{"as_of":"2026-08-24T00:20:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:72363312f5099ef1b4566de38f1294b5b0bfa327113cf3a11fa006b8860853f3","coverage":[{"denominator":84,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":84,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T10:51:38.118484Z","state":"measured"},{"denominator":84,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":84,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-23T06:30:58.430688+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/2412.16275/citation-record","integrity":"/paper/2412.16275/integrity","json":"/paper/2412.16275/citation-record.json","paper":"/paper/2412.16275"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:37.693087Z","title":"Unsupervised robust domain adaptation with- out source data","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:37.693087Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:0d54670238789c3b572db9f3921d3a7c0fa445f05a0f7809a56c25da9f36cdfc","observation_id":"c92ff85c-ba5b-467f-b0e4-40b2b2e5a426","resolution":{"observed_at":"2026-08-11T10:51:37.693087Z","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":"2026-08-11T10:51:37.699035Z","title":"Com- positional mixture representations for vision and text","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:37.699035Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:b4b45f7089438f0f11aff3676bf439e5c5f85530d45d01c3c72ff20a3a394f68","observation_id":"0a166639-bfec-4a3d-b7ad-2c458dbbde6f","resolution":{"observed_at":"2026-08-11T10:51:37.699035Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2008.12284","last_updated":"2020-08-28T03:48:50Z","snapshot_observed_at":"2026-08-13T02:50:10.164953Z","submitted_at":"2020-08-27T17:41:34Z","title":"learn2learn: A Library for Meta-Learning Research","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2008.12284","snapshot_observed_at":"2026-08-11T10:51:37.704614Z","title":null,"venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:37.704614Z"},"links":{"cited_paper":"/paper/2008.12284","citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:59f6d036ca3ce63095ecab7469ccc7ffc4e5a427081ecd83767692eeb4a05ce8","observation_id":"92c2ef20-1274-4262-9003-efa1c1b27c25","resolution":{"observed_at":"2026-08-11T10:51:37.704614Z","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":"2026-08-11T10:51:37.709957Z","title":"Reed, Roei Herzig, Gal Chechik, Anna Rohrbach, Trevor Darrell, and Amir Globerson","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:37.709957Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:36124ab2bf6744e2ea23a2ca71e44f7565c3cf2ceece9c548016e33042f51235","observation_id":"0164af2d-7a17-44d6-b787-113db08cbc5a","resolution":{"observed_at":"2026-08-11T10:51:37.709957Z","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":"2026-08-11T10:51:37.715397Z","title":"Is space-time attention all you need for video understanding? In ICML, pages 813–824, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:37.715397Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:f34626fcb3d3cafee60065beb8b4c4b66a1d5c418bc64229c2eb4463254799fa","observation_id":"d2ca56c9-2790-463e-8ed2-b961cf7f0b4b","resolution":{"observed_at":"2026-08-11T10:51:37.715397Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:39.440976Z","title":"Swimming pool and car detec- tion","venue":null,"work_id":"fa8ece29-55c2-4b88-b8c3-4b88a9e54dd5","year":null},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:37.720879Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:cf97a2955e2c491c8d3443884686d02dcc6398147aedd8d02d72c0ebeec1e587","observation_id":"3896b21c-df4f-447e-ac76-1c329092daf0","resolution":{"observed_at":"2026-08-11T10:51:39.446136Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:39.425449Z","title":"Few-shot video classification via tem- poral alignment","venue":null,"work_id":"cbadce8e-8b87-4d35-a0f7-1efd87a05479","year":2020},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:37.726002Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:6272310a25fa397d67f36aaad3f2ba7987b5c68b6fb3293b2ea896c381abdca7","observation_id":"24a40244-94b2-46e4-8efc-00790c323663","resolution":{"observed_at":"2026-08-11T10:51:39.430759Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:39.410306Z","title":"Unsupervised learn- ing of visual features by contrasting cluster assignments","venue":null,"work_id":"47a7d54f-0078-4e91-8754-e4d8283e332c","year":2020},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:37.731446Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:47c9b5c38a50648213f25f5c83cca953c61aaba2d856337b58bd91cfb4dfe5f2","observation_id":"d206dccb-435c-4c84-9209-ad67b0272891","resolution":{"observed_at":"2026-08-11T10:51:39.415282Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:39.396544Z","title":"Emerg- ing properties in self-supervised vision transformers","venue":null,"work_id":"c4aa17b0-d564-4b57-9935-97b6deebe0c1","year":2021},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:37.736211Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:ea165a7e2a2abb679bdbd94e36b5d8efd7d5582fb631806edd0471a0a7900251","observation_id":"242d0e15-0c82-4bdb-90e8-93b21adea5c5","resolution":{"observed_at":"2026-08-11T10:51:39.401070Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:39.382740Z","title":"Fewshotqa: A sim- ple framework for few-shot learning of question answering tasks using pre-trained text-to-text models","venue":null,"work_id":"5c281c5a-8872-44e0-aaf1-52c55b480311","year":2021},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:37.740787Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:2c7193601fd3de10049649ce631efca5c2341c6ceec4c09103c1cda72ce9cfe7","observation_id":"944ec192-9886-42ed-88b3-16e74e9b679e","resolution":{"observed_at":"2026-08-11T10:51:39.387518Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:39.368293Z","title":"Meta-baseline: Exploring simple meta- learning for few-shot learning","venue":null,"work_id":"d2a12420-ee6e-4a94-a95a-47e83222bf4f","year":null},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:37.746650Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:be60f789394b840945bbe69cdb79cfcdbf40a231c016cfca4d445bb2921bfb32","observation_id":"c8091164-c5f9-425b-b6aa-83cd2987e675","resolution":{"observed_at":"2026-08-11T10:51:39.372830Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:39.352952Z","title":"The cityscapes dataset for semantic urban scene understanding","venue":null,"work_id":"36d223ce-bce3-43ec-b632-33bef692c4af","year":2016},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:37.751981Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:7ee43a3dd78586d775f06ad5acd852b09b984dff3e09da544bb4b1d507ce9898","observation_id":"f1cb351c-1810-462a-8b39-a628013ba6d2","resolution":{"observed_at":"2026-08-11T10:51:39.357903Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:39.335623Z","title":"A baseline for few-shot image clas- sification","venue":null,"work_id":"063dde7c-1015-483c-a7f6-ab297b0b8868","year":2020},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:37.756828Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:41d338c06531c8d7c52bfcc01c9dc74ff9736404450ebc0071d579310165547d","observation_id":"fc2dd614-dd61-4494-adc1-2a706a5c42e6","resolution":{"observed_at":"2026-08-11T10:51:39.340533Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:39.317772Z","title":null,"venue":null,"work_id":"a99f8f00-3828-480e-9021-45e31507f8de","year":2022},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:37.762600Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:0e012e828c51bf9cb024c36a80aea7cabf3e26dc3f5c26c439a66438d48a70ec","observation_id":"ee675774-90f4-456b-ad9c-62762f4b16d0","resolution":{"observed_at":"2026-08-11T10:51:39.323683Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:39.298260Z","title":null,"venue":null,"work_id":"b9150a2a-ff95-476f-a150-0e4bcf648060","year":null},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:37.767793Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:4bf45a41785fb7002cac7e538b2cb979a4a75065d3580f5d44fc3f964d9cc1a1","observation_id":"58d85c3c-fafd-411b-ba5c-dddd510bdf03","resolution":{"observed_at":"2026-08-11T10:51:39.304999Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:39.281598Z","title":"Unsupervised domain adaptation by statistics alignment for deep sleep staging networks","venue":null,"work_id":"7fdddfe0-6341-4e22-ae63-5a33c64288ab","year":2022},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:37.772757Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:2946346a0e770890317128253568759d332f8ecbe2c6441165c2dba82c747088","observation_id":"0ba5c085-7119-4ce0-8ea2-54ba5c95fbae","resolution":{"observed_at":"2026-08-11T10:51:39.286507Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:39.263030Z","title":"Model- agnostic meta-learning for fast adaptation of deep networks","venue":null,"work_id":"a09df2f9-6f9d-4108-9682-4ab9889782fa","year":2017},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:37.777910Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:b0381d8554ccdc350599951eaafdd1612d2f4763c76bc9fb843b63583cad437a","observation_id":"42a8909a-d1eb-4579-8b04-c8f59de1b2c5","resolution":{"observed_at":"2026-08-11T10:51:39.268680Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:39.245973Z","title":"Deep residual learning for image recognition","venue":null,"work_id":"2611ac43-56a4-45ed-afdd-1cfd4197160a","year":2016},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:37.783254Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:3983f13772a6fa51396ffe6fa5818d7f1b43d4e60c09c87251b09e1c7761a1e7","observation_id":"1dd247e3-db49-49d5-b5b3-d6839a5796ec","resolution":{"observed_at":"2026-08-11T10:51:39.251483Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:39.230962Z","title":"Masked autoencoders are scalable vision learners","venue":null,"work_id":"0ea915b2-dabe-422a-b04b-80f6e4db82e9","year":2022},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:37.789390Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:c33aea3576cd835b5ac49da7539e53e223b5d9d4df69f6ed445e89bdb5bf1820","observation_id":"73a8d6b1-879a-4c80-814d-859f463a2897","resolution":{"observed_at":"2026-08-11T10:51:39.235860Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:39.217319Z","title":"Hospedales","venue":null,"work_id":"2ed216df-3700-4595-98dd-f096a27a7b41","year":2022},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:37.793970Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:5f2edf1e7081fa1caf38a2bca674e981bea6a95e00577c1320f099c691075ab3","observation_id":"ac88a9fb-1d28-4a88-b248-25eb8dba1133","resolution":{"observed_at":"2026-08-11T10:51:39.221626Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:39.201802Z","title":"Model adaptation: Historical contrastive learning for unsu- pervised domain adaptation without source data","venue":null,"work_id":"0eb389f7-c1ab-483e-8de0-500bcd052ad0","year":2021},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:37.798715Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:30537bb6ee9ecd0a3fcd46fe6df3bfb47c3503308870e9828754c6a439ec0dbc","observation_id":"bc1ff591-a35c-40ad-886a-efa88051dea7","resolution":{"observed_at":"2026-08-11T10:51:39.207578Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:39.187840Z","title":null,"venue":null,"work_id":"d6623169-da14-4c81-bdc8-e38066bb7913","year":1994},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:37.802941Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:ec23ee84650555deabe7d27f7df0b4edb688238bdeb34eb6eb2dfbcbeeec8add","observation_id":"fd965dcf-ab24-4f0e-899c-9802e8f352ae","resolution":{"observed_at":"2026-08-11T10:51:39.192090Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:39.173050Z","title":"Hydra - a framework for elegantly configur- ing complex applications","venue":null,"work_id":"badc930f-febc-4343-8998-8b06f621c535","year":null},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:37.807089Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:5ece83c332563b0e0b5da8a67aa9ee91fe1459234503bd821783af41e6d1c4c4","observation_id":"6a82183c-d296-4965-aff9-0346006e4e51","resolution":{"observed_at":"2026-08-11T10:51:39.177963Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:39.157796Z","title":"Cross-domain weakly-supervised object de- tection through progressive domain adaptation","venue":null,"work_id":"071a738c-1b95-43ef-8b8e-0a856bd428e5","year":2018},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:37.811993Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:a7833683dc4398b15f8571e555526ddbe2f3af951b9268b77fb626c7200e6bd2","observation_id":"32608fa2-c654-41c0-a8e0-320ff9f7ea92","resolution":{"observed_at":"2026-08-11T10:51:39.162861Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2101.10842","last_updated":"2021-01-19T14:22:33Z","snapshot_observed_at":"2026-08-21T04:35:20.381074Z","submitted_at":"2021-01-19T14:22:33Z","title":"Source-free Domain Adaptation via Distributional Alignment by Matching Batch Normalization Statistics","version":1},"cited_work":{"arxiv_id":"2101.10842","doi":null,"metadata_source":"pith","pith_arxiv_id":"2101.10842","snapshot_observed_at":"2026-08-11T10:51:38.384528Z","title":"Source-free Domain Adaptation via Distributional Alignment by Matching Batch Normalization Statistics","venue":"cs.CV","work_id":"9c3b77b6-b8d7-4c9b-a9f0-d41c409836fe","year":2021},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:37.818156Z"},"links":{"cited_paper":"/paper/2101.10842","citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:1c607b12493f2fce1c3da9b8a213f4cc10c2492ce86683f8cc8974602fd530c2","observation_id":"10930183-f672-4854-aefe-6df97441e454","resolution":{"observed_at":"2026-08-11T10:51:38.390220Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:39.142883Z","title":"Driving in the matrix: Can virtual worlds replace human- generated annotations for real world tasks? In ICRA, pages 746–753, 2017","venue":null,"work_id":"3db38be3-9897-4020-95f4-18e63123d9b9","year":2017},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:37.823253Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:83d642f19136eaf9ed88e2915ed662002779cedddf2e978dde7f177754fed396","observation_id":"3861f138-99cd-4787-97cd-52a6d07ced6a","resolution":{"observed_at":"2026-08-11T10:51:39.147599Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1705.06950","last_updated":"2017-05-19T12:07:01Z","snapshot_observed_at":"2026-08-20T22:03:51.775198Z","submitted_at":"2017-05-19T12:07:01Z","title":"The Kinetics Human Action Video Dataset","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1705.06950","snapshot_observed_at":"2026-08-11T10:51:37.828623Z","title":"The kinetics human action video dataset","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:37.828623Z"},"links":{"cited_paper":"/paper/1705.06950","citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:4cb1a76a8ea0d46081d55aab145853e7ac564809a89a4f098b1edd19cf02a8fc","observation_id":"b37a41cc-5a2a-4555-9113-211bedc6804c","resolution":{"observed_at":"2026-08-11T10:51:37.828623Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:39.128430Z","title":"Novel dataset for fine-grained image categorization: Stanford dogs","venue":null,"work_id":"931a245c-9d44-4b09-bb10-0822410ae391","year":2011},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:37.833887Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:415c3a28f4754ccf0af1f06b7db04ac515f035521d5c6b2db5ab3e47caf15453","observation_id":"24b595b8-5daf-4c14-9d23-17e752f9e903","resolution":{"observed_at":"2026-08-11T10:51:39.133417Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:39.113035Z","title":"3d object representations for fine-grained categorization","venue":null,"work_id":"9a9f33b5-d78d-44e7-adc6-1b9450d598f7","year":2013},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:37.839584Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:10c55c6cb52141e7cbd866e2fb4e074aabefb565965978dede0541f6dc6160fd","observation_id":"9c9f40d6-7b24-40b6-8102-77b25c3e7f2d","resolution":{"observed_at":"2026-08-11T10:51:39.118213Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:39.096938Z","title":"Learning multiple layers of features from tiny images, 2009","venue":null,"work_id":"bad5d652-040f-482c-9845-e65dd2485241","year":2009},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:37.844300Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:520e365609d86ceb62a82bdc640627575632f939d38311e20e0f2a9917b3f77d","observation_id":"1e3684fe-8a1f-4020-b173-a5f3bc20d5f0","resolution":{"observed_at":"2026-08-11T10:51:39.101965Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:39.081739Z","title":"Poggio, and Thomas Serre","venue":null,"work_id":"ad83a17d-6b26-459b-b7ae-6a4208aa86fb","year":2011},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:37.849283Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:5bc28123bc84f9a9063db40c0a20529c9e562395e660e54a09f552cc7a121cd3","observation_id":"e817ea26-204f-43f5-913b-b734f9427826","resolution":{"observed_at":"2026-08-11T10:51:39.086523Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:39.067319Z","title":"Towards a framework for privacy-preserving pedes- trian analysis","venue":null,"work_id":"1b1b51a6-e430-4f34-b240-b4a73962ba78","year":2023},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:37.853421Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:204009594c2293f161b8738b92425c592aa972639ecab65174bf160aefacf98f","observation_id":"a41cdce4-9262-406c-b3d1-133876d5696d","resolution":{"observed_at":"2026-08-11T10:51:39.071980Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:39.052467Z","title":"Looking back at labels: A class based domain adaptation technique","venue":null,"work_id":"385fcac0-5398-401b-a55b-e0fedbce863d","year":2019},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:37.857704Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:f3df142c6a3f7fea698229b65c6be851becd3ec5e8981acfd58e0473b6fbc5af","observation_id":"2604ffd9-125d-43de-a561-382cbf37c48b","resolution":{"observed_at":"2026-08-11T10:51:39.057346Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1802.07856","last_updated":"2018-02-22T00:26:46Z","snapshot_observed_at":"2026-08-14T19:43:30.523356Z","submitted_at":"2018-02-22T00:26:46Z","title":"xView: Objects in Context in Overhead Imagery","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1802.07856","snapshot_observed_at":"2026-08-11T10:51:37.862362Z","title":"xview: Objects in context in overhead imagery","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:37.862362Z"},"links":{"cited_paper":"/paper/1802.07856","citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:6ba0ef1c470f21682ca27296fcab517080a40717edbbe2c57a43e3423a248e25","observation_id":"d5266832-3ba7-4c3a-a21c-cda0d85f469d","resolution":{"observed_at":"2026-08-11T10:51:37.862362Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:39.037307Z","title":"Gradient-based learning applied to document recog- nition","venue":null,"work_id":"c58c8d7e-e985-4e69-963b-ae8fe98f2fdf","year":1998},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:37.868333Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:09ce3ac8b32af478dcbc2dd5d196568c140ff80479d39a68ac20de6c98c52d03","observation_id":"79740f07-06ea-4c87-b50a-6dea02235cd3","resolution":{"observed_at":"2026-08-11T10:51:39.042117Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:39.022351Z","title":"Meta-learning with differentiable convex op- timization","venue":null,"work_id":"330bb685-85db-4eef-b82b-3211bc22dd5b","year":2019},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:37.873189Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:19134a19d4c3f6a0ae88b8a4c8bca85259018abfd5c881ddec6e71866cca9d97","observation_id":"ccfe7eba-8d06-4c45-8546-884924182e71","resolution":{"observed_at":"2026-08-11T10:51:39.026941Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2109.04898","last_updated":"2022-09-15T14:19:01Z","snapshot_observed_at":"2026-08-16T17:57:31.680553Z","submitted_at":"2021-09-10T14:12:37Z","title":"LibFewShot: A Comprehensive Library for Few-shot Learning","version":3},"cited_work":{"arxiv_id":"2109.04898","doi":null,"metadata_source":"pith","pith_arxiv_id":"2109.04898","snapshot_observed_at":"2026-08-11T10:51:38.330168Z","title":"LibFewShot: A Comprehensive Library for Few-shot Learning","venue":"cs.CV","work_id":"04e100d3-2435-442e-b575-85a1d147692b","year":2021},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:37.878451Z"},"links":{"cited_paper":"/paper/2109.04898","citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:d013b340ab20f1751abec10f38411f9096cda4bd8c0aaeafc71114e2fc447d1e","observation_id":"6128ffe2-8fb5-41ed-ac09-c2b6e014235e","resolution":{"observed_at":"2026-08-11T10:51:38.335824Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1707.09835","last_updated":"2017-09-28T15:59:41Z","snapshot_observed_at":"2026-08-15T18:17:24.754611Z","submitted_at":"2017-07-31T13:08:11Z","title":"Meta-SGD: Learning to Learn Quickly for Few-Shot Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1707.09835","snapshot_observed_at":"2026-08-11T10:51:37.884021Z","title":"Meta- sgd: Learning to learn quickly for few shot learning","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:37.884021Z"},"links":{"cited_paper":"/paper/1707.09835","citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:82cb7bf1d4906f8cb47b5ceebc7689fa2717e46c0f97f6654a05d1f1626a4f2e","observation_id":"96411fdd-4602-4896-ba80-aa714cf5cfe7","resolution":{"observed_at":"2026-08-11T10:51:37.884021Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:39.002802Z","title":"KITTI-360: A novel dataset and benchmarks for urban scene understanding in 2d and 3d","venue":null,"work_id":"39daf059-223b-4cd5-90c2-72aa00bf721e","year":2023},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:37.889138Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:91261bc51fc2ec900a2d511360ddcb57cdf9281c3995800670c9ddc7197b53cf","observation_id":"63deb45f-5d1f-4b98-9be0-89363b5038dd","resolution":{"observed_at":"2026-08-11T10:51:39.012403Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2210.06409","last_updated":"2022-10-12T17:05:06Z","snapshot_observed_at":"2026-08-21T04:35:19.389035Z","submitted_at":"2022-10-12T17:05:06Z","title":"A Unified Framework with Meta-dropout for Few-shot Learning","version":1},"cited_work":{"arxiv_id":"2210.06409","doi":null,"metadata_source":"pith","pith_arxiv_id":"2210.06409","snapshot_observed_at":"2026-08-11T10:51:38.290756Z","title":"A Unified Framework with Meta-dropout for Few-shot Learning","venue":"cs.CV","work_id":"51eb3945-dc38-4ed8-af21-72ba920c7087","year":2022},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:37.893912Z"},"links":{"cited_paper":"/paper/2210.06409","citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:9636615437c989067743fb2e3bf651176243d60b847d6071ec27fb87f9862944","observation_id":"d2370b09-abd7-45b0-b488-49ef50152408","resolution":{"observed_at":"2026-08-11T10:51:38.295691Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:38.987304Z","title":"Graph consistency based mean-teaching for unsupervised domain adaptive person re- identification","venue":null,"work_id":"ac9d8256-0229-427d-b5bb-c2308b48c5e2","year":2021},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:37.899198Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:e6304a0672587381e825a01d479228f7d31f8c47b778288ecc7e56e401fc73e5","observation_id":"b09396f5-79f2-47fa-9dd4-dda9848376ff","resolution":{"observed_at":"2026-08-11T10:51:38.992095Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:38.971823Z","title":"Expanding language-image pretrained models for gen- eral video recognition, 2022","venue":null,"work_id":"7164af3e-377f-4d2c-8ac1-fdd42ed0342b","year":2022},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:37.903243Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:dfbd0169547bf48664594ce73d3a30c98cb55e40a2276b82f0f535a7fa03849a","observation_id":"6efec13c-56a9-4582-be42-b4218720e520","resolution":{"observed_at":"2026-08-11T10:51:38.976796Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:38.955407Z","title":"Sindagi, Vibashan VS, and Vishal M","venue":null,"work_id":"c285d49d-ca3e-4b82-8800-faa5ed088c9e","year":2021},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:37.907587Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:621eba76bf71e0468c9b09cf3712628c1285dfd66f01dcc5a3c5505957ca5836","observation_id":"a140d747-7ec2-44e0-ae7d-6123eeb48e2a","resolution":{"observed_at":"2026-08-11T10:51:38.960734Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:38.938866Z","title":"Multi-adversarial domain adaptation","venue":null,"work_id":"e011b5c0-43c5-48d0-b234-e9a7c8a2e36e","year":2018},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:37.913884Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:ca0b57c33db03655b90ab9135e39a13dff71ceb2f7b8487222e3cd2bebbe7603","observation_id":"2c207c2f-485d-4f87-9bf1-f138fc5935b3","resolution":{"observed_at":"2026-08-11T10:51:38.943730Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1710.06924","last_updated":"2017-11-29T04:04:18Z","snapshot_observed_at":"2026-08-16T06:32:04.347989Z","submitted_at":"2017-10-18T20:20:49Z","title":"VisDA: The Visual Domain Adaptation Challenge","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.06924","snapshot_observed_at":"2026-08-11T10:51:37.918823Z","title":"Visda: The visual domain adaptation challenge","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:37.918823Z"},"links":{"cited_paper":"/paper/1710.06924","citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:2de4652ded2b4ffbce892d4cb36021419d885d1d4c951d72dd8432c522d5a41f","observation_id":"aa650566-ff67-47ec-82ff-c8c48d034253","resolution":{"observed_at":"2026-08-11T10:51:37.918823Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:38.923012Z","title":"Moment matching for multi-source domain adaptation","venue":null,"work_id":"c4beef7a-4dd8-486a-800d-0a629a6184e8","year":2019},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:37.924784Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:147e1b01bb3b32738be731b8bddb48ccd2dc5a334e3896062841727db9063432","observation_id":"7b5ba633-30b0-4bc3-88c0-d5c0ec917b26","resolution":{"observed_at":"2026-08-11T10:51:38.928037Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:38.907182Z","title":"Adapting self-supervised vision transformers by probing attention-conditioned masking consistency","venue":null,"work_id":"47007ae6-1656-4ae6-ba8f-9536cfd414d1","year":2022},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:37.930396Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:3b0a839f3cf017fe2ab06dc8c510769685d7ceb90a5d9912f9a00833c66675d9","observation_id":"3c57bfa9-0be7-426e-81d0-e0be97d4e189","resolution":{"observed_at":"2026-08-11T10:51:38.912158Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:38.891419Z","title":"Learning transferable visual models from natural language supervision","venue":null,"work_id":"62c7ce4a-b9c4-4fb6-86bd-588dcf68b22d","year":2021},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:37.936467Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:dc36500d9e5a4ac688dd7eff64c1d3155c709c036bc7ced951ff7b003fb4fa6f","observation_id":"347059a5-e684-4c7a-ba30-ceec4f02d0bc","resolution":{"observed_at":"2026-08-11T10:51:38.896537Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:38.875894Z","title":"Tenenbaum, Hugo Larochelle, and Richard S","venue":null,"work_id":"576fc630-893a-49d1-ae4a-58c5bcfe2d66","year":2018},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:37.942416Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:631a05e66089553d8543f8af4968b5f3c8cabd9eccb554853cbd1ece2a18b7e4","observation_id":"30c56465-e6ac-4eb9-91b0-28ef91d663c8","resolution":{"observed_at":"2026-08-11T10:51:38.880953Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:37.947261Z","title":"Imagenet large scale visual recognition challenge.IJCV, 115:211–252,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:37.947261Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:55b80544c3e2af9ac6938df3b47fdcf856171d14a777cb08f68f8b3628b07ba7","observation_id":"8af52f72-cc05-4a2f-99e5-6ad1ee92b688","resolution":{"observed_at":"2026-08-11T10:51:37.947261Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:38.850891Z","title":"Adapting visual category models to new domains","venue":null,"work_id":"5750c2c9-a6f9-4806-a36f-826fe269015a","year":2010},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:37.953144Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:91d222a19eba48592cd2af45eec261c052ef30bc18a64619f6f8e9960ae9a8a2","observation_id":"488245d2-554f-4cd8-8269-d5e685253809","resolution":{"observed_at":"2026-08-11T10:51:38.855159Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:38.836241Z","title":"Semi-supervised domain adaptation via minimax entropy","venue":null,"work_id":"7c9f53a5-c610-4743-b258-9c7959d48b14","year":2019},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:37.957837Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:abe7f6157dbd7b4232047bccbb449c814fd3c77ee537562222e29b80cd94ff1e","observation_id":"2409660a-be69-4465-aaee-d25947dc451e","resolution":{"observed_at":"2026-08-11T10:51:38.840863Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:38.820548Z","title":"Seman- tic foggy scene understanding with synthetic data.IJCV, 126 (9):973–992, 2018","venue":null,"work_id":"4c1d14bd-d73c-4705-8400-391d7ba12d82","year":2018},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:37.962609Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:af30f9bfcd69da7ab72f09e2c69c9d5839ab28c436c353436a5c520c18ed6127","observation_id":"bd88ff66-b988-4ead-b430-ac69db67f764","resolution":{"observed_at":"2026-08-11T10:51:38.826022Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:38.805222Z","title":"Normalized cuts and image segmentation","venue":null,"work_id":"99add2db-e8b9-435d-82ee-57bd4e747330","year":2000},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:37.968040Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:7479af3622a93e14def168f1497b307848dd51fa3d7d4c6f7e98be62abb615a7","observation_id":"a96502b9-6276-4589-abcf-69dbb96ffc15","resolution":{"observed_at":"2026-08-11T10:51:38.810364Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2205.06743","last_updated":"2022-05-24T05:24:48Z","snapshot_observed_at":"2026-08-21T04:35:24.227777Z","submitted_at":"2022-05-13T16:24:35Z","title":"A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.06743","snapshot_observed_at":"2026-08-11T10:51:37.973086Z","title":"Mondal, and Jy- oti Prakash Sahoo","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:37.973086Z"},"links":{"cited_paper":"/paper/2205.06743","citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:4c4a3a06148d14125bc16b177a49d5ea571b31a29cde65f2e7dbfab67a631db7","observation_id":"28155326-92f9-49f7-9763-3cfce2b74160","resolution":{"observed_at":"2026-08-11T10:51:37.973086Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1212.0402","last_updated":"2012-12-03T14:45:31Z","snapshot_observed_at":"2026-08-16T21:21:44.768787Z","submitted_at":"2012-12-03T14:45:31Z","title":"UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1212.0402","snapshot_observed_at":"2026-08-11T10:51:37.977965Z","title":"UCF101: A dataset of 101 human actions classes from videos in the wild","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:37.977965Z"},"links":{"cited_paper":"/paper/1212.0402","citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:3d33e1c0e69ab82be7a05a7b97c6a062b09f7cbf67b7cd2157cddf8a50aa5855","observation_id":"d4c331e9-4d88-4af7-b6b4-1e908e604c29","resolution":{"observed_at":"2026-08-11T10:51:37.977965Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:38.790227Z","title":"Discriminative adversarial domain adaptation","venue":null,"work_id":"577bb6ff-29cc-4b96-94de-4671dd610caf","year":2020},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:37.983133Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:09359633a107feacb734dd0c76262388ac92ec2e7d49ea72e7b6cc2f8bd82a59","observation_id":"f14614e0-2c49-4800-a92d-808748eb2d9d","resolution":{"observed_at":"2026-08-11T10:51:38.795133Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:38.773824Z","title":"Model adaptation through hypothesis transfer with gradual knowledge distillation","venue":null,"work_id":"04aac472-623c-4237-b945-e3d6c5b33704","year":2021},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:37.987761Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:a0dc5819093d024daee9a49dc417739fbfbbeffbb1ab606d910e5b4044b48b13","observation_id":"2aeb9aa2-17c7-4bf4-9802-315dd6049678","resolution":{"observed_at":"2026-08-11T10:51:38.778806Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:38.757196Z","title":"Meta-dataset: A dataset of datasets for learning to learn from few examples","venue":null,"work_id":"94ed702f-484d-4228-88bb-29e6497f80d0","year":2020},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:37.992540Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:0ebdd819a4877a76143a00223734537ef27e094088432ece2e6b92856eec4155","observation_id":"9154219b-b57f-4976-b7d3-ae8d88b4027f","resolution":{"observed_at":"2026-08-11T10:51:38.762945Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:38.736331Z","title":"Adversarial discriminative domain adaptation","venue":null,"work_id":"117c31a4-394b-4eea-81f7-11dc355e9eed","year":2017},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:37.997119Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:a511d97deeddd3116abaae3ad2560d8f5e45f36b481b5ba66ad889bfc24265c0","observation_id":"883a50e0-8872-4039-a355-f4a90d45b39d","resolution":{"observed_at":"2026-08-11T10:51:38.740743Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:38.722313Z","title":null,"venue":null,"work_id":"7be4432d-1ad1-4bb6-985f-ee3d61c93d95","year":2013},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:38.002075Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:3b8ab81b9062e7309d1e7c0183864776323d5b5f1072dd3c7aa46ab228162bf3","observation_id":"94a283cb-352b-44b6-bfb8-67961c3ae268","resolution":{"observed_at":"2026-08-11T10:51:38.726522Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:38.707810Z","title":"Deep hashing network for unsupervised domain adaptation","venue":null,"work_id":"6ddd6141-3e1c-4355-9a8a-ae8a8c01a6d3","year":2017},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:38.006886Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:5879a5c373ec24fc6832d8720c9d03be3faef4c6fb60affe53461576b9007f3e","observation_id":"7def9689-94b2-46d5-8963-34e170d03c75","resolution":{"observed_at":"2026-08-11T10:51:38.712045Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:38.687807Z","title":"Matching networks for one shot learning","venue":null,"work_id":"aa4694a0-700e-4945-8077-85f23dbcd95b","year":2016},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:38.011781Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:5461ffb5809d92df3d5ffd1ac4462ee8b74e9727b00b7549d6e73f7d576145c4","observation_id":"bfb643c0-3cc0-4a04-a255-4ccdf1956519","resolution":{"observed_at":"2026-08-11T10:51:38.693392Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:38.671833Z","title":"Matching networks for one shot learning","venue":null,"work_id":"3244ca65-de1c-466f-83bc-55a2723cdbe3","year":2016},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:38.016547Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:896fcefe598a039c7131cbee98900a546011086a22e81d62cd15c16a52ffe248","observation_id":"0ebfd621-a7ba-4482-a565-8c4a07803bfa","resolution":{"observed_at":"2026-08-11T10:51:38.677101Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:38.654782Z","title":"Visda2019 - visual domain adaptation chal- lenge","venue":null,"work_id":"8a0186f3-68f6-4294-9969-630bdee91995","year":2019},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:38.022383Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:3a8e9d116e47fbaedbcb2a21a8b58c54f48a7943d9148221a5b15292b11b13f1","observation_id":"208c57ae-6273-42b2-993a-e887636646f2","resolution":{"observed_at":"2026-08-11T10:51:38.659632Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:38.639231Z","title":"Belongie","venue":null,"work_id":"1a6fec68-008f-4fea-830f-ea4dd955f7e0","year":2011},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:38.027583Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:a52c2baceffc51860430df28a53141546bf101c58bdf258f6938cf32ecb10b24","observation_id":"d43de17d-2a51-4efe-943f-651663d00d99","resolution":{"observed_at":"2026-08-11T10:51:38.644060Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:38.622232Z","title":"Cross-domain contrastive learning for unsupervised domain adaptation","venue":null,"work_id":"99dddbb8-f2a9-4bf5-bb48-d44848d65478","year":2022},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:38.033668Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:10378824e5c19295e60e89e1b65ef309f7082a43979529ebc9f4535605a840cd","observation_id":"3e592f8a-6956-4626-b567-b5f96dd1d066","resolution":{"observed_at":"2026-08-11T10:51:38.627658Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2301.11320","last_updated":"2023-01-26T18:57:13Z","snapshot_observed_at":"2026-08-21T04:35:30.631486Z","submitted_at":"2023-01-26T18:57:13Z","title":"Cut and Learn for Unsupervised Object Detection and Instance Segmentation","version":1},"cited_work":{"arxiv_id":"2301.11320","doi":null,"metadata_source":"pith","pith_arxiv_id":"2301.11320","snapshot_observed_at":"2026-08-11T10:51:38.212826Z","title":"Cut and Learn for Unsupervised Object Detection and Instance Segmentation","venue":"cs.CV","work_id":"bf26e56f-e13b-414f-b2f0-c99ef2417495","year":2023},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:38.038670Z"},"links":{"cited_paper":"/paper/2301.11320","citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:15265606440ebcc4518bc0c6006cf3076c2b4e75b1a1a617165de193b8828989","observation_id":"2cbee99a-64a5-46ac-af68-1c908846b639","resolution":{"observed_at":"2026-08-11T10:51:38.221225Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:38.607612Z","title":"Msmcnet: A modular few-shot learning framework for signal modulation classification","venue":null,"work_id":"140c34a7-d60c-48a6-8f10-b72bf73020e8","year":2022},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:38.043939Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:98087b3a7546ba1f990b5a25e733b553b47f1038716955ca8a16b3996ad70f44","observation_id":"6ba08902-2b3e-4cd5-a156-dcf9f9dda148","resolution":{"observed_at":"2026-08-11T10:51:38.612342Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:38.594077Z","title":null,"venue":null,"work_id":"2c15d90d-2bc0-4483-baf9-8693e1b60fb2","year":null},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:38.048757Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:353ed94b61b1939173a2c990ab6bc7582c5fd8b14399e75aea9f44efab108a4a","observation_id":"79a225ef-2af5-4fcf-a205-c07f35f8cbca","resolution":{"observed_at":"2026-08-11T10:51:38.598634Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:38.577198Z","title":"Adap- tive adversarial network for source-free domain adaptation","venue":null,"work_id":"f7d10c86-679b-4c38-8418-13d27c10df64","year":2021},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:38.053402Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:e56b93ef0ff041f1899c5f8d1ffc6e1425eb88aa59bbd1ec2c414549db3bcae2","observation_id":"98646a51-44ba-4820-8018-e9341d1015bd","resolution":{"observed_at":"2026-08-11T10:51:38.583601Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:38.561376Z","title":"Source data-free domain adaptation of object detector through domain-specific perturbation","venue":null,"work_id":"05ae15e1-b54e-4f50-9129-afbe0e996b86","year":2021},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:38.057540Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:f44b4228bbc3a57c991b74eb18923ef05f1482ba8f619465063eda6149f51118","observation_id":"03a7c35d-95cc-4d0b-a5a6-ef7c04dfaff3","resolution":{"observed_at":"2026-08-11T10:51:38.566590Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2006.03876","last_updated":"2022-08-19T05:41:15Z","snapshot_observed_at":"2026-08-21T04:35:24.683289Z","submitted_at":"2020-06-06T14:25:52Z","title":"ARID: A New Dataset for Recognizing Action in the Dark","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.03876","snapshot_observed_at":"2026-08-11T10:51:38.061939Z","title":"ARID: A new dataset for recog- nizing action in the dark","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:38.061939Z"},"links":{"cited_paper":"/paper/2006.03876","citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:1388553a3393ddc1636c8bcdbd53e3cd667766df2729e1b86ad9a167001192fe","observation_id":"09d467e0-a495-4087-8784-ff83ac4f19c5","resolution":{"observed_at":"2026-08-11T10:51:38.061939Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2211.10412","last_updated":"2024-07-27T14:54:24Z","snapshot_observed_at":"2026-08-21T04:35:28.910388Z","submitted_at":"2022-11-17T05:05:42Z","title":"Video Unsupervised Domain Adaptation with Deep Learning: A Comprehensive Survey","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2211.10412","snapshot_observed_at":"2026-08-11T10:51:38.066487Z","title":"Video unsupervised domain adapta- tion with deep learning: A comprehensive survey","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:38.066487Z"},"links":{"cited_paper":"/paper/2211.10412","citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:2c320ffaca431f6a35aff53518778caab72aca5f2887f87b35a7ca875364ae26","observation_id":"c757c6b0-008c-47a7-961b-a531eb4b4a18","resolution":{"observed_at":"2026-08-11T10:51:38.066487Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:38.544806Z","title":"Aligning correlation information for domain adaptation in action recognition","venue":null,"work_id":"92057a0a-66ca-4203-bd00-27de1b285d9c","year":2022},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:38.072212Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:5e7357f91085ee8ea2b42900d38ae4e1ae0413579c9356cf4780832b4410123e","observation_id":"796c84b0-6729-4d13-ab18-3b482b639ce2","resolution":{"observed_at":"2026-08-11T10:51:38.550626Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2105.14138","last_updated":"2021-05-28T23:06:26Z","snapshot_observed_at":"2026-08-21T04:33:11.691595Z","submitted_at":"2021-05-28T23:06:26Z","title":"Transformer-Based Source-Free Domain Adaptation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2105.14138","snapshot_observed_at":"2026-08-11T10:51:38.077113Z","title":"Transformer-based source- free domain adaptation","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:38.077113Z"},"links":{"cited_paper":"/paper/2105.14138","citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:62b46483755dae6d1a1351c40fe31ad6b096542189f7106cbf14b3afffa6e73d","observation_id":"e8372c7e-787e-42db-a9d0-df49427513ba","resolution":{"observed_at":"2026-08-11T10:51:38.077113Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:38.529451Z","title":"Interact before align: Leveraging cross-modal knowledge for domain adaptive action recognition","venue":null,"work_id":"6c7edb28-9034-4767-8f64-8f7f6ac57086","year":2022},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:38.082550Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:e31360f0a0c1afacf749005975f5ef56bfa4712633364abd2a6e510fd80ba91c","observation_id":"4e9b93b0-9e9a-4771-83d6-186301a1dcf3","resolution":{"observed_at":"2026-08-11T10:51:38.534283Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:38.514615Z","title":"Unsupervised domain adaptation for one-stage object detector using offsets to bounding box","venue":null,"work_id":"50746139-76b8-4110-b6c0-7276513e10bc","year":2022},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:38.087646Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:4ae49e15e7b569403902bafa20c9e7b1ed7141f031c3e98ae5fc9a65a90227c7","observation_id":"ede68a2b-8344-47f8-b755-55e6bb54a938","resolution":{"observed_at":"2026-08-11T10:51:38.519470Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:38.497409Z","title":"BDD100K: A diverse driving dataset for heterogeneous multitask learning","venue":null,"work_id":"acf36bc4-0792-45a9-ab62-69d20dc04ae1","year":2020},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:38.092570Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:4b9135363e60d41c4a917a6a81dd8b57351da28cd0164cc733224deb62654987","observation_id":"ce7ad5c7-a6fe-49a2-9498-1b3170931840","resolution":{"observed_at":"2026-08-11T10:51:38.503801Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:38.480297Z","title":"Source-free domain adaptation for real-world image dehazing","venue":null,"work_id":"a53862e4-a401-498b-9df7-83449f05037b","year":2022},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:38.097464Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:4f9da601ce4721b14120b43f6bb5e0d19c1b20ce5e945a1338bebce823629fd3","observation_id":"13cc6747-7dfa-4ba1-8a7a-62f13e619a76","resolution":{"observed_at":"2026-08-11T10:51:38.485857Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:38.465210Z","title":"Source-style transferred mean teacher for source-data free object detection","venue":null,"work_id":"15c0a860-45c1-4e6e-b247-4169dd630638","year":2021},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:38.102325Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:24645643450fc2787569f175b8b0aeb58c5686972c39bd4bf1ab0787b1018424","observation_id":"92fe056c-3575-4d58-9faa-ac34fe43c1c2","resolution":{"observed_at":"2026-08-11T10:51:38.469595Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:38.450796Z","title":"Inpaint2learn: A self-supervised framework for affordance learning","venue":null,"work_id":"b4a26419-cbc2-47ef-924e-7068ef6e3601","year":2022},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:38.107183Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:357da8c28c3007c8a4a8e64e41e536c49d69e132250d69cbd249973367a3be7b","observation_id":"7a447d08-bdcb-4919-bb6f-f9dacbfd2f01","resolution":{"observed_at":"2026-08-11T10:51:38.455265Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:38.434918Z","title":"Robust re-weighting prototypical networks for few-shot clas- sification","venue":null,"work_id":"54683f81-5d64-47c7-9c1c-5fa13fcd37d7","year":2020},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:38.112855Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:5054822bf2e45b4f94f2483a1ecfd0e1ec0a2ba5053f0ce71b881a3695969096","observation_id":"550e54d6-ba2d-4ab4-9f84-f9b73dd2ea4a","resolution":{"observed_at":"2026-08-11T10:51:38.440056Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:51:38.418136Z","title":"A closer look at few-shot video classification: A new baseline and benchmark","venue":null,"work_id":"178728c7-ab7d-40d1-9513-0c4808b115ab","year":2021},"citing_paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning","version":1},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-11T10:51:38.118484Z"},"links":{"citing_paper":"/paper/2412.16275"},"observation_digest":"sha256:2e8c801d666c833d29dd1a5e703ee9873f1c19c709a6249b3b6003a54689fcb5","observation_id":"5b0afc00-0672-4fcd-814d-37d8825005e5","resolution":{"observed_at":"2026-08-11T10:51:38.423590Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2412.16275","last_updated":"2024-12-20T17:16:15Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-18T02:32:40.167322Z","submitted_at":"2024-12-20T17:16:15Z","title":"LEARN: A Unified Framework for Multi-Task Domain Adapt Few-Shot Learning"},"reference_resolution":{"displayed":84,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":20,"verified_exact":4,"verified_fuzzy":60},"total_outbound_references":84},"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":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"thesis":"As of 24 August 2026, this Paper Citation Record lists 84 of 84 outbound references and 0 inbound Pith citation observations for arXiv:2412.16275."}