{"as_of":"2026-08-18T21:33:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e5648d4d9c81a905c9df549dc643e149eba24770849a6b38435ae18bf99f8561","coverage":[{"denominator":64,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":64,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T23:17:26.779322Z","state":"measured"},{"denominator":64,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":64,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2505.05091/citation-record","integrity":"/paper/2505.05091/integrity","json":"/paper/2505.05091/citation-record.json","paper":"/paper/2505.05091"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T23:17:27.945591Z","title":"On the unreasonable vulnerability of transformers for image restoration-and an easy fix","venue":null,"work_id":"e707c5c3-19e0-4004-bfa7-2e477ac21c9f","year":2023},"citing_paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T23:17:26.454444Z"},"links":{"citing_paper":"/paper/2505.05091"},"observation_digest":"sha256:76fb64c3823b3e1537dc9774d2d4f44786b673039e949216ba3cf91c9518f11c","observation_id":"5852a6b2-d9fb-4514-80e4-dec7a95ec7fe","resolution":{"observed_at":"2026-08-15T23:17:27.950345Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:17:27.930218Z","title":"Improving stability during upsampling – on the importance of spatial context, 2023","venue":null,"work_id":"43d24063-d731-4461-b568-604bfbd934ee","year":2023},"citing_paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T23:17:26.461558Z"},"links":{"citing_paper":"/paper/2505.05091"},"observation_digest":"sha256:19a6e12e3efd9c312384cc612f74aab17e10ea2f6d56734893c856ff6b6cdc26","observation_id":"7dee57ae-8df0-4096-915f-c22394d5b975","resolution":{"observed_at":"2026-08-15T23:17:27.935416Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.07435","last_updated":"2026-06-16T11:18:22Z","snapshot_observed_at":"2026-08-16T13:44:06.189824Z","submitted_at":"2024-06-11T16:42:17Z","title":"Beware of Aliases -- Signal Preservation is Crucial for Robust Image Restoration","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.07435","snapshot_observed_at":"2026-08-15T23:17:26.467060Z","title":"Beware of aliases–signal preservation is crucial for robust image restoration","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T23:17:26.467060Z"},"links":{"cited_paper":"/paper/2406.07435","citing_paper":"/paper/2505.05091"},"observation_digest":"sha256:a276ae680365e4d22c8ab4ed88b818a3d49c0d47537d9467f9e7ded16ceccbcc","observation_id":"25e40b61-4e9f-4ba0-ae96-a458ee889f6e","resolution":{"observed_at":"2026-08-15T23:17:26.467060Z","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":"2026-08-15T23:17:27.915316Z","title":"CosPGD: an efficient white-box adversarial attack for pixel- wise prediction tasks","venue":null,"work_id":"ff79e5d6-b99e-4cbd-add7-aa7b34d43968","year":2024},"citing_paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T23:17:26.473240Z"},"links":{"citing_paper":"/paper/2505.05091"},"observation_digest":"sha256:09d92e6b439ddb311a9522bbcafba6434a2600dffb626fe057eb52a3de34b54a","observation_id":"374feadf-33d9-45f2-aebf-6570fff418df","resolution":{"observed_at":"2026-08-15T23:17:27.919965Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:17:27.899156Z","title":"Roll the dice: Monte carlo downsampling as a low-cost adversarial defence, 2024","venue":null,"work_id":"ede8861c-67dd-44a4-9401-e74e79206e36","year":2024},"citing_paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T23:17:26.478805Z"},"links":{"citing_paper":"/paper/2505.05091"},"observation_digest":"sha256:279c364d0897418724da20e1f80cdde3aeb5cc9c4c4168054fc59cdaa357628e","observation_id":"9bd8749e-9860-468d-afb8-35db8388ff19","resolution":{"observed_at":"2026-08-15T23:17:27.905034Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:17:27.883265Z","title":"Flowbench: A robustness benchmark for optical flow estimation, 2025","venue":null,"work_id":"4283d277-df7e-4e48-af49-9fd2e90092f0","year":2025},"citing_paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T23:17:26.483810Z"},"links":{"citing_paper":"/paper/2505.05091"},"observation_digest":"sha256:787559c67d8f226a9abe92fae98dbe5c0d34bdee3094873a96778745afc0c189","observation_id":"62575ebd-3f9d-46de-bf86-acd8011cb933","resolution":{"observed_at":"2026-08-15T23:17:27.888530Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:17:27.867542Z","title":"Are Synthetic Corruptions A Reliable Proxy For Real-World Corruptions? In CVPR Workshop On Synthetic Data for Computer Vision,","venue":null,"work_id":"0a236eac-a6b4-4207-91a7-260cc7418081","year":null},"citing_paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T23:17:26.490233Z"},"links":{"citing_paper":"/paper/2505.05091"},"observation_digest":"sha256:2c0007d17ad5a3e823cd1d6aae3166f4d0de1ea413387eb041de46645188c968","observation_id":"dd8d35f6-d2b1-4fbd-a428-6ab4a884a6d9","resolution":{"observed_at":"2026-08-15T23:17:27.872649Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:17:27.851292Z","title":"Frod: Robust object detection for free","venue":null,"work_id":"fcd1bc13-1d26-446a-bd84-ea9f5949572e","year":null},"citing_paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T23:17:26.496481Z"},"links":{"citing_paper":"/paper/2505.05091"},"observation_digest":"sha256:d85c0b9c107df45d1ea9f5b02c6aa7e9ef4236e93a59ef0820c0c993e8b9e98d","observation_id":"e84c0bb8-e2f4-410f-8764-2ed04588f361","resolution":{"observed_at":"2026-08-15T23:17:27.856489Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:17:27.836238Z","title":"Butler, Jonas Wulff, Garrett B","venue":null,"work_id":"f08cac8b-f6e8-4b5d-a12e-2e46dc9d4be1","year":2012},"citing_paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T23:17:26.501811Z"},"links":{"citing_paper":"/paper/2505.05091"},"observation_digest":"sha256:290ae65d995e2482ff63f13c3db0320e938f1d2a79ca87a146d8f762989dcf68","observation_id":"36bcfe06-f097-4070-9609-c45d2ebd7da6","resolution":{"observed_at":"2026-08-15T23:17:27.840739Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:17:27.820572Z","title":"Deep learning-based incorporation of planar constraints for robust stereo depth estimation in au- tonomous vehicle applications","venue":null,"work_id":"e8a2f8a3-3015-413a-b241-59e46bb17c4b","year":2021},"citing_paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T23:17:26.506709Z"},"links":{"citing_paper":"/paper/2505.05091"},"observation_digest":"sha256:3de3d26dd168df42a7805d5166cb67e8342a4d2d515b952ed6363e9fbabbf45e","observation_id":"3293737f-a7f9-4f73-8c37-94dc2e48506a","resolution":{"observed_at":"2026-08-15T23:17:27.825656Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:17:27.802885Z","title":"The cityscapes dataset for semantic urban scene understanding, 2016","venue":null,"work_id":"21bf00b5-9693-47ed-826f-1779216b2b59","year":2016},"citing_paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T23:17:26.511890Z"},"links":{"citing_paper":"/paper/2505.05091"},"observation_digest":"sha256:99c33db0815c94e7e3b3709a751fc452601a71881dc249860d76005c33b7b6c4","observation_id":"02ecd537-f37d-4e44-84b2-d80ee8084089","resolution":{"observed_at":"2026-08-15T23:17:27.809141Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:17:27.786649Z","title":"RobustBench: a standardized adversarial robustness benchmark","venue":null,"work_id":"73acc765-2366-4237-961b-3741b2a56242","year":2021},"citing_paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T23:17:26.516840Z"},"links":{"citing_paper":"/paper/2505.05091"},"observation_digest":"sha256:bc2efad8b673eea37740f5123f3d8c09c1b457bd34ea567f6c2c0f6871623dcb","observation_id":"dde98290-c22e-43f2-a337-0c06e150a8fd","resolution":{"observed_at":"2026-08-15T23:17:27.791809Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:17:27.769819Z","title":"Sp2 net for generalized zero-label seman- tic segmentation","venue":null,"work_id":"00ffd8fb-f01b-40bd-97b5-98b6e2fb5778","year":2021},"citing_paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T23:17:26.522169Z"},"links":{"citing_paper":"/paper/2505.05091"},"observation_digest":"sha256:2a366ee01da253e0dd51ccbf2b54c8f90503f671587f8a5f71e7c1954cb225c1","observation_id":"3bb1bbc7-fe50-4d67-b0d5-79dac6588cbb","resolution":{"observed_at":"2026-08-15T23:17:27.775219Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:17:27.752204Z","title":"Weakly-supervised domain adaptive semantic segmentation with prototypical contrastive learning","venue":null,"work_id":"c28e00f4-3dbc-4603-96fd-c8e3ddf9050e","year":2023},"citing_paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T23:17:26.527259Z"},"links":{"citing_paper":"/paper/2505.05091"},"observation_digest":"sha256:cdbc3b42dbf8bc9e1a57e7b4607ad202531a0e25e5df30c2897948eed1a6341d","observation_id":"b3d3a523-bbb0-4b7f-820a-b08c8477ac22","resolution":{"observed_at":"2026-08-15T23:17:27.757623Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:17:27.735514Z","title":"Robust object detection in extreme construction conditions","venue":null,"work_id":"fbb5268e-4811-43b2-98a9-276b505b7e62","year":2024},"citing_paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T23:17:26.532161Z"},"links":{"citing_paper":"/paper/2505.05091"},"observation_digest":"sha256:7a907008db91b96a6314b22bdfedc32b2856c86fab176871133ca29e79106c7f","observation_id":"647e2e20-b1ae-41a3-9494-02ca36d756f0","resolution":{"observed_at":"2026-08-15T23:17:27.740935Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:17:27.718793Z","title":"Adversarially-aware robust object detector","venue":null,"work_id":"787daae4-f791-4584-aa03-da8c47653609","year":2022},"citing_paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T23:17:26.537379Z"},"links":{"citing_paper":"/paper/2505.05091"},"observation_digest":"sha256:9e5b2146fd757934e0214b34d2f8cc3ea552d67f5f1a4fb5eb150f37cd56bb60","observation_id":"b14a226d-5672-4e63-a41d-5cca493d3224","resolution":{"observed_at":"2026-08-15T23:17:27.724316Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:17:27.701749Z","title":"Flownet: Learning optical flow with convolutional networks","venue":null,"work_id":"9dbbca43-bdcc-47b3-87a3-1ac0aa4e3a40","year":2015},"citing_paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T23:17:26.542458Z"},"links":{"citing_paper":"/paper/2505.05091"},"observation_digest":"sha256:0e3bd08f3158769e697e71a944065ee592f0b2b893672deae901d485455eed5b","observation_id":"7d66a80d-192e-4f02-b6f9-8eac9f85ef43","resolution":{"observed_at":"2026-08-15T23:17:27.707073Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:17:27.684477Z","title":"CARLA: An open urban driving simulator","venue":null,"work_id":"4cf9b4a8-dc67-4409-bed1-52698a122b80","year":2017},"citing_paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T23:17:26.547319Z"},"links":{"citing_paper":"/paper/2505.05091"},"observation_digest":"sha256:ecf14c15cd9079b08f10462347666de22873d9f9f8e1efc0d206687d4031ee66","observation_id":"180915b5-8411-4931-a8be-4a5ed378de3c","resolution":{"observed_at":"2026-08-15T23:17:27.690024Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.14470","last_updated":"2024-10-18T13:54:46Z","snapshot_observed_at":"2026-08-16T13:08:01.799009Z","submitted_at":"2024-10-18T13:54:46Z","title":"How Do Training Methods Influence the Utilization of Vision Models?","version":1},"cited_work":{"arxiv_id":"2410.14470","doi":null,"metadata_source":"pith","pith_arxiv_id":"2410.14470","snapshot_observed_at":"2026-08-15T23:17:27.086845Z","title":"How Do Training Methods Influence the Utilization of Vision Models?","venue":"cs.CV","work_id":"5393dd79-52d4-4b7b-85fa-840bf3fb0e1c","year":2024},"citing_paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T23:17:26.552825Z"},"links":{"cited_paper":"/paper/2410.14470","citing_paper":"/paper/2505.05091"},"observation_digest":"sha256:a8f9e3551eed660cf036eb271a2e2c340d9e4f1d2719fd917fa74f37fab35ccd","observation_id":"129cc19a-b685-4fbb-9440-b5106d0f6711","resolution":{"observed_at":"2026-08-15T23:17:27.094544Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:17:27.667713Z","title":"Imagenet-trained cnns are biased towards texture; increasing shape bias improves accuracy and robustness","venue":null,"work_id":"6f71570d-a400-4743-9301-b08730e95bf0","year":2018},"citing_paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T23:17:26.558093Z"},"links":{"citing_paper":"/paper/2505.05091"},"observation_digest":"sha256:526cdd60d0a9fd09ba029cc3fb6e607e7445f706a7e7f6d79056e34766fe103e","observation_id":"f4bc0c44-d36e-42e9-92df-75f4b4712401","resolution":{"observed_at":"2026-08-15T23:17:27.672988Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:17:27.651118Z","title":"Wichmann","venue":null,"work_id":"49b07cd8-8d87-4179-9644-b360d33fd984","year":2020},"citing_paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T23:17:26.562920Z"},"links":{"citing_paper":"/paper/2505.05091"},"observation_digest":"sha256:d1fdbb9c8d21a80eada0fcb14566485cf0a75fd95524a3103fac66795dba7299","observation_id":"14cd3996-43eb-4273-b5f3-9973a5659d9d","resolution":{"observed_at":"2026-08-15T23:17:27.656284Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:17:27.634928Z","title":"Explaining and harnessing adversarial examples","venue":null,"work_id":"2dbbe113-9578-40e9-8f72-935c13e3c14a","year":null},"citing_paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T23:17:26.567736Z"},"links":{"citing_paper":"/paper/2505.05091"},"observation_digest":"sha256:43c10839b17ea67ac9de9097e53fd7d9197b176b8f62019ddbbf761aefd8f0f6","observation_id":"a07ad5ea-e81b-4440-99ef-a4ada14b6575","resolution":{"observed_at":"2026-08-15T23:17:27.640517Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:17:27.619133Z","title":"Robust models are less over-confident","venue":null,"work_id":"aa7ffec3-4021-45e4-bfbe-c9446c81cf43","year":null},"citing_paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T23:17:26.572731Z"},"links":{"citing_paper":"/paper/2505.05091"},"observation_digest":"sha256:ceed33015ffe649bc88cfe8b8d776605735456574c9ed00f50cc7bd1ad1282fc","observation_id":"50914646-e013-45b9-8a90-53199edf2b08","resolution":{"observed_at":"2026-08-15T23:17:27.624031Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:17:27.603578Z","title":"Frequencylowcut pooling-plug and play against catas- trophic overfitting","venue":null,"work_id":"fe88541f-a598-4a9e-9888-c83134ce4d22","year":2022},"citing_paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T23:17:26.577815Z"},"links":{"citing_paper":"/paper/2505.05091"},"observation_digest":"sha256:5e5bc8281b6da2ceaaaaef17c673367ee1a3af02157a1b91aa7fa7c51102d110","observation_id":"c5decc6a-a2b8-449a-90b8-f5280812a5bf","resolution":{"observed_at":"2026-08-15T23:17:27.608744Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:17:27.588352Z","title":"Alias- ing and adversarial robust generalization of cnns","venue":null,"work_id":"b139e384-4e34-4c3c-89dc-80a9afac1255","year":2022},"citing_paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T23:17:26.582899Z"},"links":{"citing_paper":"/paper/2505.05091"},"observation_digest":"sha256:82d01ee17768c8646e4e6426839f33ddddf739ebf230422fcedb4fc7dd15642d","observation_id":"e72c4fd8-0309-4915-beea-e1979a4e1e62","resolution":{"observed_at":"2026-08-15T23:17:27.593224Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:17:27.572597Z","title":"Group-wise correlation stereo network","venue":null,"work_id":"0f3ab077-720b-45cb-87d0-65a71274900b","year":2019},"citing_paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T23:17:26.587922Z"},"links":{"citing_paper":"/paper/2505.05091"},"observation_digest":"sha256:fb46735315e334fb1348383961621fca152288b14e49516e8dd3d16b889c50de","observation_id":"1d0efceb-bb83-4271-9f8a-19413b66ce99","resolution":{"observed_at":"2026-08-15T23:17:27.577518Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.00343","last_updated":"2024-12-11T11:04:22Z","snapshot_observed_at":"2026-08-17T20:53:19.645057Z","submitted_at":"2023-12-01T04:35:47Z","title":"OpenStereo: A Comprehensive Benchmark for Stereo Matching and Strong Baseline","version":8},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.00343","snapshot_observed_at":"2026-08-15T23:17:26.593145Z","title":"Openstereo: 9 A comprehensive benchmark for stereo matching and strong baseline","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T23:17:26.593145Z"},"links":{"cited_paper":"/paper/2312.00343","citing_paper":"/paper/2505.05091"},"observation_digest":"sha256:534b1a04d2472572fcc5ab4cf479ceca9c8b88dd3aa83bd0227c1e667d281ae0","observation_id":"40e093f5-69ec-414c-a91b-d0fdbef3359c","resolution":{"observed_at":"2026-08-15T23:17:26.593145Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.19833","last_updated":"2025-02-26T07:26:43Z","snapshot_observed_at":"2026-08-16T13:38:46.730217Z","submitted_at":"2024-06-28T11:11:24Z","title":"LightStereo: Channel Boost Is All You Need for Efficient 2D Cost Aggregation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.19833","snapshot_observed_at":"2026-08-15T23:17:26.598705Z","title":"Lightstereo: Channel boost is all your need for efficient 2d cost aggregation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-15T23:17:26.598705Z"},"links":{"cited_paper":"/paper/2406.19833","citing_paper":"/paper/2505.05091"},"observation_digest":"sha256:3c68567afedd7620e38f43389b233d759d9ff81143f44395b8a37b39a0fd46ad","observation_id":"041b85fe-d06d-424c-a772-69ba6fd57bfa","resolution":{"observed_at":"2026-08-15T23:17:26.598705Z","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":"2026-08-15T23:17:26.604135Z","title":"Stereo anything: Unifying stereo matching with large- scale mixed data","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T23:17:26.604135Z"},"links":{"citing_paper":"/paper/2505.05091"},"observation_digest":"sha256:4f2b8ce99cd6dd25a2fd954a37985b07c9f7b7649ee66d2bed90d6037023ab4c","observation_id":"ca154160-8d54-4165-aa45-0426be865ff2","resolution":{"observed_at":"2026-08-15T23:17:26.604135Z","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":"2026-08-15T23:17:27.557421Z","title":"Robust object detection in challeng- ing weather conditions","venue":null,"work_id":"8e688006-5cbf-443b-ad1d-8f5e1d0c878a","year":2024},"citing_paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-15T23:17:26.609029Z"},"links":{"citing_paper":"/paper/2505.05091"},"observation_digest":"sha256:7db77c1e67c9d92e8115ee23b2e727e710608962d3ea101c8edd66d5aa37833e","observation_id":"cdf04bb8-8bc2-4ac1-8f74-c0be27dac2b4","resolution":{"observed_at":"2026-08-15T23:17:27.562484Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:17:27.542887Z","title":"Benchmarking neu- ral network robustness to common corruptions and perturba- tions","venue":null,"work_id":"4d67ddab-7c87-4d8f-bc3c-987a8de2ef64","year":2019},"citing_paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-15T23:17:26.613849Z"},"links":{"citing_paper":"/paper/2505.05091"},"observation_digest":"sha256:9b36310d9f90dfd16f4c47399562b8069b2aad17510536192afeeef4d219aa01","observation_id":"f1727e57-7064-462e-bb33-0333e56093fa","resolution":{"observed_at":"2026-08-15T23:17:27.547624Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:17:27.527657Z","title":"Cubuk, Barret Zoph, Justin Gilmer, and Balaji Lakshminarayanan","venue":null,"work_id":"2e48c3aa-371a-49ba-b0d9-d7e601f9fb09","year":2020},"citing_paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-15T23:17:26.618608Z"},"links":{"citing_paper":"/paper/2505.05091"},"observation_digest":"sha256:78f429c30b09c8b4a9994eca5811ba57e3f21ce7d5560edc50b37ac51f726a8b","observation_id":"6725073c-a00c-4975-928b-705a99d2628d","resolution":{"observed_at":"2026-08-15T23:17:27.532569Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:17:27.512664Z","title":"Towards improving robustness of compressed cnns","venue":null,"work_id":"29540cb4-2435-4031-8f77-395ba45e03fa","year":2021},"citing_paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-15T23:17:26.623230Z"},"links":{"citing_paper":"/paper/2505.05091"},"observation_digest":"sha256:a8aa1e58a1b05da06c2519af116df8a638631f2712792d83a7c4f0e76d012f59","observation_id":"3526b08f-59ba-4b12-a89b-1bb9a9519dc4","resolution":{"observed_at":"2026-08-15T23:17:27.517589Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:17:27.495577Z","title":"3d common corruptions and data augmentation","venue":null,"work_id":"f7c13adb-a5d8-4dec-ab4d-786786258f4d","year":2022},"citing_paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-15T23:17:26.627835Z"},"links":{"citing_paper":"/paper/2505.05091"},"observation_digest":"sha256:0fef78e1ff16748cadf7b35660c8dd8da126851df7f2dcc3f923b344eb26b46e","observation_id":"b8672933-2590-497f-92c9-734f8eeec891","resolution":{"observed_at":"2026-08-15T23:17:27.500703Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:17:27.479744Z","title":"Goodfellow, and Samy Bengio","venue":null,"work_id":"4f37820c-a58c-4794-8811-a92e5014eb9f","year":2017},"citing_paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-15T23:17:26.632574Z"},"links":{"citing_paper":"/paper/2505.05091"},"observation_digest":"sha256:778d8442bef412c55eab90cfc145962923b3f3b5c5992f775e4c5a2b1cd632c8","observation_id":"ec5fb610-906a-41df-9322-69dfb91aa8a5","resolution":{"observed_at":"2026-08-15T23:17:27.484776Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:17:27.463116Z","title":"Ad- versarial examples in the physical world","venue":null,"work_id":"fcbbfb2e-e125-417c-ad99-b96cb488fc67","year":2018},"citing_paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-15T23:17:26.637749Z"},"links":{"citing_paper":"/paper/2505.05091"},"observation_digest":"sha256:fc30abe853576be2c8477e9605d26b64345579b330e69fc53e9165d7d1dc4e20","observation_id":"cec1d0cc-e004-4688-8249-92862b8588f0","resolution":{"observed_at":"2026-08-15T23:17:27.468457Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:17:27.446681Z","title":"Intra-source style augmentation for improved domain gener- alization","venue":null,"work_id":"35c39907-9498-447f-b79f-4af110060f32","year":null},"citing_paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-15T23:17:26.643407Z"},"links":{"citing_paper":"/paper/2505.05091"},"observation_digest":"sha256:a8236743aa556957a22ffd066570fd39ff287a78498caa686fc5661581475333","observation_id":"13a29f85-c2a2-448d-a998-d11d74ca3ee3","resolution":{"observed_at":"2026-08-15T23:17:27.451683Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:17:27.431480Z","title":"Adversarial supervision makes layout-to-image diffusion models thrive","venue":null,"work_id":"1825734f-4c7a-4c8b-a404-70221ccc8e3f","year":2024},"citing_paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-15T23:17:26.648742Z"},"links":{"citing_paper":"/paper/2505.05091"},"observation_digest":"sha256:2552e5d6e8244aa5e9217cdb7c3d64f54ca04f59291a5460a87827c124b40526","observation_id":"8e2e2665-13f0-4649-94e7-4ebfcce554cc","resolution":{"observed_at":"2026-08-15T23:17:27.436316Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:17:27.416189Z","title":"Creighton, Russell H","venue":null,"work_id":"5918035a-1085-4673-8b5c-d31fb5dd591b","year":2021},"citing_paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-15T23:17:26.653519Z"},"links":{"citing_paper":"/paper/2505.05091"},"observation_digest":"sha256:0280b66c23693343f6cab0e50ab34a455f5427a9fb30f68d2c1601bca675f236","observation_id":"265856d6-622f-42fe-9eb6-f1ac114c56af","resolution":{"observed_at":"2026-08-15T23:17:27.420889Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:17:27.401203Z","title":"Global occlusion-aware transformer for robust stereo matching","venue":null,"work_id":"210ff2a5-4e44-4726-a084-07d5cc540e99","year":2024},"citing_paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-15T23:17:26.658188Z"},"links":{"citing_paper":"/paper/2505.05091"},"observation_digest":"sha256:5a2e50c901ac35845660ccdf6291af1397aa03cd464eab9b6ffd8acad5d36200","observation_id":"ba85b56c-9f8f-430c-9f26-fc6befe86372","resolution":{"observed_at":"2026-08-15T23:17:27.406192Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:17:27.384869Z","title":"A large dataset to train convolutional networks for disparity, optical flow, and scene flow estimation","venue":null,"work_id":"d76ace65-6639-4c2d-aa2b-2d9754c7788d","year":2016},"citing_paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-15T23:17:26.662908Z"},"links":{"citing_paper":"/paper/2505.05091"},"observation_digest":"sha256:278697627a07b7e51afe9f1584bb3a6e8d9a9db0422373ff2f53db3c6ecf7cd9","observation_id":"343f3709-3555-4601-a520-795aa7c62269","resolution":{"observed_at":"2026-08-15T23:17:27.390025Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2411.19853","last_updated":"2025-03-13T13:19:33Z","snapshot_observed_at":"2026-08-12T05:43:10.558596Z","submitted_at":"2024-11-29T17:09:59Z","title":"Towards Class-wise Robustness Analysis","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.19853","snapshot_observed_at":"2026-08-15T23:17:26.668118Z","title":"Towards class-wise robustness analysis","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-15T23:17:26.668118Z"},"links":{"cited_paper":"/paper/2411.19853","citing_paper":"/paper/2505.05091"},"observation_digest":"sha256:95de1c6bfc1021449e371935261e62c3721c58ad05a719807f7bfef3081dfa9f","observation_id":"7b23b60f-f2bd-47ea-91ef-c908531e01ef","resolution":{"observed_at":"2026-08-15T23:17:26.668118Z","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":"2026-08-15T23:17:27.369168Z","title":"Fair-tat: Improving model fairness using targeted adversarial train- ing","venue":null,"work_id":"0615d55e-6621-4fcf-ae8b-0c2472748976","year":2025},"citing_paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-15T23:17:26.674360Z"},"links":{"citing_paper":"/paper/2505.05091"},"observation_digest":"sha256:a69e05d9b3533244800f284f30869926246905ed288ebfa9bf35d390f2a68e80","observation_id":"c7e29e08-d4da-474d-8301-11f0384409e2","resolution":{"observed_at":"2026-08-15T23:17:27.373924Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:17:27.354728Z","title":"Object scene flow for au- tonomous vehicles","venue":null,"work_id":"342a1e1a-2480-4276-bcd2-1fceeca6fb16","year":2015},"citing_paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-15T23:17:26.679622Z"},"links":{"citing_paper":"/paper/2505.05091"},"observation_digest":"sha256:7abf76845144377c7d4ff419fa54f7ddbaed4b22b5c8b0a4e9d055a217b6bddd","observation_id":"aaea68dd-69de-44ca-835b-6a5cd3ed9816","resolution":{"observed_at":"2026-08-15T23:17:27.359475Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1907.07484","last_updated":"2020-03-31T08:42:46Z","snapshot_observed_at":"2026-08-18T15:20:55.276879Z","submitted_at":"2019-07-17T12:51:10Z","title":"Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Coming","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1907.07484","snapshot_observed_at":"2026-08-15T23:17:26.686054Z","title":"Benchmarking ro- bustness in object detection: Autonomous driving when win- ter is coming","venue":null,"work_id":null,"year":1907},"citing_paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-15T23:17:26.686054Z"},"links":{"cited_paper":"/paper/1907.07484","citing_paper":"/paper/2505.05091"},"observation_digest":"sha256:0932b48dc36d6f41fe712f716fa08fbc869d247c67cebf0502689e48b1f8f29a","observation_id":"ccf63b28-447d-463b-bf45-fecfc2166ba7","resolution":{"observed_at":"2026-08-15T23:17:26.686054Z","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":"2026-08-15T23:17:27.339483Z","title":"Fast high-resolution disparity estimation for laparoscopic surgery","venue":null,"work_id":"9944a497-362b-4962-8415-843cc925fc40","year":2022},"citing_paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-15T23:17:26.691122Z"},"links":{"citing_paper":"/paper/2505.05091"},"observation_digest":"sha256:4b004adf4de0d9eb2b7eb93120a086eac6c94700eaff67d241455ac974386db4","observation_id":"edcc2a02-bc08-4de3-90da-4f94dcfbdf21","resolution":{"observed_at":"2026-08-15T23:17:27.344521Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:17:27.324183Z","title":"Towards Robust and Resilient Machine Learning","venue":null,"work_id":"882613e6-fa2e-48b6-a3a7-c2f798cd8681","year":2022},"citing_paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-15T23:17:26.695821Z"},"links":{"citing_paper":"/paper/2505.05091"},"observation_digest":"sha256:7f6c4b8b6c61acf79210cb33b8077c31cec2e78b94af8ad6690c1c9f3d60b6fa","observation_id":"f41abbb1-8cac-42bf-bfac-aad8a4f346b0","resolution":{"observed_at":"2026-08-15T23:17:27.328858Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:17:27.309891Z","title":"Msdesis: Multitask stereo disparity estimation and surgical instrument segmen- tation","venue":null,"work_id":"006eea3e-760c-4ef2-9123-38de384db95d","year":2022},"citing_paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-15T23:17:26.700816Z"},"links":{"citing_paper":"/paper/2505.05091"},"observation_digest":"sha256:af1fb5fbc06cf299f3afc1882fa575d016d46b04dc195c1b41c33d7937cec04c","observation_id":"94f155f4-1ece-4654-a249-1e326214f83d","resolution":{"observed_at":"2026-08-15T23:17:27.314623Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2005.03778","last_updated":"2020-06-22T00:47:14Z","snapshot_observed_at":"2026-08-15T21:39:06.105813Z","submitted_at":"2020-05-07T21:57:19Z","title":"LGSVL Simulator: A High Fidelity Simulator for Autonomous Driving","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.03778","snapshot_observed_at":"2026-08-15T23:17:26.705510Z","title":"Lgsvl simulator: A high fidelity simulator for autonomous driving","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-15T23:17:26.705510Z"},"links":{"cited_paper":"/paper/2005.03778","citing_paper":"/paper/2505.05091"},"observation_digest":"sha256:7e01fcb48bbd7a536b5892a6cc925e2f6e1b8120528b82d9816bfe9015d5e4bb","observation_id":"563d11b6-336f-42fe-bb09-ac5684a5ccd7","resolution":{"observed_at":"2026-08-15T23:17:26.705510Z","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":"2026-08-15T23:17:27.294124Z","title":"ACDC: The adverse conditions dataset with correspondences for se- mantic driving scene understanding","venue":null,"work_id":"ddc24bcb-71cd-4bd1-a785-4516a3ff4080","year":2021},"citing_paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-15T23:17:26.710486Z"},"links":{"citing_paper":"/paper/2505.05091"},"observation_digest":"sha256:a64518a16b897b3d6f922d1459861b4e91c2a5d037301c4553e7d8d11b71a35f","observation_id":"3113dfb9-89f9-4df9-8669-1d240e8a3619","resolution":{"observed_at":"2026-08-15T23:17:27.299391Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:17:27.279029Z","title":"Detection defenses: An empty promise against adver- sarial patch attacks on optical flow","venue":null,"work_id":"0a4ca2f6-b4b2-4a2a-86d9-a8217bb1e931","year":null},"citing_paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-15T23:17:26.715074Z"},"links":{"citing_paper":"/paper/2505.05091"},"observation_digest":"sha256:7d6f4da9f034a529ab2cd6a7a3d72808364916412b6f99e6e0deedc563e0335a","observation_id":"f124bf13-1a4b-4556-8ab5-37f0966cd58b","resolution":{"observed_at":"2026-08-15T23:17:27.283962Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:17:27.264683Z","title":"At- tacking motion estimation with adversarial snow","venue":null,"work_id":"4f9a3ebe-a65f-4bac-8da4-f42af1ac8790","year":2022},"citing_paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-15T23:17:26.720162Z"},"links":{"citing_paper":"/paper/2505.05091"},"observation_digest":"sha256:986710fa691e88135a86056de18a94cbefdfc92e55b9ea3a57d1d4c6b483eec8","observation_id":"357a6590-6d76-4ded-9d01-baaf526f7aec","resolution":{"observed_at":"2026-08-15T23:17:27.269339Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:17:27.249318Z","title":"A perturbation-constrained adversarial attack for evaluating the robustness of optical flow","venue":null,"work_id":"841760c6-02b2-4ff3-886e-960621ee83df","year":2022},"citing_paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-15T23:17:26.725039Z"},"links":{"citing_paper":"/paper/2505.05091"},"observation_digest":"sha256:b90f7331ed5acfae4a36b2218ad53fd82d9efe1b223b30224029aeb91da7bbdd","observation_id":"36944384-4905-4ce6-9bfe-b38ecfef8bbe","resolution":{"observed_at":"2026-08-15T23:17:27.253955Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:17:27.234391Z","title":"Airsim: High-fidelity visual and physical simula- tion for autonomous vehicles","venue":null,"work_id":"6e4f3a13-baa0-4812-b77f-91f69e8cda55","year":null},"citing_paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-15T23:17:26.729658Z"},"links":{"citing_paper":"/paper/2505.05091"},"observation_digest":"sha256:62101fba86ec61f668774c9fabe75f8a05263eded30ddaa37f79874af3985b15","observation_id":"7bc7754a-0157-4ebd-b015-610a3fbfbcbd","resolution":{"observed_at":"2026-08-15T23:17:27.239613Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:17:27.218522Z","title":"Cfnet: Cascade and fused cost volume for robust stereo matching","venue":null,"work_id":"c2f0dba3-3013-47e5-99c3-8c222def3188","year":2021},"citing_paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-15T23:17:26.734080Z"},"links":{"citing_paper":"/paper/2505.05091"},"observation_digest":"sha256:a165cc745817f47cdd2d6b2a5aa892f5516005d085e414a9c2c3729c7d452145","observation_id":"c168462e-e2aa-4d11-8a4a-3f9d773998f2","resolution":{"observed_at":"2026-08-15T23:17:27.224027Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2304.14736","last_updated":"2023-04-28T10:28:09Z","snapshot_observed_at":"2026-08-16T15:37:01.814999Z","submitted_at":"2023-04-28T10:28:09Z","title":"Differentiable Sensor Layouts for End-to-End Learning of Task-Specific Camera Parameters","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.14736","snapshot_observed_at":"2026-08-15T23:17:26.738954Z","title":"Differentiable sensor layouts for end-to-end learn- ing of task-specific camera parameters","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-15T23:17:26.738954Z"},"links":{"cited_paper":"/paper/2304.14736","citing_paper":"/paper/2505.05091"},"observation_digest":"sha256:b7d39b186258905a2d0c6cdc6097d35489c52be419e427b3f9fe71c80f102467","observation_id":"a72a068d-fd33-40d4-8bb3-e16e5ed9d2a9","resolution":{"observed_at":"2026-08-15T23:17:26.738954Z","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":"2026-08-15T23:17:27.202403Z","title":"Task driven sensor layouts-joint optimiza- tion of pixel layout and network parameters","venue":null,"work_id":"c452d258-834f-47ad-9b44-ab8296798f96","year":2024},"citing_paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-15T23:17:26.744063Z"},"links":{"citing_paper":"/paper/2505.05091"},"observation_digest":"sha256:74664960a7d643c2bd6819ed96e4f2b9d64eba1ed0a5d67c7f1c4768da175707","observation_id":"4157dda0-a4fb-4bfc-b7d9-24f0eef28640","resolution":{"observed_at":"2026-08-15T23:17:27.207452Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2109.05211","last_updated":"2022-01-14T03:19:06Z","snapshot_observed_at":"2026-08-17T00:07:05.796006Z","submitted_at":"2021-09-11T08:01:14Z","title":"RobustART: Benchmarking Robustness on Architecture Design and Training Techniques","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.05211","snapshot_observed_at":"2026-08-15T23:17:26.748813Z","title":"Torr, and Dacheng Tao","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-15T23:17:26.748813Z"},"links":{"cited_paper":"/paper/2109.05211","citing_paper":"/paper/2505.05091"},"observation_digest":"sha256:1ad6d7c50cacdcac1080e60d2b660d4bf37eed5d289485fd6ec2200afa6eccbb","observation_id":"7cc70fa2-5915-4e01-acd9-479e9b6d1dfb","resolution":{"observed_at":"2026-08-15T23:17:26.748813Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2001.03994","last_updated":"2020-01-12T20:30:22Z","snapshot_observed_at":"2026-08-10T02:39:16.757240Z","submitted_at":"2020-01-12T20:30:22Z","title":"Fast is better than free: Revisiting adversarial training","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2001.03994","snapshot_observed_at":"2026-08-15T23:17:26.753762Z","title":"Zico Kolter","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-15T23:17:26.753762Z"},"links":{"cited_paper":"/paper/2001.03994","citing_paper":"/paper/2505.05091"},"observation_digest":"sha256:d9ae59e4da5c307b38e88eeb8aeb470c4bbac60ca3df014bffc18985e296e000","observation_id":"e7a91111-1a5f-4728-8de8-464cd6c4941b","resolution":{"observed_at":"2026-08-15T23:17:26.753762Z","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":"2026-08-15T23:17:27.185040Z","title":"Disparity estimation of stereo-endoscopic images us- ing deep generative network","venue":null,"work_id":"f1e02edb-23ae-4690-b00f-f5fe855631ea","year":2024},"citing_paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-15T23:17:26.758828Z"},"links":{"citing_paper":"/paper/2505.05091"},"observation_digest":"sha256:7f90da49deb8ed1d29d7fc3d807e1efee3207a228f9e3e627882a8210d7f3cb3","observation_id":"1e4f6e1d-fc2e-4253-9bb1-2c5db077f75a","resolution":{"observed_at":"2026-08-15T23:17:27.190050Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:17:27.168249Z","title":"Improving 2d feature representations by 3d-aware fine-tuning","venue":null,"work_id":"7a7b0027-c910-48ff-a44c-8f0670e5ab6e","year":2024},"citing_paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-15T23:17:26.763841Z"},"links":{"citing_paper":"/paper/2505.05091"},"observation_digest":"sha256:ab470e73641cffad78c7714ef6d20fe8f44a4daa02e9a8624a9f2b063b04a96d","observation_id":"04a56b34-d273-4560-b641-09848f8620e9","resolution":{"observed_at":"2026-08-15T23:17:27.173338Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:17:27.152895Z","title":"Robust synthetic-to-real transfer for stereo matching","venue":null,"work_id":"684cb796-1210-4d45-ae6d-ef4f84be7988","year":2024},"citing_paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-15T23:17:26.768915Z"},"links":{"citing_paper":"/paper/2505.05091"},"observation_digest":"sha256:ab2b5ea44c59be394bca92737a0a950b9e81fc88aaaa14da32c346f67ca09a8e","observation_id":"3e00268d-a0a0-471e-bd5f-35028420d8cc","resolution":{"observed_at":"2026-08-15T23:17:27.157729Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:17:27.137995Z","title":"Robust stereo matching with surface normal prediction","venue":null,"work_id":"bb2787da-a24e-4a68-add4-3f901b232ec3","year":2017},"citing_paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-15T23:17:26.774301Z"},"links":{"citing_paper":"/paper/2505.05091"},"observation_digest":"sha256:333bf54c4d8111c733cd2d4b2f2e723f01f818efa4e3f927f9ecc397712b94ef","observation_id":"aa86862e-45a1-4147-91e7-1b50f140fc58","resolution":{"observed_at":"2026-08-15T23:17:27.142790Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T23:17:27.122448Z","title":"in the wild","venue":null,"work_id":"fe56a99d-be4f-468e-a820-008ec5030390","year":null},"citing_paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","version":1},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-15T23:17:26.779322Z"},"links":{"citing_paper":"/paper/2505.05091"},"observation_digest":"sha256:32b4524a7c11becec0eefe152314237e2beaaf87cdf2603116d9e37f57f52686","observation_id":"58c091d1-ce40-4cef-8a4f-a0b9071a77a6","resolution":{"observed_at":"2026-08-15T23:17:27.127308Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2505.05091","last_updated":"2025-05-08T09:40:17Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-18T15:22:58.027129Z","submitted_at":"2025-05-08T09:40:17Z","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions"},"reference_resolution":{"displayed":64,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":10,"verified_exact":1,"verified_fuzzy":52},"total_outbound_references":64},"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":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 64 of 64 outbound references and 0 inbound Pith citation observations for arXiv:2505.05091."}