{"as_of":"2026-08-09T14:57:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:150dc7cd9e9b35d438f100b7e52c7fa67532531408fc6815becc795136118b0f","coverage":[{"denominator":87,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":87,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-03T17:19:04.604580Z","state":"measured"},{"denominator":87,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":87,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+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/2512.10244/citation-record","integrity":"/paper/2512.10244/integrity","json":"/paper/2512.10244/citation-record.json","paper":"/paper/2512.10244"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T17:18:54.250365Z","title":"Pseudo-labeling and confirmation bias in deep semi-supervised learning","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-03T17:18:54.250365Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:407592d24fb7d2968ff7ec3454bb081c62d7794822c6f668dfd9aa1e9a909c58","observation_id":"fa803f8e-848a-4c18-91a1-da9608fff9c0","resolution":{"observed_at":"2026-08-03T17:18:54.250365Z","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":"2026-08-03T17:18:54.353941Z","title":"Mixmatch: A holistic approach to semi-supervised learning.Advances in Neural Information Processing Systems (NeurIPS), 32, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-03T17:18:54.353941Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:7c1b3a5dfc4d89ec7c0551d37cdc52957c9756b962177c0e91b32037e013f1fb","observation_id":"e5366ae3-813f-4b0c-b147-5fc6a04d33c9","resolution":{"observed_at":"2026-08-03T17:18:54.353941Z","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":"2026-08-03T17:18:54.469420Z","title":"Cubuk, Alex Ku- rakin, Kihyuk Sohn, Han Zhang, and Colin Raffel","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-03T17:18:54.469420Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:0ab748e7ed31d7981fcc93369fcf1ad586499978f6bd8924dbd292d316ff44ee","observation_id":"31083e39-43e8-470a-84ba-473a06a83560","resolution":{"observed_at":"2026-08-03T17:18:54.469420Z","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":"2026-08-03T17:18:54.615120Z","title":"Adamatch: A unified approach to semi-supervised learning and domain adaptation","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-03T17:18:54.615120Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:83bfcbcbcae322d988686ed51cc4292b50f7962a5a17a9a07d9cb0c9a37d76dd","observation_id":"cf9769f0-725f-4da5-9fcb-70e4492dc352","resolution":{"observed_at":"2026-08-03T17:18:54.615120Z","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":"2026-08-03T17:18:54.730866Z","title":"Exponential moving average normalization for self-supervised and semi- supervised learning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-03T17:18:54.730866Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:2cb4391554ae5055628c6e4dc54aa5b10a7305b1708ac6f6195e3b15e2bfc52e","observation_id":"fc1c8c5e-ec21-4b55-85b0-9c746366767b","resolution":{"observed_at":"2026-08-03T17:18:54.730866Z","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":"2026-08-03T17:18:54.867182Z","title":"Curriculum labeling: Revisiting pseudo-labeling for semi-supervised learning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-03T17:18:54.867182Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:ad045e1bf053a3b4a0729bb35dd7b18d4ef6f5d46df52d3bdffd30c53bbc8243","observation_id":"d24066bb-ab4f-4540-9a1f-6670eb2b4410","resolution":{"observed_at":"2026-08-03T17:18:54.867182Z","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":"2026-08-03T17:18:55.009564Z","title":"Semi-supervised learning (chapelle, o","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-03T17:18:55.009564Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:96b11cd13e51c954d84d1ac296e31894a881db74f83fcc943d3ea975bfea3ca2","observation_id":"9f4214b9-f004-44a8-832e-14322b750ae2","resolution":{"observed_at":"2026-08-03T17:18:55.009564Z","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":"2026-08-03T17:18:55.157852Z","title":"Plot: Prompt learning with optimal transport for vision-language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-03T17:18:55.157852Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:065b0665e403ca39bbb65c94616d985df82cba747d593c90b15def3aa6593232","observation_id":"43d0a68d-ef0b-40ad-bfc2-fbb47992b7c5","resolution":{"observed_at":"2026-08-03T17:18:55.157852Z","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":"2026-08-03T17:18:55.328810Z","title":"Softmatch: Addressing the quantity-quality tradeoff in semi- supervised learning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-03T17:18:55.328810Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:efeefc32b51fdd2af7348ed8207d28db5e29cf0e189a8c9925681280c08aca47","observation_id":"b885693d-ee31-4790-bc1b-4adf42dbda2f","resolution":{"observed_at":"2026-08-03T17:18:55.328810Z","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":"2026-08-03T17:18:55.503035Z","title":"A simple framework for contrastive learning of visual representations","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-03T17:18:55.503035Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:1b6dc84a99b798c6ae437e4397ae1a161e8887c7277c8e8939ff283b088980d9","observation_id":"a72c4a10-46b5-4dad-b166-ef5cddcdcc23","resolution":{"observed_at":"2026-08-03T17:18:55.503035Z","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":"2026-08-03T17:18:55.634761Z","title":"Big self-supervised models are strong semi-supervised learners.Advances in Neural Information Processing Systems (NeurIPS), 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-03T17:18:55.634761Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:0beb1c0b8299d512c4ecb4cad35c99bcacd1a8a033721d9cbb568462378dd105","observation_id":"81675ae9-5bcf-40a7-a5c0-0b32c8d7178d","resolution":{"observed_at":"2026-08-03T17:18:55.634761Z","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":"2026-08-03T17:18:55.764328Z","title":"Reproducible scaling laws for contrastive language-image learning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-03T17:18:55.764328Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:9fe7d2f519a907cb4d1e70d07dcc14102dc968f331d28df6dcda8fd2a615187b","observation_id":"83259781-3a64-413c-80d0-db96cb3f1f3b","resolution":{"observed_at":"2026-08-03T17:18:55.764328Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.12584","last_updated":"2025-05-28T22:49:18Z","snapshot_observed_at":"2026-08-07T18:10:03.494932Z","submitted_at":"2025-02-18T06:41:53Z","title":"Enhancing Semi-supervised Learning with Zero-shot Pseudolabels","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.12584","snapshot_observed_at":"2026-08-03T17:18:55.829407Z","title":"Enhancing semi-supervised learning with zero-shot pseudolabels.arXiv preprint arXiv:2502.12584, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-03T17:18:55.829407Z"},"links":{"cited_paper":"/paper/2502.12584","citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:424e65e5ca379ff3fd0a50ada43e009fe4c3a06fbd6de7fc2951920827cbf2f9","observation_id":"cf81058d-3bfc-4e38-a840-df30bbd1697c","resolution":{"observed_at":"2026-08-03T17:18:55.829407Z","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":"2026-08-03T17:18:55.895380Z","title":"Describing textures in the wild","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-03T17:18:55.895380Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:a9ab9eb09cca8c8a1a416ca876a36f09a1d9a40a25cdcb63c10f46894b34af4b","observation_id":"f9ca760e-2be8-45d6-9b07-fcabb5183d80","resolution":{"observed_at":"2026-08-03T17:18:55.895380Z","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":"2026-08-03T17:18:55.950394Z","title":"Imagenet: A large-scale hierarchical image database","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-03T17:18:55.950394Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:2436c400c5b4624fa30fa624f376d8bed0422c456f5f49eddacddff938f41ecd","observation_id":"85be580a-d1e6-4c2f-8d29-0a3b26ddbc24","resolution":{"observed_at":"2026-08-03T17:18:55.950394Z","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":"2026-08-03T17:18:56.062689Z","title":"Pseudo-labeling based practical semi-supervised meta-training for few-shot learning.IEEE Transactions on Image Processing (TIP), 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-03T17:18:56.062689Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:b68f7adb14fd2cd02cdd870d8cd7d36a3ebcb026e10e057c32fcc92b8b3e6d26","observation_id":"86f22a81-4a04-4fe4-bd0d-872addee952e","resolution":{"observed_at":"2026-08-03T17:18:56.062689Z","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":"2026-08-03T17:18:56.190849Z","title":"An image is worth 16x16 words: Transform- ers for image recognition at scale","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-03T17:18:56.190849Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:85c6bb517a6c321ff63b5a6e20ec141c3f6c60059e2f0902dfdfa0c1ccb039df","observation_id":"b557e78e-503f-47d3-8f91-6193d725f561","resolution":{"observed_at":"2026-08-03T17:18:56.190849Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.13505","last_updated":"2024-07-30T07:52:34Z","snapshot_observed_at":"2026-08-05T01:22:45.377898Z","submitted_at":"2024-02-21T03:39:04Z","title":"SimPro: A Simple Probabilistic Framework Towards Realistic Long-Tailed Semi-Supervised Learning","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.13505","snapshot_observed_at":"2026-08-03T17:18:56.256196Z","title":"Simpro: A simple probabilistic framework towards realistic long-tailed semi- supervised learning.arXiv preprint arXiv:2402.13505, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-03T17:18:56.256196Z"},"links":{"cited_paper":"/paper/2402.13505","citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:187d92dca144e9ad0eead8995bc197b32669f5a3dae6ca24aba0e52c0a4c3724","observation_id":"f1711d3b-1051-4d48-a942-abf845e95cff","resolution":{"observed_at":"2026-08-03T17:18:56.256196Z","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":"2026-08-03T17:18:56.350440Z","title":"Erasing the bias: Fine-tuning founda- tion models for semi-supervised learning.Forty-first Interna- tional Conference on Machine Learning (ICML), 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-03T17:18:56.350440Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:eeae08856f0ece995d6ddb663f66cbcf3093d39d4aaec32413edf88de7aabb4e","observation_id":"a1248a2f-ccfe-47a7-905e-a743ea4e9096","resolution":{"observed_at":"2026-08-03T17:18:56.350440Z","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":"2026-08-03T17:18:56.406847Z","title":"Clip- adapter: Better vision-language models with feature adapters","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-03T17:18:56.406847Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:1d0dc02002ddab015906e7dcceec0854dfe70b4a229fecd5381f4ea402362000","observation_id":"301d6dc0-a1ff-4bfd-af10-bbe9a9e88cc2","resolution":{"observed_at":"2026-08-03T17:18:56.406847Z","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":"2026-08-03T17:18:56.531130Z","title":"On calibration of modern neural networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-03T17:18:56.531130Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:06a3a7ec0a42ecbb0f9eaa7f69d9cbde3206bf1c56668d87476c9f0437147a88","observation_id":"b774fcc4-d24f-41a6-8517-09079d175824","resolution":{"observed_at":"2026-08-03T17:18:56.531130Z","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":"2026-08-03T17:18:56.624138Z","title":"Class-imbalanced semi- supervised learning with adaptive thresholding","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-03T17:18:56.624138Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:dccbbc1536dc98b0c3188cc0e2741be7be26e93c4cf194aa3fc22b1a20bb9b2f","observation_id":"b6563588-1ab4-4bef-98ab-0b5020e1dbae","resolution":{"observed_at":"2026-08-03T17:18:56.624138Z","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":"2026-08-03T17:18:56.715443Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-03T17:18:56.715443Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:fcff600c7b576dc52079ea7cea04270d57b934d65a9bbfeb9697a63ec52652e6","observation_id":"c3906061-bd89-4894-a942-842ba2ee7dd4","resolution":{"observed_at":"2026-08-03T17:18:56.715443Z","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":"2026-08-03T17:18:56.848564Z","title":"Momentum contrast for unsupervised visual repre- sentation learning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-03T17:18:56.848564Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:9fbe96baec3171b976e91c5a503210057e957fcd62ac6ec31b5474cadc4fe4ee","observation_id":"e90acde3-602f-4cff-a555-eabd7caa1d5a","resolution":{"observed_at":"2026-08-03T17:18:56.848564Z","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":"2026-08-03T17:18:56.962449Z","title":"Introducing eurosat: A novel dataset and deep learning benchmark for land use and land cover clas- sification","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-03T17:18:56.962449Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:954a23e925604215906553492aab7c6c25bc158169533e840c0d01e82aca9bed","observation_id":"a97915ae-29f8-48e2-b2a9-5c1ae4c1a1bf","resolution":{"observed_at":"2026-08-03T17:18:56.962449Z","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":"2026-08-03T17:18:57.113076Z","title":"Deep anomaly detection with outlier exposure","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-03T17:18:57.113076Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:4029be5450de7125a67f45305548083010d17a76d3d455f424c25698be8b3165","observation_id":"cbd54c1f-ab07-4b8a-aaea-df55584372e0","resolution":{"observed_at":"2026-08-03T17:18:57.113076Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1503.02531","last_updated":"2015-03-09T15:44:49Z","snapshot_observed_at":"2026-07-06T04:11:24.157003Z","submitted_at":"2015-03-09T15:44:49Z","title":"Distilling the Knowledge in a Neural Network","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1503.02531","snapshot_observed_at":"2026-08-03T17:18:57.254228Z","title":"Distill- ing the knowledge in a neural network.arXiv preprint arXiv:1503.02531, 2015","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-03T17:18:57.254228Z"},"links":{"cited_paper":"/paper/1503.02531","citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:cbf21a350ab8654988ff977d2b0d6a82830f67413a16f54317a359d004b88922","observation_id":"3721f9d0-f407-41e7-befc-1743253ec219","resolution":{"observed_at":"2026-08-03T17:18:57.254228Z","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":"2026-08-03T17:18:57.311954Z","title":"The curious case of neural text degeneration","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-03T17:18:57.311954Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:286473c65ea2ff060fc9abd3ce191760a51d1e78621c287fa437b3778ff80da2","observation_id":"67147960-12db-44de-a007-c7950aaa9df4","resolution":{"observed_at":"2026-08-03T17:18:57.311954Z","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":"2026-08-03T17:18:57.407993Z","title":"Pseudo-loss confidence metric for semi-supervised few- shot learning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-03T17:18:57.407993Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:39d49fe3ddaf2a60c4a40d3e7b1727e6784593bb0baba5813f7b750084867c6b","observation_id":"fd6da85f-b170-403c-8dd3-47f6d26cfbd5","resolution":{"observed_at":"2026-08-03T17:18:57.407993Z","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":"2026-08-03T17:18:57.534797Z","title":"Retrieval-enhanced contrastive vision-text models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-03T17:18:57.534797Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:347cfd37f27097be5ff95391923941a10cc63b5374a820cf0e21af63722f6368","observation_id":"b4a8cfa2-a28f-40fb-bd67-d41d040d55f7","resolution":{"observed_at":"2026-08-03T17:18:57.534797Z","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":"2026-08-03T17:18:57.607143Z","title":"Categorical reparam- eterization with gumbel-softmax","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-03T17:18:57.607143Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:5818b34a8ce6a3329c17467b5b3da665778babebf83a17b0c37eb05384e7ae53","observation_id":"d48aa36b-1d9b-43f2-8205-d4f1dd964dfd","resolution":{"observed_at":"2026-08-03T17:18:57.607143Z","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":"2026-08-03T17:18:57.662329Z","title":"Scaling up visual and vision-language representa- tion learning with noisy text supervision","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-03T17:18:57.662329Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:e3a5c7fce8efdb6e916da03df0285f6cc7ec0a821068a585518186bc8dfa38dd","observation_id":"13af4d13-47fa-421b-b086-31004565f13b","resolution":{"observed_at":"2026-08-03T17:18:57.662329Z","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":"2026-08-03T17:18:57.769850Z","title":"Opengan: Open-set recog- nition via open data generation","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-03T17:18:57.769850Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:8e1b938fb1ad4c5e71313ddddd03d76565b335a0df36e1948958c2e926e6a218","observation_id":"b90a7327-4195-4d47-9311-99d93cff307b","resolution":{"observed_at":"2026-08-03T17:18:57.769850Z","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":"2026-08-03T17:18:57.889368Z","title":"3d object representations for fine-grained categorization","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-03T17:18:57.889368Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:122f72e30067ff7b6e08ebfb0fddd88b2bacddaf9656765102da1f5c2efbc17c","observation_id":"3b49568e-03b5-4b23-80f3-75fa86daae95","resolution":{"observed_at":"2026-08-03T17:18:57.889368Z","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":"2026-08-03T17:18:58.000509Z","title":"Temporal ensembling for semi- supervised learning","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-03T17:18:58.000509Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:a54c820ed40aa2d429f0914fed6afa00dd1c99e067cceb439c63d9bc0a51378d","observation_id":"e000848e-0ab8-43bb-807d-1ab59a27b616","resolution":{"observed_at":"2026-08-03T17:18:58.000509Z","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":"2026-08-03T17:18:58.135921Z","title":"Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-03T17:18:58.135921Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:20fba79a8c5c3b8b75f686ba7edaedb3007b06595563ec4159d437e06c87ffa1","observation_id":"c3a2926c-3d76-48f6-8823-8ccce9e9b1a6","resolution":{"observed_at":"2026-08-03T17:18:58.135921Z","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":"2026-08-03T17:18:58.231964Z","title":"Learning to self-train for semi-supervised few-shot classification.Advances in Neural Information Processing Systems (NeurIPS), 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-03T17:18:58.231964Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:07a5002e6db7bab26dd748e300851579cf9cb33b6de43fee0df384169140d737","observation_id":"5c45cfdc-a11f-4612-9a30-ec9e411fbb4b","resolution":{"observed_at":"2026-08-03T17:18:58.231964Z","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":"2026-08-03T17:18:58.334399Z","title":"Multimodality helps unimodality: Cross- modal few-shot learning with multimodal models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-03T17:18:58.334399Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:d31d24bbd7b53ab83fdb6dacd6753e387f2cc7f365b76d6ea820743ccbe8a54e","observation_id":"d6933c19-b7e6-4936-a568-428628e824cb","resolution":{"observed_at":"2026-08-03T17:18:58.334399Z","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":"2026-08-03T17:18:58.420842Z","title":"Semi- supervised few-shot learning via multi-factor clustering","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-03T17:18:58.420842Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:6efc3bc96ca7985f8fb754c634878e597509ffe0f36eb073436137cad66f4035","observation_id":"d0442ae9-7b19-4fe7-bf8b-cef0b34050c9","resolution":{"observed_at":"2026-08-03T17:18:58.420842Z","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":"2026-08-03T17:18:58.520670Z","title":"Learning customized visual models with retrieval-augmented knowledge","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-03T17:18:58.520670Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:983fd391634f764c0cd36a06d300baa5644d34e851b3b0f0c4533901c91d84f9","observation_id":"d2e1a5d3-a784-4717-befc-a7ab2a7b0f65","resolution":{"observed_at":"2026-08-03T17:18:58.520670Z","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":"2026-08-03T17:18:58.641034Z","title":"Few-shot recognition via stage-wise retrieval-augmented fine- tuning","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-03T17:18:58.641034Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:782c891602eb97c8cc7b12abd9d02c5d1ad2efc59346e3215c1748c6b987f886","observation_id":"82f04371-768e-40f3-83af-4c671f7b336c","resolution":{"observed_at":"2026-08-03T17:18:58.641034Z","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":"2026-08-03T17:18:58.820334Z","title":"Tenet: Beyond pseudo-labeling for semi-supervised few-shot learn- ing.Machine Intelligence Research, pages 1–13, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-03T17:18:58.820334Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:f1833cc7496afcaa063993e87f3f4178fdca64dcf4c10cc80ff5d710c52bb3b7","observation_id":"e4194083-fea0-49c4-9d34-ed5af28ec175","resolution":{"observed_at":"2026-08-03T17:18:58.820334Z","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":"2026-08-03T17:18:58.971177Z","title":"Revisiting few-shot object detection with vision-language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-03T17:18:58.971177Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:4ffd735549098b4b80aa3c735294167b3ab1b7dfb765645286e5413a66bae6fd","observation_id":"364e7c56-0b51-48a3-848e-3cadf06621b8","resolution":{"observed_at":"2026-08-03T17:18:58.971177Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1306.5151","last_updated":"2013-06-21T14:31:57Z","snapshot_observed_at":"2026-07-06T03:16:28.287173Z","submitted_at":"2013-06-21T14:31:57Z","title":"Fine-Grained Visual Classification of Aircraft","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1306.5151","snapshot_observed_at":"2026-08-03T17:18:59.172123Z","title":"Fine-grained visual clas- sification of aircraft.arXiv:1306.5151, 2013","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-03T17:18:59.172123Z"},"links":{"cited_paper":"/paper/1306.5151","citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:3fd9c40bbfa0411b2318fc9bce69d84c840cc0329a76077f7cbd825b44c6cb08","observation_id":"66056b0e-7a88-4138-8f9f-e1a2f4a8f4a3","resolution":{"observed_at":"2026-08-03T17:18:59.172123Z","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":"2026-08-03T17:18:59.303030Z","title":"En- hancing clip with clip: Exploring pseudolabeling for limited- label prompt tuning.Advances in Neural Information Pro- cessing Systems (NeurIPS), 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-03T17:18:59.303030Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:aa1c39a609342ab914967a82e89e237c2cbd7cdd50f7dbfed4ed1f28acfa39f1","observation_id":"247a7bb1-0b66-4360-9d2f-dbc5c36fa92e","resolution":{"observed_at":"2026-08-03T17:18:59.303030Z","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":"2026-08-03T17:18:59.392267Z","title":"Long-tail learning via logit adjustment","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-03T17:18:59.392267Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:f80791f6af9c855445014864a1ba82be76db0305a260b5e09d01409c27ab5791","observation_id":"00594dc6-91f0-40aa-b857-9136ef84e65e","resolution":{"observed_at":"2026-08-03T17:18:59.392267Z","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":"2026-08-03T17:18:59.537334Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-03T17:18:59.537334Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:37ad19ab1bba3d6248c782c1d9ec2764f06b37de7670b91ce95a7fef4142581c","observation_id":"a9b8f252-155e-4208-83ff-6974afbbbb25","resolution":{"observed_at":"2026-08-03T17:18:59.537334Z","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":"2026-08-03T17:18:59.667625Z","title":"The neglected tails in vision-language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-03T17:18:59.667625Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:350b3e20e159ce3d6c34d56cbc4bab8e2043df10bc91b5878b665e4921cae155","observation_id":"6e62ee2b-d1a2-4dce-903c-4d54b67b75ee","resolution":{"observed_at":"2026-08-03T17:18:59.667625Z","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":"2026-08-03T17:18:59.819402Z","title":"Learning transferable visual models from natural language supervision","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-03T17:18:59.819402Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:3d40842f940d753114a34bbf239ad3c06b870d0c91d4030e42f34dd70291802c","observation_id":"cbc78a09-77dc-46d3-bf71-ad71b1fbb7b3","resolution":{"observed_at":"2026-08-03T17:18:59.819402Z","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":"2026-08-03T17:18:59.991170Z","title":"Im- proved zero-shot classification by adapting vlms with text 10 descriptions","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-03T17:18:59.991170Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:764e795b0ea4d8a7610da53ec93201adb5a5b07a9497c48a4884e22e180ef916","observation_id":"7212060e-8f95-49a8-a204-72de3a41dc2c","resolution":{"observed_at":"2026-08-03T17:18:59.991170Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2111.02114","last_updated":"2021-11-03T10:16:39Z","snapshot_observed_at":"2026-08-02T08:12:49.547570Z","submitted_at":"2021-11-03T10:16:39Z","title":"LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2111.02114","snapshot_observed_at":"2026-08-03T17:19:00.071554Z","title":"Laion-400m: Open dataset of clip-filtered 400 million image-text pairs","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-03T17:19:00.071554Z"},"links":{"cited_paper":"/paper/2111.02114","citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:e9f885d0fbc0d7b19190395729efda760258180f10fb46b7c93ecafbf3036ad0","observation_id":"e543abb1-d5eb-47ea-9a01-1cae7cdb98b7","resolution":{"observed_at":"2026-08-03T17:19:00.071554Z","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":"2026-08-03T17:19:00.239723Z","title":"Laion-5b: An open large-scale dataset for training next gen- eration image-text models.Advances in Neural Information Processing Systems (NeurIPS), 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-03T17:19:00.239723Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:f1709b0d86a7d16d8f3ab0928b0ab5bf8987dc42fd1d3fd0483483fff0ce81a9","observation_id":"8a1359f1-ab13-4f9c-9fcf-8ea176d5f61a","resolution":{"observed_at":"2026-08-03T17:19:00.239723Z","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":"2026-08-03T17:19:00.366920Z","title":"A closer look at the few-shot adaptation of large vision-language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-03T17:19:00.366920Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:9e1adc1c864596c5476b9e09c8d9e6efd4fddb66c93329cc150b25e2b8b8f460","observation_id":"effc1ccd-4511-4c32-930c-dd2aa8028fca","resolution":{"observed_at":"2026-08-03T17:19:00.366920Z","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":"2026-08-03T17:19:00.514622Z","title":"Fixmatch: Simpli- fying semi-supervised learning with consistency and confi- dence.Advances in Neural Information Processing Systems (NeurIPS), 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-03T17:19:00.514622Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:fac1864f4fe92154b329fdd26f64175e7d1f7368031e323b094cdc77fb19468b","observation_id":"e5271104-25c8-41e3-ab5a-d6046c56d311","resolution":{"observed_at":"2026-08-03T17:19:00.514622Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2103.06937","last_updated":"2021-03-11T20:21:16Z","snapshot_observed_at":"2026-07-06T10:49:09.382403Z","submitted_at":"2021-03-11T20:21:16Z","title":"The Semi-Supervised iNaturalist-Aves Challenge at FGVC7 Workshop","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.06937","snapshot_observed_at":"2026-08-03T17:19:00.645472Z","title":"The semi- supervised inaturalist-aves challenge at fgvc7 workshop","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-03T17:19:00.645472Z"},"links":{"cited_paper":"/paper/2103.06937","citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:2ab157f1de4397cc12b87df96db749873a79c5ab121f50314a733830b0fde4e2","observation_id":"82188966-40a1-4360-a877-79315d3ad2db","resolution":{"observed_at":"2026-08-03T17:19:00.645472Z","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":"2026-08-03T17:19:00.778893Z","title":"A real- istic evaluation of semi-supervised learning for fine-grained classification","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-03T17:19:00.778893Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:d2dac1157feac3e56915d2a3e6632dc86d8e06003e5ead834c2e0b17e1596e6f","observation_id":"03327b97-da68-472b-a3e2-e06a54c0ef2c","resolution":{"observed_at":"2026-08-03T17:19:00.778893Z","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":"2026-08-03T17:19:00.926087Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-03T17:19:00.926087Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:9ead9255b30ad2d97c8630b8ac978a1d2a59372e39fee37b82a6b546af1b7fc7","observation_id":"9a4d1d3d-3318-443c-9ced-598a5396e206","resolution":{"observed_at":"2026-08-03T17:19:00.926087Z","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":"2026-08-03T17:19:01.103054Z","title":"A closer look at the robustness of contrastive language-image pre-training (clip)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-03T17:19:01.103054Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:c76dcab5f4ebb6a3ec27d7497df5364dd746f39cd8cd4d0dfa32e6fad6d60668","observation_id":"4a9afe3c-3bbe-43f6-b331-209ffd5b50a7","resolution":{"observed_at":"2026-08-03T17:19:01.103054Z","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":"2026-08-03T17:19:01.252021Z","title":"An empirical study into what matters for calibrating vision-language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-03T17:19:01.252021Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:0e999002d00a3c238adef0424288b4db26bff2640c5c8cb0ce40df294347f885","observation_id":"f207a2b8-192f-4f5a-a6c5-6f9a3cb76c57","resolution":{"observed_at":"2026-08-03T17:19:01.252021Z","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":"2026-08-03T17:19:01.446551Z","title":"Neural priming for sample-efficient adaptation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-03T17:19:01.446551Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:1df219ed1b1e380cb7c151570674181ea543af94b9ea627c9ce46af9efb3d2a2","observation_id":"fdeca76f-1829-435d-b00f-198d2d95c0e8","resolution":{"observed_at":"2026-08-03T17:19:01.446551Z","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":"2026-08-03T17:19:01.640495Z","title":"Normface: L2 hypersphere embedding for face verifi- cation","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-03T17:19:01.640495Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:5fa4bcfef39ff21c0fe08df411f299a03afcccc518d7dd7e403b39dcf2a9c202","observation_id":"c7137a49-7384-491a-b4bb-9349bd344071","resolution":{"observed_at":"2026-08-03T17:19:01.640495Z","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":"2026-08-03T17:19:01.857858Z","title":"Enabling val- idation for robust few-shot recognition.arXiv preprint arXiv:2506.04713, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-03T17:19:01.857858Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:10e7fe22ca6a74118ce642075de5f0e0c45baeeb36cfa5eb3789c569e7a0972d","observation_id":"d8773510-abad-45e3-a91a-01c36a33f4b4","resolution":{"observed_at":"2026-08-03T17:19:01.857858Z","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":"2026-08-03T17:19:01.925854Z","title":"Debiased learning from naturally imbalanced pseudo-labels","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-03T17:19:01.925854Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:7cac6fafb5f5b6e18335a54ebf18c94327558f60bc3df243a32440031170c978","observation_id":"114256ee-15ad-4eb1-8125-c3c150c21dea","resolution":{"observed_at":"2026-08-03T17:19:01.925854Z","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":"2026-08-03T17:19:02.115105Z","title":"USB: A unified semi-supervised learning benchmark for classification","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-03T17:19:02.115105Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:1cf3a9247f41b8c18156ed7ae9de615a21acbfeb6715b9e6765e34313e07ddeb","observation_id":"95f88d44-1924-49a7-a859-b61aba964c5e","resolution":{"observed_at":"2026-08-03T17:19:02.115105Z","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":"2026-08-03T17:19:02.249801Z","title":"Freematch: Self-adaptive thresholding for semi-supervised learning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-03T17:19:02.249801Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:149978816f44b785dbdc7067610beb3e4d9e948362fc9c40d6564c91ade1eeb2","observation_id":"25fb76cf-573b-46b1-b4e7-9f2796989ffc","resolution":{"observed_at":"2026-08-03T17:19:02.249801Z","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":"2026-08-03T17:19:02.399632Z","title":"Towards realistic long-tailed semi- supervised learning: Consistency is all you need","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-03T17:19:02.399632Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:cd77113bc26cfdf51f9a04563481f803ba5f87e5783cd1cf6eaa8699d4c107ed","observation_id":"087e82eb-fc46-465c-a564-d962d5e34d03","resolution":{"observed_at":"2026-08-03T17:19:02.399632Z","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":"2026-08-03T17:19:02.576056Z","title":"An embarrassingly simple approach to semi-supervised few-shot learning.Advances in Neural Information Process- ing Systems (NeurIPS), 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-03T17:19:02.576056Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:a1fb6e430a20529eaaf5ed707f5a195989707cf6cc6d1db3bb7736ef504ff911","observation_id":"4cf0b6dd-78fd-4bd6-ae38-da9a72adb854","resolution":{"observed_at":"2026-08-03T17:19:02.576056Z","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":"2026-08-03T17:19:02.681777Z","title":"Robust fine-tuning of zero-shot models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-03T17:19:02.681777Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:c77f66cae4599a475f57cdf0d95a98fa0c24d42bf05e1fb2ddd6e490389cd79c","observation_id":"0eb11fac-60ec-4edd-be45-0095007a89df","resolution":{"observed_at":"2026-08-03T17:19:02.681777Z","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":"2026-08-03T17:19:02.817121Z","title":"Unsupervised feature learning via non-parametric instance discrimination","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-03T17:19:02.817121Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:74e54c9e33fa48b7cdecb95daff1d1841606dbd28766e55b4300049761564ebd","observation_id":"fa663c69-33e3-4d55-936d-181f80099046","resolution":{"observed_at":"2026-08-03T17:19:02.817121Z","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":"2026-08-03T17:19:02.958435Z","title":"Self-training with noisy student improves imagenet clas- sification","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-03T17:19:02.958435Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:6fe376aceaa51d079c61c0795eb5f55aad30532fc4592eb21b959f5c9b52a617","observation_id":"67e7d1de-8245-4066-9514-e8510a4af749","resolution":{"observed_at":"2026-08-03T17:19:02.958435Z","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":"2026-08-03T17:19:03.027898Z","title":"Demysti- fying clip data","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-03T17:19:03.027898Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:412e49a66fad38a197c257485e7257fbeec0a65e67b4fd1f626ce6331745f81a","observation_id":"09d23c76-3583-4545-acd1-d3ad0eeb0750","resolution":{"observed_at":"2026-08-03T17:19:03.027898Z","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":"2026-08-03T17:19:03.202580Z","title":"Dash: Semi-supervised learning with dynamic thresholding","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-03T17:19:03.202580Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:6acdf02b40073743ce55edf372cab7f7adb96fef68f0a7e0be397dc32b2d26c1","observation_id":"3f3502cb-f7ef-4d9f-b6a7-bcb8e64e3794","resolution":{"observed_at":"2026-08-03T17:19:03.202580Z","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":"2026-08-03T17:19:03.304757Z","title":"Unimatch v2: Pushing the limit of semi-supervised semantic segmenta- tion","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-03T17:19:03.304757Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:223ff365380502c60774b61e86028be9d0e2cedb02f097a306bf71806fa53036","observation_id":"bb38ec88-570a-4f25-8b17-f46adbb43243","resolution":{"observed_at":"2026-08-03T17:19:03.304757Z","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":"2026-08-03T17:19:03.432408Z","title":"Task residual for tuning vision-language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-03T17:19:03.432408Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:8c132d337eb6ed03aa252ee043a48ec2d04375e4ceb8a3b9e99235446e369ae0","observation_id":"bd506807-94ac-49c2-8b2e-9a4524639e5c","resolution":{"observed_at":"2026-08-03T17:19:03.432408Z","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":"2026-08-03T17:19:03.504388Z","title":"Task residual for tuning vision-language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-03T17:19:03.504388Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:7ac1f5efeb486c00c5a9f734190598a08a6ea6fcfee56ca684f1f4fd3d7823f8","observation_id":"c80f7676-b777-4bb3-8dbb-b264c8748598","resolution":{"observed_at":"2026-08-03T17:19:03.504388Z","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":"2026-08-03T17:19:03.573376Z","title":"Flexmatch: Boosting semi-supervised learning with curriculum pseudo labeling.Advances in Neural Information Processing Systems (NeurIPS), 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-03T17:19:03.573376Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:4bd2fb151cc2860518f4d917e7d88f111804a63804d0d2a5dc4457b8fd7e871a","observation_id":"85438b39-4bb0-41e5-b869-7ac982fe46d4","resolution":{"observed_at":"2026-08-03T17:19:03.573376Z","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":"2026-08-03T17:19:03.659889Z","title":"En- hancing vision-language few-shot adaptation with negative learning","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-03T17:19:03.659889Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:252b62a5ba1408c5d394719bc6c3cffe361c2b1e79a3b2e6af207027b3433a64","observation_id":"4d4a7296-ce93-45fa-8e67-60f6c656bc3a","resolution":{"observed_at":"2026-08-03T17:19:03.659889Z","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":"2026-08-03T17:19:03.762411Z","title":"Candidate pseudolabel learning: Enhancing vision-language models by prompt tuning with unlabeled data.Forty-first International Conference on Machine Learning (ICML), 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-03T17:19:03.762411Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:067a39b6ef4ac1427ae733282f5ad7a9bae5703d86644bc4e1f303f048ae5697","observation_id":"f81f267a-131a-4631-a700-c2c264498d06","resolution":{"observed_at":"2026-08-03T17:19:03.762411Z","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":"2026-08-03T17:19:03.877945Z","title":"Revisiting semi-supervised learning in the era of foundation models","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-03T17:19:03.877945Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:9a6da896472761e971c7e66dfe662046216e738c1ee5070cf1d46e280ce15bd1","observation_id":"5640e4f8-1330-451d-82dc-0c4e8d7c7218","resolution":{"observed_at":"2026-08-03T17:19:03.877945Z","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":"2026-08-03T17:19:03.953377Z","title":"Revisiting semi-supervised learning in the era of foundation models","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-03T17:19:03.953377Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:a6b92bf7476b280f6a367dcf5ba3f47af3852b025270bd2ae54eb95d849deb9e","observation_id":"50bfb3ca-2c4c-4e65-9f79-2540ccf37c96","resolution":{"observed_at":"2026-08-03T17:19:03.953377Z","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":"2026-08-03T17:19:04.033967Z","title":"Revisiting semi-supervised learning in the era of foun- dation models.Advances in Neural Information Processing Systems (NeurIPS), 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-03T17:19:04.033967Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:90b95236ec4da57e2f0227bd04c1ed3d84ee854fdc82a5073e4b29bb699b7610","observation_id":"12c15386-ed5a-45bf-b05d-7d8f75804758","resolution":{"observed_at":"2026-08-03T17:19:04.033967Z","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":"2026-08-03T17:19:04.111034Z","title":"Tip- adapter: Training-free adaptation of clip for few-shot classifi- cation","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-03T17:19:04.111034Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:f32410a6029274dd73d290846fb4057f92603fef26836786033b346a3218ff32","observation_id":"2fc51c2e-660c-4d7c-a03d-9981d9ba225a","resolution":{"observed_at":"2026-08-03T17:19:04.111034Z","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":"2026-08-03T17:19:04.167673Z","title":"Simmatch: Semi-supervised learning with similarity matching","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-03T17:19:04.167673Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:ef6a7502a899de774cd4ab2eea5dc48cb7e4cefd8c8a31c525c420b1fe1a0469","observation_id":"e4e30573-92e4-4c45-bbf2-13cac5b01150","resolution":{"observed_at":"2026-08-03T17:19:04.167673Z","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":"2026-08-03T17:19:04.250788Z","title":"string- matching","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-03T17:19:04.250788Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:3e019c674f0d3cc08059989480a124ad2e8f2149f6e25b60ac63a06475cce62a","observation_id":"dd28173c-75e7-467e-a569-cb7b9a55fb77","resolution":{"observed_at":"2026-08-03T17:19:04.250788Z","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":"2026-08-03T17:19:04.370762Z","title":"flat softmax probabilities","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-03T17:19:04.370762Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:acaaf25df338258d47188fbacc57a44b2aac287eea04d9b925529038dd439999","observation_id":"d8c5969b-bb85-4b8b-a37b-b09e11f743c4","resolution":{"observed_at":"2026-08-03T17:19:04.370762Z","resolver_source":null,"status":"malformed_identifier"},"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":"2026-08-03T17:19:04.512761Z","title":"Specifically, for both FSL and SSL, we initialize the classifier via linear probing on few-shot data per Tab","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-03T17:19:04.512761Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:ce65853f92f2a3db4e4d631701c21f4b47062a7064b84bf9bc6cc2bb265dce6d","observation_id":"4bb5b2c3-ac84-4ca9-9d5e-a167b352111c","resolution":{"observed_at":"2026-08-03T17:19:04.512761Z","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":"2026-08-03T17:19:04.604580Z","title":"We compare the performance with finetuning DINOv2 directly using few-shot data (FS-FT) following [41]","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective","version":3},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-03T17:19:04.604580Z"},"links":{"citing_paper":"/paper/2512.10244"},"observation_digest":"sha256:0813d4f17f1d9333be9fdfadec34fb45efa7ee016d8eaccb5a49cc884f374eca","observation_id":"64be7eea-7101-4e37-babd-0c6a7ab958c3","resolution":{"observed_at":"2026-08-03T17:19:04.604580Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2512.10244","last_updated":"2026-06-25T05:14:55Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-03T17:18:52.692516Z","submitted_at":"2025-12-11T03:06:16Z","title":"Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective"},"reference_resolution":{"displayed":87,"state_counts":{"malformed_identifier":2,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":85,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":87},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 87 of 87 outbound references and 0 inbound Pith citation observations for arXiv:2512.10244."}