{"as_of":"2026-08-14T20:19:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:b2c07df410a719c4d0934be9a424688426f28a76f80c0dfdc402d7f6cee997e6","coverage":[{"denominator":74,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":74,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T17:52:18.464538Z","state":"measured"},{"denominator":74,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":74,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-14T06:32:32.682623+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/2508.15567/citation-record","integrity":"/paper/2508.15567/integrity","json":"/paper/2508.15567/citation-record.json","paper":"/paper/2508.15567"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T17:52:12.360995Z","title":"Food-101–Mining Discriminative Components with Random Forests","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:12.360995Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:0a1b30ec03ba2c0115d003c9cb23f56dae0ff3749c7b33357f251221854edacb","observation_id":"90d1ca91-8276-4079-bd95-5608a80f50b5","resolution":{"observed_at":"2026-08-05T17:52:12.360995Z","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":"2026-08-05T17:52:12.472388Z","title":"Information maximization for few-shot learning","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:12.472388Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:1b85e23e0ddb0a8f2ab741a2603fe66eafaff49103f08bd029dca96538735ee6","observation_id":"8b78154c-4f1e-44fc-9371-d680e3521bfb","resolution":{"observed_at":"2026-08-05T17:52:12.472388Z","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":"2026-08-05T17:52:12.614580Z","title":"Describing Textures in the Wild","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:12.614580Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:56074c599b7d9fc0ec20fae4ecfcb6e9f928223ac7372cb6faaff4409aa2bab4","observation_id":"39a59357-48a0-4112-b2de-7da251277a48","resolution":{"observed_at":"2026-08-05T17:52:12.614580Z","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":"2026-08-05T17:52:12.793259Z","title":"Imagenet: A Large-Scale Hierarchical Image Database","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:12.793259Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:21d8a6ce7ce8b11aa498e2c203db70aa312ee50a1225f1a3f55f056a16040f62","observation_id":"3fbe639c-9639-45b1-8055-62c4d1d3b442","resolution":{"observed_at":"2026-08-05T17:52:12.793259Z","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":"2026-08-05T17:52:12.919470Z","title":"A normality test for multivariate dependent samples.Signal Processing, 201:108705, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:12.919470Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:b8df56e63995c72e1dd7d3d0285261569b9c5a3d0389ba099bfcf443a40bc6d2","observation_id":"1de50f76-72a8-4b45-9d8d-bb7ae6851b80","resolution":{"observed_at":"2026-08-05T17:52:12.919470Z","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":"2026-08-05T17:52:13.063961Z","title":"Joint normality test via two-dimensional projection","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:13.063961Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:1b1217ad2314282e69af5ee63530ad2ec2e38556a8b50c41ae9dcb7d56296c44","observation_id":"90a68c74-1e9f-477d-8865-e6e25aee306b","resolution":{"observed_at":"2026-08-05T17:52:13.063961Z","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":"2026-08-05T17:52:13.242718Z","title":"Frus- tratingly easy test-time adaptation of vision-language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:13.242718Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:24677b899e9741cb18de35b7d1ff613eda18f22c902584ceb205e8ea9b11ac38","observation_id":"56e020ab-3681-4916-afea-9e6bf667f38a","resolution":{"observed_at":"2026-08-05T17:52:13.242718Z","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":"2026-08-05T17:52:13.387538Z","title":"Learning Generative Visual Models from Few Training Examples: An Incremental Bayesian Approach Tested on 101 Object Categories","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:13.387538Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:6e3283279a7facd151b2bd15e3b51b1484edb18c28f40efe88e263f6496c4868","observation_id":"7f71ffdb-64fa-4fce-9bc1-f928ee83b0da","resolution":{"observed_at":"2026-08-05T17:52:13.387538Z","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":"2026-08-05T17:52:13.510836Z","title":"Diverse data augmenta- tion with diffusions for effective test-time prompt tuning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:13.510836Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:53dc40be0bd0dcd7b9571e4fb15d69eafcb027a9f52275f17f8dc64259646b91","observation_id":"d6fa09dd-05e1-4810-ad63-53d2ca21cdbd","resolution":{"observed_at":"2026-08-05T17:52:13.510836Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.04352","last_updated":"2025-01-08T08:49:52Z","snapshot_observed_at":"2026-08-10T21:32:51.946200Z","submitted_at":"2025-01-08T08:49:52Z","title":"Online Gaussian Test-Time Adaptation of Vision-Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.04352","snapshot_observed_at":"2026-08-05T17:52:13.565783Z","title":"Online gaussian test-time adaptation of vision-language models.arXiv preprint arXiv:2501.04352, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:13.565783Z"},"links":{"cited_paper":"/paper/2501.04352","citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:1ca0823558a4adf35b5389f360fed55a924f048b118fa26f755fab4f30acce80","observation_id":"2694e7e9-c4ca-4b2c-886c-dd0c199cc657","resolution":{"observed_at":"2026-08-05T17:52:13.565783Z","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":"2026-08-05T17:52:13.614116Z","title":"Clip-adapter: Better vision-language models with feature adapters.IJCV, 132(2), 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:13.614116Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:e2b4123c220c73ed379320eb555fef122c6a11dd80fc60b0e318279e94aa1776","observation_id":"b7de665f-88e3-428d-b8a0-3744c53d1413","resolution":{"observed_at":"2026-08-05T17:52:13.614116Z","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":"2026-08-05T17:52:13.698341Z","title":"Dota: Distributional test-time adaptation of vision-language models.arXiv preprint arXiv:2409.19375, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:13.698341Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:5c03ab7a4515acea30bfce11dc360631d50a38d754b0195513d5586f1b4bac27","observation_id":"c40554e3-ee62-4180-b2cb-6dc86e23d573","resolution":{"observed_at":"2026-08-05T17:52:13.698341Z","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":"2026-08-05T17:52:13.785404Z","title":"Discriminant analysis by gaussian mixtures.Journal of the Royal Statistical Society Series B: Statistical Methodology, 58(1):155–176, 1996","venue":null,"work_id":null,"year":1996},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:13.785404Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:8c24748e9b5e7e362c31c4c69c41a19ad4488c634c4b7fe31bd0ad772fc7de66","observation_id":"c7e527ae-31af-406b-8402-07807ebac181","resolution":{"observed_at":"2026-08-05T17:52:13.785404Z","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":"2026-08-05T17:52:13.915034Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:13.915034Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:2b8a1019ad9ad83dcadcf835880fc7bd7074759b03175cab8d250855106ca01b","observation_id":"355b4cb0-8060-4ba6-9953-819e6659e807","resolution":{"observed_at":"2026-08-05T17:52:13.915034Z","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":"2026-08-05T17:52:13.999890Z","title":"The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:13.999890Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:38f4178a72eb01bdb3a7c7793cb05c6dd392b12040a27d2fc3481bf50f35be14","observation_id":"64b9fd22-761f-4cc9-9657-9319104a64b4","resolution":{"observed_at":"2026-08-05T17:52:13.999890Z","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":"2026-08-05T17:52:14.108287Z","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:14.108287Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:0a6ed65384b873e47e73cf480007cdf1135accf10373d43cc393f81f02d727e7","observation_id":"45a9910b-80fd-4e3b-8800-919a8e19b593","resolution":{"observed_at":"2026-08-05T17:52:14.108287Z","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":"2026-08-05T17:52:14.212817Z","title":"Natural Adversarial Examples","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:14.212817Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:dbf645d8a21569fbe4d6c68d8d5b999e197f8304352b9d882411c92e18bcfc28","observation_id":"7ea610a9-deb9-4e5a-a088-33f06114cfa6","resolution":{"observed_at":"2026-08-05T17:52:14.212817Z","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":"2026-08-05T17:52:14.274239Z","title":"A class of invariant consistent tests for multivariate normality","venue":null,"work_id":null,"year":1990},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:14.274239Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:025cea14d0e4764c44032974eef039a470002d6cb2fcc181c422d98e8780a3fe","observation_id":"fa4324ce-67e4-4d57-a137-fd3c082adb02","resolution":{"observed_at":"2026-08-05T17:52:14.274239Z","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":"2026-08-05T17:52:14.346695Z","title":"Test-time classifier adjustment module for model-agnostic domain generalization","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:14.346695Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:190dfd75baeead05e853eddd0afaf82fbe43c06864a67b3b125f112150c05c0a","observation_id":"397582c5-e774-42f2-a9fa-3d3c014ba65c","resolution":{"observed_at":"2026-08-05T17:52:14.346695Z","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":"2026-08-05T17:52:14.400485Z","title":"Transductive inference for text classification using support vector machines","venue":null,"work_id":null,"year":1999},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:14.400485Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:b2340f5c544f8e5371f35ea1168de42621fbfe4fa5d2c572843070bed381ec9b","observation_id":"2a20ae8d-6097-433a-a3f3-2cbdcb2afe22","resolution":{"observed_at":"2026-08-05T17:52:14.400485Z","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":"2026-08-05T17:52:14.491451Z","title":"Label propagation for zero-shot classification with vision-language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:14.491451Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:362057595df4762ba9ad3029b79886f51ba4804bab87c0f529e08982a959c9a9","observation_id":"569e8fe7-5169-4eb3-8de1-eac3ef82e9f0","resolution":{"observed_at":"2026-08-05T17:52:14.491451Z","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":"2026-08-05T17:52:14.542686Z","title":"Efficient test-time adaptation of vision-language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:14.542686Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:15b19d70122ac33834a52f98de7a8969d04549749a0580e8bc005e36466c6a31","observation_id":"7ebc2282-a86a-4294-a74a-444d235bcc3f","resolution":{"observed_at":"2026-08-05T17:52:14.542686Z","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":"2026-08-05T17:52:14.589661Z","title":"3D Object Representations for Fine-Grained Categorization","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:14.589661Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:920843c9cc929b9228ebc8eee621f81229d46c42cfc807e5d3a405ebc83d3b53","observation_id":"81837e87-b5d0-4867-a0d5-99dd83e54e41","resolution":{"observed_at":"2026-08-05T17:52:14.589661Z","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":"2026-08-05T17:52:14.645034Z","title":"Estimation of the precision matrix of a singular wishart distribution and its application in high-dimensional data","venue":null,"work_id":null,"year":1906},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:14.645034Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:a00dad12cb8f358a9fe85c4e6c4c9cc5f15aa524cfb6143340eaf086632ec90f","observation_id":"fc0f9e89-3981-483e-9717-8224f5c8cac7","resolution":{"observed_at":"2026-08-05T17:52:14.645034Z","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":"2026-08-05T17:52:14.697746Z","title":"Ra-tta: Retrieval-augmented test-time adaptation for vision-language models","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:14.697746Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:ff4984e6c1644ecc5fb975bc83c14b7da348c416ae3cdbd2149a004272e16a98","observation_id":"7da17092-8ba0-4ebe-9071-75090ee8de85","resolution":{"observed_at":"2026-08-05T17:52:14.697746Z","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":"2026-08-05T17:52:14.756497Z","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:14.756497Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:c829875511d0b270fe8c59324d7a33660359aa8b3f302b9e405b29bdb82186d8","observation_id":"d0846674-d7c5-4538-890f-7f44c7df4faa","resolution":{"observed_at":"2026-08-05T17:52:14.756497Z","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":"2026-08-05T17:52:14.834082Z","title":"Align Before Fuse: Vision and Language Representation Learning with Momentum Distillation","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:14.834082Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:cacaba12981b6dd95fb1562e7095f13ea2e8a2c2c02b6e73cf18e9656a529728","observation_id":"0e1ea2d1-0263-4aab-9a9a-a59cdbabfb00","resolution":{"observed_at":"2026-08-05T17:52:14.834082Z","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":"2026-08-05T17:52:14.891564Z","title":"Using discriminant analysis for multi-class classification: an experimental investigation.Knowledge and information systems, 10:453–472, 2006","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:14.891564Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:b586d9f1451182e655c7436886cb87f877dcdb735219334bbd051b262d25dd13","observation_id":"7d37d181-df6a-43bd-8eff-2da847c72e74","resolution":{"observed_at":"2026-08-05T17:52:14.891564Z","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":"2026-08-05T17:52:14.948079Z","title":"Text and image are mutually beneficial: Enhancing training-free few-shot classification with clip","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:14.948079Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:fad5c4508c905a9726a72865ae83ff22d80b871c96f37d317ad37d32606f37e3","observation_id":"111fba3a-d99a-4450-8576-b5fdcb20ccfb","resolution":{"observed_at":"2026-08-05T17:52:14.948079Z","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":"2026-08-05T17:52:15.009926Z","title":"Efficient and context-aware label propagation for zero-/few-shot training-free adaptation of vision-language model","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:15.009926Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:dc65a3d8e95072973da94885ede6f33d4e87eeb88ef6f41310de1e025c9ec196","observation_id":"002f8c12-d5e0-4a28-934f-770d85ead807","resolution":{"observed_at":"2026-08-05T17:52:15.009926Z","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":"2026-08-05T17:52:15.050696Z","title":"Learning to propagate labels: Transductive propagation network for few-shot learning","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:15.050696Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:9a08b7141faf20ac722cb4f5d59216b25c8eb0e3d0f8e578748a7f2ce22e2d1a","observation_id":"aae444ed-16b2-4cba-b0c0-fa43a6968a8c","resolution":{"observed_at":"2026-08-05T17:52:15.050696Z","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":"2026-08-05T17:52:15.131836Z","title":"Swapprompt: Test-time prompt adaptation for vision-language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:15.131836Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:66b94e36e0411149f20212ec8a7039da41db4d20f4875a781f4c4c205a1d8bd4","observation_id":"4863d18e-ed57-4585-aa11-7ab230f5bdba","resolution":{"observed_at":"2026-08-05T17:52:15.131836Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1306.5151","last_updated":"2013-06-21T14:31:57Z","snapshot_observed_at":"2026-08-12T17:35:23.022229Z","submitted_at":"2013-06-21T14:31:57Z","title":"Fine-Grained Visual Classification of Aircraft","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1306.5151","snapshot_observed_at":"2026-08-05T17:52:15.245474Z","title":"Fine- Grained Visual Classification of Aircraft.arXiv preprint arXiv:1306.5151, 2013","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:15.245474Z"},"links":{"cited_paper":"/paper/1306.5151","citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:5b846e6c0edfe3363fbf4562a33a78de53ac333b4c4063f892513caa7fc22fd9","observation_id":"e93fba51-403d-48a0-ab30-f3aa4582f735","resolution":{"observed_at":"2026-08-05T17:52:15.245474Z","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":"2026-08-05T17:52:15.333446Z","title":"Test-time prompt tuning for zero-shot generalization in vision-language models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:15.333446Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:fb42da6cafda7ab403665d058efad26aee868b6f7a2235b16fc0f8c483b589dc","observation_id":"447bddbc-e365-46c2-b941-1a472b7151b5","resolution":{"observed_at":"2026-08-05T17:52:15.333446Z","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":"2026-08-05T17:52:19.926637Z","title":"Black-box test-time prompt tuning for vision-language models","venue":null,"work_id":"726795e9-b953-4b0f-a452-784e8ce30b8a","year":2025},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:15.412277Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:9fe7472e9bb6160f98126c85dfa4197ff98135281ea674432b65064fe965649d","observation_id":"ebe59501-a5dc-410e-b687-1d890056db51","resolution":{"observed_at":"2026-08-05T17:52:20.043522Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-05T17:52:19.700159Z","title":"A random-projection based test of gaussianity for stationary processes.Computational Statistics & Data Analysis, 75:124–141, 2014","venue":null,"work_id":"6ae02ed2-96fa-48fd-a3e4-feba942001be","year":2014},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:15.487612Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:32e521a3f9921291b72525db500b78045793b218439d4c9db6a33f66057e985f","observation_id":"1850004a-c0ca-42c3-b62a-361fd3934d3a","resolution":{"observed_at":"2026-08-05T17:52:19.791555Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-05T17:52:15.544339Z","title":"Automated Flower Classification over a Large Number of Classes","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:15.544339Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:30d2ecb15a4d74953c689d807b8aded9fa5768a52ef715834a22c691dfb6f23e","observation_id":"b46de9d6-7537-493b-8652-abd1f8ab5a81","resolution":{"observed_at":"2026-08-05T17:52:15.544339Z","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":"2026-08-05T17:52:15.600383Z","title":"Cats and Dogs","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:15.600383Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:fa9df784e157de636b17244aaa0556fecc3457ea21f025eec72bbb2825c7a5e9","observation_id":"e2874cb3-e58f-4d54-a276-4131a85998df","resolution":{"observed_at":"2026-08-05T17:52:15.600383Z","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":"2026-08-05T17:52:15.657162Z","title":"The matrix cookbook.Technical University of Denmark, 7(15):510, 2008","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:15.657162Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:563d81efef565a1cf4d0f8d97d4e5bcc6da341ba128c2abc97b4cf5dd2ced652","observation_id":"edecc1ae-dafc-41dd-b97f-bcac466f34a8","resolution":{"observed_at":"2026-08-05T17:52:15.657162Z","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":"2026-08-05T17:52:15.729984Z","title":"Learning transferable visual models from natural language supervision","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:15.729984Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:a41d10b97b3b4b567120c947894afa147a097875bbcca32a88cdc24f40e9d8d6","observation_id":"7d0f67cd-8566-42a9-85ac-b809310390d8","resolution":{"observed_at":"2026-08-05T17:52:15.729984Z","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":"2026-08-05T17:52:15.817022Z","title":"Do imagenet classifiers generalize to imagenet? InICML, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:15.817022Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:7254159c7e9e19de2a39ef22eb4e5f978182bb86ebab8e3b623aeea9d19c766b","observation_id":"ab303d02-910e-4206-a492-737a4d9f5e20","resolution":{"observed_at":"2026-08-05T17:52:15.817022Z","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":"2026-08-05T17:52:15.875442Z","title":"An extension of shapiro and wilk’s w test for normality to large samples","venue":null,"work_id":null,"year":1982},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:15.875442Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:1d1f11e432c05554da530c3b5941645abfe3b4bb27e169cb60b60217bd3ddcfc","observation_id":"6f84c52a-c69e-4cba-839c-822755393e11","resolution":{"observed_at":"2026-08-05T17:52:15.875442Z","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":"2026-08-05T17:52:15.968095Z","title":"Align your prompts: Test-time prompting with distribution alignment for zero-shot generalization","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:15.968095Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:b6a4561c70ccf3091643f50597dbd182579de14ea21fb2ced425655406cc4ec1","observation_id":"41539fea-444c-484d-abae-62906e86481a","resolution":{"observed_at":"2026-08-05T17:52:15.968095Z","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":"2026-08-05T17:52:16.003212Z","title":"An analysis of variance test for normality.Biometrika, 52(3):591– 611, 1965","venue":null,"work_id":null,"year":1965},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:16.003212Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:67e5fe0b72f3655b3801f3418273f920984ae4f8d34be9c86e5249653590d6d2","observation_id":"d839f897-7875-4b26-8910-aa7763776cb9","resolution":{"observed_at":"2026-08-05T17:52:16.003212Z","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":"2026-08-05T17:52:16.064041Z","title":"High-dimensional linear discriminant analysis classifier for spiked covariance model.Journal of Machine Learning Research, 21(112):1–24, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:16.064041Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:452ed63da64fa85bc0f477d347c7e2e56e5682cca305c4aa93203e5092b88155","observation_id":"f6b610c0-94f4-4320-8257-94b9d4f41f78","resolution":{"observed_at":"2026-08-05T17:52:16.064041Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1212.0402","last_updated":"2012-12-03T14:45:31Z","snapshot_observed_at":"2026-08-13T22:00:40.727122Z","submitted_at":"2012-12-03T14:45:31Z","title":"UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1212.0402","snapshot_observed_at":"2026-08-05T17:52:16.138204Z","title":"UCF101: A Dataset of 101 Human Actions Classes from Videos in the Wild.arXiv preprint arXiv:1212.0402, 2012","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:16.138204Z"},"links":{"cited_paper":"/paper/1212.0402","citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:f4d1411ba129a41771d42affe765fce66b5cb53647a29f5e5fbaa01f8d61b4d7","observation_id":"7206b777-a3b2-40e3-8f9d-7e2e864798aa","resolution":{"observed_at":"2026-08-05T17:52:16.138204Z","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":"2026-08-05T17:52:16.226694Z","title":"Just shift it: Test-time prototype shifting for zero-shot generalization with vision-language models","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:16.226694Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:ab79f1c191bc63c9758bb738e9b161ff3762c8847a2f8208a25e4e8603a258e4","observation_id":"07b41894-4c46-46a7-a4f4-e1efad15ab55","resolution":{"observed_at":"2026-08-05T17:52:16.226694Z","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":"2026-08-05T17:52:16.362852Z","title":"Sus-x: Training-free name-only transfer of vision-language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:16.362852Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:e7f53d57df3bf05f904768806bc5616485beac37abd389eb6c3107cd039b8728","observation_id":"e535d5c7-8b48-487f-ba52-ba8945c5ef9b","resolution":{"observed_at":"2026-08-05T17:52:16.362852Z","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":"2026-08-05T17:52:16.448902Z","title":"Discriminative gaussian process latent variable model for classification","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:16.448902Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:3106c6f840ef9d5b56d8cb02481192d80ec59013c444fd092ac6df1f31f924d4","observation_id":"162ff320-0092-479c-a30b-ecb1ddc0b4fd","resolution":{"observed_at":"2026-08-05T17:52:16.448902Z","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":"2026-08-05T17:52:16.512410Z","title":"Tent: Fully test-time adaptation by entropy minimization","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:16.512410Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:0ecbbeaff09533e17bdd023f091731bb2ff22a9f2d5da6a79a545c5f5e3d9d84","observation_id":"8887e1aa-7aea-42af-b276-489b2fe00b9c","resolution":{"observed_at":"2026-08-05T17:52:16.512410Z","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":"2026-08-05T17:52:16.587467Z","title":"Learning Robust Global Representations by Penalizing Local Rredictive Power","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:16.587467Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:2e9c2d60675c853d01b904db63ec9ae5e5bfbe0ad486a2fed4615f82e95814fc","observation_id":"5f555050-64ef-4ebe-80e8-5515718e6d20","resolution":{"observed_at":"2026-08-05T17:52:16.587467Z","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":"2026-08-05T17:52:16.647576Z","title":"A hard-to-beat baseline for training-free clip-based adaptation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:16.647576Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:fedae494e21c64f8dd000aae7852f40230ee8daf38fb87a76f0c28f3c7eb3d93","observation_id":"2ddeb9a1-8c32-4145-ad68-e8f0277f3b28","resolution":{"observed_at":"2026-08-05T17:52:16.647576Z","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":"2026-08-05T17:52:16.755925Z","title":"Is less more? exploring token condensation as training-free adaptation for clip","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:16.755925Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:efc01f035a4117569479605985610b2aac6a0a4350a8ff3ed5a481a5e7b1f63c","observation_id":"5257d646-075c-4e26-b9e5-de656dfbd317","resolution":{"observed_at":"2026-08-05T17:52:16.755925Z","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":"2026-08-05T17:52:16.825406Z","title":"Sun Database: Large-Scale Scene Recognition from Abbey to Zoo","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:16.825406Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:0523bc00f1f22b42b4ef874241048f8509d957cf0e71cfe7e7c0ce1028801564","observation_id":"a1689d06-8da2-4e84-bef0-fe47e69904f1","resolution":{"observed_at":"2026-08-05T17:52:16.825406Z","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":"2026-08-05T17:52:19.350849Z","title":"Dynaprompt: Dynamic test-time prompt tuning","venue":null,"work_id":"b3ef5140-4dc2-4006-8df2-cc179c6d6349","year":2025},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:16.894825Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:7f1feced129a7c708598523beedfcca85b6ab73bb6db3e9861dad84afb9b632e","observation_id":"97a306f0-a8dd-4e36-990a-2400e2777f1c","resolution":{"observed_at":"2026-08-05T17:52:19.449296Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-05T17:52:19.169074Z","title":"C-tpt: Calibrated test-time prompt tuning for vision-language models via text feature dispersion","venue":null,"work_id":"3a65f55f-cb4f-4933-af8c-44612962a5f9","year":2024},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:16.991674Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:bbb6efe30108e7dd0d896c50542384bb65fbc24039dd0da566a262a8572841ae","observation_id":"9dea127c-df4e-499f-a6df-aa24b25d14cd","resolution":{"observed_at":"2026-08-05T17:52:19.257320Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-05T17:52:17.068354Z","title":"Task residual for tuning vision- language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:17.068354Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:ebbc87157e04a44b3dbf24f184efb6f30da3c092a88be47d1510cf341bebfc73","observation_id":"6d269f3b-4654-4d03-88c0-a90b19c14e8b","resolution":{"observed_at":"2026-08-05T17:52:17.068354Z","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":"2026-08-05T17:52:17.159060Z","title":"On the test-time zero-shot generalization of vision- language models: Do we really need prompt learning? InCVPR, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:17.159060Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:f684c5bf666f266724e26fbf37a8b371083d9ed6020545a48125e27e2a180ee7","observation_id":"17b37dd4-4066-415b-99d8-c7e125ba85ff","resolution":{"observed_at":"2026-08-05T17:52:17.159060Z","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":"2026-08-05T17:52:17.230232Z","title":"Realistic test-time adaptation of vision-language models","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:17.230232Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:5d012e3126873e57dd517bfdef385758905f0580cdea0868bbaf7f2e54e994c5","observation_id":"123757ff-eb55-40aa-884a-d03ee22ff986","resolution":{"observed_at":"2026-08-05T17:52:17.230232Z","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":"2026-08-05T17:52:17.293413Z","title":"Boosting vision-language models with transduction","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:17.293413Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:e4a8d0df94b029e19bf7f2edceeea1a2968e8357b59ad716e02d09749bc6b79c","observation_id":"100871cc-205f-4ed6-a375-846a5ba4df64","resolution":{"observed_at":"2026-08-05T17:52:17.293413Z","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":"2026-08-05T17:52:17.383392Z","title":"Boosting vision-language models for histopathology classification: Predict all at once","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:17.383392Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:52cb6b15a58d751d746f15fe72161d6bbda91f1f3654314eb2cd10b3c54b7858","observation_id":"26a95091-b029-4fad-95d1-6b0033a7c385","resolution":{"observed_at":"2026-08-05T17:52:17.383392Z","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":"2026-08-05T17:52:17.455559Z","title":"Dual prototype evolving for test-time generalization of vision-language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:17.455559Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:6e4c029f4b077a5b2d06509064f0bdf97167a0c44cb77fba073756f55d8752e1","observation_id":"1388aee8-9ae9-4bb7-bc11-1804b6419dd0","resolution":{"observed_at":"2026-08-05T17:52:17.455559Z","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":"2026-08-05T17:52:17.514778Z","title":"Historical test-time prompt tuning for vision foundation models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:17.514778Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:7e08ac5c8989e4f0270e7370524e2567afd9538f4f6188c55e52b108b28b9079","observation_id":"a7185619-ab39-4a2b-bbb2-ef1394a06b9a","resolution":{"observed_at":"2026-08-05T17:52:17.514778Z","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":"2026-08-05T17:52:17.632482Z","title":"Tip-adapter: Training-free adaption of clip for few-shot classification","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:17.632482Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:1001199ce3116ca91dc29a78d618953ffffcee31c1b28b14741d2687679e3d7c","observation_id":"a441098c-0307-4936-b613-17a3bd923ea8","resolution":{"observed_at":"2026-08-05T17:52:17.632482Z","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":"2026-08-05T17:52:17.700628Z","title":"Boostadapter: Improving vision-language test-time adaptation via regional bootstrapping","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:17.700628Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:8aa36b939e180cfc40f7085cae5fd94065281978f6f8b6c9362973fd1e8c39d4","observation_id":"2072ea5d-d3cd-4cc8-8b54-811bc62f03a5","resolution":{"observed_at":"2026-08-05T17:52:17.700628Z","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":"2026-08-05T17:52:17.835924Z","title":"Dual memory networks: A versatile adaptation approach for vision-language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:17.835924Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:39556851d4434ab7ee44ce8a1f3a6ea1dbf3ea1192fc0be8e267dc20b4346403","observation_id":"1e4bfd14-07bf-474f-96c3-435de18365a4","resolution":{"observed_at":"2026-08-05T17:52:17.835924Z","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":"2026-08-05T17:52:18.884245Z","title":"Dpcore: Dynamic prompt coreset for continual test-time adaptation","venue":null,"work_id":"c2fd9f5b-f63e-4b54-970c-097d6a53edb5","year":2025},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:17.936800Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:182e143933eb1e33aa4546c265df45a9f97fc9f64c9bcdc496eaf1afd7f0bf30","observation_id":"586308bb-695a-4ea3-a2cf-850e61b5d95b","resolution":{"observed_at":"2026-08-05T17:52:18.983845Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+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":"2026-08-05T17:52:18.010214Z","title":"Learning with local and global consistency","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:18.010214Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:3df7fa8ea1b4c5aae1263a9f26a48d7f38a84aeb26165bd1cc3bdf9c885cc3d0","observation_id":"8f350e15-dc50-41a7-a7e4-5e5f6ebd1af5","resolution":{"observed_at":"2026-08-05T17:52:18.010214Z","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":"2026-08-05T17:52:18.120894Z","title":"Bayesian test-time adaptation for vision-language models","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:18.120894Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:c12e5a640e3fc107b51102028d8e50189d98bda67376b120b1f2cecfc3f39172","observation_id":"13566bc7-d370-4ec6-af69-52eca2fe4c5f","resolution":{"observed_at":"2026-08-05T17:52:18.120894Z","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":"2026-08-05T17:52:18.198323Z","title":"Not all features matter: Enhancing few-shot clip with adaptive prior refinement","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:18.198323Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:7fa0609242d0de78d0a42a2084b072c8587ae54420d832a47427a0565e709f8e","observation_id":"1b20693e-c8d2-43db-863a-0bac02456020","resolution":{"observed_at":"2026-08-05T17:52:18.198323Z","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":"2026-08-05T17:52:18.261191Z","title":"Enhancing zero-shot vision models by label-free prompt distribution learning and bias correcting","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:18.261191Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:6641edd0d51a35c3b11ce289dc112b37ff1ee2e866a1c051441c7822b7baaf02","observation_id":"ad3c4893-6e91-4d85-9ca4-fb9ba612295c","resolution":{"observed_at":"2026-08-05T17:52:18.261191Z","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":"2026-08-05T17:52:18.337167Z","title":"Awt: Transferring vision-language models via augmentation, weighting, and transportation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:18.337167Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:7c86f91cd3ff8c807ab504caf192edb7abb39ccc79b23cb7f872187543b6e092","observation_id":"e6ad9063-e25b-4256-a825-1de392764050","resolution":{"observed_at":"2026-08-05T17:52:18.337167Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.05775","last_updated":"2024-08-11T13:55:58Z","snapshot_observed_at":"2026-08-12T23:05:21.391640Z","submitted_at":"2024-08-11T13:55:58Z","title":"Efficient Test-Time Prompt Tuning for Vision-Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.05775","snapshot_observed_at":"2026-08-05T17:52:18.399067Z","title":"Efficient test-time prompt tuning for vision-language models.arXiv preprint arXiv:2408.05775, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:18.399067Z"},"links":{"cited_paper":"/paper/2408.05775","citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:d95cb1f3c748a50dffa235931537f58b19944a29e8c05b356ea37da00761678b","observation_id":"ae1a233a-76b0-4f27-baf7-e907078da5bf","resolution":{"observed_at":"2026-08-05T17:52:18.399067Z","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":"2026-08-05T17:52:18.464538Z","title":"Laplacian regularized few-shot learning","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-05T17:52:18.464538Z"},"links":{"citing_paper":"/paper/2508.15567"},"observation_digest":"sha256:9d6812d4e273b213ef80cfa2913c986ab72296f3c794d49da64ff7dcd6fc7d9e","observation_id":"49710201-58b1-4500-89fe-2dc538b7a1aa","resolution":{"observed_at":"2026-08-05T17:52:18.464538Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2508.15567","last_updated":"2025-08-21T13:41:21Z","latest_version":1,"primary_category":"stat.ME","snapshot_observed_at":"2026-08-09T03:07:22.224313Z","submitted_at":"2025-08-21T13:41:21Z","title":"Clustering-based aggregate value regression"},"reference_resolution":{"displayed":74,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":68,"verified_exact":0,"verified_fuzzy":5},"total_outbound_references":74},"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":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"thesis":"As of 14 August 2026, this Paper Citation Record lists 74 of 74 outbound references and 0 inbound Pith citation observations for arXiv:2508.15567."}