23:34:35.313289Z"},"links":{"citing_paper":"/paper/2505.04375"},"observation_digest":"sha256:8d7128da4b2db24b6d324823c6f39d5e108faa2c9c4015af528e9de7ecb5399d","observation_id":"0180a95b-4ed6-463b-a918-cf42ecb066cd","resolution":{"observed_at":"2026-08-15T23:34:35.313289Z","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":"2026-08-15T23:34:35.584600Z","title":null,"venue":null,"work_id":"28329e84-46e7-4f0a-82b8-c5948ffe129c","year":2014},"citing_paper":{"arxiv_id":"2505.04375","last_updated":"2025-05-07T12:53:13Z","snapshot_observed_at":"2026-08-17T23:48:00.705474Z","submitted_at":"2025-05-07T12:53:13Z","title":"Balancing Accuracy, Calibration, and Efficiency in Active Learning with Vision Transformers Under Label Noise","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T23:34:35.317731Z"},"links":{"citing_paper":"/paper/2505.04375"},"observation_digest":"sha256:9acb0965051f6574091d45425b63a4607567d718bb80f19794d028770c913287","observation_id":"5998b4d6-89c8-49fd-bb88-8b342456adb1","resolution":{"observed_at":"2026-08-15T23:34:35.589363Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T23:34:35.322067Z","title":"A simple framework for contrastive learning of visual representations","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.04375","last_updated":"2025-05-07T12:53:13Z","snapshot_observed_at":"2026-08-17T23:48:00.705474Z","submitted_at":"2025-05-07T12:53:13Z","title":"Balancing Accuracy, Calibration, and Efficiency in Active Learning with Vision Transformers Under Label Noise","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T23:34:35.322067Z"},"links":{"citing_paper":"/paper/2505.04375"},"observation_digest":"sha256:e0c179859dd4283427f0f3518887cced72c928616473144e87ff4b12aac6a9ad","observation_id":"bb23b5f5-3c65-473d-8227-7ff03c89d3b7","resolution":{"observed_at":"2026-08-15T23:34:35.322067Z","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":"2026-08-15T23:34:35.326318Z","title":"Momentum contrast for unsupervised visual representation learning","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.04375","last_updated":"2025-05-07T12:53:13Z","snapshot_observed_at":"2026-08-17T23:48:00.705474Z","submitted_at":"2025-05-07T12:53:13Z","title":"Balancing Accuracy, Calibration, and Efficiency in Active Learning with Vision Transformers Under Label Noise","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T23:34:35.326318Z"},"links":{"citing_paper":"/paper/2505.04375"},"observation_digest":"sha256:30f640ebf44dc5564eb9ed6bdd1740b8b321f7b75f6f711f5132f78dbb0ee794","observation_id":"b1a9f571-ff70-4670-98f2-7dbfac89bc78","resolution":{"observed_at":"2026-08-15T23:34:35.326318Z","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":"2026-08-15T23:34:35.330721Z","title":"Training data-efficient image transformers & distillation through attention","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.04375","last_updated":"2025-05-07T12:53:13Z","snapshot_observed_at":"2026-08-17T23:48:00.705474Z","submitted_at":"2025-05-07T12:53:13Z","title":"Balancing Accuracy, Calibration, and Efficiency in Active Learning with Vision Transformers Under Label Noise","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T23:34:35.330721Z"},"links":{"citing_paper":"/paper/2505.04375"},"observation_digest":"sha256:9376b257d1b2fa0aeb7c760a841bb9a14bfcbfaa79c35d531493f6e90ef57e53","observation_id":"0b20047a-e189-44a0-934e-40617dc099af","resolution":{"observed_at":"2026-08-15T23:34:35.330721Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.03801","last_updated":"2021-06-07T17:13:59Z","snapshot_observed_at":"2026-08-16T18:19:00.078304Z","submitted_at":"2021-06-07T17:13:59Z","title":"Visual Transformer for Task-aware Active Learning","version":1},"cited_work":{"arxiv_id":"2106.03801","doi":null,"metadata_source":"pith","pith_arxiv_id":"2106.03801","snapshot_observed_at":"2026-08-15T23:34:35.414879Z","title":"Visual Transformer for Task-aware Active Learning","venue":"cs.CV","work_id":"55b59715-3bd8-49ab-ae20-42f225947723","year":2021},"citing_paper":{"arxiv_id":"2505.04375","last_updated":"2025-05-07T12:53:13Z","snapshot_observed_at":"2026-08-17T23:48:00.705474Z","submitted_at":"2025-05-07T12:53:13Z","title":"Balancing Accuracy, Calibration, and Efficiency in Active Learning with Vision Transformers Under Label Noise","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T23:34:35.335046Z"},"links":{"cited_paper":"/paper/2106.03801","citing_paper":"/paper/2505.04375"},"observation_digest":"sha256:4bd6085b773aeed0a9ae67e02b8fea794c8918c429a8f8255021bd3883db3c97","observation_id":"cfa96600-fe06-4077-a7c2-8d45e475d1d7","resolution":{"observed_at":"2026-08-15T23:34:35.421619Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T23:34:35.541099Z","title":"Kelei, G","venue":null,"work_id":"8e099d02-11b4-427e-bdf6-7b33b52b8c30","year":2023},"citing_paper":{"arxiv_id":"2505.04375","last_updated":"2025-05-07T12:53:13Z","snapshot_observed_at":"2026-08-17T23:48:00.705474Z","submitted_at":"2025-05-07T12:53:13Z","title":"Balancing Accuracy, Calibration, and Efficiency in Active Learning with Vision Transformers Under Label Noise","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T23:34:35.339431Z"},"links":{"citing_paper":"/paper/2505.04375"},"observation_digest":"sha256:d6028eae96b7176fa7304ac1669ccf8643e7e2cacec376b83721530b86d5dffe","observation_id":"f5dedb43-47e1-4429-b741-57c52ad0b4ea","resolution":{"observed_at":"2026-08-15T23:34:35.546176Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T23:34:35.525015Z","title":"Rotman and R","venue":null,"work_id":"06bebe6c-15fb-4279-bc2d-5ac0eb2e1180","year":2022},"citing_paper":{"arxiv_id":"2505.04375","last_updated":"2025-05-07T12:53:13Z","snapshot_observed_at":"2026-08-17T23:48:00.705474Z","submitted_at":"2025-05-07T12:53:13Z","title":"Balancing Accuracy, Calibration, and Efficiency in Active Learning with Vision Transformers Under Label Noise","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-15T23:34:35.343529Z"},"links":{"citing_paper":"/paper/2505.04375"},"observation_digest":"sha256:b2e7c16d090084d871ce08a26a412ec53c036eeb5ac251306c449466bea493d5","observation_id":"124db22b-418f-4d54-8bcd-3fcd8ca6f387","resolution":{"observed_at":"2026-08-15T23:34:35.529980Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T23:34:35.510997Z","title":"Scaling vision transformers","venue":null,"work_id":"62018c5f-9c47-470e-b536-c3c8d0a571e3","year":2022},"citing_paper":{"arxiv_id":"2505.04375","last_updated":"2025-05-07T12:53:13Z","snapshot_observed_at":"2026-08-17T23:48:00.705474Z","submitted_at":"2025-05-07T12:53:13Z","title":"Balancing Accuracy, Calibration, and Efficiency in Active Learning with Vision Transformers Under Label Noise","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T23:34:35.347952Z"},"links":{"citing_paper":"/paper/2505.04375"},"observation_digest":"sha256:82f021de2fb9d6f46b04e1bb5a0e2240f77fbeed101e7f4d40430346f1da0662","observation_id":"041f974a-074b-4193-bf1b-730450747daf","resolution":{"observed_at":"2026-08-15T23:34:35.515243Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T23:34:35.496559Z","title":"Emerging properties in self-supervised vision transformers","venue":null,"work_id":"caf981a9-3656-4537-bc3a-b4df7b1f6a12","year":2021},"citing_paper":{"arxiv_id":"2505.04375","last_updated":"2025-05-07T12:53:13Z","snapshot_observed_at":"2026-08-17T23:48:00.705474Z","submitted_at":"2025-05-07T12:53:13Z","title":"Balancing Accuracy, Calibration, and Efficiency in Active Learning with Vision Transformers Under Label Noise","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-15T23:34:35.352095Z"},"links":{"citing_paper":"/paper/2505.04375"},"observation_digest":"sha256:5a4c8ca0d7be75ec2dd01c9f6cdc54ef866503f0f2c9bbcd6ae7bd4b3cb602b6","observation_id":"83f020fa-66b7-48d5-8538-d1784e0da542","resolution":{"observed_at":"2026-08-15T23:34:35.501279Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T23:34:35.482301Z","title":"Crossvit: Cross-attention multi-scale vision transformer for image classification","venue":null,"work_id":"88b4e2a2-1bcf-4c70-9a62-4ff232cd341c","year":2021},"citing_paper":{"arxiv_id":"2505.04375","last_updated":"2025-05-07T12:53:13Z","snapshot_observed_at":"2026-08-17T23:48:00.705474Z","submitted_at":"2025-05-07T12:53:13Z","title":"Balancing Accuracy, Calibration, and Efficiency in Active Learning with Vision Transformers Under Label Noise","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-15T23:34:35.356385Z"},"links":{"citing_paper":"/paper/2505.04375"},"observation_digest":"sha256:ffaac74d6e66f4d0d9d4c2a85956787d2c7a70b2b2cdbddec87acbda6b0cf3f4","observation_id":"8292f11d-0fe4-4879-a076-302a89bec9d9","resolution":{"observed_at":"2026-08-15T23:34:35.486863Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T23:34:35.467157Z","title":"Transformers meet small datasets","venue":null,"work_id":"5424da24-7d8c-4bb9-80d8-29109d6721c4","year":2022},"citing_paper":{"arxiv_id":"2505.04375","last_updated":"2025-05-07T12:53:13Z","snapshot_observed_at":"2026-08-17T23:48:00.705474Z","submitted_at":"2025-05-07T12:53:13Z","title":"Balancing Accuracy, Calibration, and Efficiency in Active Learning with Vision Transformers Under Label Noise","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-15T23:34:35.360730Z"},"links":{"citing_paper":"/paper/2505.04375"},"observation_digest":"sha256:2b77425c5b00a39c59fd5b8736842a3afdebc25fd34d0d0a6db17c493f6fe18f","observation_id":"4952a513-5c43-48b7-ac24-e0f6ac19057c","resolution":{"observed_at":"2026-08-15T23:34:35.472118Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2302.03751","last_updated":"2023-02-07T20:56:21Z","snapshot_observed_at":"2026-08-16T15:56:58.933498Z","submitted_at":"2023-02-07T20:56:21Z","title":"Understanding Why ViT Trains Badly on Small Datasets: An Intuitive Perspective","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.03751","snapshot_observed_at":"2026-08-15T23:34:35.364842Z","title":"Understanding why vit trains badly on small datasets: An intuitive perspective","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.04375","last_updated":"2025-05-07T12:53:13Z","snapshot_observed_at":"2026-08-17T23:48:00.705474Z","submitted_at":"2025-05-07T12:53:13Z","title":"Balancing Accuracy, Calibration, and Efficiency in Active Learning with Vision Transformers Under Label Noise","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-15T23:34:35.364842Z"},"links":{"cited_paper":"/paper/2302.03751","citing_paper":"/paper/2505.04375"},"observation_digest":"sha256:af23ae2b47537c81d969cb3af9c13f7faab8298eef42f5c77d0d49b875735fdf","observation_id":"a1c62524-f2a7-44ef-9083-d8f3d7f3842f","resolution":{"observed_at":"2026-08-15T23:34:35.364842Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2505.04375","last_updated":"2025-05-07T12:53:13Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-17T23:48:00.705474Z","submitted_at":"2025-05-07T12:53:13Z","title":"Balancing Accuracy, Calibration, and Efficiency in Active Learning with Vision Transformers Under Label Noise"},"reference_resolution":{"displayed":33,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":15,"verified_exact":2,"verified_fuzzy":16},"total_outbound_references":33},"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 33 of 33 outbound references and 0 inbound Pith citation observations for arXiv:2505.04375."}