{"as_of":"2026-08-18T18:14:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d9722df818e4a60e5c6ee86acdbdc4554cef4aaafb3efaaa9d5c6ac1838fc7e2","coverage":[{"denominator":97,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":97,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T23:13:47.577731Z","state":"measured"},{"denominator":97,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":97,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+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/2505.05279/citation-record","integrity":"/paper/2505.05279/integrity","json":"/paper/2505.05279/citation-record.json","paper":"/paper/2505.05279"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T23:13:47.189191Z","title":"Bayesian uncertainty for gradient aggregation in multi-task learning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.189191Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:ea22f20f6e64b82f5ddc077633f67854975ee1ad75e5421068102af00daf5bae","observation_id":"906edc2a-172d-4a41-8aeb-a47aab0de92f","resolution":{"observed_at":"2026-08-15T23:13:47.189191Z","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":"2026-08-15T23:13:47.193260Z","title":"and Ji, K","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.193260Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:61c91a44ae3ca651b1a33add7f6a969acee3f034ebc597818f9ab4d5220c46c9","observation_id":"14e085c8-c720-43eb-bb2b-a68ab6ac32a4","resolution":{"observed_at":"2026-08-15T23:13:47.193260Z","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":"2026-08-15T23:13:47.198148Z","title":"D., and Tygar, J","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.198148Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:ae889404f1cc8420c003f5d5ab388b9ccb69de875509a789f4d4b7fea629f586","observation_id":"a620d2b3-2570-4507-9501-e0c62ce5cc49","resolution":{"observed_at":"2026-08-15T23:13:47.198148Z","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":"2026-08-15T23:13:47.201815Z","title":"A model of inductive bias learning","venue":null,"work_id":null,"year":2000},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.201815Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:7b3cbf8e56a13159021f394561ad8a9636d6a7bb7a397d8c0a0e05162380d3d3","observation_id":"f4ed088b-9a2e-4f11-ab4e-590ba94c1a89","resolution":{"observed_at":"2026-08-15T23:13:47.201815Z","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":"2026-08-15T23:13:47.205539Z","title":"Poisoning attacks against support vector machines","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.205539Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:1ad173100627c95970499f5fc9f7356ca79f51ca563eec808cecd37ee8261d36","observation_id":"620c9117-2ca0-4e00-977d-18b601d1df85","resolution":{"observed_at":"2026-08-15T23:13:47.205539Z","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":"2026-08-15T23:13:47.210326Z","title":"Facial biometrics training dataset leads to bipa lawsuits against amazon, alphabet and microsoft, jul 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.210326Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:1eb2b95e6b4271b1f3759dd62d3515e93e7d7f32c05449e536e740c4b98bec3a","observation_id":"32311906-1e05-45ca-99c9-5d83c9725744","resolution":{"observed_at":"2026-08-15T23:13:47.210326Z","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":"2026-08-15T23:13:47.214375Z","title":"Multitask learning: A knowledge-based source of inductive bias","venue":null,"work_id":null,"year":1993},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.214375Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:8ae17e21cba386dca01e199ec4cb839a3b3a54e2e5903253f96958f96febb8ff","observation_id":"63f66ffb-473d-483f-85d8-05b0cf4a5cb2","resolution":{"observed_at":"2026-08-15T23:13:47.214375Z","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":"2026-08-15T23:13:47.218000Z","title":"One for all: A universal generator for concept unlearnability via multi-modal alignment","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.218000Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:30882ba11c7161ec01878265fbb97a8aa9a1de5740a781cf399b433da4cf81db","observation_id":"e65f5480-1fb3-4b2d-8d86-4da2edf25d52","resolution":{"observed_at":"2026-08-15T23:13:47.218000Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.09138","last_updated":"2024-04-28T07:25:45Z","snapshot_observed_at":"2026-08-16T17:55:36.401046Z","submitted_at":"2021-09-19T14:51:51Z","title":"Multi-Task Learning in Natural Language Processing: An Overview","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.09138","snapshot_observed_at":"2026-08-15T23:13:47.223161Z","title":"Multi-task learning in natural language processing: An overview","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.223161Z"},"links":{"cited_paper":"/paper/2109.09138","citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:886a1aeb8a1be70f2eded9277ee855d4e69b33fc7284d6e5afd2983593d75dcc","observation_id":"4d361237-510a-46e0-bd9d-2837b12f0f67","resolution":{"observed_at":"2026-08-15T23:13:47.223161Z","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":"2026-08-15T23:13:47.227484Z","title":"Self-ensemble protection: Training checkpoints are good data protectors","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.227484Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:aafefe5297457cf1e8bc0f220be6eb23c132e61616545911b02eed02575c8140","observation_id":"3a81f670-e833-4298-8e67-b8628dd06914","resolution":{"observed_at":"2026-08-15T23:13:47.227484Z","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":"2026-08-15T23:13:47.231731Z","title":"Multi-task learning for dangerous object detection in autonomous driving","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.231731Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:c966a5c0a244fb524d482c602271fe6bbe1b45fe3b84dd1c0e7122a712478590","observation_id":"b6fe6e37-6a5d-4185-86fa-dcc7dff0ba65","resolution":{"observed_at":"2026-08-15T23:13:47.231731Z","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":"2026-08-15T23:13:47.235541Z","title":"Multinet: Multi-modal multi-task learning for autonomous driving","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.235541Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:4b984ea28fa180bc25b8cd110646f617030fcdeb9218bcdbed45f4255a445368","observation_id":"24d352f3-c607-4bdb-b32e-3ecc791c22a2","resolution":{"observed_at":"2026-08-15T23:13:47.235541Z","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":"2026-08-15T23:13:47.239261Z","title":"Improvable gap balancing for multi-task learning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.239261Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:cd7ed8c367e7b76b6fb9416bb790ed2bb8ceef26761942a9727e4c0ee50044bc","observation_id":"0e1634ea-4a08-41b3-bcc6-1614caf09191","resolution":{"observed_at":"2026-08-15T23:13:47.239261Z","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":"2026-08-15T23:13:47.243935Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.243935Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:9c424ffba33a965d619d41476b64e9d93f8880d93eb38bc4e42d17bf801cda4a","observation_id":"c884c52d-4d1c-4ff2-9838-7494b6db7730","resolution":{"observed_at":"2026-08-15T23:13:47.243935Z","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":"2026-08-15T23:13:47.248488Z","title":"Learning to confuse: generating training time adversarial data with auto-encoder","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.248488Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:6e13b432cb2cc7a3855a1cceae50bfdc438ce3896cb2fcb6c16c6a587f9a873e","observation_id":"50ddce1d-7690-4849-97d2-a3f48e34b89c","resolution":{"observed_at":"2026-08-15T23:13:47.248488Z","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":"2026-08-15T23:13:47.252412Z","title":"Efficiently identifying task groupings for multi-task learning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.252412Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:ed7babe7214aede4ab744c6f43a25b16a0e78868a83678139956bfc62af540ef","observation_id":"77c8b851-8e1e-4f0e-9b4e-b674a269846a","resolution":{"observed_at":"2026-08-15T23:13:47.252412Z","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":"2026-08-15T23:13:47.256139Z","title":"W., and Shi, M","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.256139Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:40f94640f35d57479158c93f9c2a1484d2fb637184ca1d40f16584bed6b08af6","observation_id":"7876674d-0711-4f4e-9b21-ca975786f1a0","resolution":{"observed_at":"2026-08-15T23:13:47.256139Z","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":"2026-08-15T23:13:47.260297Z","title":"Adversarial examples make strong poisons","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.260297Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:b29292b005e1903b0943ddfee62884a14619face18de8a0c000897770e146318","observation_id":"e3bc4c29-c1f2-4402-84d9-576a0a1b240f","resolution":{"observed_at":"2026-08-15T23:13:47.260297Z","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":"2026-08-15T23:13:48.579157Z","title":"Robust unlearnable examples: Protecting data privacy against adversarial learning","venue":null,"work_id":"cc35cad6-d050-483f-856e-785cda2fc553","year":2022},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.265220Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:3d1ccbbbeb41dcdfd798c8e4d0d76d213561faa2c3f45675e363f084f63ed1f2","observation_id":"711eca46-8911-45ff-922a-2b41d43d4cb7","resolution":{"observed_at":"2026-08-15T23:13:48.584098Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:13:48.566220Z","title":"Dynamic channel pruning: Feature boosting and suppression","venue":null,"work_id":"3fe964d9-7de2-40ea-8cf9-b1ddfc284d25","year":2019},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.269535Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:77e77415b3853b1acf50621d1ae8801a52c596f129c2d271ea33625781818ef6","observation_id":"1e366748-c90e-482f-970a-5c57e19b9d0d","resolution":{"observed_at":"2026-08-15T23:13:48.570552Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:13:48.554565Z","title":"Mora: Improving ensemble robustness evaluation with model reweighing attack","venue":null,"work_id":"501a451f-243c-4b71-ac2d-289b57d39e34","year":2022},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.273415Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:13771007ebba76d25d9d7fb4caac284a78b27e6542d8816ee9f281944cdca213","observation_id":"e47fd4aa-78bf-4a47-93e7-c9d67ff8003d","resolution":{"observed_at":"2026-08-15T23:13:48.558574Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:13:48.542377Z","title":"Dataset security for machine learning: Data poisoning, backdoor attacks, and defenses","venue":null,"work_id":"31adbe11-6038-4cd7-97d7-563b3314d4da","year":2022},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.278004Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:08c93b03e64ec0bf10fe510dafa6da60c528792e5bdb930281c685783f5edce4","observation_id":"b00ca94f-134b-41f3-871e-ec2721f3c903","resolution":{"observed_at":"2026-08-15T23:13:48.546326Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1708.06733","last_updated":"2019-03-11T20:45:33Z","snapshot_observed_at":"2026-08-12T15:43:59.037380Z","submitted_at":"2017-08-22T17:31:54Z","title":"BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1708.06733","snapshot_observed_at":"2026-08-15T23:13:47.281490Z","title":"Badnets: Identifying vulnerabilities in the machine learning model supply chain","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.281490Z"},"links":{"cited_paper":"/paper/1708.06733","citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:3c361c8bbc563450b4abf076703c787293c95328ce0ff1eed59348bbc45f1630","observation_id":"e109bd10-abad-4598-83de-193bfa62fbba","resolution":{"observed_at":"2026-08-15T23:13:47.281490Z","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":"2026-08-15T23:13:48.530131Z","title":"Dynamic task prioritization for multitask learning","venue":null,"work_id":"cf8afd59-c3dc-4150-acda-efaae61b9b37","year":2018},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.285736Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:965ab1ae9475490e388124423eea66c1769ba17f2d290377d2a421c8304f164d","observation_id":"3874721b-cb9a-47b4-9bc0-7e3da3b79072","resolution":{"observed_at":"2026-08-15T23:13:48.534867Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:13:48.518099Z","title":"Learning to branch for multi-task learning","venue":null,"work_id":"1697cea9-c154-4d2d-8550-9f8e75c1f13d","year":2020},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.289566Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:7ff9d2bafba2f02d04d8f7fa5faed5f61a4abaaa40de193ea33fba4748402ef6","observation_id":"227df6e5-a6ea-471f-953c-f5fdc41d1034","resolution":{"observed_at":"2026-08-15T23:13:48.522711Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:13:48.506865Z","title":"S., and Osadchy, R","venue":null,"work_id":"747a05b9-8aac-4ad5-aef4-726b915252a7","year":2018},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.293674Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:ca88eb8b268f96fb079b005f0aefeed7ce5d87f28971580dfe76130fa8d628d5","observation_id":"b28ad85a-f33c-4cd1-84fb-fc82e144897a","resolution":{"observed_at":"2026-08-15T23:13:48.510665Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:13:48.494084Z","title":"Indiscriminate poisoning attacks on unsupervised contrastive learning","venue":null,"work_id":"dad1a5ce-b808-473f-a5d8-ff8190b1bbcf","year":2023},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.297800Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:1e1b8f16e2f68f004ef7a1d92049ffe5342cea13e3294b0c7a13945d6d22b588","observation_id":"f9e9c1ec-4c5a-4255-b464-783c1f3c6004","resolution":{"observed_at":"2026-08-15T23:13:48.498236Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:13:48.481878Z","title":"Deep residual learning for image recognition","venue":null,"work_id":"2d2aadf3-e03f-4297-b18d-bed90be11b1e","year":2016},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.302611Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:800c8656016f3c1b90f3da5fdb88a1498316ce1438ab09079f95340895643ccf","observation_id":"8aee2e9a-39b2-4e62-8ffa-a294ec8353c8","resolution":{"observed_at":"2026-08-15T23:13:48.486253Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:13:48.469606Z","title":"Lead: Exploring logit space evolution for model selection","venue":null,"work_id":"652706bb-ecbf-4bf8-ab62-1b0bb9890f68","year":2024},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.306895Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:56ece892c6c5d204e77a1cd683bf3f12657cf644d945e018d6128d7c506ab4e9","observation_id":"e85f3b35-4f9a-489d-9791-ae4063a5b082","resolution":{"observed_at":"2026-08-15T23:13:48.474459Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:13:48.457019Z","title":null,"venue":null,"work_id":"d6b1cee4-02c4-406a-969b-e0c23fbdab56","year":2017},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.310277Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:b138aab05f64b727520ebc32ce56e8712508044789d69bd35dfae18acab06a21","observation_id":"0c5991a3-9756-4921-b276-57e985c6bff6","resolution":{"observed_at":"2026-08-15T23:13:48.461479Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:13:48.445638Z","title":"M., Bailey, J., and Wang, Y","venue":null,"work_id":"51fdbcd7-efa9-47c0-8c02-267d927a6d30","year":2021},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.314415Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:fdc218e4c6fdaa5169d0d44b2aef2da001674e99c1da533120cfed008667c659","observation_id":"ca6c34ab-6ec7-48af-b3e9-59f21d0765c5","resolution":{"observed_at":"2026-08-15T23:13:48.449564Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:13:48.434263Z","title":null,"venue":null,"work_id":"e9271b57-6f0a-4d8d-b8d9-34f3d7d05004","year":2025},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.317913Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:67e3cede39d6f22be06600f2686713fbc822d5cff2333390c7ce971d401250ec","observation_id":"14c01416-017e-4ff1-b422-5195bb836401","resolution":{"observed_at":"2026-08-15T23:13:48.437897Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2504.09772","last_updated":"2025-08-19T01:06:10Z","snapshot_observed_at":"2026-08-16T12:41:32.591456Z","submitted_at":"2025-04-14T00:27:45Z","title":"Two Heads are Better Than One: Test-time Scaling of Multi-agent Collaborative Reasoning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.09772","snapshot_observed_at":"2026-08-15T23:13:47.321220Z","title":"N., and Che, T","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.321220Z"},"links":{"cited_paper":"/paper/2504.09772","citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:0e734430451098a3282b2991b18529908bf95ce090a243391ed3cf736245a301","observation_id":"3c1b734e-9734-444a-875a-b0ba294443d4","resolution":{"observed_at":"2026-08-15T23:13:47.321220Z","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":"2026-08-15T23:13:48.422447Z","title":"and Joo, J","venue":null,"work_id":"b1889a94-2a10-409a-8a09-474083f8f139","year":2021},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.325122Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:721cf4d99898eb5c77c2fef3fbfe7badb5af72da56f47d541ecba6453f30573d","observation_id":"6af3f67d-cec0-4979-97ea-82f77d6b6c55","resolution":{"observed_at":"2026-08-15T23:13:48.426248Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:13:48.410683Z","title":"Multi-task learning using uncertainty to weigh losses for scene geometry and semantics","venue":null,"work_id":"edc56d43-2d42-4223-98b2-8d4e3a1f7db2","year":2018},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.329221Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:38351a93554f4de59538bfd625346dbd24736fd67b2065b222b62630b0ec90dc","observation_id":"0d34285a-4307-45a8-b0c0-8d198a65fb0f","resolution":{"observed_at":"2026-08-15T23:13:48.414806Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:13:48.398618Z","title":null,"venue":null,"work_id":"bd1aa48c-2ed0-4006-a3b9-7e73376320bc","year":2017},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.333294Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:0afd5bc7e9a82dcae6b280538e47eb90b242d88dd88d2d482df71ccad90b83f9","observation_id":"137433d1-d8d0-42e4-9e44-3c625848c6e4","resolution":{"observed_at":"2026-08-15T23:13:48.402252Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:13:48.387513Z","title":"Reasonable effectiveness of random weighting: A litmus test for multi-task learning","venue":null,"work_id":"98117779-ab09-4ba7-baa5-efe98b78295f","year":2022},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.337662Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:bf143c775b8e6985752cb6c427884d86a4f8c8420d3beec7c32fcee8ecc5d799","observation_id":"cbd0dc49-6e37-437d-b95f-cb3d4416f6f3","resolution":{"observed_at":"2026-08-15T23:13:48.391421Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:13:48.376161Z","title":"Pareto multi-task learning","venue":null,"work_id":"1c6b64c0-f7fa-42b0-9b36-27b58f87d5fc","year":2019},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.341660Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:dc9901d00e8557b847ad6b539e9c3d0e46f73ffe1ad64b68bec7411f671ab8bd","observation_id":"a3088efe-f9e1-4217-9b49-dfcd0c02214b","resolution":{"observed_at":"2026-08-15T23:13:48.380147Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.14250","last_updated":"2024-03-21T09:22:23Z","snapshot_observed_at":"2026-08-16T14:43:07.895150Z","submitted_at":"2024-03-21T09:22:23Z","title":"Safeguarding Medical Image Segmentation Datasets against Unauthorized Training via Contour- and Texture-Aware Perturbations","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.14250","snapshot_observed_at":"2026-08-15T23:13:47.346166Z","title":"Safeguarding medical image segmentation datasets against unauthorized training via contour-and texture-aware perturbations","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.346166Z"},"links":{"cited_paper":"/paper/2403.14250","citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:a9fecc0e66980f181c27c6c0373e255004a55acfcb4f07eafd7675ef93950906","observation_id":"7d617747-8f2f-4eab-b9e1-83badd3f04a0","resolution":{"observed_at":"2026-08-15T23:13:47.346166Z","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":"2026-08-15T23:13:48.365325Z","title":null,"venue":null,"work_id":"91cfe8a0-e02d-4d05-8046-ae4295ebdba3","year":2019},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.350257Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:1b5f1d75b1821a44fe1fb6c65fd149e969ba06732290c98f31f7b41165b3af30","observation_id":"016dcccd-3f3e-4ffc-81ac-85064136ba54","resolution":{"observed_at":"2026-08-15T23:13:48.369098Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:13:48.354014Z","title":null,"venue":null,"work_id":"12f847f6-7461-431d-b494-c319c6e9ba0e","year":2019},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.354077Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:88865a13b3d71b7a6421034e9b5567da2f0ae6229006bce67a13239906edd325","observation_id":"496d9b5a-0845-4768-97bb-180e14e82d90","resolution":{"observed_at":"2026-08-15T23:13:48.358016Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:13:48.341962Z","title":"Game-theoretic unlearnable example generator","venue":null,"work_id":"fe52a20d-168e-480b-a47a-1660d7d05b09","year":2024},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.358117Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:b6429912fc53b412517353c0330d0564e101bba9a1c165935d01f448a95ec12a","observation_id":"4033f4ca-10ea-4f54-8483-330098c514e6","resolution":{"observed_at":"2026-08-15T23:13:48.345857Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:13:48.330697Z","title":"Breaking free from MMI : A new frontier in rationalization by probing input utilization","venue":null,"work_id":"35bb00ea-d229-4b38-9f0c-9e5a51588265","year":2025},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.362907Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:92085c3c7bf7c24f1cfcab7bf85f54254c0b2711fa2fe7510ebc1f6564004950","observation_id":"a6c4d38f-ad13-4839-adb9-c9aeb211e070","resolution":{"observed_at":"2026-08-15T23:13:48.334800Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:13:48.318600Z","title":"Adversarial cooperative rationalization: The risk of spurious correlations in even clean datasets","venue":null,"work_id":"92e52f39-f59c-4cd4-8767-a3ccff98c33f","year":2025},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.366790Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:9dded9201c9bb54b6c5283529db7f07191d28257e35e213cd2a66076c343ca95","observation_id":"03f71c0b-7b48-4f56-a599-f6cb10d8f06f","resolution":{"observed_at":"2026-08-15T23:13:48.322867Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:13:48.303040Z","title":"Multimodal unlearnable examples: Protecting data against multimodal contrastive learning","venue":null,"work_id":"5ff4c3e7-bc07-4f96-a850-04e53cb549ad","year":2024},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.370552Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:5fe1d59f96224bc8ab3435306b9d140e17cc6a4bbf92d3235e74ae6934c6d0e3","observation_id":"771ee326-8221-4f5d-8fdd-ead17d3cc79d","resolution":{"observed_at":"2026-08-15T23:13:48.308556Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:13:48.290841Z","title":"Deep learning face attributes in the wild","venue":null,"work_id":"ae79df1f-8b92-4682-9e14-d1291d5f97af","year":2015},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.374478Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:c13e37ff96a06c33d86031437b6c0b3842f584de72f2067d86d85fe54baea57e","observation_id":"a1ddd532-a3af-4c96-8b1a-bcee02f8bd3d","resolution":{"observed_at":"2026-08-15T23:13:48.294882Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:13:48.278516Z","title":"Image shortcut squeezing: Countering perturbative availability poisons with compression","venue":null,"work_id":"edb1b755-ab3a-47a7-b56e-4bd9214af718","year":2023},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.378394Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:e839a3da10eb4125a10c2594de480d747722f1cf7f63071a2f913e5c6525d3af","observation_id":"27b49673-7640-4a37-9df7-22689c19778f","resolution":{"observed_at":"2026-08-15T23:13:48.283030Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:13:48.267224Z","title":"Exploring the limits of model-targeted indiscriminate data poisoning attacks","venue":null,"work_id":"53a251b8-e4ad-4079-a259-0a175f0f7e23","year":2023},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.382069Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:58dee0151028b9c0f5555765c34886f6cfc6dd186669626ad343bb760dc4db30","observation_id":"6d0f341a-ecfb-47a4-b87b-de586e09f390","resolution":{"observed_at":"2026-08-15T23:13:48.271013Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:13:48.254145Z","title":"Towards deep learning models resistant to adversarial attacks","venue":null,"work_id":"ce39a4fa-8130-4afb-b971-29119d0cbcac","year":2018},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.385992Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:a7f896a625085a3e8e5306346d04a87fbec142ebad273af73daea0dd4a4c6026","observation_id":"2618a103-d6ec-49a9-868b-1baf9ddbf8d4","resolution":{"observed_at":"2026-08-15T23:13:48.258687Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:13:48.241884Z","title":null,"venue":null,"work_id":"eee937fe-5beb-40e5-ac25-0ffd530d30df","year":2024},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.389811Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:9b911a9a8a37db1bdfc97f1fcba0e00fce936d39145e141b3d059b3db8c4ce8c","observation_id":"ed821f0f-59b4-4fce-a037-d8763d8c44a1","resolution":{"observed_at":"2026-08-15T23:13:48.246381Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:13:48.229259Z","title":"Cross-stitch networks for multi-task learning","venue":null,"work_id":"a91ac083-07f5-45dd-8ffa-a70ca627cd58","year":2016},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.393935Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:d25692e51dd061a7547dca139f68cc0072946137db8061566a2347372fc35b02","observation_id":"5ae9741a-f76f-4226-9c59-0d4aead0321b","resolution":{"observed_at":"2026-08-15T23:13:48.233413Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:13:48.218009Z","title":null,"venue":null,"work_id":"31527739-a517-4763-aebf-56a97f06311a","year":2012},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.397826Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:5f2e5ab4dc66de166712aa02585bca9cf16a3c8d16c74e6cdbd0817c2db086e9","observation_id":"15f0feb7-dfa3-4b0e-8dd5-2669cdf4ea6e","resolution":{"observed_at":"2026-08-15T23:13:48.221816Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:13:48.205713Z","title":"Multi-task learning as a bargaining game","venue":null,"work_id":"20f6fdeb-32af-49ff-879d-9133276f05ec","year":2022},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.401854Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:25c42748e32a66f8f7aa2d2de4a2289661bc27f08be0093b41b7bf259356b327","observation_id":"32a775fa-bb7b-49e9-a4cb-3e6e711b4ff2","resolution":{"observed_at":"2026-08-15T23:13:48.210156Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:13:48.193021Z","title":"Destruction-restoration suppresses data protection perturbations against diffusion models","venue":null,"work_id":"dee1ddf9-19dc-45ee-802c-314f9b08d809","year":2023},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.405614Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:d93284b987a49deadf0aa06b3c50764dd951c79c749ce5b3cbec0e465b32bdad","observation_id":"184d0b55-5bda-4386-8747-96b1525599dc","resolution":{"observed_at":"2026-08-15T23:13:48.197253Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.15127","last_updated":"2023-03-27T12:00:54Z","snapshot_observed_at":"2026-08-16T15:45:05.599496Z","submitted_at":"2023-03-27T12:00:54Z","title":"Learning the Unlearnable: Adversarial Augmentations Suppress Unlearnable Example Attacks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.15127","snapshot_observed_at":"2026-08-15T23:13:47.409491Z","title":"Learning the unlearnable: Adversarial augmentations suppress unlearnable example attacks","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.409491Z"},"links":{"cited_paper":"/paper/2303.15127","citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:c7bed3f219c9c925167a989e03b497faeb2fb691178e8737127fe86d61c0fe29","observation_id":"9145cefa-e988-430b-a43d-e2bb65974845","resolution":{"observed_at":"2026-08-15T23:13:47.409491Z","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":"2026-08-15T23:13:48.181330Z","title":"Apbench: A unified availability poisoning attack and defenses benchmark","venue":null,"work_id":"ed7415ef-0237-4d6d-9b22-84e92566f4f2","year":2024},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":56,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.413570Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:581958a8f9f3bf6d449d2f199075b3001e754659cab146a79d45121869445fe9","observation_id":"fd831e0e-b1e7-4772-a413-49bb953a58c6","resolution":{"observed_at":"2026-08-15T23:13:48.185670Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:13:48.169940Z","title":"Scalarization for multi-task and multi-domain learning at scale","venue":null,"work_id":"4b67c50f-5ce1-4be5-a1a8-bc12d49fd50a","year":2023},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":57,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.417118Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:d3c30d0b77ef13e96f16c31b9dc6b735be5d489ba1360bfd0d76113295b4fd37","observation_id":"fcc0882c-45fb-4571-8a36-afcc689c8d69","resolution":{"observed_at":"2026-08-15T23:13:48.173916Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1706.05098","last_updated":"2017-06-15T21:38:12Z","snapshot_observed_at":"2026-08-13T21:53:02.384757Z","submitted_at":"2017-06-15T21:38:12Z","title":"An Overview of Multi-Task Learning in Deep Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1706.05098","snapshot_observed_at":"2026-08-15T23:13:47.420765Z","title":"An overview of multi-task learning in deep neural networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":58,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.420765Z"},"links":{"cited_paper":"/paper/1706.05098","citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:916c867c2bbbb4bdd1adf37c7bfc65e27d7d98ece83a3fd12b40874e07e9acb5","observation_id":"56e075ab-4cbc-4499-b9a5-d405a5d4c6e4","resolution":{"observed_at":"2026-08-15T23:13:47.420765Z","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":"2026-08-15T23:13:48.158809Z","title":"Autoregressive perturbations for data poisoning","venue":null,"work_id":"549b02e3-5ff4-4e31-896f-b05d196ec044","year":2022},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":59,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.425101Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:459fb344bd4db8052d05067f91315e20b260bcfac85cf0011dad5de2b205503e","observation_id":"700ee653-da2f-490b-a997-b1b0d4977dea","resolution":{"observed_at":"2026-08-15T23:13:48.162733Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:13:48.146912Z","title":"P., and Goldstein, T","venue":null,"work_id":"64a679f6-9145-4369-ba4a-9ce89acf581c","year":2021},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":60,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.428496Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:cd9b89cbdd218ba97bec35a04329e69a3491bae030cecb0ad17bfd625ea1d11d","observation_id":"cda1c0ff-83df-45ad-84dd-725857fa612e","resolution":{"observed_at":"2026-08-15T23:13:48.150765Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:13:48.135531Z","title":"and Koltun, V","venue":null,"work_id":"91eb6670-e022-4ab2-b913-ccf86c901d11","year":2018},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":61,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.432279Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:a43ec03f94565ad2510504e22d1fe89f25a1eeb15b6aa7efc0dd4148d2e43b5c","observation_id":"e418a39e-7e62-45d3-ade6-eac5e1c2887d","resolution":{"observed_at":"2026-08-15T23:13:48.139156Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:13:48.124389Z","title":"Independent component alignment for multi-task learning","venue":null,"work_id":"f01c4a21-47e4-4cac-aff9-9ad1296a3005","year":2023},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":62,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.436068Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:c76ac474d9ff2cc789307f8aa675f699a09488eb10e34cbf18c1ac68e9918127","observation_id":"42c3bbd8-f33f-4f0f-b4dc-de81ca2173d4","resolution":{"observed_at":"2026-08-15T23:13:48.127897Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:13:48.111853Z","title":"and Zisserman, A","venue":null,"work_id":"ef5b2a8f-93ad-4dd9-8f6c-b73d6989b8dc","year":2015},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":63,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.439843Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:b12e1ab2b16a561f971358d52b9919c1fc104ec2687559e7ff996acc0d1fe4ac","observation_id":"26f03b6b-09c8-4617-983d-072f36001e28","resolution":{"observed_at":"2026-08-15T23:13:48.115937Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:13:48.099871Z","title":"Which tasks should be learned together in multi-task learning? In Proc","venue":null,"work_id":"e17c7a2a-7d31-4301-87d4-ac588e9ebd6b","year":2020},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":64,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.444778Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:e5d391571a6db0651012fe92daf15493096855fabce834557a1097cc9f10f4d8","observation_id":"2c8718db-73b8-48b4-9634-69e56c0c6624","resolution":{"observed_at":"2026-08-15T23:13:48.103947Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.09909","last_updated":"2024-10-13T16:34:46Z","snapshot_observed_at":"2026-08-16T14:42:24.371423Z","submitted_at":"2024-10-13T16:34:46Z","title":"UnSeg: One Universal Unlearnable Example Generator is Enough against All Image Segmentation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.09909","snapshot_observed_at":"2026-08-15T23:13:47.449225Z","title":"Unseg: One universal unlearnable example generator is enough against all image segmentation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":65,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.449225Z"},"links":{"cited_paper":"/paper/2410.09909","citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:5573a9a3612fa4f19f6829af437cb7387add33f77518bd01312e245d597df4ea","observation_id":"03911c19-11d7-45b2-94ce-be4e47cf20f4","resolution":{"observed_at":"2026-08-15T23:13:47.449225Z","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":"2026-08-15T23:13:48.086833Z","title":"Google accused of inappropriate access to medical data in potential class-action lawsuit, jun 2019","venue":null,"work_id":"fe2761c8-2847-4ec4-888d-92e534e99af6","year":2019},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":66,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.453330Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:aa7814016a20f85b0bc72f067e82b49be3387b7e4329e91b4b86e14b83374635","observation_id":"5fcbdee7-9639-481b-8329-677e5a8ec2d9","resolution":{"observed_at":"2026-08-15T23:13:48.091092Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:13:48.074797Z","title":"Benchmarking adversarial robustness of image shadow removal with shadow-adaptive attacks","venue":null,"work_id":"3bc5442b-6db3-4a3d-a5d6-9947aa57cb5e","year":2024},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":67,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.457585Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:97657446412d98c8f9d05153587c1721f0022c474867ac2f266a7e77067e71e9","observation_id":"7e59a513-bcaf-4ba3-8837-3a3680ecd959","resolution":{"observed_at":"2026-08-15T23:13:48.079000Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:13:48.061288Z","title":null,"venue":null,"work_id":"e0cdf9cc-e8fd-4e54-94a4-7222aa1e4995","year":2017},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":68,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.461522Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:58af0f151ea2fa47fe2471a2045e15e2ea94d9d4063aa561aeff4ae8334580b5","observation_id":"77dd6d80-f3f5-47a0-9c3d-fefade406165","resolution":{"observed_at":"2026-08-15T23:13:48.066383Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.03644","last_updated":"2024-10-04T17:49:32Z","snapshot_observed_at":"2026-08-16T14:43:05.036449Z","submitted_at":"2024-10-04T17:49:32Z","title":"Unlearnable 3D Point Clouds: Class-wise Transformation Is All You Need","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.03644","snapshot_observed_at":"2026-08-15T23:13:47.465955Z","title":"Unlearnable 3d point clouds: Class-wise transformation is all you need","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":69,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.465955Z"},"links":{"cited_paper":"/paper/2410.03644","citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:42d9d2b5abdb898ab71413171b872aaf782d3674e602085aaa0de8b58b47b870","observation_id":"5d12a5b4-b65a-4fd9-b2fd-bff26ca01331","resolution":{"observed_at":"2026-08-15T23:13:47.465955Z","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":"2026-08-15T23:13:48.047966Z","title":"A3: Few-shot prompt learning of unlearnable examples with cross-modal adversarial feature alignment","venue":null,"work_id":"f0a740c5-028b-4c8a-a957-9338b60de28f","year":2025},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":70,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.470001Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:fd59742d09b4ceeb6230002fdfc679aa555a657820bd01f005dba741067ad646","observation_id":"3ec219d8-7d53-4d42-86de-6968d87e5402","resolution":{"observed_at":"2026-08-15T23:13:48.051802Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2503.16872","last_updated":"2025-04-01T08:56:20Z","snapshot_observed_at":"2026-08-18T17:15:12.954228Z","submitted_at":"2025-03-21T06:12:06Z","title":"Lie Detector: Unified Backdoor Detection via Cross-Examination Framework","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.16872","snapshot_observed_at":"2026-08-15T23:13:47.473794Z","title":"Lie detector: Unified backdoor detection via cross-examination framework","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":71,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.473794Z"},"links":{"cited_paper":"/paper/2503.16872","citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:cb14678ff87d923d9a4785eb879d14b8febfb19fa8ceae0c7327227afa9f681e","observation_id":"05620809-b67d-4be2-b8b6-1ed9016aedc4","resolution":{"observed_at":"2026-08-15T23:13:47.473794Z","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":"2026-08-15T23:13:48.035758Z","title":"One-pixel shortcut: On the learning preference of deep neural networks","venue":null,"work_id":"bfec0099-bffa-4985-98c7-06a0d4e1ee3c","year":2023},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":72,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.477678Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:5348140c59a0a4aa99ebc7f701fe149ae18b41f95807cc9e55aab35ec07acd14","observation_id":"7b9dbe64-a740-4a4a-98c9-1f4b225307b8","resolution":{"observed_at":"2026-08-15T23:13:48.040347Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:13:48.024402Z","title":"Transferable adversarial attacks on sam and its downstream models","venue":null,"work_id":"73744f92-6a0d-483f-9c96-d95e80ea9324","year":2024},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":73,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.481535Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:898fd9d52b229522d78926c3fc4ea7ce38f6554b05cfd981455145da74e92730","observation_id":"5ae105ad-fe37-4e12-8281-10027232a8f2","resolution":{"observed_at":"2026-08-15T23:13:48.028018Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:13:48.010675Z","title":"Mitigating the curse of dimensionality for certified robustness via dual randomized smoothing","venue":null,"work_id":"3745a093-5b52-4e99-895a-74168ea39ca0","year":2024},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":74,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.486119Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:58c3ea3592bc57b60a445df6613411fd90ee4bbd24041097f3a520e9d42f3376","observation_id":"6e01d0f9-be3f-4a5b-99b8-82b85c08e7f5","resolution":{"observed_at":"2026-08-15T23:13:48.014864Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2503.00383","last_updated":"2025-04-03T05:50:56Z","snapshot_observed_at":"2026-08-16T14:43:09.728195Z","submitted_at":"2025-03-01T07:15:21Z","title":"Theoretical Insights in Model Inversion Robustness and Conditional Entropy Maximization for Collaborative Inference Systems","version":2},"cited_work":{"arxiv_id":"2503.00383","doi":null,"metadata_source":"pith","pith_arxiv_id":"2503.00383","snapshot_observed_at":"2026-08-15T23:13:47.651481Z","title":"Theoretical Insights in Model Inversion Robustness and Conditional Entropy Maximization for Collaborative Inference Systems","venue":"cs.LG","work_id":"fb4789c5-f112-48d6-b70d-6b62cd1292db","year":2025},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":75,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.490407Z"},"links":{"cited_paper":"/paper/2503.00383","citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:a7c0a7a817f1cc9e900b21c886f80ec02b13f34fea1debae81c31b1597ca8974","observation_id":"8d1c173a-6132-498b-9f3b-12e6d50f06ca","resolution":{"observed_at":"2026-08-15T23:13:47.655394Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:13:47.998506Z","title":"Is feature selection secure against training data poisoning? In Proc","venue":null,"work_id":"4e8ad7e1-edf4-4dd7-a8c8-77450d1d7a89","year":2015},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":76,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.495345Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:47af236371858c785eb53a5b0124283ceeb02cb5b9fd5d687778d277f576bf8e","observation_id":"43df5350-ca80-4ce8-a257-7213d7e2d826","resolution":{"observed_at":"2026-08-15T23:13:48.002766Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.01017","last_updated":"2024-07-02T05:47:02Z","snapshot_observed_at":"2026-08-16T13:38:14.863135Z","submitted_at":"2024-07-01T07:05:44Z","title":"Coding for Intelligence from the Perspective of Category","version":2},"cited_work":{"arxiv_id":"2407.01017","doi":null,"metadata_source":"pith","pith_arxiv_id":"2407.01017","snapshot_observed_at":"2026-08-15T23:13:47.634418Z","title":"Coding for Intelligence from the Perspective of Category","venue":"cs.CV","work_id":"ff7097a5-1154-4940-93a6-7b991b7db94b","year":2024},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":77,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.499949Z"},"links":{"cited_paper":"/paper/2407.01017","citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:816c66a9ebb4da46c235ebb7ae14153c0f2b10feb97f502162b049320dd546b3","observation_id":"1bf7db17-ebfa-434f-a940-ceea8f11db23","resolution":{"observed_at":"2026-08-15T23:13:47.638777Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:13:47.986609Z","title":"Availability attacks create shortcuts","venue":null,"work_id":"d1b5506e-2315-4f91-9ab0-d552fe6975a7","year":2022},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":78,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.504364Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:87194236a032f8bc0361a49f7318d4ef8b90436189f27d834c1887a13f549aac","observation_id":"1b4249b8-6d2e-4e01-87b5-a3cc1c1399f6","resolution":{"observed_at":"2026-08-15T23:13:47.990836Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:13:47.974060Z","title":"Gradient surgery for multi-task learning","venue":null,"work_id":"ee1278d6-e665-47d8-83bd-b0ba5826f53b","year":2020},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":79,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.508349Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:ca197534851c43bff3e2bea54dd5b7e6e798916122677e42ef89aff2de4ed3f1","observation_id":"94594bee-e78a-4417-9223-75fd82ed3454","resolution":{"observed_at":"2026-08-15T23:13:47.978007Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:13:47.961608Z","title":"Lafeat: Piercing through adversarial defenses with latent features","venue":null,"work_id":"50307905-3ab5-4518-b511-009901b673b3","year":2021},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":80,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.511368Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:6596a122e8ef8d411eee2e8b6f5c10cad14c9c422f7d6e28b5fa5b37489aa62e","observation_id":"7e065b3e-0c73-4e4e-be6e-78be7c457016","resolution":{"observed_at":"2026-08-15T23:13:47.966142Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:13:47.949526Z","title":null,"venue":null,"work_id":"8df1ab71-c4c3-407b-b786-d4dff5635e3f","year":2022},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":81,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.514349Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:83d8e7daea7812459b855149852e0713a05beef48f0fa6b20c07bec3fe77af0e","observation_id":"92be5b92-419c-483c-9ca4-6858b2e6ef9d","resolution":{"observed_at":"2026-08-15T23:13:47.953318Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:13:47.936437Z","title":"Lafit: Efficient and reliable evaluation of adversarial defenses with latent features","venue":null,"work_id":"9bb3d68a-cb4c-479f-999e-a1ca2cc66bf0","year":2023},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":82,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.517734Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:52469cf61492cb255c4678f48feb0aa73994f0ac9261fb26e74ca179d4f21011","observation_id":"c6081058-3113-4826-87e4-7f75d9859907","resolution":{"observed_at":"2026-08-15T23:13:47.941506Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:13:47.925739Z","title":null,"venue":null,"work_id":"af65d250-7121-48a4-982c-2ff43ef4806b","year":2023},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":83,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.521358Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:982928ad8e07acf523966016c8305b5d8d8bf31b10358321b6e9e8a054107817","observation_id":"04fea6b3-cd66-4b99-b36a-f9fa8cb851c1","resolution":{"observed_at":"2026-08-15T23:13:47.929087Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:13:47.913947Z","title":null,"venue":null,"work_id":"44ecc381-15a1-488e-a43b-22769392a610","year":2024},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":84,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.524747Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:a48eed08d43c4d7a6d674f82c6593528382b038c9c889604c3d227f1ade791de","observation_id":"31be5133-30f0-436b-b724-954f2a6fec1e","resolution":{"observed_at":"2026-08-15T23:13:47.918227Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:13:47.900398Z","title":null,"venue":null,"work_id":"ea918253-04af-4cc0-bded-93343c0065ac","year":2024},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":85,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.527965Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:96224af2062893ca16730e088a83b1f9a2d8a81f83353e3d07e70152d6f8404b","observation_id":"3bfb5e09-931e-4ca7-98cc-5f42acdf2129","resolution":{"observed_at":"2026-08-15T23:13:47.904943Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:13:47.886187Z","title":"Unlearnable examples detection via iterative filtering","venue":null,"work_id":"dc36d49a-3915-45a9-8bbf-e3b467e84048","year":2024},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":86,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.531200Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:96ef5fe11aedb303c3a2bbb5bfb314311351665f9830f1905cdbc76fe1b3606a","observation_id":"fe5a5467-80ac-4154-865b-ffadccf9cb2c","resolution":{"observed_at":"2026-08-15T23:13:47.890534Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:13:47.873081Z","title":"Backdoor attacks against no-reference image quality assessment models via a scalable trigger","venue":null,"work_id":"d6a74943-8c47-4e95-8fb2-6bc082a930d3","year":2025},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":87,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.534539Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:a8e85d7e096d94d601c4c56c9f4db96ef7417e3d91f7ea635572116725221abb","observation_id":"4ebdd889-6dd1-4c49-aa69-1f232eda6111","resolution":{"observed_at":"2026-08-15T23:13:47.878004Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:13:47.859864Z","title":"and Wu, S.-H","venue":null,"work_id":"844100de-d1f9-4bf1-8ce8-4be40b100402","year":2021},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":88,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.538387Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:963b53fcb449e421f73cb3e0c1715b91959925cd287a97f041475286998e4f9f","observation_id":"abd921a2-dd44-4ef3-ba1c-26e5a8bb59ec","resolution":{"observed_at":"2026-08-15T23:13:47.864514Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:13:47.847344Z","title":"and Cho, H","venue":null,"work_id":"b270024f-98ad-43fd-895b-af49504af136","year":2023},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":89,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.542942Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:067c4ef8746781bf509e2ae43bd9566fcb9536d3db6382a10ff8041db94f4cc6","observation_id":"f32e8859-8825-4e08-b440-61bda4c9e151","resolution":{"observed_at":"2026-08-15T23:13:47.851552Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:13:47.835601Z","title":"Unlearnable clusters: Towards label-agnostic unlearnable examples","venue":null,"work_id":"4fdb1506-eb0f-489f-a154-a7267c5627ca","year":2023},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":90,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.547261Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:7b42e080b1e6329a46fa0603f50c85eda0c783be9b262d18a488c0d11f363901","observation_id":"954cb499-163b-4285-95af-1106eb5d08c2","resolution":{"observed_at":"2026-08-15T23:13:47.839762Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:13:47.551726Z","title":"and Yang, Q","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":91,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.551726Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:9a691afcde670ccbf329ee2093762b7875199f6bc24dba68a9e8e19be87ebbb6","observation_id":"5dff599f-423a-4380-8e16-603d13922714","resolution":{"observed_at":"2026-08-15T23:13:47.551726Z","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":"2026-08-15T23:13:47.816664Z","title":"Age progression/regression by conditional adversarial autoencoder","venue":null,"work_id":"d7dd312b-ea5a-42c5-bbea-554eeea2d173","year":2017},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":92,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.555549Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:b9ed1bd1b9ef59a828b44ba6377a81384d4ba844bb80ffbe0b9f572450a36231","observation_id":"e6cb0418-2724-48c2-a456-a191efe41520","resolution":{"observed_at":"2026-08-15T23:13:47.820214Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:13:47.803855Z","title":"and Lao, Y","venue":null,"work_id":"0eb335de-01dc-40eb-b52a-d3583ae53b74","year":2022},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":93,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.560192Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:b0129cf97b075736d395bb620ea708afa97440b38a50fecada5a62b58ffe8f42","observation_id":"32152f38-1b42-4e14-be27-2d825d90fa69","resolution":{"observed_at":"2026-08-15T23:13:47.808195Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:13:47.790528Z","title":"Towards physical world backdoor attacks against skeleton action recognition","venue":null,"work_id":"fae134cb-4548-4223-bc48-80f4fc05ab8d","year":2024},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":94,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.564449Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:5d3b4a3cf3bccfb20092feb92d3aa5d95e9c5e9ecb72efdc3e3f4ebfc83855b3","observation_id":"93c74da6-f18e-49ba-829c-9df00114de99","resolution":{"observed_at":"2026-08-15T23:13:47.795392Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.11011","last_updated":"2024-06-26T08:13:30Z","snapshot_observed_at":"2026-08-16T13:39:31.280651Z","submitted_at":"2024-06-26T08:13:30Z","title":"Toward Availability Attacks in 3D Point Clouds","version":1},"cited_work":{"arxiv_id":"2407.11011","doi":null,"metadata_source":"pith","pith_arxiv_id":"2407.11011","snapshot_observed_at":"2026-08-15T23:13:47.614354Z","title":"Toward Availability Attacks in 3D Point Clouds","venue":"cs.CR","work_id":"17c42a88-45c4-4719-8139-a2310c513465","year":2024},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":95,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.569566Z"},"links":{"cited_paper":"/paper/2407.11011","citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:b7d9f88b86d7717455d3364c8a70c579e391d19d163c11e8cabb50c6b2f20164","observation_id":"3bceb56f-d12b-4152-a74c-1f9209803377","resolution":{"observed_at":"2026-08-15T23:13:47.620782Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:13:47.778055Z","title":"Detection and defense of unlearnable examples","venue":null,"work_id":"7fa63fae-e71e-490e-9e09-77b9815bf8b7","year":2024},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":96,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.573532Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:f9dba40cc928d48d56d1e966e6f7e73080e0847802d34741ce2bf311c137010b","observation_id":"545fa827-6fdc-4ce8-af42-d809e03778cd","resolution":{"observed_at":"2026-08-15T23:13:47.782378Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:13:47.577731Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning","version":1},"reference_index":97,"source":"arxiv_source","source_observed_at":"2026-08-15T23:13:47.577731Z"},"links":{"citing_paper":"/paper/2505.05279"},"observation_digest":"sha256:f97dd71e10575867a0109e7a90005587d3a50db9c305e41e4e1d9e7616c7c032","observation_id":"12dfc59a-3625-486b-95b9-37cdf4364585","resolution":{"observed_at":"2026-08-15T23:13:47.577731Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2505.05279","last_updated":"2025-05-08T14:26:00Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-16T14:42:42.384496Z","submitted_at":"2025-05-08T14:26:00Z","title":"MTL-UE: Learning to Learn Nothing for Multi-Task Learning"},"reference_resolution":{"displayed":97,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":40,"verified_exact":3,"verified_fuzzy":54},"total_outbound_references":97},"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":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 97 of 97 outbound references and 0 inbound Pith citation observations for arXiv:2505.05279."}