{"as_of":"2026-08-07T11:36:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d514812bb8b127cb3023aa203ca6db7b9f58a08fea85eb8b34e0db6fe1c1fb33","coverage":[{"denominator":126,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":100,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T18:28:06.197063Z","state":"measured"},{"denominator":100,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":100,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+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/2507.08400/citation-record","integrity":"/paper/2507.08400/integrity","json":"/paper/2507.08400/citation-record.json","paper":"/paper/2507.08400"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T18:27:55.316029Z","title":"Unifying flow, stereo and depth estimation,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T18:27:55.316029Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:8041509820e5ca85f75f7189d245d780b3c0f55167fb3a1506521da3d4fd898c","observation_id":"8e08957f-df30-4a39-b100-e668b58de074","resolution":{"observed_at":"2026-08-06T18:27:55.316029Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.11755","last_updated":"2024-03-15T00:41:08Z","snapshot_observed_at":"2026-07-06T16:34:50.603335Z","submitted_at":"2023-10-18T07:30:08Z","title":"RGM: A Robust Generalizable Matching Model","version":4},"cited_work":{"arxiv_id":"2310.11755","doi":null,"metadata_source":"pith","pith_arxiv_id":"2310.11755","snapshot_observed_at":"2026-08-06T18:28:09.366606Z","title":"RGM: A Robust Generalizable Matching Model","venue":"cs.CV","work_id":"78528646-5a0d-437d-aec0-f9afeb790fb7","year":2023},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T18:27:55.413951Z"},"links":{"cited_paper":"/paper/2310.11755","citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:820451ea7959ae99a18462cbe8e40680d3c151797c5ed488ee0e8707585ad6eb","observation_id":"a4856018-3235-4066-a28e-a20c3cf4d745","resolution":{"observed_at":"2026-08-06T18:28:09.448495Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:27:55.520556Z","title":"VGGT: Visual geometry grounded transformer,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T18:27:55.520556Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:aecaac3888ae11390253feee6edc4a7ef5cf060db59d1bd2c41a77de8d0a69d7","observation_id":"22dc7895-08a4-4bef-9892-a0b22db49a05","resolution":{"observed_at":"2026-08-06T18:27:55.520556Z","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":"2026-08-06T18:27:55.693953Z","title":"ITSA: An information-theoretic approach to au- tomatic shortcut avoidance and domain generalization in stereo matching networks,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T18:27:55.693953Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:c4989f9e94ae01bb0eca5e4897e5ac612c1eb5ea04b2367e0bb7a2066b049302","observation_id":"a68af55c-c400-42f4-938e-496ddc470e5d","resolution":{"observed_at":"2026-08-06T18:27:55.693953Z","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":"2026-08-06T18:27:55.848362Z","title":"Practical stereo matching via cascaded recurrent network with adaptive correlation,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T18:27:55.848362Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:9a8cf280b878a7e1b533dd0bba2b0782ed6e5157c32e0318404b1f3a0d77defb","observation_id":"dc776604-6663-4346-94a0-6840b3c8d2d5","resolution":{"observed_at":"2026-08-06T18:27:55.848362Z","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":"2026-08-06T18:27:55.983967Z","title":"Falling Things: A synthetic dataset for 3D object detection and pose estimation,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T18:27:55.983967Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:8707ef0de0a498481a5032ed98eccd5198d401f8c6496f0a032a1b5352a9a413","observation_id":"a84b3da9-beff-4998-b935-8ba936c4be83","resolution":{"observed_at":"2026-08-06T18:27:55.983967Z","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":"2026-08-06T18:27:56.130540Z","title":"A large dataset to train convolutional networks for disparity, optical flow, and scene flow estimation,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T18:27:56.130540Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:d7a7052d68290560ee0e5bbcaeaffaa1ea9515d4297c3b5b8c7a564df89fe4a5","observation_id":"8eb9d2df-ef9b-402f-aaef-51c33f30c590","resolution":{"observed_at":"2026-08-06T18:27:56.130540Z","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":"2026-08-06T18:27:56.280902Z","title":"FlowNet: Learning optical flow with convolutional networks,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T18:27:56.280902Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:1d888e8f28e41fb0d0f29456d9361853317aa24a7b0e0f0d4bc75ffe4ffdde54","observation_id":"523e6c0e-c3e1-425e-85cb-a6594a0f432f","resolution":{"observed_at":"2026-08-06T18:27:56.280902Z","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":"2026-08-06T18:27:56.405097Z","title":"AutoFlow: Learning a better training set for optical flow,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T18:27:56.405097Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:4c5d13277380e3790a394f0c9514f9be746ce34b740d520412db075006f6c4e9","observation_id":"56bf137e-42f2-43c7-807b-9142825cefc0","resolution":{"observed_at":"2026-08-06T18:27:56.405097Z","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":"2026-08-06T18:27:56.542683Z","title":"Virtual KITTI 2,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T18:27:56.542683Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:106edfa5755279756bd3ab80d288d12d03381283924bd7a811f3da216cc5dbb8","observation_id":"3563ed27-7027-4748-a5c5-dca5bf7b8290","resolution":{"observed_at":"2026-08-06T18:27:56.542683Z","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":"2026-08-06T18:27:56.678347Z","title":"Tartanair: A dataset to push the limits of visual SLAM,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T18:27:56.678347Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:249c620d682657d84da95e05bd7bd9e0976638b0da10d91c24a7d1af17d6e869","observation_id":"623ac377-7737-4e01-99df-196e8ec5d2c1","resolution":{"observed_at":"2026-08-06T18:27:56.678347Z","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":"2026-08-06T18:27:56.810938Z","title":"Hypersim: A photore- alistic synthetic dataset for holistic indoor scene understanding,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T18:27:56.810938Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:4ba99be5dc51eb1e9613af2b1407fd833f63f85e70671b20233087219e6f3b57","observation_id":"d7227d8c-2405-4d4b-a851-34f393eddd60","resolution":{"observed_at":"2026-08-06T18:27:56.810938Z","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":"2026-08-06T18:27:56.915233Z","title":"MegaDepth: Learning single-view depth prediction from internet photos,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T18:27:56.915233Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:ac3b4b836908baf56137ce9c19116f8ac190cc7337f0b87ac1f26388ea5db7d3","observation_id":"13a5178e-2507-4b54-9066-6fd6246ab2ff","resolution":{"observed_at":"2026-08-06T18:27:56.915233Z","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":"2026-08-06T18:27:56.995080Z","title":"CroCo v2: Improved cross-view completion pre-training for stereo match- ing and optical flow,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T18:27:56.995080Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:f5dd0641d8bf3961ce5747a98e0e5814b60433e7071d376a62743df69fd9d216","observation_id":"08a5d74e-5d15-4d08-b83d-1addc6550e21","resolution":{"observed_at":"2026-08-06T18:27:56.995080Z","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":"2026-08-06T18:27:57.078547Z","title":"Stereo Anything: Unifying stereo matching with large-scale mixed data,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T18:27:57.078547Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:f1ad8588014ee25fda557146478ba14c548e60b32ea4d7763c631d1ad665182a","observation_id":"de3a09c5-6ba9-44da-9aff-9b1cd063a342","resolution":{"observed_at":"2026-08-06T18:27:57.078547Z","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":"2026-08-06T18:27:57.135272Z","title":"FoundationStereo: Zero-shot stereo matching,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T18:27:57.135272Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:a3d8453971844182454281666fd1701d9707191d5df2b4326eaaae3734a023f1","observation_id":"74b6f3d5-a437-4759-98f7-f8da660c5c0a","resolution":{"observed_at":"2026-08-06T18:27:57.135272Z","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":"2026-08-06T18:27:57.214637Z","title":"Learning representations from foundation models for domain generalized stereo matching,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T18:27:57.214637Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:0487dbde80d36032eda3a9a26b547dddf68795b74a5472d19b7501c48c481167","observation_id":"e0a1d5ed-4c20-4868-baf4-780e8c467411","resolution":{"observed_at":"2026-08-06T18:27:57.214637Z","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":"2026-08-06T18:27:57.334619Z","title":"On the synergies between machine learning and binocular stereo for depth estimation from images: A survey,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T18:27:57.334619Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:19e0899a0a237ebd415481561c14a3671db583b023667c6d4cf97e7e2c7a3196","observation_id":"d86f6b7d-4b5f-4d06-a933-fcc639613a2f","resolution":{"observed_at":"2026-08-06T18:27:57.334619Z","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":"2026-08-06T18:27:57.497838Z","title":"A survey on deep learning techniques for stereo-based depth estimation,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T18:27:57.497838Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:f0c00c3ad0a4fe36ea39983e1cebc0ed82dad0e7f5f2adb2f954daba2a96f3a8","observation_id":"6de3392b-d0a8-49b9-906b-359a829e600c","resolution":{"observed_at":"2026-08-06T18:27:57.497838Z","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":"2026-08-06T18:27:57.643882Z","title":"Computing the stereo matching cost with a convolutional neural network,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T18:27:57.643882Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:a8e838dc4d1638a8b5637fbc4197b460ef568bcfd4e09481fd0405b5b4c77758","observation_id":"7a0af0fa-e914-4443-b8b6-bae8ea49fa71","resolution":{"observed_at":"2026-08-06T18:27:57.643882Z","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":"2026-08-06T18:27:57.814027Z","title":"SGM-Nets: Semi-global matching with neural networks,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T18:27:57.814027Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:65f683d3ecf297f6346bbb122f01163288b2eccb762b4f67c9a0ffeea03d2c82","observation_id":"f51a7b76-4f78-4d9e-9d0a-f9f75a090f57","resolution":{"observed_at":"2026-08-06T18:27:57.814027Z","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":"2026-08-06T18:27:58.026699Z","title":"A taxonomy and evaluation of dense two-frame stereo correspondence algorithms,","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T18:27:58.026699Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:3590b50923371d192987d41b59e073ed368198bf6f362168e4f09d75e7432186","observation_id":"c5afac59-5f1e-4738-b339-0b533d4618e3","resolution":{"observed_at":"2026-08-06T18:27:58.026699Z","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":"2026-08-06T18:27:58.138180Z","title":"Accurate and efficient stereo processing by semi-global matching and mutual information,","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T18:27:58.138180Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:4e60aad82ffbd199f285029946bf1de85b58acc0fdefb76e9bfa7494e0caceaa","observation_id":"ab66bdd6-e65d-4876-9a7b-2df83edefeaa","resolution":{"observed_at":"2026-08-06T18:27:58.138180Z","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":"2026-08-06T18:27:58.245456Z","title":"Pyramid stereo matching network,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T18:27:58.245456Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:5ac36b4e6d1dedfe878feeedc3db912a1397178d762ee4ca8de35c8567351170","observation_id":"d6dc37c7-540a-41e5-8916-411c3cf9a9f5","resolution":{"observed_at":"2026-08-06T18:27:58.245456Z","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":"2026-08-06T18:27:58.388134Z","title":"GA- Net: Guided aggregation net for end-to-end stereo matching,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T18:27:58.388134Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:60d30ed7b80d3f68f33484b3fac695a9eb26e3b4d5aa692be01c3500b4de8861","observation_id":"10d4a89f-97bf-4145-a64a-726100d771a6","resolution":{"observed_at":"2026-08-06T18:27:58.388134Z","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":"2026-08-06T18:27:58.567188Z","title":"AANet: Adaptive aggregation network for efficient stereo matching,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T18:27:58.567188Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:a69f52be54250abc62325dcf623d083fb603173637c2296ff90b5ea640b7607f","observation_id":"56802dd9-6455-4431-a8f2-2fdabac496a6","resolution":{"observed_at":"2026-08-06T18:27:58.567188Z","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":"2026-08-06T18:27:58.703406Z","title":"Attention concatenation volume for accurate and efficient stereo matching,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T18:27:58.703406Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:cdfe3cf29ae40ec100deae14a81f5546627f26a6930c04427ef5ead0df60b391","observation_id":"d2d53f5a-b8dd-4523-8e44-1bbe7aa29448","resolution":{"observed_at":"2026-08-06T18:27:58.703406Z","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":"2026-08-06T18:27:58.838315Z","title":"Stereo matching using multi-level cost volume and multi-scale feature constancy,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T18:27:58.838315Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:ecaeb38e79d5a57e77b72a7908d191f88c9e73b6587271a301202636362d90a4","observation_id":"abf963bc-a1cf-4617-9e5e-dec46f7c8369","resolution":{"observed_at":"2026-08-06T18:27:58.838315Z","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":"2026-08-06T18:27:58.915961Z","title":"Hierarchical deep stereo matching on high-resolution images,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T18:27:58.915961Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:873a9ece3984d697fef2abce11eb0166f3d1bd7f1bcdd61d4245f914e88f983d","observation_id":"c898ba81-bbe2-44e8-bcc7-1a63c5d605c6","resolution":{"observed_at":"2026-08-06T18:27:58.915961Z","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":"2026-08-06T18:27:59.041638Z","title":"Accurate and efficient stereo matching via attention concatenation volume,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T18:27:59.041638Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:85325c7f2da5055650183239ffbaacf17316614ea385eac44e618d063d14cbdb","observation_id":"d5a1e05f-e9bf-4754-b727-05ba1c421ffc","resolution":{"observed_at":"2026-08-06T18:27:59.041638Z","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":"2026-08-06T18:27:59.143521Z","title":"HITNet: Hierarchical iterative tile refinement network for real-time stereo matching,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T18:27:59.143521Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:686d9ceb5c06cf39a0426f728136d1888aaf7327cc104a924d35a020908b3f8f","observation_id":"de7dc1dc-b6e0-4247-b5bc-bbe80a89a97a","resolution":{"observed_at":"2026-08-06T18:27:59.143521Z","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":"2026-08-06T18:27:59.255720Z","title":"IGEV++: Iterative multi-range geometry encoding volumes for stereo matching,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T18:27:59.255720Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:e21755e42449af7524f712b0f7ff2291d623b3c70d3f99fbe66ec1f8871575b9","observation_id":"f4e53f92-e248-463a-a7b0-b9793de1798a","resolution":{"observed_at":"2026-08-06T18:27:59.255720Z","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":"2026-08-06T18:27:59.364437Z","title":"RAFT: recurrent all-pairs field transforms for optical flow,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T18:27:59.364437Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:59c9e656e59a38898dd0355ca4ae1202b01d807ed0fb9c30f5383814e49be835","observation_id":"4ee729f9-a356-4ed1-ab79-58ca44112ccb","resolution":{"observed_at":"2026-08-06T18:27:59.364437Z","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":"2026-08-06T18:27:59.430824Z","title":"RAFT-Stereo: Multilevel recur- rent field transforms for stereo matching,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T18:27:59.430824Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:ce5dca3618f5f4f6acf1cbcb99a526aa29dda132cdf0824bce54175d64076244","observation_id":"93f8cf5f-bb72-41de-818e-352348c577f1","resolution":{"observed_at":"2026-08-06T18:27:59.430824Z","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":"2026-08-06T18:27:59.519047Z","title":"Iterative geometry encoding volume for stereo matching,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T18:27:59.519047Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:a24c4bb69277869cde2520bcbe23404b10a0d61e76da4b6574a7828f7ab453b4","observation_id":"f7d00240-a3fa-4288-b773-9941718b1a21","resolution":{"observed_at":"2026-08-06T18:27:59.519047Z","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":"2026-08-06T18:27:59.629643Z","title":"Selective-Stereo: Adaptive frequency information selection for stereo matching,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T18:27:59.629643Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:37cac7c4053736a9bf02b76a58aeef436f269da91ec28f8bfd1f8fcff5e238f5","observation_id":"423a0676-0577-45ea-8189-9cb7b29695a0","resolution":{"observed_at":"2026-08-06T18:27:59.629643Z","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":"2026-08-06T18:27:59.684099Z","title":"Domain-invariant stereo matching networks,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T18:27:59.684099Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:9d7817fd663530bb15dc95d77f186afd67564174c5bb05fccfa8d2464c984531","observation_id":"da4e5a55-8a53-4db5-8a93-b2f359dcee8c","resolution":{"observed_at":"2026-08-06T18:27:59.684099Z","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":"2026-08-06T18:27:59.780051Z","title":"Matching-space stereo networks for cross-domain generalization,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T18:27:59.780051Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:a911cbd2ad8e9b0523eb443eba14355325f83358c3b0aab913944a73fba19dda","observation_id":"470f34df-99ff-46f7-94e4-7ce5bb6d641f","resolution":{"observed_at":"2026-08-06T18:27:59.780051Z","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":"2026-08-06T18:27:59.886699Z","title":"GraftNet: Towards domain general- ized stereo matching with a broad-spectrum and task-oriented feature,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T18:27:59.886699Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:80f1b80bf92862d2aa58f7b98c09a5cdbe0f8f64ded8262827bf8748a6059f3b","observation_id":"14ea3598-6a0b-415f-9a1a-361604af975b","resolution":{"observed_at":"2026-08-06T18:27:59.886699Z","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":"2026-08-06T18:27:59.971047Z","title":"Revisiting domain generalized stereo matching networks from a feature consistency perspective,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-06T18:27:59.971047Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:70c6cb23bc5af50a2253c13225b3578c29442171ffbc3e36c8b0f294c0dbe3fd","observation_id":"3d7beaef-a09f-4870-848f-78268e2199d6","resolution":{"observed_at":"2026-08-06T18:27:59.971047Z","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":"2026-08-06T18:28:00.029207Z","title":"An information-theoretic method to auto- matic shortcut avoidance and domain generalization for dense prediction tasks,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-06T18:28:00.029207Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:5b52b1520994a9a166f4b9e0b01436dd964470d16e3ca413fe4581feb702b71f","observation_id":"6cb79a5a-77e7-45e0-a362-528734f59f09","resolution":{"observed_at":"2026-08-06T18:28:00.029207Z","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":"2026-08-06T18:28:00.112929Z","title":"Domain generalized stereo matching via hierarchical visual transformation,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-06T18:28:00.112929Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:340d0f07e86fc72ac250be361e726fed938e8bfe3edc9c49da6530820f1a6d97","observation_id":"a022320b-c9b7-4e48-acd1-1a1f855e8edb","resolution":{"observed_at":"2026-08-06T18:28:00.112929Z","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":"2026-08-06T18:28:00.172988Z","title":"Masked representation learning for domain generalized stereo matching,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-06T18:28:00.172988Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:6185a8a678b365e6e2ea06a5477f7a0186785498736563e47b206dfd49a5e594","observation_id":"3c3ee99a-78e3-4d27-9fb9-19f662a7b9ac","resolution":{"observed_at":"2026-08-06T18:28:00.172988Z","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":"2026-08-06T18:28:00.250488Z","title":"ProbFlow: Joint optical flow and uncertainty estimation,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-06T18:28:00.250488Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:007f113df209f545a0ec47482d95d559e9acbd50ade6a1169a07c70cb200c118","observation_id":"15a37b8b-ac28-4807-9db4-8a5bf90e74e1","resolution":{"observed_at":"2026-08-06T18:28:00.250488Z","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":"2026-08-06T18:28:00.334103Z","title":"PWC-Net: Cnns for optical flow using pyramid, warping, and cost volume,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-06T18:28:00.334103Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:7871324387429306cca61efbd803cb3c8c06a81254d4d60fe86cf1866bf7e956","observation_id":"70b19502-fd2d-409a-b9ef-23771ddac057","resolution":{"observed_at":"2026-08-06T18:28:00.334103Z","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":"2026-08-06T18:28:00.418353Z","title":"Flownet 2.0: Evolution of optical flow estimation with deep networks,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-06T18:28:00.418353Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:e65718e353817f5761605fbd5f501efa2a541a92a634578d8c6c77ca082c4767","observation_id":"7b53521b-093e-4a8b-813e-69c5f4075f1c","resolution":{"observed_at":"2026-08-06T18:28:00.418353Z","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":"2026-08-06T18:28:00.495491Z","title":"Learning to estimate hidden motions with global motion aggregation,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-06T18:28:00.495491Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:af5a1df89c257e0fdcd4c577d09a340312a753156181b1f6361abfad44c5a4ee","observation_id":"3f49da2c-cb40-46d1-8459-a619b9fa4cf5","resolution":{"observed_at":"2026-08-06T18:28:00.495491Z","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":"2026-08-06T18:28:00.578918Z","title":"SEA-RAFT: simple, efficient, accurate RAFT for optical flow,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-06T18:28:00.578918Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:77bdabb9f1ad60426c9231d3c6a0bba85e0dbb69c794d5a735e145dcbab68ce5","observation_id":"76c06f85-8484-4679-9a66-35ce32db27ae","resolution":{"observed_at":"2026-08-06T18:28:00.578918Z","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":"2026-08-06T18:28:16.760721Z","title":"GMFlow: Learning optical flow via global matching,","venue":null,"work_id":"30533450-5aae-4234-b857-328195686cb3","year":2022},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-06T18:28:00.634110Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:d4cdee7f80b790ceb5df50b98a5983b6e1f910346dc911584dbc88da8b08c51b","observation_id":"225ebbe0-b5c2-470f-96df-0f0415d8d4ac","resolution":{"observed_at":"2026-08-06T18:28:16.764926Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:28:16.746603Z","title":"FlowFormer: A transformer architecture for optical flow,","venue":null,"work_id":"5b50c957-87f7-4235-9134-d3df7dd60f18","year":2022},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-06T18:28:00.719378Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:855b6d80d2bf64e4c1d3dcc41f0b58983caad4ce6f3e06fb2f8c7c5943b36e6c","observation_id":"dd342ed8-7abb-4622-b4f6-52b63b398424","resolution":{"observed_at":"2026-08-06T18:28:16.751102Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:28:16.732736Z","title":"A naturalistic open source movie for optical flow evaluation,","venue":null,"work_id":"c2118634-393a-4d3c-8663-6b99ebf4c748","year":2012},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-06T18:28:00.804319Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:73d12d757fbcb48faa71d8017abc03f661062d0652b2d61024c944e4b5bc6371","observation_id":"ab6f01c9-215e-4928-b5ed-d78e60f28b2d","resolution":{"observed_at":"2026-08-06T18:28:16.737166Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:28:16.718081Z","title":"Object scene flow,","venue":null,"work_id":"e72721c3-9885-4ff8-82c8-934efcf4320b","year":2018},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-06T18:28:00.873168Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:3eb66ec655a6ca36386b004c0ce60c2536083c9b73b558575ee119f07d720a91","observation_id":"342e49b3-281f-4111-bb8d-491753d34387","resolution":{"observed_at":"2026-08-06T18:28:16.722692Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:28:00.948144Z","title":"Playing for bench- marks,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-06T18:28:00.948144Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:a15a441ff0fecd2547bb7a3ff4cbe684bfbaeb5945e276a896bca069c960d814","observation_id":"4e1c594c-2e78-4345-b300-9c34ebcca8c3","resolution":{"observed_at":"2026-08-06T18:28:00.948144Z","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":"2026-08-06T18:28:16.692767Z","title":"Are we ready for au- tonomous driving? The KITTI vision benchmark suite,","venue":null,"work_id":"4a392242-6e96-46b4-831b-e83dc6f1b369","year":2012},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-06T18:28:01.000926Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:eb1f0bed5a0272379db69d073614a783092aaafa8cbd6c4221005efff2da7bc7","observation_id":"8c8e03a1-f094-4b11-a207-d47e208c01c5","resolution":{"observed_at":"2026-08-06T18:28:16.697491Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:28:16.679443Z","title":"Kubric: A scalable dataset generator,","venue":null,"work_id":"4ee535f0-db80-4f54-92e0-54f7604386cb","year":2022},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-06T18:28:01.084350Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:22de142519b7574152c942a3706dddbb33e4a29498221eaa51a08cc7443a2836","observation_id":"7218007d-7293-47e8-9f59-b882096aabc3","resolution":{"observed_at":"2026-08-06T18:28:16.683467Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:28:16.665436Z","title":"LIFT: learned invariant feature transform,","venue":null,"work_id":"f780fa54-65f0-4522-bafd-ab65e0431860","year":2016},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-06T18:28:01.163674Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:9e2f9d02401448b7a0c8782a1f1e337173fcc65215d251a89a4237b08fdebfa5","observation_id":"210794ed-489e-4eef-b6c7-d5203d98f2cf","resolution":{"observed_at":"2026-08-06T18:28:16.669838Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:28:16.651311Z","title":"SuperPoint: Self- supervised interest point detection and description,","venue":null,"work_id":"e9cf627c-5ca0-406c-99b6-ac05e50a34ac","year":2018},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-06T18:28:01.243934Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:be934d3d695ca4f800bb6cad9be4e34ff210e585e57bb8eccc93c0a661b2a65b","observation_id":"ad2f4bba-09df-4a80-8fe7-d9baf4b13be9","resolution":{"observed_at":"2026-08-06T18:28:16.655605Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:28:16.637186Z","title":"Super- Glue: Learning feature matching with graph neural networks,","venue":null,"work_id":"5b35aabd-3de9-4dd7-b087-9b520a9638f9","year":2020},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-06T18:28:01.322080Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:e3def50e7a4b84969454c133d75b99db63aafa0163ed820a6e56a69d1193f3de","observation_id":"36799e8f-f377-46c3-9af9-01912aa88735","resolution":{"observed_at":"2026-08-06T18:28:16.642077Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:28:16.623578Z","title":"Decoupling makes weakly supervised local feature better,","venue":null,"work_id":"55c13e1c-ee7e-4175-a13f-ae9e4f853eef","year":2022},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-06T18:28:01.363223Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:5093783136c521f20ed5c58ac1a33576062cb778f124d08205d4b23aac4a0d76","observation_id":"6a85f75c-ec04-4e6b-b7f9-ff1e62ba0ba0","resolution":{"observed_at":"2026-08-06T18:28:16.628070Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:28:16.610652Z","title":"Efficient neighbourhood consensus networks via submanifold sparse convolutions,","venue":null,"work_id":"72a4a766-2e97-4c19-a84f-de0efcb26548","year":2020},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-06T18:28:01.408546Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:08f5c9688a8b482cb88c416e4856e101bb451a0b5100f937769d9a5921fac845","observation_id":"73bb0844-5826-43db-aa86-196ae2de7da9","resolution":{"observed_at":"2026-08-06T18:28:16.614767Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:28:16.596172Z","title":"Dual-resolution corre- spondence networks,","venue":null,"work_id":"c50cc283-4bd3-4400-aaab-6e8ee477761c","year":2020},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-06T18:28:01.489650Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:4d2a1d2daf859919029ae27973a7573970517224f13b7a8bd67160254cadbffb","observation_id":"d766640d-214e-4f17-9eaa-363605ddda9b","resolution":{"observed_at":"2026-08-06T18:28:16.600899Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:28:16.582001Z","title":"LoFTR: Detector- free local feature matching with transformers,","venue":null,"work_id":"d560df8a-787d-4c0b-804e-12d2b5cdc514","year":2021},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-06T18:28:01.574049Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:7b8d053b1c3124010c9c049205f690330a6426563f2a8764747efe91ee52fae9","observation_id":"28fa2dd2-b475-470e-a36e-e2839054320d","resolution":{"observed_at":"2026-08-06T18:28:16.586746Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:28:16.568155Z","title":"RoMa: Robust dense feature matching,","venue":null,"work_id":"55378835-fb5c-4bf9-9733-35629080d8de","year":2024},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-06T18:28:01.636241Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:2acd8c8309246410789bc55e0f0810f439a1cb293d5d75c6a9a68a5c5cea99dc","observation_id":"dad95db4-5419-490d-a859-d37851252af9","resolution":{"observed_at":"2026-08-06T18:28:16.572849Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:28:16.554402Z","title":"DKM: dense kernelized feature matching for geometry estima- tion,","venue":null,"work_id":"fde5aeb5-d511-443e-8f5b-49e5efd9e406","year":2023},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-06T18:28:01.713917Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:5adf6288c3590e6efedf81e85b7be50c6912f33aa9dccd69914fc8702cace736","observation_id":"49dee2b5-e895-442e-994f-01674a519f24","resolution":{"observed_at":"2026-08-06T18:28:16.558573Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:28:16.539392Z","title":"Semi- dense feature matching with transformers and its applications in multiple-view geometry,","venue":null,"work_id":"eb56bdde-700f-4a0a-8c6f-b6ff211e8ce2","year":2023},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-06T18:28:01.808413Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:cb8e44aa3da0503da78eb89d6e9fe1a9850ec0e24faf9ce21385c02eb0e37b93","observation_id":"cb839b1d-3952-45eb-83bd-cf3e4d0751be","resolution":{"observed_at":"2026-08-06T18:28:16.544241Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2304.07193","last_updated":"2024-02-02T10:24:09Z","snapshot_observed_at":"2026-08-06T05:58:29.182448Z","submitted_at":"2023-04-14T15:12:19Z","title":"DINOv2: Learning Robust Visual Features without Supervision","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.07193","snapshot_observed_at":"2026-08-06T18:28:01.819806Z","title":"DI- NOv2: Learning robust visual features without supervision,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-06T18:28:01.819806Z"},"links":{"cited_paper":"/paper/2304.07193","citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:d88491b3d14c35c6e1a78cef6bfc63d9cc2c2f7e7e23e875e194a8c467766045","observation_id":"2468ec58-4be4-4f60-a583-a174b4e71078","resolution":{"observed_at":"2026-08-06T18:28:01.819806Z","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":"2026-08-06T18:28:16.524112Z","title":"Hierarchical discrete distribution decomposition for match density estimation,","venue":null,"work_id":"3c3429bc-7fb4-4d77-a1d7-afbddd6618b6","year":2019},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-06T18:28:01.907063Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:32e4d5811358608748bd356b3dd70dac9cbe5899950b2bd00bdef3f294efe162","observation_id":"a4e8efd8-5551-4f15-9b8f-644493418ca4","resolution":{"observed_at":"2026-08-06T18:28:16.528870Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:28:16.510385Z","title":"Learning accurate dense correspondences and when to trust them,","venue":null,"work_id":"7382d87c-2750-4395-822e-9fe1121af3c1","year":2021},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-06T18:28:01.996911Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:e002c6f98471a6e5b5980846dc80808e46e183e7c8c4dfab86f661a4ed3106ca","observation_id":"a900fd7a-1f5a-41c0-99ed-8b61605be8d9","resolution":{"observed_at":"2026-08-06T18:28:16.514541Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:28:16.497049Z","title":"PDC-Net+: Enhanced probabilistic dense correspondence network,","venue":null,"work_id":"658afd4d-f641-4361-9f22-4fefd0b385b3","year":2023},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-06T18:28:02.141089Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:a6a0e2d452542077f3e007adf0e4631fd513f55cf045819cd93745cd3a69c579","observation_id":"685755d5-b55d-43d5-bc4f-c0d3f4b36656","resolution":{"observed_at":"2026-08-06T18:28:16.501028Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:28:16.482647Z","title":"Learning transferable visual models from natural language supervision,","venue":null,"work_id":"f592fccf-1302-4222-901e-67116f573b64","year":2021},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-06T18:28:02.251941Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:93717aaf4d63e6bda752f8549f4369a1845aeb2333f97d48dd00cff56c10dd5e","observation_id":"56c50c65-c225-4a94-a936-abb17fbe0e02","resolution":{"observed_at":"2026-08-06T18:28:16.487404Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2304.02643","last_updated":"2023-04-05T17:59:46Z","snapshot_observed_at":"2026-07-06T15:12:37.953383Z","submitted_at":"2023-04-05T17:59:46Z","title":"Segment Anything","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.02643","snapshot_observed_at":"2026-08-06T18:28:02.320340Z","title":"Segment anything,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-06T18:28:02.320340Z"},"links":{"cited_paper":"/paper/2304.02643","citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:c97ba1ce52031026ac8a3a20207c110909f2a9f17338c187aa406685e6416609","observation_id":"da9c8a8d-1d7d-4bd5-b9f1-9089dcb386d9","resolution":{"observed_at":"2026-08-06T18:28:02.320340Z","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":"2026-08-06T18:28:16.468558Z","title":"Depth Anything: Unleashing the power of large-scale unlabeled data,","venue":null,"work_id":"4c848c3b-1c49-4695-849f-8b8cc5eb1268","year":2024},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-06T18:28:02.510342Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:15ff1df7f3e005e09e6bcb0e48bf8de777066e5e854ff64dbbbbb04d585cdaad","observation_id":"3bb9421e-1bce-4fdc-b7b1-64ab84224443","resolution":{"observed_at":"2026-08-06T18:28:16.473202Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:28:02.608693Z","title":"Vision transformer adapter for dense predictions,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-06T18:28:02.608693Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:a36f252bbb865bdd6c8ee05e6ccda13ae3e9cf20ba52c60928f0def50f297c3c","observation_id":"3f1537e4-d460-4591-a8b6-2a5b96bd17e8","resolution":{"observed_at":"2026-08-06T18:28:02.608693Z","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":"2026-08-06T18:28:16.443933Z","title":"Convolution meets lora: Parameter efficient finetuning for segment anything model,","venue":null,"work_id":"a4353a47-6a6d-496c-86b3-7b64b07afe35","year":2024},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-06T18:28:02.695951Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:53d8ecc4cc75acb7b4c1f21c2af0a9079b63ba551253db5766dc627f95ae3834","observation_id":"288b6057-146d-4a78-b617-c77d02d16e29","resolution":{"observed_at":"2026-08-06T18:28:16.448122Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.06261","last_updated":"2024-04-09T12:34:28Z","snapshot_observed_at":"2026-08-03T18:35:34.869337Z","submitted_at":"2024-04-09T12:34:28Z","title":"Playing to Vision Foundation Model's Strengths in Stereo Matching","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.06261","snapshot_observed_at":"2026-08-06T18:28:02.897608Z","title":"Playing to vision foundation model’s strengths in stereo matching,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-06T18:28:02.897608Z"},"links":{"cited_paper":"/paper/2404.06261","citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:2fe9626a7aa97a6a39ed5ab84de78b9a2f7e46262f07daf31dc98ca91b0d1dfc","observation_id":"4c50c942-a0a5-40b9-957d-7b532f76bdbe","resolution":{"observed_at":"2026-08-06T18:28:02.897608Z","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":"2026-08-06T18:28:16.405640Z","title":"Stereo Any- where: Robust zero-shot deep stereo matching even where either stereo or mono fail,","venue":null,"work_id":"91100323-6e97-4614-8dbf-a402fe6062d9","year":2025},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-06T18:28:03.053671Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:2d6d4ce53662128c5359529e498209a4e649629cd9c0916c02581d029f49a0a1","observation_id":"222e93f0-ff81-486c-8cab-9efda67fc022","resolution":{"observed_at":"2026-08-06T18:28:16.434050Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:28:16.265728Z","title":"Depth Anything V2,","venue":null,"work_id":"0560b750-7691-4575-ad3c-f21e32c9bf93","year":2024},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-06T18:28:03.189212Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:63dd04ff1d3371d9b8ba3afe9e652b60d6ccd50864b664cd1964059e64fd98bf","observation_id":"967f44ce-76a1-4e73-ad1f-a84325082ab6","resolution":{"observed_at":"2026-08-06T18:28:16.332279Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:28:16.201912Z","title":"SAMFlow: Eliminating any fragmentation in optical flow with segment anything model,","venue":null,"work_id":"5896065b-677b-4878-a40f-d288cf481c2a","year":2024},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-06T18:28:03.342178Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:52477c7b0d986ca31fe9429a948e941dc4692e5add164dd1513f4d6580ddca9f","observation_id":"95c7b3e9-dbb2-41d1-93c3-fe00a2fa5a9a","resolution":{"observed_at":"2026-08-06T18:28:16.227028Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:28:16.008729Z","title":"Decon- volutional networks,","venue":null,"work_id":"0c20bb2d-7dcf-4ffd-b3fc-93ab705be6d6","year":2010},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-06T18:28:03.501676Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:1f652521532113e69fe781ef617406e3f36e78ad7028e6918473a84208263427","observation_id":"4ebb7b36-2e87-4463-a4cb-f38407db18e1","resolution":{"observed_at":"2026-08-06T18:28:16.142618Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:28:03.624852Z","title":"Attention is all you need,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-06T18:28:03.624852Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:4d98e18d35ad52daf889bd7e08aacc8ea8e4881c8b0e360d3a62b932283d2857","observation_id":"dc2f5136-ce8f-4c81-91d1-ca5cd47fa350","resolution":{"observed_at":"2026-08-06T18:28:03.624852Z","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":"2026-08-06T18:28:15.743626Z","title":"A ConvNet for the 2020s,","venue":null,"work_id":"c04cb2bc-3ae7-40ca-b8e2-07dfbefc1e6f","year":2022},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-06T18:28:03.738799Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:98b31c49bb40bc385a42bd773b150663c5969e55722aba863eb498a6feece28c","observation_id":"3644632e-f506-426f-9353-3dd4b588a43c","resolution":{"observed_at":"2026-08-06T18:28:15.848283Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:28:15.559070Z","title":"Momentum contrast for unsupervised visual representation learning,","venue":null,"work_id":"a01d4054-d922-4168-94f4-e7c333bf5694","year":2020},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-06T18:28:03.860928Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:8fe910cf7146a0e408f0ecbb2e8fb82a0aba651607b4b8a14fecfb8eed21faec","observation_id":"2bd1ce66-c1e3-4f58-a34c-54a9de1d4496","resolution":{"observed_at":"2026-08-06T18:28:15.667734Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:28:15.260588Z","title":"DynamicStereo: Consistent dynamic depth from stereo videos,","venue":null,"work_id":"096a5435-ba98-4dd2-a445-99bb87f14839","year":2023},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-06T18:28:03.957646Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:bc99e25bb5e4cd23d1235fd5335c9fb63a38e89d496fc9e408ee09caa4e0b34b","observation_id":"5fb0403b-c482-47f8-ad6c-1095c8913e9f","resolution":{"observed_at":"2026-08-06T18:28:15.375570Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:28:15.162883Z","title":"AccFlow: Backward accumulation for long-range optical flow,","venue":null,"work_id":"ddf723a4-bcbb-4274-bae2-e159055e1135","year":2023},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-06T18:28:04.093743Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:6b703317befab6d134cacc5a2761f3b5faafdd3f2ddcf24d54609607dc204519","observation_id":"8c71ab7e-856c-47df-ad11-7f1d5b20d91f","resolution":{"observed_at":"2026-08-06T18:28:15.188045Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:28:15.058555Z","title":"Vision trans- formers need registers,","venue":null,"work_id":"bc498f7e-508d-400d-87f1-877631ecec8e","year":2024},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-06T18:28:04.216703Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:cb7f0638908d3457d921b3ae87b534304a015ce842cdb2948464a9de596cbf27","observation_id":"18ce96c3-1f3a-495f-8fe5-a81d276417c5","resolution":{"observed_at":"2026-08-06T18:28:15.096091Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:28:04.286053Z","title":"Decoupled weight decay regulariza- tion,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-06T18:28:04.286053Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:e7ba8abc9c37cb4681deb4ac470e11ef68dd64373d0df3482cf830b5452e303f","observation_id":"a76bf2fd-4260-4053-8eaf-3d891b9cfbde","resolution":{"observed_at":"2026-08-06T18:28:04.286053Z","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":"2026-08-06T18:28:14.927317Z","title":"Flow- Anything: Learning real-world optical flow estimation from large-scale single-view images,","venue":null,"work_id":"9958e2c3-c5dd-4f47-8218-ce75cf9a7448","year":2025},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-06T18:28:04.361195Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:197293cf544486192287e27742dfceabbf725e611e1c2aee05b91760757d3327","observation_id":"0405c4db-49da-48c1-b89a-b17f38220222","resolution":{"observed_at":"2026-08-06T18:28:14.993926Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:28:14.802207Z","title":"High-resolution stereo datasets with subpixel-accurate ground truth,","venue":null,"work_id":"b6bb2357-8dd9-46d6-be76-1aa2d1b44b38","year":2014},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-06T18:28:04.504181Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:124b24537d36e2bff2b9dffdb826b562a0f525fb16fef60bcebc253506ae92fe","observation_id":"523a3ad8-0da1-4999-9dcd-be7385e23837","resolution":{"observed_at":"2026-08-06T18:28:14.866368Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:28:14.722571Z","title":"A multi-view stereo benchmark with high-resolution images and multi-camera videos,","venue":null,"work_id":"08c25034-903d-4d3f-9283-4975f2d56d24","year":2017},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-08-06T18:28:04.675856Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:d11895bb57549924067c69bbd935bed28709630f2a39e687a03264811478b1d4","observation_id":"1a8b717f-2a85-4626-b18c-5b9c8df53244","resolution":{"observed_at":"2026-08-06T18:28:14.746901Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:28:14.609756Z","title":"Infinite photorealistic worlds using procedural generation,","venue":null,"work_id":"42d1e0ee-4a39-441f-9b84-0fc1d568bb82","year":2023},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-06T18:28:04.803144Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:d62917cca32e3157d7875676f38a6cf2c19dc820eccf7318670ae3882858032a","observation_id":"b2c7b987-60ec-40d2-8473-fad5ab1b006e","resolution":{"observed_at":"2026-08-06T18:28:14.648671Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:28:14.489086Z","title":"Spring: A high-resolution high-detail dataset and benchmark for scene flow, optical flow and stereo,","venue":null,"work_id":"b25a9631-e130-42c9-b807-4763284b53f9","year":2023},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-08-06T18:28:04.901861Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:00bd37c3f97fb9076ea847b1480e1cf76e0d00fbdaec72b89003d6aec0c0a1d8","observation_id":"95f0f366-90a3-4443-bef0-faae87752ec4","resolution":{"observed_at":"2026-08-06T18:28:14.547750Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:28:14.377117Z","title":"ScanNet: Richly-annotated 3D reconstructions of indoor scenes,","venue":null,"work_id":"e89b93c9-d4b3-41ea-b7fa-d3ecde790cf5","year":2017},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-08-06T18:28:05.049490Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:750ed29e5062297e4fe3274f7275030c34edcf7dc82146156ca3f88cf64268d2","observation_id":"6bd7c2d1-4e2d-4069-bf13-2fc8fc6945f8","resolution":{"observed_at":"2026-08-06T18:28:14.429805Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:28:14.272001Z","title":"YFCC100M: the new data in multimedia research,","venue":null,"work_id":"a906bbee-4122-47cf-960f-86d6100353ba","year":2016},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-08-06T18:28:05.198044Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:191da747ae6669cb489283c8b4992df459178bb0b94c54dc7470f9dc22d3265b","observation_id":"7acd1d3c-d5fd-4c24-a444-9928d042f719","resolution":{"observed_at":"2026-08-06T18:28:14.324374Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:28:14.154941Z","title":"WxBS: Wide baseline stereo generalizations,","venue":null,"work_id":"db844518-5048-49ba-8e0a-a687d6cfacad","year":2015},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":94,"source":"pdf_text","source_observed_at":"2026-08-06T18:28:05.367708Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:a2cd627fe7a1787f4c9b0f1a21f137ddf0252b04460ed9460f67c51b234b25d3","observation_id":"9251a0a4-6a90-4822-b5a5-89236745c504","resolution":{"observed_at":"2026-08-06T18:28:14.219261Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:28:14.022780Z","title":"Open challenges in deep stereo: the Booster dataset,","venue":null,"work_id":"dca3ec9c-82a7-4ff3-83cd-97471e81ded9","year":2022},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":95,"source":"pdf_text","source_observed_at":"2026-08-06T18:28:05.520308Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:47d6a892e48c42e98bc547094244667f0534f71d6b45fdf40b19b171d84c72d5","observation_id":"d46bf167-6370-4228-b13a-db4043a11b8f","resolution":{"observed_at":"2026-08-06T18:28:14.084079Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2101.01133","last_updated":"2021-01-28T20:09:37Z","snapshot_observed_at":"2026-08-05T15:58:56.319433Z","submitted_at":"2021-01-04T17:58:48Z","title":"Stereo Correspondence and Reconstruction of Endoscopic Data Challenge","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2101.01133","snapshot_observed_at":"2026-08-06T18:28:05.646183Z","title":"Stereo corre- spondence and reconstruction of endoscopic data challenge,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":96,"source":"pdf_text","source_observed_at":"2026-08-06T18:28:05.646183Z"},"links":{"cited_paper":"/paper/2101.01133","citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:40575f062eaf8d149d74778bf53ca063802dce868241ad30037a73c490409853","observation_id":"2f76a102-3cb4-4564-86d2-3b0277423d40","resolution":{"observed_at":"2026-08-06T18:28:05.646183Z","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":"2026-08-06T18:28:13.871714Z","title":"Drivingstereo: A large-scale dataset for stereo matching in au- tonomous driving scenarios,","venue":null,"work_id":"8949a9ca-852e-46a5-accd-e1e9f34682e8","year":2019},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":97,"source":"pdf_text","source_observed_at":"2026-08-06T18:28:05.807890Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:65618326d952ca9ac026933205ae87dd9630498120bdbb4f01a9eff76a6d3d65","observation_id":"a24ebcc5-0b88-4fe5-bf9f-3f632b9125dc","resolution":{"observed_at":"2026-08-06T18:28:13.948994Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:28:13.719981Z","title":"SUN3D: A database of big spaces reconstructed using sfm and object labels,","venue":null,"work_id":"22393b85-9442-4a89-b521-d345eced1f0f","year":2013},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":98,"source":"pdf_text","source_observed_at":"2026-08-06T18:28:05.937706Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:8407277f2c6e512c13085c55b5bc27e16fbaf1237fb92fd4a9a5dd9f26b902a3","observation_id":"b99dd61b-3ce8-48a4-96bd-4ab77fb4f2fd","resolution":{"observed_at":"2026-08-06T18:28:13.788626Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:28:13.570765Z","title":"A benchmark for the evaluation of RGB-D SLAM systems,","venue":null,"work_id":"cf36d325-a634-4da2-a177-995b0fa4734f","year":2012},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":99,"source":"pdf_text","source_observed_at":"2026-08-06T18:28:06.083463Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:6bd6dc842cae0a9884fd888d76c45592ae3397ce338a0ab1f1b2de3615955136","observation_id":"6c1d23ed-6f05-44db-86a2-7cbcc9c3b979","resolution":{"observed_at":"2026-08-06T18:28:13.639169Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-06T18:28:13.445406Z","title":"Flickr1024: A large-scale dataset for stereo image super-resolution,","venue":null,"work_id":"22738427-151a-4d83-a774-394dc2b8e873","year":2019},"citing_paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","version":1},"reference_index":100,"source":"pdf_text","source_observed_at":"2026-08-06T18:28:06.197063Z"},"links":{"citing_paper":"/paper/2507.08400"},"observation_digest":"sha256:2fa91b2cab4f75bb0adf39453db6acffb65f87dc31103800d05315c650e48ad6","observation_id":"f40e6da8-c91b-47df-aa13-7d7a32991b65","resolution":{"observed_at":"2026-08-06T18:28:13.488877Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2507.08400","last_updated":"2025-07-11T08:18:52Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-06T18:17:19.344380Z","submitted_at":"2025-07-11T08:18:52Z","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models"},"reference_resolution":{"displayed":100,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":55,"verified_exact":1,"verified_fuzzy":44},"total_outbound_references":126},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 100 of 126 outbound references and 0 inbound Pith citation observations for arXiv:2507.08400."}