{"as_of":"2026-08-08T09:21:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3ec5429568a90d4ca61c9815366a03f0842ec55a743ef9ca848892e5a3e15dda","coverage":[{"denominator":47,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":47,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T13:13:43.154341Z","state":"measured"},{"denominator":47,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":47,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2505.22458/citation-record","integrity":"/paper/2505.22458/integrity","json":"/paper/2505.22458/citation-record.json","paper":"/paper/2505.22458"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:13:50.735160Z","title":"On the effectiveness of image rotation for open set domain adaptation","venue":null,"work_id":"b90e534b-9880-46f7-a589-4f2f8a47e0fa","year":2020},"citing_paper":{"arxiv_id":"2505.22458","last_updated":"2025-06-05T22:38:25Z","snapshot_observed_at":"2026-08-07T22:12:30.212777Z","submitted_at":"2025-05-28T15:14:11Z","title":"Universal Domain Adaptation for Semantic Segmentation","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:37.983177Z"},"links":{"citing_paper":"/paper/2505.22458"},"observation_digest":"sha256:afc1f2512c98171d115362bfaab17746712b3b3986edfa35c20b8488f170681e","observation_id":"9c177bed-85e4-4fb1-8638-f0f2130f9969","resolution":{"observed_at":"2026-08-07T13:13:50.808220Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:13:50.605879Z","title":"Unified optimal transport framework for universal domain adaptation.Advances in Neural Information Processing Sys- tems, 35:29512–29524, 2022","venue":null,"work_id":"9d923a65-1fc0-4da1-a02c-1546314bfa6d","year":2022},"citing_paper":{"arxiv_id":"2505.22458","last_updated":"2025-06-05T22:38:25Z","snapshot_observed_at":"2026-08-07T22:12:30.212777Z","submitted_at":"2025-05-28T15:14:11Z","title":"Universal Domain Adaptation for Semantic Segmentation","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:38.059359Z"},"links":{"citing_paper":"/paper/2505.22458"},"observation_digest":"sha256:d3cdf8c6c34d6502a4d85ccd112e619b4d52956df109d9a699879e53d0533a86","observation_id":"be34476f-f75b-454d-8809-915a5196e1ca","resolution":{"observed_at":"2026-08-07T13:13:50.665710Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:13:50.453992Z","title":"Synergistic image and feature adaptation: Towards cross-modality domain adaptation for medical image seg- mentation","venue":null,"work_id":"585e9c8f-306f-4314-a522-4ccd57f1d8e2","year":2019},"citing_paper":{"arxiv_id":"2505.22458","last_updated":"2025-06-05T22:38:25Z","snapshot_observed_at":"2026-08-07T22:12:30.212777Z","submitted_at":"2025-05-28T15:14:11Z","title":"Universal Domain Adaptation for Semantic Segmentation","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:38.144722Z"},"links":{"citing_paper":"/paper/2505.22458"},"observation_digest":"sha256:4350364e1f58c7140e9b5b2c5bba25ced99344e9e39ef8d0700105ad6bed84a1","observation_id":"cff5abe1-4fd4-476d-807f-8782688bf247","resolution":{"observed_at":"2026-08-07T13:13:50.531251Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:13:50.159756Z","title":null,"venue":null,"work_id":"782518bf-5c99-4089-8b53-c01a62969cf1","year":2017},"citing_paper":{"arxiv_id":"2505.22458","last_updated":"2025-06-05T22:38:25Z","snapshot_observed_at":"2026-08-07T22:12:30.212777Z","submitted_at":"2025-05-28T15:14:11Z","title":"Universal Domain Adaptation for Semantic Segmentation","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:38.257773Z"},"links":{"citing_paper":"/paper/2505.22458"},"observation_digest":"sha256:2347c807d79ee8267df88e8f5fef016211256fe1f907dea9e278eec738a6f0e8","observation_id":"926f3915-5c6d-4989-88e3-2ad5236fdad8","resolution":{"observed_at":"2026-08-07T13:13:50.327276Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:13:49.913312Z","title":"Do- main adaptation for semantic segmentation with maximum squares loss","venue":null,"work_id":"1bfa28a2-1896-4bdc-946d-52d7c1927c77","year":2019},"citing_paper":{"arxiv_id":"2505.22458","last_updated":"2025-06-05T22:38:25Z","snapshot_observed_at":"2026-08-07T22:12:30.212777Z","submitted_at":"2025-05-28T15:14:11Z","title":"Universal Domain Adaptation for Semantic Segmentation","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:38.381300Z"},"links":{"citing_paper":"/paper/2505.22458"},"observation_digest":"sha256:b1dd84a4aae76fc4df9e1e892915f853e10680667661f61a902579f1867d658e","observation_id":"d10ae03e-f42b-486f-90c7-16f557b99cb0","resolution":{"observed_at":"2026-08-07T13:13:49.939052Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:13:49.698726Z","title":"Open-set domain adaptation for semantic segmentation","venue":null,"work_id":"3280cf04-b2bc-4861-8493-a6576328cf48","year":2024},"citing_paper":{"arxiv_id":"2505.22458","last_updated":"2025-06-05T22:38:25Z","snapshot_observed_at":"2026-08-07T22:12:30.212777Z","submitted_at":"2025-05-28T15:14:11Z","title":"Universal Domain Adaptation for Semantic Segmentation","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:38.499456Z"},"links":{"citing_paper":"/paper/2505.22458"},"observation_digest":"sha256:3ec54c937fac19213131ddd4eee5aa067e5e02d9df782efef1cb8626bfc0c3cb","observation_id":"02ea3c69-8f74-427a-b234-2bbf80a9f3c9","resolution":{"observed_at":"2026-08-07T13:13:49.806225Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:13:38.622246Z","title":"The cityscapes dataset for semantic urban scene understanding","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.22458","last_updated":"2025-06-05T22:38:25Z","snapshot_observed_at":"2026-08-07T22:12:30.212777Z","submitted_at":"2025-05-28T15:14:11Z","title":"Universal Domain Adaptation for Semantic Segmentation","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:38.622246Z"},"links":{"citing_paper":"/paper/2505.22458"},"observation_digest":"sha256:af088af881e5747eafc8ed0619843781dfac1c850c9af02baaa5ee9880127d5a","observation_id":"052767a5-0d5d-4adb-b562-7e74d315fb9b","resolution":{"observed_at":"2026-08-07T13:13:38.622246Z","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":"2026-08-07T13:13:38.745323Z","title":"Imagenet: A large-scale hierarchical image database","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2505.22458","last_updated":"2025-06-05T22:38:25Z","snapshot_observed_at":"2026-08-07T22:12:30.212777Z","submitted_at":"2025-05-28T15:14:11Z","title":"Universal Domain Adaptation for Semantic Segmentation","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:38.745323Z"},"links":{"citing_paper":"/paper/2505.22458"},"observation_digest":"sha256:4aed2540ab66e524a92f6168e0a8d3ad6925c1b646c32151f41be13194e64876","observation_id":"fa50a50e-455a-4b09-a431-912f6a810ed0","resolution":{"observed_at":"2026-08-07T13:13:38.745323Z","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":"2026-08-07T13:13:49.551161Z","title":"Ssf-dan: Separated semantic feature based domain adaptation network for semantic segmentation","venue":null,"work_id":"328d18ae-7672-4a03-a0c3-9264b9c82328","year":2019},"citing_paper":{"arxiv_id":"2505.22458","last_updated":"2025-06-05T22:38:25Z","snapshot_observed_at":"2026-08-07T22:12:30.212777Z","submitted_at":"2025-05-28T15:14:11Z","title":"Universal Domain Adaptation for Semantic Segmentation","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:38.821548Z"},"links":{"citing_paper":"/paper/2505.22458"},"observation_digest":"sha256:4c4cec3dc61983c652dcb71eaf38ab605d892dd321782a940284c0215bfd627e","observation_id":"491196a1-d344-43dc-9e3c-39b209523a0a","resolution":{"observed_at":"2026-08-07T13:13:49.608944Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:13:49.371456Z","title":"Learning to detect open classes for universal domain adapta- tion","venue":null,"work_id":"0da01045-e9da-4c5e-8f9d-b066da2490af","year":2020},"citing_paper":{"arxiv_id":"2505.22458","last_updated":"2025-06-05T22:38:25Z","snapshot_observed_at":"2026-08-07T22:12:30.212777Z","submitted_at":"2025-05-28T15:14:11Z","title":"Universal Domain Adaptation for Semantic Segmentation","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:38.897762Z"},"links":{"citing_paper":"/paper/2505.22458"},"observation_digest":"sha256:cd2d9f357ec3e0f89f3d8c97e9e79ada48153b55e185b145425a755c4b3a36fd","observation_id":"90f93546-dc2b-4d85-b056-59cf30f35a4e","resolution":{"observed_at":"2026-08-07T13:13:49.437175Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:13:38.984908Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.22458","last_updated":"2025-06-05T22:38:25Z","snapshot_observed_at":"2026-08-07T22:12:30.212777Z","submitted_at":"2025-05-28T15:14:11Z","title":"Universal Domain Adaptation for Semantic Segmentation","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:38.984908Z"},"links":{"citing_paper":"/paper/2505.22458"},"observation_digest":"sha256:ba563830e20453d246d1ab2bf31ddc8dae23e181881959242fc96b96c770e5dc","observation_id":"31918203-4d35-4c96-883f-8783730cf4e9","resolution":{"observed_at":"2026-08-07T13:13:38.984908Z","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":"2026-08-07T13:13:49.167507Z","title":"Conditional generative adversarial network for struc- tured domain adaptation","venue":null,"work_id":"90c187c3-ce94-4d92-ab59-01bf0d68cbe6","year":2018},"citing_paper":{"arxiv_id":"2505.22458","last_updated":"2025-06-05T22:38:25Z","snapshot_observed_at":"2026-08-07T22:12:30.212777Z","submitted_at":"2025-05-28T15:14:11Z","title":"Universal Domain Adaptation for Semantic Segmentation","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:39.063782Z"},"links":{"citing_paper":"/paper/2505.22458"},"observation_digest":"sha256:5479e50ba49eadef14bb15817651460156edd3f5559026085ceeb01f81414604","observation_id":"f83d7d70-cbb8-42a4-8106-c6e011bd4386","resolution":{"observed_at":"2026-08-07T13:13:49.255404Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:13:48.949080Z","title":"Daformer: Improving network architectures and training strategies for domain-adaptive semantic segmentation","venue":null,"work_id":"a80c7764-0e23-43e3-980f-d54bb836dd77","year":2022},"citing_paper":{"arxiv_id":"2505.22458","last_updated":"2025-06-05T22:38:25Z","snapshot_observed_at":"2026-08-07T22:12:30.212777Z","submitted_at":"2025-05-28T15:14:11Z","title":"Universal Domain Adaptation for Semantic Segmentation","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:39.191281Z"},"links":{"citing_paper":"/paper/2505.22458"},"observation_digest":"sha256:d659741306e92e1e5cf84d3f9a2a9b2eb115848d746f1a1c9d5cb0be1dc050f2","observation_id":"394d2b04-27e2-4fab-a863-93576f04a8de","resolution":{"observed_at":"2026-08-07T13:13:49.021509Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:13:48.721538Z","title":"Hrda: Context-aware high-resolution domain-adaptive semantic segmentation","venue":null,"work_id":"1409be57-111e-4e71-8a33-686c0df0562c","year":2022},"citing_paper":{"arxiv_id":"2505.22458","last_updated":"2025-06-05T22:38:25Z","snapshot_observed_at":"2026-08-07T22:12:30.212777Z","submitted_at":"2025-05-28T15:14:11Z","title":"Universal Domain Adaptation for Semantic Segmentation","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:39.237471Z"},"links":{"citing_paper":"/paper/2505.22458"},"observation_digest":"sha256:a14d8d0bfe0480273ba0dab3d520dfe484df028562b87cb1259c29d4a22f5bd3","observation_id":"49c52ed2-1e70-4c7f-a07b-74ff70228078","resolution":{"observed_at":"2026-08-07T13:13:48.835370Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:13:48.575868Z","title":"Mic: Masked image consistency for context- enhanced domain adaptation","venue":null,"work_id":"0470faf6-b8d3-487d-b81e-8ddcb0afc6fc","year":2023},"citing_paper":{"arxiv_id":"2505.22458","last_updated":"2025-06-05T22:38:25Z","snapshot_observed_at":"2026-08-07T22:12:30.212777Z","submitted_at":"2025-05-28T15:14:11Z","title":"Universal Domain Adaptation for Semantic Segmentation","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:39.311273Z"},"links":{"citing_paper":"/paper/2505.22458"},"observation_digest":"sha256:0d3c1fc41bd323b5df342619d405e5b535a2823cee3d3eef4ac387c3ef024f9b","observation_id":"f3513010-a395-40c2-9bd4-57a335880162","resolution":{"observed_at":"2026-08-07T13:13:48.641109Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:13:48.406661Z","title":"Learning texture invari- ant representation for domain adaptation of semantic seg- mentation","venue":null,"work_id":"394b9e16-7385-4cb0-9d27-0c0fb4d32532","year":2020},"citing_paper":{"arxiv_id":"2505.22458","last_updated":"2025-06-05T22:38:25Z","snapshot_observed_at":"2026-08-07T22:12:30.212777Z","submitted_at":"2025-05-28T15:14:11Z","title":"Universal Domain Adaptation for Semantic Segmentation","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:39.400280Z"},"links":{"citing_paper":"/paper/2505.22458"},"observation_digest":"sha256:6d6bee9a980106218c9787017f7d3ed393ca32fe65d99cc7fe4090012b2fd38b","observation_id":"4e75798e-bbca-4c7d-96cd-26226d08b2b6","resolution":{"observed_at":"2026-08-07T13:13:48.500080Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:13:48.210830Z","title":"Improv- ing semantic segmentation via decoupled body and edge su- pervision","venue":null,"work_id":"798a352c-f7e3-469a-8ea3-8456b847eb92","year":2020},"citing_paper":{"arxiv_id":"2505.22458","last_updated":"2025-06-05T22:38:25Z","snapshot_observed_at":"2026-08-07T22:12:30.212777Z","submitted_at":"2025-05-28T15:14:11Z","title":"Universal Domain Adaptation for Semantic Segmentation","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:39.483817Z"},"links":{"citing_paper":"/paper/2505.22458"},"observation_digest":"sha256:510f431c5867781dbf2658a76c06916be7ed23f6252b7ca3e98c83d5407d0b73","observation_id":"1c60044f-78a9-4812-b1ec-089c5873ce1b","resolution":{"observed_at":"2026-08-07T13:13:48.301665Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:13:48.100231Z","title":"Bidirectional learning for domain adaptation of semantic segmentation","venue":null,"work_id":"157cadce-9adf-4e98-b308-8ec1cbe6cba6","year":2019},"citing_paper":{"arxiv_id":"2505.22458","last_updated":"2025-06-05T22:38:25Z","snapshot_observed_at":"2026-08-07T22:12:30.212777Z","submitted_at":"2025-05-28T15:14:11Z","title":"Universal Domain Adaptation for Semantic Segmentation","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:39.619315Z"},"links":{"citing_paper":"/paper/2505.22458"},"observation_digest":"sha256:6b58dd1317043979205bacf9e0e02d00608fcdbd6506e0bc9421553e44093251","observation_id":"643b223e-8c6c-4446-86d7-3f4a3093c5a8","resolution":{"observed_at":"2026-08-07T13:13:48.137516Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:13:47.968629Z","title":"Constructing self-motivated pyramid curriculums for cross- domain semantic segmentation: A non-adversarial approach","venue":null,"work_id":"a3a8cadc-7743-4d04-83f9-a9d5b49a354c","year":2019},"citing_paper":{"arxiv_id":"2505.22458","last_updated":"2025-06-05T22:38:25Z","snapshot_observed_at":"2026-08-07T22:12:30.212777Z","submitted_at":"2025-05-28T15:14:11Z","title":"Universal Domain Adaptation for Semantic Segmentation","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:39.736559Z"},"links":{"citing_paper":"/paper/2505.22458"},"observation_digest":"sha256:2f95e927f047ed1c7ae81db3ee462d605560122dce7b0c11e0cd02007e1769ed","observation_id":"354adf24-5e94-4dc5-953b-4dd52e31ec53","resolution":{"observed_at":"2026-08-07T13:13:48.047107Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1506.04579","last_updated":"2015-11-19T22:19:28Z","snapshot_observed_at":"2026-08-05T00:27:11.198825Z","submitted_at":"2015-06-15T13:00:59Z","title":"ParseNet: Looking Wider to See Better","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1506.04579","snapshot_observed_at":"2026-08-07T13:13:39.843740Z","title":"Parsenet: Looking wider to see better.arXiv preprint arXiv:1506.04579, 2015","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2505.22458","last_updated":"2025-06-05T22:38:25Z","snapshot_observed_at":"2026-08-07T22:12:30.212777Z","submitted_at":"2025-05-28T15:14:11Z","title":"Universal Domain Adaptation for Semantic Segmentation","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:39.843740Z"},"links":{"cited_paper":"/paper/1506.04579","citing_paper":"/paper/2505.22458"},"observation_digest":"sha256:d622f638532e4e1a9dda21987020ebfc1295f2389f122e7080611ff0d38f6b60","observation_id":"499acf74-92cc-4f21-8672-067469b83e52","resolution":{"observed_at":"2026-08-07T13:13:39.843740Z","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":"2026-08-07T13:13:47.835020Z","title":"Fully convolutional networks for semantic segmentation","venue":null,"work_id":"d2504934-3659-4b96-865b-b406d96ffd84","year":2015},"citing_paper":{"arxiv_id":"2505.22458","last_updated":"2025-06-05T22:38:25Z","snapshot_observed_at":"2026-08-07T22:12:30.212777Z","submitted_at":"2025-05-28T15:14:11Z","title":"Universal Domain Adaptation for Semantic Segmentation","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:39.936347Z"},"links":{"citing_paper":"/paper/2505.22458"},"observation_digest":"sha256:70af70e0565a4ae6e92bf3dd01c9a0048e3f1b1dbeb8dd41602abadab6f5e4a2","observation_id":"991ab964-9913-4bc4-a923-10d9c06c0183","resolution":{"observed_at":"2026-08-07T13:13:47.928998Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:13:47.588779Z","title":"Mlnet: Mutual learning network with neighbor- hood invariance for universal domain adaptation","venue":null,"work_id":"130790d5-d245-476f-b6b2-e34523829fb6","year":2024},"citing_paper":{"arxiv_id":"2505.22458","last_updated":"2025-06-05T22:38:25Z","snapshot_observed_at":"2026-08-07T22:12:30.212777Z","submitted_at":"2025-05-28T15:14:11Z","title":"Universal Domain Adaptation for Semantic Segmentation","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:40.091209Z"},"links":{"citing_paper":"/paper/2505.22458"},"observation_digest":"sha256:e4f72c65e230826e52bdbbc743fa292ab0edfa56d372c861c1f33af02f5072b2","observation_id":"0e0c0bb4-bf87-4957-883a-e250aac8f4a9","resolution":{"observed_at":"2026-08-07T13:13:47.675620Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:13:47.446080Z","title":"Pixmatch: Unsu- pervised domain adaptation via pixelwise consistency train- ing","venue":null,"work_id":"35c464e6-e935-47fd-bb49-059200059863","year":null},"citing_paper":{"arxiv_id":"2505.22458","last_updated":"2025-06-05T22:38:25Z","snapshot_observed_at":"2026-08-07T22:12:30.212777Z","submitted_at":"2025-05-28T15:14:11Z","title":"Universal Domain Adaptation for Semantic Segmentation","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:40.212487Z"},"links":{"citing_paper":"/paper/2505.22458"},"observation_digest":"sha256:7337402b7507a8271c8b2f733db112b6158bf2f3bf2d2b2c7625c2852cd26274","observation_id":"a6c8a878-7062-4e43-a6db-eedb7bccd76b","resolution":{"observed_at":"2026-08-07T13:13:47.505333Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:13:47.190102Z","title":"The role of context for object detection and semantic segmentation in the wild","venue":null,"work_id":"a9ecc4d7-e503-492a-a342-e5e18f8a2f2b","year":2014},"citing_paper":{"arxiv_id":"2505.22458","last_updated":"2025-06-05T22:38:25Z","snapshot_observed_at":"2026-08-07T22:12:30.212777Z","submitted_at":"2025-05-28T15:14:11Z","title":"Universal Domain Adaptation for Semantic Segmentation","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:40.381854Z"},"links":{"citing_paper":"/paper/2505.22458"},"observation_digest":"sha256:7e01c7067878665a3d23413bbf5372af94e61722e396413f7c6de3d76838f015","observation_id":"4fa77995-543c-4a0d-b6d8-d2da6a96f270","resolution":{"observed_at":"2026-08-07T13:13:47.323753Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:13:47.033212Z","title":"Unsupervised intra-domain adaptation for se- mantic segmentation through self-supervision","venue":null,"work_id":"4dfeb8be-4ee4-45db-bd2b-4bef24eab3c5","year":2020},"citing_paper":{"arxiv_id":"2505.22458","last_updated":"2025-06-05T22:38:25Z","snapshot_observed_at":"2026-08-07T22:12:30.212777Z","submitted_at":"2025-05-28T15:14:11Z","title":"Universal Domain Adaptation for Semantic Segmentation","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:40.488588Z"},"links":{"citing_paper":"/paper/2505.22458"},"observation_digest":"sha256:4b2431e385aad8dabe2c4f899014f0245de0f8d10a509081086140089b8ce3b9","observation_id":"1ed21738-dee6-4ae9-a3d6-f06388bdcdf4","resolution":{"observed_at":"2026-08-07T13:13:47.127972Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:13:46.757694Z","title":"Prevalence of neural collapse during the terminal phase of deep learning training.Proceedings of the National Academy of Sciences, 117(40):24652–24663, 2020","venue":null,"work_id":"bbf5ba78-9c43-41a6-b352-261627a96c73","year":2020},"citing_paper":{"arxiv_id":"2505.22458","last_updated":"2025-06-05T22:38:25Z","snapshot_observed_at":"2026-08-07T22:12:30.212777Z","submitted_at":"2025-05-28T15:14:11Z","title":"Universal Domain Adaptation for Semantic Segmentation","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:40.744086Z"},"links":{"citing_paper":"/paper/2505.22458"},"observation_digest":"sha256:6838fc4ce91df116d91cd515a68f41f97ab6a62f33687b9c4dff1b5ab181cfb3","observation_id":"3796a133-c886-48e1-9dfe-4f794c16eaf2","resolution":{"observed_at":"2026-08-07T13:13:46.886489Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:13:46.620951Z","title":"Playing for data: Ground truth from computer games","venue":null,"work_id":"368e942b-67cd-4622-a354-8096bc9db717","year":2016},"citing_paper":{"arxiv_id":"2505.22458","last_updated":"2025-06-05T22:38:25Z","snapshot_observed_at":"2026-08-07T22:12:30.212777Z","submitted_at":"2025-05-28T15:14:11Z","title":"Universal Domain Adaptation for Semantic Segmentation","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:41.259497Z"},"links":{"citing_paper":"/paper/2505.22458"},"observation_digest":"sha256:089412d6c40837e33c6d355ac4286c571918548810edba27f6bdca0b57174fbf","observation_id":"167e8f1f-e2d5-4892-8099-0377a70fcf86","resolution":{"observed_at":"2026-08-07T13:13:46.691173Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:13:46.332870Z","title":"Ovanet: One-vs-all net- work for universal domain adaptation","venue":null,"work_id":"c2fc2f9f-ba1f-4597-be3f-3758cd7e3087","year":2021},"citing_paper":{"arxiv_id":"2505.22458","last_updated":"2025-06-05T22:38:25Z","snapshot_observed_at":"2026-08-07T22:12:30.212777Z","submitted_at":"2025-05-28T15:14:11Z","title":"Universal Domain Adaptation for Semantic Segmentation","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:41.556690Z"},"links":{"citing_paper":"/paper/2505.22458"},"observation_digest":"sha256:fb3f35f13bc951374e5894797e664fca27bd10a4c3611f5e83e4f44ef2f0c311","observation_id":"5a60b72d-1476-4aaf-a1d4-a72c35b07787","resolution":{"observed_at":"2026-08-07T13:13:46.485436Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:13:46.122989Z","title":"Universal domain adaptation through self supervi- sion.Advances in neural information processing systems, 33:16282–16292, 2020","venue":null,"work_id":"6d33a47b-7afe-4763-a05c-ae4dcddcab58","year":2020},"citing_paper":{"arxiv_id":"2505.22458","last_updated":"2025-06-05T22:38:25Z","snapshot_observed_at":"2026-08-07T22:12:30.212777Z","submitted_at":"2025-05-28T15:14:11Z","title":"Universal Domain Adaptation for Semantic Segmentation","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:41.627035Z"},"links":{"citing_paper":"/paper/2505.22458"},"observation_digest":"sha256:6e992e442148edbc37b2a551def50643a56ad1f8c7fc1a68ff68c1738674e6fe","observation_id":"2333b8cf-bde4-459e-88df-8a04ae789077","resolution":{"observed_at":"2026-08-07T13:13:46.187908Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:13:41.750064Z","title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results.Advances in neural information processing systems, 30, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.22458","last_updated":"2025-06-05T22:38:25Z","snapshot_observed_at":"2026-08-07T22:12:30.212777Z","submitted_at":"2025-05-28T15:14:11Z","title":"Universal Domain Adaptation for Semantic Segmentation","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:41.750064Z"},"links":{"citing_paper":"/paper/2505.22458"},"observation_digest":"sha256:20e37455004c54711edf011f69b615c8e3f0286bf527cafd70a7e1b7f2022394","observation_id":"0ddf6d12-5fd4-4567-8dfc-323685a99835","resolution":{"observed_at":"2026-08-07T13:13:41.750064Z","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":"2026-08-07T13:13:45.875551Z","title":"Dacs: Domain adaptation via cross- domain mixed sampling","venue":null,"work_id":"e9cda194-c4e1-4062-a204-55ebfc11d943","year":2021},"citing_paper":{"arxiv_id":"2505.22458","last_updated":"2025-06-05T22:38:25Z","snapshot_observed_at":"2026-08-07T22:12:30.212777Z","submitted_at":"2025-05-28T15:14:11Z","title":"Universal Domain Adaptation for Semantic Segmentation","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:41.820991Z"},"links":{"citing_paper":"/paper/2505.22458"},"observation_digest":"sha256:82d7099c4c34ebedbb7608a4ac02b9a339b7b35ae2a1810565fe5898744af4c2","observation_id":"ed28a76b-2971-4dcd-aa5e-92ae02022855","resolution":{"observed_at":"2026-08-07T13:13:46.000818Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:13:45.737900Z","title":"Learning to adapt structured output space for semantic seg- mentation","venue":null,"work_id":"8e1530e1-fb2f-469c-9249-df2eb00eb951","year":null},"citing_paper":{"arxiv_id":"2505.22458","last_updated":"2025-06-05T22:38:25Z","snapshot_observed_at":"2026-08-07T22:12:30.212777Z","submitted_at":"2025-05-28T15:14:11Z","title":"Universal Domain Adaptation for Semantic Segmentation","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:41.941579Z"},"links":{"citing_paper":"/paper/2505.22458"},"observation_digest":"sha256:73e8edcf9da32d7871d467e62d89515c09fe0adb7ebd4fc6be43a846da4eaaf4","observation_id":"2a39c817-ef5d-4e15-a01a-fcf85bab366e","resolution":{"observed_at":"2026-08-07T13:13:45.788189Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:13:45.501974Z","title":"Domain adaptation for structured output via discriminative patch representations","venue":null,"work_id":"57e1ea9d-f05d-40d7-ace2-d1abe9d687fe","year":2019},"citing_paper":{"arxiv_id":"2505.22458","last_updated":"2025-06-05T22:38:25Z","snapshot_observed_at":"2026-08-07T22:12:30.212777Z","submitted_at":"2025-05-28T15:14:11Z","title":"Universal Domain Adaptation for Semantic Segmentation","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:42.011168Z"},"links":{"citing_paper":"/paper/2505.22458"},"observation_digest":"sha256:8e7a9db1a2aa13f76ce07a57694950e1764bcea09d84b2c9335ad2eb83799fb4","observation_id":"2bb2af7d-dab1-4ba8-b204-6d4c9df02d06","resolution":{"observed_at":"2026-08-07T13:13:45.595946Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:13:45.275931Z","title":"Idd: A dataset for exploring problems of autonomous navigation in uncon- strained environments","venue":null,"work_id":"466f646f-7816-4917-8f44-67edeee1f01d","year":2019},"citing_paper":{"arxiv_id":"2505.22458","last_updated":"2025-06-05T22:38:25Z","snapshot_observed_at":"2026-08-07T22:12:30.212777Z","submitted_at":"2025-05-28T15:14:11Z","title":"Universal Domain Adaptation for Semantic Segmentation","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:42.098677Z"},"links":{"citing_paper":"/paper/2505.22458"},"observation_digest":"sha256:5624193d86d11a382e12fb02bf8594927a3ead74d4d6fc8a5ef08915c4a549dc","observation_id":"bea84e08-7ff4-4ea5-a9b7-7a48c5ddddfc","resolution":{"observed_at":"2026-08-07T13:13:45.382016Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:13:45.064121Z","title":"Domain adaptive semantic segmentation with self-supervised depth estimation","venue":null,"work_id":"7eadd715-b4da-4297-a366-40e371e54105","year":2021},"citing_paper":{"arxiv_id":"2505.22458","last_updated":"2025-06-05T22:38:25Z","snapshot_observed_at":"2026-08-07T22:12:30.212777Z","submitted_at":"2025-05-28T15:14:11Z","title":"Universal Domain Adaptation for Semantic Segmentation","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:42.192245Z"},"links":{"citing_paper":"/paper/2505.22458"},"observation_digest":"sha256:46b389a0615eb398e54c1a8bd6f604db35ebabff9b23dcfdba802b0f3ec6d349","observation_id":"63f9761c-0262-4cc7-8a27-0f342f5209cb","resolution":{"observed_at":"2026-08-07T13:13:45.168039Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:13:44.868139Z","title":"Uncertainty-aware pseudo label refinery for domain adaptive semantic segmentation","venue":null,"work_id":"d34e5540-7b66-4863-b1ce-b01c3e185e57","year":2021},"citing_paper":{"arxiv_id":"2505.22458","last_updated":"2025-06-05T22:38:25Z","snapshot_observed_at":"2026-08-07T22:12:30.212777Z","submitted_at":"2025-05-28T15:14:11Z","title":"Universal Domain Adaptation for Semantic Segmentation","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:42.298994Z"},"links":{"citing_paper":"/paper/2505.22458"},"observation_digest":"sha256:59156a22d2d15f810fd5b72192a2a4fd0bcc5cb3f735dcbe53133829aef82b7d","observation_id":"c6eb006a-bca2-4952-883b-fc263c7cd74f","resolution":{"observed_at":"2026-08-07T13:13:44.982165Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:13:44.698537Z","title":"Segformer: Simple and efficient design for semantic segmentation with transform- ers.Advances in Neural Information Processing Systems, 34:12077–12090, 2021","venue":null,"work_id":"694ec141-bad8-49bb-832a-728dc75fd1e5","year":2021},"citing_paper":{"arxiv_id":"2505.22458","last_updated":"2025-06-05T22:38:25Z","snapshot_observed_at":"2026-08-07T22:12:30.212777Z","submitted_at":"2025-05-28T15:14:11Z","title":"Universal Domain Adaptation for Semantic Segmentation","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:42.404171Z"},"links":{"citing_paper":"/paper/2505.22458"},"observation_digest":"sha256:da004e3dbd0f0923d2fedc31e68f49c57a542d760ecbe3e12bba97637a86df9f","observation_id":"946a753d-382a-47a0-af00-00cd14121e4e","resolution":{"observed_at":"2026-08-07T13:13:44.772675Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:13:44.502957Z","title":"Universal domain adaptation","venue":null,"work_id":"1a36fe0c-804e-426c-990f-54cd8d4fdbbc","year":2019},"citing_paper":{"arxiv_id":"2505.22458","last_updated":"2025-06-05T22:38:25Z","snapshot_observed_at":"2026-08-07T22:12:30.212777Z","submitted_at":"2025-05-28T15:14:11Z","title":"Universal Domain Adaptation for Semantic Segmentation","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:42.525472Z"},"links":{"citing_paper":"/paper/2505.22458"},"observation_digest":"sha256:149ce76f0189a504ae322cb8ace31e9e87a7fe2d8e99079443dd25a7220c2b30","observation_id":"1c8507e3-3f4b-45cf-8cdd-9f6a9ab07683","resolution":{"observed_at":"2026-08-07T13:13:44.614476Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.14289","last_updated":"2023-07-01T07:26:22Z","snapshot_observed_at":"2026-07-06T15:46:29.060519Z","submitted_at":"2023-06-25T16:37:25Z","title":"Faster Segment Anything: Towards Lightweight SAM for Mobile Applications","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.14289","snapshot_observed_at":"2026-08-07T13:13:42.651381Z","title":"Faster segment anything: Towards lightweight sam for mo- bile applications.arXiv preprint arXiv:2306.14289, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.22458","last_updated":"2025-06-05T22:38:25Z","snapshot_observed_at":"2026-08-07T22:12:30.212777Z","submitted_at":"2025-05-28T15:14:11Z","title":"Universal Domain Adaptation for Semantic Segmentation","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:42.651381Z"},"links":{"cited_paper":"/paper/2306.14289","citing_paper":"/paper/2505.22458"},"observation_digest":"sha256:f647ea19fdbde3882a17efb43df92663f93785fd44a72cb72c1a195639ec1bb4","observation_id":"0302bbe1-15ba-43e5-8065-258d71b27dc7","resolution":{"observed_at":"2026-08-07T13:13:42.651381Z","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":"2026-08-07T13:13:44.333679Z","title":"Prototypical pseudo label denoising and tar- get structure learning for domain adaptive semantic segmen- tation","venue":null,"work_id":"8c74f8a6-0876-4bdf-a8a0-ff5eea4d8215","year":null},"citing_paper":{"arxiv_id":"2505.22458","last_updated":"2025-06-05T22:38:25Z","snapshot_observed_at":"2026-08-07T22:12:30.212777Z","submitted_at":"2025-05-28T15:14:11Z","title":"Universal Domain Adaptation for Semantic Segmentation","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:42.756014Z"},"links":{"citing_paper":"/paper/2505.22458"},"observation_digest":"sha256:b92d7ba0f3402e142d9bc6cd5aeeadf5ac101d394b3bbc81a0176d77d0ec3416","observation_id":"1f09ace1-835d-4c53-ba2e-77a1b0ab7172","resolution":{"observed_at":"2026-08-07T13:13:44.445251Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:13:42.792805Z","title":"Pyramid scene parsing network","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.22458","last_updated":"2025-06-05T22:38:25Z","snapshot_observed_at":"2026-08-07T22:12:30.212777Z","submitted_at":"2025-05-28T15:14:11Z","title":"Universal Domain Adaptation for Semantic Segmentation","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:42.792805Z"},"links":{"citing_paper":"/paper/2505.22458"},"observation_digest":"sha256:d9f5229a6f34bb643615859228d729c4231275ab093157ae70fa173af78ad123","observation_id":"a319738d-050b-4060-8206-73f39c0a4ca8","resolution":{"observed_at":"2026-08-07T13:13:42.792805Z","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":"2026-08-07T13:13:44.104576Z","title":"Psanet: Point- wise spatial attention network for scene parsing","venue":null,"work_id":"70ef165d-7344-4f7f-a5ec-e209ec3cd2ad","year":2018},"citing_paper":{"arxiv_id":"2505.22458","last_updated":"2025-06-05T22:38:25Z","snapshot_observed_at":"2026-08-07T22:12:30.212777Z","submitted_at":"2025-05-28T15:14:11Z","title":"Universal Domain Adaptation for Semantic Segmentation","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:42.810484Z"},"links":{"citing_paper":"/paper/2505.22458"},"observation_digest":"sha256:d1d04bd251c0ebbd015d83e316b7b981ed69ad47878974e390c5390706624061","observation_id":"ddc91453-94db-4656-aaf9-1b2bae325cb3","resolution":{"observed_at":"2026-08-07T13:13:44.205242Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:13:42.903988Z","title":"Rethinking semantic segmen- tation from a sequence-to-sequence perspective with trans- formers","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.22458","last_updated":"2025-06-05T22:38:25Z","snapshot_observed_at":"2026-08-07T22:12:30.212777Z","submitted_at":"2025-05-28T15:14:11Z","title":"Universal Domain Adaptation for Semantic Segmentation","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:42.903988Z"},"links":{"citing_paper":"/paper/2505.22458"},"observation_digest":"sha256:d3f19a8e4bdfdfc85b95219e67fb18860f41878b1619a27f6a6a5da70aafca65","observation_id":"6fffe085-27a9-4de8-a4ec-9f16dec21b6d","resolution":{"observed_at":"2026-08-07T13:13:42.903988Z","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":"2026-08-07T13:13:43.867196Z","title":"Rethinking semantic segmentation: A proto- type view","venue":null,"work_id":"90506409-7e69-4932-ae45-9b94f73a10cb","year":2022},"citing_paper":{"arxiv_id":"2505.22458","last_updated":"2025-06-05T22:38:25Z","snapshot_observed_at":"2026-08-07T22:12:30.212777Z","submitted_at":"2025-05-28T15:14:11Z","title":"Universal Domain Adaptation for Semantic Segmentation","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:42.975594Z"},"links":{"citing_paper":"/paper/2505.22458"},"observation_digest":"sha256:c8ab90c337f4930968e7e3aaebfbffacb4a55be77d9c7fabfb6ec1729c488742","observation_id":"d8181759-461e-41a7-8a47-ef3ebc4e3fe1","resolution":{"observed_at":"2026-08-07T13:13:43.962500Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:13:43.662914Z","title":"Asymmetric non-local neural networks for seman- tic segmentation","venue":null,"work_id":"a609a5d7-c029-4c64-88ee-f11942ed2c9b","year":null},"citing_paper":{"arxiv_id":"2505.22458","last_updated":"2025-06-05T22:38:25Z","snapshot_observed_at":"2026-08-07T22:12:30.212777Z","submitted_at":"2025-05-28T15:14:11Z","title":"Universal Domain Adaptation for Semantic Segmentation","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:43.138327Z"},"links":{"citing_paper":"/paper/2505.22458"},"observation_digest":"sha256:af60b4abb2289425fb3aae26b65863cdbcd8bd16792603dd796adbaa4127b16b","observation_id":"e522a856-d37b-4c4b-b089-5fb5da89a453","resolution":{"observed_at":"2026-08-07T13:13:43.753727Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:13:43.480432Z","title":"Unsupervised domain adaptation for semantic segmentation via class-balanced self-training","venue":null,"work_id":"f560551d-c110-4c0a-86a9-c9fbe738901e","year":2018},"citing_paper":{"arxiv_id":"2505.22458","last_updated":"2025-06-05T22:38:25Z","snapshot_observed_at":"2026-08-07T22:12:30.212777Z","submitted_at":"2025-05-28T15:14:11Z","title":"Universal Domain Adaptation for Semantic Segmentation","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:43.144032Z"},"links":{"citing_paper":"/paper/2505.22458"},"observation_digest":"sha256:f752084c9ccec5c60d4a3cfb7e9b42417346f6faf8940332c466551cfdd9e08f","observation_id":"0934f3c7-1e37-4648-bd26-3f0dd93462ac","resolution":{"observed_at":"2026-08-07T13:13:43.569334Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T13:13:43.305839Z","title":"Confidence regularized self-training","venue":null,"work_id":"6f3307db-ccb0-4c6c-a20f-225c40fa8137","year":2019},"citing_paper":{"arxiv_id":"2505.22458","last_updated":"2025-06-05T22:38:25Z","snapshot_observed_at":"2026-08-07T22:12:30.212777Z","submitted_at":"2025-05-28T15:14:11Z","title":"Universal Domain Adaptation for Semantic Segmentation","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-07T13:13:43.154341Z"},"links":{"citing_paper":"/paper/2505.22458"},"observation_digest":"sha256:712aa31cd72bef0196206cca00152286b0ce2a24a8580dc2261db727641d8253","observation_id":"85b0f9d7-e47e-4e6c-b0f4-fa2de59b71f6","resolution":{"observed_at":"2026-08-07T13:13:43.395134Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2505.22458","last_updated":"2025-06-05T22:38:25Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-07T22:12:30.212777Z","submitted_at":"2025-05-28T15:14:11Z","title":"Universal Domain Adaptation for Semantic Segmentation"},"reference_resolution":{"displayed":47,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":9,"verified_exact":0,"verified_fuzzy":38},"total_outbound_references":47},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 47 of 47 outbound references and 0 inbound Pith citation observations for arXiv:2505.22458."}