{"as_of":"2026-08-08T04:06:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:611455d5141ac26bb38806fe90f4564c7bbba6af7839e55cf7798563d927c1b6","coverage":[{"denominator":55,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":55,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-28T15:28:21.303268Z","state":"measured"},{"denominator":55,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":55,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+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/2606.02079/citation-record","integrity":"/paper/2606.02079/integrity","json":"/paper/2606.02079/citation-record.json","paper":"/paper/2606.02079"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T15:28:21.303268Z","title":"Bridging the gap between pre-training and fine-tuning for end-to-end speech translation,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2606.02079","last_updated":"2026-06-01T11:08:31Z","snapshot_observed_at":"2026-08-02T15:24:15.565847Z","submitted_at":"2026-06-01T11:08:31Z","title":"FACT: A Simple and Efficient Framework for Active Finetuning","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-06-28T15:28:21.303268Z"},"links":{"citing_paper":"/paper/2606.02079"},"observation_digest":"sha256:805d1fef6b5402060b3f356beceb3e8928c4bf2f249c45a0b78b66e2c28b1f12","observation_id":"ffb049f7-e18b-42bf-bbf0-3467819d65ae","resolution":{"observed_at":"2026-06-28T15:28:21.303268Z","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":"2026-06-28T15:28:21.303268Z","title":"Code: contrastive pre-training with adversarial fine-tuning for zero-shot expert linking,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.02079","last_updated":"2026-06-01T11:08:31Z","snapshot_observed_at":"2026-08-02T15:24:15.565847Z","submitted_at":"2026-06-01T11:08:31Z","title":"FACT: A Simple and Efficient Framework for Active Finetuning","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-06-28T15:28:21.303268Z"},"links":{"citing_paper":"/paper/2606.02079"},"observation_digest":"sha256:31781ff835399ad07c6d928ae909f036ca9eb6614a015b806f13a67da2187420","observation_id":"f4786e8c-77dc-4018-8518-9575cd268523","resolution":{"observed_at":"2026-06-28T15:28:21.303268Z","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":"2026-06-28T15:28:21.303268Z","title":"Equi-tuning: Group equivariant fine-tuning of pretrained models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.02079","last_updated":"2026-06-01T11:08:31Z","snapshot_observed_at":"2026-08-02T15:24:15.565847Z","submitted_at":"2026-06-01T11:08:31Z","title":"FACT: A Simple and Efficient Framework for Active Finetuning","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-06-28T15:28:21.303268Z"},"links":{"citing_paper":"/paper/2606.02079"},"observation_digest":"sha256:2e248d541287b43b4452d40e7b5bef39fbd271ba9ffdbf476ad6d3c5cbc33d5d","observation_id":"07fd75b0-5fc8-4b2f-8717-920e91f92d4a","resolution":{"observed_at":"2026-06-28T15:28:21.303268Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.02719","last_updated":"2026-04-07T06:07:49Z","snapshot_observed_at":"2026-08-02T14:15:42.685513Z","submitted_at":"2023-07-06T01:57:37Z","title":"Understanding Uncertainty Sampling via Equivalent Loss","version":4},"cited_work":{"arxiv_id":"2307.02719","doi":null,"metadata_source":"pith","pith_arxiv_id":"2307.02719","snapshot_observed_at":"2026-07-01T22:16:17.176281Z","title":"Understanding Uncertainty Sampling via Equivalent Loss","venue":"cs.LG","work_id":"fbf2300c-1cb9-4fe9-81aa-43e85a09f06f","year":2023},"citing_paper":{"arxiv_id":"2606.02079","last_updated":"2026-06-01T11:08:31Z","snapshot_observed_at":"2026-08-02T15:24:15.565847Z","submitted_at":"2026-06-01T11:08:31Z","title":"FACT: A Simple and Efficient Framework for Active Finetuning","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-06-28T15:28:21.303268Z"},"links":{"cited_paper":"/paper/2307.02719","citing_paper":"/paper/2606.02079"},"observation_digest":"sha256:9a8fafb4399ddb8c9e0ba4d7f41f3cd0dff25063142bec3666c3aba6e7e1ef59","observation_id":"c02c945c-9d55-4173-9cf4-c916f08d76d7","resolution":{"observed_at":"2026-07-01T22:16:17.177728Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-06-28T15:28:21.303268Z","title":"Learning loss for active learning,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2606.02079","last_updated":"2026-06-01T11:08:31Z","snapshot_observed_at":"2026-08-02T15:24:15.565847Z","submitted_at":"2026-06-01T11:08:31Z","title":"FACT: A Simple and Efficient Framework for Active Finetuning","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-06-28T15:28:21.303268Z"},"links":{"citing_paper":"/paper/2606.02079"},"observation_digest":"sha256:ddb0ced51e920b88d004e1eac43f35a2a1aa89114b381bf9440c25a16b64a319","observation_id":"0101283b-54b2-4000-b271-a51cdba13e81","resolution":{"observed_at":"2026-06-28T15:28:21.303268Z","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":"2026-06-28T15:28:21.303268Z","title":"Deep batch active learning by diverse, uncertain gradient lower bounds,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2606.02079","last_updated":"2026-06-01T11:08:31Z","snapshot_observed_at":"2026-08-02T15:24:15.565847Z","submitted_at":"2026-06-01T11:08:31Z","title":"FACT: A Simple and Efficient Framework for Active Finetuning","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-06-28T15:28:21.303268Z"},"links":{"citing_paper":"/paper/2606.02079"},"observation_digest":"sha256:a433264d1a354cfd839de0c184194ad94fc097a6b4e34eac395a5201a1bb28f2","observation_id":"d1c55536-96a1-46eb-b81a-2bfd1304cfd5","resolution":{"observed_at":"2026-06-28T15:28:21.303268Z","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":"2026-06-28T15:28:21.303268Z","title":"Task-aware variational adversarial active learning,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2606.02079","last_updated":"2026-06-01T11:08:31Z","snapshot_observed_at":"2026-08-02T15:24:15.565847Z","submitted_at":"2026-06-01T11:08:31Z","title":"FACT: A Simple and Efficient Framework for Active Finetuning","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-06-28T15:28:21.303268Z"},"links":{"citing_paper":"/paper/2606.02079"},"observation_digest":"sha256:4fc87c464a43f29fc5e08e6ef5e8ce7129d49006f937ee4636ae3800e3ebfc48","observation_id":"d25d0d3e-db9d-4b5e-ac08-742b9db302c6","resolution":{"observed_at":"2026-06-28T15:28:21.303268Z","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":"2026-06-28T15:28:21.303268Z","title":"Active learning by feature mixing,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.02079","last_updated":"2026-06-01T11:08:31Z","snapshot_observed_at":"2026-08-02T15:24:15.565847Z","submitted_at":"2026-06-01T11:08:31Z","title":"FACT: A Simple and Efficient Framework for Active Finetuning","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-06-28T15:28:21.303268Z"},"links":{"citing_paper":"/paper/2606.02079"},"observation_digest":"sha256:5f756b0a3662fa0e7b9ad05573ed08ab3af5c7610d79405661a1bbde5a5167da","observation_id":"4da1c96e-3988-4e89-84b7-8582106830a5","resolution":{"observed_at":"2026-06-28T15:28:21.303268Z","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":"2026-06-28T15:28:21.303268Z","title":"Deep active learning with noise stability,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.02079","last_updated":"2026-06-01T11:08:31Z","snapshot_observed_at":"2026-08-02T15:24:15.565847Z","submitted_at":"2026-06-01T11:08:31Z","title":"FACT: A Simple and Efficient Framework for Active Finetuning","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-06-28T15:28:21.303268Z"},"links":{"citing_paper":"/paper/2606.02079"},"observation_digest":"sha256:cbb97fd3120624ad2760495221a9db1684e8d933b7ebd311890509a654d0900c","observation_id":"fc6fc095-42d0-4252-bbc8-04169d02a3ed","resolution":{"observed_at":"2026-06-28T15:28:21.303268Z","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":"2026-06-28T15:28:21.303268Z","title":"Re- ducing label effort: Self-supervised meets active learning,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2606.02079","last_updated":"2026-06-01T11:08:31Z","snapshot_observed_at":"2026-08-02T15:24:15.565847Z","submitted_at":"2026-06-01T11:08:31Z","title":"FACT: A Simple and Efficient Framework for Active Finetuning","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-06-28T15:28:21.303268Z"},"links":{"citing_paper":"/paper/2606.02079"},"observation_digest":"sha256:44ccff7ac31af961e028ba36098cf07cd860d6be2d017a9289a0c219a6270dde","observation_id":"7366bfd0-b498-4535-919a-95c36e596335","resolution":{"observed_at":"2026-06-28T15:28:21.303268Z","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":"2026-06-28T15:28:21.303268Z","title":"Active finetuning: Exploiting annotation budget in the pretraining-finetuning paradigm,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.02079","last_updated":"2026-06-01T11:08:31Z","snapshot_observed_at":"2026-08-02T15:24:15.565847Z","submitted_at":"2026-06-01T11:08:31Z","title":"FACT: A Simple and Efficient Framework for Active Finetuning","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-06-28T15:28:21.303268Z"},"links":{"citing_paper":"/paper/2606.02079"},"observation_digest":"sha256:74a370fcedf73aaa356d16629cc5cd6733d7ed1ac1bb4c084e3eaad631e8a4b7","observation_id":"687a74fa-4826-4f5c-ac37-757e6fc8c6df","resolution":{"observed_at":"2026-06-28T15:28:21.303268Z","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":"2026-06-28T15:28:21.303268Z","title":"Activedc: Distribution calibration for active finetuning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.02079","last_updated":"2026-06-01T11:08:31Z","snapshot_observed_at":"2026-08-02T15:24:15.565847Z","submitted_at":"2026-06-01T11:08:31Z","title":"FACT: A Simple and Efficient Framework for Active Finetuning","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-06-28T15:28:21.303268Z"},"links":{"citing_paper":"/paper/2606.02079"},"observation_digest":"sha256:17fb5f22287767b2d8697388a3c808347b7775b421551169b2fb6e09c5811b06","observation_id":"f487a267-c6c8-48e0-84a8-9cce8c6f0d5c","resolution":{"observed_at":"2026-06-28T15:28:21.303268Z","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":"2026-06-28T15:28:21.303268Z","title":"Boundary matters: A bi-level active finetuning method,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.02079","last_updated":"2026-06-01T11:08:31Z","snapshot_observed_at":"2026-08-02T15:24:15.565847Z","submitted_at":"2026-06-01T11:08:31Z","title":"FACT: A Simple and Efficient Framework for Active Finetuning","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-06-28T15:28:21.303268Z"},"links":{"citing_paper":"/paper/2606.02079"},"observation_digest":"sha256:a7d319f19b8eda09dea68b1046f5ed83f7af776c1331996a050718180c09f17f","observation_id":"5b3eb848-42d1-41b7-a9b7-5a5ef9d55670","resolution":{"observed_at":"2026-06-28T15:28:21.303268Z","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":"2026-06-28T15:28:21.303268Z","title":"Vecaf: Vision-language collaborative active finetuning with training objective awareness,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.02079","last_updated":"2026-06-01T11:08:31Z","snapshot_observed_at":"2026-08-02T15:24:15.565847Z","submitted_at":"2026-06-01T11:08:31Z","title":"FACT: A Simple and Efficient Framework for Active Finetuning","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-06-28T15:28:21.303268Z"},"links":{"citing_paper":"/paper/2606.02079"},"observation_digest":"sha256:8c97794db883cb7471fa9817032d0cecb4eb20f9a102513f0e1040cc2ae0c7f3","observation_id":"a921f9e1-52ec-4caa-8b88-4d301fb1c5f8","resolution":{"observed_at":"2026-06-28T15:28:21.303268Z","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":"2026-06-28T15:28:21.303268Z","title":"Fine-tuning can distort pretrained features and underperform out-of- distribution,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.02079","last_updated":"2026-06-01T11:08:31Z","snapshot_observed_at":"2026-08-02T15:24:15.565847Z","submitted_at":"2026-06-01T11:08:31Z","title":"FACT: A Simple and Efficient Framework for Active Finetuning","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-06-28T15:28:21.303268Z"},"links":{"citing_paper":"/paper/2606.02079"},"observation_digest":"sha256:e934dab73f0e1b49dd07ec286cb31cdf538838d19ea4da4412451c8a5dc50413","observation_id":"2796a49d-6ccb-43b8-98e8-3fd14c2a3850","resolution":{"observed_at":"2026-06-28T15:28:21.303268Z","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":"2026-06-28T15:28:21.303268Z","title":"Revisit finetuning strategy for few-shot learning to transfer the emdeddings,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.02079","last_updated":"2026-06-01T11:08:31Z","snapshot_observed_at":"2026-08-02T15:24:15.565847Z","submitted_at":"2026-06-01T11:08:31Z","title":"FACT: A Simple and Efficient Framework for Active Finetuning","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-06-28T15:28:21.303268Z"},"links":{"citing_paper":"/paper/2606.02079"},"observation_digest":"sha256:337d69f4d6bba524a726eb6b5f706bb53ab9bfca80650a6872ebf6f9f206c36e","observation_id":"ca41aa67-aaa4-44c4-a656-6ba665ef9525","resolution":{"observed_at":"2026-06-28T15:28:21.303268Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.08096","last_updated":"2025-02-11T18:25:07Z","snapshot_observed_at":"2026-07-06T17:29:13.310354Z","submitted_at":"2024-02-12T22:32:12Z","title":"An Efficient Rehearsal Scheme for Catastrophic Forgetting Mitigation during Multi-stage Fine-tuning","version":3},"cited_work":{"arxiv_id":"2402.08096","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2402.08096","snapshot_observed_at":"2026-07-01T22:16:17.169082Z","title":"InFindings of the Asso- ciation for Computational Linguistics: EMNLP 2024, pages 17167–17186","venue":null,"work_id":"8aaded80-f0bf-4faa-8bab-6b74227dd7bc","year":2024},"citing_paper":{"arxiv_id":"2606.02079","last_updated":"2026-06-01T11:08:31Z","snapshot_observed_at":"2026-08-02T15:24:15.565847Z","submitted_at":"2026-06-01T11:08:31Z","title":"FACT: A Simple and Efficient Framework for Active Finetuning","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-06-28T15:28:21.303268Z"},"links":{"cited_paper":"/paper/2402.08096","citing_paper":"/paper/2606.02079"},"observation_digest":"sha256:4b3f33c282a03bdbd70b47597f05bdeb34e7db660cf6044faf2a888d10f49b4c","observation_id":"ae4bc505-b9cd-4d1b-8cbc-9f3d15b62613","resolution":{"observed_at":"2026-07-01T22:16:17.171887Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-06-28T15:28:21.303268Z","title":"Deep neural networks for high dimension, low sample size data","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2606.02079","last_updated":"2026-06-01T11:08:31Z","snapshot_observed_at":"2026-08-02T15:24:15.565847Z","submitted_at":"2026-06-01T11:08:31Z","title":"FACT: A Simple and Efficient Framework for Active Finetuning","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-06-28T15:28:21.303268Z"},"links":{"citing_paper":"/paper/2606.02079"},"observation_digest":"sha256:161fa1930993574e6810cd4eb1fba59a97ce5a81e5b6d587c4086557582a60b0","observation_id":"4e853147-90d8-4c38-bb3c-ab5063820111","resolution":{"observed_at":"2026-06-28T15:28:21.303268Z","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":"2026-06-28T15:28:21.303268Z","title":"Pushing the limits of simple pipelines for few-shot learning: External data and fine- tuning make a difference,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.02079","last_updated":"2026-06-01T11:08:31Z","snapshot_observed_at":"2026-08-02T15:24:15.565847Z","submitted_at":"2026-06-01T11:08:31Z","title":"FACT: A Simple and Efficient Framework for Active Finetuning","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-06-28T15:28:21.303268Z"},"links":{"citing_paper":"/paper/2606.02079"},"observation_digest":"sha256:bb32874b3ba363e85d62fb52fd70e7f658d8941f4b63c69af9a8d84666e9f9a7","observation_id":"6735241b-a6bb-48f8-a41c-7f17db6a5267","resolution":{"observed_at":"2026-06-28T15:28:21.303268Z","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":"2026-06-28T15:28:21.303268Z","title":"Active learning on a budget: Opposite strategies suit high and low budgets,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.02079","last_updated":"2026-06-01T11:08:31Z","snapshot_observed_at":"2026-08-02T15:24:15.565847Z","submitted_at":"2026-06-01T11:08:31Z","title":"FACT: A Simple and Efficient Framework for Active Finetuning","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-06-28T15:28:21.303268Z"},"links":{"citing_paper":"/paper/2606.02079"},"observation_digest":"sha256:0527a9d1e73ad7285b38d3718ecf8ed115d9b8365db44ae59691412b7e4f5e79","observation_id":"84e8ef2f-a60e-4b20-9d52-6191296c4e10","resolution":{"observed_at":"2026-06-28T15:28:21.303268Z","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":"2026-06-28T15:28:21.303268Z","title":"Learning transferable visual models from natural language supervision,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2606.02079","last_updated":"2026-06-01T11:08:31Z","snapshot_observed_at":"2026-08-02T15:24:15.565847Z","submitted_at":"2026-06-01T11:08:31Z","title":"FACT: A Simple and Efficient Framework for Active Finetuning","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-06-28T15:28:21.303268Z"},"links":{"citing_paper":"/paper/2606.02079"},"observation_digest":"sha256:1f5ff06a85bfbca0c4d01e5b6b31f04042d395bb22900932939acbd2eeb03579","observation_id":"561028df-8141-44f1-9986-82633b0bfe15","resolution":{"observed_at":"2026-06-28T15:28:21.303268Z","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":"2026-06-28T15:28:21.303268Z","title":"Blip-2: Bootstrapping language- image pre-training with frozen image encoders and large language models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.02079","last_updated":"2026-06-01T11:08:31Z","snapshot_observed_at":"2026-08-02T15:24:15.565847Z","submitted_at":"2026-06-01T11:08:31Z","title":"FACT: A Simple and Efficient Framework for Active Finetuning","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-06-28T15:28:21.303268Z"},"links":{"citing_paper":"/paper/2606.02079"},"observation_digest":"sha256:8997e51480e49c3ca781b6755672a1f9720aa593930ab353acf830d99419aadc","observation_id":"c06a9335-210e-4a9d-a18f-de4a269633a0","resolution":{"observed_at":"2026-06-28T15:28:21.303268Z","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":"2026-06-28T15:28:21.303268Z","title":"An image is worth 16x16 words: Trans- formers for image recognition at scale,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2606.02079","last_updated":"2026-06-01T11:08:31Z","snapshot_observed_at":"2026-08-02T15:24:15.565847Z","submitted_at":"2026-06-01T11:08:31Z","title":"FACT: A Simple and Efficient Framework for Active Finetuning","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-06-28T15:28:21.303268Z"},"links":{"citing_paper":"/paper/2606.02079"},"observation_digest":"sha256:119e395db38d7a0e40c8c8e278e08dc6e4e7c5ef9194eb8cb959d0aa95d48842","observation_id":"b50dfa44-b1e5-4a12-ae20-a5be4e1572eb","resolution":{"observed_at":"2026-06-28T15:28:21.303268Z","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":"2026-06-28T15:28:21.303268Z","title":"Training data-efficient image transformers & distillation through attention,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2606.02079","last_updated":"2026-06-01T11:08:31Z","snapshot_observed_at":"2026-08-02T15:24:15.565847Z","submitted_at":"2026-06-01T11:08:31Z","title":"FACT: A Simple and Efficient Framework for Active Finetuning","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-06-28T15:28:21.303268Z"},"links":{"citing_paper":"/paper/2606.02079"},"observation_digest":"sha256:ae4f81770e1b8f68658d0913092fcac4315c123c2577b0f5bc7aaa10f99d2a8b","observation_id":"b0149390-8a1a-428f-8171-d5c39d13b649","resolution":{"observed_at":"2026-06-28T15:28:21.303268Z","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":"2026-06-28T15:28:21.303268Z","title":"A convnet for the 2020s,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.02079","last_updated":"2026-06-01T11:08:31Z","snapshot_observed_at":"2026-08-02T15:24:15.565847Z","submitted_at":"2026-06-01T11:08:31Z","title":"FACT: A Simple and Efficient Framework for Active Finetuning","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-06-28T15:28:21.303268Z"},"links":{"citing_paper":"/paper/2606.02079"},"observation_digest":"sha256:f73eb2bf1ac9b7f906b58453b10d12634cba444637db82ed7399195e7bfd9df1","observation_id":"f352a3c8-b49d-46ad-b9d1-3f6f3a48e490","resolution":{"observed_at":"2026-06-28T15:28:21.303268Z","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":"2026-06-28T15:28:21.303268Z","title":"Vision-LSTM: xLSTM as generic vision backbone,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.02079","last_updated":"2026-06-01T11:08:31Z","snapshot_observed_at":"2026-08-02T15:24:15.565847Z","submitted_at":"2026-06-01T11:08:31Z","title":"FACT: A Simple and Efficient Framework for Active Finetuning","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-06-28T15:28:21.303268Z"},"links":{"citing_paper":"/paper/2606.02079"},"observation_digest":"sha256:29f32b41e80be10f71f3b0dcf27bd5e2d9fc0420f293c3edfb3aa1b0170514b6","observation_id":"198fe951-87c4-4541-8dc3-5c62f23a7e5b","resolution":{"observed_at":"2026-06-28T15:28:21.303268Z","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":"2026-06-28T15:28:21.303268Z","title":"A closer look at few-shot classification,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2606.02079","last_updated":"2026-06-01T11:08:31Z","snapshot_observed_at":"2026-08-02T15:24:15.565847Z","submitted_at":"2026-06-01T11:08:31Z","title":"FACT: A Simple and Efficient Framework for Active Finetuning","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-06-28T15:28:21.303268Z"},"links":{"citing_paper":"/paper/2606.02079"},"observation_digest":"sha256:d2b6970200c8c4b1d6825dc3bee65bc01815af9cbbf259c88bf9018f6c988a33","observation_id":"929331ef-197b-47a2-b8ca-d1743f9dfaf0","resolution":{"observed_at":"2026-06-28T15:28:21.303268Z","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":"2026-06-28T15:28:21.303268Z","title":"Charting the right manifold: Manifold mixup for few-shot learning,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2606.02079","last_updated":"2026-06-01T11:08:31Z","snapshot_observed_at":"2026-08-02T15:24:15.565847Z","submitted_at":"2026-06-01T11:08:31Z","title":"FACT: A Simple and Efficient Framework for Active Finetuning","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-06-28T15:28:21.303268Z"},"links":{"citing_paper":"/paper/2606.02079"},"observation_digest":"sha256:3d0a25030b73cd1935548be8e4450b0910244a92a979e0a14c51ad37ae448acb","observation_id":"43ac43c1-586f-4d16-8959-68b75c616de7","resolution":{"observed_at":"2026-06-28T15:28:21.303268Z","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":"2026-06-28T15:28:21.303268Z","title":"Autoaug- ment: Learning augmentation strategies from data,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2606.02079","last_updated":"2026-06-01T11:08:31Z","snapshot_observed_at":"2026-08-02T15:24:15.565847Z","submitted_at":"2026-06-01T11:08:31Z","title":"FACT: A Simple and Efficient Framework for Active Finetuning","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-06-28T15:28:21.303268Z"},"links":{"citing_paper":"/paper/2606.02079"},"observation_digest":"sha256:ccd346df6a14ef6b85a2140e6fda587dd7218bc7773f06b480f45437bf48a701","observation_id":"c564cdbd-26e1-4df9-a6fb-497db77f8b3d","resolution":{"observed_at":"2026-06-28T15:28:21.303268Z","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":"2026-06-28T15:28:21.303268Z","title":"Trivialaugment: Tuning-free yet state-of- the-art data augmentation,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2606.02079","last_updated":"2026-06-01T11:08:31Z","snapshot_observed_at":"2026-08-02T15:24:15.565847Z","submitted_at":"2026-06-01T11:08:31Z","title":"FACT: A Simple and Efficient Framework for Active Finetuning","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-06-28T15:28:21.303268Z"},"links":{"citing_paper":"/paper/2606.02079"},"observation_digest":"sha256:4f2286b8198a10c0e9e13439084dc705eb8c3b21f12ecc3eebcb4e1105546379","observation_id":"4b3463e6-1c46-4b39-8653-172eb3c0a818","resolution":{"observed_at":"2026-06-28T15:28:21.303268Z","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":"2026-06-28T15:28:21.303268Z","title":"Partial is better than all: Revisiting fine-tuning strategy for few-shot learning,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2606.02079","last_updated":"2026-06-01T11:08:31Z","snapshot_observed_at":"2026-08-02T15:24:15.565847Z","submitted_at":"2026-06-01T11:08:31Z","title":"FACT: A Simple and Efficient Framework for Active Finetuning","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-06-28T15:28:21.303268Z"},"links":{"citing_paper":"/paper/2606.02079"},"observation_digest":"sha256:4a6f5e53744f56386ae8e9759f6ec4a6d8a6833f9e94f2fd718bfedadbbc7961","observation_id":"c4e3d236-0520-4d4b-8bd9-a088ad0c1f66","resolution":{"observed_at":"2026-06-28T15:28:21.303268Z","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":"2026-06-28T15:28:21.303268Z","title":"LoRA+: Efficient low rank adaptation of large models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.02079","last_updated":"2026-06-01T11:08:31Z","snapshot_observed_at":"2026-08-02T15:24:15.565847Z","submitted_at":"2026-06-01T11:08:31Z","title":"FACT: A Simple and Efficient Framework for Active Finetuning","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-06-28T15:28:21.303268Z"},"links":{"citing_paper":"/paper/2606.02079"},"observation_digest":"sha256:d5f24c6cc1db1a0d6994da7cac5a02ed077e2b641282937e35e2a7ba026ffea1","observation_id":"ac2cf820-5124-45c6-b6d3-3008f44497e4","resolution":{"observed_at":"2026-06-28T15:28:21.303268Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.05000","last_updated":"2024-07-16T07:32:23Z","snapshot_observed_at":"2026-07-06T18:42:18.289966Z","submitted_at":"2024-07-06T08:37:21Z","title":"LoRA-GA: Low-Rank Adaptation with Gradient Approximation","version":2},"cited_work":{"arxiv_id":"2407.05000","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2407.05000","snapshot_observed_at":"2026-07-04T08:19:44.421796Z","title":"Alex Warstadt, Amanpreet Singh, and Samuel R","venue":null,"work_id":"9650afce-8dba-4f1b-ba1f-5fb2041799ae","year":2024},"citing_paper":{"arxiv_id":"2606.02079","last_updated":"2026-06-01T11:08:31Z","snapshot_observed_at":"2026-08-02T15:24:15.565847Z","submitted_at":"2026-06-01T11:08:31Z","title":"FACT: A Simple and Efficient Framework for Active Finetuning","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-06-28T15:28:21.303268Z"},"links":{"cited_paper":"/paper/2407.05000","citing_paper":"/paper/2606.02079"},"observation_digest":"sha256:7d3bbf96b1b241f081c11e69e1b11b9d907d3970412283279faa4477a87b968d","observation_id":"423cf796-4eea-400a-9c21-d5e6ad618682","resolution":{"observed_at":"2026-07-01T22:16:17.174886Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-06-28T15:28:21.303268Z","title":"Qlora: Efficient finetuning of quantized llms,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.02079","last_updated":"2026-06-01T11:08:31Z","snapshot_observed_at":"2026-08-02T15:24:15.565847Z","submitted_at":"2026-06-01T11:08:31Z","title":"FACT: A Simple and Efficient Framework for Active Finetuning","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-06-28T15:28:21.303268Z"},"links":{"citing_paper":"/paper/2606.02079"},"observation_digest":"sha256:73f53fc40cbce18b3a55a04a68aa7a5804acb1ff63d3893f5ce8bda58bc4ae61","observation_id":"7368ac41-449d-484b-a490-d9d9478950c4","resolution":{"observed_at":"2026-06-28T15:28:21.303268Z","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":"2026-06-28T15:28:21.303268Z","title":"LoRA: Low-rank adaptation of large language models,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.02079","last_updated":"2026-06-01T11:08:31Z","snapshot_observed_at":"2026-08-02T15:24:15.565847Z","submitted_at":"2026-06-01T11:08:31Z","title":"FACT: A Simple and Efficient Framework for Active Finetuning","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-06-28T15:28:21.303268Z"},"links":{"citing_paper":"/paper/2606.02079"},"observation_digest":"sha256:34e2daa855e5fae9400f27fab7c61a437df799eb43efa9bcae6e519c3bb3015b","observation_id":"fae049c5-e9ce-4c71-b261-630c799350ca","resolution":{"observed_at":"2026-06-28T15:28:21.303268Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.14608","last_updated":"2024-09-16T02:54:50Z","snapshot_observed_at":"2026-08-04T09:07:42.158421Z","submitted_at":"2024-03-21T17:55:50Z","title":"Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey","version":7},"cited_work":{"arxiv_id":"2403.14608","doi":"10.3390/math12050746","metadata_source":"pith","pith_arxiv_id":"2403.14608","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey","venue":"cs.LG","work_id":"51ba0d2f-0aed-4d36-9376-9bb85fe70b81","year":2024},"citing_paper":{"arxiv_id":"2606.02079","last_updated":"2026-06-01T11:08:31Z","snapshot_observed_at":"2026-08-02T15:24:15.565847Z","submitted_at":"2026-06-01T11:08:31Z","title":"FACT: A Simple and Efficient Framework for Active Finetuning","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-06-28T15:28:21.303268Z"},"links":{"cited_paper":"/paper/2403.14608","citing_paper":"/paper/2606.02079"},"observation_digest":"sha256:71f8983a65f6868936e1640c09fce592d140c0f5b3be17cee2d992749438f9e3","observation_id":"106c3829-6139-4d35-9914-dc0605154560","resolution":{"observed_at":"2026-07-01T22:16:17.182888Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-06-28T15:28:21.303268Z","title":"Visual prompt tuning,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.02079","last_updated":"2026-06-01T11:08:31Z","snapshot_observed_at":"2026-08-02T15:24:15.565847Z","submitted_at":"2026-06-01T11:08:31Z","title":"FACT: A Simple and Efficient Framework for Active Finetuning","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-06-28T15:28:21.303268Z"},"links":{"citing_paper":"/paper/2606.02079"},"observation_digest":"sha256:2af77dad70fe8695fba234c42b5aa510b0eb8f6c5ce2097b3220bef8cae50b8a","observation_id":"9e2f5b80-f451-4ba0-9467-0be8ba2698b6","resolution":{"observed_at":"2026-06-28T15:28:21.303268Z","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":"2026-06-28T15:28:21.303268Z","title":"Prefix-tuning: Optimizing continuous prompts for generation,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2606.02079","last_updated":"2026-06-01T11:08:31Z","snapshot_observed_at":"2026-08-02T15:24:15.565847Z","submitted_at":"2026-06-01T11:08:31Z","title":"FACT: A Simple and Efficient Framework for Active Finetuning","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-06-28T15:28:21.303268Z"},"links":{"citing_paper":"/paper/2606.02079"},"observation_digest":"sha256:3f2ff751023ff9d1075721c647fd367342c2369d4d3f186f11fd2fe95e0fa207","observation_id":"81b32901-4464-4dd2-8d71-05fbc9978f5a","resolution":{"observed_at":"2026-06-28T15:28:21.303268Z","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":"2026-06-28T15:28:21.303268Z","title":"Parameter- efficient fine-tuning in spectral domain for point cloud learning,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.02079","last_updated":"2026-06-01T11:08:31Z","snapshot_observed_at":"2026-08-02T15:24:15.565847Z","submitted_at":"2026-06-01T11:08:31Z","title":"FACT: A Simple and Efficient Framework for Active Finetuning","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-06-28T15:28:21.303268Z"},"links":{"citing_paper":"/paper/2606.02079"},"observation_digest":"sha256:efe52cef634d8652ec1ed2b2e86b13750283f09c7bc3432b858511f249a73ed3","observation_id":"42059ced-bac1-4b1c-88f3-8681e389d2dd","resolution":{"observed_at":"2026-06-28T15:28:21.303268Z","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":"2026-06-28T15:28:21.303268Z","title":"Finetune like you pretrain: Improved finetuning of zero-shot vision models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.02079","last_updated":"2026-06-01T11:08:31Z","snapshot_observed_at":"2026-08-02T15:24:15.565847Z","submitted_at":"2026-06-01T11:08:31Z","title":"FACT: A Simple and Efficient Framework for Active Finetuning","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-06-28T15:28:21.303268Z"},"links":{"citing_paper":"/paper/2606.02079"},"observation_digest":"sha256:b6010eedf31db3482042fb66bf67f05fbaea6292c22b3c2384c869e04bc151af","observation_id":"8d5ea37f-c86e-4e96-a8bd-fbad18c4e313","resolution":{"observed_at":"2026-06-28T15:28:21.303268Z","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":"2026-06-28T15:28:21.303268Z","title":"Frozen feature augmentation for few-shot image classification,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.02079","last_updated":"2026-06-01T11:08:31Z","snapshot_observed_at":"2026-08-02T15:24:15.565847Z","submitted_at":"2026-06-01T11:08:31Z","title":"FACT: A Simple and Efficient Framework for Active Finetuning","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-06-28T15:28:21.303268Z"},"links":{"citing_paper":"/paper/2606.02079"},"observation_digest":"sha256:a3c62ae8f32f7319e9b6c291a3433d99328cebad725e473609d4c3834b5045b5","observation_id":"16edb30c-584d-464b-b988-f6e351765508","resolution":{"observed_at":"2026-06-28T15:28:21.303268Z","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":"2026-06-28T15:28:21.303268Z","title":"Big transfer (bit): General visual representation learning,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2606.02079","last_updated":"2026-06-01T11:08:31Z","snapshot_observed_at":"2026-08-02T15:24:15.565847Z","submitted_at":"2026-06-01T11:08:31Z","title":"FACT: A Simple and Efficient Framework for Active Finetuning","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-06-28T15:28:21.303268Z"},"links":{"citing_paper":"/paper/2606.02079"},"observation_digest":"sha256:e3bf2589d2db7896ae6d0c1540d3fd358183ddadf89ddf58fe574342f345b8e2","observation_id":"5c464315-76d9-43ad-aa80-7531e7f2bc59","resolution":{"observed_at":"2026-06-28T15:28:21.303268Z","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":"2026-06-28T15:28:21.303268Z","title":"Scaling vision transformers,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.02079","last_updated":"2026-06-01T11:08:31Z","snapshot_observed_at":"2026-08-02T15:24:15.565847Z","submitted_at":"2026-06-01T11:08:31Z","title":"FACT: A Simple and Efficient Framework for Active Finetuning","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-06-28T15:28:21.303268Z"},"links":{"citing_paper":"/paper/2606.02079"},"observation_digest":"sha256:4c761994910bc039ecfdf54c74163e0541ed5243f75ccf5576411c54092a9815","observation_id":"00b54c58-5688-45c4-b540-aacd8f8717ab","resolution":{"observed_at":"2026-06-28T15:28:21.303268Z","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":"2026-06-28T15:28:21.303268Z","title":"A progressive batching l-bfgs method for machine learning,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2606.02079","last_updated":"2026-06-01T11:08:31Z","snapshot_observed_at":"2026-08-02T15:24:15.565847Z","submitted_at":"2026-06-01T11:08:31Z","title":"FACT: A Simple and Efficient Framework for Active Finetuning","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-06-28T15:28:21.303268Z"},"links":{"citing_paper":"/paper/2606.02079"},"observation_digest":"sha256:94b507cff318e20bad9eefe6cafeac76bfaea88c5e044b29955a31686052c20f","observation_id":"76d2793f-79b8-461c-8d8c-9afc0e829f23","resolution":{"observed_at":"2026-06-28T15:28:21.303268Z","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":"2026-06-28T15:28:21.303268Z","title":"An accelerated linearly convergent stochastic l-bfgs algorithm,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2606.02079","last_updated":"2026-06-01T11:08:31Z","snapshot_observed_at":"2026-08-02T15:24:15.565847Z","submitted_at":"2026-06-01T11:08:31Z","title":"FACT: A Simple and Efficient Framework for Active Finetuning","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-06-28T15:28:21.303268Z"},"links":{"citing_paper":"/paper/2606.02079"},"observation_digest":"sha256:c207bf0e92217dc5f1c0ae2f2d631ebe345afee229f059c21bfcd675f4e1ba27","observation_id":"cd678768-4b2a-4b76-8387-d2ab92d9e1ce","resolution":{"observed_at":"2026-06-28T15:28:21.303268Z","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":"2026-06-28T15:28:21.303268Z","title":"Set trans- former: A framework for attention-based permutation-invariant neural networks,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2606.02079","last_updated":"2026-06-01T11:08:31Z","snapshot_observed_at":"2026-08-02T15:24:15.565847Z","submitted_at":"2026-06-01T11:08:31Z","title":"FACT: A Simple and Efficient Framework for Active Finetuning","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-06-28T15:28:21.303268Z"},"links":{"citing_paper":"/paper/2606.02079"},"observation_digest":"sha256:a0b7e0d03a6975fe7b63d68e4f78b7da043a25b012c48031e3c6543c322de741","observation_id":"32857315-201e-4f1b-bc9a-3ecc07fec5bb","resolution":{"observed_at":"2026-06-28T15:28:21.303268Z","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":"2026-06-28T15:28:21.303268Z","title":"Learning multiple layers of features from tiny images,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2606.02079","last_updated":"2026-06-01T11:08:31Z","snapshot_observed_at":"2026-08-02T15:24:15.565847Z","submitted_at":"2026-06-01T11:08:31Z","title":"FACT: A Simple and Efficient Framework for Active Finetuning","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-06-28T15:28:21.303268Z"},"links":{"citing_paper":"/paper/2606.02079"},"observation_digest":"sha256:2d399095ec285ab9d7313e0a00d585330e317f12ba35eab9f27a893e977fe569","observation_id":"6344d1d3-48e9-459c-b1c9-62c8ebf6dd1a","resolution":{"observed_at":"2026-06-28T15:28:21.303268Z","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":"2026-06-28T15:28:21.303268Z","title":"Imagenet large scale visual recognition challenge,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2606.02079","last_updated":"2026-06-01T11:08:31Z","snapshot_observed_at":"2026-08-02T15:24:15.565847Z","submitted_at":"2026-06-01T11:08:31Z","title":"FACT: A Simple and Efficient Framework for Active Finetuning","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-06-28T15:28:21.303268Z"},"links":{"citing_paper":"/paper/2606.02079"},"observation_digest":"sha256:bd05368608461a15ba7df2d548e26cb9cf221e716289263fae684ebab40c75d5","observation_id":"fd10b659-a306-457d-a2e4-5db056bbd0bd","resolution":{"observed_at":"2026-06-28T15:28:21.303268Z","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":"2026-06-28T15:28:21.303268Z","title":"Learning imbal- anced datasets with label-distribution-aware margin loss,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2606.02079","last_updated":"2026-06-01T11:08:31Z","snapshot_observed_at":"2026-08-02T15:24:15.565847Z","submitted_at":"2026-06-01T11:08:31Z","title":"FACT: A Simple and Efficient Framework for Active Finetuning","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-06-28T15:28:21.303268Z"},"links":{"citing_paper":"/paper/2606.02079"},"observation_digest":"sha256:08106168d3a1ac405b141bb85d7c03e18305a510c33973a72603bc363f954a09","observation_id":"2b6b7af4-0b13-4324-b7ee-e65d9aa7fffb","resolution":{"observed_at":"2026-06-28T15:28:21.303268Z","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":"2026-06-28T15:28:21.303268Z","title":"3d object representations for fine-grained categorization,","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2606.02079","last_updated":"2026-06-01T11:08:31Z","snapshot_observed_at":"2026-08-02T15:24:15.565847Z","submitted_at":"2026-06-01T11:08:31Z","title":"FACT: A Simple and Efficient Framework for Active Finetuning","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-06-28T15:28:21.303268Z"},"links":{"citing_paper":"/paper/2606.02079"},"observation_digest":"sha256:1292aa347f6bdd933c3796beba422f135ad1c642c92c2b9c06cf1dd1078fcd19","observation_id":"d4e33a71-5c7f-46d0-ac2e-2186a0b9f5cf","resolution":{"observed_at":"2026-06-28T15:28:21.303268Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1306.5151","last_updated":"2013-06-21T14:31:57Z","snapshot_observed_at":"2026-07-06T03:16:28.287173Z","submitted_at":"2013-06-21T14:31:57Z","title":"Fine-Grained Visual Classification of Aircraft","version":1},"cited_work":{"arxiv_id":"1306.5151","doi":null,"metadata_source":"pith","pith_arxiv_id":"1306.5151","snapshot_observed_at":"2026-07-11T03:07:53.092922Z","title":"Fine-Grained Visual Classification of Aircraft","venue":"cs.CV","work_id":"ed360110-3ce4-4959-8c74-1785cd9e537d","year":2013},"citing_paper":{"arxiv_id":"2606.02079","last_updated":"2026-06-01T11:08:31Z","snapshot_observed_at":"2026-08-02T15:24:15.565847Z","submitted_at":"2026-06-01T11:08:31Z","title":"FACT: A Simple and Efficient Framework for Active Finetuning","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-06-28T15:28:21.303268Z"},"links":{"cited_paper":"/paper/1306.5151","citing_paper":"/paper/2606.02079"},"observation_digest":"sha256:c853997c74534897049bd25bcfd9b9c336cfaa920d9370d70725a8d1fee262a8","observation_id":"d454a15a-ed30-4cca-8887-cda7a0127d0c","resolution":{"observed_at":"2026-07-01T22:16:17.180477Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-06-28T15:28:21.303268Z","title":"Emerging properties in self-supervised vision transformers,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2606.02079","last_updated":"2026-06-01T11:08:31Z","snapshot_observed_at":"2026-08-02T15:24:15.565847Z","submitted_at":"2026-06-01T11:08:31Z","title":"FACT: A Simple and Efficient Framework for Active Finetuning","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-06-28T15:28:21.303268Z"},"links":{"citing_paper":"/paper/2606.02079"},"observation_digest":"sha256:8592fe12024750c0a4c75c40630df69d626e7efdf926bb6e5cd001fad7ac8bca","observation_id":"a177237c-57ab-4b3e-9fc7-db5a0d1f509f","resolution":{"observed_at":"2026-06-28T15:28:21.303268Z","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":"2026-06-28T15:28:21.303268Z","title":"MMSegmentation: Openmmlab semantic seg- mentation toolbox and benchmark,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2606.02079","last_updated":"2026-06-01T11:08:31Z","snapshot_observed_at":"2026-08-02T15:24:15.565847Z","submitted_at":"2026-06-01T11:08:31Z","title":"FACT: A Simple and Efficient Framework for Active Finetuning","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-06-28T15:28:21.303268Z"},"links":{"citing_paper":"/paper/2606.02079"},"observation_digest":"sha256:60b9a1a8f79ff0006eb6f6cc2c658d36db4ffcf9c00c686c567f16fe8c147bbd","observation_id":"a02268c0-17af-409a-afb6-1346fa753543","resolution":{"observed_at":"2026-06-28T15:28:21.303268Z","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":"2026-06-28T15:28:21.303268Z","title":"Unified perceptual parsing for scene understanding,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2606.02079","last_updated":"2026-06-01T11:08:31Z","snapshot_observed_at":"2026-08-02T15:24:15.565847Z","submitted_at":"2026-06-01T11:08:31Z","title":"FACT: A Simple and Efficient Framework for Active Finetuning","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-06-28T15:28:21.303268Z"},"links":{"citing_paper":"/paper/2606.02079"},"observation_digest":"sha256:ec0f4324302a1754d796184b200a0f3b5b3aeaaa0e6fa1cdcc0a38b810161612","observation_id":"3757fafb-5299-4914-bf6b-f5fa5eaf5f75","resolution":{"observed_at":"2026-06-28T15:28:21.303268Z","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":"2026-06-28T15:28:21.303268Z","title":"Scene parsing through ade20k dataset,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2606.02079","last_updated":"2026-06-01T11:08:31Z","snapshot_observed_at":"2026-08-02T15:24:15.565847Z","submitted_at":"2026-06-01T11:08:31Z","title":"FACT: A Simple and Efficient Framework for Active Finetuning","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-06-28T15:28:21.303268Z"},"links":{"citing_paper":"/paper/2606.02079"},"observation_digest":"sha256:960ff9123dcb6e1422e1e982d80f6110e1e6ecfffd67e9e1a4eef2ba02ed2d69","observation_id":"c67f2f14-4227-4661-84eb-208b6be0a5ec","resolution":{"observed_at":"2026-06-28T15:28:21.303268Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2606.02079","last_updated":"2026-06-01T11:08:31Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-02T15:24:15.565847Z","submitted_at":"2026-06-01T11:08:31Z","title":"FACT: A Simple and Efficient Framework for Active Finetuning"},"reference_resolution":{"displayed":55,"state_counts":{"malformed_identifier":0,"metadata_mismatch":2,"parse_uncertain":0,"unresolved":50,"verified_exact":3,"verified_fuzzy":0},"total_outbound_references":55},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 55 of 55 outbound references and 0 inbound Pith citation observations for arXiv:2606.02079."}