{"as_of":"2026-08-22T04:25:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e1c44d42158a6b1db44dd6b1bfd2ab791ec4a0822852cdb16a873186c3b3c714","coverage":[{"denominator":94,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":94,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T05:33:54.116652Z","state":"measured"},{"denominator":96,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":96,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-21T06:32:19.484+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T10:52:48.578209Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-12T12:16:16.734455Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.07740","snapshot_observed_at":"2026-07-14T11:29:19.914651Z","title":"arXiv preprint arXiv:2506.07740 (2025)","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.10470","last_updated":"2026-07-11T20:18:23Z","snapshot_observed_at":"2026-08-14T09:57:08.962044Z","submitted_at":"2026-07-11T20:18:23Z","title":"On the Real-World Generalisability of Optical Flow Models","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-07-14T11:29:19.914651Z"},"links":{"cited_paper":"/paper/2506.07740","citing_paper":"/paper/2607.10470"},"observation_digest":"sha256:80cfee066852942eba3a3c4f23c4548230e06728b35fad09ad0139fbb39f1dd4","observation_id":"8931c9b9-9e23-401c-ad98-32b3411c90b1","resolution":{"observed_at":"2026-07-14T11:29:19.914651Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"cited_work":{"arxiv_id":"2506.07740","doi":"10.48550/arxiv.2506.07740","metadata_source":"pith","pith_arxiv_id":"2506.07740","snapshot_observed_at":"2026-08-12T12:16:16.734455Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","venue":"cs.CV","work_id":"257b4560-b470-4011-acea-282b1dd4f271","year":2025},"citing_paper":{"arxiv_id":"2608.11075","last_updated":"2026-08-11T15:37:49Z","snapshot_observed_at":"2026-08-19T12:09:59.032539Z","submitted_at":"2026-08-11T15:37:49Z","title":"Static in Frames, Dynamic in Events: Rethinking Features in Event Cameras as Motion Cues","version":1},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-12T10:52:48.578209Z"},"links":{"cited_paper":"/paper/2506.07740","citing_paper":"/paper/2608.11075"},"observation_digest":"sha256:bcdf21f038e0bec54d5b4c7c43c169651d1fa489f234c46dc9835dbbb3ac7173","observation_id":"827814c2-ed3e-44bc-84f5-5ec0eeb032d2","resolution":{"observed_at":"2026-08-12T10:53:37.098834Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2506.07740/citation-record","integrity":"/paper/2506.07740/integrity","json":"/paper/2506.07740/citation-record.json","paper":"/paper/2506.07740"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:33:42.614357Z","title":"Object tracking in satellite videos based on a multiframe optical flow tracker,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:42.614357Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:0670935b1c83a6c4f408495ef3549bc18d17fa578a7161ba548de847749ea2fa","observation_id":"c3bdf08a-572b-45f6-81b2-1c5708cf3174","resolution":{"observed_at":"2026-08-07T05:33:42.614357Z","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":"2026-08-07T05:33:42.678062Z","title":"Siamese-detr for generic multi- object tracking,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:42.678062Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:40316b2fdf9649329a5ca5bfeeb4655e47ab6c297e37fb53716cc49a50f2595b","observation_id":"82868004-9fa6-40b1-bc05-121807833087","resolution":{"observed_at":"2026-08-07T05:33:42.678062Z","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":"2026-08-07T05:33:42.780141Z","title":"Optical flow-based segmentation of moving objects for mobile robot navigation using pre-trained deep learning models,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:42.780141Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:97c8a85b1ade83ad5f89373a2b2b6db16adbb6b003a436ec60e714c1e4363735","observation_id":"3e69676f-71b6-4f6f-b5ef-447819854700","resolution":{"observed_at":"2026-08-07T05:33:42.780141Z","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":"2026-08-07T05:33:42.873056Z","title":"Learning monocular 3d reconstruc- tion of articulated categories from motion,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:42.873056Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:ba2de0384bf8fcca0dc1dbf1ca26cb97997b2c40d67c6f86505b517bd545a68f","observation_id":"b0b27218-4bcd-4f98-a6c3-bb0b618f902d","resolution":{"observed_at":"2026-08-07T05:33:42.873056Z","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":"2026-08-07T05:33:42.938351Z","title":"Flow- fusion: Dynamic dense rgb-d slam based on optical flow,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:42.938351Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:81f3c78b7d0ec931dfdb7efe7251e52a5f5627b09ce0bb8e4b54448d150316c4","observation_id":"3e5febd8-56aa-49e2-a435-dcde46bd9c58","resolution":{"observed_at":"2026-08-07T05:33:42.938351Z","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":"2026-08-07T05:33:43.143140Z","title":"Improving monocular visual slam in dynamic environments: an optical-flow-based ap- proach,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:43.143140Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:4d14112016ca3cebfece2522154c5f900954280dc14179d5f08c70afc24d2122","observation_id":"00538166-cdd7-4ea7-957c-37bf2ebb3338","resolution":{"observed_at":"2026-08-07T05:33:43.143140Z","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":"2026-08-07T05:33:43.303847Z","title":"Pwc-net: Cnns for optical flow using pyramid, warping, and cost volume,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:43.303847Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:a32336c68965de597b82d1803f38247450a7128c16f2554b1c07f69830091507","observation_id":"3ce91636-3c75-446c-bea4-0b61ddd0d0d2","resolution":{"observed_at":"2026-08-07T05:33:43.303847Z","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":"2026-08-07T05:33:43.386938Z","title":"Raft: Recurrent all-pairs field transforms for optical flow,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:43.386938Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:5f6024c9d2ac6bfb7b2bb10ac86439b8c93c53ae2e89e725ad92972bd36b3d18","observation_id":"23544dac-ef3f-45af-8225-2119c573d749","resolution":{"observed_at":"2026-08-07T05:33:43.386938Z","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":"2026-08-07T05:33:43.443667Z","title":"A lightweight optical flow cnn —revisiting data fidelity and regularization,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:43.443667Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:4ea50bd8f5dc66696c5a0312ac1ce084a267b94b0c43a3ecf9a0cf3b8048cb88","observation_id":"e32b2e9c-d82c-404e-b545-37412a802b24","resolution":{"observed_at":"2026-08-07T05:33:43.443667Z","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":"2026-08-07T05:33:43.554899Z","title":"Motion detail preserving optical flow estimation,","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:43.554899Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:167e150290bdb2c1291879abb2a10e49c5f0d4cb7fe81dde6ac32d9646e856ae","observation_id":"95e22663-80e9-4e14-afab-db589705c2e4","resolution":{"observed_at":"2026-08-07T05:33:43.554899Z","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":"2026-08-07T05:33:43.709616Z","title":"Deep- flow: Large displacement optical flow with deep matching,","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:43.709616Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:346d029d16661cc1b488bc04bec6e367b7b0cb2abdd62a0f95002150d27d8367","observation_id":"9af93bd0-925a-46d7-8b62-93a4cff77a50","resolution":{"observed_at":"2026-08-07T05:33:43.709616Z","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":"2026-08-07T05:33:43.833508Z","title":"Flownet: Learning op- tical flow with convolutional networks,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:43.833508Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:a34be33f240330b02923404ed2a1469cc9918f4887d128431d379daf29f295fa","observation_id":"8b53ee18-b789-419e-afe4-90951d7cc191","resolution":{"observed_at":"2026-08-07T05:33:43.833508Z","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":"2026-08-07T05:33:43.961850Z","title":"Flownet 2.0: Evolution of optical flow estimation with deep networks,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:43.961850Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:37450ae13844c6c47e44b407bbe66008ea766ed53c598431201cc553ca63a658","observation_id":"421eb532-bb89-4e12-b1b0-34b2a32a457c","resolution":{"observed_at":"2026-08-07T05:33:43.961850Z","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":"2026-08-07T05:33:44.103788Z","title":"Are we ready for autonomous driving? the kitti vision benchmark suite,","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:44.103788Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:6bfa31b7d095ba4a10d79482e9f51259d1769c5efa4ce8c57ccf60eb9023b0ae","observation_id":"f5a85dd7-7e2d-45a1-8e72-760c797419a1","resolution":{"observed_at":"2026-08-07T05:33:44.103788Z","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":"2026-08-07T05:33:56.393597Z","title":"Object scene flow for autonomous vehicles,","venue":null,"work_id":"82214fde-d477-4645-acbe-9f64430fe0f2","year":2015},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:44.238494Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:920e6867325da2b7f1f90553c54bef2cb1f0325cef272649c2c41bfd923608cc","observation_id":"7de1a2df-1fae-4686-b390-fc0b5924e1a6","resolution":{"observed_at":"2026-08-07T05:33:56.396851Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:56.383692Z","title":"Dynamic shape capture via periodical- illumination optical flow estimation and multi-view photometric stereo,","venue":null,"work_id":"380d4574-f9ae-4daa-b660-e703a30e1d78","year":2011},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:44.332005Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:8d67165a3f60e34f56bd4b5c89a4a559cf8e9092e97ef889c8442ff98ed16b01","observation_id":"d4c7ca85-cd94-4080-b8b9-c3ec62e23147","resolution":{"observed_at":"2026-08-07T05:33:56.386867Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:56.373947Z","title":"Learning optical flow and scene flow with bidirectional camera-lidar fusion,","venue":null,"work_id":"10e89d53-0aa3-433c-8813-06ba8b944133","year":2024},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:44.441277Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:25dc5159ce716cc6150492670fe0ab06f0ff4f93061df5a7d39720d9c6daf6a2","observation_id":"a0a3aae3-5111-410e-ba57-3a12deebc625","resolution":{"observed_at":"2026-08-07T05:33:56.377194Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:56.364723Z","title":"Dense continuous- time optical flow from event cameras,","venue":null,"work_id":"a5769e18-3260-458d-aaac-bd6d4df9cbe7","year":2024},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:44.559805Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:5a5fec2628d7898da7c03529e3098d5456a63218824209d12f5a671e63e1b725","observation_id":"a34c7f51-99e5-4a3e-a374-560ba7412017","resolution":{"observed_at":"2026-08-07T05:33:56.367900Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:56.355078Z","title":"How do neural networks estimate optical flow? a neuropsychology- inspired study,","venue":null,"work_id":"7e93033a-b320-4edb-a9bd-2bbf9c4b3c16","year":2021},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:44.659524Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:588410e160f9fb623a5ac567b5231b886d475a8a5b980f3281e83344d09a71f0","observation_id":"4b3aaf8d-5051-455e-a018-45aff1c623e9","resolution":{"observed_at":"2026-08-07T05:33:56.358369Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:56.345498Z","title":"Instance segmen- tation in the dark,","venue":null,"work_id":"f11535ca-d4ea-49f3-b200-1d49bf1de37b","year":2023},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:44.772163Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:fcb51641dbd0bab6e935f84c2087c63fde0912266f8c8eb2f1dca14a865f5c3c","observation_id":"5cb1d18d-974c-4acc-8c87-61db17e17c45","resolution":{"observed_at":"2026-08-07T05:33:56.348791Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:56.335830Z","title":"Learning optical flow from still images,","venue":null,"work_id":"90152c0c-b943-49e3-abba-df6c57f13ddd","year":2021},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:44.914939Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:0a669656fa0f284b504cc837c308c8d04a6e15d0dd55658e96106e2aaf0fb7df","observation_id":"8b6a2e90-4fee-49a9-b76a-7dc75b5a20ee","resolution":{"observed_at":"2026-08-07T05:33:56.339343Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:56.325711Z","title":"Realflow: Em-based realistic optical flow dataset generation from videos,","venue":null,"work_id":"df64d97f-c0db-4956-8e56-4fcac2cd3488","year":2022},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:45.044610Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:1553194c00d7e2dbf7d786cfa6c17c34440533aad7f777335cf75b1c7ac6c0ab","observation_id":"c9472c7f-0651-471d-a21d-6c83b6da1393","resolution":{"observed_at":"2026-08-07T05:33:56.329173Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:56.315234Z","title":"Single-view view synthesis with mul- tiplane images,","venue":null,"work_id":"759c4596-9611-49f0-9a7a-cc1f1cf367d0","year":2020},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:45.116132Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:b894aba96b931aa6ba3ba324aca9f40d6359f0cd927df8dbef7b49d9543ca55f","observation_id":"b1981d5e-2acb-4856-9d2f-44addc033cc0","resolution":{"observed_at":"2026-08-07T05:33:56.318843Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:56.304305Z","title":"Single-view view synthesis in the wild with learned adaptive multiplane images,","venue":null,"work_id":"7b933346-22b6-4f6b-8b06-65dfb7b8804f","year":2022},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:45.231629Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:c211dc853a87184ce47cb45b0e4176d7b1e3b50af9a36d9bb91d1bcda6a40414","observation_id":"b54959a2-c078-4a4d-a59b-856d02b0be8b","resolution":{"observed_at":"2026-08-07T05:33:56.308421Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2001.10773","last_updated":"2020-01-29T12:13:20Z","snapshot_observed_at":"2026-07-06T08:53:28.193420Z","submitted_at":"2020-01-29T12:13:20Z","title":"Virtual KITTI 2","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2001.10773","snapshot_observed_at":"2026-08-07T05:33:45.521762Z","title":"Virtual kitti 2,","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:45.521762Z"},"links":{"cited_paper":"/paper/2001.10773","citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:5693b3a84474f5cd5b590a533c6a63fbd4ccabab1491773acfcdc289213ba85e","observation_id":"8bb32027-9c03-4fa6-84f2-cf9ac9b6ca27","resolution":{"observed_at":"2026-08-07T05:33:45.521762Z","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":"2026-08-07T05:33:56.283609Z","title":"Spring: A high-resolution high-detail dataset and benchmark for scene flow, optical flow and stereo,","venue":null,"work_id":"4bd91d4a-50a6-4998-90ce-81962f121951","year":2023},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:45.682200Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:e0dff6c6219b8e0f398eb69cb239fdc0eaabbc12c88616e0c247234f106c540a","observation_id":"07965378-cfc1-4d2f-a217-bf89f1a82b0c","resolution":{"observed_at":"2026-08-07T05:33:56.286991Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:56.273361Z","title":"Stereo ground truth with error bars,","venue":null,"work_id":"e8a13b6d-7a99-4f2b-a579-e42ed477e0c8","year":2015},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:45.839102Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:fded52230c69dab112c983339034fbc444c07701dd20db69bb3eb7e7faa9ce35","observation_id":"6eba3e63-3ccc-4d7c-9195-09dbc8f5057c","resolution":{"observed_at":"2026-08-07T05:33:56.276655Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:56.263666Z","title":"Multi-scale binocular stereo matching based on semantic association,","venue":null,"work_id":"d292ac94-d7a5-4151-b2e1-f303a0fa0bb7","year":2024},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:45.947107Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:9baa0141fb7c5f991970d905a193ce70db822bb6c495b67321ec8467cb386af0","observation_id":"cf208f81-34d8-4d3e-a322-44bc4034e5df","resolution":{"observed_at":"2026-08-07T05:33:56.266835Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:56.253443Z","title":"Liteflownet: A lightweight convolutional neural network for optical flow estimation,","venue":null,"work_id":"52ccd3cc-55ed-4690-8b63-dc395eebe5eb","year":2018},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:46.095524Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:6a2b5de9421475c786a8e5e1b0d0b271f55b7c3a1203d7a97c73e62f2464eff8","observation_id":"3e26e391-5596-421d-9717-f0417580a978","resolution":{"observed_at":"2026-08-07T05:33:56.257203Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:56.244086Z","title":"Iterative residual refinement for joint optical flow and occlusion estimation,","venue":null,"work_id":"42a0eee4-c2c5-466d-a96f-19eaa0fd5e9d","year":2019},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:46.182923Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:9456dbf9b605b02fd06ec4156be8afaf8a7f2f3bce266ac157cfbe4b90533470","observation_id":"9adf627c-6785-423f-8c56-6d31ad13793e","resolution":{"observed_at":"2026-08-07T05:33:56.247165Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:56.233590Z","title":"Learning optical flow with adaptive graph reasoning,","venue":null,"work_id":"8f53ab9a-d5c3-472c-bf4c-e280706241bb","year":2022},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:46.349429Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:6f3fd8e6a56f5a9c9dd0bc8bb0abc4aa72af37d62e8d3287b0e22c0df476af16","observation_id":"1b360999-0652-4031-8080-71b30ad82e02","resolution":{"observed_at":"2026-08-07T05:33:56.237157Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:56.222847Z","title":"Transformer based pluralistic image completion with reduced information loss,","venue":null,"work_id":"a11b2ac9-ffc0-4ba4-844a-2dff3c88e6df","year":2024},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:46.443693Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:5652beef96a75db6d18f6faba0947d61cd11004af7e052e8af9d42c6021d6183","observation_id":"3c4718dd-4279-4320-8428-5745c7df1604","resolution":{"observed_at":"2026-08-07T05:33:56.226182Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:56.212502Z","title":"Flowformer++: Masked cost volume autoencod- ing for pretraining optical flow estimation,","venue":null,"work_id":"1a34cf01-31cd-4ac0-8d02-5281743e5a5b","year":2023},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:46.559205Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:ce89bb0587c7e987c36151a4bf53a933978a9dd90933ee919c6830b7398e16f5","observation_id":"64d28427-94a3-4442-a428-a7c7c07d92c9","resolution":{"observed_at":"2026-08-07T05:33:56.215882Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.14793","last_updated":"2024-05-23T17:04:04Z","snapshot_observed_at":"2026-08-16T13:50:05.645403Z","submitted_at":"2024-05-23T17:04:04Z","title":"SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical Flow","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.14793","snapshot_observed_at":"2026-08-07T05:33:46.710167Z","title":"Sea-raft: Simple, efficient, accu- rate raft for optical flow,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:46.710167Z"},"links":{"cited_paper":"/paper/2405.14793","citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:d4f1159a34b79b19e1f5e8c8a3c56d3e5b01baf473feef256accf06b5f8a6d12","observation_id":"936bed64-45b9-4762-a8a1-80afc56a2a81","resolution":{"observed_at":"2026-08-07T05:33:46.710167Z","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":"2026-08-07T05:33:56.202238Z","title":"Physics-based noise mod- eling for extreme low-light photography,","venue":null,"work_id":"80ef868b-212e-40c5-b4a2-4b842e099339","year":2022},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:46.847239Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:46bd6b62055b0d296e610b13f9fd164e5415ef928fec765776826f2f911fbbee","observation_id":"15fe043a-2471-43c8-9b48-f128e843b306","resolution":{"observed_at":"2026-08-07T05:33:56.205656Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:56.191663Z","title":"Relation-guided adversarial learning for data- free knowledge transfer,","venue":null,"work_id":"5a3d098f-45e6-4c52-897b-981c94684604","year":2025},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:46.905773Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:9fce247474514e6dc0e0133943c62ee6aaa82fefdaa2005292296d5681cb91c7","observation_id":"0306ae51-9e5a-431a-920f-71a4f9516c3a","resolution":{"observed_at":"2026-08-07T05:33:56.195212Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:56.180639Z","title":"Guided hyperspectral image denoising with realistic data,","venue":null,"work_id":"64b11d28-9952-47b6-bd27-37f1e531e534","year":2022},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:47.031999Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:c74df8127515998f0ed58eedf88bb6271a289b52cfd8550a7c7b7f0e098c220a","observation_id":"782a1eb3-6459-4a6a-8589-f3d3282753c5","resolution":{"observed_at":"2026-08-07T05:33:56.184349Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:47.139841Z","title":"Low-light raw video denoising with a high-quality realistic motion dataset,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:47.139841Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:8b6ca9ac6b3475288fd23e0f9df7a5bfb20786d5b02ab67ff1bb5c5f4d245588","observation_id":"43780c11-2c92-4cae-a075-a313e8cd24b5","resolution":{"observed_at":"2026-08-07T05:33:47.139841Z","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":"2026-08-07T05:33:56.164053Z","title":"Eventhdr: From event to high-speed hdr videos and beyond,","venue":null,"work_id":"e2c070c6-5ac3-4b7e-8298-9d7ca2e34ca0","year":2024},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:47.247545Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:16fd5adf1dba052ee7c2c471091a8c9c41600b9f806cf713f0401e4d5e2b4b65","observation_id":"92c54511-7e95-4f4d-8298-f1097bcba53c","resolution":{"observed_at":"2026-08-07T05:33:56.167192Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:56.154784Z","title":"A database and evaluation methodology for optical flow,","venue":null,"work_id":"61af78bf-2ae0-4948-a568-de7010d740db","year":2011},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:47.369573Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:0a69c5aceafd6c72e02a64e936b1ddcdf19bdfc641b039e837b0a1e70077bbaf","observation_id":"42cf3658-6649-49f5-b768-fa3e4d5064cf","resolution":{"observed_at":"2026-08-07T05:33:56.157866Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:56.144613Z","title":"Autoflow: Learning a better training set for optical flow,","venue":null,"work_id":"96694ab3-a9eb-4681-9ab1-374b0cfd816e","year":2021},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:47.473053Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:a2b4a07d5d74c72b6dc37d1ac4b1f7736b197cc6bd351d4c344ae1b7abca26b8","observation_id":"c6c3bc5e-8a59-4179-b744-e9839f8979ad","resolution":{"observed_at":"2026-08-07T05:33:56.148009Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:56.134211Z","title":"Mpi-flow: Learning realistic optical flow with multiplane images,","venue":null,"work_id":"cc0d0dea-e4ba-407f-9141-a3c913f60c94","year":2023},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:47.653610Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:e80a735f9fbd4c5fb1b349cd9f7563e41fe1b4ea50eede4469de1087d1229cfb","observation_id":"f5e3a5a5-aff8-4863-a091-fa4f3185a856","resolution":{"observed_at":"2026-08-07T05:33:56.137761Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1906.07751","last_updated":"2019-06-18T18:21:46Z","snapshot_observed_at":"2026-08-14T16:13:43.526790Z","submitted_at":"2019-06-18T18:21:46Z","title":"Neural Volumes: Learning Dynamic Renderable Volumes from Images","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1906.07751","snapshot_observed_at":"2026-08-07T05:33:47.803779Z","title":"Neural volumes: Learning dynamic renderable volumes from images,","venue":null,"work_id":null,"year":1906},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:47.803779Z"},"links":{"cited_paper":"/paper/1906.07751","citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:e324cb0ddbd5f71ab5fd5f90936678716ac180339722179af28ef882db81a13d","observation_id":"72f78ee1-99de-41f9-ba5b-d5747856284c","resolution":{"observed_at":"2026-08-07T05:33:47.803779Z","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":"2026-08-07T05:33:47.978932Z","title":"Nerf: Representing scenes as neural radiance fields for view synthesis,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:47.978932Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:22e6f64f41cb6726c92d0d438fb1d656703e5d48ea379c53348446d37eeb9ba7","observation_id":"d1a2fd31-cfc0-4150-9805-99ec4e573356","resolution":{"observed_at":"2026-08-07T05:33:47.978932Z","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":"2026-08-07T05:33:56.117659Z","title":"Hsi-guided intrinsic image decomposition for outdoor scenes,","venue":null,"work_id":"07c1cb89-5b6a-4698-b49c-83e310f83fb6","year":2022},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:48.126114Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:55e7e3ecbad36c858f27947ba6a5323966ff0f7c1db6e80b96c063c5c34bf9bb","observation_id":"ddd86d4a-3bb7-49c7-90cd-0e7ef88e9092","resolution":{"observed_at":"2026-08-07T05:33:56.120932Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:56.108438Z","title":"Geometry-free view syn- thesis: Transformers and no 3d priors,","venue":null,"work_id":"d21d02e3-e262-4948-9d16-68afc3736560","year":2021},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:48.324798Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:557b0288b78abb36d08d1d32ed45656a8895944f25cececcd4eaf0d887aa3923","observation_id":"f97421c0-d45c-4085-8268-ba3f208e22cd","resolution":{"observed_at":"2026-08-07T05:33:56.111746Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:56.098476Z","title":"Pixelsynth: Generating a 3d-consistent experience from a single image,","venue":null,"work_id":"dae07e00-b645-458c-80bc-0e9341a08c4b","year":2021},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:48.402406Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:6be3d3c5244a27ff9abe13b289e77b073f5d9738ff347686cef4362ec6a117b7","observation_id":"33727bff-cc82-40ed-bb58-9e5a7d3c7eb2","resolution":{"observed_at":"2026-08-07T05:33:56.102189Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:56.088463Z","title":"Mine: Towards continuous depth mpi with nerf for novel view synthe- sis,","venue":null,"work_id":"2c15c7ca-3c1a-400c-abb8-2ef64321b15a","year":2021},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:48.582784Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:f71c26809cf2dfd6a21dd627050d5a12117db3ed5d0ccad15352b6325e78e829","observation_id":"f079012c-d5cf-4519-8802-5d66098e9ad2","resolution":{"observed_at":"2026-08-07T05:33:56.092135Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:56.078914Z","title":"Depth anything: Unleashing the power of large-scale unlabeled data,","venue":null,"work_id":"f0d6cc2a-ca83-47ba-97c6-fd3dc470376d","year":2024},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:48.715083Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:d44160cf6f0137d423536ca92984c341b89b8a9e5f191042f5eec68122e3b2c5","observation_id":"622178c1-25a9-416e-aea8-41ec620331b7","resolution":{"observed_at":"2026-08-07T05:33:56.082139Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:56.058962Z","title":"Multiple view geometry,","venue":null,"work_id":"3b2842ae-d6e3-4031-b1f7-6c9df99ccd58","year":2005},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:48.988307Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:0d904b770c67a0b70709af802b34bd582ec30c9222c36a74c72b73d4708b5ece","observation_id":"f1e88481-2048-4d7f-a8f1-d5545d4592b4","resolution":{"observed_at":"2026-08-07T05:33:56.061914Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:56.049200Z","title":"High-resolution image synthesis with latent diffusion models,","venue":null,"work_id":"0dfab9aa-3a67-4b6a-917b-7dd063ec59e7","year":2022},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:49.104227Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:a9373887f183098c0049c578dffc1b8894db538fcb890a7a014f9b6e77e0ade4","observation_id":"419e3ad1-f171-45c0-990b-4cc76ee52d2d","resolution":{"observed_at":"2026-08-07T05:33:56.052692Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:56.293751Z","title":"A naturalistic open source movie for optical flow evaluation,","venue":null,"work_id":"1bc862c5-e28c-49b1-912a-519734153755","year":2012},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:49.308462Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:fc30dc5faee559586d89ec7b601841ff513f75e1142a218c1b46347f78eb3cf1","observation_id":"e9ad5295-813c-4859-813d-0fbe7d03074c","resolution":{"observed_at":"2026-08-07T05:33:56.297396Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:56.039175Z","title":"Bdd100k: A diverse driving dataset for hetero- geneous multitask learning,","venue":null,"work_id":"4afba1b0-eebf-4128-9c8a-4a4ddcf18905","year":2020},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:49.462340Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:19121b9ca6ab16d9be1bb0ac247f25668ee4f24dca9e36a20c37dfc9680fdc54","observation_id":"7ba530a6-19f7-459c-be5d-1d67735d97fd","resolution":{"observed_at":"2026-08-07T05:33:56.042607Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:56.029065Z","title":"Microsoft coco: Common objects in context,","venue":null,"work_id":"1920d73d-ec95-41a9-9a72-31c1eb9aaffa","year":2014},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:49.688087Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:456277c102a02105cad91b628d9296dac80873ba3df7f47326e563a844f28cd7","observation_id":"e623816d-a920-41be-847b-ffe9b232227a","resolution":{"observed_at":"2026-08-07T05:33:56.032380Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:56.019060Z","title":"Google landmarks dataset v2-a large-scale benchmark for instance-level recognition and retrieval,","venue":null,"work_id":"df5c9c93-807e-43dd-a537-ab240d68f3d2","year":2020},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:49.835916Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:eb82d26e9567ce8302a604f3f2bdaaef84a0867a970bda6482e7bbccd0553e4b","observation_id":"8743a2ca-820c-4354-b4a8-4539ac8029b0","resolution":{"observed_at":"2026-08-07T05:33:56.022481Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:56.009697Z","title":"nuscenes: A mul- timodal dataset for autonomous driving,","venue":null,"work_id":"a4299fd0-ca1f-474f-a2fc-703c15a96b00","year":2020},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:49.989891Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:ef58602d4b430b028b6ec85d4edce17a08bf571b5d9bd6dfd95471a2065b21cc","observation_id":"a47ee091-eea3-46a9-b9b9-e232132da8da","resolution":{"observed_at":"2026-08-07T05:33:56.012806Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:55.998871Z","title":"Sun rgb-d: A rgb-d scene understanding benchmark suite,","venue":null,"work_id":"8f2588fe-9d95-499a-8dd1-648d22525e54","year":2015},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:50.094233Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:8def463d5f7fc07a7ac97d04c9ab3dfff8050c360a3f024d58f1ffaad97b0b0e","observation_id":"42dd22a2-1bfa-4ddc-b6cc-3115f00b8832","resolution":{"observed_at":"2026-08-07T05:33:56.002526Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:55.988458Z","title":"Vision meets robotics: The kitti dataset,","venue":null,"work_id":"e71b7d6f-3e13-409e-b03a-8124096af7fc","year":2013},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:50.212505Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:f28d701de30fb534a6d805d407725dc06ec7085702ffcb5b862884e82edc7a99","observation_id":"7b9618d3-5647-423b-a12a-c6f64d2ef2ef","resolution":{"observed_at":"2026-08-07T05:33:55.991648Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:55.978121Z","title":"Indoor segmen- tation and support inference from rgbd images,","venue":null,"work_id":"88b1d90e-10af-4e0e-8b4b-bca4bed1ad75","year":2012},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:50.382751Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:76ea06433214f6d84ce529f289bef0a2849d5f443d0366c733b06efc3801c141","observation_id":"bf68993e-90ce-41a5-bc96-6d8440f6412b","resolution":{"observed_at":"2026-08-07T05:33:55.981667Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:55.967809Z","title":"The cityscapes dataset for semantic urban scene understanding,","venue":null,"work_id":"b675175d-6ff5-4ce9-9ae7-09befcc840a7","year":2016},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:50.533970Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:c502487f917534a2061327584a6fd03e2c85d9c337d3f7371f8db56c16479137","observation_id":"15fb85ce-5e1a-4045-b558-a61ae6f30185","resolution":{"observed_at":"2026-08-07T05:33:55.971446Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:55.956802Z","title":"A benchmark dataset and evaluation methodology for video object segmentation,","venue":null,"work_id":"6cb2c80d-abde-455b-aecc-f529fdadc673","year":2016},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:50.646026Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:465eac39742b38a861e93e9b9d5f7000f930b735486776f0ba8249280ec7fa8b","observation_id":"700ce5c0-b096-47f0-8f8a-206b8aada1bc","resolution":{"observed_at":"2026-08-07T05:33:55.960802Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:56.068541Z","title":"Masked-attention mask transformer for universal image segmen- tation,","venue":null,"work_id":"5ea80504-4e35-4d0a-a433-239b9525615d","year":2022},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:50.787271Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:e01531a2e82d8cf4cee73510139239bf06dc2a177b7108c20677a326b49e4753","observation_id":"0820dc34-de6d-4998-9325-3268838c6dc7","resolution":{"observed_at":"2026-08-07T05:33:56.072000Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:55.946343Z","title":"Learning to estimate hidden motions with global motion aggregation,","venue":null,"work_id":"0258107f-5e69-473d-9f48-bbd7046cc7a8","year":2021},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:50.951449Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:cf9b7dd8e1c7ad1c815378cb282190a244c6bc8fe4529bb7f583445c8ae9aab0","observation_id":"5dcefa69-e7a2-4f3a-a9ed-ef8fe1725c05","resolution":{"observed_at":"2026-08-07T05:33:55.950209Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:55.935078Z","title":"Skflow: Learning optical flow with super kernels,","venue":null,"work_id":"3ca5e70c-3c39-41fa-abf4-50e961db7443","year":2022},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:51.079064Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:dc56ed9b27e2ed73470bd8fb6f6f282e1525b929614d2aa4aa69252df9233c25","observation_id":"dd0c4256-18a6-4d88-9d56-b2397ee28a87","resolution":{"observed_at":"2026-08-07T05:33:55.938898Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:55.925383Z","title":"Flowformer: A transformer architecture for optical flow,","venue":null,"work_id":"a08e9880-239a-4b9b-acc8-2e0ecc8ff7a1","year":2022},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:51.149902Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:70400e3b386498e306dd07f8bde227856190747eecf9e3d5e8cb7cb9e5c36291","observation_id":"f387b999-bc6b-4db4-81f9-2ebbd0590726","resolution":{"observed_at":"2026-08-07T05:33:55.928588Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:55.915310Z","title":"Dip: Deep inverse patchmatch for high-resolution optical flow,","venue":null,"work_id":"2e620f8c-ac6c-40a8-89fd-e8055a1a7a41","year":2022},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:51.304602Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:a5983d29e0647daa3fa754eb8e90fb8d9615eca3b2a21899f8f9f346617c0720","observation_id":"8a1c3565-4d88-4ad6-905f-88c378919651","resolution":{"observed_at":"2026-08-07T05:33:55.918740Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:55.904430Z","title":"Explicit motion disentangling for efficient optical flow estimation,","venue":null,"work_id":"97724bfe-0362-4e7b-a002-cdcc08ee5b10","year":2023},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:51.375771Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:f93da8993466f1d8795d055e31189dae45b80691e4cf003c9e18c5a1b3ece14e","observation_id":"d78afe54-6ddb-4dc3-af08-7eea26a681c9","resolution":{"observed_at":"2026-08-07T05:33:55.908195Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:55.894859Z","title":"Craft: Cross-attentional flow transformer for robust optical flow,","venue":null,"work_id":"0d4c3409-6f88-4542-81bb-47dae4e95074","year":2022},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:51.500976Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:8a21c3551476ef30986af3ff4a71f35655a5bf5cb56a5d33e49efbfa3b2f458d","observation_id":"93d6432d-790d-4743-81c7-923eeb0d38fc","resolution":{"observed_at":"2026-08-07T05:33:55.898118Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:55.885461Z","title":"Recurrent partial kernel network for efficient optical flow estimation,","venue":null,"work_id":"0d3de378-3dfe-4d97-ae09-faf8f60577f0","year":2024},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:51.609453Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:7c7820864cf5d883c4d0585033e6e72b82c785c59e0e6adb9cd67da168469e4a","observation_id":"f3247eaf-ddbb-469c-81e9-5974be0dc649","resolution":{"observed_at":"2026-08-07T05:33:55.888763Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:55.875728Z","title":"Global matching with overlapping attention for optical flow estimation,","venue":null,"work_id":"44394dba-e056-414e-bbfd-dfc37cc2418c","year":2022},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:51.773168Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:b0e3fb692a0e3e25417a8a5d9458a3835723c47a359b2e536d5a84f0f891fd4a","observation_id":"14a1dfe0-7b07-40fd-b1a7-ac52b633c07b","resolution":{"observed_at":"2026-08-07T05:33:55.879069Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:55.865896Z","title":"Gmflow: Learning optical flow via global matching,","venue":null,"work_id":"61798563-d50b-4254-aaec-bc5a617b7e50","year":2022},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:51.859870Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:7fe6c2e78cd26c3dc11bb134fb0d4d7a1dec2e9955752f1c20223b1f8f237069","observation_id":"7e718602-5e92-48c2-bb5c-39c0ac2d6b87","resolution":{"observed_at":"2026-08-07T05:33:55.869031Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:55.856198Z","title":"Unifying flow, stereo and depth estimation,","venue":null,"work_id":"2f6e913f-56e8-47c7-9f9d-e2297ab6c002","year":2023},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:52.011763Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:2977f7cde25db44b3df126a0c72d1b130a5ea21473d2c8becc981896543a629a","observation_id":"80aa33e3-e402-4400-a858-582e2bbd1fd7","resolution":{"observed_at":"2026-08-07T05:33:55.859812Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:55.846050Z","title":"Youtube-vos: Sequence-to-sequence video object segmentation,","venue":null,"work_id":"d6357cfa-2c3c-4a6d-9fdd-779425d311be","year":2018},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:52.158052Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:cf39f7434455910a9b811b32dc08d7b0d02b1e17e3b451f779e68a31ff5a0146","observation_id":"5cfb6ed7-3a4d-4412-a99d-10442bed06c0","resolution":{"observed_at":"2026-08-07T05:33:55.849781Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:55.835532Z","title":"Tartanair: A dataset to push the limits of visual slam,","venue":null,"work_id":"6501ed02-19d3-405c-b4d9-d700a5235ec9","year":2020},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:52.271709Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:31482749948dd26d8286b2e06849e5a14c05f1fda576c116ec999d2e918d4cb3","observation_id":"57a3ddf2-c4e5-4caf-923e-8b356fbcdbbb","resolution":{"observed_at":"2026-08-07T05:33:55.838921Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:55.824595Z","title":"Unflow: Unsupervised learning of optical flow with a bidirectional census loss,","venue":null,"work_id":"c937c335-f6cf-4d51-96bf-b5cf3960e89b","year":2018},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:52.423433Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:06d84ff5fdabebee514f00faeab654ebb2359c3faaf0d8b1dff08b4bcbc25c4f","observation_id":"7916db84-4f05-4828-966d-fd93299553b7","resolution":{"observed_at":"2026-08-07T05:33:55.828190Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:55.813051Z","title":"Ddflow: Learning optical flow with unlabeled data distillation,","venue":null,"work_id":"fdac9f2d-8346-4e36-81b3-4031b06e2c48","year":2019},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:52.580153Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:104001c58c987184906bd6efac27d91ab0b349a024c122278eaf6706e7e4afc4","observation_id":"a65bd20f-cfa7-4637-bb12-45be9d3a30c8","resolution":{"observed_at":"2026-08-07T05:33:55.817482Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:55.802174Z","title":"Selflow: Self-supervised learning of optical flow,","venue":null,"work_id":"3d59ff85-0e30-4950-994a-0682124dde36","year":2019},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:52.644526Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:56fd5337b9254449ab19c8c61f90f7b40695da24aab685f7f873ac1cab83483c","observation_id":"c41cd526-c688-470e-8f07-f4455432f025","resolution":{"observed_at":"2026-08-07T05:33:55.805614Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:55.791002Z","title":"Unsupervised learning of op- tical flow with deep feature similarity,","venue":null,"work_id":"4b525a06-a81c-42d7-a3a1-32e5c5ab051b","year":2020},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:52.790929Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:102b91a504739888df489f6699577f1a5950ee3b93c97f3ac62a7647323c81d6","observation_id":"e8de33d6-29e3-4f86-8a2a-b7cd9900dff1","resolution":{"observed_at":"2026-08-07T05:33:55.794404Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:55.780963Z","title":"What matters in unsupervised optical flow,","venue":null,"work_id":"570e411a-195f-464b-8fa8-1a2d80dc283b","year":2020},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:52.884229Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:b0997f3da8a93fda9246031a99ee9e33aaef10f2108edea78eff695fd94d2d66","observation_id":"9bc0203f-2cf6-44cb-8e5d-d134c2d06a07","resolution":{"observed_at":"2026-08-07T05:33:55.784720Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:55.770468Z","title":"Upflow: Upsampling pyramid for unsupervised optical flow learning,","venue":null,"work_id":"4c6b5939-0e39-4105-9cc1-44388ee0df6c","year":2021},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:53.032639Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:1792cf16a816e82058e3e647b228cfe73a36f4b54d03550e7a45eac2538ec5d8","observation_id":"43438b09-0d84-4181-b304-6542a8be7408","resolution":{"observed_at":"2026-08-07T05:33:55.774589Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:55.759529Z","title":"Learning by analogy: Reliable supervision from transformations for unsupervised optical flow estimation,","venue":null,"work_id":"2b51e830-9092-445a-b23a-45499e101e68","year":2020},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:53.186619Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:81ac7b16eb0b2765f0f74d8cf6fda25060e195308a5ac18f9dc8e1c85bb41f84","observation_id":"b7fe14b4-f1ee-4a19-996e-e59fae5e8446","resolution":{"observed_at":"2026-08-07T05:33:55.763129Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:55.748291Z","title":"Semarflow: Injecting se- mantics into unsupervised optical flow estimation for autonomous driving,","venue":null,"work_id":"3a53b04a-d337-4950-ba82-df47de11e418","year":2023},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:53.263042Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:754805b31f41b8f3103bbd6fc07e535e2a143a3663546339a83fc6741f8a2969","observation_id":"4d863d27-1304-4962-9c36-df1924585023","resolution":{"observed_at":"2026-08-07T05:33:55.752252Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:55.737711Z","title":"Semi-supervised learning of optical flow by flow supervisor,","venue":null,"work_id":"06778536-e1cf-4740-bcca-9fb9430d4184","year":2022},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:53.339809Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:3d65c38149f6acba5e4b273da92af75c7ba384128568209979fb2a900e70c4d6","observation_id":"d73b4c22-cd0e-429f-9d14-4806871c5dab","resolution":{"observed_at":"2026-08-07T05:33:55.741471Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.02608","last_updated":"2024-05-04T08:27:12Z","snapshot_observed_at":"2026-08-18T01:51:13.472758Z","submitted_at":"2024-05-04T08:27:12Z","title":"UnSAMFlow: Unsupervised Optical Flow Guided by Segment Anything Model","version":1},"cited_work":{"arxiv_id":"2405.02608","doi":null,"metadata_source":"pith","pith_arxiv_id":"2405.02608","snapshot_observed_at":"2026-08-07T05:33:54.230236Z","title":"UnSAMFlow: Unsupervised Optical Flow Guided by Segment Anything Model","venue":"cs.CV","work_id":"105f6e6f-911d-493e-a41a-4d8983974aac","year":2024},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:53.387897Z"},"links":{"cited_paper":"/paper/2405.02608","citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:48e5728152b6ecab992f91aab83f3926b896b3cd76cbe0690d4002293fc19adf","observation_id":"bc1fffdb-3ef0-4f57-aa7e-1483af0adabb","resolution":{"observed_at":"2026-08-07T05:33:54.279064Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:55.726395Z","title":"Self-supervised autoflow,","venue":null,"work_id":"97d944d4-fc52-4f83-9e62-0ba64a1347c0","year":2023},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:53.454164Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:3e0ba4b30fc3e2dcab1b054250493979dde0da5f66c11d8790642c13490206d4","observation_id":"ccef2381-ce3c-47e7-ac70-5e3e5736d61d","resolution":{"observed_at":"2026-08-07T05:33:55.730340Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:55.715038Z","title":"Smurf: Self-teaching multi-frame unsupervised raft with full- image warping,","venue":null,"work_id":"e6cf12f0-444d-4ca9-a501-be513a10eff8","year":2021},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:53.563144Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:93f354ddeb473df937afba830e3c478ff20b68218eb18bc852fc248bc3c32744","observation_id":"27d4ba9b-2916-40c4-8215-299f3d53917e","resolution":{"observed_at":"2026-08-07T05:33:55.718729Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:55.702914Z","title":"Tap-vid: A benchmark for tracking any point in a video,","venue":null,"work_id":"d07fcfd7-cc68-4ca6-8e82-03d0389fe339","year":2022},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:53.646701Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:c847ee96c48841d30fac2ef72a023cec529b7f23626c98d76a37d1ca9b0940c6","observation_id":"7cce5367-0b02-478c-9477-5c90b46b2abc","resolution":{"observed_at":"2026-08-07T05:33:55.707503Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:55.630970Z","title":"Propainter: Improving propagation and transformer for video inpainting,","venue":null,"work_id":"ca9862ac-ea1e-4c97-afa2-5d5e714a1d82","year":2023},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:53.732240Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:db777f271a2f50f4dfaf03f963c46133c56023380cf0f6903d58d5b7dd76c840","observation_id":"19b664d8-f2f0-4bae-ab83-37d941a9a6a0","resolution":{"observed_at":"2026-08-07T05:33:55.681180Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:55.405597Z","title":"Tokencut: Segmenting objects in images and videos with self-supervised transformer and normalized cut,","venue":null,"work_id":"49729723-eb2d-418d-9892-827782d6f2aa","year":2023},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:53.798259Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:055b91d4be1dc722ff57782846993cd8feec60f83e4965322e4f9b27967723a4","observation_id":"3ca2286e-2d39-4646-9b27-358758b68c9c","resolution":{"observed_at":"2026-08-07T05:33:55.525897Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:55.169532Z","title":"Treating motion as option to reduce motion dependency in unsupervised video object segmentation,","venue":null,"work_id":"fcd28f7b-98a9-4d47-aa6c-4d73241612a2","year":2023},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:53.849145Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:4b009d61fed30642a54960cedee0e3fe83d7d7f771358264266e80247b00ebb3","observation_id":"9ca9e946-c566-432d-8ee9-7722cd8daad5","resolution":{"observed_at":"2026-08-07T05:33:55.281230Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:54.927739Z","title":"Dynamic view syn- thesis from dynamic monocular video,","venue":null,"work_id":"828c42fb-084b-44f0-b5f6-a428e90aa128","year":2021},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:53.919337Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:4dc486e1cc8d72471de04ee2532b82f8cb10aca323727d6607ec9524dd9d2b94","observation_id":"20e78951-057f-4431-8bbf-da9586d445bb","resolution":{"observed_at":"2026-08-07T05:33:55.024955Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:54.676831Z","title":"Neural scene flow fields for space-time view synthesis of dynamic scenes,","venue":null,"work_id":"31f510d2-5500-4bb2-b9d4-c74d668d6ec1","year":2021},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":94,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:53.983297Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:f4e5f7c02b2549c2446e4c613618be3b6a16d7e90b9db8cbc04344e435b6af77","observation_id":"7593c6e6-04ec-49aa-bf75-52a0299e5d92","resolution":{"observed_at":"2026-08-07T05:33:54.788835Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:54.509220Z","title":"FLATTEN: optical FLow-guided ATTENtion for consistent text-to-video editing,","venue":null,"work_id":"629ddc0e-bf8e-471d-98d6-bf4130bfe14a","year":2024},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":95,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:54.041501Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:2b10a4dac7101cb9808ed0ec44a95d39fafb9a8fb86e29ec3f9f56658357e9c7","observation_id":"c448eadf-921c-460f-a7a6-b2ba378f3ac0","resolution":{"observed_at":"2026-08-07T05:33:54.578993Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-07T05:33:54.333913Z","title":"Tune-a-video: One-shot tuning of image diffusion models for text-to-video generation,","venue":null,"work_id":"3809fb7c-f04d-4291-ae1b-fbe8a66776ad","year":2023},"citing_paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images","version":1},"reference_index":96,"source":"pdf_text","source_observed_at":"2026-08-07T05:33:54.116652Z"},"links":{"citing_paper":"/paper/2506.07740"},"observation_digest":"sha256:3747c27e4fd8e3857fce1f9df08917405bfc81368c0297e17ea76b9eac8a7fe6","observation_id":"b2b6f601-c0ef-4ae3-bec2-971060bcad6c","resolution":{"observed_at":"2026-08-07T05:33:54.429284Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2506.07740","last_updated":"2025-06-09T13:23:44Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-17T17:40:11.187271Z","submitted_at":"2025-06-09T13:23:44Z","title":"Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images"},"reference_resolution":{"displayed":94,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":19,"verified_exact":1,"verified_fuzzy":74},"total_outbound_references":94},"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":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"thesis":"As of 22 August 2026, this Paper Citation Record lists 94 of 94 outbound references and 2 inbound Pith citation observations for arXiv:2506.07740."}