{"as_of":"2026-08-10T10:52:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d6367694665f25fc96b2f17df7bb175fa1dd50210378d48a393b81d09a273513","coverage":[{"denominator":45,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":45,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T21:55:06.821861Z","state":"measured"},{"denominator":46,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":46,"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":"2026-07-13T18:01:47.434552Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2506.23151","last_updated":"2025-06-29T09:01:42Z","snapshot_observed_at":"2026-08-08T15:19:19.263227Z","submitted_at":"2025-06-29T09:01:42Z","title":"MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.23151","snapshot_observed_at":"2026-07-13T18:01:47.434552Z","title":"arXiv preprint arXiv:2506.23151 (2025) 3, 7","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.25739","last_updated":"2026-07-07T18:00:02Z","snapshot_observed_at":"2026-07-13T18:01:46.253748Z","submitted_at":"2026-03-26T17:59:51Z","title":"MegaFlow: Zero-Shot Large Displacement Optical Flow","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-07-13T18:01:47.434552Z"},"links":{"cited_paper":"/paper/2506.23151","citing_paper":"/paper/2603.25739"},"observation_digest":"sha256:15739c011313bcdbd231ab081ad4041835957b77ba8df1517840b4b86bace65c","observation_id":"b6710f12-5970-479f-a6b7-10648190ccec","resolution":{"observed_at":"2026-07-13T18:01:47.434552Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2506.23151/citation-record","integrity":"/paper/2506.23151/integrity","json":"/paper/2506.23151/citation-record.json","paper":"/paper/2506.23151"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:55:14.475051Z","title":"Patchmatch: A randomized correspon- dence algorithm for structural image editing","venue":null,"work_id":"20b79462-e29a-4c7b-aafb-a76ee5fce595","year":2009},"citing_paper":{"arxiv_id":"2506.23151","last_updated":"2025-06-29T09:01:42Z","snapshot_observed_at":"2026-08-08T15:19:19.263227Z","submitted_at":"2025-06-29T09:01:42Z","title":"MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:02.039784Z"},"links":{"citing_paper":"/paper/2506.23151"},"observation_digest":"sha256:4c8fa015e924d17d7fcda4dba1d93306cc595e7b994e771d7a5dfb6fdd486792","observation_id":"6ebc1d3b-8aee-4d1e-b2b8-61f82becd4a6","resolution":{"observed_at":"2026-08-06T21:55:14.548994Z","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":"2026-08-06T21:55:14.285830Z","title":"A naturalistic open source movie for op- tical flow evaluation","venue":null,"work_id":"8554eb36-61fd-4fe7-9aad-226a9d69923e","year":null},"citing_paper":{"arxiv_id":"2506.23151","last_updated":"2025-06-29T09:01:42Z","snapshot_observed_at":"2026-08-08T15:19:19.263227Z","submitted_at":"2025-06-29T09:01:42Z","title":"MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:02.136010Z"},"links":{"citing_paper":"/paper/2506.23151"},"observation_digest":"sha256:b4cc4ee60afadb6e5ead1e46ddb728c52b215884aadc135cdc762185bc4fafc2","observation_id":"f173ac64-9338-4c2e-b5ea-b0539e516d8d","resolution":{"observed_at":"2026-08-06T21:55:14.401912Z","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":"2026-08-06T21:55:14.097086Z","title":"Basicvsr: The search for essential compo- nents in video super-resolution and beyond","venue":null,"work_id":"f32f5ec2-e8e6-48d1-9eb7-238f5cf3e78b","year":2021},"citing_paper":{"arxiv_id":"2506.23151","last_updated":"2025-06-29T09:01:42Z","snapshot_observed_at":"2026-08-08T15:19:19.263227Z","submitted_at":"2025-06-29T09:01:42Z","title":"MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:02.328867Z"},"links":{"citing_paper":"/paper/2506.23151"},"observation_digest":"sha256:fd8aec488426efd9efe252dd1333969870d47f5bfd7f0203791fae1150c73dcd","observation_id":"a82ea4a6-9920-430d-8de9-e6baf7688f09","resolution":{"observed_at":"2026-08-06T21:55:14.195278Z","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":"2026-08-06T21:55:13.860900Z","title":"Memflow: Optical flow esti- mation and prediction with memory","venue":null,"work_id":"ebc6349b-0060-4d09-bb25-e02050b16a76","year":2024},"citing_paper":{"arxiv_id":"2506.23151","last_updated":"2025-06-29T09:01:42Z","snapshot_observed_at":"2026-08-08T15:19:19.263227Z","submitted_at":"2025-06-29T09:01:42Z","title":"MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:02.477584Z"},"links":{"citing_paper":"/paper/2506.23151"},"observation_digest":"sha256:302bde7bc82e4ed25162dcd724c123766df818e81f88628e551f790dc3d7d177","observation_id":"85339030-237c-4d03-aa72-7ebe2d0f6973","resolution":{"observed_at":"2026-08-06T21:55:13.980493Z","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":"2026-08-06T21:55:13.702767Z","title":"Flownet: Learning optical flow with convolutional networks","venue":null,"work_id":"e501df09-ddb9-42b3-b6cb-00fdca6761c3","year":2015},"citing_paper":{"arxiv_id":"2506.23151","last_updated":"2025-06-29T09:01:42Z","snapshot_observed_at":"2026-08-08T15:19:19.263227Z","submitted_at":"2025-06-29T09:01:42Z","title":"MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:02.602897Z"},"links":{"citing_paper":"/paper/2506.23151"},"observation_digest":"sha256:2f2c5be2574a4453c42d7a689ca948f52419bfaa4adf88e0c7aa08e658716dab","observation_id":"300e618c-6662-4a58-9e0c-567c255cc960","resolution":{"observed_at":"2026-08-06T21:55:13.748630Z","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":"2026-08-06T21:55:02.766456Z","title":"Two-frame motion estimation based on polynomial expansion","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2506.23151","last_updated":"2025-06-29T09:01:42Z","snapshot_observed_at":"2026-08-08T15:19:19.263227Z","submitted_at":"2025-06-29T09:01:42Z","title":"MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:02.766456Z"},"links":{"citing_paper":"/paper/2506.23151"},"observation_digest":"sha256:f9f0b6130d9e87cf2e1b759c796a0e321d69c5ee93b8662f858e6754b59992c9","observation_id":"4b187e18-3abd-4610-b2a0-a2e7be6de39c","resolution":{"observed_at":"2026-08-06T21:55:02.766456Z","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":"2026-08-06T21:55:02.882925Z","title":"Vision meets robotics: The kitti dataset","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.23151","last_updated":"2025-06-29T09:01:42Z","snapshot_observed_at":"2026-08-08T15:19:19.263227Z","submitted_at":"2025-06-29T09:01:42Z","title":"MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:02.882925Z"},"links":{"citing_paper":"/paper/2506.23151"},"observation_digest":"sha256:4db3e2cd6b34cf8668d80526ba927bf99fe6c77f204d60fbcc4df49b1442f77f","observation_id":"53435d7c-fbb9-435a-8b51-94c6b9274d54","resolution":{"observed_at":"2026-08-06T21:55:02.882925Z","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":"2026-08-06T21:55:03.022825Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.23151","last_updated":"2025-06-29T09:01:42Z","snapshot_observed_at":"2026-08-08T15:19:19.263227Z","submitted_at":"2025-06-29T09:01:42Z","title":"MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:03.022825Z"},"links":{"citing_paper":"/paper/2506.23151"},"observation_digest":"sha256:fbdc6197be125a5e34ce8a31e3d6eaeca33683acf0532f62749840ca6ff4ea6e","observation_id":"f45e53dd-2cfe-4fd4-8471-59181f245d76","resolution":{"observed_at":"2026-08-06T21:55:03.022825Z","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":"2026-08-06T21:55:13.525759Z","title":"Determining op- tical flow","venue":null,"work_id":"c5c1ea9a-e8fc-4a7c-9c3b-4862afc0a678","year":1981},"citing_paper":{"arxiv_id":"2506.23151","last_updated":"2025-06-29T09:01:42Z","snapshot_observed_at":"2026-08-08T15:19:19.263227Z","submitted_at":"2025-06-29T09:01:42Z","title":"MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:03.145673Z"},"links":{"citing_paper":"/paper/2506.23151"},"observation_digest":"sha256:aa09eda341311ff33127b5a35978bdb6f64f96b8077a03e7aaa8599c83f58ec4","observation_id":"db415172-0de1-40d6-a5e4-d05a848dd47c","resolution":{"observed_at":"2026-08-06T21:55:13.604016Z","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":"2026-08-06T21:55:13.367146Z","title":"Flowformer: A transformer architecture for optical flow","venue":null,"work_id":"97ce9384-8871-42c7-80d7-98d8e450455f","year":2022},"citing_paper":{"arxiv_id":"2506.23151","last_updated":"2025-06-29T09:01:42Z","snapshot_observed_at":"2026-08-08T15:19:19.263227Z","submitted_at":"2025-06-29T09:01:42Z","title":"MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:03.255123Z"},"links":{"citing_paper":"/paper/2506.23151"},"observation_digest":"sha256:d38cf665517d1d22b418d309fd031a237288e66e2838d14b76021965e22f1007","observation_id":"ec74ee9b-c066-4a41-81d0-6503dbeba398","resolution":{"observed_at":"2026-08-06T21:55:13.416613Z","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":"2026-08-06T21:55:13.066946Z","title":"Real-time intermediate flow estima- tion for video frame interpolation","venue":null,"work_id":"c7c7c67f-748a-4b5e-903d-873c37be8904","year":2022},"citing_paper":{"arxiv_id":"2506.23151","last_updated":"2025-06-29T09:01:42Z","snapshot_observed_at":"2026-08-08T15:19:19.263227Z","submitted_at":"2025-06-29T09:01:42Z","title":"MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:03.346073Z"},"links":{"citing_paper":"/paper/2506.23151"},"observation_digest":"sha256:5a02b03184927e106441191dbf62591ef89d6b055ed7db550d7e6d9eb0caf751","observation_id":"82790219-dc64-425b-bd97-c98eb8c982ac","resolution":{"observed_at":"2026-08-06T21:55:13.223117Z","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":"2026-08-06T21:55:12.836753Z","title":"Flownet 2.0: Evolu- tion of optical flow estimation with deep networks","venue":null,"work_id":"35a8bb44-fca1-4db5-a10d-91de8eaf136f","year":2017},"citing_paper":{"arxiv_id":"2506.23151","last_updated":"2025-06-29T09:01:42Z","snapshot_observed_at":"2026-08-08T15:19:19.263227Z","submitted_at":"2025-06-29T09:01:42Z","title":"MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:03.470166Z"},"links":{"citing_paper":"/paper/2506.23151"},"observation_digest":"sha256:a014bee0da7f653b3bb55dafa9612cf830f4d319890430a3e3d8bd44882bbec0","observation_id":"d3584d88-cd0e-4f07-b292-b0a03d2428a3","resolution":{"observed_at":"2026-08-06T21:55:12.956857Z","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":"2026-08-06T21:55:12.609670Z","title":"Learning to estimate hidden motions with global motion aggregation","venue":null,"work_id":"338b1e35-69a3-468d-b237-c46c65fb5ea2","year":null},"citing_paper":{"arxiv_id":"2506.23151","last_updated":"2025-06-29T09:01:42Z","snapshot_observed_at":"2026-08-08T15:19:19.263227Z","submitted_at":"2025-06-29T09:01:42Z","title":"MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:03.633584Z"},"links":{"citing_paper":"/paper/2506.23151"},"observation_digest":"sha256:20ee237b0dd0bed3de82ee9c824da274c2dd8804cc9d7df9edc73e63dd90da11","observation_id":"439bfa08-e161-420c-8ea9-88b0b98ca562","resolution":{"observed_at":"2026-08-06T21:55:12.718916Z","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":"2026-08-06T21:55:12.358722Z","title":"Learning optical flow from a few matches","venue":null,"work_id":"81f287e3-643b-4ee6-8815-280a1c98bb0e","year":2021},"citing_paper":{"arxiv_id":"2506.23151","last_updated":"2025-06-29T09:01:42Z","snapshot_observed_at":"2026-08-08T15:19:19.263227Z","submitted_at":"2025-06-29T09:01:42Z","title":"MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:03.793573Z"},"links":{"citing_paper":"/paper/2506.23151"},"observation_digest":"sha256:814e24cdd5c4c5c7aaeeef7128183cdbe88b70675d2b327d748e1ffc8518c37a","observation_id":"7a6b444e-50a7-4538-b6bf-6bbe5532d58d","resolution":{"observed_at":"2026-08-06T21:55:12.475822Z","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":"2026-08-06T21:55:12.099981Z","title":"Face deblurring using dual camera fusion on mobile phones","venue":null,"work_id":"9dc93a12-f5ba-4dff-95d2-864fce44bd28","year":2022},"citing_paper":{"arxiv_id":"2506.23151","last_updated":"2025-06-29T09:01:42Z","snapshot_observed_at":"2026-08-08T15:19:19.263227Z","submitted_at":"2025-06-29T09:01:42Z","title":"MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:03.921057Z"},"links":{"citing_paper":"/paper/2506.23151"},"observation_digest":"sha256:59ce726366fb221600c34d32e9b9457929e5a1097250971f47e2e5b1f19cef46","observation_id":"78f8e515-fd5d-4ce2-b137-9fcd36d6ce7c","resolution":{"observed_at":"2026-08-06T21:55:12.220212Z","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":"2026-08-06T21:55:04.118643Z","title":"Video frame inter- polation via optical flow estimation with image inpainting","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.23151","last_updated":"2025-06-29T09:01:42Z","snapshot_observed_at":"2026-08-08T15:19:19.263227Z","submitted_at":"2025-06-29T09:01:42Z","title":"MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:04.118643Z"},"links":{"citing_paper":"/paper/2506.23151"},"observation_digest":"sha256:439461d802ec745d67dbf31bd8b7b22a12e755172572b398765406b0b93e2f14","observation_id":"ab1d0659-3b49-4e7c-86d4-c7e6ccbd8de6","resolution":{"observed_at":"2026-08-06T21:55:04.118643Z","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":"2026-08-06T21:55:11.847610Z","title":"An iterative image reg- istration technique with an application to stereo vision","venue":null,"work_id":"010550e0-04da-4d85-b9a6-b333b0d6283e","year":1981},"citing_paper":{"arxiv_id":"2506.23151","last_updated":"2025-06-29T09:01:42Z","snapshot_observed_at":"2026-08-08T15:19:19.263227Z","submitted_at":"2025-06-29T09:01:42Z","title":"MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:04.281842Z"},"links":{"citing_paper":"/paper/2506.23151"},"observation_digest":"sha256:0863995331c9e5161789ebd4b575e2a9ff4c90c61e54673170b886f4d826ebff","observation_id":"ba4cdd3e-ef95-4627-b010-77d3ab69dc96","resolution":{"observed_at":"2026-08-06T21:55:11.957555Z","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":"2026-08-06T21:55:11.688775Z","title":"Spring: A high-resolution high- detail dataset and benchmark for scene flow, optical flow and stereo","venue":null,"work_id":"b786c71c-3a22-47b4-8009-ff08d8ed8b73","year":2023},"citing_paper":{"arxiv_id":"2506.23151","last_updated":"2025-06-29T09:01:42Z","snapshot_observed_at":"2026-08-08T15:19:19.263227Z","submitted_at":"2025-06-29T09:01:42Z","title":"MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:04.445556Z"},"links":{"citing_paper":"/paper/2506.23151"},"observation_digest":"sha256:687e6eadda823897f7ea315f7654c006701eac898da13b29e27161a83536dae0","observation_id":"a92a5046-7233-46ab-a2d1-c80127e65ce4","resolution":{"observed_at":"2026-08-06T21:55:11.754806Z","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":"2026-08-06T21:55:11.537106Z","title":"Object scene flow for autonomous vehicles","venue":null,"work_id":"e6f1e1a7-0fc0-4ed8-b134-c61c9d35cba6","year":2015},"citing_paper":{"arxiv_id":"2506.23151","last_updated":"2025-06-29T09:01:42Z","snapshot_observed_at":"2026-08-08T15:19:19.263227Z","submitted_at":"2025-06-29T09:01:42Z","title":"MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:04.518816Z"},"links":{"citing_paper":"/paper/2506.23151"},"observation_digest":"sha256:19e2f102af1716e8464519ceb94c42409fe12eca85a8e5aca5b6e9810617c631","observation_id":"f143a3ea-8152-47b0-976a-e7f8594869ab","resolution":{"observed_at":"2026-08-06T21:55:11.627373Z","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":"2026-08-06T21:55:11.417565Z","title":"Recurrent partial kernel network for efficient optical flow estimation","venue":null,"work_id":"652895c4-f88c-4590-bff6-e1a787ca5131","year":2024},"citing_paper":{"arxiv_id":"2506.23151","last_updated":"2025-06-29T09:01:42Z","snapshot_observed_at":"2026-08-08T15:19:19.263227Z","submitted_at":"2025-06-29T09:01:42Z","title":"MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:04.621928Z"},"links":{"citing_paper":"/paper/2506.23151"},"observation_digest":"sha256:aad28309c4900729e2bfadb87884c51403ee3ad4cc22aba8f889fa4a289d2375","observation_id":"42cd33db-4849-476b-8ee0-98c897820046","resolution":{"observed_at":"2026-08-06T21:55:11.481709Z","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":"2026-08-06T21:55:11.252583Z","title":"A benchmark dataset and evaluation methodology for video object segmentation","venue":null,"work_id":"f9f1269b-711a-4358-a39b-bb9ec7e9db90","year":2016},"citing_paper":{"arxiv_id":"2506.23151","last_updated":"2025-06-29T09:01:42Z","snapshot_observed_at":"2026-08-08T15:19:19.263227Z","submitted_at":"2025-06-29T09:01:42Z","title":"MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:04.696241Z"},"links":{"citing_paper":"/paper/2506.23151"},"observation_digest":"sha256:b950711bd3d178d044889711f80b86acf11de8d7c46963b1c05986bec6649c88","observation_id":"44494cb7-dda4-41db-9ef0-2277590d8904","resolution":{"observed_at":"2026-08-06T21:55:11.324625Z","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":"2026-08-06T21:55:11.086089Z","title":"Representation flow for action recognition","venue":null,"work_id":"e2c114fc-5432-4016-9236-daf639e60aea","year":2019},"citing_paper":{"arxiv_id":"2506.23151","last_updated":"2025-06-29T09:01:42Z","snapshot_observed_at":"2026-08-08T15:19:19.263227Z","submitted_at":"2025-06-29T09:01:42Z","title":"MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:04.776997Z"},"links":{"citing_paper":"/paper/2506.23151"},"observation_digest":"sha256:f9e22bd850745d723c9f2bb3308ccb337f7d323e2f0e00282294cab8b9cdb19a","observation_id":"0a78b410-2d27-499a-b790-9de7b3890882","resolution":{"observed_at":"2026-08-06T21:55:11.154973Z","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":"2026-08-06T21:55:10.976780Z","title":"A fusion approach for multi- frame optical flow estimation","venue":null,"work_id":"222346e0-d843-4037-adca-65ed44089ab0","year":null},"citing_paper":{"arxiv_id":"2506.23151","last_updated":"2025-06-29T09:01:42Z","snapshot_observed_at":"2026-08-08T15:19:19.263227Z","submitted_at":"2025-06-29T09:01:42Z","title":"MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:04.851105Z"},"links":{"citing_paper":"/paper/2506.23151"},"observation_digest":"sha256:b9126aa4f344c88d86fb26bec9e713a7520404e8bedaf684569b3a45908e526f","observation_id":"5150ad89-13cc-45db-b3a4-e1a3be5f78cf","resolution":{"observed_at":"2026-08-06T21:55:11.020609Z","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":"2026-08-06T21:55:10.788376Z","title":"Playing for benchmarks","venue":null,"work_id":"3f675c8a-b8db-45b3-8ac5-876a54bd52d5","year":2017},"citing_paper":{"arxiv_id":"2506.23151","last_updated":"2025-06-29T09:01:42Z","snapshot_observed_at":"2026-08-08T15:19:19.263227Z","submitted_at":"2025-06-29T09:01:42Z","title":"MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:04.970169Z"},"links":{"citing_paper":"/paper/2506.23151"},"observation_digest":"sha256:bf961d7a76ec81a7eaae5788faf13840ebf15d8ec169c292a539b97b3eb750a3","observation_id":"510bd4df-6040-41b5-858d-e82e4f8b92ee","resolution":{"observed_at":"2026-08-06T21:55:10.861191Z","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":"2026-08-06T21:55:10.682471Z","title":"The surprising effectiveness of diffusion models for optical flow and monocular depth estimation","venue":null,"work_id":"a3fe6a98-ad39-4a5c-aa58-2ed6feead938","year":2023},"citing_paper":{"arxiv_id":"2506.23151","last_updated":"2025-06-29T09:01:42Z","snapshot_observed_at":"2026-08-08T15:19:19.263227Z","submitted_at":"2025-06-29T09:01:42Z","title":"MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:05.071768Z"},"links":{"citing_paper":"/paper/2506.23151"},"observation_digest":"sha256:4b0411dc4c2eef595256685308a37b7b12ccf716c34066ad810e59339eae4904","observation_id":"8cdd2fff-1da8-4f71-82b1-fe039968d8b2","resolution":{"observed_at":"2026-08-06T21:55:10.732034Z","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":"2026-08-06T21:55:10.480914Z","title":"Videoflow: Exploiting temporal cues for multi-frame optical flow estimation","venue":null,"work_id":"863d22e6-019a-4c44-a746-7cbea7601418","year":2023},"citing_paper":{"arxiv_id":"2506.23151","last_updated":"2025-06-29T09:01:42Z","snapshot_observed_at":"2026-08-08T15:19:19.263227Z","submitted_at":"2025-06-29T09:01:42Z","title":"MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:05.154657Z"},"links":{"citing_paper":"/paper/2506.23151"},"observation_digest":"sha256:a907fe63990d304915baf1bfc4f9af8377374aa0fc24eceaf53daf20f9074b13","observation_id":"afaca056-16d4-4540-a196-bdf40f25c05e","resolution":{"observed_at":"2026-08-06T21:55:10.585143Z","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":"2026-08-06T21:55:10.241493Z","title":"Flowformer++: Masked cost volume autoen- coding for pretraining optical flow estimation","venue":null,"work_id":"31a02b8f-d1fd-4176-addb-b4779a080bc2","year":2023},"citing_paper":{"arxiv_id":"2506.23151","last_updated":"2025-06-29T09:01:42Z","snapshot_observed_at":"2026-08-08T15:19:19.263227Z","submitted_at":"2025-06-29T09:01:42Z","title":"MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:05.240445Z"},"links":{"citing_paper":"/paper/2506.23151"},"observation_digest":"sha256:a1261e047e3331a54e7f18a452504a21cd24206d576dcd57756254c4c5effc4c","observation_id":"ab8a8432-86ed-4f52-9be0-ddbaff123f3d","resolution":{"observed_at":"2026-08-06T21:55:10.362498Z","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":"2026-08-06T21:55:10.081455Z","title":"Pwc-net: Cnns for optical flow using pyramid, warping, and cost volume","venue":null,"work_id":"35c68e7c-5440-4617-acd7-61d6790906d2","year":2018},"citing_paper":{"arxiv_id":"2506.23151","last_updated":"2025-06-29T09:01:42Z","snapshot_observed_at":"2026-08-08T15:19:19.263227Z","submitted_at":"2025-06-29T09:01:42Z","title":"MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:05.304660Z"},"links":{"citing_paper":"/paper/2506.23151"},"observation_digest":"sha256:86fa723864c6d976d73bfed0cc4f8843694f9eca8920e0ef572ea503c5a8ffd5","observation_id":"27274c8d-dc65-451c-b579-f1f93ac10e60","resolution":{"observed_at":"2026-08-06T21:55:10.145718Z","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":"2026-08-06T21:55:09.921716Z","title":"Optical flow guided feature: A fast and robust motion representation for video action recognition","venue":null,"work_id":"937d3c24-6933-4ffe-aab6-2d8d7f366e98","year":2018},"citing_paper":{"arxiv_id":"2506.23151","last_updated":"2025-06-29T09:01:42Z","snapshot_observed_at":"2026-08-08T15:19:19.263227Z","submitted_at":"2025-06-29T09:01:42Z","title":"MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:05.376042Z"},"links":{"citing_paper":"/paper/2506.23151"},"observation_digest":"sha256:9c58f9eca7675f5e05960075adf0c16bf88e587b5af007191f65ee519b0175c9","observation_id":"83d6c470-6131-423c-bb16-19579fe96130","resolution":{"observed_at":"2026-08-06T21:55:09.973182Z","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":"2026-08-06T21:55:09.757978Z","title":"Streamflow: streamlined multi- frame optical flow estimation for video sequences","venue":null,"work_id":"6b37cc40-d68c-4b77-92de-cfbb874a28c1","year":2025},"citing_paper":{"arxiv_id":"2506.23151","last_updated":"2025-06-29T09:01:42Z","snapshot_observed_at":"2026-08-08T15:19:19.263227Z","submitted_at":"2025-06-29T09:01:42Z","title":"MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:05.442581Z"},"links":{"citing_paper":"/paper/2506.23151"},"observation_digest":"sha256:5f7dec21163a10c8f3092a79b7cb106e66a26558cfc1bd226ed5bed3a84931bc","observation_id":"15fbc532-1058-479f-ba70-2230b52b9a78","resolution":{"observed_at":"2026-08-06T21:55:09.871122Z","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":"2026-08-06T21:55:05.502363Z","title":"Raft: Recurrent all-pairs field transforms for optical flow","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.23151","last_updated":"2025-06-29T09:01:42Z","snapshot_observed_at":"2026-08-08T15:19:19.263227Z","submitted_at":"2025-06-29T09:01:42Z","title":"MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:05.502363Z"},"links":{"citing_paper":"/paper/2506.23151"},"observation_digest":"sha256:9e2a2373c0267062561e9e4a5450caa2f69aa0ed3d4cf8b98689ad31cd19ef26","observation_id":"33a5c8bb-dc68-4e66-baf2-31db04c70bf2","resolution":{"observed_at":"2026-08-06T21:55:05.502363Z","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":"2026-08-06T21:55:05.594861Z","title":"Sea-raft: Simple, efficient, accurate raft for optical flow","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.23151","last_updated":"2025-06-29T09:01:42Z","snapshot_observed_at":"2026-08-08T15:19:19.263227Z","submitted_at":"2025-06-29T09:01:42Z","title":"MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:05.594861Z"},"links":{"citing_paper":"/paper/2506.23151"},"observation_digest":"sha256:10ffa520bbe9d1c99c7b91d73fd57bad27022f882f87f36af565080500d5c137","observation_id":"a9dbb6e8-b31a-4407-8c49-888e72411d4b","resolution":{"observed_at":"2026-08-06T21:55:05.594861Z","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":"2026-08-06T21:55:09.420379Z","title":"Croco v2: Improved cross-view completion pre- training for stereo matching and optical flow","venue":null,"work_id":"8ce0a8a8-f08e-4510-a1a5-55028c9c78b8","year":2023},"citing_paper":{"arxiv_id":"2506.23151","last_updated":"2025-06-29T09:01:42Z","snapshot_observed_at":"2026-08-08T15:19:19.263227Z","submitted_at":"2025-06-29T09:01:42Z","title":"MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:05.818026Z"},"links":{"citing_paper":"/paper/2506.23151"},"observation_digest":"sha256:eb5f650d1baea8a79a4ee19b97d8f61fab03d061570270fb557b0c2818e29213","observation_id":"3fc65bb0-0da1-4792-a5ed-ab25212ac058","resolution":{"observed_at":"2026-08-06T21:55:09.537488Z","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":"2312.03790","last_updated":"2025-03-04T12:54:46Z","snapshot_observed_at":"2026-07-06T16:57:55.137830Z","submitted_at":"2023-12-06T12:43:11Z","title":"Memory-Efficient Optical Flow via Radius-Distribution Orthogonal Cost Volume","version":2},"cited_work":{"arxiv_id":"2312.03790","doi":null,"metadata_source":"pith","pith_arxiv_id":"2312.03790","snapshot_observed_at":"2026-08-06T21:55:06.960107Z","title":"Memory-Efficient Optical Flow via Radius-Distribution Orthogonal Cost Volume","venue":"cs.CV","work_id":"cb7df1a4-f9c6-47af-b4bc-91af78a99047","year":2023},"citing_paper":{"arxiv_id":"2506.23151","last_updated":"2025-06-29T09:01:42Z","snapshot_observed_at":"2026-08-08T15:19:19.263227Z","submitted_at":"2025-06-29T09:01:42Z","title":"MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:05.904854Z"},"links":{"cited_paper":"/paper/2312.03790","citing_paper":"/paper/2506.23151"},"observation_digest":"sha256:f02c98a8ddfb0fd047307a02c943b3881b4db90fcaa044c947aa24128d8a6873","observation_id":"a6f81615-54bd-4e49-8cc8-4d7cafffac9b","resolution":{"observed_at":"2026-08-06T21:55:07.075693Z","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":"2026-08-06T21:55:09.204010Z","title":"High-resolution optical flow from 1d attention and correlation","venue":null,"work_id":"f5663d32-64ce-4215-9259-f41bdf1141e5","year":2021},"citing_paper":{"arxiv_id":"2506.23151","last_updated":"2025-06-29T09:01:42Z","snapshot_observed_at":"2026-08-08T15:19:19.263227Z","submitted_at":"2025-06-29T09:01:42Z","title":"MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:05.981072Z"},"links":{"citing_paper":"/paper/2506.23151"},"observation_digest":"sha256:a24b4403747c18d259f9f7bac4a253db483f3aa14cb374fb794b4d424c958054","observation_id":"ae8e2f96-9472-4f3b-8863-d4fb2dedec12","resolution":{"observed_at":"2026-08-06T21:55:09.321134Z","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":"2026-08-06T21:55:08.906930Z","title":"Gmflow: Learning optical flow via global matching","venue":null,"work_id":"49bf1cf0-cd11-478e-96f5-2b5434f1e652","year":2022},"citing_paper":{"arxiv_id":"2506.23151","last_updated":"2025-06-29T09:01:42Z","snapshot_observed_at":"2026-08-08T15:19:19.263227Z","submitted_at":"2025-06-29T09:01:42Z","title":"MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:06.055699Z"},"links":{"citing_paper":"/paper/2506.23151"},"observation_digest":"sha256:d09266111255809e76a101d408c1477012c75a33ff1c37097c20752ee7c223a0","observation_id":"ce81df7b-58b9-44a9-bb74-33251537dfbd","resolution":{"observed_at":"2026-08-06T21:55:09.087111Z","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":"2026-08-06T21:55:08.670738Z","title":"Quadratic video interpolation","venue":null,"work_id":"eff46c8a-22c4-469e-8322-c3219e1f5c6b","year":null},"citing_paper":{"arxiv_id":"2506.23151","last_updated":"2025-06-29T09:01:42Z","snapshot_observed_at":"2026-08-08T15:19:19.263227Z","submitted_at":"2025-06-29T09:01:42Z","title":"MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:06.177974Z"},"links":{"citing_paper":"/paper/2506.23151"},"observation_digest":"sha256:283cdb0cdebd51aebbd5b534563f620527df15fdb74a3b869d9450b76d770973","observation_id":"d97e7731-4d20-4622-8696-c0c8b84c9049","resolution":{"observed_at":"2026-08-06T21:55:08.800019Z","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":"2026-08-06T21:55:08.501638Z","title":"Improved two-stream model for human action recognition","venue":null,"work_id":"1413242a-3e15-47f8-aeb7-08ffeeb18883","year":2020},"citing_paper":{"arxiv_id":"2506.23151","last_updated":"2025-06-29T09:01:42Z","snapshot_observed_at":"2026-08-08T15:19:19.263227Z","submitted_at":"2025-06-29T09:01:42Z","title":"MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:06.305743Z"},"links":{"citing_paper":"/paper/2506.23151"},"observation_digest":"sha256:96489c57e9ee621918100b4a0b7f8d5a26cc590133d87d413199dfb076907321","observation_id":"7503bc27-b09b-4bc4-b1c7-164991ebc198","resolution":{"observed_at":"2026-08-06T21:55:08.585616Z","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":"2026-08-06T21:55:08.256117Z","title":"Hybrid cost volume for memory-efficient optical flow","venue":null,"work_id":"82c2cb4e-4362-42e4-b381-ff34265bf747","year":2024},"citing_paper":{"arxiv_id":"2506.23151","last_updated":"2025-06-29T09:01:42Z","snapshot_observed_at":"2026-08-08T15:19:19.263227Z","submitted_at":"2025-06-29T09:01:42Z","title":"MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:06.428110Z"},"links":{"citing_paper":"/paper/2506.23151"},"observation_digest":"sha256:085dd58f5014d96f0a3a2e75d90b05c1a5809c2acb9fc8e890b272987b2589bf","observation_id":"9d5330f7-3402-47b3-90c2-058626c2f18f","resolution":{"observed_at":"2026-08-06T21:55:08.388940Z","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":"2026-08-06T21:55:08.066018Z","title":"Dip: Deep inverse patchmatch for high-resolution optical flow","venue":null,"work_id":"512daf51-bc93-48f3-95ad-d7f9616449ad","year":null},"citing_paper":{"arxiv_id":"2506.23151","last_updated":"2025-06-29T09:01:42Z","snapshot_observed_at":"2026-08-08T15:19:19.263227Z","submitted_at":"2025-06-29T09:01:42Z","title":"MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:06.534951Z"},"links":{"citing_paper":"/paper/2506.23151"},"observation_digest":"sha256:f507d676c1492326fe177c1751277d909c918a6e5c5afab8b760827d5719fe44","observation_id":"38db1009-4991-4a7f-aa6d-d613d153201c","resolution":{"observed_at":"2026-08-06T21:55:08.159825Z","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":"2026-08-06T21:55:07.716607Z","title":null,"venue":null,"work_id":"ce315480-fe9b-4144-be38-ca86b816ca2d","year":1920},"citing_paper":{"arxiv_id":"2506.23151","last_updated":"2025-06-29T09:01:42Z","snapshot_observed_at":"2026-08-08T15:19:19.263227Z","submitted_at":"2025-06-29T09:01:42Z","title":"MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:06.675660Z"},"links":{"citing_paper":"/paper/2506.23151"},"observation_digest":"sha256:232f9382e0570e1381344c81464e9a26a3a9b16060100db6416207f57e6ba08f","observation_id":"c89ba91d-2e25-4228-a201-48fd69cea9ca","resolution":{"observed_at":"2026-08-06T21:55:07.833890Z","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":"2026-08-06T21:55:07.478144Z","title":null,"venue":null,"work_id":"7c4467da-a4e6-4d72-bc7a-5044ea369069","year":null},"citing_paper":{"arxiv_id":"2506.23151","last_updated":"2025-06-29T09:01:42Z","snapshot_observed_at":"2026-08-08T15:19:19.263227Z","submitted_at":"2025-06-29T09:01:42Z","title":"MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:06.733253Z"},"links":{"citing_paper":"/paper/2506.23151"},"observation_digest":"sha256:a5e4941efb271e7ca81d2fccd8b1a11ccd0ee76a9a809051a2d8cb68938a9dbb","observation_id":"19222573-ab59-41c2-afe1-d19ba82ce77f","resolution":{"observed_at":"2026-08-06T21:55:07.602928Z","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"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:55:07.206338Z","title":null,"venue":null,"work_id":"93d1aa59-3be6-4dcb-96b9-060c40d75f71","year":null},"citing_paper":{"arxiv_id":"2506.23151","last_updated":"2025-06-29T09:01:42Z","snapshot_observed_at":"2026-08-08T15:19:19.263227Z","submitted_at":"2025-06-29T09:01:42Z","title":"MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:06.821861Z"},"links":{"citing_paper":"/paper/2506.23151"},"observation_digest":"sha256:600cf40ed0f1033b6f5944b26cf3d495b3db91dad12ab502eed879f0b39cf864","observation_id":"d60ac51d-5aad-4175-b4fa-805f75a423df","resolution":{"observed_at":"2026-08-06T21:55:07.336927Z","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":"2026-08-06T21:55:09.590271Z","title":"2, 4, 5, 6, 7","venue":null,"work_id":"1eb550f3-6ebb-4346-bf7e-6054bd8acd1d","year":2024},"citing_paper":{"arxiv_id":"2506.23151","last_updated":"2025-06-29T09:01:42Z","snapshot_observed_at":"2026-08-08T15:19:19.263227Z","submitted_at":"2025-06-29T09:01:42Z","title":"MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:05.725398Z"},"links":{"citing_paper":"/paper/2506.23151"},"observation_digest":"sha256:e1795db0e9009135853f4ee8c756fbc5afeb4faedfc2a41db0ec0fef008465b7","observation_id":"d959df4c-3b11-4710-9c97-e9a82f166413","resolution":{"observed_at":"2026-08-06T21:55:09.627639Z","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":"2026-08-06T21:55:07.910381Z","title":null,"venue":null,"work_id":"2bc25b55-6e22-4c59-ad9a-89deaf0a8261","year":null},"citing_paper":{"arxiv_id":"2506.23151","last_updated":"2025-06-29T09:01:42Z","snapshot_observed_at":"2026-08-08T15:19:19.263227Z","submitted_at":"2025-06-29T09:01:42Z","title":"MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-06T21:55:06.578564Z"},"links":{"citing_paper":"/paper/2506.23151"},"observation_digest":"sha256:e37b25674ef5a1076f157e13a9ffd1b1e0f59249b646b089d9042ec7aeac41ed","observation_id":"b7a66337-5551-43e9-a78c-b149dc1eb56e","resolution":{"observed_at":"2026-08-06T21:55:07.983117Z","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"}}],"paper":{"arxiv_id":"2506.23151","last_updated":"2025-06-29T09:01:42Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-08T15:19:19.263227Z","submitted_at":"2025-06-29T09:01:42Z","title":"MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation"},"reference_resolution":{"displayed":45,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":9,"verified_exact":1,"verified_fuzzy":34},"total_outbound_references":45},"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 45 of 45 outbound references and 1 inbound Pith citation observation for arXiv:2506.23151."}