{"as_of":"2026-08-10T17:49:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:7a5ce365913715edc498b702f9a6f6df79766110863f97d45a7f68309b7b60e2","coverage":[{"denominator":99,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":99,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T05:28:45.734335Z","state":"measured"},{"denominator":100,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":100,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-26T01:09:36.824562Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-04T15:59:56.790826Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"cited_work":{"arxiv_id":"2509.05297","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2509.05297","snapshot_observed_at":"2026-07-04T15:59:56.790826Z","title":"Flowseek: Optical flow made easier with depth foundation models and motion bases,","venue":null,"work_id":"a0e973b5-a846-4a45-8e6d-ee6f106af2e7","year":2025},"citing_paper":{"arxiv_id":"2606.24282","last_updated":"2026-06-23T08:03:58Z","snapshot_observed_at":"2026-08-07T15:45:36.634596Z","submitted_at":"2026-06-23T08:03:58Z","title":"UniRED: Unified RGB-D Video Frame Interpolation with Event Guidance","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-06-26T01:09:36.824562Z"},"links":{"cited_paper":"/paper/2509.05297","citing_paper":"/paper/2606.24282"},"observation_digest":"sha256:1cdd0322752f69f4f6140741e49b75da59b34ec6bc1a63a0c134d8fb998718c1","observation_id":"47ad1655-15ee-4ef7-bb32-5084d54d218b","resolution":{"observed_at":"2026-07-04T15:59:56.792684Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2509.05297/citation-record","integrity":"/paper/2509.05297/integrity","json":"/paper/2509.05297/citation-record.json","paper":"/paper/2509.05297"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T05:28:32.091064Z","title":"Learning optical flow from still images","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:32.091064Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:8030aeac342c473f7f8efda9558135809a3c90f6d0d25662f3baafbba100009d","observation_id":"967d0ca6-45cb-4c7a-9e19-1358fe15beb2","resolution":{"observed_at":"2026-08-05T05:28:32.091064Z","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":"2026-08-05T05:28:32.293441Z","title":"Stereo anywhere: Robust zero-shot deep stereo matching even where either stereo or mono fail","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:32.293441Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:d6d0f130e260aff601d5e14c7671580844303d540f248d78e58bb227db546640","observation_id":"e3b27845-89c9-4a5a-bb4c-defab15cf623","resolution":{"observed_at":"2026-08-05T05:28:32.293441Z","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":"2026-08-05T05:28:32.427003Z","title":"A framework for the robust estimation of optical flow","venue":null,"work_id":null,"year":1993},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:32.427003Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:96fa8e72c32fcfa45dbb48088aa78a996863233cb77ab8e6b28c788dd0ff88a2","observation_id":"b8b9fadb-8ff3-4bdc-88fe-0a7f7cf7a94c","resolution":{"observed_at":"2026-08-05T05:28:32.427003Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.02073","last_updated":"2025-04-21T12:09:08Z","snapshot_observed_at":"2026-08-02T06:32:26.688405Z","submitted_at":"2024-10-02T22:42:20Z","title":"Depth Pro: Sharp Monocular Metric Depth in Less Than a Second","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.02073","snapshot_observed_at":"2026-08-05T05:28:32.585592Z","title":"Depth pro: Sharp monocular metric depth in less than a second.arXiv preprint arXiv:2410.02073, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:32.585592Z"},"links":{"cited_paper":"/paper/2410.02073","citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:6725f837e719bb9714e535234f6a372afda66739a1edaa77d95e0a804bcaef43","observation_id":"986870ac-230c-41c8-a68b-76d9090ca019","resolution":{"observed_at":"2026-08-05T05:28:32.585592Z","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":"2026-08-05T05:28:32.793167Z","title":"Dimensions of motion: Monocular prediction through flow subspaces","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:32.793167Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:2d84053e879af2a5fc6c31b98edb74ba6d21dad9cc0f6a48b83cdcfe7588dcd2","observation_id":"646a0239-4663-4507-933b-4018f029cc02","resolution":{"observed_at":"2026-08-05T05:28:32.793167Z","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":"2026-08-05T05:28:32.894982Z","title":"High accuracy optical flow estimation based on a theory for warping","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:32.894982Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:e1b570b2fe835cd11af64fd9fee6bd4edec6241213afe9118368ebbb64827d68","observation_id":"07f0bcb9-ce2a-4471-bd71-b3079dfbc866","resolution":{"observed_at":"2026-08-05T05:28:32.894982Z","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":"2026-08-05T05:28:33.034263Z","title":"Large displacement optical flow","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:33.034263Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:9315f70e02a7169ff98fe3d171a3f61b4b8e8515b5b0a2645dcd54a5ca0daa95","observation_id":"8ebfb160-7b66-405f-9bb3-4c9292740105","resolution":{"observed_at":"2026-08-05T05:28:33.034263Z","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":"2026-08-05T05:28:33.141194Z","title":"A naturalistic open source movie for op- tical flow evaluation","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:33.141194Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:428220a0f447ba29ec7b2b0ae434fb2b4d0fccdd72ef42c5bb3ed36c8698d745","observation_id":"6c7f6192-0c69-42c3-8a5a-5eb575840aa8","resolution":{"observed_at":"2026-08-05T05:28:33.141194Z","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":"2026-08-05T05:28:33.228906Z","title":"Emerg- ing properties in self-supervised vision transformers","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:33.228906Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:1e2c7b0043d59131825800f8437429013677652dc6e62605b5773ad4828f30bd","observation_id":"75bf56fd-1084-4671-b10d-007b10cd93da","resolution":{"observed_at":"2026-08-05T05:28:33.228906Z","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":"2026-08-05T05:28:33.303107Z","title":"Full flow: Optical flow estimation by global optimization over regular grids","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:33.303107Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:9ebd4843868857846ed125e07d2749cb4275f7c79ff60854b81407f89375a906","observation_id":"2fb9a7b0-5b75-4009-9475-8118a2494b10","resolution":{"observed_at":"2026-08-05T05:28:33.303107Z","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":"2026-08-05T05:28:33.365450Z","title":"Monster: Marry monodepth to stereo unleashes power","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:33.365450Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:09d395ff4ca8790372497757bcb2b213b4771f040c0c58ddfcd4ef2e49de9733","observation_id":"c8115d5e-5389-40a0-88a7-49b7ec9a2c6b","resolution":{"observed_at":"2026-08-05T05:28:33.365450Z","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":"2026-08-05T05:28:33.437828Z","title":"Flowtrack: Revisiting optical flow for long- range dense tracking","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:33.437828Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:f9b1082c3b8b831da49176fc97f4331a90e3340f1c2dc4be0c4c40b265766877","observation_id":"fda7abb2-9e5b-4ab3-b3e1-e3987f2f47d9","resolution":{"observed_at":"2026-08-05T05:28:33.437828Z","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":"2026-08-05T05:28:33.523585Z","title":"Explicit motion disen- tangling for efficient optical flow estimation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:33.523585Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:b4e3e4dd31a012b01e1440ca1e54c83046319dfc268fc511ea8d7b2e7273995c","observation_id":"ab303125-9002-4b6d-861f-be7965ebf05b","resolution":{"observed_at":"2026-08-05T05:28:33.523585Z","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":"2026-08-05T05:28:33.580129Z","title":"Rethinking opti- cal flow from geometric matching consistent perspective","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:33.580129Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:3ff06fff3ffbc1b330370aea354577e9eb06a6df34bc2ec986aaca77f0f2b2d9","observation_id":"bbd1bf13-33b3-4bdc-87d8-75e604b4e381","resolution":{"observed_at":"2026-08-05T05:28:33.580129Z","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":"2026-08-05T05:28:33.659933Z","title":"Flownet: Learning optical flow with convolutional networks","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:33.659933Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:fa67f3d4d1934a57e7549ad5e795ab57f197d355aa9a1cfa4bb873cae4b954c9","observation_id":"51157368-c5ce-40b3-b157-183e55c8941b","resolution":{"observed_at":"2026-08-05T05:28:33.659933Z","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":"2026-08-05T05:28:33.757792Z","title":"Fast dynamic radiance fields with time-aware neural voxels","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:33.757792Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:dbeed381df4dbb2bbacb64d15b62c9bb367816330857111e235171251f923240","observation_id":"5e005a9b-5218-487e-9967-892f1e5b4f69","resolution":{"observed_at":"2026-08-05T05:28:33.757792Z","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":"2026-08-05T05:28:33.840863Z","title":"Vision meets robotics: The kitti dataset.The Inter- national Journal of Robotics Research, 32(11):1231–1237,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:33.840863Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:c8a2a8ec1d8ba0d3a5f33d44d0881f4d6a93b49e296bb2c5dbab7bf43d948e95","observation_id":"d34cabd3-13e9-415a-bb7f-b7d3dd1685c9","resolution":{"observed_at":"2026-08-05T05:28:33.840863Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.12948","last_updated":"2026-01-04T03:57:36Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-01-22T15:19:35Z","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.12948","snapshot_observed_at":"2026-08-05T05:28:33.932607Z","title":"Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning.arXiv preprint arXiv:2501.12948, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:33.932607Z"},"links":{"cited_paper":"/paper/2501.12948","citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:8660db0b99c0dc2c5f24af44f3cba584f49e3d668f88b0ffcde4d9d594665c7c","observation_id":"6eb92621-8901-4df6-8890-fceeefe817d4","resolution":{"observed_at":"2026-08-05T05:28:33.932607Z","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":"2026-08-05T05:28:34.075944Z","title":"Realflow: Em- based realistic optical flow dataset generation from videos","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:34.075944Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:935edc1ed65c941570d7bcbd6eda86ec841909a4ce1ae711f76915ae14239ada","observation_id":"4b21276e-df1d-400a-85be-86f1205ea924","resolution":{"observed_at":"2026-08-05T05:28:34.075944Z","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":"2026-08-05T05:28:34.156017Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:34.156017Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:9854c4f2d326654d27b9364372dd553bb683d941d5d268b4fc5e34797dc7d386","observation_id":"e9fac067-65df-42f4-8781-d1063e0bd751","resolution":{"observed_at":"2026-08-05T05:28:34.156017Z","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":"2026-08-05T05:28:34.271250Z","title":"Subspace methods for recovering rigid motion i: Algorithm and implementation","venue":null,"work_id":null,"year":1992},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:34.271250Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:33a0006d3cd06b5fb4187f653a92cfdaffbca58ecada4df636b0cd26a633ac28","observation_id":"88c9f056-8270-4225-92ff-dd9062387277","resolution":{"observed_at":"2026-08-05T05:28:34.271250Z","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":"2026-08-05T05:28:50.144349Z","title":"Determining op- tical flow.Artificial intelligence, 17(1-3):185–203, 1981","venue":null,"work_id":"0d5bb7eb-905c-4f58-b105-0f84d0679960","year":1981},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:34.381660Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:ec7169adc3e7207458e374dbaea1d063f4398048fe2f0d445f2ff0d92bc2a201","observation_id":"3f0bb030-b94e-4068-bd6a-f125cbf15c30","resolution":{"observed_at":"2026-08-05T05:28:50.148782Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:28:50.129778Z","title":"Efficient coarse-to- fine patchmatch for large displacement optical flow","venue":null,"work_id":"4bb3d06e-2036-4881-9f53-abd2ba325700","year":2016},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:34.419282Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:82f4bfdfa360095bee1bcec7e2d6555ce923f20cf3c73c23d47ffda638e5829b","observation_id":"6799c32d-98fa-44cb-bb46-3a145e5cd267","resolution":{"observed_at":"2026-08-05T05:28:50.134235Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:28:50.114775Z","title":"Robust interpola- tion of correspondences for large displacement optical flow","venue":null,"work_id":"16ddf2c9-35c6-407a-af5a-b1d31f08be2d","year":2017},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:34.494545Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:e4d6562047315f253b98fdc09bc5a4850bcd550ab4eee1a917686b515049d690","observation_id":"93aff474-f4e7-420b-af35-851497cc4ef7","resolution":{"observed_at":"2026-08-05T05:28:50.119741Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2011.06294","last_updated":"2022-07-13T06:51:21Z","snapshot_observed_at":"2026-07-06T10:13:57.236233Z","submitted_at":"2020-11-12T10:12:06Z","title":"Real-Time Intermediate Flow Estimation for Video Frame Interpolation","version":12},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2011.06294","snapshot_observed_at":"2026-08-05T05:28:34.662508Z","title":"Rife: Real-time intermediate flow estimation for video frame interpolation.arXiv preprint arXiv:2011.06294, 2020","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:34.662508Z"},"links":{"cited_paper":"/paper/2011.06294","citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:10e1d6c5776ff7b267328a00b69c65dbf07ac9e6de11f63d350c82317d8e1f59","observation_id":"3efc8377-a38f-4e7b-a2de-8332c31617cc","resolution":{"observed_at":"2026-08-05T05:28:34.662508Z","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":"2026-08-05T05:28:50.098131Z","title":"Flowformer: A transformer architecture for optical flow","venue":null,"work_id":"dcd2378d-1b9c-4514-b04d-8030f22bea0d","year":2022},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:34.837676Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:f71e25adb06ba67da839f8b842f4d7a05391c0e61a9909b7a29b70b6e8fb9438","observation_id":"184194de-2e74-4e9f-9b9d-6144bf7b00c9","resolution":{"observed_at":"2026-08-05T05:28:50.103601Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:28:50.082358Z","title":"LiteFlowNet3: Resolv- ing Correspondence Ambiguity for More Accurate Optical Flow Estimation","venue":null,"work_id":"a9d04b25-b640-4841-aa05-510a31124a69","year":2020},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:34.994265Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:82f5758d598906a6de0bc66150bacd3c275751f3fd0672f66a29d68b044f5a6d","observation_id":"808c28b6-bffe-44d7-8435-0c63b1e9daa4","resolution":{"observed_at":"2026-08-05T05:28:50.086877Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:28:50.067511Z","title":"Lite- FlowNet: A Lightweight Convolutional Neural Network for Optical Flow Estimation","venue":null,"work_id":"de69b36e-ee99-43b0-a60c-1dd3e4ae6b51","year":2018},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:35.153981Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:56969ce83724d81650fbbb433812f42aeab07c6498366427ea3fc26475898174","observation_id":"07fb4930-a909-4949-9c2d-9a58e64db9b9","resolution":{"observed_at":"2026-08-05T05:28:50.071890Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:28:50.053610Z","title":"A lightweight optical flow cnn - revisiting data fidelity and reg- ularization","venue":null,"work_id":"eced847c-b24d-43d2-af2f-d2f153ce4052","year":2020},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:35.279140Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:a85efacfe3ac1bc8a56ff767cb71b1a84a354b0b479eab01f5acd796b11c8d65","observation_id":"9a005186-90ec-4aca-b216-47aa0637856b","resolution":{"observed_at":"2026-08-05T05:28:50.057931Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:28:50.038932Z","title":null,"venue":null,"work_id":"ea602640-883b-4693-a41e-2132843f8f94","year":2017},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:35.414403Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:e0e466282b60f741fc9e9f7fc305402e1435d71438bb00a18f461a3e9bab6714","observation_id":"65c4122b-3475-4691-be3d-d84aef44dd5e","resolution":{"observed_at":"2026-08-05T05:28:50.043903Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:28:50.023367Z","title":"Brostow, and Jamie Watson","venue":null,"work_id":"650b0b8c-25d1-4a60-a178-631a244bbf3b","year":2025},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:35.568145Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:9bef7ea7e391614e69a51bedd02a799fcf8c99beeed1721f5411dc1ab30f8a7b","observation_id":"0406e4ab-cb4b-4383-a548-4bc8bc763f4c","resolution":{"observed_at":"2026-08-05T05:28:50.028369Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:28:50.006904Z","title":"Ccmr: High resolution optical flow estimation via coarse-to-fine context-guided motion reasoning","venue":null,"work_id":"8fa6a686-b0de-43aa-a3c0-c3d6e9bc085e","year":2024},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:35.708869Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:7ffdbbb97ad3e69728228c2bfcacb7118066c9d8831a23fe9366735ca4b1efd7","observation_id":"a60219a4-d634-4e69-a6dc-ad8930cc0c93","resolution":{"observed_at":"2026-08-05T05:28:50.012544Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:28:49.992321Z","title":"Ms-raft+: high resolution multi-scale raft.International Journal of Computer Vision, 132(5): 1835–1856, 2024","venue":null,"work_id":"ca284055-7984-4b93-8b0c-df3b2c8b6649","year":2024},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:35.836322Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:b39d45ad88415dace7808459f0852239760b9fcc97dd1ae741f435039dec2ede","observation_id":"d0ecf0f8-d417-47a9-b435-29fcfd3de05b","resolution":{"observed_at":"2026-08-05T05:28:49.997000Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:28:49.977282Z","title":"Distractflow: Improving optical flow estimation via real- istic distractions and pseudo-labeling","venue":null,"work_id":"774db567-66ab-4395-a691-33d83af2a759","year":2023},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:36.056821Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:310c86b641fe0e5e1fb6cb9948824c4546f16a13ba2b882aca978581a20dfb71","observation_id":"9836c31a-d0f7-41d4-a555-ccf895fe8843","resolution":{"observed_at":"2026-08-05T05:28:49.982539Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:28:49.963230Z","title":"Defom-stereo: Depth foundation model based stereo matching","venue":null,"work_id":"32c0fe93-a8ab-4c09-93d7-416c3458c83c","year":2025},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:36.207161Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:13d3af4430f2201e549a75d09b2963417d5dd7610837bb26ea7fc31e6f7bb8bb","observation_id":"2d92c609-2e41-4362-8922-0e56f7ced16a","resolution":{"observed_at":"2026-08-05T05:28:49.967383Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:28:49.948130Z","title":"Learning to estimate hidden motions with global motion aggregation","venue":null,"work_id":"96ccc1cb-d239-468d-b88f-30877456e216","year":2021},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:36.350402Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:6154c51b7c341bca55e4ef1de7ba55da360c622d5be2161d0f6c64e7db58c36b","observation_id":"53bba4de-9415-4b34-aafb-f7afa0e04c58","resolution":{"observed_at":"2026-08-05T05:28:49.952977Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:28:49.934005Z","title":"Effiscene: Efficient per-pixel rigidity inference for unsupervised joint learning of optical flow, depth, camera pose and motion seg- mentation","venue":null,"work_id":"3b8a9d88-c7a2-4476-9245-d5862165c241","year":2021},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:36.495965Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:7753ffc799e5a121f12f86cb06653f613dc00e5af5d928de9d9061cbbf6072c1","observation_id":"90af267e-a1d0-4bf9-a244-d331a5a1f219","resolution":{"observed_at":"2026-08-05T05:28:49.938134Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:28:49.918344Z","title":"What mat- ters in unsupervised optical flow","venue":null,"work_id":"90693584-1d0a-483b-8f13-b7c9e0f9a5bc","year":2020},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:36.650461Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:0a5c25cc3267c018bcd4511dcfb64f438415e01c3ad7e3c8d70ec39134fab141","observation_id":"8bae388e-ea0b-4f13-8ea3-2cb78ea179ae","resolution":{"observed_at":"2026-08-05T05:28:49.922625Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:28:49.902414Z","title":"Repurpos- ing diffusion-based image generators for monocular depth estimation","venue":null,"work_id":"1e07c1c2-c064-4037-88e5-f592f82e2b05","year":2024},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:36.857146Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:fbee309660e47dd6b3384b555c33b55a56cd112f9e60dbd40d7a00f569f08626","observation_id":"b3df536c-dd0c-4b02-803c-8c6127c7d49e","resolution":{"observed_at":"2026-08-05T05:28:49.907216Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:28:49.887666Z","title":"The hci benchmark suite: Stereo and flow ground truth with uncertainties for urban autonomous driv- ing","venue":null,"work_id":"0b85f17a-5cef-4234-bc3a-94860ce760cf","year":null},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:37.025099Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:fd2732be0460536f635cb662e773f66aa21772292d398c91f3365d3560e1e62c","observation_id":"4571ea0e-e960-4233-a4f8-f443de01c346","resolution":{"observed_at":"2026-08-05T05:28:49.892037Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:28:49.871999Z","title":"Locally affine sparse-to-dense matching for motion and occlusion estimation","venue":null,"work_id":"1f5c717c-7944-4832-a8c6-64ef05575b36","year":null},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:37.183312Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:d04f96a64ab57d49de9595e773baf6d24a492174aa20f81f377380d3c42a6458","observation_id":"eb904980-6895-41a4-8c66-d6f8dad65475","resolution":{"observed_at":"2026-08-05T05:28:49.876802Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.00632","last_updated":"2024-03-22T15:38:53Z","snapshot_observed_at":"2026-08-10T05:54:54.449070Z","submitted_at":"2023-10-01T10:06:01Z","title":"Win-Win: Training High-Resolution Vision Transformers from Two Windows","version":2},"cited_work":{"arxiv_id":"2310.00632","doi":null,"metadata_source":"pith","pith_arxiv_id":"2310.00632","snapshot_observed_at":"2026-08-05T05:28:46.385048Z","title":"Win-Win: Training High-Resolution Vision Transformers from Two Windows","venue":"cs.CV","work_id":"c2587856-0fa4-46c4-9206-88dbe6373e4e","year":2023},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:37.369257Z"},"links":{"cited_paper":"/paper/2310.00632","citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:9ea24e558c6eb4c83adcc7931d09433b7060a0abb57d87a0d9877f324f4454a5","observation_id":"a99281de-d4ba-453c-864c-1e6df3ad8050","resolution":{"observed_at":"2026-08-05T05:28:46.484827Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:28:49.856408Z","title":"Fast guided global interpolation for depth and motion","venue":null,"work_id":"886a29ed-1d94-4748-9f25-caaa4466cdbd","year":2016},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:37.507165Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:19471234ccdd25875c26d9429045172923a8d93e12213e8c1f44578e4eb89d7a","observation_id":"247c2729-0bf9-452e-a346-9503ac11035e","resolution":{"observed_at":"2026-08-05T05:28:49.861222Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:28:49.842014Z","title":"Megadepth: Learning single- view depth prediction from internet photos","venue":null,"work_id":"d026741b-523a-47d0-a4dd-676afe1abb22","year":2041},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:37.638672Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:cf9e8965aa0e3cb596d0b3d273c8a0c9dc4831244786781af7834b5e7eaf5278","observation_id":"4cbcaa54-03e9-4b75-8090-1d9b458c1a7c","resolution":{"observed_at":"2026-08-05T05:28:49.846502Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T05:28:46.105680Z","title":"Playing to vision foundation model’s strengths in stereo match- ing.IEEE Transactions on Intelligent Vehicles, 2024","venue":null,"work_id":"0a9f7320-7f2d-46d7-9879-777f067c1445","year":2024},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:37.877848Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:259330c67a1c9a4b9cb90f15760c11a54572f4df307f0bc1777f6573d9c4fa78","observation_id":"b26b5acb-4b77-43a2-a87c-01b8985ff701","resolution":{"observed_at":"2026-08-05T05:28:46.237518Z","resolver_source":"arxiv_id_nonexistent","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:28:37.997573Z","title":"Learning by analogy: Reliable supervi- sion from transformations for unsupervised optical flow es- timation","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:37.997573Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:438a89e08d006fcd7befd357e53b7b6ab754dc84d5dcf4c33f539cc356ac0e6b","observation_id":"2f202b15-b1d7-4766-9fa8-d47d5d67cbb6","resolution":{"observed_at":"2026-08-05T05:28:37.997573Z","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":"2026-08-05T05:28:49.815886Z","title":"Flow2stereo: Effective self-supervised learning of optical flow and stereo matching","venue":null,"work_id":"5544ee84-0671-4bdf-ac0c-8ddd197a3d23","year":2020},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:38.198505Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:a208d4ba433b83b049cc6397e437e2a85718f60b90cefec92abf55db4bc3c43d","observation_id":"aebe42f4-3f0a-4ad5-9fc8-23724b350471","resolution":{"observed_at":"2026-08-05T05:28:49.820624Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:28:49.801906Z","title":"Unsupervised global and local ho- mography estimation with motion basis learning.IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(6):7885–7899, 2022","venue":null,"work_id":"a1ce3de7-49e7-4337-b397-07e53779f115","year":2022},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:38.377338Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:dcd190eada1137e7253efacd576f2ac8988e464502fac2bba0957ceb5ff43e03","observation_id":"40869fb2-428a-49a7-b524-2a5e694b34e1","resolution":{"observed_at":"2026-08-05T05:28:49.806296Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:28:49.787221Z","title":"Video frame inter- polation via optical flow estimation with image inpainting","venue":null,"work_id":"39fe65e3-06af-4fcd-8f96-ecbe7747def5","year":2087},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:38.578445Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:4aacc24e33ae5c4c63a230ef2139285d858df2813c5c94eb6b2ce1dcd684d536","observation_id":"47e29e3a-7162-4a6f-a531-0d00c1d11f4c","resolution":{"observed_at":"2026-08-05T05:28:49.791452Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:28:49.773497Z","title":"Transflow: Trans- former as flow learner","venue":null,"work_id":"3e4aadc9-7c69-4c5c-9644-3f5277773796","year":2023},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:38.720080Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:b4898b93e6a2c840b463651b3d846b247d7b19cdb4b425b7ef2dbfd1a8edf618","observation_id":"d459ee66-82c1-471e-822d-d4c84ed8f002","resolution":{"observed_at":"2026-08-05T05:28:49.777440Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:28:49.759106Z","title":"Learning optical flow with kernel patch attention","venue":null,"work_id":"d22b357d-a90e-4542-8f43-35cc6101ae66","year":2022},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:38.871440Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:302850693121cf3a5f75d42e61f38a3839a09899d35c4bbcf2d9aefcf33e5cf6","observation_id":"9535b5ca-b1d3-400a-bb8c-631688d36415","resolution":{"observed_at":"2026-08-05T05:28:49.763770Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:28:49.742505Z","title":"A large dataset to train convolutional networks for disparity, optical flow, and scene flow estimation","venue":null,"work_id":"6a0eadf7-f50d-40b4-8d3d-dc928a7775c8","year":2016},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:38.958210Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:ab2e4e9b6bf77e832ff14a477b3eabc2652d7e215ddd7f6c3c17854dd7e554d5","observation_id":"d6a3be95-86a5-483c-8c5b-e7e153949ee6","resolution":{"observed_at":"2026-08-05T05:28:49.747133Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:28:49.728075Z","title":"Spring: A high-resolution high- detail dataset and benchmark for scene flow, optical flow and stereo","venue":null,"work_id":"95917187-6854-4f04-86f3-c21ecfb33aec","year":2023},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:39.098956Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:d74c9c3cff65e2c65e1900793fc02bb71d1d7ddaf24cc79520094c32c5e8b1b9","observation_id":"3b088960-94fa-4daa-b396-926590b2df4c","resolution":{"observed_at":"2026-08-05T05:28:49.732320Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:28:49.713497Z","title":"Object scene flow for au- tonomous vehicles","venue":null,"work_id":"1923c9ff-4a00-4b24-bc5e-4bf7d3063dea","year":2015},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:39.304246Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:4ff4e1f6f1016fc71a372d3c938def8bb81c8c27569c495b1d7ecdba55dfbb8a","observation_id":"3690aadb-304e-45d7-8392-ccebc9d39c4a","resolution":{"observed_at":"2026-08-05T05:28:49.717712Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:28:49.699183Z","title":"Recurrent partial kernel network for efficient optical flow estimation","venue":null,"work_id":"515e7a7a-88d8-4fc6-ae19-5e4282fe0b11","year":2024},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:39.425507Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:c7d13cf76815d2555c4b1477c79afd2b7f261f444c0da49ad2ceebfabdd507ec","observation_id":"e60c5b8d-d48c-4000-adbd-8107e1de6561","resolution":{"observed_at":"2026-08-05T05:28:49.703303Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:28:49.685476Z","title":"Hello GPT-4o, 2024","venue":null,"work_id":"ebd14439-c841-4b33-84a2-d6617530c7b2","year":2024},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:39.586529Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:d15e580d99def3b4d0d16571c20fa803ab70f7fdabc4d7218fbf79f8423e5e1c","observation_id":"099b6375-3389-4d82-a26d-ad0970e287f5","resolution":{"observed_at":"2026-08-05T05:28:49.689639Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:28:39.724233Z","title":"Learning transferable visual models from natural language supervi- sion","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:39.724233Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:32ba007cb16e0f885266c1da225bb0c134623256957e14c87995a640042ee2c9","observation_id":"86bd7cf2-1663-4c32-9e6d-7c4806271708","resolution":{"observed_at":"2026-08-05T05:28:39.724233Z","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":"2026-08-05T05:28:49.659878Z","title":null,"venue":null,"work_id":"de383697-e7eb-4b3e-af67-9bab00193d2d","year":2020},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:39.876094Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:3a130a4e012471e9d1efa6ae28258502aeacd27cce3a844d87ffead8423855e0","observation_id":"71ac322c-154f-4cd8-82c4-3cc45d8b6dd5","resolution":{"observed_at":"2026-08-05T05:28:49.664096Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:28:49.645553Z","title":"Vi- sion transformers for dense prediction.ArXiv preprint, 2021","venue":null,"work_id":"8c964f1f-53d5-4d7b-93df-aa0edbd28f02","year":2021},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:40.016898Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:36df2e4eccf25ac299df44107f7fa545376bdce295ab003fdb9858922bbf0298","observation_id":"ecc3a63d-ddb3-4be9-b6fa-cca389e97a33","resolution":{"observed_at":"2026-08-05T05:28:49.650209Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:28:49.630576Z","title":"Optical flow estima- tion using a spatial pyramid network","venue":null,"work_id":"86a445dd-162d-40d6-94ce-4c4123bb7901","year":2017},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:40.228407Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:7b5d76a2de17f32764e287b457f4b6a5d1ec9f6cb4c81d83e5efe290f57acbc3","observation_id":"17ada299-275f-41fb-9b4d-a9c66eebff03","resolution":{"observed_at":"2026-08-05T05:28:49.635758Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:28:49.615788Z","title":"Epicflow: Edge-preserving interpolation of correspondences for optical flow","venue":null,"work_id":"47ce187a-6a80-4917-b9d8-68b9a1d00897","year":2015},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:40.432539Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:d0bd5e1502f5bf76dfb6b64a6d0d1eeba53bb7ef499dfe0ec764cdfed9c58ffd","observation_id":"56412419-4ab8-4f63-9939-253ba6f5cbd4","resolution":{"observed_at":"2026-08-05T05:28:49.619991Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:28:49.600906Z","title":"Playing for benchmarks","venue":null,"work_id":"407d4e66-4061-44e8-9ec5-c0351559e0f3","year":null},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:40.607356Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:ffd9dd9a19f6896f92da40441b7ce5dfb7beddacf83cc16452a2f1cc9db5753c","observation_id":"5b498576-75e9-4433-b8f8-7b71866520b8","resolution":{"observed_at":"2026-08-05T05:28:49.605715Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:28:40.762656Z","title":"High-resolution image synthesis with latent diffusion models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:40.762656Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:e6854d1964fe7ebf01bba80d5bb43a46eb3918e62813dc2845632287f7433297","observation_id":"c604d3d1-1194-4672-b5dd-2a5b42f5821b","resolution":{"observed_at":"2026-08-05T05:28:40.762656Z","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":"2026-08-05T05:28:49.573575Z","title":"Multi-object discov- ery by low-dimensional object motion","venue":null,"work_id":"b455c350-ed4a-41ad-892c-eba27dd5ab79","year":2023},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:40.875030Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:f682eb1fbce5385d6333298cda4ae65376d64eaf01d2aa480dfd4942b83907cf","observation_id":"a7d0b5a0-6e10-4f13-8298-446f9475a59b","resolution":{"observed_at":"2026-08-05T05:28:49.578253Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:28:49.557861Z","title":"The surprising effectiveness of diffusion models for optical flow and monocular depth estimation.Advances in Neural Information Processing Systems, 36, 2023","venue":null,"work_id":"57d81598-2ac1-4166-a5ff-2a7884f1ed0c","year":2023},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:41.057603Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:3a4358cc800c579eeaf3a6daaf7910dd55daf433f1863e111ac1b5451920115e","observation_id":"c0604be7-725b-462f-9b49-f5066dcbb822","resolution":{"observed_at":"2026-08-05T05:28:49.562478Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:28:49.541890Z","title":"Videoflow: Exploiting temporal cues for multi-frame optical flow estimation","venue":null,"work_id":"c050b856-5c54-40ae-9182-f5c209f87686","year":2023},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:41.205567Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:26c5c650247c61c5084c97ebd3298d78f6da24b8347ea779c0679944cb0ee2c0","observation_id":"17e0d0d5-4fc7-401c-9d28-7223e2ee88b6","resolution":{"observed_at":"2026-08-05T05:28:49.546614Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:28:49.526025Z","title":"Flowformer++: Masked cost volume autoen- coding for pretraining optical flow estimation","venue":null,"work_id":"628abe0e-0105-422b-86f4-30ce6889d43a","year":2023},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:41.402045Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:dea6471491b016b0f50312dc21d287ab82499d604212b58b1a5e19ad13698bc9","observation_id":"c7bc95b5-c7f5-4ee0-b18b-fd6bf9525c62","resolution":{"observed_at":"2026-08-05T05:28:49.531329Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:28:49.509580Z","title":"Craft: Cross- attentional flow transformer for robust optical flow","venue":null,"work_id":"850c1bc0-0f06-4f54-8160-8d2119affbd3","year":2022},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:41.564101Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:f469e24e9eb914276440634bf7bb629a53d0f7d2193c15a67af449123ffaa4ba","observation_id":"ca2fc311-07f5-417b-97f4-96b481c5d039","resolution":{"observed_at":"2026-08-05T05:28:49.514937Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:28:49.493710Z","title":"Secrets of optical flow estimation and their principles","venue":null,"work_id":"852b9bbc-fa0b-4dc5-8170-12a83558c1d4","year":2010},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:41.782036Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:97ad3add269413a35185fdb42d8586ff3edfe8b5245de9b9720b0f785ee9dc9e","observation_id":"50473326-5b8f-47fe-ab72-32a8bc79e79e","resolution":{"observed_at":"2026-08-05T05:28:49.498852Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:28:41.937568Z","title":"Pwc-net: Cnns for optical flow using pyramid, warping, and cost volume","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:41.937568Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:ab40f32b28cc458e598e498f48c4b83f4d489fabd691ec08b211125c4cb75193","observation_id":"40e9eda7-4901-434e-9c07-f1154a1875a6","resolution":{"observed_at":"2026-08-05T05:28:41.937568Z","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":"2026-08-05T05:28:49.466291Z","title":"Models matter, so does training: An empirical study of cnns for optical flow estimation.IEEE transactions on pattern analysis and machine intelligence, 42(6):1408–1423, 2019","venue":null,"work_id":"c2d65100-47d6-41c8-90d5-b5cb14a9edd2","year":2019},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:42.147389Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:18e5acc8cc0c7a85393c3da582320a18ab9fa3eeee31d93ac5698845afc156cd","observation_id":"d628ed86-e348-4a2d-b5ba-1d50df92abe8","resolution":{"observed_at":"2026-08-05T05:28:49.470891Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:28:49.451449Z","title":"Autoflow: Learning a better training set for optical flow","venue":null,"work_id":"8574e392-91c9-4dc6-ad6a-955e4d3bfee3","year":2021},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:42.336607Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:001f9b858fbcd2c780bd4873d6fe8eb5a1e29f9bdd7326a586d3adc94cfe5caa","observation_id":"cfdf8987-db38-4ba7-afc9-e0d89739f137","resolution":{"observed_at":"2026-08-05T05:28:49.456147Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:28:49.437735Z","title":"Disentan- 11 gling architecture and training for optical flow","venue":null,"work_id":"0264dac5-29cb-4f37-8b1b-f97b0571c49d","year":null},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:42.514612Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:790c069bd23865d2b4879c556002320390d125fc0445b83f707c82f969252ad4","observation_id":"bc89be36-e94f-41da-bcc1-25fe9f245158","resolution":{"observed_at":"2026-08-05T05:28:49.441882Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:28:49.421727Z","title":"Optical flow guided feature: A fast and robust motion representation for video action recognition","venue":null,"work_id":"5aeea163-15ab-4b82-807d-1527e0e05194","year":2018},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:42.625516Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:ac3fffcda6f04b6b79c7a70a931e656292c06ff5d0ffb9935df6bd2e70285e71","observation_id":"e71d7011-4cec-4fda-9508-d2142e3a8b8c","resolution":{"observed_at":"2026-08-05T05:28:49.426687Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:28:49.406478Z","title":"Skflow: Learning optical flow with super kernels","venue":null,"work_id":"8c9777cd-fca6-446c-ab0d-41bf2a28849f","year":2022},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:42.796687Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:3735def85960db3b0e1b1abb5db03b07289ae40569b6e7ef92d1d3d9be6386b7","observation_id":"42f77fc3-6f6b-4f72-9a99-69a0edaaa390","resolution":{"observed_at":"2026-08-05T05:28:49.411374Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:28:42.922894Z","title":"Raft: Recurrent all-pairs field transforms for optical flow","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:42.922894Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:690108fb46cf37476c8c4972377c3f4cd6028c640aa2d01f6d2e9703ecb5f101","observation_id":"a31c7035-8df3-4f63-8592-cc7b4bffccfb","resolution":{"observed_at":"2026-08-05T05:28:42.922894Z","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":"2026-08-05T05:28:49.377214Z","title":"Displacement-invariant matching cost learning for accurate optical flow estimation.Advances in Neural Information Processing Systems, 33, 2020","venue":null,"work_id":"005562de-8b76-40b2-9701-1ed9bbca0e56","year":2020},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:43.041023Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:cf493dd9c1e4c5c97456845ac0f39bfa52e2a5b011ffcf17c91c704ddf4d8749","observation_id":"ab4e1769-1483-4f9e-83d4-4408656b6e40","resolution":{"observed_at":"2026-08-05T05:28:49.382750Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:28:49.361212Z","title":"Tracking everything everywhere all at once","venue":null,"work_id":"91f5448b-83d2-4df8-a643-8d946ec1d419","year":2023},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:43.158549Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:e649970887c80ddd394f340e1397745af414854ab47ed16ef36aaf74f0fc8af4","observation_id":"9f8e30df-1463-4fcb-b9aa-3f37602e7be2","resolution":{"observed_at":"2026-08-05T05:28:49.366180Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:28:43.276766Z","title":"Dust3r: Geometric 3d vi- sion made easy","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:43.276766Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:e49c263888d6ea9005d215b71959950b2ed52fdd824aeda4a9dee3cfef3939c0","observation_id":"3ac8a261-3bfd-4f63-b1e2-1f650cefd238","resolution":{"observed_at":"2026-08-05T05:28:43.276766Z","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":"2026-08-05T05:28:49.335236Z","title":"Tartanair: A dataset to push the limits of visual slam","venue":null,"work_id":"3579da20-d6c8-4a02-b9f4-a4c442154286","year":2020},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:43.407262Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:242aae9a3a9ee4ccc934fce3925e927a81a4b86e52390b3359c1de8055381a67","observation_id":"975aaac4-d642-4bf3-9ee2-9ee362052b9f","resolution":{"observed_at":"2026-08-05T05:28:49.340153Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:28:49.318286Z","title":"Sea-raft: Simple, efficient, accurate raft for optical flow","venue":null,"work_id":"1f611722-4f23-40c8-8e7b-c33de60ae181","year":2024},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:43.525221Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:2da723a97d8e63244840d6277a0e5538152e93ad131142057a9670b742c8b251","observation_id":"ecb3c14a-5b42-4ea6-89ba-39352907e0fd","resolution":{"observed_at":"2026-08-05T05:28:49.324095Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:28:49.300767Z","title":"Foundationpose: Unified 6d pose estimation and tracking of novel objects","venue":null,"work_id":"d9cc98c5-3228-4d43-b6f8-1fa5b4d2d3b4","year":2024},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:43.645439Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:63a73f92bfeb96361564ed0ca678c7941c1adfe76ea77ddfeaf1302bbfd560d7","observation_id":"23112d01-df05-418f-812f-932d2180964b","resolution":{"observed_at":"2026-08-05T05:28:49.305437Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:28:49.285814Z","title":"Foundationstereo: Zero- shot stereo matching.arXiv, 2025","venue":null,"work_id":"c84a03b2-ef49-4e5e-b0d4-736f0f1f6496","year":2025},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:43.759949Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:d015bd7e3b1e14712dc9c22fd34bb63a682f09ed1c2341015a99b06166a26fcf","observation_id":"5456ddab-8eb1-492d-9f00-3ac514c4934f","resolution":{"observed_at":"2026-08-05T05:28:49.290021Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:28:49.270970Z","title":"Layeredflow: A real-world benchmark for non-lambertian multi-layer optical flow","venue":null,"work_id":"d2e54c11-a74a-4dad-969f-09b5d5fbb5c1","year":null},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:43.880639Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:bcf1df7d88d5588cebdf996501d44c1367a4c92d039cf765b1e553762a58fca9","observation_id":"363423bc-35a0-4c69-a6ff-d709850686c0","resolution":{"observed_at":"2026-08-05T05:28:49.275937Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:28:49.256497Z","title":"4d gaussian splatting for real-time dynamic scene render- ing","venue":null,"work_id":"2882c202-0e58-412e-a7ec-1c86fd681cb2","year":2024},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:43.993486Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:85fa607b29011f8c3095ff9cdaf559790b157a0c56770d67dad4d03c18cea7f6","observation_id":"221f2375-45be-4293-9cdb-92ba74702fba","resolution":{"observed_at":"2026-08-05T05:28:49.260693Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:28:49.241096Z","title":null,"venue":null,"work_id":"d090b2b1-bf4b-494c-b0a8-644b30303f3d","year":2015},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:44.141802Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:96e97e2367cc728b192fdf2eb06314d50caa01fea02146d2d8e69b3a470f869e","observation_id":"e79a9eb6-bc24-4d3f-b7c6-fb7f92ee7d19","resolution":{"observed_at":"2026-08-05T05:28:49.245388Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:28:49.163364Z","title":"Gmflow: Learning optical flow via global matching","venue":null,"work_id":"abf8a4f3-25f2-454f-b562-47efa6c0d211","year":null},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:44.264020Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:9aecf5ed5412405a56b69fb857f993275e430a0014c5e1e509774445da4ea738","observation_id":"edec9b74-2b7f-405e-a884-7156b0684b75","resolution":{"observed_at":"2026-08-05T05:28:49.230848Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:28:48.935438Z","title":"Unifying flow, stereo and depth estimation.IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(11):13941– 13958, 2023","venue":null,"work_id":"2506178a-d2ee-42fa-b91f-c40dffb70594","year":2023},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:44.381620Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:484df7c24c30f9535e5027387ccdf826bf0e2966d357b3eb6e402cf11597ceb7","observation_id":"c979c6e0-05e4-4c1d-9707-7a4e9e161ddb","resolution":{"observed_at":"2026-08-05T05:28:49.043364Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1809.03327","last_updated":"2018-09-06T04:19:45Z","snapshot_observed_at":"2026-07-06T07:00:12.122241Z","submitted_at":"2018-09-06T04:19:45Z","title":"YouTube-VOS: A Large-Scale Video Object Segmentation Benchmark","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1809.03327","snapshot_observed_at":"2026-08-05T05:28:44.443964Z","title":"Youtube-vos: A large-scale video object segmentation benchmark.arXiv preprint arXiv:1809.03327, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:44.443964Z"},"links":{"cited_paper":"/paper/1809.03327","citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:1a0bfacdf665b5c55dc8e540d8e7dd1238833d8de20389c0575acc3f7c08c042","observation_id":"71a37c2a-352c-4fdc-a98e-6d621cf2c18d","resolution":{"observed_at":"2026-08-05T05:28:44.443964Z","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":"2026-08-05T05:28:48.657494Z","title":"Quadratic video interpolation.Advances in Neural Information Processing Systems, 32, 2019","venue":null,"work_id":"9ac89aa9-8a67-4907-becb-294eac36e5a2","year":2019},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:44.566404Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:acbae4abf5f8a5b94406e72241c493aae81c4230e21f521b78faafcc298650ef","observation_id":"491552bf-a96d-4734-8ca7-e43f577a2137","resolution":{"observed_at":"2026-08-05T05:28:48.762862Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:28:48.411373Z","title":"V olumetric correspon- dence networks for optical flow.Advances in neural infor- mation processing systems, 32, 2019","venue":null,"work_id":"5938bdd3-ec28-41bf-820e-e18123b2071e","year":2019},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:44.672822Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:7a2b371469ad6cc5d0a140971815373ecb79f50d07f97e227c815a688943949d","observation_id":"fac5092d-c0ed-4145-b8cd-99fbcd32cfe1","resolution":{"observed_at":"2026-08-05T05:28:48.535807Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:28:48.132041Z","title":"Depth anything: Unleashing the power of large-scale unlabeled data","venue":null,"work_id":"027faaa3-135f-4bac-9709-c39f9d010cf5","year":2024},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:44.792982Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:b94f3f54febf4d257b2a340f8defe9f3d93c7250ce9a2f322d4a44eb7b20067f","observation_id":"36eaf9a3-fd0e-4a74-921c-465f476a08ae","resolution":{"observed_at":"2026-08-05T05:28:48.248902Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:28:47.902370Z","title":"Depth any- thing v2.Advances in Neural Information Processing Sys- tems, 37:21875–21911, 2024","venue":null,"work_id":"7df2b06e-3a7c-4f62-9d26-bfee0871166f","year":2024},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:44.953439Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:c4b62ba41afe7a7b02619885da299d0fa2a900be4f80ea82977b321fd50f3889","observation_id":"87569f14-8bb2-4f49-9a48-d2a0a2d3386f","resolution":{"observed_at":"2026-08-05T05:28:48.003240Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:28:47.689783Z","title":"Motion basis learning for unsupervised deep homogra- phy estimation with subspace projection","venue":null,"work_id":"7b1c897c-6e35-4304-9d9d-f454d3b32194","year":2021},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":94,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:45.079998Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:26555edd1d433ad2680479147cdb45f5eba6566b0cbae89b43a3f14f766899ea","observation_id":"de53301e-3be2-473a-8350-d7054e4c1736","resolution":{"observed_at":"2026-08-05T05:28:47.772739Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:28:47.452947Z","title":"A du- ality based approach for realtime tv-l 1 optical flow","venue":null,"work_id":"ccc32c54-ce67-4361-a5d6-d6418ce3b407","year":2007},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":95,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:45.268053Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:33dd345339fdf1f580deb02ce76cca201c84ea5366c6eae10049ababf891bd5d","observation_id":"5abcf0be-c53b-4d66-92e8-180eccafc283","resolution":{"observed_at":"2026-08-05T05:28:47.562209Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.03825","last_updated":"2025-05-08T08:32:16Z","snapshot_observed_at":"2026-07-06T19:28:08.374354Z","submitted_at":"2024-10-04T18:00:07Z","title":"MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.03825","snapshot_observed_at":"2026-08-05T05:28:45.385386Z","title":"Monst3r: A simple approach for estimat- ing geometry in the presence of motion.arXiv preprint arXiv:2410.03825, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":96,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:45.385386Z"},"links":{"cited_paper":"/paper/2410.03825","citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:89e080496a10aa4f3496693e482dd544953a34fd38e94b100482f214effa106e","observation_id":"15e72066-3602-4d64-877b-ce8fd028b833","resolution":{"observed_at":"2026-08-05T05:28:45.385386Z","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":"2026-08-05T05:28:47.175589Z","title":"Global matching with overlapping at- tention for optical flow estimation","venue":null,"work_id":"4845b3a5-7d5f-405a-a873-c2333e656e7b","year":2022},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":97,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:45.498674Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:e31646f15bd9124c0466e80bf4211144806af6d0e10b826d11493bb47c752892","observation_id":"b2ec3052-9752-4959-9d38-01f795d5802c","resolution":{"observed_at":"2026-08-05T05:28:47.283616Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:28:46.951962Z","title":"Dip: Deep inverse patch- match for high-resolution optical flow","venue":null,"work_id":"b2e26ee7-cc78-4341-b4b6-36dd507240c8","year":2022},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":98,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:45.617062Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:53985f6d8c57b25cfa7aa62ae81710394dccb271ec6874cbcefe6e3dd28a47f1","observation_id":"6ae9656e-6185-47a1-b1bc-9b54d0f6e277","resolution":{"observed_at":"2026-08-05T05:28:47.068303Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-05T05:28:46.690039Z","title":"C→T→TSKH","venue":null,"work_id":"4591aae5-dc2f-450e-8fd2-2062634ea1df","year":2025},"citing_paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases","version":1},"reference_index":99,"source":"pdf_text","source_observed_at":"2026-08-05T05:28:45.734335Z"},"links":{"citing_paper":"/paper/2509.05297"},"observation_digest":"sha256:7db3d76a2b625e8572e6753d2b06dcc90ad505266008fd0bc3142ac1d5d515c5","observation_id":"5a023086-2bfa-4b9d-83e4-f455d994c04f","resolution":{"observed_at":"2026-08-05T05:28:46.803989Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2509.05297","last_updated":"2025-09-05T17:59:59Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-10T13:06:38.572418Z","submitted_at":"2025-09-05T17:59:59Z","title":"FlowSeek: Optical Flow Made Easier with Depth Foundation Models and Motion Bases"},"reference_resolution":{"displayed":99,"state_counts":{"malformed_identifier":2,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":33,"verified_exact":1,"verified_fuzzy":63},"total_outbound_references":99},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 99 of 99 outbound references and 1 inbound Pith citation observation for arXiv:2509.05297."}