{"as_of":"2026-08-16T15:16:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:b8c5728d62a038c46e53340fd2c984cec34c7dd053d2db6a9618a88f9990fe0b","coverage":[{"denominator":48,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":48,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T22:24:59.716448Z","state":"measured"},{"denominator":52,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":52,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-16T06:30:59.297886+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-02T16:16:22.897866Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-10T10:24:21.464641Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2505.07251","last_updated":"2025-05-12T05:57:39Z","snapshot_observed_at":"2026-08-15T22:19:07.366866Z","submitted_at":"2025-05-12T05:57:39Z","title":"Incomplete In-context Learning","version":1},"cited_work":{"arxiv_id":"2505.07251","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.07251","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"052b3872-e4fe-4251-8e63-7ab92dc75039","year":2025},"citing_paper":{"arxiv_id":"2604.14586","last_updated":"2026-07-21T17:16:37Z","snapshot_observed_at":"2026-08-12T14:59:29.121048Z","submitted_at":"2026-04-16T03:25:18Z","title":"CPGRec+: A Balance-oriented Framework for Personalized Video Game Recommendations","version":2},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-05-10T10:21:36.624663Z"},"links":{"cited_paper":"/paper/2505.07251","citing_paper":"/paper/2604.14586"},"observation_digest":"sha256:b0b484257e72946d3c65f4d0c48ddb3bc2dd5b5cb752286739ee0a7c0d4f8848","observation_id":"7274ed97-2981-409b-97c3-fd2c63db3ef9","resolution":{"observed_at":"2026-05-10T10:24:21.466808Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.07251","last_updated":"2025-05-12T05:57:39Z","snapshot_observed_at":"2026-08-15T22:19:07.366866Z","submitted_at":"2025-05-12T05:57:39Z","title":"Incomplete In-context Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.07251","snapshot_observed_at":"2026-08-02T16:15:50.337661Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2604.14586","last_updated":"2026-07-21T17:16:37Z","snapshot_observed_at":"2026-08-12T14:59:29.121048Z","submitted_at":"2026-04-16T03:25:18Z","title":"CPGRec+: A Balance-oriented Framework for Personalized Video Game Recommendations","version":3},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-02T16:15:50.337661Z"},"links":{"cited_paper":"/paper/2505.07251","citing_paper":"/paper/2604.14586"},"observation_digest":"sha256:50bb9e6429768fc9e26dcd9d6f93d1375a47ac782417e661d3bd3c353b09d166","observation_id":"95b14b61-0ea7-4f31-a939-b8d0dc9ae2a3","resolution":{"observed_at":"2026-08-02T16:15:50.337661Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.07251","last_updated":"2025-05-12T05:57:39Z","snapshot_observed_at":"2026-08-15T22:19:07.366866Z","submitted_at":"2025-05-12T05:57:39Z","title":"Incomplete In-context Learning","version":1},"cited_work":{"arxiv_id":"2505.07251","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.07251","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"052b3872-e4fe-4251-8e63-7ab92dc75039","year":2025},"citing_paper":{"arxiv_id":"2604.14598","last_updated":"2026-07-21T17:16:48Z","snapshot_observed_at":"2026-08-12T17:36:18.182563Z","submitted_at":"2026-04-16T04:03:45Z","title":"Category-based and Popularity-guided Video Game Recommendation: A Balance-oriented Framework","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-05-10T10:17:30.010781Z"},"links":{"cited_paper":"/paper/2505.07251","citing_paper":"/paper/2604.14598"},"observation_digest":"sha256:4224e51a69e4034c64f1f04de113abfa59f941b78e8704a096ae646f99b3215b","observation_id":"ee9d26c4-e3fb-4ad9-a5ba-48566e89c6d4","resolution":{"observed_at":"2026-05-10T10:19:20.115129Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.07251","last_updated":"2025-05-12T05:57:39Z","snapshot_observed_at":"2026-08-15T22:19:07.366866Z","submitted_at":"2025-05-12T05:57:39Z","title":"Incomplete In-context Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.07251","snapshot_observed_at":"2026-08-02T16:16:22.897866Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2604.14598","last_updated":"2026-07-21T17:16:48Z","snapshot_observed_at":"2026-08-12T17:36:18.182563Z","submitted_at":"2026-04-16T04:03:45Z","title":"Category-based and Popularity-guided Video Game Recommendation: A Balance-oriented Framework","version":3},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-02T16:16:22.897866Z"},"links":{"cited_paper":"/paper/2505.07251","citing_paper":"/paper/2604.14598"},"observation_digest":"sha256:87c1dcdc71e2c9b2781d55be25a64e08bfeb789521db7ab4846962484f3ff01d","observation_id":"6d0d6bdf-3358-4b8f-97d9-e076229c3ccb","resolution":{"observed_at":"2026-08-02T16:16:22.897866Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2505.07251/citation-record","integrity":"/paper/2505.07251/integrity","json":"/paper/2505.07251/citation-record.json","paper":"/paper/2505.07251"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:25:00.495675Z","title":"Cifar-10: Knn-based ensemble of classifiers","venue":null,"work_id":"c7063e16-3deb-488c-aeeb-6c82a6804c8e","year":2016},"citing_paper":{"arxiv_id":"2505.07251","last_updated":"2025-05-12T05:57:39Z","snapshot_observed_at":"2026-08-15T22:19:07.366866Z","submitted_at":"2025-05-12T05:57:39Z","title":"Incomplete In-context Learning","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T22:24:59.512365Z"},"links":{"citing_paper":"/paper/2505.07251"},"observation_digest":"sha256:9ada2aa144923b773a8b1a72b4b68b184bccdd63d03ef244f02707d1975a913e","observation_id":"597c116e-4546-419d-868b-3b759035b806","resolution":{"observed_at":"2026-08-15T22:25:00.501126Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:25:00.474727Z","title":"Handling extreme class imbal- ance in technical logbook datasets","venue":null,"work_id":"c002cbda-1973-496e-a26a-9f3ef11ec443","year":2021},"citing_paper":{"arxiv_id":"2505.07251","last_updated":"2025-05-12T05:57:39Z","snapshot_observed_at":"2026-08-15T22:19:07.366866Z","submitted_at":"2025-05-12T05:57:39Z","title":"Incomplete In-context Learning","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T22:24:59.518145Z"},"links":{"citing_paper":"/paper/2505.07251"},"observation_digest":"sha256:88890a5443c724e3a00475f8c4bd6b447c85314d34c25f69bbf3a5a5041c9ec3","observation_id":"27e6451e-f175-4640-8f2e-a7c4fe457e54","resolution":{"observed_at":"2026-08-15T22:25:00.481070Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:25:00.454657Z","title":"Why label when you can search? alternatives to active learning for applying human resources to build classification models under extreme class imbalance","venue":null,"work_id":"34a4e37f-45b1-4fba-8616-aa4b14930842","year":2010},"citing_paper":{"arxiv_id":"2505.07251","last_updated":"2025-05-12T05:57:39Z","snapshot_observed_at":"2026-08-15T22:19:07.366866Z","submitted_at":"2025-05-12T05:57:39Z","title":"Incomplete In-context Learning","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T22:24:59.522698Z"},"links":{"citing_paper":"/paper/2505.07251"},"observation_digest":"sha256:c6006c80925d6be2216807733d3313d9d9a3fc4027517981578313d98b5212ef","observation_id":"682e501f-120e-418b-a9af-175bbd24cdad","resolution":{"observed_at":"2026-08-15T22:25:00.462332Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:25:00.436981Z","title":"Language models are few-shot learners.Advances in neural information processing systems, 33:1877–1901, 2020","venue":null,"work_id":"3acac6d4-11a1-4847-99dd-6157d8917c66","year":1901},"citing_paper":{"arxiv_id":"2505.07251","last_updated":"2025-05-12T05:57:39Z","snapshot_observed_at":"2026-08-15T22:19:07.366866Z","submitted_at":"2025-05-12T05:57:39Z","title":"Incomplete In-context Learning","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T22:24:59.527562Z"},"links":{"citing_paper":"/paper/2505.07251"},"observation_digest":"sha256:92a56db33d1a3de13ba81c61e032beb34e3d53361c20f87994c02fe6d3c689a8","observation_id":"911b8709-57f0-4e72-8a62-933285b40a34","resolution":{"observed_at":"2026-08-15T22:25:00.444356Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:25:00.422750Z","title":null,"venue":null,"work_id":"c814b3c0-7493-40aa-9994-0fba2b2bbe14","year":1901},"citing_paper":{"arxiv_id":"2505.07251","last_updated":"2025-05-12T05:57:39Z","snapshot_observed_at":"2026-08-15T22:19:07.366866Z","submitted_at":"2025-05-12T05:57:39Z","title":"Incomplete In-context Learning","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T22:24:59.533324Z"},"links":{"citing_paper":"/paper/2505.07251"},"observation_digest":"sha256:7ba637f515ee4929f3e645f48f88d29820dcddadc8b6db95bfdc8385b7d8aeda","observation_id":"2aefb74e-5d24-4452-b517-ccabf4919a7a","resolution":{"observed_at":"2026-08-15T22:25:00.426633Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:25:00.408867Z","title":"Class incremental learning for image classification with out- of-distribution task identification.IEEE Transactions on Mul- timedia, 2025","venue":null,"work_id":"9a239128-249c-4b8e-8ef8-3d57e6f6d9bd","year":2025},"citing_paper":{"arxiv_id":"2505.07251","last_updated":"2025-05-12T05:57:39Z","snapshot_observed_at":"2026-08-15T22:19:07.366866Z","submitted_at":"2025-05-12T05:57:39Z","title":"Incomplete In-context Learning","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T22:24:59.537923Z"},"links":{"citing_paper":"/paper/2505.07251"},"observation_digest":"sha256:a632efcf9532b5ab6ef8f1a088a6c64fd1866658fbaf1125008600c8937e3baa","observation_id":"91da7573-2b51-4f90-ba4f-b793ef64e51d","resolution":{"observed_at":"2026-08-15T22:25:00.413537Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.05271","last_updated":"2025-09-26T12:52:41Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-12-06T18:57:08Z","title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.05271","snapshot_observed_at":"2026-08-15T22:24:59.542651Z","title":"Expanding performance boundaries of open-source multimodal models with model, data, and test-time scaling.arXiv preprint arXiv:2412.05271, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.07251","last_updated":"2025-05-12T05:57:39Z","snapshot_observed_at":"2026-08-15T22:19:07.366866Z","submitted_at":"2025-05-12T05:57:39Z","title":"Incomplete In-context Learning","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T22:24:59.542651Z"},"links":{"cited_paper":"/paper/2412.05271","citing_paper":"/paper/2505.07251"},"observation_digest":"sha256:e9d23b8db1f02127ace994eb75c71ea02d6dc2729960363da2bd3beb1ef6d531","observation_id":"dfc3a5c9-9871-447b-b2c9-cbd3b18667bf","resolution":{"observed_at":"2026-08-15T22:24:59.542651Z","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":"2026-08-15T22:24:59.547200Z","title":"Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.07251","last_updated":"2025-05-12T05:57:39Z","snapshot_observed_at":"2026-08-15T22:19:07.366866Z","submitted_at":"2025-05-12T05:57:39Z","title":"Incomplete In-context Learning","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T22:24:59.547200Z"},"links":{"citing_paper":"/paper/2505.07251"},"observation_digest":"sha256:651e0ac32c503f9b6f9227c2341e4cfd67870d4eb95b566ef2c531ac84a27320","observation_id":"12e1a943-16fb-4ca7-9c9f-ae092eff4b47","resolution":{"observed_at":"2026-08-15T22:24:59.547200Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.18191","last_updated":"2024-05-01T09:15:16Z","snapshot_observed_at":"2026-08-16T13:57:12.852999Z","submitted_at":"2024-04-28T14:05:23Z","title":"Exploring the Robustness of In-Context Learning with Noisy Labels","version":2},"cited_work":{"arxiv_id":"2404.18191","doi":null,"metadata_source":"pith","pith_arxiv_id":"2404.18191","snapshot_observed_at":"2026-08-15T22:24:59.840401Z","title":"Exploring the Robustness of In-Context Learning with Noisy Labels","venue":"cs.CL","work_id":"ad723f12-90ba-4cf5-82e8-b0fd3976f872","year":2024},"citing_paper":{"arxiv_id":"2505.07251","last_updated":"2025-05-12T05:57:39Z","snapshot_observed_at":"2026-08-15T22:19:07.366866Z","submitted_at":"2025-05-12T05:57:39Z","title":"Incomplete In-context Learning","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T22:24:59.551948Z"},"links":{"cited_paper":"/paper/2404.18191","citing_paper":"/paper/2505.07251"},"observation_digest":"sha256:016e1efd3d4ab1e155455672a79facc5f8ebfcddab878ad858bf8daeb204d7b8","observation_id":"c7b5c7ad-628d-415b-a94c-b48b0e7e67c8","resolution":{"observed_at":"2026-08-15T22:24:59.846941Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:25:00.385766Z","title":"Meta-in-context learning in large language models.Advances in Neural Infor- mation Processing Systems, 36:65189–65201, 2023","venue":null,"work_id":"2ee055c3-6cb2-4b1b-91b3-8685733abec6","year":2023},"citing_paper":{"arxiv_id":"2505.07251","last_updated":"2025-05-12T05:57:39Z","snapshot_observed_at":"2026-08-15T22:19:07.366866Z","submitted_at":"2025-05-12T05:57:39Z","title":"Incomplete In-context Learning","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T22:24:59.556252Z"},"links":{"citing_paper":"/paper/2505.07251"},"observation_digest":"sha256:f6202c09e25584abb3582a296601eb19473981e35a99a3344cf7b63745294749","observation_id":"8a174988-350d-4fe3-a09b-af28ead73259","resolution":{"observed_at":"2026-08-15T22:25:00.390572Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:25:00.369320Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale","venue":null,"work_id":"a691f1e1-f6af-418c-848a-e35731fe2e71","year":2021},"citing_paper":{"arxiv_id":"2505.07251","last_updated":"2025-05-12T05:57:39Z","snapshot_observed_at":"2026-08-15T22:19:07.366866Z","submitted_at":"2025-05-12T05:57:39Z","title":"Incomplete In-context Learning","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T22:24:59.560287Z"},"links":{"citing_paper":"/paper/2505.07251"},"observation_digest":"sha256:33c580d597846f7f3b0499c24555473a3031d4ee4f54ab41a2549f4cb0059386","observation_id":"f03f847f-dea8-4680-99a9-7d8fdc14f870","resolution":{"observed_at":"2026-08-15T22:25:00.374804Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:25:00.350556Z","title":"Mit- igating label biases for in-context learning","venue":null,"work_id":"6e71a78d-84ed-422e-b651-409dd51cece6","year":2023},"citing_paper":{"arxiv_id":"2505.07251","last_updated":"2025-05-12T05:57:39Z","snapshot_observed_at":"2026-08-15T22:19:07.366866Z","submitted_at":"2025-05-12T05:57:39Z","title":"Incomplete In-context Learning","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T22:24:59.564431Z"},"links":{"citing_paper":"/paper/2505.07251"},"observation_digest":"sha256:5a010e83f6852449954935db582d88680b5668bfaf92800f8494f3c3f3f765dd","observation_id":"3b7ee574-bf89-4e38-8f0b-1b160b474d52","resolution":{"observed_at":"2026-08-15T22:25:00.356646Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:25:00.334163Z","title":"Complexity-based prompting for multi-step reasoning","venue":null,"work_id":"b8cd811d-6c55-4518-825a-fa45ae01d312","year":2023},"citing_paper":{"arxiv_id":"2505.07251","last_updated":"2025-05-12T05:57:39Z","snapshot_observed_at":"2026-08-15T22:19:07.366866Z","submitted_at":"2025-05-12T05:57:39Z","title":"Incomplete In-context Learning","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T22:24:59.568351Z"},"links":{"citing_paper":"/paper/2505.07251"},"observation_digest":"sha256:9023a86602b7411d9adc49d5b14179372a749da0571c3be5a6d3d8612b6844cb","observation_id":"0da746ec-6f9b-4db7-afa4-a23b8042c1a8","resolution":{"observed_at":"2026-08-15T22:25:00.339393Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:25:00.319196Z","title":"Demystifying prompts in language models via perplexity estimation","venue":null,"work_id":"5396f390-5a10-425b-9c95-e3ee0a076442","year":2023},"citing_paper":{"arxiv_id":"2505.07251","last_updated":"2025-05-12T05:57:39Z","snapshot_observed_at":"2026-08-15T22:19:07.366866Z","submitted_at":"2025-05-12T05:57:39Z","title":"Incomplete In-context Learning","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T22:24:59.572312Z"},"links":{"citing_paper":"/paper/2505.07251"},"observation_digest":"sha256:44a50fefb33edc40b7680934a15e2771daa4e624fd8ebea75565a51c58c27aa0","observation_id":"2b8ecec0-4c65-46ca-9806-e2f368953470","resolution":{"observed_at":"2026-08-15T22:25:00.324514Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.16549","last_updated":"2023-12-27T12:20:12Z","snapshot_observed_at":"2026-08-16T14:31:24.129806Z","submitted_at":"2023-12-27T12:20:12Z","title":"How Robust are LLMs to In-Context Majority Label Bias?","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.16549","snapshot_observed_at":"2026-08-15T22:24:59.576587Z","title":"How robust are llms to in- context majority label bias?arXiv preprint arXiv:2312.16549, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.07251","last_updated":"2025-05-12T05:57:39Z","snapshot_observed_at":"2026-08-15T22:19:07.366866Z","submitted_at":"2025-05-12T05:57:39Z","title":"Incomplete In-context Learning","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T22:24:59.576587Z"},"links":{"cited_paper":"/paper/2312.16549","citing_paper":"/paper/2505.07251"},"observation_digest":"sha256:e3f2663120cc61bb81f515e89257328d453bf28096a6095c5a81256f7a837022","observation_id":"26cd35f1-ff27-4fe3-9998-4d6e690351fe","resolution":{"observed_at":"2026-08-15T22:24:59.576587Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:25:00.302779Z","title":"Coverage- based example selection for in-context learning","venue":null,"work_id":"af388df2-5610-4112-bb97-a33969749f04","year":2023},"citing_paper":{"arxiv_id":"2505.07251","last_updated":"2025-05-12T05:57:39Z","snapshot_observed_at":"2026-08-15T22:19:07.366866Z","submitted_at":"2025-05-12T05:57:39Z","title":"Incomplete In-context Learning","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T22:24:59.580991Z"},"links":{"citing_paper":"/paper/2505.07251"},"observation_digest":"sha256:4b78e022455be689f6fc2f76b6fb54c5dad59f8a51d8854156fc5b348e54b4f2","observation_id":"48bee1ae-367e-4eed-95c9-3e1bb2ee82e5","resolution":{"observed_at":"2026-08-15T22:25:00.307849Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:25:00.285459Z","title":"In-context learning learns label relationships but is not conventional learning","venue":null,"work_id":"d6a341b7-9e51-4a1c-8ef3-a67e1a8e2b9f","year":2024},"citing_paper":{"arxiv_id":"2505.07251","last_updated":"2025-05-12T05:57:39Z","snapshot_observed_at":"2026-08-15T22:19:07.366866Z","submitted_at":"2025-05-12T05:57:39Z","title":"Incomplete In-context Learning","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T22:24:59.584994Z"},"links":{"citing_paper":"/paper/2505.07251"},"observation_digest":"sha256:354d704da84cd6f3a72748c254935438bb6454487036eecb00d300e15dee591c","observation_id":"95b8a870-5220-4e68-b7c8-893e71d0336d","resolution":{"observed_at":"2026-08-15T22:25:00.290393Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T22:24:59.589031Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2505.07251","last_updated":"2025-05-12T05:57:39Z","snapshot_observed_at":"2026-08-15T22:19:07.366866Z","submitted_at":"2025-05-12T05:57:39Z","title":"Incomplete In-context Learning","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T22:24:59.589031Z"},"links":{"citing_paper":"/paper/2505.07251"},"observation_digest":"sha256:171ebba1cb8807df23ed51fbdb8a48fca00eb8e09d85ef94db4f21e0c30738cc","observation_id":"b117614f-d14f-43bf-9862-4c41164e2749","resolution":{"observed_at":"2026-08-15T22:24:59.589031Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:25:00.251263Z","title":"Prompt-based concept learning for few-shot class-incremental learning.IEEE Transactions on Circuits and Systems for Video Technology, 2025","venue":null,"work_id":"7f207987-bf49-4825-a291-7a221d9f5905","year":2025},"citing_paper":{"arxiv_id":"2505.07251","last_updated":"2025-05-12T05:57:39Z","snapshot_observed_at":"2026-08-15T22:19:07.366866Z","submitted_at":"2025-05-12T05:57:39Z","title":"Incomplete In-context Learning","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T22:24:59.592669Z"},"links":{"citing_paper":"/paper/2505.07251"},"observation_digest":"sha256:364f2e92dd1065f55eb0427206f5a305c01e8e99b65432d658db66bd1c1a148b","observation_id":"72c02d9c-074b-47ef-a60c-25663eb455fd","resolution":{"observed_at":"2026-08-15T22:25:00.259962Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:25:00.223543Z","title":"Finding support examples for in- context learning","venue":null,"work_id":"12976a6f-a203-4bf1-b9b1-90fa4b1f4cae","year":2023},"citing_paper":{"arxiv_id":"2505.07251","last_updated":"2025-05-12T05:57:39Z","snapshot_observed_at":"2026-08-15T22:19:07.366866Z","submitted_at":"2025-05-12T05:57:39Z","title":"Incomplete In-context Learning","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T22:24:59.596776Z"},"links":{"citing_paper":"/paper/2505.07251"},"observation_digest":"sha256:5fa3de1c44e098b32567e078590fdc94a516234611d57120d843043d0917c997","observation_id":"2062bd19-13a0-4365-93f7-e25a5f91320d","resolution":{"observed_at":"2026-08-15T22:25:00.231109Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:25:00.204226Z","title":"Mot: Pre-thinking and recall- ing enable chatgpt to self-improve with memory-of-thoughts","venue":null,"work_id":"8a19e3dc-c63a-45bb-8bb3-e0995bab2cfd","year":2023},"citing_paper":{"arxiv_id":"2505.07251","last_updated":"2025-05-12T05:57:39Z","snapshot_observed_at":"2026-08-15T22:19:07.366866Z","submitted_at":"2025-05-12T05:57:39Z","title":"Incomplete In-context Learning","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T22:24:59.600868Z"},"links":{"citing_paper":"/paper/2505.07251"},"observation_digest":"sha256:f82b5e12e47cd8352f671c0412cf08665c6fe66b08891e40b7ec8786d18422e0","observation_id":"7bcf0c1e-b270-4792-bf58-86329f1c6520","resolution":{"observed_at":"2026-08-15T22:25:00.209788Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:25:00.187037Z","title":null,"venue":null,"work_id":"e0622500-07cc-4002-a414-337055d28ed3","year":2022},"citing_paper":{"arxiv_id":"2505.07251","last_updated":"2025-05-12T05:57:39Z","snapshot_observed_at":"2026-08-15T22:19:07.366866Z","submitted_at":"2025-05-12T05:57:39Z","title":"Incomplete In-context Learning","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T22:24:59.604998Z"},"links":{"citing_paper":"/paper/2505.07251"},"observation_digest":"sha256:a0730c2d7527610cd2fd96cff23fee5780e6a2e1de4678ec77b744f1812b2c13","observation_id":"941ede49-54db-45b8-b431-baff451d742b","resolution":{"observed_at":"2026-08-15T22:25:00.192276Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T22:24:59.608809Z","title":"Class incremental learning with self-supervised pre-training and prototype learning.Pattern Recognition, 157:110943, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.07251","last_updated":"2025-05-12T05:57:39Z","snapshot_observed_at":"2026-08-15T22:19:07.366866Z","submitted_at":"2025-05-12T05:57:39Z","title":"Incomplete In-context Learning","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T22:24:59.608809Z"},"links":{"citing_paper":"/paper/2505.07251"},"observation_digest":"sha256:93c2a774bafab72579109605dfb07a6b222c01ef6339812d07b07e305345c03d","observation_id":"0884c381-4823-4ebe-b7fe-72ecc98bf164","resolution":{"observed_at":"2026-08-15T22:24:59.608809Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.07546","last_updated":"2024-07-23T12:28:14Z","snapshot_observed_at":"2026-08-16T14:01:50.696255Z","submitted_at":"2024-04-11T08:20:10Z","title":"Does In-Context Learning Really Learn? Rethinking How Large Language Models Respond and Solve Tasks via In-Context Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.07546","snapshot_observed_at":"2026-08-15T22:24:59.613022Z","title":"Decomposing label space, format and discrimination: Re- thinking how llms respond and solve tasks via in-context learning.arXiv preprint arXiv:2404.07546, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.07251","last_updated":"2025-05-12T05:57:39Z","snapshot_observed_at":"2026-08-15T22:19:07.366866Z","submitted_at":"2025-05-12T05:57:39Z","title":"Incomplete In-context Learning","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T22:24:59.613022Z"},"links":{"cited_paper":"/paper/2404.07546","citing_paper":"/paper/2505.07251"},"observation_digest":"sha256:0f61a2c2e9eb041b23bada6d431de9c2e44b7c230672b03e246b3742b8d303fe","observation_id":"c3728138-18b0-468d-9ad6-11084ab14046","resolution":{"observed_at":"2026-08-15T22:24:59.613022Z","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":"2026-08-15T22:24:59.617780Z","title":"Fantastically ordered prompts and where to find them: Overcoming few-shot prompt order sensitivity","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.07251","last_updated":"2025-05-12T05:57:39Z","snapshot_observed_at":"2026-08-15T22:19:07.366866Z","submitted_at":"2025-05-12T05:57:39Z","title":"Incomplete In-context Learning","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T22:24:59.617780Z"},"links":{"citing_paper":"/paper/2505.07251"},"observation_digest":"sha256:1dfe1f83a7af6b91d55753c2afa0705a4e057755557eca52984e3edd4ca2db21","observation_id":"8cb81720-6142-4ece-a4e0-ae0888f2bf80","resolution":{"observed_at":"2026-08-15T22:24:59.617780Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:25:00.142667Z","title":"Z-ICL: Zero-shot in-context learning with pseudo-demonstrations","venue":null,"work_id":"d36c7da3-0cca-4bc4-bb96-7afa74fd7b47","year":2023},"citing_paper":{"arxiv_id":"2505.07251","last_updated":"2025-05-12T05:57:39Z","snapshot_observed_at":"2026-08-15T22:19:07.366866Z","submitted_at":"2025-05-12T05:57:39Z","title":"Incomplete In-context Learning","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T22:24:59.621714Z"},"links":{"citing_paper":"/paper/2505.07251"},"observation_digest":"sha256:42e618ca05d6a8b65b191fa97e9f7a8e4677e1c375b8a032fc7c6a697871eb06","observation_id":"bc42c7f3-9c86-4d15-81e2-e818c5e2fe4d","resolution":{"observed_at":"2026-08-15T22:25:00.148989Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.20046","last_updated":"2023-10-30T22:03:55Z","snapshot_observed_at":"2026-08-16T14:47:25.878053Z","submitted_at":"2023-10-30T22:03:55Z","title":"Which Examples to Annotate for In-Context Learning? Towards Effective and Efficient Selection","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.20046","snapshot_observed_at":"2026-08-15T22:24:59.625516Z","title":"Which examples to annotate for in-context learning? towards effective and efficient selection.arXiv preprint arXiv:2310.20046, 2023","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.07251","last_updated":"2025-05-12T05:57:39Z","snapshot_observed_at":"2026-08-15T22:19:07.366866Z","submitted_at":"2025-05-12T05:57:39Z","title":"Incomplete In-context Learning","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T22:24:59.625516Z"},"links":{"cited_paper":"/paper/2310.20046","citing_paper":"/paper/2505.07251"},"observation_digest":"sha256:ef8284bbeeb6ea4ed05dbc6f8caa932e465adb7ce3ecaadde2a6483008d5a5a1","observation_id":"05f0a30a-4984-441d-83ab-3afffa52305b","resolution":{"observed_at":"2026-08-15T22:24:59.625516Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:25:00.121358Z","title":"In- context learning for text classification with many labels","venue":null,"work_id":"aeee3529-fb80-4afc-adbc-d4d4a7fc4103","year":2023},"citing_paper":{"arxiv_id":"2505.07251","last_updated":"2025-05-12T05:57:39Z","snapshot_observed_at":"2026-08-15T22:19:07.366866Z","submitted_at":"2025-05-12T05:57:39Z","title":"Incomplete In-context Learning","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-15T22:24:59.630301Z"},"links":{"citing_paper":"/paper/2505.07251"},"observation_digest":"sha256:2ba9f0c88752a2d0dffa1c39977c6ff3e69543f5fb910ce631260acebd6def1e","observation_id":"692d33fb-c678-4ca1-b80a-0064f3dd6f67","resolution":{"observed_at":"2026-08-15T22:25:00.128562Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:25:00.102211Z","title":"MetaICL: Learning to learn in context","venue":null,"work_id":"05c9a822-ba1c-4d78-910c-b10a0590bce7","year":2022},"citing_paper":{"arxiv_id":"2505.07251","last_updated":"2025-05-12T05:57:39Z","snapshot_observed_at":"2026-08-15T22:19:07.366866Z","submitted_at":"2025-05-12T05:57:39Z","title":"Incomplete In-context Learning","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T22:24:59.634219Z"},"links":{"citing_paper":"/paper/2505.07251"},"observation_digest":"sha256:187e2dabe93785cbd2d119ba52df6516934afa3a518546761411814e889a2a33","observation_id":"3e6c7129-2354-4c3b-a1ae-cf0df61ee5ca","resolution":{"observed_at":"2026-08-15T22:25:00.108786Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:25:00.084534Z","title":null,"venue":null,"work_id":"bf33c657-d9aa-4d21-9ac9-2a46b177d233","year":2022},"citing_paper":{"arxiv_id":"2505.07251","last_updated":"2025-05-12T05:57:39Z","snapshot_observed_at":"2026-08-15T22:19:07.366866Z","submitted_at":"2025-05-12T05:57:39Z","title":"Incomplete In-context Learning","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-15T22:24:59.639220Z"},"links":{"citing_paper":"/paper/2505.07251"},"observation_digest":"sha256:649a7ba6d37d88185ab2730439ca428a77e6bdb63bd74a9356a8d452d1cb8a6c","observation_id":"9bb54492-e368-4b0d-a5cc-2c081bfed8d2","resolution":{"observed_at":"2026-08-15T22:25:00.089412Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:25:00.065225Z","title":"Diversity of thought improves reasoning abilities of large language models","venue":null,"work_id":"2f465696-ac09-4b27-a60d-e2ed3b7e8abb","year":2023},"citing_paper":{"arxiv_id":"2505.07251","last_updated":"2025-05-12T05:57:39Z","snapshot_observed_at":"2026-08-15T22:19:07.366866Z","submitted_at":"2025-05-12T05:57:39Z","title":"Incomplete In-context Learning","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-15T22:24:59.643802Z"},"links":{"citing_paper":"/paper/2505.07251"},"observation_digest":"sha256:ce978bb636aebced408113c07b6f44a177f16b8a546a43c5a57984d56b9d34b4","observation_id":"f03c1c6a-0acc-4431-ba64-48b39af256ca","resolution":{"observed_at":"2026-08-15T22:25:00.070441Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T22:24:59.647956Z","title":"Improving language understanding by gener- ative pre-training","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.07251","last_updated":"2025-05-12T05:57:39Z","snapshot_observed_at":"2026-08-15T22:19:07.366866Z","submitted_at":"2025-05-12T05:57:39Z","title":"Incomplete In-context Learning","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-15T22:24:59.647956Z"},"links":{"citing_paper":"/paper/2505.07251"},"observation_digest":"sha256:c7ae65849a7bebf797ce27ae4d705cb21ba393066ca243d8871785c72bb604e8","observation_id":"b9c681cc-c2ec-45ae-85f3-6745c415d28e","resolution":{"observed_at":"2026-08-15T22:24:59.647956Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:25:00.022033Z","title":"Language models are unsuper- vised multitask learners.OpenAI blog, 1(8):9, 2019","venue":null,"work_id":"65e69449-4326-44a2-8faa-bcf8158ad59f","year":2019},"citing_paper":{"arxiv_id":"2505.07251","last_updated":"2025-05-12T05:57:39Z","snapshot_observed_at":"2026-08-15T22:19:07.366866Z","submitted_at":"2025-05-12T05:57:39Z","title":"Incomplete In-context Learning","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-15T22:24:59.652321Z"},"links":{"citing_paper":"/paper/2505.07251"},"observation_digest":"sha256:446e787ca598f1e5e13c69369f8b68cb2d7b44efae92f9db82349b4aef725310","observation_id":"76326bfe-21b1-4d2d-9994-3d1826c00be5","resolution":{"observed_at":"2026-08-15T22:25:00.034653Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:24:59.998613Z","title":"Learning transferable visual models from natural language supervision","venue":null,"work_id":"8284f359-932c-44f4-bdeb-c75c6ea01a47","year":2021},"citing_paper":{"arxiv_id":"2505.07251","last_updated":"2025-05-12T05:57:39Z","snapshot_observed_at":"2026-08-15T22:19:07.366866Z","submitted_at":"2025-05-12T05:57:39Z","title":"Incomplete In-context Learning","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-15T22:24:59.656543Z"},"links":{"citing_paper":"/paper/2505.07251"},"observation_digest":"sha256:8fe43c29581aad84050c56a45269accd42a41e5ed29559cd1eca8747707e3a78","observation_id":"4b65addf-672e-497e-a3fd-516b4ba18c9b","resolution":{"observed_at":"2026-08-15T22:25:00.005125Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T22:24:59.660253Z","title":"Learning transferable visual models from natural language supervi- sion","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.07251","last_updated":"2025-05-12T05:57:39Z","snapshot_observed_at":"2026-08-15T22:19:07.366866Z","submitted_at":"2025-05-12T05:57:39Z","title":"Incomplete In-context Learning","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-15T22:24:59.660253Z"},"links":{"citing_paper":"/paper/2505.07251"},"observation_digest":"sha256:4cb417d2ef70f75640ad94e6268c043b065038e22ab74326865eacaf05ebb140","observation_id":"3159a7a6-221f-4908-83f3-0266dbe9779a","resolution":{"observed_at":"2026-08-15T22:24:59.660253Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:24:59.978382Z","title":null,"venue":null,"work_id":"ab318296-42c7-4989-9799-7c3141b2e9e8","year":2020},"citing_paper":{"arxiv_id":"2505.07251","last_updated":"2025-05-12T05:57:39Z","snapshot_observed_at":"2026-08-15T22:19:07.366866Z","submitted_at":"2025-05-12T05:57:39Z","title":"Incomplete In-context Learning","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-15T22:24:59.664876Z"},"links":{"citing_paper":"/paper/2505.07251"},"observation_digest":"sha256:b6a4ac26b7f8281770166fc4682f7dc6506cdfb321d604f9cffd48bad543f330","observation_id":"19c6f671-62d8-44ff-8c42-1345681e7297","resolution":{"observed_at":"2026-08-15T22:24:59.982858Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1505.00855","last_updated":"2015-05-05T01:25:26Z","snapshot_observed_at":"2026-08-14T22:49:52.971698Z","submitted_at":"2015-05-05T01:25:26Z","title":"Large-scale Classification of Fine-Art Paintings: Learning The Right Metric on The Right Feature","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1505.00855","snapshot_observed_at":"2026-08-15T22:24:59.668599Z","title":"Large-scale classification of fine-art paintings: Learning the right metric on the right feature.arXiv preprint arXiv:1505.00855, 2015","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2505.07251","last_updated":"2025-05-12T05:57:39Z","snapshot_observed_at":"2026-08-15T22:19:07.366866Z","submitted_at":"2025-05-12T05:57:39Z","title":"Incomplete In-context Learning","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-15T22:24:59.668599Z"},"links":{"cited_paper":"/paper/1505.00855","citing_paper":"/paper/2505.07251"},"observation_digest":"sha256:2defcf60d23af68691fa2b98048aa2e29379776ef0ddcc23fe9a2c36d7abedfc","observation_id":"0f783ea6-27db-47c3-accb-090fcc6b1fd2","resolution":{"observed_at":"2026-08-15T22:24:59.668599Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:24:59.965219Z","title":"Label words are anchors: An information flow perspective for understanding in-context learning","venue":null,"work_id":"16c7e03f-5eeb-40d8-ac47-45bd30d460d0","year":2023},"citing_paper":{"arxiv_id":"2505.07251","last_updated":"2025-05-12T05:57:39Z","snapshot_observed_at":"2026-08-15T22:19:07.366866Z","submitted_at":"2025-05-12T05:57:39Z","title":"Incomplete In-context Learning","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-15T22:24:59.673583Z"},"links":{"citing_paper":"/paper/2505.07251"},"observation_digest":"sha256:790a10a1160691fe8d93503537aae41b210ff91a50ac667e5d7a924a17ff9c60","observation_id":"970eef8e-84b8-4567-8a2b-a838c19d36d3","resolution":{"observed_at":"2026-08-15T22:24:59.969467Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:24:59.952793Z","title":"Large language models are latent variable models: Explaining and finding good demonstrations for in-context learning","venue":null,"work_id":"a176e9b9-5160-47c5-9923-e83380e1f0b9","year":2023},"citing_paper":{"arxiv_id":"2505.07251","last_updated":"2025-05-12T05:57:39Z","snapshot_observed_at":"2026-08-15T22:19:07.366866Z","submitted_at":"2025-05-12T05:57:39Z","title":"Incomplete In-context Learning","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-15T22:24:59.677632Z"},"links":{"citing_paper":"/paper/2505.07251"},"observation_digest":"sha256:14c1612322e5f8b8d4b40c545acb31f2f26bcb1cbcaa93ede84a26997f95c8a8","observation_id":"916cd7b0-fff0-458b-8cbd-f4262230278d","resolution":{"observed_at":"2026-08-15T22:24:59.956956Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:24:59.939054Z","title":"Chi, Tatsunori Hashimoto, Oriol Vinyals, Percy Liang, Jeff Dean, and William Fedus","venue":null,"work_id":"2f7764ca-a3f8-4e6a-a510-231f752aa53c","year":2022},"citing_paper":{"arxiv_id":"2505.07251","last_updated":"2025-05-12T05:57:39Z","snapshot_observed_at":"2026-08-15T22:19:07.366866Z","submitted_at":"2025-05-12T05:57:39Z","title":"Incomplete In-context Learning","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-15T22:24:59.682001Z"},"links":{"citing_paper":"/paper/2505.07251"},"observation_digest":"sha256:2aa8a9029b732da1d21f21532124ffe26c70de63898d259894448b6ddcb27379","observation_id":"8e083543-98c4-41da-85b2-afe785cd4325","resolution":{"observed_at":"2026-08-15T22:24:59.944337Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T22:24:59.685996Z","title":"Chi, Quoc V","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.07251","last_updated":"2025-05-12T05:57:39Z","snapshot_observed_at":"2026-08-15T22:19:07.366866Z","submitted_at":"2025-05-12T05:57:39Z","title":"Incomplete In-context Learning","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-15T22:24:59.685996Z"},"links":{"citing_paper":"/paper/2505.07251"},"observation_digest":"sha256:bf31743d0363557ce156dd3aedb2ae7b016448000412dacef27a6c823864343f","observation_id":"10a12eb9-a504-428e-8f5b-3d06998c0634","resolution":{"observed_at":"2026-08-15T22:24:59.685996Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:24:59.913292Z","title":"Symbol tuning improves in- context learning in language models","venue":null,"work_id":"426d7862-ae9d-41b4-909b-dd7f5d74555e","year":2023},"citing_paper":{"arxiv_id":"2505.07251","last_updated":"2025-05-12T05:57:39Z","snapshot_observed_at":"2026-08-15T22:19:07.366866Z","submitted_at":"2025-05-12T05:57:39Z","title":"Incomplete In-context Learning","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-15T22:24:59.690493Z"},"links":{"citing_paper":"/paper/2505.07251"},"observation_digest":"sha256:bcc718f0ee3b1c41742e28602f62ce7348b5c5fbff7dd1d9e5f775ac54148453","observation_id":"2a39cc9c-7fed-4452-92cb-61d92573c9fc","resolution":{"observed_at":"2026-08-15T22:24:59.917812Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.03846","last_updated":"2023-03-08T07:37:43Z","snapshot_observed_at":"2026-08-13T12:29:57.122699Z","submitted_at":"2023-03-07T12:24:17Z","title":"Larger language models do in-context learning differently","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.03846","snapshot_observed_at":"2026-08-15T22:24:59.694539Z","title":"Larger language models do in-context learning differently.arXiv preprint arXiv:2303.03846, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.07251","last_updated":"2025-05-12T05:57:39Z","snapshot_observed_at":"2026-08-15T22:19:07.366866Z","submitted_at":"2025-05-12T05:57:39Z","title":"Incomplete In-context Learning","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-15T22:24:59.694539Z"},"links":{"cited_paper":"/paper/2303.03846","citing_paper":"/paper/2505.07251"},"observation_digest":"sha256:9f1d330c5c4ce436d44722ebdb6d4368747a606a97c78136044ecad2705eaaec","observation_id":"16370a3b-e427-4e7e-acf6-71b03a41b8d8","resolution":{"observed_at":"2026-08-15T22:24:59.694539Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:24:59.898158Z","title":"Self-adaptive in-context learning: An information compression perspective for in-context example selection and ordering","venue":null,"work_id":"3213bce3-985c-4fbe-ac44-ae4772affaa6","year":2023},"citing_paper":{"arxiv_id":"2505.07251","last_updated":"2025-05-12T05:57:39Z","snapshot_observed_at":"2026-08-15T22:19:07.366866Z","submitted_at":"2025-05-12T05:57:39Z","title":"Incomplete In-context Learning","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-15T22:24:59.698950Z"},"links":{"citing_paper":"/paper/2505.07251"},"observation_digest":"sha256:5e8fb82358dd78f2b924082ca0e3edcff81e8c581500132dd9b3083508fa2a86","observation_id":"15fb0835-d7d1-4abc-a89c-82f2127f7c56","resolution":{"observed_at":"2026-08-15T22:24:59.902755Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1708.07747","last_updated":"2017-09-15T21:29:49Z","snapshot_observed_at":"2026-08-13T15:13:33.081929Z","submitted_at":"2017-08-25T14:01:29Z","title":"Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1708.07747","snapshot_observed_at":"2026-08-15T22:24:59.703634Z","title":"Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms.arXiv preprint arXiv:1708.07747, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.07251","last_updated":"2025-05-12T05:57:39Z","snapshot_observed_at":"2026-08-15T22:19:07.366866Z","submitted_at":"2025-05-12T05:57:39Z","title":"Incomplete In-context Learning","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-15T22:24:59.703634Z"},"links":{"cited_paper":"/paper/1708.07747","citing_paper":"/paper/2505.07251"},"observation_digest":"sha256:ac53ea1ccc6f55479fff1cabcb7eac3b8d1fe2d17c12cf520b46c91f72ff63b4","observation_id":"43a1dfea-1394-4f7f-8dce-b59160319996","resolution":{"observed_at":"2026-08-15T22:24:59.703634Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:24:59.885552Z","title":"Few-shot class-incremental learning for classifi- cation and object detection: A survey.IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025","venue":null,"work_id":"a163b58a-0a8c-4307-807a-34cad188c637","year":2025},"citing_paper":{"arxiv_id":"2505.07251","last_updated":"2025-05-12T05:57:39Z","snapshot_observed_at":"2026-08-15T22:19:07.366866Z","submitted_at":"2025-05-12T05:57:39Z","title":"Incomplete In-context Learning","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-15T22:24:59.708322Z"},"links":{"citing_paper":"/paper/2505.07251"},"observation_digest":"sha256:a6f1a4e2ce36ff06fe99b86decc90b533c7aa06687d176764f9d2c5d7ca7d24a","observation_id":"faa3a691-89c1-44e9-b595-4cdbce57bccf","resolution":{"observed_at":"2026-08-15T22:24:59.889907Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T22:24:59.869050Z","title":"Towards robust ranker for text retrieval","venue":null,"work_id":"a4d7ab20-6483-45d7-9c01-5ac18f7a3c71","year":2023},"citing_paper":{"arxiv_id":"2505.07251","last_updated":"2025-05-12T05:57:39Z","snapshot_observed_at":"2026-08-15T22:19:07.366866Z","submitted_at":"2025-05-12T05:57:39Z","title":"Incomplete In-context Learning","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-15T22:24:59.712422Z"},"links":{"citing_paper":"/paper/2505.07251"},"observation_digest":"sha256:aa602605c04b7b15ebf0638b6dd0fe78c213e5a5c7b3b0d73128cceab639a5da","observation_id":"1e3ea481-805e-4206-83b0-870d942e3f3b","resolution":{"observed_at":"2026-08-15T22:24:59.874045Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.11574","last_updated":"2024-02-18T12:43:38Z","snapshot_observed_at":"2026-08-16T14:17:36.905874Z","submitted_at":"2024-02-18T12:43:38Z","title":"Visual In-Context Learning for Large Vision-Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.11574","snapshot_observed_at":"2026-08-15T22:24:59.716448Z","title":"Visual in-context learning for large vision-language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.07251","last_updated":"2025-05-12T05:57:39Z","snapshot_observed_at":"2026-08-15T22:19:07.366866Z","submitted_at":"2025-05-12T05:57:39Z","title":"Incomplete In-context Learning","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-15T22:24:59.716448Z"},"links":{"cited_paper":"/paper/2402.11574","citing_paper":"/paper/2505.07251"},"observation_digest":"sha256:d7884eabce6b44b7f4d6cd585e3756c2c5bea018d8707f355a66457ab8e5c55b","observation_id":"d72af2e4-4f7f-4bcb-b81f-3a340d8485f2","resolution":{"observed_at":"2026-08-15T22:24:59.716448Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2505.07251","last_updated":"2025-05-12T05:57:39Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-15T22:19:07.366866Z","submitted_at":"2025-05-12T05:57:39Z","title":"Incomplete In-context Learning"},"reference_resolution":{"displayed":48,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":19,"verified_exact":1,"verified_fuzzy":28},"total_outbound_references":48},"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":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 48 of 48 outbound references and 4 inbound Pith citation observations for arXiv:2505.07251."}