{"as_of":"2026-08-19T03:37:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:cc852a90f39c03929846997644979baf2642a873ed96340135140bfe7cc413c4","coverage":[{"denominator":300,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":100,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T13:09:58.059610Z","state":"measured"},{"denominator":100,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":100,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2507.21205/citation-record","integrity":"/paper/2507.21205/integrity","json":"/paper/2507.21205/citation-record.json","paper":"/paper/2507.21205"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2206.03996","last_updated":"2022-08-14T19:51:07Z","snapshot_observed_at":"2026-08-18T19:51:55.475812Z","submitted_at":"2022-06-08T16:20:11Z","title":"Sharp-MAML: Sharpness-Aware Model-Agnostic Meta Learning","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.03996","snapshot_observed_at":"2026-08-06T13:09:47.893992Z","title":"Sharp-maml: Sharpness- aware model-agnostic meta learning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:47.893992Z"},"links":{"cited_paper":"/paper/2206.03996","citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:7e3765404328147025a445d8b73bc81a732be72c873d79d0faaf89a3ea2ea8a8","observation_id":"2093883e-b6b7-4f58-9208-8e328c5875fd","resolution":{"observed_at":"2026-08-06T13:09:47.893992Z","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":"2026-08-06T13:09:48.041993Z","title":"Labels4free: Unsupervised seg- mentation using stylegan","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:48.041993Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:79a05fd1412653abf74db64c81cc3bc5d77b5ef326ffd5fce92860df421a93e3","observation_id":"91ae9940-756d-40f2-8b6f-7c0b9d0d0a09","resolution":{"observed_at":"2026-08-06T13:09:48.041993Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2005.00928","last_updated":"2020-05-31T16:59:40Z","snapshot_observed_at":"2026-08-14T07:01:16.499526Z","submitted_at":"2020-05-02T21:45:27Z","title":"Quantifying Attention Flow in Transformers","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.00928","snapshot_observed_at":"2026-08-06T13:09:48.198270Z","title":"Quantifying attention flow in transformers","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:48.198270Z"},"links":{"cited_paper":"/paper/2005.00928","citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:8f7fe2350f38cb6069868462c769a9d5cdce64a72b9d969ca6ce3f7901cecd26","observation_id":"83f2a644-b095-4893-a360-d15ca788a86b","resolution":{"observed_at":"2026-08-06T13:09:48.198270Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.11344","last_updated":"2021-06-21T18:21:09Z","snapshot_observed_at":"2026-08-16T18:15:32.538257Z","submitted_at":"2021-06-21T18:21:09Z","title":"f-Domain-Adversarial Learning: Theory and Algorithms","version":1},"cited_work":{"arxiv_id":"2106.11344","doi":null,"metadata_source":"pith","pith_arxiv_id":"2106.11344","snapshot_observed_at":"2026-08-06T13:10:20.086869Z","title":"f-Domain-Adversarial Learning: Theory and Algorithms","venue":"cs.LG","work_id":"505b4413-5a0d-45f2-a197-a012cc93f0ec","year":2021},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:48.325868Z"},"links":{"cited_paper":"/paper/2106.11344","citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:7d222fe3535eaf824a533b08d39a166fc34976255a68296589a8c7c669dc27b6","observation_id":"324dcf90-39ad-4bba-a07b-2987326190b5","resolution":{"observed_at":"2026-08-06T13:10:20.090028Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:09:48.477459Z","title":"Degan: Data-enriching gan for retrieving representative samples from a trained classifier","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:48.477459Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:97dfa69dd16f4baa83dec227fd3eb5d5cd6d349b6705da397b2ad258f3cf4183","observation_id":"60bfece5-dc32-4115-baea-c57b925e1630","resolution":{"observed_at":"2026-08-06T13:09:48.477459Z","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":"2026-08-06T13:09:48.670014Z","title":"One-network adversarial fairness","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:48.670014Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:1bbba9e8668abdf4edc9d9a72401f42fd53707add228d1ebce5477b3d7bced37","observation_id":"ebac7244-3df8-47ad-95d8-df2cd8b57ec2","resolution":{"observed_at":"2026-08-06T13:09:48.670014Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2108.02818","last_updated":"2021-08-05T19:05:57Z","snapshot_observed_at":"2026-08-16T18:04:57.242101Z","submitted_at":"2021-08-05T19:05:57Z","title":"Evaluating CLIP: Towards Characterization of Broader Capabilities and Downstream Implications","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.02818","snapshot_observed_at":"2026-08-06T13:09:48.854564Z","title":"Evaluating clip: towards characterization of broader capabilities and downstream implications","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:48.854564Z"},"links":{"cited_paper":"/paper/2108.02818","citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:c5193869754eabfa5f61f3e965ff32f23f0279293e10b646a3d66734747ad085","observation_id":"4a56f9e5-172e-4ad3-a4da-dcecce4dfbad","resolution":{"observed_at":"2026-08-06T13:09:48.854564Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1902.02366","last_updated":"2019-02-06T19:18:13Z","snapshot_observed_at":"2026-08-17T00:37:01.800092Z","submitted_at":"2019-02-06T19:18:13Z","title":"Negative eigenvalues of the Hessian in deep neural networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.02366","snapshot_observed_at":"2026-08-06T13:09:48.969185Z","title":"Negative eigenvalues of the hessian in deep neural networks","venue":null,"work_id":null,"year":1902},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:48.969185Z"},"links":{"cited_paper":"/paper/1902.02366","citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:70184aa5d20c7d360ff9a299b34de78f6456157bf22afce983a18c88a13eb609","observation_id":"56320421-6c9d-4097-8e90-07ada986f6d3","resolution":{"observed_at":"2026-08-06T13:09:48.969185Z","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":"2026-08-06T13:09:49.073449Z","title":"Hyperstyle: Stylegan inversion with hypernetworks for real image editing","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:49.073449Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:bd19dd6a8f9fdfb2c6131fa17b9f0e960d0c92a91f587a30ecd761fc0f151590","observation_id":"549e0a71-be5d-4c04-842e-adcecfbd4090","resolution":{"observed_at":"2026-08-06T13:09:49.073449Z","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":"2026-08-06T13:09:49.181424Z","title":"The long tail: Why the future of business is selling less of more","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:49.181424Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:5d968086b1a8cf83716dd29ca27834a5052ca95a5f51d795ec9df029358d6671","observation_id":"b60dab1a-708a-445a-bf5b-45f24c34a3f0","resolution":{"observed_at":"2026-08-06T13:09:49.181424Z","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":"2026-08-06T13:09:49.412810Z","title":"Understanding sharpness-aware minimiza- tion, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:49.412810Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:dd119e0889bbd9947ea40fe6867c3cf3b04121ebf948b1ba17005765dd16904e","observation_id":"0372d278-9350-40cc-8314-78af5279625d","resolution":{"observed_at":"2026-08-06T13:09:49.412810Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.16292","last_updated":"2023-10-28T22:02:29Z","snapshot_observed_at":"2026-08-16T15:29:36.720483Z","submitted_at":"2023-05-25T17:46:53Z","title":"Sharpness-Aware Minimization Leads to Low-Rank Features","version":2},"cited_work":{"arxiv_id":"2305.16292","doi":null,"metadata_source":"pith","pith_arxiv_id":"2305.16292","snapshot_observed_at":"2026-08-06T13:10:20.058999Z","title":"Sharpness-Aware Minimization Leads to Low-Rank Features","venue":"cs.LG","work_id":"8f9355c2-949b-4047-9724-30c25fa669b2","year":2023},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:49.558256Z"},"links":{"cited_paper":"/paper/2305.16292","citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:1f50cc1e6f064b796be7ed418bcd7d0d0ae2d0befb830e6c7b99f67d0a99b55a","observation_id":"72041a50-cc3a-4ed0-a4b1-2edcfbb74727","resolution":{"observed_at":"2026-08-06T13:10:20.062483Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1701.07875","last_updated":"2017-12-06T20:01:54Z","snapshot_observed_at":"2026-08-17T13:47:14.071303Z","submitted_at":"2017-01-26T21:10:29Z","title":"Wasserstein GAN","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1701.07875","snapshot_observed_at":"2026-08-06T13:09:49.696374Z","title":"Wasserstein GAN","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:49.696374Z"},"links":{"cited_paper":"/paper/1701.07875","citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:6b2b5bc1075371ebe777986bdd60276393fabf6bc74f4063268cf0d1b7003bd9","observation_id":"12321ec6-d9b9-472e-aa63-c0f851c979b1","resolution":{"observed_at":"2026-08-06T13:09:49.696374Z","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":"2026-08-06T13:09:49.803197Z","title":"Theory of deep learn- ing, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:49.803197Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:e185057649f92f6224e3d48c1ce46d32aeedcf581466c15bf29b75744a68ab23","observation_id":"41eb67d4-96b6-4dfe-8169-8574ecd53d72","resolution":{"observed_at":"2026-08-06T13:09:49.803197Z","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":"2026-08-06T13:09:49.959400Z","title":"Ash, Chicheng Zhang, Akshay Krishnamurthy, John Langford, and Alekh Agarwal","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:49.959400Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:9f0de349f7e69f76043373643f167bfa37d17642e2c6aed1ef09c220b9516d9a","observation_id":"73068e2a-b422-4ce0-9783-e9c2527f8e0b","resolution":{"observed_at":"2026-08-06T13:09:49.959400Z","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":"2026-08-06T13:09:50.097305Z","title":"Schapire","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:50.097305Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:843c7b63865849fd79fb40ac6dd7647b948447f19890a62ec79ac34bdb7b4162","observation_id":"7ab665f7-6e0e-4583-806e-07e05f842692","resolution":{"observed_at":"2026-08-06T13:09:50.097305Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2110.08529","last_updated":"2022-03-15T23:33:33Z","snapshot_observed_at":"2026-08-16T17:48:49.034304Z","submitted_at":"2021-10-16T09:44:06Z","title":"Sharpness-Aware Minimization Improves Language Model Generalization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.08529","snapshot_observed_at":"2026-08-06T13:09:50.207703Z","title":"Sharpness-aware minimization improves language model generalization","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:50.207703Z"},"links":{"cited_paper":"/paper/2110.08529","citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:2bd0413257e2be6fd533212bfb5ad878e6cb3d7bbcff430caa20d1e687cedd97","observation_id":"e0adc907-7896-4e8a-b148-0e44487840c8","resolution":{"observed_at":"2026-08-06T13:09:50.207703Z","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":"2026-08-06T13:09:50.349920Z","title":"Can we gain more from orthogonality regularizations in training deep networks? Advances in Neural Information Processing Systems (NeurIPS), 31, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:50.349920Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:80987d5bc320a390eece307c98091ef01be13d0f7488964b64a4962dd4d16d50","observation_id":"7168f0de-4ac3-4c29-a79a-d9f901907659","resolution":{"observed_at":"2026-08-06T13:09:50.349920Z","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":"2026-08-06T13:09:50.463242Z","title":"VICReg: Variance-invariance-covariance regu- larization for self-supervised learning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:50.463242Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:becd95c44893f14d06d205fb1fcd860eefcf86c2140ef2993b84acb907c8b481","observation_id":"b53588ac-0ce9-4b14-81d8-f936e52ccf04","resolution":{"observed_at":"2026-08-06T13:09:50.463242Z","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":"2026-08-06T13:09:50.587065Z","title":"A theory of learning from different domains","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:50.587065Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:44106b6ca6df0e6c0a318f2af9e53b0be7ffff4a19ee91f8cb7ca462ee6d158f","observation_id":"fb979f6b-bf15-4415-8e31-175a6a05cf59","resolution":{"observed_at":"2026-08-06T13:09:50.587065Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1911.09785","last_updated":"2020-02-13T23:14:46Z","snapshot_observed_at":"2026-08-12T10:52:49.073310Z","submitted_at":"2019-11-21T23:44:25Z","title":"ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1911.09785","snapshot_observed_at":"2026-08-06T13:09:50.675277Z","title":"Cubuk, Alex Kurakin, Kihyuk Sohn, Han Zhang, and Colin Raffel","venue":null,"work_id":null,"year":1911},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:50.675277Z"},"links":{"cited_paper":"/paper/1911.09785","citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:6756873c356e96ea864d7ec127d8cf003cefe489e93c5b1cba726366641a8cce","observation_id":"912151fd-b943-414e-baf4-04027bef0f54","resolution":{"observed_at":"2026-08-06T13:09:50.675277Z","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":"2026-08-06T13:09:50.774794Z","title":"Mixmatch: A holistic approach to semi-supervised learning","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:50.774794Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:a700071364cc5eb5c756d29a3ffa0361ccfdfd9405b40792ca3a785db7cb9c78","observation_id":"04c4b5fb-02d3-4153-9e5c-f34bc9594224","resolution":{"observed_at":"2026-08-06T13:09:50.774794Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.04732","last_updated":"2022-03-15T16:42:38Z","snapshot_observed_at":"2026-08-16T18:18:34.836742Z","submitted_at":"2021-06-08T23:39:12Z","title":"AdaMatch: A Unified Approach to Semi-Supervised Learning and Domain Adaptation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.04732","snapshot_observed_at":"2026-08-06T13:09:50.902108Z","title":"Adamatch: A unified approach to semi-supervised learning and domain adaptation","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:50.902108Z"},"links":{"cited_paper":"/paper/2106.04732","citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:8c5a15224cae629465100236a3c394ff99eb6b523eb0a3e61b216d068b5a25df","observation_id":"ac615e13-0d64-4481-bc21-69c872287a99","resolution":{"observed_at":"2026-08-06T13:09:50.902108Z","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":"stable/2504788","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:10:20.015446Z","title":"Bhattacharyya","venue":null,"work_id":"bd6f1ee9-d6ab-4403-8c2e-bf8657494d21","year":1933},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:51.018099Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:5e21bce4f3b01a55fb3a56d3c3bb90e8584f660ec3cb87d083139e9c39c632cc","observation_id":"ec23d118-67d9-4a43-8308-a7143181455a","resolution":{"observed_at":"2026-08-06T13:10:20.020301Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:09:51.131415Z","title":"Stylegan knows normal, depth, albedo, and more","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:51.131415Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:ca66c68dbbe6e0a50cafec8ece34330b58c32c4aa88a2ee1035fb7ced88592e2","observation_id":"21a79773-63ba-4e67-9c06-bebda8b20f96","resolution":{"observed_at":"2026-08-06T13:09:51.131415Z","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":"2026-08-06T13:09:51.243095Z","title":"Experiment tracking with weights and biases, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:51.243095Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:a63cd83f496e4daeed1daffbfbc162ca1cfccb9b8629bc433ec557ce055af143","observation_id":"f468e7a6-6694-4cb8-9956-a7a92957fcb9","resolution":{"observed_at":"2026-08-06T13:09:51.243095Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.08025","last_updated":"2022-02-04T14:02:34Z","snapshot_observed_at":"2026-08-16T17:27:09.695774Z","submitted_at":"2022-01-20T07:13:04Z","title":"Low-Pass Filtering SGD for Recovering Flat Optima in the Deep Learning Optimization Landscape","version":2},"cited_work":{"arxiv_id":"2201.08025","doi":null,"metadata_source":"pith","pith_arxiv_id":"2201.08025","snapshot_observed_at":"2026-08-06T13:10:19.952037Z","title":"Low-Pass Filtering SGD for Recovering Flat Optima in the Deep Learning Optimization Landscape","venue":"cs.LG","work_id":"98e7330c-5337-46db-b9a3-8fc18dc09d1d","year":2022},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:51.331976Z"},"links":{"cited_paper":"/paper/2201.08025","citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:c418ff1638eecbd001b8fb575e01f6aeaa0f470fa10efc784cd9439f70eaa19d","observation_id":"96ad4a2a-b517-4b7e-9a6c-a1c0797aa025","resolution":{"observed_at":"2026-08-06T13:10:19.955171Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:09:51.440403Z","title":"An isoperimetric inequality on the discrete cube, and an elementary proof of the isoperimetric inequality in gauss space","venue":null,"work_id":null,"year":1997},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:51.440403Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:726c673a9ada46d5ad2d8282f95f5daba1d74cb9dd2cb693c4d3c5bce0229819","observation_id":"4a72245e-d5f4-4c1d-91fb-8acd1b576b73","resolution":{"observed_at":"2026-08-06T13:09:51.440403Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2202.00046","last_updated":"2022-10-06T15:02:35Z","snapshot_observed_at":"2026-08-16T17:24:35.165560Z","submitted_at":"2022-01-31T19:14:03Z","title":"Finding Directions in GAN's Latent Space for Neural Face Reenactment","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.00046","snapshot_observed_at":"2026-08-06T13:09:51.574479Z","title":"Finding directions in gan’s latent space for neural face reenactment","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:51.574479Z"},"links":{"cited_paper":"/paper/2202.00046","citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:6217f41fa56244bbf70b9c014647ac15945be0a4ae43578d400d877e39798466","observation_id":"0f9969f6-87f1-46a3-9842-1a81c5be8056","resolution":{"observed_at":"2026-08-06T13:09:51.574479Z","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":"2026-08-06T13:09:51.662756Z","title":"Large scale GAN training for high fidelity natural image synthesis","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:51.662756Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:c0e876f236a0a8a40ba9d2b40627acbf261b9b6ee2ca813b401fcb30049b72d3","observation_id":"7e73f1cd-46e9-4db5-9d2d-9df39e4b1317","resolution":{"observed_at":"2026-08-06T13:09:51.662756Z","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":"2026-08-06T13:09:51.777638Z","title":"A systematic study of the class im- balance problem in convolutional neural networks","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:51.777638Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:c70488e1a6cb6c8af60f3d47ac0750ab5f63cb4f952dbd66d6a26385043e3289","observation_id":"6b2244c9-664d-43fc-96c3-fb5657e77c96","resolution":{"observed_at":"2026-08-06T13:09:51.777638Z","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":"2026-08-06T13:09:51.954379Z","title":"What is the effect of importance weighting in deep learning? In International Conference on Machine Learning (ICML) , pages 872–881","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:51.954379Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:0fb389bc19d975dc9aeeffd927a174dc4c1b3cc6586cb944b5d1d412b41d93d0","observation_id":"874e194c-295e-49eb-a9ea-5d721fe201ff","resolution":{"observed_at":"2026-08-06T13:09:51.954379Z","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":"2026-08-06T13:09:52.077139Z","title":"Ace: Ally complementary experts for solving long-tailed recognition in one-shot","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:52.077139Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:1f76210732e2709799972b2c233bb2292dda44f53ec9322765679ffa2572bc03","observation_id":"3020f37c-6901-40c8-8ca9-e4e7303fb8db","resolution":{"observed_at":"2026-08-06T13:09:52.077139Z","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":"2026-08-06T13:09:52.190467Z","title":"Learning imbalanced datasets with label-distribution-aware margin loss","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:52.190467Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:fdda735779c4b0d85fb77f68a0a3a41ddfaa1263ab14be85413a7b7a8ccc8180","observation_id":"fa405c96-bc28-4f95-8840-5fb13ef3c3c2","resolution":{"observed_at":"2026-08-06T13:09:52.190467Z","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":"2026-08-06T13:09:52.297125Z","title":"End-to-end object detection with transformers","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:52.297125Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:acdbaa7a1f74e7c070bf39d387c977ece75156637d1efba5261483f70c9e51ff","observation_id":"e15c6716-6798-4847-a9ba-0c238a1f8565","resolution":{"observed_at":"2026-08-06T13:09:52.297125Z","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":"2026-08-06T13:09:52.439011Z","title":"Lower bounds for finding stationary points I","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:52.439011Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:00c4efde985719427fd492f87e3543f1c750ed8288381a2fb100f7c3ff584921","observation_id":"ffd4b1c4-3a83-498c-aed7-74f01a097185","resolution":{"observed_at":"2026-08-06T13:09:52.439011Z","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":"2026-08-06T13:09:52.604917Z","title":"Unsupervised learning of visual features by contrasting cluster assignments","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:52.604917Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:d5108589ddadf6d76bc34f4064e3881415a5c8927e25ae3f23b9dcd0bdfc097c","observation_id":"64dcb842-ae08-4484-ac94-37e127a13d81","resolution":{"observed_at":"2026-08-06T13:09:52.604917Z","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":"2026-08-06T13:09:52.754986Z","title":"Emerging properties in self-supervised vision transformers","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:52.754986Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:05189802b78797fba4cf07f178ac28e9085472326c8e923f4e8510f1f21779ec","observation_id":"e2397496-830c-434e-9617-d2be668f9dec","resolution":{"observed_at":"2026-08-06T13:09:52.754986Z","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":"2026-08-06T13:09:52.868757Z","title":"Instance-conditioned gan","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:52.868757Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:d5761b2476a0c1dab2eaab2e7f82ba75b775fee2b277be0a1ee73de3348bcf69","observation_id":"85ab8c05-8df3-4245-8535-1fcb09592cf3","resolution":{"observed_at":"2026-08-06T13:09:52.868757Z","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":"2026-08-06T13:09:53.007902Z","title":"Is facial recognition too biased to be let loose? Nature, 587(7834):347–350,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:53.007902Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:3a0546ec3ceaedc8de7a4e62d98d792100d92c05d0b94dfed62e7fc1a2c48f16","observation_id":"2bdaf0ca-93fd-4ffe-926c-4a0ca830e65b","resolution":{"observed_at":"2026-08-06T13:09:53.007902Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2102.08604","last_updated":"2021-11-03T08:33:52Z","snapshot_observed_at":"2026-08-16T18:45:01.046533Z","submitted_at":"2021-02-17T06:42:09Z","title":"SWAD: Domain Generalization by Seeking Flat Minima","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2102.08604","snapshot_observed_at":"2026-08-06T13:09:53.141074Z","title":"Swad: Domain generalization by seeking flat minima","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:53.141074Z"},"links":{"cited_paper":"/paper/2102.08604","citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:04f970ea2ce02b398a99ba80f3f10b779fac13ba938dc3d72cedec69384ec6f5","observation_id":"bbdfe252-d6d4-44fa-8ae6-82cd7b0921c1","resolution":{"observed_at":"2026-08-06T13:09:53.141074Z","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":"2026-08-06T13:09:53.232894Z","title":"Adaptive batch mode active learning","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:53.232894Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:01d56c1913e1d7c92d266fd5ee61fccc55371b44928e38731cd654ada184ca48","observation_id":"836da3ce-8fde-40bb-8485-2ac0c65b512c","resolution":{"observed_at":"2026-08-06T13:09:53.232894Z","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":"2026-08-06T13:09:53.432674Z","title":"Semi-supervised learning (chapelle, o","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:53.432674Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:06d3eb5d229a5d43c9d82d681e55680e08952216a361f1eb735bc91ba5af07b8","observation_id":"1074e7ee-ab4f-421e-9c12-4904061c8374","resolution":{"observed_at":"2026-08-06T13:09:53.432674Z","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":"2026-08-06T13:09:53.553064Z","title":"Joint transfer and batch-mode active learning","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:53.553064Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:67552ac593b0096719516407cb4c6cb32ec57d00637d57b4470e2ea75875567e","observation_id":"d12d7bd6-b9dd-47d2-9d9c-578e841026b8","resolution":{"observed_at":"2026-08-06T13:09:53.553064Z","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":"2026-08-06T13:09:53.611699Z","title":"Entropy-sgd: Biasing gradient descent into wide valleys","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:53.611699Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:cfa36dcd3ca38a32e70961a9b5b4a1158718c535a0b77f0ba94ee8046faf6ff2","observation_id":"eaa0140d-4b7f-4fce-825b-9753b51c6913","resolution":{"observed_at":"2026-08-06T13:09:53.611699Z","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":"2026-08-06T13:09:53.683681Z","title":"Smote: synthetic minority over-sampling technique","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:53.683681Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:fbecc6526dee35d661f344a0c6a6d6c458237417b7156b069e2a15ef5d071468","observation_id":"a009699c-8e09-42f1-9b06-03e4fee4ac40","resolution":{"observed_at":"2026-08-06T13:09:53.683681Z","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":"2026-08-06T13:09:53.739882Z","title":"Transmix: Attend to mix for vision transformers","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:53.739882Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:3a315d6785b503cd4d3015b6919dde079b01035701b9b3568bdcb23f70996915","observation_id":"a4c60c67-a902-4ec7-9283-be9d36350c97","resolution":{"observed_at":"2026-08-06T13:09:53.739882Z","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":"2026-08-06T13:09:53.875964Z","title":"Reltrans- former: A transformer-based long-tail visual relationship recognition","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:53.875964Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:64d5b4830fd6340cd097d2a075983e239b2ce2134a4649e1c93a5b8c3e9e9f55","observation_id":"f77bd812-da0a-4596-9e5f-e2f4ca501bbe","resolution":{"observed_at":"2026-08-06T13:09:53.875964Z","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":"2026-08-06T13:09:53.976122Z","title":"Adversarial-learned loss for domain adaptation","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:53.976122Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:5583d6fe7c9e698cf3ea842ef042a0f5e4a7cf955ec4554ecc35a412267dd249","observation_id":"84341384-9a5d-4ffd-bc31-aad232e86207","resolution":{"observed_at":"2026-08-06T13:09:53.976122Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2001.01046","last_updated":"2020-01-04T06:24:44Z","snapshot_observed_at":"2026-08-07T17:06:29.623044Z","submitted_at":"2020-01-04T06:24:44Z","title":"Adversarial-Learned Loss for Domain Adaptation","version":1},"cited_work":{"arxiv_id":"2001.01046","doi":null,"metadata_source":"pith","pith_arxiv_id":"2001.01046","snapshot_observed_at":"2026-08-06T13:10:19.923555Z","title":"Adversarial-Learned Loss for Domain Adaptation","venue":"cs.CV","work_id":"7aa25378-8fe8-450a-9c85-a721e9b1bbf2","year":2020},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:54.053516Z"},"links":{"cited_paper":"/paper/2001.01046","citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:a54729efcf9ad47d03ca243b634cf3dcd1556b04ff60a04136a63bde36b889f9","observation_id":"51e9841e-0e90-4d10-a5ad-18b5b1574b28","resolution":{"observed_at":"2026-08-06T13:10:19.926455Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2002.05709","last_updated":"2020-07-01T00:09:08Z","snapshot_observed_at":"2026-08-15T20:49:51.676387Z","submitted_at":"2020-02-13T18:50:45Z","title":"A Simple Framework for Contrastive Learning of Visual Representations","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.05709","snapshot_observed_at":"2026-08-06T13:09:54.151249Z","title":"A simple framework for contrastive learning of visual representations","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:54.151249Z"},"links":{"cited_paper":"/paper/2002.05709","citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:6759e96f508d3c10487a41b62b0cbc25ba2bc68f1f6a86098fddaf6a69b6c69d","observation_id":"a7976bab-e5a1-4ef0-b707-834b0b8a41fe","resolution":{"observed_at":"2026-08-06T13:09:54.151249Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.01548","last_updated":"2022-03-13T18:58:43Z","snapshot_observed_at":"2026-08-17T00:40:52.565251Z","submitted_at":"2021-06-03T02:08:03Z","title":"When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.01548","snapshot_observed_at":"2026-08-06T13:09:54.209778Z","title":"When vision transformers outperform resnets without pretraining or strong data augmentations","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:54.209778Z"},"links":{"cited_paper":"/paper/2106.01548","citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:5fed0a30939fec7cfd014d167042fa58e96a8d23a78e01034670922b6d6b4c15","observation_id":"8f4c89bb-98de-41ad-b10d-a61cb51e2ee9","resolution":{"observed_at":"2026-08-06T13:09:54.209778Z","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":"2026-08-06T13:09:54.282492Z","title":"Domain adaptive faster r-cnn for object detection in the wild","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:54.282492Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:5dc8210b9597ca93b5c42f34058b60aa9b34621ebf04955c4d61bb9c4cb995d9","observation_id":"b5f24b88-73fd-4912-86f5-8844e1d46237","resolution":{"observed_at":"2026-08-06T13:09:54.282492Z","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":"2026-08-06T13:09:54.343802Z","title":"New exponential bounds and approx- imations for the computation of error probability in fading channels","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:54.343802Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:85b5bfd9aabe856da400928196f8d41d309fcfd3b50a1ef30f09ba2b33769c21","observation_id":"566a2e97-cb62-4421-8746-273e9066bd83","resolution":{"observed_at":"2026-08-06T13:09:54.343802Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2002.04185","last_updated":"2020-02-11T03:08:28Z","snapshot_observed_at":"2026-08-12T11:54:06.893027Z","submitted_at":"2020-02-11T03:08:28Z","title":"Smoothness and Stability in GANs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.04185","snapshot_observed_at":"2026-08-06T13:09:54.402409Z","title":"Smoothness and stability in gans","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:54.402409Z"},"links":{"cited_paper":"/paper/2002.04185","citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:9b164801311eefe24dc538618a52e67bec3bfe4e201b156ce1ba9fd82404953d","observation_id":"cd13e989-8715-46f0-8e02-15c3445e1a68","resolution":{"observed_at":"2026-08-06T13:09:54.402409Z","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":"2026-08-06T13:09:54.471825Z","title":"Improving generalization with active learning","venue":null,"work_id":null,"year":1994},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:54.471825Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:281ace0c981db58868ded12d6cf94800cf82b732b62e2996673e7b820f0ad939","observation_id":"a22c8819-52c6-411e-9bf9-4a5ae8fc71aa","resolution":{"observed_at":"2026-08-06T13:09:54.471825Z","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":"2026-08-06T13:09:54.558353Z","title":"Facility location problem — Wikipedia, the free encyclopedia,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:54.558353Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:02b03c11afe7801a0988e6ffa33670d378f56faec008eb742002effc4fcddd83","observation_id":"3b83e100-fd9a-4553-87d9-8bfe7dadf81b","resolution":{"observed_at":"2026-08-06T13:09:54.558353Z","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":"2026-08-06T13:09:54.709016Z","title":"The cityscapes dataset for seman- tic urban scene understanding","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:54.709016Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:652ee66dd57f4c086dee249dbb2e849b155af2f58e05457b5b4605062fd528c1","observation_id":"26a18234-3bbb-47e4-869a-c9cd0a5e3698","resolution":{"observed_at":"2026-08-06T13:09:54.709016Z","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":"2026-08-06T13:09:54.777636Z","title":"Training well-generalizing classifiers for fairness metrics and other data-dependent constraints","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:54.777636Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:dcf79cb763aa1720de07f0c078845235aed4f209acf7dd3cf3b916ae4427e324","observation_id":"7395397b-7f3a-46ad-8dc3-d143ff81387d","resolution":{"observed_at":"2026-08-06T13:09:54.777636Z","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":"2026-08-06T13:09:54.872561Z","title":"Optimization with non-differentiable constraints with applications to fairness, recall, churn, and other goals","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:54.872561Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:48a5bbac80c19ef6e0d8c3501c35f2ef0e5ef14c440cff8537b5d5513428e122","observation_id":"5a25989b-87c7-44e5-bb22-410b026cc4ba","resolution":{"observed_at":"2026-08-06T13:09:54.872561Z","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":"2026-08-06T13:09:54.960214Z","title":"Parametric contrastive learning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:54.960214Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:ea507c8b4fe3d0ea0edf56708d6dab8947a58a711c88e5a762c01d1de7044d8d","observation_id":"09a218e6-3d79-4767-a5fc-7dcb2194e3be","resolution":{"observed_at":"2026-08-06T13:09:54.960214Z","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":"2026-08-06T13:09:55.053430Z","title":"Gradually vanishing bridge for adversarial domain adaptation","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:55.053430Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:baa8cd1aa006e52ee888c1c855f778db0353db7b159376cfd9d76c7c8b56e9ff","observation_id":"5d2499ac-7c87-4707-8289-bb708a4dfb2d","resolution":{"observed_at":"2026-08-06T13:09:55.053430Z","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":"2026-08-06T13:09:55.149064Z","title":"Class-balanced loss based on effective number of samples","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:55.149064Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:bd070e63fedcf89060dd904a9adba71df5fa5db0aa1a18a4180a04fdc011498a","observation_id":"1a96a054-ba11-4015-8a50-7f546848a78b","resolution":{"observed_at":"2026-08-06T13:09:55.149064Z","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":"2026-08-06T13:09:55.240933Z","title":"Class-balanced loss based on effective number of samples","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:55.240933Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:59f9b7e09289761f51fc08e9975d538a0f9924fb8e9a8e2d24a56aab72acdce3","observation_id":"540a81a5-b453-4b95-bc73-eaec689f4147","resolution":{"observed_at":"2026-08-06T13:09:55.240933Z","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":"2026-08-06T13:09:55.344903Z","title":"Escaping saddles with stochastic gradients","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:55.344903Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:6db6defdd38214d5d6de563740400e41c3079f0a3b8631fe43a4a7f9d18ed5b7","observation_id":"7f548b20-87de-4191-a4db-8e06bc72a6fa","resolution":{"observed_at":"2026-08-06T13:09:55.344903Z","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":"2026-08-06T13:09:55.445553Z","title":"Identifying and attacking the saddle point problem in high-dimensional non- convex optimization","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:55.445553Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:faf0d833adeb74d26e7d2f347df60e7950aff28713367d96f165fca97e646c30","observation_id":"448b2afb-9255-4325-a064-875e9621c673","resolution":{"observed_at":"2026-08-06T13:09:55.445553Z","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":"2026-08-06T13:09:55.535337Z","title":"Modulating early visual processing by language","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:55.535337Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:dbc7df566189b51ecb690f79a8be200d4f5a15583be774e1406b1dd939cf67a6","observation_id":"98ca8fbe-1edd-4a56-976c-a2fe0ac962cb","resolution":{"observed_at":"2026-08-06T13:09:55.535337Z","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":"2026-08-06T13:09:55.632027Z","title":null,"venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:55.632027Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:9b243192fdd3abb61a70c292657488d54738c112d09b16de3d0dad6328bc239b","observation_id":"b45ad431-38f0-467c-b242-e48ced13025a","resolution":{"observed_at":"2026-08-06T13:09:55.632027Z","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":"2026-08-06T13:09:55.738334Z","title":"Imagenet: A large-scale hierarchical image database","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:55.738334Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:a342e175a5796032d31fdc7c641fbda50f874fe9a59bf7bd7416a9280f94f77e","observation_id":"916ae0a1-b7c9-4803-9065-83b061caaa92","resolution":{"observed_at":"2026-08-06T13:09:55.738334Z","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":"2026-08-06T13:09:55.811826Z","title":"Cluster alignment with a teacher for unsupervised domain adaptation","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:55.811826Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:a40358571330fef5bd5a440e94e736d1d01d2b57310ed01e1fbf5f39926df256","observation_id":"7b6bdb31-0fef-49b7-990c-dc1b56fac14f","resolution":{"observed_at":"2026-08-06T13:09:55.811826Z","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":"2026-08-06T13:09:55.871539Z","title":"Discriminative unsupervised feature learning with exemplar convolutional neural networks","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:55.871539Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:79485cbe7474a63e062a722f61b332811f79c68c4c86e0256cb84d27a0975455","observation_id":"c9e73f0d-846a-4f17-b88f-7d23bfe67bba","resolution":{"observed_at":"2026-08-06T13:09:55.871539Z","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":"2026-08-06T13:09:55.972028Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:55.972028Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:24c569d2c307b8382e91aca9a2390dff3d241280fffbfd8619e11871489619df","observation_id":"d3fc8a4b-230a-472d-812b-1492293f7a2e","resolution":{"observed_at":"2026-08-06T13:09:55.972028Z","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":"2026-08-06T13:09:56.051379Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:56.051379Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:b7506898475780324e7f2e0fe55145c079571cd40ee2c31941d847302aef1b16","observation_id":"02ac5654-5fe5-4388-9ad4-40281b16d286","resolution":{"observed_at":"2026-08-06T13:09:56.051379Z","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":"2026-08-06T13:09:56.136573Z","title":"Global and local mixture consistency cumulative learning for long-tailed visual recognitions","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:56.136573Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:47070de0dc3ee829398e108bf2c4068929be4c6b8a68685dc8cd9d89dc631e17","observation_id":"4d1340ed-802e-4b06-a77e-383b0945dfa6","resolution":{"observed_at":"2026-08-06T13:09:56.136573Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1802.09841","last_updated":"2018-02-27T12:02:33Z","snapshot_observed_at":"2026-08-18T23:45:16.889564Z","submitted_at":"2018-02-27T12:02:33Z","title":"Adversarial Active Learning for Deep Networks: a Margin Based Approach","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1802.09841","snapshot_observed_at":"2026-08-06T13:09:56.240883Z","title":"Adversarial active learning for deep networks: a margin based approach","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:56.240883Z"},"links":{"cited_paper":"/paper/1802.09841","citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:563e77a9614b0c9356b80146db479aff14131b5bdcaabd440c2e01a6443d863d","observation_id":"8d3a90c5-a537-43fd-844f-4455a90e2f9a","resolution":{"observed_at":"2026-08-06T13:09:56.240883Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1703.11008","last_updated":"2017-10-19T03:39:56Z","snapshot_observed_at":"2026-08-14T21:08:53.042410Z","submitted_at":"2017-03-31T17:56:41Z","title":"Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1703.11008","snapshot_observed_at":"2026-08-06T13:09:56.316540Z","title":"Computing nonvacuous generalization bounds for deep (stochastic) neural networks with many more parameters than training data","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:56.316540Z"},"links":{"cited_paper":"/paper/1703.11008","citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:d4ae35b1ceb486a45c455b624dc36c3070c5ee3bb7772f88cc59991bd19c0dd6","observation_id":"729f58a2-32d5-4519-b212-7d4c7d1e9304","resolution":{"observed_at":"2026-08-06T13:09:56.316540Z","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":"2026-08-06T13:09:56.376714Z","title":"Scalable learning of non-decomposable objectives","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:56.376714Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:dd7d6b368ccb7a97758b16fd85f10d7bc4dea74b8dd4efc9ebc5c0f652badcd4","observation_id":"8f68b364-d42c-4218-80d4-dd7a885b58bf","resolution":{"observed_at":"2026-08-06T13:09:56.376714Z","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":"2026-08-06T13:09:56.450772Z","title":"The pascal visual object classes (voc) challenge","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:56.450772Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:ed935a84a37013c352f2137eb77d32a68e7bb23a25d48ebac04d02648ed044a1","observation_id":"af0b56ad-2138-4ef7-8b99-a9983446d02d","resolution":{"observed_at":"2026-08-06T13:09:56.450772Z","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":"2026-08-06T13:09:56.532696Z","title":"Cossl: Co-learning of representation and classifier for imbalanced semi-supervised learning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:56.532696Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:298cc67bb45c8172166c2715775b8d6aba3ff21d74d51e2cf3ab48923f87f1b0","observation_id":"9626932b-a948-48de-9169-92891c335d06","resolution":{"observed_at":"2026-08-06T13:09:56.532696Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.01412","last_updated":"2021-04-29T16:44:25Z","snapshot_observed_at":"2026-08-15T12:34:14.131778Z","submitted_at":"2020-10-03T19:02:10Z","title":"Sharpness-Aware Minimization for Efficiently Improving Generalization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.01412","snapshot_observed_at":"2026-08-06T13:09:56.610787Z","title":"Sharpness-aware mini- mization for efficiently improving generalization","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:56.610787Z"},"links":{"cited_paper":"/paper/2010.01412","citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:3d03b386cee621b005f052d83430db03096e0df78f5ef1b67abddfcf0465eea8","observation_id":"d126fc55-cc53-4745-831c-4916cdb2054f","resolution":{"observed_at":"2026-08-06T13:09:56.610787Z","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":"2026-08-06T13:09:56.683356Z","title":"Sharpness-aware mini- mization for efficiently improving generalization","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:56.683356Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:d65a8fb664f216c50e6442c73d5eecbd75fa067a602429f16d3d7d9b8a42c113","observation_id":"57a7dfb8-c138-4bd9-97ab-9020a31dafe7","resolution":{"observed_at":"2026-08-06T13:09:56.683356Z","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":"2026-08-06T13:09:56.784479Z","title":"A decision-theoretic generalization of on-line learning and an application to boosting","venue":null,"work_id":null,"year":1997},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:56.784479Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:86fdcfff048cfcfb28ae251be035072f8e0b617a5391a5e50595ba26bccbe881","observation_id":"9d51102f-2cfc-43e8-bbd2-a48df9f743e5","resolution":{"observed_at":"2026-08-06T13:09:56.784479Z","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":"2026-08-06T13:09:56.844597Z","title":"Unsupervised domain adaptation by backpropagation","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:56.844597Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:10cd902e766ba72dedbe21cfabe89f7712e92a13b61d457eb4b41fa6ef95e4e5","observation_id":"ffb7de7c-e935-4506-85fc-48bafff8f705","resolution":{"observed_at":"2026-08-06T13:09:56.844597Z","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":"2026-08-06T13:09:56.936874Z","title":"Domain-adversarial training of neural net- works","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:56.936874Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:148c819624d46ef7ffe7d46a02e37513ccaabf02c366206b957ee6291254b079","observation_id":"5ed8243a-3764-40c9-8893-c148b54affe9","resolution":{"observed_at":"2026-08-06T13:09:56.936874Z","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":"2026-08-06T13:09:56.991771Z","title":"Escaping from saddle points—online stochas- tic gradient for tensor decomposition","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:56.991771Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:eec38c33467cf4b503ac71e3ae3a299812183bcc13612016281091e13540ceab","observation_id":"37964a59-3311-4f98-8f6d-1392e4c97d3e","resolution":{"observed_at":"2026-08-06T13:09:56.991771Z","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":"2026-08-06T13:09:57.041295Z","title":"An investigation into neural net optimiza- tion via hessian eigenvalue density","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:57.041295Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:f04818bb7abde2d10238d50f190b64d190676a6555a5bc9de0cbb0aa108b39a2","observation_id":"727c1e80-d436-418f-9c97-f0acc86cde15","resolution":{"observed_at":"2026-08-06T13:09:57.041295Z","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":"2026-08-06T13:09:57.100569Z","title":"An investigation into neural net op- timization via hessian eigenvalue density","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:57.100569Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:3dc0bb1cc1c46f8e01102cf6c69a2519523af4a9a6715d7577acaae5be4e2dc0","observation_id":"3e3a6376-1d32-43d5-9529-58bf52a50832","resolution":{"observed_at":"2026-08-06T13:09:57.100569Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2110.04369","last_updated":"2021-10-08T20:25:48Z","snapshot_observed_at":"2026-08-16T17:50:44.923851Z","submitted_at":"2021-10-08T20:25:48Z","title":"A Loss Curvature Perspective on Training Instability in Deep Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.04369","snapshot_observed_at":"2026-08-06T13:09:57.185189Z","title":"A loss curvature perspective on training instability in deep learning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:57.185189Z"},"links":{"cited_paper":"/paper/2110.04369","citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:11192eafea5295353f97d4546f8fdd5f459bd2550104464110a5c01d1edfbc2a","observation_id":"b3299cb5-a237-47ce-a2f4-dd24f5142834","resolution":{"observed_at":"2026-08-06T13:09:57.185189Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.05665","last_updated":"2023-05-31T04:57:12Z","snapshot_observed_at":"2026-08-18T09:52:42.083004Z","submitted_at":"2023-05-09T17:59:07Z","title":"ImageBind: One Embedding Space To Bind Them All","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.05665","snapshot_observed_at":"2026-08-06T13:09:57.253731Z","title":"Imagebind: One embedding space to bind them all","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:57.253731Z"},"links":{"cited_paper":"/paper/2305.05665","citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:a8ad679ef06a374dda4256a2bf4fca1fd4d96f8f3f4197e0f4e1a57da94dd06c","observation_id":"8420d55f-4461-4204-8bee-fa62af796319","resolution":{"observed_at":"2026-08-06T13:09:57.253731Z","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":"2026-08-06T13:09:57.306849Z","title":"Satisfying real-world goals with dataset constraints","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:57.306849Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:6bf2d9b6f748f4681d464368522dad18e5f56e7bd392b78cb64616bdea54d0ac","observation_id":"d53b4a1b-6cdb-47af-8961-5e82f78f9238","resolution":{"observed_at":"2026-08-06T13:09:57.306849Z","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":"2026-08-06T13:09:57.386426Z","title":"Goluba and Henk A","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:57.386426Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:b9ae2d1dfd26b18c6693b4fcec3061a82fab5b8f257ce5496bd5fc71e1c631e1","observation_id":"f560e0b9-a765-4daa-be16-41283b66ecd8","resolution":{"observed_at":"2026-08-06T13:09:57.386426Z","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":"2026-08-06T13:09:57.470534Z","title":"Generative adversarial nets","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:57.470534Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:4d4c8fd92f9afce6f85158d7a0944372c5b9fa69e152e8d2e2dbf836fbabed7a","observation_id":"fa50f320-e6eb-4236-9d01-9d96a036bc5a","resolution":{"observed_at":"2026-08-06T13:09:57.470534Z","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":"2026-08-06T13:09:57.546327Z","title":"Generative adversarial networks","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:57.546327Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:5378a2a401a3dbb501ca10127b895f7951b69d99ec6394343f7c8ef28a63e7f6","observation_id":"d84aa863-eb96-4f6c-90fd-e906331bf4c2","resolution":{"observed_at":"2026-08-06T13:09:57.546327Z","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":"2026-08-06T13:09:57.609266Z","title":"Bootstrap your own latent-a new approach to self-supervised learning","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":94,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:57.609266Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:41402dbee281f36ccf4d92c3be8411e097c7956f3f19febc93e5bcea4d3c9051","observation_id":"aeb818e8-25d2-4356-b13c-b25b2451779a","resolution":{"observed_at":"2026-08-06T13:09:57.609266Z","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":"2026-08-06T13:09:57.707472Z","title":"Weighted entropy","venue":null,"work_id":null,"year":1971},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":95,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:57.707472Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:198ea75343f32476f5b8305b908dbbbc29a562e95fdb67801d4debbbf4e00aa5","observation_id":"63fcb08b-9dd4-4577-b546-0fbf66f59f27","resolution":{"observed_at":"2026-08-06T13:09:57.707472Z","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":"2026-08-06T13:09:57.809084Z","title":"Improved training of wasserstein gans","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":96,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:57.809084Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:30ff18e20522f12520315dad4f8908f941815059c7b08e209247d50c1a24960d","observation_id":"dbcff351-882a-402b-a733-b1ae5ae3d4eb","resolution":{"observed_at":"2026-08-06T13:09:57.809084Z","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":"2026-08-06T13:09:57.871802Z","title":"Ganspace: Discovering interpretable gan controls","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":97,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:57.871802Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:b3400d2d3ec4169a4e9d2fe277e8fc973b601913dda606848c1a8aac0d7b515c","observation_id":"0f7acb47-f5d2-4813-ba9b-c89f72c6e649","resolution":{"observed_at":"2026-08-06T13:09:57.871802Z","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":"2026-08-06T13:09:57.941207Z","title":null,"venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":98,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:57.941207Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:43aa4fa73607fe93178b85c2da680c29d09e890b6f7d6452b15a5abbba58955d","observation_id":"4cf8f3f0-1ca8-43eb-b4e9-01113cb5e322","resolution":{"observed_at":"2026-08-06T13:09:57.941207Z","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":"2026-08-06T13:09:58.001360Z","title":"Asymmetric valleys: beyond sharp and flat local minima","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":99,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:58.001360Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:60bd7338aa3889a7544a45b708e9afc41c544e176efa83be3afa2dd3dc14bac2","observation_id":"7e0f0f4d-5632-4261-8eb0-1307cc3c870f","resolution":{"observed_at":"2026-08-06T13:09:58.001360Z","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":"2026-08-06T13:09:58.059610Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data","version":1},"reference_index":100,"source":"pdf_text","source_observed_at":"2026-08-06T13:09:58.059610Z"},"links":{"citing_paper":"/paper/2507.21205"},"observation_digest":"sha256:0a35a598ee3dad58924c23c197b63dcbbe511ea345f3ab131decd860ac3ea739","observation_id":"b50b1825-5940-40de-a020-767bf4e4050a","resolution":{"observed_at":"2026-08-06T13:09:58.059610Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2507.21205","last_updated":"2025-07-28T17:54:15Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-16T23:05:30.522047Z","submitted_at":"2025-07-28T17:54:15Z","title":"Learning from Limited and Imperfect Data"},"reference_resolution":{"displayed":100,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":95,"verified_exact":5,"verified_fuzzy":0},"total_outbound_references":300},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 100 of 300 outbound references and 0 inbound Pith citation observations for arXiv:2507.21205."}