{"as_of":"2026-08-12T14:40:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:fed81966375ec8b7ace189ad530d45ad2db1240ae288f3b4ca7bfc2b352b97e5","coverage":[{"denominator":86,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":86,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T22:46:20.024862Z","state":"measured"},{"denominator":86,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":86,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-12T06:34:41.77262+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/2506.22509/citation-record","integrity":"/paper/2506.22509/integrity","json":"/paper/2506.22509/citation-record.json","paper":"/paper/2506.22509"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T22:46:19.552289Z","title":"Ntire 2017 challenge on single image super-resolution: Dataset and study","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.552289Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:08a106fdcfd33a689441152d928cdfd99b3666de23b4c7228e58ac040cf2de6e","observation_id":"d08c52a0-b7aa-464f-95c0-2ae0733b273d","resolution":{"observed_at":"2026-08-06T22:46:19.552289Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2112.00390","last_updated":"2022-09-07T04:14:48Z","snapshot_observed_at":"2026-08-07T15:26:15.477145Z","submitted_at":"2021-12-01T10:17:25Z","title":"SegDiff: Image Segmentation with Diffusion Probabilistic Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2112.00390","snapshot_observed_at":"2026-08-06T22:46:19.558486Z","title":"Segdiff: Image segmentation with diffusion proba- bilistic models.arXiv preprint arXiv:2112.00390, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.558486Z"},"links":{"cited_paper":"/paper/2112.00390","citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:28935f4c72309f068f86a1480fb9998bfb6af2e4c95db50606e52eaa2730c3fc","observation_id":"5621f5a6-0016-4454-8950-4e0f13f710ae","resolution":{"observed_at":"2026-08-06T22:46:19.558486Z","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":"2026-08-06T22:46:19.565129Z","title":"Test-time adaptation for optical flow estimation using motion vec- tors.IEEE Transactions on Image Processing, 32:4977– 4988, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.565129Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:7f29b7572d4b0aae6751f9237d759df3980fd624e180b531a9a3a82b8edf0bd7","observation_id":"ddbb6e7f-945d-492e-aad3-1ddfdb3b4ae1","resolution":{"observed_at":"2026-08-06T22:46:19.565129Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.06503","last_updated":"2022-05-03T08:05:54Z","snapshot_observed_at":"2026-08-12T08:50:33.587550Z","submitted_at":"2022-01-17T16:28:12Z","title":"Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.06503","snapshot_observed_at":"2026-08-06T22:46:19.570585Z","title":"Analytic- dpm: an analytic estimate of the optimal reverse vari- ance in diffusion probabilistic models.arXiv preprint arXiv:2201.06503, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.570585Z"},"links":{"cited_paper":"/paper/2201.06503","citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:0f77b939a768ccdd0c62536ab1b7e0a913be806ee99fcbe02543881f720deaf2","observation_id":"10595e6a-2339-43d0-a784-d546d415e23c","resolution":{"observed_at":"2026-08-06T22:46:19.570585Z","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":"2026-08-06T22:46:19.575775Z","title":"Analysis of representations for domain adapta- tion.Advances in neural information processing systems, 19, 2006","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.575775Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:9d09608a6d96b85e681950ad71653b68d946ebe67fa940ee52b3eca646b7b4e9","observation_id":"858b24cd-ec90-4e95-9b5b-ba3d95d833c7","resolution":{"observed_at":"2026-08-06T22:46:19.575775Z","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":"2026-08-06T22:46:19.581184Z","title":"One-shot unsupervised do- main adaptation with personalized diffusion models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.581184Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:2b3eb702adc6aae674baf52952cfcf953d06e2dc06b9b0ae709d7b07a2a2a8a0","observation_id":"be0bc5bf-2380-4fe7-affd-a80af50c01dd","resolution":{"observed_at":"2026-08-06T22:46:19.581184Z","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":"2026-08-06T22:46:19.587235Z","title":"Contrastive model adaptation for cross- condition robustness in semantic segmentation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.587235Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:6bc07d0ba5e4f94b777d728b2b9543620d72d71596322360774ba394959e3b15","observation_id":"22215e1a-aa65-4b94-90fb-11310ae2f8f0","resolution":{"observed_at":"2026-08-06T22:46:19.587235Z","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":"2026-08-06T22:46:19.593101Z","title":"A naturalistic open source movie for opti- cal flow evaluation","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.593101Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:bc384f7754fd04700010dcf1f1d093f5bb08752e0b2b3500241b3bb71f8df8cd","observation_id":"f3619697-bfbb-42f0-b81b-9bc513c4ecad","resolution":{"observed_at":"2026-08-06T22:46:19.593101Z","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":"2026-08-06T22:46:19.597515Z","title":"nuscenes: A multi- modal dataset for autonomous driving","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.597515Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:b4c7d8cac31d99782ac912d5868a82ca74b43ee4c5654ccb4f105f544594e230","observation_id":"5bcc08aa-ea56-459d-8297-c38ef80144e9","resolution":{"observed_at":"2026-08-06T22:46:19.597515Z","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":"2026-08-06T22:46:21.675924Z","title":"Toward real-world single image super-resolution: A new benchmark and a new model","venue":null,"work_id":"ac4d7814-0b7f-4097-8c58-aed415931d93","year":2019},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.601969Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:4a3dab5490b6596f52f921a4fb1a8bdb39690d1f40cc65b481f82b6889333cb6","observation_id":"fe58b432-3508-4e32-9ac5-68102b6070b0","resolution":{"observed_at":"2026-08-06T22:46:21.681772Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T22:46:21.657392Z","title":"Progressive feature alignment for unsupervised do- main adaptation","venue":null,"work_id":"154a2634-a3bb-4547-b900-de388385caaf","year":2019},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.606548Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:79c166682a4aa7e6a147dd8faf5f28a71f366bc818030616585851d06d71fb46","observation_id":"593a2fdb-1e4e-4a5f-a3a5-e6821fde01e0","resolution":{"observed_at":"2026-08-06T22:46:21.663282Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T22:46:19.611178Z","title":"Amplitude-phase recombination: Rethink- ing robustness of convolutional neural networks in frequency domain","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.611178Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:3edfa7bb0e8e4a2298eb3d8652d11dcfa6f21dc422d5ec550076644795bf058f","observation_id":"8670cbef-83fe-4269-ac5f-e6b9f0eef27a","resolution":{"observed_at":"2026-08-06T22:46:19.611178Z","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":"2026-08-06T22:46:21.627122Z","title":"S2r-depthnet: Learning a generalizable depth-specific structural representation","venue":null,"work_id":"6d49271a-863c-4d3c-b679-a625b1d1c350","year":2021},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.615767Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:702439f47cfe9df8d2484cee1e9a6fba80a0ba3e8007ce1c3ba359a888884333","observation_id":"cbf49ec6-66e0-4176-a715-8edc3b1e77f4","resolution":{"observed_at":"2026-08-06T22:46:21.632128Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T22:46:21.609782Z","title":"Text-to-image diffusion mod- els are zero shot classifiers.Advances in Neural Information Processing Systems, 36:58921–58937, 2023","venue":null,"work_id":"a02b0840-b9a1-4f68-bc30-7ba1bbe3a3d8","year":2023},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.621058Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:a76f0de52a17a88c98a6b8198f6dfabcbe1ef20379e1c0b4b6d244a132df9ed8","observation_id":"9ef0f121-38a6-4074-a59e-1ae979a81b91","resolution":{"observed_at":"2026-08-06T22:46:21.615124Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T22:46:19.626307Z","title":"The cityscapes dataset for semantic urban scene understanding","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.626307Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:d8c61ccb92705b4a4884a7ec0fc0bf91e60cb1418bed72d3c42a2fb9301c18c7","observation_id":"56b06615-af3f-4704-9720-47e142199f05","resolution":{"observed_at":"2026-08-06T22:46:19.626307Z","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":"2026-08-06T22:46:21.579404Z","title":"Joint distribution optimal transportation for domain adaptation.Advances in neural information pro- cessing systems, 30, 2017","venue":null,"work_id":"c3a2879d-ca8f-4956-9b33-31748a1726f9","year":2017},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.630784Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:2becce061009b4d549f6c5b27d8e10f20fbd4b9e9e3f88eb337c16063c84c998","observation_id":"bcb0d816-66e1-4946-a020-3a13ef217528","resolution":{"observed_at":"2026-08-06T22:46:21.585847Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1702.05374","last_updated":"2017-03-30T15:42:12Z","snapshot_observed_at":"2026-07-06T05:30:25.930441Z","submitted_at":"2017-02-17T15:07:40Z","title":"Domain Adaptation for Visual Applications: A Comprehensive Survey","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1702.05374","snapshot_observed_at":"2026-08-06T22:46:19.635632Z","title":"Domain adaptation for visual applications: A comprehensive survey.arXiv preprint arXiv:1702.05374,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.635632Z"},"links":{"cited_paper":"/paper/1702.05374","citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:b94c580655a72dd811e25b1a7bbc854d7f9f6b147d5b7a0545a6748f214c7a00","observation_id":"81c08683-536e-4434-b32f-f1aa20aa2b94","resolution":{"observed_at":"2026-08-06T22:46:19.635632Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.01746","last_updated":"2023-12-04T09:10:25Z","snapshot_observed_at":"2026-08-11T19:00:58.923313Z","submitted_at":"2023-12-04T09:10:25Z","title":"Open-DDVM: A Reproduction and Extension of Diffusion Model for Optical Flow Estimation","version":1},"cited_work":{"arxiv_id":"2312.01746","doi":null,"metadata_source":"pith","pith_arxiv_id":"2312.01746","snapshot_observed_at":"2026-08-06T22:46:20.607275Z","title":"Open-DDVM: A Reproduction and Extension of Diffusion Model for Optical Flow Estimation","venue":"cs.CV","work_id":"274cf105-e23c-4635-ae73-5ea7f589cdcf","year":2023},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.640733Z"},"links":{"cited_paper":"/paper/2312.01746","citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:db1c614e221d5920551c617345c26995e27c64c9a1c4f2577393de16e778895c","observation_id":"2716d3f4-b48e-4c81-bc37-8d0ec7150ce3","resolution":{"observed_at":"2026-08-06T22:46:20.614940Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1505.03906","last_updated":"2015-05-14T22:18:42Z","snapshot_observed_at":"2026-07-06T04:17:55.895445Z","submitted_at":"2015-05-14T22:18:42Z","title":"Training generative neural networks via Maximum Mean Discrepancy optimization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1505.03906","snapshot_observed_at":"2026-08-06T22:46:19.646286Z","title":"Training generative neural networks via maximum mean discrepancy optimization.arXiv preprint arXiv:1505.03906, 2015","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.646286Z"},"links":{"cited_paper":"/paper/1505.03906","citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:a947487190857872507df1da1ece91bcab01f31c94da3e75b12255af9cb81a56","observation_id":"a6229ce5-1eb0-4a6b-9c85-3134c41c9064","resolution":{"observed_at":"2026-08-06T22:46:19.646286Z","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":"2026-08-06T22:46:19.652640Z","title":"A brief review of domain adaptation","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.652640Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:c9969d7c45944befc34a275974eb047e95cccf59dbe2f0b8b50b5072cc1f975a","observation_id":"983f1c99-4323-4425-833f-feaa658196f2","resolution":{"observed_at":"2026-08-06T22:46:19.652640Z","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":"2026-08-06T22:46:21.548279Z","title":"Virtual worlds as proxy for multi-object tracking anal- ysis","venue":null,"work_id":"72b985bc-c35b-4d56-b209-1fc93ae799b9","year":2016},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.657169Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:c1104fe439fa01b6c77ca701c50c5099b62d25245cace7f50f40b281c2c56c39","observation_id":"f817344a-296e-417f-afb4-996d0a1579be","resolution":{"observed_at":"2026-08-06T22:46:21.553485Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T22:46:19.661537Z","title":"Domain-adversarial training of neural networks.Journal of machine learning research, 17(59):1–35, 2016","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.661537Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:adc2d12e1b390ee63239b68d36e5e890e576a0f7d1dda6b40470d1a91ca3c5eb","observation_id":"8d2c328e-9f37-4cf4-afa2-bff39724b06d","resolution":{"observed_at":"2026-08-06T22:46:19.661537Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.18124","last_updated":"2025-01-18T20:14:54Z","snapshot_observed_at":"2026-08-12T06:19:10.348850Z","submitted_at":"2024-09-26T17:58:55Z","title":"Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.18124","snapshot_observed_at":"2026-08-06T22:46:19.666447Z","title":"Lotus: Diffusion-based visual foundation model for high-quality dense prediction.arXiv preprint arXiv:2409.18124, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.666447Z"},"links":{"cited_paper":"/paper/2409.18124","citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:9b36b9cc75bc864688faebbdc4a29dd9321bd32118ca596832714e948fc41cae","observation_id":"79f90f1d-71c7-49ac-a5fc-81842e49e766","resolution":{"observed_at":"2026-08-06T22:46:19.666447Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.05387","last_updated":"2023-12-08T21:52:00Z","snapshot_observed_at":"2026-07-06T16:59:03.166901Z","submitted_at":"2023-12-08T21:52:00Z","title":"Cross Domain Generative Augmentation: Domain Generalization with Latent Diffusion Models","version":1},"cited_work":{"arxiv_id":"2312.05387","doi":null,"metadata_source":"pith","pith_arxiv_id":"2312.05387","snapshot_observed_at":"2026-08-06T22:46:20.543794Z","title":"Cross Domain Generative Augmentation: Domain Generalization with Latent Diffusion Models","venue":"cs.LG","work_id":"53983112-a756-4cba-9be4-2ba91fe49284","year":2023},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.671298Z"},"links":{"cited_paper":"/paper/2312.05387","citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:327cbd4816e41f1094748638e2aa46011709ebe85262e2e4844e358cfa507dcb","observation_id":"962be878-d998-4072-a208-d25d6e272c4d","resolution":{"observed_at":"2026-08-06T22:46:20.551193Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2207.12598","last_updated":"2022-07-26T01:42:07Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2022-07-26T01:42:07Z","title":"Classifier-Free Diffusion Guidance","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2207.12598","snapshot_observed_at":"2026-08-06T22:46:19.676623Z","title":"Classifier-free diffusion guidance.arXiv preprint arXiv:2207.12598, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.676623Z"},"links":{"cited_paper":"/paper/2207.12598","citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:3366970bdb0a3fd5a5afb4305c120a3034f2ab275ac29ec4ab8a1dc5252db048","observation_id":"057b51cc-de30-4cde-b7b1-6639a0a67464","resolution":{"observed_at":"2026-08-06T22:46:19.676623Z","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":"2026-08-06T22:46:19.682365Z","title":"Cascaded diffu- sion models for high fidelity image generation.Journal of Machine Learning Research, 23(47):1–33, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.682365Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:4d0b9069ec3a542e6d48d08d7aa90031fa1383736e17a16ecbc154158a15cbf1","observation_id":"39751d7e-35e3-4045-9577-abc1bea3c408","resolution":{"observed_at":"2026-08-06T22:46:19.682365Z","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":"2026-08-06T22:46:21.511063Z","title":"Daformer: Improving network architectures and training strategies for domain-adaptive semantic segmentation","venue":null,"work_id":"fcb260d4-6bbf-4936-9925-e67d700e13a5","year":2022},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.688350Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:ae8f622505cc16a5f1171d5e6de003057fe23487daa16a424861a153149ea8d9","observation_id":"c185016a-95e0-45cf-bcd5-15cba5724e57","resolution":{"observed_at":"2026-08-06T22:46:21.516387Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T22:46:19.693264Z","title":"Arbitrary style transfer in real-time with adaptive instance normalization","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.693264Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:e7869a95bebfaa16facfcf6824f8ed94de94b60532263b14c0ad0bb5af02e387","observation_id":"84820182-5f2a-4d5f-9e5d-97f1a68066f3","resolution":{"observed_at":"2026-08-06T22:46:19.693264Z","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":"2026-08-06T22:46:19.698561Z","title":"Dpbridge: La- tent diffusion bridge for dense prediction.arXiv preprint arXiv:2412.20506, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.698561Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:1ca9b655e7fb50b65b9006c8a7ed45160c7076a3d4d0d07d8c8b53b2daf5b945","observation_id":"00772ae5-e8e3-4de9-8772-3d47b9a2d863","resolution":{"observed_at":"2026-08-06T22:46:19.698561Z","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":"2026-08-06T22:46:21.482918Z","title":"Ddp: Diffusion model for dense visual prediction","venue":null,"work_id":"fbe099ce-e78c-480a-865d-5de3e4fcfdfb","year":2023},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.702817Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:bba111013b899734ad2770fb40fdf3ff289899af1f5c02b117a2bf783b30a133","observation_id":"5ed75a27-68d0-44a3-b188-98e55ce3f139","resolution":{"observed_at":"2026-08-06T22:46:21.488194Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T22:46:21.465482Z","title":"Repurpos- ing diffusion-based image generators for monocular depth estimation","venue":null,"work_id":"325d4abb-ad7e-4177-96a4-2d5f6a637eee","year":2024},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.707153Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:959c2ac876e51fb9a2154d841a7477d8164b1899908d028b5bef72be67b4b3cf","observation_id":"6a6e5bbb-7964-41aa-ae3d-c4cd595788ff","resolution":{"observed_at":"2026-08-06T22:46:21.470928Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T22:46:19.711456Z","title":"Musiq: Multi-scale image quality transformer","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.711456Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:2a5c4996d23842e9b73e6d21e8df2ce5c0a4f5b81f2c544c561d2e1eb6bb57d5","observation_id":"32c7d410-c270-43e5-a0c5-19ab65eb5259","resolution":{"observed_at":"2026-08-06T22:46:19.711456Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.12047","last_updated":"2023-02-23T14:19:07Z","snapshot_observed_at":"2026-07-06T14:55:04.061802Z","submitted_at":"2023-02-23T14:19:07Z","title":"Domain Generalisation via Domain Adaptation: An Adversarial Fourier Amplitude Approach","version":1},"cited_work":{"arxiv_id":"2302.12047","doi":null,"metadata_source":"pith","pith_arxiv_id":"2302.12047","snapshot_observed_at":"2026-08-06T22:46:20.216008Z","title":"Domain Generalisation via Domain Adaptation: An Adversarial Fourier Amplitude Approach","venue":"cs.LG","work_id":"8d802e98-fafc-46d3-b236-d9b700dfc6ee","year":2023},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.716250Z"},"links":{"cited_paper":"/paper/2302.12047","citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:70a92ffb387b0c98bb8e1ee17bf9982e1d0e46765059b1ecfa5cfde0e6aae4c3","observation_id":"af0e54d9-58ab-4312-8972-801de47fab64","resolution":{"observed_at":"2026-08-06T22:46:20.222995Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T22:46:21.435167Z","title":"Semi-supervised do- main adaptation via selective pseudo labeling and progres- sive self-training","venue":null,"work_id":"f149f822-85b9-45c2-a177-a1f73b612d78","year":2021},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.721273Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:6b73fb5efa1490542bf8d910e799e8d0153c6be851320f360f3861fbc28f822f","observation_id":"2e079107-5f74-4714-9c68-91a89fd435bc","resolution":{"observed_at":"2026-08-06T22:46:21.440246Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T22:46:21.419772Z","title":"Ex- ploiting diffusion prior for generalizable dense prediction","venue":null,"work_id":"bb6be876-17a0-4ed3-925a-b1afbb3195e7","year":2024},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.727840Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:5784ec1c843f5f2ab350cc9dccbbdfc4a7ff1643dcbef7c90e4633a3b295000c","observation_id":"56807980-ffec-4631-933b-0e14962c9ee9","resolution":{"observed_at":"2026-08-06T22:46:21.424726Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T22:46:19.732477Z","title":"Your diffusion model is secretly a zero-shot classifier","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.732477Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:dcf8549a334283a3624c8c012eed295bbb364246aa4a72f5b80cab953b594e9e","observation_id":"f1b0ddb5-b3aa-4d30-b6a6-48a36e860488","resolution":{"observed_at":"2026-08-06T22:46:19.732477Z","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":"2026-08-06T22:46:21.393486Z","title":"Maximum density divergence for domain adaptation.IEEE transactions on pattern analysis and machine intelligence, 43(11):3918–3930, 2020","venue":null,"work_id":"ccb1d824-6ebe-49e0-ab28-587ea8f12b44","year":2020},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.737454Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:919c68fd7e1584abbfc59e16ca7ed05b4d35675844623aff4df545ccc1d97ea2","observation_id":"ac10a987-d80f-4a33-87a3-04d6cb00b29c","resolution":{"observed_at":"2026-08-06T22:46:21.399451Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.15583","last_updated":"2024-06-16T15:12:11Z","snapshot_observed_at":"2026-07-06T15:32:58.159006Z","submitted_at":"2023-05-24T21:39:27Z","title":"Alleviating Exposure Bias in Diffusion Models through Sampling with Shifted Time Steps","version":8},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.15583","snapshot_observed_at":"2026-08-06T22:46:19.742670Z","title":"Alleviating exposure bias in diffusion mod- els through sampling with shifted time steps.arXiv preprint arXiv:2305.15583, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.742670Z"},"links":{"cited_paper":"/paper/2305.15583","citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:47849cc109769f3568028452cce17f01fcc893e9b535f29137927f81a953ddf8","observation_id":"86adab34-8262-4fcb-be91-487012aff1c0","resolution":{"observed_at":"2026-08-06T22:46:19.742670Z","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":"2026-08-06T22:46:21.375850Z","title":"Unsupervised domain adap- tation with progressive adaptation of subspaces.Pattern Recognition, 132:108918, 2022","venue":null,"work_id":"6d3d5efc-8da8-4eea-8da2-61f6805f0b0c","year":2022},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.747798Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:6ee538c114c4f666f81faf8162613dfd44770193056dbda868b55513253a4e63","observation_id":"3ec8d72f-5a72-42d0-99f8-a17d3167d682","resolution":{"observed_at":"2026-08-06T22:46:21.381814Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T22:46:21.360401Z","title":"Test- time domain adaptation for monocular depth estimation","venue":null,"work_id":"23357ad4-025c-4430-81b5-ee45a722bc29","year":2023},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.753568Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:6eb67020eebe52df8f29c1de0e680d62d64b49caa5feeefb7fd828ca9bd3d665","observation_id":"47f62d11-b81a-4830-9b01-3a66af7cfa53","resolution":{"observed_at":"2026-08-06T22:46:21.365310Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T22:46:19.758708Z","title":"Swinir: Image restoration us- ing swin transformer","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.758708Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:5af30c40a6f2841502c8b8048acc9325d7976c9555d3bd1ccace44794cab63a4","observation_id":"ff04ac35-fe92-41e1-871a-1fe3fdbfdfda","resolution":{"observed_at":"2026-08-06T22:46:19.758708Z","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":"2026-08-06T22:46:21.328136Z","title":"Common diffusion noise schedules and sample steps are flawed","venue":null,"work_id":"626b86f2-f83c-45a5-8b1e-d104d71633d2","year":2024},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.764191Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:4e3f030480388564326997f65ea32c8e90aecd8a4e7f862b19846e613b5bcf25","observation_id":"8bc73fb4-5e6d-4dbd-84f2-d8f90597e20b","resolution":{"observed_at":"2026-08-06T22:46:21.334171Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T22:46:21.305566Z","title":"Diff- bir: Toward blind image restoration with generative diffusion prior","venue":null,"work_id":"05a6dc44-18db-4757-943a-3c3ab28859c4","year":2024},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.770663Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:cdb2f38e5cfc2bd8192315c4e737fe9d8b2344d10b15b5ad95899b0cb8774264","observation_id":"adbd9662-aa1b-4f7d-b8f8-6c658a14ff5c","resolution":{"observed_at":"2026-08-06T22:46:21.312149Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T22:46:21.288442Z","title":"Stability and generalization in structured prediction.Journal of Machine Learning Research, 17(221):1–52, 2016","venue":null,"work_id":"3b78623b-22b9-411d-b9ac-58f02ed54a5f","year":2016},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.776719Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:6637f63e865ee7d777b3099322d095f6c071010f3b0a12538c45ecc9025f9c87","observation_id":"cb40bd47-23d7-48d2-b85f-7e1be2c23021","resolution":{"observed_at":"2026-08-06T22:46:21.293362Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T22:46:21.272666Z","title":"Conditional adversarial domain adapta- tion.Advances in neural information processing systems, 31, 2018","venue":null,"work_id":"099bbe1b-3fb8-4e08-b032-c6219b6a9b88","year":2018},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.781617Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:edad676d405f147e5ef9b7300fb4d7545de89d448c4e40948663947481f62d53","observation_id":"b14e9997-08d1-4f67-b9e0-7976d4653766","resolution":{"observed_at":"2026-08-06T22:46:21.277255Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T22:46:21.256201Z","title":"Desc: Domain adaptation for depth estimation via semantic con- sistency.International Journal of Computer Vision, 131(3): 752–771, 2023","venue":null,"work_id":"9d448731-5029-49f4-879d-702e035b6c77","year":2023},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.788154Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:f3e196f60363f3e1c4926636ec5fe6f1df71169aaca8e6394b2eef3bfec5fd94","observation_id":"b1232960-8f34-4bd9-a88c-34424cee6acb","resolution":{"observed_at":"2026-08-06T22:46:21.261925Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T22:46:19.793897Z","title":"Flowdiffuser: Advancing optical flow estimation with diffusion models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.793897Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:66d6d64a1e73236fd04fdd13b1a496775ef785e7c408646934c29f6bdea151cc","observation_id":"996f0244-af51-4585-b02b-b77891c58d69","resolution":{"observed_at":"2026-08-06T22:46:19.793897Z","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":"2026-08-06T22:46:21.225837Z","title":"1 year, 1000 km: The oxford robotcar dataset","venue":null,"work_id":"fe135ccf-8e9d-432a-a84b-9dc615ab8de0","year":null},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.800057Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:4538e0bfe303aac7b6db1bd95d79530ed32f80394a8f22e3c02abdf9a96e6818","observation_id":"56d1d5d6-4d1c-4e04-8062-375107f0d92c","resolution":{"observed_at":"2026-08-06T22:46:21.231671Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T22:46:21.207909Z","title":"Generalization by adaptation: Diffusion-based domain extension for domain-generalized semantic segmentation","venue":null,"work_id":"91797cfb-690d-4740-bed9-2b5e53f8878a","year":2024},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.805801Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:3ca6f4743073a6ea9dcc46a3ad512d22d9e4e093d97b935e33a71b3d38685f12","observation_id":"361155d2-3b2e-42d0-bcc2-196b30bcc4a6","resolution":{"observed_at":"2026-08-06T22:46:21.213991Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.15321","last_updated":"2024-04-10T18:13:00Z","snapshot_observed_at":"2026-08-12T00:14:03.084948Z","submitted_at":"2023-08-29T14:16:09Z","title":"Elucidating the Exposure Bias in Diffusion Models","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.15321","snapshot_observed_at":"2026-08-06T22:46:19.811786Z","title":"Elucidating the exposure bias in diffusion models.arXiv preprint arXiv:2308.15321, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.811786Z"},"links":{"cited_paper":"/paper/2308.15321","citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:2733c10d7e27dfdde87ccfcf610c055e7bc33b4b6357584bffab59dcfc568d22","observation_id":"98654895-5a7b-4405-afa8-af7a454aba1a","resolution":{"observed_at":"2026-08-06T22:46:19.811786Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2301.11706","last_updated":"2023-06-18T14:41:57Z","snapshot_observed_at":"2026-07-06T14:45:15.791471Z","submitted_at":"2023-01-27T13:34:54Z","title":"Input Perturbation Reduces Exposure Bias in Diffusion Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.11706","snapshot_observed_at":"2026-08-06T22:46:19.818201Z","title":"Input perturbation re- duces exposure bias in diffusion models.arXiv preprint arXiv:2301.11706, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.818201Z"},"links":{"cited_paper":"/paper/2301.11706","citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:c20fe9d00bc23ab7604590952bc657c1bcedf0b80d7c6db22d1feefbee7f33e6","observation_id":"04517ec6-5a21-4a97-8a3f-50e8ad323294","resolution":{"observed_at":"2026-08-06T22:46:19.818201Z","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":"2026-08-06T22:46:21.190335Z","title":null,"venue":null,"work_id":"338124a2-e616-4bd7-9c79-12dac5ce3173","year":2020},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.824545Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:0980080d05bf2e5a7a6e50b2b30df8afa0a9b76990b0f764030aec3bd56716f9","observation_id":"c356b1e4-534a-4269-8b9a-cca09be9f826","resolution":{"observed_at":"2026-08-06T22:46:21.196070Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T22:46:21.172905Z","title":"Vi- sion transformers for dense prediction","venue":null,"work_id":"fc59e1af-3796-455c-b028-827c667c63c7","year":2021},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.837584Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:94f2596fbb492de0a07b691a3b9f83a70e849233f47959e9e12f7635e573c3c2","observation_id":"df95d1da-ec04-4498-a28e-e21a4167da97","resolution":{"observed_at":"2026-08-06T22:46:21.178419Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T22:46:21.156059Z","title":"Multi-step denoising scheduled sampling: Towards alleviating exposure bias for diffusion models","venue":null,"work_id":"d2603bd2-26eb-43ca-8c89-bf5442ba0e00","year":2024},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.843282Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:7575d100c4dc4b3929279476e38c451997d366b136df0d858aa4c259572eb1c4","observation_id":"c114f3ad-8140-49e6-b949-c7bb75ceb797","resolution":{"observed_at":"2026-08-06T22:46:21.161220Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T22:46:19.849864Z","title":"Hypersim: A photorealistic syn- thetic dataset for holistic indoor scene understanding","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.849864Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:b42acc83f4235c88edd2a945ed3c9b641a92c5f7ce8f79d38b60a863fc5cb5a0","observation_id":"748dc212-6971-4fa8-9571-dc97dc0665c9","resolution":{"observed_at":"2026-08-06T22:46:19.849864Z","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":"2026-08-06T22:46:19.855302Z","title":"High-resolution image synthesis with latent diffusion models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.855302Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:be463605dfdc0e44d406e87c145116a411eca579f3991e9bad3f9cefdadf605c","observation_id":"909e9647-0c46-4578-b6db-df14a9c85007","resolution":{"observed_at":"2026-08-06T22:46:19.855302Z","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":"2026-08-06T22:46:21.118077Z","title":"Universal domain adaptation through self supervi- sion.Advances in neural information processing systems, 33:16282–16292, 2020","venue":null,"work_id":"049cab7b-2492-411d-9d8a-a4f575f66b75","year":2020},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.860108Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:d6b18d036d17e9d5978eb96b98422e73565a94f291550e180a14e92549dc3596","observation_id":"23af3349-460c-4459-a54b-1f962581e4f0","resolution":{"observed_at":"2026-08-06T22:46:21.124185Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T22:46:21.100902Z","title":null,"venue":null,"work_id":"d3e4010c-9aa0-48be-9a69-9e91fe2d7521","year":2020},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.864867Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:3045047f6d8f1e307db03d3d380a2ecf66201d4e43cb4f8e51bc8e8f175b2c52","observation_id":"268e47b6-1d58-4516-90ed-5762eba6b3d4","resolution":{"observed_at":"2026-08-06T22:46:21.105655Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T22:46:21.084842Z","title":"Acdc: The adverse conditions dataset with correspondences for semantic driving scene understanding","venue":null,"work_id":"4391f9e7-65b7-4014-bb50-41ac353b33f8","year":2021},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.870073Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:2274b66d46e98ccca42bdfc97515c4bdefdc2d432ad24398432d25b5c92c1e39","observation_id":"a747f126-8f90-4cb3-8205-ac4259192876","resolution":{"observed_at":"2026-08-06T22:46:21.090591Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T22:46:21.067796Z","title":"The surprising effectiveness of diffusion models for optical flow and monocular depth estimation.Advances in Neural Information Processing Systems, 36:39443–39469, 2023","venue":null,"work_id":"e24f08bc-25f2-4f43-b8ba-b19ccd50f9be","year":2023},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.874907Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:8e7351287d790807417bac59992b0a485e802e8b76ff4e618c3bf5b78e01e266","observation_id":"4b34a87e-4250-4b7e-9d89-af488ac0760a","resolution":{"observed_at":"2026-08-06T22:46:21.073442Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T22:46:19.879727Z","title":"Laion-5b: An open large-scale dataset for training next generation image-text models.Advances in neural in- formation processing systems, 35:25278–25294, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.879727Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:b1e42e4aa30d9d922e144954811b20209cbebea5a02a6c7f412e498579f2d153","observation_id":"6b30d417-a09a-4b36-a4d1-85399315bb29","resolution":{"observed_at":"2026-08-06T22:46:19.879727Z","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":"2026-08-06T22:46:21.040633Z","title":"Indoor segmentation and support inference from rgbd images","venue":null,"work_id":"af146297-d6a8-41c0-b0d3-d4d9f6756a16","year":2012},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.886310Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:03b7b7ef3aa7250faca1680733030229db1b2a5ccd20261ca9706ea55a2ff9b5","observation_id":"0889ca79-dcd9-4641-83a1-e5b0b2464a49","resolution":{"observed_at":"2026-08-06T22:46:21.045805Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2212.04473","last_updated":"2022-12-09T08:58:13Z","snapshot_observed_at":"2026-08-08T09:01:41.824069Z","submitted_at":"2022-12-08T18:46:19Z","title":"Diffusion Guided Domain Adaptation of Image Generators","version":2},"cited_work":{"arxiv_id":"2212.04473","doi":null,"metadata_source":"pith","pith_arxiv_id":"2212.04473","snapshot_observed_at":"2026-08-06T22:46:20.130843Z","title":"Diffusion Guided Domain Adaptation of Image Generators","venue":"cs.CV","work_id":"97f5a1c4-b9b1-4b81-bfa1-39f3e51aa1e9","year":2022},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.891803Z"},"links":{"cited_paper":"/paper/2212.04473","citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:9f40215552ad2632e87c8d3626f21693d68d8590f447d2c5b86f9023699a6fd4","observation_id":"eec69955-e386-4bb9-90ce-d24c92cdcc1c","resolution":{"observed_at":"2026-08-06T22:46:20.139813Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T22:46:21.024491Z","title":"Autoflow: Learning a better training set for optical flow","venue":null,"work_id":"49a5a067-4772-4c64-8b6f-683dc080c15f","year":2021},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.897917Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:34c97ae0694270672c7d00a29645886e684b008713a56222cc16e1f7587eadcf","observation_id":"aa169ab3-d830-4d59-b287-1eb309eb2695","resolution":{"observed_at":"2026-08-06T22:46:21.029942Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1909.11825","last_updated":"2019-09-29T08:09:29Z","snapshot_observed_at":"2026-07-06T08:24:41.779661Z","submitted_at":"2019-09-26T00:21:16Z","title":"Unsupervised Domain Adaptation through Self-Supervision","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1909.11825","snapshot_observed_at":"2026-08-06T22:46:19.903728Z","title":"Unsupervised domain adaptation through self-supervision","venue":null,"work_id":null,"year":1909},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.903728Z"},"links":{"cited_paper":"/paper/1909.11825","citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:6d80f6255630db55ff3542bed9e045bff1b5065d9489c3815b68ba979be1d6c8","observation_id":"e4898237-482d-436a-8fc8-b453c1885907","resolution":{"observed_at":"2026-08-06T22:46:19.903728Z","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":"2026-08-06T22:46:21.008833Z","title":"Distortion-aware convolutional filters for dense prediction in panoramic images","venue":null,"work_id":"da69031a-770d-4832-82eb-4435f3aa1ecd","year":2018},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.909802Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:35b67aaad77c2516b6fc1967308188338c44e904a454fe94061c6a562eef33e0","observation_id":"13890410-d25c-4b70-9a17-0d5fe242f842","resolution":{"observed_at":"2026-08-06T22:46:21.014094Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T22:46:20.992618Z","title":"Ntire 2017 challenge on single image super-resolution: Methods and results","venue":null,"work_id":"ab80041a-9e0f-430e-a1db-9ecdf86047e8","year":2017},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.916811Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:2f124e982de0f4266aaf2c9ebf095416d6d153b5a36280c9a126c08e7d412662","observation_id":"acc29d2e-d527-4322-a40c-8333a2414ef4","resolution":{"observed_at":"2026-08-06T22:46:20.998254Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T22:46:20.978140Z","title":"Dacs: Domain adaptation via cross- domain mixed sampling","venue":null,"work_id":"60d211a8-f0ce-4a43-b638-410a1323afa9","year":2021},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.925305Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:96968e4fd173c367ea7341cb10758d8228d0129f0d0510a38287d57bd6aa1667","observation_id":"7a39be25-dd89-45de-b205-cbd6eaac3d61","resolution":{"observed_at":"2026-08-06T22:46:20.982751Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T22:46:19.931176Z","title":"Adversarial discriminative domain adaptation","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.931176Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:133c0efc641572151b261beb427abf8e1b47defb3022bc04dafbe5c940516dc4","observation_id":"763f8b0b-c150-44b5-9e4a-1e0f38b817b1","resolution":{"observed_at":"2026-08-06T22:46:19.931176Z","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":"2026-08-06T22:46:20.952215Z","title":"Undaf: A general unsupervised domain adapta- tion framework for disparity or optical flow estimation","venue":null,"work_id":"5574a5ce-83dd-4bc8-92f4-2842f803fced","year":2022},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.936529Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:0ea44227101a96f882c28ea14f5a07bea63afa73e1ba4b0dc72012acc797c7e8","observation_id":"ef5f7697-3834-4581-9591-914aefc95741","resolution":{"observed_at":"2026-08-06T22:46:20.957834Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T22:46:20.933929Z","title":"Exploiting diffusion prior for real-world image super-resolution.International Journal of Computer Vision, 132(12):5929–5949, 2024","venue":null,"work_id":"bce90994-b7a3-4696-8045-70bbffa4fb51","year":2024},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.941714Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:fa1073ee23d9f433b07b1ac2b06b12dd340aac51cc9e741fe4de0d8c5aec16bf","observation_id":"24763833-f11c-442f-8a66-7c3c98003eec","resolution":{"observed_at":"2026-08-06T22:46:20.939485Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T22:46:20.917788Z","title":"Deep visual domain adapta- tion: A survey.Neurocomputing, 312:135–153, 2018","venue":null,"work_id":"05388d0a-d697-4b0b-93ec-659f9080820a","year":2018},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.946998Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:8f8e31e1948158792559fcd47f335e235f9f9c11a0ca3503229992909852f8ab","observation_id":"953e67b4-75a1-44a4-9c9f-6cc9ca7a8727","resolution":{"observed_at":"2026-08-06T22:46:20.923293Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T22:46:20.900974Z","title":"Rethinking maxi- mum mean discrepancy for visual domain adaptation.IEEE Transactions on Neural Networks and Learning Systems, 34 (1):264–277, 2021","venue":null,"work_id":"1eb8b0c8-c429-42fa-aa5f-e84c80a0e09c","year":2021},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.952504Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:74ba5f042a6098c18581af3d5e5ca48d4cd0f82917fb7421fbf269fd4592ab8c","observation_id":"bde136e7-e78e-4288-8457-01585f8980ec","resolution":{"observed_at":"2026-08-06T22:46:20.906268Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T22:46:19.958446Z","title":"Pyramid vision transformer: A versatile backbone for dense prediction without convolutions","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.958446Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:c5c3f617b520322d9e12e272a6b6b8a93ac83375e5d9dcd4574da1a772b4f329","observation_id":"0481fa58-fe45-4dea-9cb9-eb496c569971","resolution":{"observed_at":"2026-08-06T22:46:19.958446Z","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":"2026-08-06T22:46:20.873774Z","title":"Component divide- and-conquer for real-world image super-resolution","venue":null,"work_id":"cb838044-dcfc-45b4-b297-626dd0b6064f","year":2020},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.964225Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:4c3dcd70eef9b0deccf09ee7276ecf9c9df4c8078e6c1ff998b3ddd76e91ebd1","observation_id":"9f2c88ab-a477-45b9-8eb8-c5014c286691","resolution":{"observed_at":"2026-08-06T22:46:20.879455Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T22:46:20.856543Z","title":"Multi-block domain adaptation with central mo- ment discrepancy for fault diagnosis.Measurement, 169: 108516, 2021","venue":null,"work_id":"eb2609fd-ca31-44a4-88c6-7ada99589ca8","year":2021},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.969199Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:4d83d05d87d3aeb8f0ac537449616727234c0b8f7fad56754082e62b2f2c1c67","observation_id":"d683b409-2957-4fae-8dd9-a908e423fa79","resolution":{"observed_at":"2026-08-06T22:46:20.861538Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T22:46:20.837214Z","title":"Maniqa: Multi-dimension attention network for no-reference image quality assessment","venue":null,"work_id":"e6107ba1-5773-40d3-9ab6-50c059471fc2","year":2022},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.974014Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:b0ce84e6c49f218d5a944617c0250d9ce691c694d5e6fcbc40f997ee09c1bb11","observation_id":"81ef28ee-e9ae-4e07-9850-5fb4b7df9837","resolution":{"observed_at":"2026-08-06T22:46:20.843127Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T22:46:20.817588Z","title":"Learning to recover 3d scene shape from a single image","venue":null,"work_id":"5b6d3cca-98ee-4a3d-9347-a53b0052f89a","year":2021},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.980069Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:5506be8ca907766f37364f4029565ed7afb0b3912fe74fa1eb8257679f89299d","observation_id":"9934f0c3-48e3-4ae8-bf81-7f7090efb6f4","resolution":{"observed_at":"2026-08-06T22:46:20.823766Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T22:46:20.799648Z","title":"Optical flow domain adaptation via target style trans- fer","venue":null,"work_id":"d716f2b4-1083-4e85-a7fc-b56ab6a60288","year":2024},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.984978Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:4c103dbeb9197cd6e931a7bedfb48a4c664c00ead7a5421a73d1a47824878332","observation_id":"f65ee1c2-1f13-4f9a-8e5f-9d3845e9a541","resolution":{"observed_at":"2026-08-06T22:46:20.805665Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.09408","last_updated":"2021-11-07T14:39:41Z","snapshot_observed_at":"2026-07-06T11:59:08.372025Z","submitted_at":"2021-10-18T15:37:58Z","title":"HRFormer: High-Resolution Transformer for Dense Prediction","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.09408","snapshot_observed_at":"2026-08-06T22:46:19.990624Z","title":"Hrformer: High- resolution transformer for dense prediction.arXiv preprint arXiv:2110.09408, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.990624Z"},"links":{"cited_paper":"/paper/2110.09408","citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:84332131be51a7d46136d42382953d71d3483f8e216294d14efd8935ac065ad7","observation_id":"f18e451b-8161-46c2-b772-7e2613bbefce","resolution":{"observed_at":"2026-08-06T22:46:19.990624Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1702.08811","last_updated":"2019-05-02T07:23:00Z","snapshot_observed_at":"2026-07-06T05:31:44.554242Z","submitted_at":"2017-02-28T15:04:54Z","title":"Central Moment Discrepancy (CMD) for Domain-Invariant Representation Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1702.08811","snapshot_observed_at":"2026-08-06T22:46:19.995918Z","title":"Central moment discrepancy (cmd) for domain-invariant representa- tion learning.arXiv preprint arXiv:1702.08811, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:19.995918Z"},"links":{"cited_paper":"/paper/1702.08811","citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:389601ab1e3b06df5d22776384053718ec5015d1bf0c30f338263cb9df286d52","observation_id":"25a17991-d17f-41ae-ac74-f0d3c332e7db","resolution":{"observed_at":"2026-08-06T22:46:19.995918Z","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":"2026-08-06T22:46:20.780554Z","title":"Three things we need to know about trans- ferring stable diffusion to visual dense prediction tasks","venue":null,"work_id":"eff0db97-72b9-4b6b-b45d-ca59e180cb76","year":2024},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:20.001692Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:45ddabdf8994d62b22c5067b7de371fb7dd3258e3f3e014e6676a82b24c09504","observation_id":"01eac61a-330e-4ab4-b0d4-fde0c6667b18","resolution":{"observed_at":"2026-08-06T22:46:20.787576Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T22:46:20.763769Z","title":"Optical flow in the dark","venue":null,"work_id":"33f9879f-934e-4d0a-b64a-e916412243f7","year":2020},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:20.007206Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:323cc0e6f4c34c8c05cddbfcf36ef96bbf5e34c65fb7952789517366291aa40f","observation_id":"2cf1e53a-5976-48cb-b8b5-0bc6a5d832cf","resolution":{"observed_at":"2026-08-06T22:46:20.769403Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T22:46:20.746878Z","title":"Unsu- pervised cumulative domain adaptation for foggy scene op- tical flow","venue":null,"work_id":"1c31c814-879f-4d5b-934c-64322f7c25d6","year":null},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:20.014264Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:46ecfb6b900bbb7ee4073dac2016910206820abef924398cec22b233335b766d","observation_id":"fe121ffa-2503-4b93-b779-9e9c045c78e0","resolution":{"observed_at":"2026-08-06T22:46:20.752411Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T22:46:20.728899Z","title":"Conditional text image generation with diffu- sion models","venue":null,"work_id":"1dde7332-ba8b-4f04-8da7-649f2da1f21e","year":2023},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:20.020392Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:32181d503df06e7c60b33a0e69a6035c063656e98a7d916e31f8949c6c6808d9","observation_id":"50f858cf-6d67-4507-adb1-27a0a605c948","resolution":{"observed_at":"2026-08-06T22:46:20.734596Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-06T22:46:20.708255Z","title":"Flowie: Efficient image enhancement via rectified flow","venue":null,"work_id":"1c42f14f-d450-45a9-876f-ba61e08f27cb","year":2024},"citing_paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment","version":1},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-06T22:46:20.024862Z"},"links":{"citing_paper":"/paper/2506.22509"},"observation_digest":"sha256:bef3d6b4b1609db4c69ccccd5b31db1725bfd9fa8862a4043ee4c7cd84a920ba","observation_id":"2c6bd0c7-e9f5-40e8-8b4b-d8169582cf53","resolution":{"observed_at":"2026-08-06T22:46:20.714301Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2506.22509","last_updated":"2025-06-26T02:54:27Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-10T18:23:35.264339Z","submitted_at":"2025-06-26T02:54:27Z","title":"FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment"},"reference_resolution":{"displayed":86,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":37,"verified_exact":4,"verified_fuzzy":45},"total_outbound_references":86},"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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 86 of 86 outbound references and 0 inbound Pith citation observations for arXiv:2506.22509."}