{"as_of":"2026-08-10T16:16:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3e689763f0cd404a036f8b3ad2a820ac9cf4772f664fdf37e9d1288a0d71ec6e","coverage":[{"denominator":14,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":14,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T18:45:26.570940Z","state":"measured"},{"denominator":14,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":14,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+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/2502.10288/citation-record","integrity":"/paper/2502.10288/integrity","json":"/paper/2502.10288/citation-record.json","paper":"/paper/2502.10288"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T18:45:26.722786Z","title":null,"venue":null,"work_id":"d15596e4-2a78-4ca9-b96b-a08cebd7bb2f","year":2024},"citing_paper":{"arxiv_id":"2502.10288","last_updated":"2025-02-14T16:50:33Z","snapshot_observed_at":"2026-08-07T18:38:09.018496Z","submitted_at":"2025-02-14T16:50:33Z","title":"Adversarial Mixup Unlearning","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T18:45:26.549985Z"},"links":{"citing_paper":"/paper/2502.10288"},"observation_digest":"sha256:58d4da23f6db2398a9e82c0d96d15e4f096c402fa87a2fe3c0198b3fe28c00e1","observation_id":"e13f8ffe-564f-45f1-97c9-b59fe3c17bf4","resolution":{"observed_at":"2026-08-07T18:45:26.728371Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1708.07747","last_updated":"2017-09-15T21:29:49Z","snapshot_observed_at":"2026-07-06T05:56:41.814255Z","submitted_at":"2017-08-25T14:01:29Z","title":"Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1708.07747","snapshot_observed_at":"2026-08-07T18:45:26.523364Z","title":"Fashion-mnist: a novel image dataset for benchmark- ing machine learning algorithms","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.10288","last_updated":"2025-02-14T16:50:33Z","snapshot_observed_at":"2026-08-07T18:38:09.018496Z","submitted_at":"2025-02-14T16:50:33Z","title":"Adversarial Mixup Unlearning","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T18:45:26.523364Z"},"links":{"cited_paper":"/paper/1708.07747","citing_paper":"/paper/2502.10288"},"observation_digest":"sha256:d4fc6608ba95f77400abaa6f7c19355613a4a92351361f3c0b362a8b57ccceb1","observation_id":"bfbe38b6-3bb3-4222-8668-6d339c292d01","resolution":{"observed_at":"2026-08-07T18:45:26.523364Z","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":"2026-08-07T18:45:26.799222Z","title":null,"venue":null,"work_id":"a9b747ee-770e-4b9d-a953-b084e91a7f1e","year":2025},"citing_paper":{"arxiv_id":"2502.10288","last_updated":"2025-02-14T16:50:33Z","snapshot_observed_at":"2026-08-07T18:38:09.018496Z","submitted_at":"2025-02-14T16:50:33Z","title":"Adversarial Mixup Unlearning","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T18:45:26.528755Z"},"links":{"citing_paper":"/paper/2502.10288"},"observation_digest":"sha256:dcbdbf9c07d88ba7ad2d86b556382db7a5d1eaf7cf1064bbb34647e34eccabf1","observation_id":"6e354d03-1ef8-4737-96d2-69aa67776696","resolution":{"observed_at":"2026-08-07T18:45:26.804858Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T18:45:26.765649Z","title":"Unroll (Thudi et al.,","venue":null,"work_id":"e4008115-b8e3-4e1d-b869-9b012e253476","year":2025},"citing_paper":{"arxiv_id":"2502.10288","last_updated":"2025-02-14T16:50:33Z","snapshot_observed_at":"2026-08-07T18:38:09.018496Z","submitted_at":"2025-02-14T16:50:33Z","title":"Adversarial Mixup Unlearning","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T18:45:26.539005Z"},"links":{"citing_paper":"/paper/2502.10288"},"observation_digest":"sha256:dce083d4c24714cf6ad6535443a553f2600a9b1758c197fd2ab03525cf3b6998","observation_id":"88728aec-d81c-4423-8907-eaff6945a73a","resolution":{"observed_at":"2026-08-07T18:45:26.771106Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T18:45:26.742534Z","title":"For RandLabel, we tune the weight for retaining loss from {0.0001, 0.01, 0.1, 1, 10, 100}","venue":null,"work_id":"5de13ca9-4c12-44c1-9aab-bbf4aa00cc4a","year":2024},"citing_paper":{"arxiv_id":"2502.10288","last_updated":"2025-02-14T16:50:33Z","snapshot_observed_at":"2026-08-07T18:38:09.018496Z","submitted_at":"2025-02-14T16:50:33Z","title":"Adversarial Mixup Unlearning","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T18:45:26.544446Z"},"links":{"citing_paper":"/paper/2502.10288"},"observation_digest":"sha256:6255126a18aa63bb0a204dbc8ff323a6cdfef553cede01fbe7801b6cdd8080dc","observation_id":"b809f0ba-1870-4c13-a633-21a2698ea202","resolution":{"observed_at":"2026-08-07T18:45:26.753202Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T18:45:26.782612Z","title":null,"venue":null,"work_id":"2d40af5e-43b8-409d-be0d-f5a740ae42ae","year":2024},"citing_paper":{"arxiv_id":"2502.10288","last_updated":"2025-02-14T16:50:33Z","snapshot_observed_at":"2026-08-07T18:38:09.018496Z","submitted_at":"2025-02-14T16:50:33Z","title":"Adversarial Mixup Unlearning","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T18:45:26.533867Z"},"links":{"citing_paper":"/paper/2502.10288"},"observation_digest":"sha256:d50402f76223c037be6d28e03eb993fb28ca088456819a1894932a9c7193dee6","observation_id":"ffcf59b9-08b2-4746-afe9-12e178eb6923","resolution":{"observed_at":"2026-08-07T18:45:26.787410Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T18:45:26.703909Z","title":"This shows that our approach can effectively handle label noise","venue":null,"work_id":"56faeab4-a8d4-4024-980b-0abf050953b9","year":2025},"citing_paper":{"arxiv_id":"2502.10288","last_updated":"2025-02-14T16:50:33Z","snapshot_observed_at":"2026-08-07T18:38:09.018496Z","submitted_at":"2025-02-14T16:50:33Z","title":"Adversarial Mixup Unlearning","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T18:45:26.555000Z"},"links":{"citing_paper":"/paper/2502.10288"},"observation_digest":"sha256:1315fb8dba6bce1954759333108d68126aa6487a626d5189b3c45a34e50facf5","observation_id":"4ded80bd-66a7-49cf-9701-ee4ec51a2906","resolution":{"observed_at":"2026-08-07T18:45:26.709627Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T18:45:26.666163Z","title":"This comparison is performed using two metrics: training accuracy on the forgotten data (Trainf ) and testing accuracy","venue":null,"work_id":"07967a9f-ac89-4d70-a824-66de263a6988","year":2009},"citing_paper":{"arxiv_id":"2502.10288","last_updated":"2025-02-14T16:50:33Z","snapshot_observed_at":"2026-08-07T18:38:09.018496Z","submitted_at":"2025-02-14T16:50:33Z","title":"Adversarial Mixup Unlearning","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T18:45:26.565865Z"},"links":{"citing_paper":"/paper/2502.10288"},"observation_digest":"sha256:d83d852379f74debf55c440ce3b0ec7795b0a8770117cc8190f08bf2d870d4cb","observation_id":"9c92db68-aee6-4610-a490-13e6ac9e7cea","resolution":{"observed_at":"2026-08-07T18:45:26.672834Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T18:45:26.646987Z","title":"vit-b16-224-in21k","venue":null,"work_id":"6d9d486c-2599-44e9-a762-34ce8912d3a8","year":2016},"citing_paper":{"arxiv_id":"2502.10288","last_updated":"2025-02-14T16:50:33Z","snapshot_observed_at":"2026-08-07T18:38:09.018496Z","submitted_at":"2025-02-14T16:50:33Z","title":"Adversarial Mixup Unlearning","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T18:45:26.570940Z"},"links":{"citing_paper":"/paper/2502.10288"},"observation_digest":"sha256:210d32316b916e1d980f34f0ff4a127c3444e9cfc0e4a3982da9a99fc9eeb025","observation_id":"7d787efa-22c5-4680-9faf-82f4dc482c04","resolution":{"observed_at":"2026-08-07T18:45:26.653737Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T18:45:26.853258Z","title":"Towards unbounded machine unlearning","venue":null,"work_id":"e19832f1-1f42-47e6-9b32-3ff1b22b4438","year":2025},"citing_paper":{"arxiv_id":"2502.10288","last_updated":"2025-02-14T16:50:33Z","snapshot_observed_at":"2026-08-07T18:38:09.018496Z","submitted_at":"2025-02-14T16:50:33Z","title":"Adversarial Mixup Unlearning","version":1},"reference_index":2009,"source":"pdf_text","source_observed_at":"2026-08-07T18:45:26.507459Z"},"links":{"citing_paper":"/paper/2502.10288"},"observation_digest":"sha256:983387db722774963ff54f12bab87de0c2bb1fee6925be85176664fee1d60ba0","observation_id":"a5fe4b99-1d9c-4989-9d22-32c1a81f92ae","resolution":{"observed_at":"2026-08-07T18:45:26.858019Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2409.05202","last_updated":"2025-04-23T17:47:35Z","snapshot_observed_at":"2026-07-06T19:12:15.383132Z","submitted_at":"2024-09-08T19:32:22Z","title":"A Survey on Mixup Augmentations and Beyond","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.05202","snapshot_observed_at":"2026-08-07T18:45:26.501429Z","title":"A survey on mixup augmentations and beyond","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.10288","last_updated":"2025-02-14T16:50:33Z","snapshot_observed_at":"2026-08-07T18:38:09.018496Z","submitted_at":"2025-02-14T16:50:33Z","title":"Adversarial Mixup Unlearning","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-07T18:45:26.501429Z"},"links":{"cited_paper":"/paper/2409.05202","citing_paper":"/paper/2502.10288"},"observation_digest":"sha256:a71e5bb7da8f95eafbf24c226b56591f0f6273af20b266cf446043f0ea8fadc8","observation_id":"1dfb4ff7-77eb-408a-b4c3-3a820e51257a","resolution":{"observed_at":"2026-08-07T18:45:26.501429Z","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":"2026-08-07T18:45:26.817251Z","title":"Reading digits in natural images with unsupervised feature learning","venue":null,"work_id":"d2f34402-a743-4db5-adbd-bf8d83550677","year":2011},"citing_paper":{"arxiv_id":"2502.10288","last_updated":"2025-02-14T16:50:33Z","snapshot_observed_at":"2026-08-07T18:38:09.018496Z","submitted_at":"2025-02-14T16:50:33Z","title":"Adversarial Mixup Unlearning","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-07T18:45:26.517727Z"},"links":{"citing_paper":"/paper/2502.10288"},"observation_digest":"sha256:412f601c886e3c6ef6cb5274b0c48a4136b199073e6c0f33ba329eb66a11e068","observation_id":"095a4102-4099-4567-9ab1-ca6cf94216dc","resolution":{"observed_at":"2026-08-07T18:45:26.822698Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T18:45:26.835881Z","title":"Convolutional networks for images, speech, and time series","venue":null,"work_id":"d89e2345-6b9d-4736-9fad-79464b3f288d","year":1995},"citing_paper":{"arxiv_id":"2502.10288","last_updated":"2025-02-14T16:50:33Z","snapshot_observed_at":"2026-08-07T18:38:09.018496Z","submitted_at":"2025-02-14T16:50:33Z","title":"Adversarial Mixup Unlearning","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-07T18:45:26.512746Z"},"links":{"citing_paper":"/paper/2502.10288"},"observation_digest":"sha256:bac4fe0e21e43ee731d819d778305cc69376fdda5ff0455d501fb222ca588de4","observation_id":"f1408678-963b-44af-b94b-33d9cc98f309","resolution":{"observed_at":"2026-08-07T18:45:26.841910Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-07T18:45:26.684382Z","title":"Compared to Retraining, which requires a complete model retraining and is thus highly time- consuming, our method demonstrates significant superiority in efficiency","venue":null,"work_id":"9204735e-41d7-4cc4-9e6f-89d2b2413ba6","year":2025},"citing_paper":{"arxiv_id":"2502.10288","last_updated":"2025-02-14T16:50:33Z","snapshot_observed_at":"2026-08-07T18:38:09.018496Z","submitted_at":"2025-02-14T16:50:33Z","title":"Adversarial Mixup Unlearning","version":1},"reference_index":3090,"source":"pdf_text","source_observed_at":"2026-08-07T18:45:26.560209Z"},"links":{"citing_paper":"/paper/2502.10288"},"observation_digest":"sha256:11a1526c9cd0b4d0aae2e62399f8ead5e4cbf50669b89ee8bf1020ca3b43e92a","observation_id":"a1d383c5-4770-4e64-b251-4a49a677f763","resolution":{"observed_at":"2026-08-07T18:45:26.690269Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2502.10288","last_updated":"2025-02-14T16:50:33Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T18:38:09.018496Z","submitted_at":"2025-02-14T16:50:33Z","title":"Adversarial Mixup Unlearning"},"reference_resolution":{"displayed":14,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":5,"verified_exact":0,"verified_fuzzy":8},"total_outbound_references":14},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 14 of 14 outbound references and 0 inbound Pith citation observations for arXiv:2502.10288."}