{"as_of":"2026-08-08T10:10:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:749b99c5548aade3a1a6b16f7e457ad5296db994ed759388242104e5797a17c5","coverage":[{"denominator":28,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":28,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-04T19:13:53.999580Z","state":"measured"},{"denominator":28,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":28,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+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/2509.09397/citation-record","integrity":"/paper/2509.09397/integrity","json":"/paper/2509.09397/citation-record.json","paper":"/paper/2509.09397"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:13:52.571134Z","title":"Which clinical decisions benefit from automation? a task complexity approach.International journal of medical infor- matics, 70(2-3):309–316, 2003","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2509.09397","last_updated":"2025-09-11T12:26:57Z","snapshot_observed_at":"2026-08-06T23:32:44.797789Z","submitted_at":"2025-09-11T12:26:57Z","title":"Decoupling Clinical and Class-Agnostic Features for Reliable Few-Shot Adaptation under Shift","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-04T19:13:52.571134Z"},"links":{"citing_paper":"/paper/2509.09397"},"observation_digest":"sha256:1c416ed7157fd20da92e5b15ea21ebf149eeafee06d20c4cf47e63e6c00638b1","observation_id":"d2ef3b6a-bbb3-46a2-a619-8ec3e8ba497c","resolution":{"observed_at":"2026-08-04T19:13:52.571134Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:13:52.627993Z","title":"Mrishift: Disentangled repre- sentation learning for 3d mri lesion segmentation under distributional shifts","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.09397","last_updated":"2025-09-11T12:26:57Z","snapshot_observed_at":"2026-08-06T23:32:44.797789Z","submitted_at":"2025-09-11T12:26:57Z","title":"Decoupling Clinical and Class-Agnostic Features for Reliable Few-Shot Adaptation under Shift","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-04T19:13:52.627993Z"},"links":{"citing_paper":"/paper/2509.09397"},"observation_digest":"sha256:ebd4a7b0830124788fb7f22257b3ad348bb3280c1a56229c2f3cb4f0a92281cd","observation_id":"94b96d06-7d0d-4ca0-89a1-67d4ba2bd9c3","resolution":{"observed_at":"2026-08-04T19:13:52.627993Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:13:52.664986Z","title":"Heterogeneity in systematic reviews of medical imaging diagnos- tic test accuracy studies: a systematic review.JAMA Network Open, 7(2):e240649– e240649, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.09397","last_updated":"2025-09-11T12:26:57Z","snapshot_observed_at":"2026-08-06T23:32:44.797789Z","submitted_at":"2025-09-11T12:26:57Z","title":"Decoupling Clinical and Class-Agnostic Features for Reliable Few-Shot Adaptation under Shift","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-04T19:13:52.664986Z"},"links":{"citing_paper":"/paper/2509.09397"},"observation_digest":"sha256:817879cf7354d5e17da4663e44938046fe1eeeddfd7197e8bf8d2992e047bd39","observation_id":"e1220fc0-d259-44a8-91df-fe1424f7864f","resolution":{"observed_at":"2026-08-04T19:13:52.664986Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:13:52.718487Z","title":"Reducing reliance on spurious features in medical image clas- sification with spatial specificity","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.09397","last_updated":"2025-09-11T12:26:57Z","snapshot_observed_at":"2026-08-06T23:32:44.797789Z","submitted_at":"2025-09-11T12:26:57Z","title":"Decoupling Clinical and Class-Agnostic Features for Reliable Few-Shot Adaptation under Shift","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-04T19:13:52.718487Z"},"links":{"citing_paper":"/paper/2509.09397"},"observation_digest":"sha256:bf726f8b607ccdd0b4040cbd06744947c8ba6a28a80f04f1cb198673416e5b52","observation_id":"be0e2605-dfe6-478e-9e5c-32ddf3de6809","resolution":{"observed_at":"2026-08-04T19:13:52.718487Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:13:52.775748Z","title":"When more is less: Incorporating additional datasets can hurt performance by introducing spuri- ous correlations","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.09397","last_updated":"2025-09-11T12:26:57Z","snapshot_observed_at":"2026-08-06T23:32:44.797789Z","submitted_at":"2025-09-11T12:26:57Z","title":"Decoupling Clinical and Class-Agnostic Features for Reliable Few-Shot Adaptation under Shift","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-04T19:13:52.775748Z"},"links":{"citing_paper":"/paper/2509.09397"},"observation_digest":"sha256:5d45858f4feae07d6b25ea79c1b3d239f4405bd04609bdba1d7742c36458c0ed","observation_id":"2a5b3f60-7283-4ada-a1da-7d7eaca1cb1a","resolution":{"observed_at":"2026-08-04T19:13:52.775748Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:13:52.820745Z","title":"Maple: Multi-modal prompt learning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.09397","last_updated":"2025-09-11T12:26:57Z","snapshot_observed_at":"2026-08-06T23:32:44.797789Z","submitted_at":"2025-09-11T12:26:57Z","title":"Decoupling Clinical and Class-Agnostic Features for Reliable Few-Shot Adaptation under Shift","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-04T19:13:52.820745Z"},"links":{"citing_paper":"/paper/2509.09397"},"observation_digest":"sha256:0919bb3bf879ad762fb8186a7abd9e275d0f4093e9cd20a68f0f53999468b1c0","observation_id":"22a22c7f-e8ee-4e65-a1a9-04b165ea2982","resolution":{"observed_at":"2026-08-04T19:13:52.820745Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:13:52.908830Z","title":"Conditional prompt learning for vision-language models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.09397","last_updated":"2025-09-11T12:26:57Z","snapshot_observed_at":"2026-08-06T23:32:44.797789Z","submitted_at":"2025-09-11T12:26:57Z","title":"Decoupling Clinical and Class-Agnostic Features for Reliable Few-Shot Adaptation under Shift","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-04T19:13:52.908830Z"},"links":{"citing_paper":"/paper/2509.09397"},"observation_digest":"sha256:203865d26e3b2d75e6472d72f992606b9f5869392978c81d6fd963fa402571ab","observation_id":"f17e0dc3-165c-4b21-bca4-bc5e20aa1112","resolution":{"observed_at":"2026-08-04T19:13:52.908830Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:13:52.937052Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.09397","last_updated":"2025-09-11T12:26:57Z","snapshot_observed_at":"2026-08-06T23:32:44.797789Z","submitted_at":"2025-09-11T12:26:57Z","title":"Decoupling Clinical and Class-Agnostic Features for Reliable Few-Shot Adaptation under Shift","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-04T19:13:52.937052Z"},"links":{"citing_paper":"/paper/2509.09397"},"observation_digest":"sha256:f61d79b9f00c493a3b3bcaf20fd07873f97d04cb518fe786c8748cd6adc7e327","observation_id":"cab37c37-4854-4111-a92b-b79ae20163e1","resolution":{"observed_at":"2026-08-04T19:13:52.937052Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.21237","last_updated":"2025-06-26T13:22:44Z","snapshot_observed_at":"2026-08-06T23:32:06.437151Z","submitted_at":"2025-06-26T13:22:44Z","title":"DiMPLe -- Disentangled Multi-Modal Prompt Learning: Enhancing Out-Of-Distribution Alignment with Invariant and Spurious Feature Separation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.21237","snapshot_observed_at":"2026-08-04T19:13:52.989408Z","title":"Dimple– disentangled multi-modal prompt learning: Enhancing out-of-distribution align- ment with invariant and spurious feature separation.arXiv preprint arXiv:2506.21237, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.09397","last_updated":"2025-09-11T12:26:57Z","snapshot_observed_at":"2026-08-06T23:32:44.797789Z","submitted_at":"2025-09-11T12:26:57Z","title":"Decoupling Clinical and Class-Agnostic Features for Reliable Few-Shot Adaptation under Shift","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-04T19:13:52.989408Z"},"links":{"cited_paper":"/paper/2506.21237","citing_paper":"/paper/2509.09397"},"observation_digest":"sha256:8dda9d5cef34e54733386555c43ef06a28650d7ada45f1e12a388d4dd6478b0e","observation_id":"3ac69a89-2b67-4ddc-87df-f7039fc74251","resolution":{"observed_at":"2026-08-04T19:13:52.989408Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:13:53.069878Z","title":"Lora: Low-rank adaptation of large language models.ICLR, 1(2):3, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.09397","last_updated":"2025-09-11T12:26:57Z","snapshot_observed_at":"2026-08-06T23:32:44.797789Z","submitted_at":"2025-09-11T12:26:57Z","title":"Decoupling Clinical and Class-Agnostic Features for Reliable Few-Shot Adaptation under Shift","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-04T19:13:53.069878Z"},"links":{"citing_paper":"/paper/2509.09397"},"observation_digest":"sha256:e1ac0a255df42a9dbf6de7f17691b7ae202493f85efb798f1496d50503694ebf","observation_id":"4a9ce373-a1b8-4edb-870e-730266f1b871","resolution":{"observed_at":"2026-08-04T19:13:53.069878Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.15913","last_updated":"2024-07-22T17:59:19Z","snapshot_observed_at":"2026-08-07T22:58:28.837265Z","submitted_at":"2024-07-22T17:59:19Z","title":"Test-Time Low Rank Adaptation via Confidence Maximization for Zero-Shot Generalization of Vision-Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.15913","snapshot_observed_at":"2026-08-04T19:13:53.096712Z","title":"Test- time low rank adaptation via confidence maximization for zero-shot generalization of vision-language models.arXiv preprint arXiv:2407.15913, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.09397","last_updated":"2025-09-11T12:26:57Z","snapshot_observed_at":"2026-08-06T23:32:44.797789Z","submitted_at":"2025-09-11T12:26:57Z","title":"Decoupling Clinical and Class-Agnostic Features for Reliable Few-Shot Adaptation under Shift","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-04T19:13:53.096712Z"},"links":{"cited_paper":"/paper/2407.15913","citing_paper":"/paper/2509.09397"},"observation_digest":"sha256:4c313d844aa69d1fde9ef8f8b4d2d9f551b32362945f346966116cdd3a80e775","observation_id":"ba47d356-c6b4-4432-8844-38e8a2f1617f","resolution":{"observed_at":"2026-08-04T19:13:53.096712Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:13:53.158548Z","title":"A compre- hensive and easy-to-use multi-domain multi-task medical imaging meta-dataset (medimeta).arXiv preprint arXiv:2404.16000, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.09397","last_updated":"2025-09-11T12:26:57Z","snapshot_observed_at":"2026-08-06T23:32:44.797789Z","submitted_at":"2025-09-11T12:26:57Z","title":"Decoupling Clinical and Class-Agnostic Features for Reliable Few-Shot Adaptation under Shift","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-04T19:13:53.158548Z"},"links":{"citing_paper":"/paper/2509.09397"},"observation_digest":"sha256:cdf3f1e5c197fd4a811b8b014bb6cee1983aea5c24ca0530ac8a40ba34c4c97a","observation_id":"04d31e52-84f6-4345-8d39-d0f23ecdcba7","resolution":{"observed_at":"2026-08-04T19:13:53.158548Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:13:53.212106Z","title":"Instructblip: Towards general-purpose vision-language models with instruction tuning, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.09397","last_updated":"2025-09-11T12:26:57Z","snapshot_observed_at":"2026-08-06T23:32:44.797789Z","submitted_at":"2025-09-11T12:26:57Z","title":"Decoupling Clinical and Class-Agnostic Features for Reliable Few-Shot Adaptation under Shift","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-04T19:13:53.212106Z"},"links":{"citing_paper":"/paper/2509.09397"},"observation_digest":"sha256:152e9e5858b2e353d5b5b93427d60c68be71f56b6c692239c7aa2dd52a3e48ed","observation_id":"c628535b-bfbe-4ecb-859d-319f2aa6cfb1","resolution":{"observed_at":"2026-08-04T19:13:53.212106Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:13:53.255050Z","title":"Domain generalization on medical imaging classification us- ing episodic training with task augmentation.Computers in biology and medicine, 141:105144, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.09397","last_updated":"2025-09-11T12:26:57Z","snapshot_observed_at":"2026-08-06T23:32:44.797789Z","submitted_at":"2025-09-11T12:26:57Z","title":"Decoupling Clinical and Class-Agnostic Features for Reliable Few-Shot Adaptation under Shift","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-04T19:13:53.255050Z"},"links":{"citing_paper":"/paper/2509.09397"},"observation_digest":"sha256:b596f03a38e77c1e47f414bc3495868fd9b4e7147e0dcd767448ac3174f4832b","observation_id":"39726994-4cd7-458e-b778-73ec0bf94460","resolution":{"observed_at":"2026-08-04T19:13:53.255050Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:13:53.325265Z","title":"Domain generalization for medical image analysis: A review.Proceedings of the IEEE, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.09397","last_updated":"2025-09-11T12:26:57Z","snapshot_observed_at":"2026-08-06T23:32:44.797789Z","submitted_at":"2025-09-11T12:26:57Z","title":"Decoupling Clinical and Class-Agnostic Features for Reliable Few-Shot Adaptation under Shift","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-04T19:13:53.325265Z"},"links":{"citing_paper":"/paper/2509.09397"},"observation_digest":"sha256:5d4421a646cd04658d27cd3505c6815dd6cf9e045a0adcc870873faf4d3832ad","observation_id":"cef7add1-cf50-4abc-a47e-1020a1edf5f9","resolution":{"observed_at":"2026-08-04T19:13:53.325265Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:13:53.391545Z","title":"Evaluation of do- main generalization and adaptation on improving model robustness to temporal dataset shift in clinical medicine.Scientific reports, 12(1):2726, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.09397","last_updated":"2025-09-11T12:26:57Z","snapshot_observed_at":"2026-08-06T23:32:44.797789Z","submitted_at":"2025-09-11T12:26:57Z","title":"Decoupling Clinical and Class-Agnostic Features for Reliable Few-Shot Adaptation under Shift","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-04T19:13:53.391545Z"},"links":{"citing_paper":"/paper/2509.09397"},"observation_digest":"sha256:26cc1bea6deae75c3ddaa12490ecf3e42fcd7bdda0d1a69ccc9e3aee8bc01fa5","observation_id":"75eeebd3-1868-4175-b3ab-050d9403b5f8","resolution":{"observed_at":"2026-08-04T19:13:53.391545Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:13:53.445730Z","title":"Few-shot adaptation of medical vision-language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.09397","last_updated":"2025-09-11T12:26:57Z","snapshot_observed_at":"2026-08-06T23:32:44.797789Z","submitted_at":"2025-09-11T12:26:57Z","title":"Decoupling Clinical and Class-Agnostic Features for Reliable Few-Shot Adaptation under Shift","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-04T19:13:53.445730Z"},"links":{"citing_paper":"/paper/2509.09397"},"observation_digest":"sha256:c9eb9dd7b767665316746a776ca1212f861304abd9df514caeae284cd2500ab4","observation_id":"de57c975-87d4-4139-8636-3ffb3fee07af","resolution":{"observed_at":"2026-08-04T19:13:53.445730Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:13:53.506124Z","title":"Clipath: Fine-tune clip with visual feature fusion for pathology image analysis towards minimizing data collection efforts","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.09397","last_updated":"2025-09-11T12:26:57Z","snapshot_observed_at":"2026-08-06T23:32:44.797789Z","submitted_at":"2025-09-11T12:26:57Z","title":"Decoupling Clinical and Class-Agnostic Features for Reliable Few-Shot Adaptation under Shift","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-04T19:13:53.506124Z"},"links":{"citing_paper":"/paper/2509.09397"},"observation_digest":"sha256:edf03d208a38f0987fe4f9dc017d63e6814ff836d83288dbc8be26c4e03d52f0","observation_id":"a125acd7-5904-43d5-a980-32f63418ba42","resolution":{"observed_at":"2026-08-04T19:13:53.506124Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.06019","last_updated":"2025-02-09T20:25:42Z","snapshot_observed_at":"2026-08-07T22:52:51.228267Z","submitted_at":"2025-02-09T20:25:42Z","title":"Noise is an Efficient Learner for Zero-Shot Vision-Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.06019","snapshot_observed_at":"2026-08-04T19:13:53.548210Z","title":"Noise is an efficient learner for zero-shot vision- language models.arXiv preprint arXiv:2502.06019, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.09397","last_updated":"2025-09-11T12:26:57Z","snapshot_observed_at":"2026-08-06T23:32:44.797789Z","submitted_at":"2025-09-11T12:26:57Z","title":"Decoupling Clinical and Class-Agnostic Features for Reliable Few-Shot Adaptation under Shift","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-04T19:13:53.548210Z"},"links":{"cited_paper":"/paper/2502.06019","citing_paper":"/paper/2509.09397"},"observation_digest":"sha256:17e5d8b5cf66cf0023606d6a853c61fa03fefa96666ec3c11fc87e4e9001e685","observation_id":"75b0ab1b-a219-4e23-b106-cf629ad64b23","resolution":{"observed_at":"2026-08-04T19:13:53.548210Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.02729","last_updated":"2025-03-29T19:44:22Z","snapshot_observed_at":"2026-08-05T09:56:00.355325Z","submitted_at":"2024-09-03T09:25:51Z","title":"Can language-guided unsupervised adaptation improve medical image classification using unpaired images and texts?","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.02729","snapshot_observed_at":"2026-08-04T19:13:53.616300Z","title":"Meduna: Language guided unsupervised adaptation of vision-language models for medical image classification.arXiv preprint arXiv:2409.02729, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.09397","last_updated":"2025-09-11T12:26:57Z","snapshot_observed_at":"2026-08-06T23:32:44.797789Z","submitted_at":"2025-09-11T12:26:57Z","title":"Decoupling Clinical and Class-Agnostic Features for Reliable Few-Shot Adaptation under Shift","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-04T19:13:53.616300Z"},"links":{"cited_paper":"/paper/2409.02729","citing_paper":"/paper/2509.09397"},"observation_digest":"sha256:a15f1e03a19d95ff11ac86792f4e4e32918a420e43a9a2895de39466273823fd","observation_id":"679573e5-d99e-4fb4-b9fd-524c6bab16ae","resolution":{"observed_at":"2026-08-04T19:13:53.616300Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:13:53.680069Z","title":"Learning disentangled representations in the imaging domain.Medical Image Analysis, 80:102516, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.09397","last_updated":"2025-09-11T12:26:57Z","snapshot_observed_at":"2026-08-06T23:32:44.797789Z","submitted_at":"2025-09-11T12:26:57Z","title":"Decoupling Clinical and Class-Agnostic Features for Reliable Few-Shot Adaptation under Shift","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-04T19:13:53.680069Z"},"links":{"citing_paper":"/paper/2509.09397"},"observation_digest":"sha256:5ceb28cc0312e5a2e9a5acf754e3e5e49d5a86be9deaa3fc93d44de5851582e3","observation_id":"b1c41123-ea04-4c22-8683-14ed050814c6","resolution":{"observed_at":"2026-08-04T19:13:53.680069Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:13:53.703004Z","title":"Domain adaptation and generalization of func- tional medical data: A systematic survey of brain data.ACM Computing Surveys, 56(10):1–39, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.09397","last_updated":"2025-09-11T12:26:57Z","snapshot_observed_at":"2026-08-06T23:32:44.797789Z","submitted_at":"2025-09-11T12:26:57Z","title":"Decoupling Clinical and Class-Agnostic Features for Reliable Few-Shot Adaptation under Shift","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-04T19:13:53.703004Z"},"links":{"citing_paper":"/paper/2509.09397"},"observation_digest":"sha256:11a680c33b6cdb68fb3e52106eb005be412fddae520723cfdd87478f2b364d0c","observation_id":"a2c998d6-3e7c-4a55-b6ca-655d63b7dbfd","resolution":{"observed_at":"2026-08-04T19:13:53.703004Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:13:53.783153Z","title":"Shenzhen hospital chest x-ray (cxr) set","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.09397","last_updated":"2025-09-11T12:26:57Z","snapshot_observed_at":"2026-08-06T23:32:44.797789Z","submitted_at":"2025-09-11T12:26:57Z","title":"Decoupling Clinical and Class-Agnostic Features for Reliable Few-Shot Adaptation under Shift","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-04T19:13:53.783153Z"},"links":{"citing_paper":"/paper/2509.09397"},"observation_digest":"sha256:0f029762a08ffed2f6095fa99dcf7c000fa3125e4a83ec4570e99529ece1420b","observation_id":"d155842b-f9c6-4e2e-a984-66af8963b8ad","resolution":{"observed_at":"2026-08-04T19:13:53.783153Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:13:53.834724Z","title":"Montgomery county chest x-ray (cxr) set","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.09397","last_updated":"2025-09-11T12:26:57Z","snapshot_observed_at":"2026-08-06T23:32:44.797789Z","submitted_at":"2025-09-11T12:26:57Z","title":"Decoupling Clinical and Class-Agnostic Features for Reliable Few-Shot Adaptation under Shift","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-04T19:13:53.834724Z"},"links":{"citing_paper":"/paper/2509.09397"},"observation_digest":"sha256:b802752259769bd93a622a9302e6168664a710c8c7375978112c2e57d7c44d39","observation_id":"e9932e46-75ce-46e7-a75a-44bedbb0d046","resolution":{"observed_at":"2026-08-04T19:13:53.834724Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:13:53.851286Z","title":"Indian diabetic retinopathy image dataset (idrid): a database for diabetic retinopathy screening research.Data, 3(3):25, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.09397","last_updated":"2025-09-11T12:26:57Z","snapshot_observed_at":"2026-08-06T23:32:44.797789Z","submitted_at":"2025-09-11T12:26:57Z","title":"Decoupling Clinical and Class-Agnostic Features for Reliable Few-Shot Adaptation under Shift","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-04T19:13:53.851286Z"},"links":{"citing_paper":"/paper/2509.09397"},"observation_digest":"sha256:f2fd145bbbe0afb9484e15130b4038c0368dd62dff25cc3a6eec64b726d3f4a2","observation_id":"3e991736-34ca-4520-89e7-52b56c2d3554","resolution":{"observed_at":"2026-08-04T19:13:53.851286Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:13:53.895236Z","title":"Isic archive: International skin imaging collaboration dataset","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.09397","last_updated":"2025-09-11T12:26:57Z","snapshot_observed_at":"2026-08-06T23:32:44.797789Z","submitted_at":"2025-09-11T12:26:57Z","title":"Decoupling Clinical and Class-Agnostic Features for Reliable Few-Shot Adaptation under Shift","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-04T19:13:53.895236Z"},"links":{"citing_paper":"/paper/2509.09397"},"observation_digest":"sha256:8b0a91f9aeb0468c8958efffa1b349e34343a21648d69836d8796d77b7b68124","observation_id":"4d17bacb-01f6-4d8b-8db9-192ac34ae85c","resolution":{"observed_at":"2026-08-04T19:13:53.895236Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.15425","last_updated":"2025-05-23T14:16:48Z","snapshot_observed_at":"2026-08-07T22:40:50.453721Z","submitted_at":"2025-05-21T12:08:31Z","title":"On the Robustness of Medical Vision-Language Models: Are they Truly Generalizable?","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.15425","snapshot_observed_at":"2026-08-04T19:13:53.947203Z","title":"On the robustness of medical vision-language models: Are they truly generalizable?arXiv preprint arXiv:2505.15425, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.09397","last_updated":"2025-09-11T12:26:57Z","snapshot_observed_at":"2026-08-06T23:32:44.797789Z","submitted_at":"2025-09-11T12:26:57Z","title":"Decoupling Clinical and Class-Agnostic Features for Reliable Few-Shot Adaptation under Shift","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-04T19:13:53.947203Z"},"links":{"cited_paper":"/paper/2505.15425","citing_paper":"/paper/2509.09397"},"observation_digest":"sha256:52ab256e7ad112da2e698fd1901812a6319bb471c923c810bea8c1f84be7055d","observation_id":"e131d344-9f9e-46f7-9fe1-dff80d68d595","resolution":{"observed_at":"2026-08-04T19:13:53.947203Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:13:53.999580Z","title":"Amend to alignment: Decoupled prompt tuning for mitigating spuri- ous correlation in vision-language models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.09397","last_updated":"2025-09-11T12:26:57Z","snapshot_observed_at":"2026-08-06T23:32:44.797789Z","submitted_at":"2025-09-11T12:26:57Z","title":"Decoupling Clinical and Class-Agnostic Features for Reliable Few-Shot Adaptation under Shift","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-04T19:13:53.999580Z"},"links":{"citing_paper":"/paper/2509.09397"},"observation_digest":"sha256:3d396ec67bf9d88c09ebabed8ce4b16810ceae98f0e80e11118ff201344be68f","observation_id":"934cb6e0-dfa0-4025-8f0c-af7ee47b0b31","resolution":{"observed_at":"2026-08-04T19:13:53.999580Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2509.09397","last_updated":"2025-09-11T12:26:57Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-06T23:32:44.797789Z","submitted_at":"2025-09-11T12:26:57Z","title":"Decoupling Clinical and Class-Agnostic Features for Reliable Few-Shot Adaptation under Shift"},"reference_resolution":{"displayed":28,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":28,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":28},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 28 of 28 outbound references and 0 inbound Pith citation observations for arXiv:2509.09397."}