{"as_of":"2026-08-12T18:23:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a8d9af05381d5f0d20ac7c3576cb332fae4922093523ab0b9d9564061369f191","coverage":[{"denominator":72,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":72,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T15:13:23.293780Z","state":"measured"},{"denominator":76,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":76,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-12T06:34:41.77262+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T18:35:26.587738Z","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":"2026-06-30T14:14:45.635113Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.11284","snapshot_observed_at":"2026-08-11T18:35:26.587738Z","title":"Learn- ing normal flow directly from event neighborhoods","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.07761","last_updated":"2025-03-25T17:58:16Z","snapshot_observed_at":"2026-08-11T18:28:46.738534Z","submitted_at":"2024-12-10T18:55:30Z","title":"Repurposing Pre-trained Video Diffusion Models for Event-based Video Interpolation","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-11T18:35:26.587738Z"},"links":{"cited_paper":"/paper/2412.11284","citing_paper":"/paper/2412.07761"},"observation_digest":"sha256:1f8e8cacca4965ecdb6b92d8bb6a2190c260676ae2d06ca0841a62d6d143e480","observation_id":"b6b3592e-60e1-41fb-add7-7af37094e3d6","resolution":{"observed_at":"2026-08-11T18:35:26.587738Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.11284","snapshot_observed_at":"2026-08-07T10:52:50.006830Z","title":"Learn- ing normal flow directly from event neighborhoods.arXiv preprint arXiv:2412.11284, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.04048","last_updated":"2025-06-04T15:14:36Z","snapshot_observed_at":"2026-08-08T05:58:51.312321Z","submitted_at":"2025-06-04T15:14:36Z","title":"EV-Flying: an Event-based Dataset for In-The-Wild Recognition of Flying Objects","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:50.006830Z"},"links":{"cited_paper":"/paper/2412.11284","citing_paper":"/paper/2506.04048"},"observation_digest":"sha256:728417b987f350e8e72350a32896ebab8a2754c26083d368737477ebd1ba7cbe","observation_id":"aa4bd4da-d0c3-44fa-9150-34733b689435","resolution":{"observed_at":"2026-08-07T10:52:50.006830Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.11284","snapshot_observed_at":"2026-08-06T15:59:05.659591Z","title":"Learn- ing normal flow directly from event neighborhoods","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.14500","last_updated":"2025-07-19T06:11:09Z","snapshot_observed_at":"2026-08-11T03:20:09.497892Z","submitted_at":"2025-07-19T06:11:09Z","title":"Motion Segmentation and Egomotion Estimation from Event-Based Normal Flow","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-06T15:59:05.659591Z"},"links":{"cited_paper":"/paper/2412.11284","citing_paper":"/paper/2507.14500"},"observation_digest":"sha256:1b6d6c7b6f192bae31124e502d79a2387a0fe8a0bad29696c8df7b9c23c8102f","observation_id":"b7fed3e4-b270-47c9-b82e-9bd5d766a55c","resolution":{"observed_at":"2026-08-06T15:59:05.659591Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"cited_work":{"arxiv_id":"2412.11284","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2412.11284","snapshot_observed_at":"2026-06-30T14:14:45.635113Z","title":"arXiv preprint arXiv:2412.11284 (2024)","venue":null,"work_id":"76ffab18-f26e-42cc-b784-49c71c4e8448","year":2024},"citing_paper":{"arxiv_id":"2605.24604","last_updated":"2026-05-23T14:42:24Z","snapshot_observed_at":"2026-07-06T23:34:38.098785Z","submitted_at":"2026-05-23T14:42:24Z","title":"LC-Flow: Learning Local Continuous Optical Flow and Confidence from events","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-06-30T14:09:45.586362Z"},"links":{"cited_paper":"/paper/2412.11284","citing_paper":"/paper/2605.24604"},"observation_digest":"sha256:1a04b687543798c4aa1f6acf543bef6b8a2ef4d8190e1fc3a54d6377980d16b2","observation_id":"27c0f5f8-ec02-43bd-a473-9f1aacbef3b5","resolution":{"observed_at":"2026-06-30T14:14:45.636498Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2412.11284/citation-record","integrity":"/paper/2412.11284/integrity","json":"/paper/2412.11284/citation-record.json","paper":"/paper/2412.11284"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T15:13:23.878480Z","title":"https://docs.scipy.org/doc/ scipy / reference / generated / scipy","venue":null,"work_id":"b41cc98c-8c38-4186-8b5a-948eda9f9dae","year":2024},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.069522Z"},"links":{"citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:07e59a4116796d1feeea4910fa358fe31c79f9dbc97a34e8c23773f8c613f3f1","observation_id":"9e9e6f62-941d-41d2-b138-a0aec3f04a73","resolution":{"observed_at":"2026-08-11T15:13:23.881363Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T15:13:23.871021Z","title":"https : / / elvers","venue":null,"work_id":"3a61df2b-526a-4880-9f75-01f7c8681e1a","year":2024},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.072682Z"},"links":{"citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:945e088ab8bfe3c4838790fd751430913dbc26bd42ffa1c8ea028d4665cd4036","observation_id":"580315c9-5847-41e0-a7ff-060af917b276","resolution":{"observed_at":"2026-08-11T15:13:23.873595Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T15:13:23.864090Z","title":"Real-time high speed motion prediction using fast aperture- robust event-driven visual flow","venue":null,"work_id":"82e18ac8-bc05-467b-aded-cb7e0eb64ff1","year":null},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.075634Z"},"links":{"citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:faef0ecd6acbc4e4a95afe62e24d42c6b37bb6aff82b4fd1a84ef9422b7e5f2e","observation_id":"b72f2f64-e5bb-4752-a46d-dd996e364083","resolution":{"observed_at":"2026-08-11T15:13:23.866909Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T15:13:23.857529Z","title":"Distance surface for event- based optical flow","venue":null,"work_id":"866273af-edb2-4b10-8112-7c1e1e701aa6","year":2020},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.078572Z"},"links":{"citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:7161469bb0a11c6a0fee3965b10a18b7306ea2b7339702ff2f93bad5657cbd71","observation_id":"38858529-ac8a-4443-90a9-7edcc4261828","resolution":{"observed_at":"2026-08-11T15:13:23.859957Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T15:13:23.850141Z","title":"Contour motion estimation for asynchronous event- driven cameras","venue":null,"work_id":"143034d9-fd69-4dbd-bea4-f0420dc7b2b3","year":2014},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.081439Z"},"links":{"citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:2f4450dd7a99f874b0a2fa42e3dd4d45a8997fd27f93f1a9c6bcf628188c6214","observation_id":"dd3f7c3c-d8b1-4007-9b1a-a88e7c8c1f81","resolution":{"observed_at":"2026-08-11T15:13:23.853235Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T15:13:23.842771Z","title":"Bio-inspired motion estimation with event-driven sensors","venue":null,"work_id":"026c730e-6d08-460c-a9e0-9a6d8a993d70","year":2015},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.084227Z"},"links":{"citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:329d0f7a8246257c40831aaa37ec4133088c6a28282df555ffdfefe16441df11","observation_id":"ef67800a-9d7c-4b58-9605-ca1cd88727a7","resolution":{"observed_at":"2026-08-11T15:13:23.845668Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T15:13:23.835651Z","title":"Joint direct estimation of 3d geometry and 3d motion using spatio temporal gradients","venue":null,"work_id":"0dd90aed-96dd-4259-bd55-f69e6cf0bdd9","year":2021},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.087406Z"},"links":{"citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:29cb92b8bf68e28dd1a494d4ceae9c566ff2eecad1313753435f34784478d2e8","observation_id":"3e2d67ff-5525-4c5a-9681-0fbc4987949a","resolution":{"observed_at":"2026-08-11T15:13:23.838571Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T15:13:23.828129Z","title":"Asynchronous frameless event-based optical flow","venue":null,"work_id":"434582a1-672c-4b65-ac47-6e4d386d053d","year":2012},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.091424Z"},"links":{"citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:3beb9e9eaca6bc42f4a1e825492511953af1b3186613349da0589a0ad5c811d6","observation_id":"04074efe-8dcb-431e-a825-071921606f3c","resolution":{"observed_at":"2026-08-11T15:13:23.831177Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T15:13:23.821178Z","title":"Event-based visual flow","venue":null,"work_id":"95f4e754-6935-4b06-88a5-33c7bec885dd","year":2013},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.094512Z"},"links":{"citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:96c5573c8dc2ffa9c9d1f38c9f5c8d95d2c43c7a9d9f488db685da510851e09d","observation_id":"0eb8718c-67e1-4d56-9ffd-05c784bdb931","resolution":{"observed_at":"2026-08-11T15:13:23.823825Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T15:13:23.814020Z","title":"Real- time optical flow for vehicular perception with low-and high- resolution event cameras","venue":null,"work_id":"39f21d7c-60bf-4034-a7c9-c54cf33b1585","year":2021},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.097797Z"},"links":{"citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:dd0de1030699fdb4af9d090b0404b98ca9bbe6adf79a84ef318a4f1feb153996","observation_id":"8f90bee5-4230-4278-b150-cd4d73d5118e","resolution":{"observed_at":"2026-08-11T15:13:23.816927Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T15:13:23.805962Z","title":"Structure from motion: Beyond the epipolar con- straint","venue":null,"work_id":"22515a26-a783-416b-8488-05687d7c88ac","year":2000},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.100759Z"},"links":{"citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:beedb99934cf39e0fd580698aa7d9e0bb52f0a65b51843dac36b217549f683db","observation_id":"b7d25564-c715-44bf-9ba7-7f0748093648","resolution":{"observed_at":"2026-08-11T15:13:23.809671Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T15:13:23.797978Z","title":"On event-based optical flow detection","venue":null,"work_id":"b2ea7e18-c646-438d-8b0d-7a6e3e90632a","year":2015},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.103690Z"},"links":{"citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:8de50ed11bb2582639f11ec4c6c0baf28266421c8246b1b600980c05bc9a7351","observation_id":"2e8d9379-7e7a-4eb5-8c0d-7efbfbf0ecfd","resolution":{"observed_at":"2026-08-11T15:13:23.801528Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2205.03467","last_updated":"2022-05-06T20:09:18Z","snapshot_observed_at":"2026-08-09T04:12:12.795228Z","submitted_at":"2022-05-06T20:09:18Z","title":"EVIMO2: An Event Camera Dataset for Motion Segmentation, Optical Flow, Structure from Motion, and Visual Inertial Odometry in Indoor Scenes with Monocular or Stereo Algorithms","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.03467","snapshot_observed_at":"2026-08-11T15:13:23.106736Z","title":"Evimo2: an event camera dataset for motion segmentation, optical flow, structure from motion, and visual inertial odometry in indoor scenes with monoc- ular or stereo algorithms","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.106736Z"},"links":{"cited_paper":"/paper/2205.03467","citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:f38206f1babf3e512d5f5e1b53ffdffcb64f345340607fa617f6e9e5cf848674","observation_id":"c843aa9b-2c3a-4688-a2ba-8ac028d43329","resolution":{"observed_at":"2026-08-11T15:13:23.106736Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.07761","last_updated":"2025-03-25T17:58:16Z","snapshot_observed_at":"2026-08-11T18:28:46.738534Z","submitted_at":"2024-12-10T18:55:30Z","title":"Repurposing Pre-trained Video Diffusion Models for Event-based Video Interpolation","version":2},"cited_work":{"arxiv_id":"2412.07761","doi":null,"metadata_source":"pith","pith_arxiv_id":"2412.07761","snapshot_observed_at":"2026-08-11T15:13:23.433063Z","title":"Repurposing Pre-trained Video Diffusion Models for Event-based Video Interpolation","venue":"cs.CV","work_id":"8e1b43c0-e962-4566-8535-6b3ec7fccad3","year":2024},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.110984Z"},"links":{"cited_paper":"/paper/2412.07761","citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:ccb05e77d36285d7df5c18266177cd09d1485e74217ada041de729c53711668a","observation_id":"5e3a8806-d54e-40bc-8f72-b7489860d6e0","resolution":{"observed_at":"2026-08-11T15:13:23.436924Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.13800","last_updated":"2024-03-20T17:57:02Z","snapshot_observed_at":"2026-08-01T15:23:39.719656Z","submitted_at":"2024-03-20T17:57:02Z","title":"TimeRewind: Rewinding Time with Image-and-Events Video Diffusion","version":1},"cited_work":{"arxiv_id":"2403.13800","doi":null,"metadata_source":"pith","pith_arxiv_id":"2403.13800","snapshot_observed_at":"2026-08-11T15:13:23.422467Z","title":"TimeRewind: Rewinding Time with Image-and-Events Video Diffusion","venue":"cs.CV","work_id":"0eed6142-8eac-4514-941a-f31cdc2f7e29","year":2024},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.114228Z"},"links":{"cited_paper":"/paper/2403.13800","citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:cdc27c7cbabec2ad9b65aa098a0b2b072a89b34a4e2434bd9aa1d3af980d7bf2","observation_id":"36dbd645-3304-4746-a11d-d2099f986168","resolution":{"observed_at":"2026-08-11T15:13:23.426310Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T15:13:23.789692Z","title":"Optical flow es- timation from event-based cameras and spiking neural net- works","venue":null,"work_id":"19f35271-a9dd-40bf-aafd-03ef2a8ed409","year":2023},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.117561Z"},"links":{"citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:7cfc01a672cc7029c84444feb7d40aa8bfb4516971de37bb48f5af4c09230957","observation_id":"dbc37052-fbeb-45ec-aafa-0a0ffbf7386b","resolution":{"observed_at":"2026-08-11T15:13:23.792618Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T15:13:23.782653Z","title":"Passive navigation as a pattern recogni- tion problem","venue":null,"work_id":"055f82e7-9402-4baf-ab8b-99aa796240b3","year":1995},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.120403Z"},"links":{"citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:5dad89a58a4e8122b15743b70861ee2049e75c0f584a4629920d92737709f359","observation_id":"30c2ee58-5921-44ab-9d73-6ff9e9d67b65","resolution":{"observed_at":"2026-08-11T15:13:23.785446Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T15:13:23.774555Z","title":"A unifying contrast maximization framework for event cam- eras, with applications to motion, depth, and optical flow estimation","venue":null,"work_id":"b74978f0-45b7-46eb-b60c-e47e43862866","year":null},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.123345Z"},"links":{"citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:079c8f38eeea6c735dafe259462b42e32a45bcb67e13094d6de2b24c42d020d9","observation_id":"a16bffd6-3423-4589-bda7-6667eb4eebe9","resolution":{"observed_at":"2026-08-11T15:13:23.778153Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T15:13:23.767176Z","title":"E-raft: Dense optical flow from event cam- eras","venue":null,"work_id":"724dcda8-a7b9-4e89-b2bd-0d209fdce5a0","year":2021},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.126486Z"},"links":{"citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:f51cddfe3f2ae053f222ed55c0bd1e18dfe60da5fa25768aadfe4b1e75b36cf5","observation_id":"9509b01f-079d-4b62-a11a-951828f0f93f","resolution":{"observed_at":"2026-08-11T15:13:23.769882Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T15:13:23.760195Z","title":"E-raft: Dense optical flow from event cam- eras","venue":null,"work_id":"a64135d3-ad06-4db2-a8c5-d454d8055dd1","year":2021},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.130697Z"},"links":{"citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:d62d56a63a955b886c490938516af520b9dcbeec18571e136ac3e9be8d05ef43","observation_id":"f9510d97-50a7-4f15-99df-aed9e26021db","resolution":{"observed_at":"2026-08-11T15:13:23.762948Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T15:13:23.752599Z","title":"Dense continuous-time optical flow from event cameras","venue":null,"work_id":"84f47662-51a6-4b2c-93e8-8b96b1f3ff81","year":2024},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.133820Z"},"links":{"citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:4b56b441cc616cfb70da1d6a495e6777a6406c68b7da9cf42b25dc31438b8fa7","observation_id":"ec341f40-16dc-4d0c-978d-2ce37f5f6ab7","resolution":{"observed_at":"2026-08-11T15:13:23.756037Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T15:13:23.744044Z","title":"Self-supervised learning of event-based optical flow with spiking neural networks","venue":null,"work_id":"41f76a6c-adf6-4d39-9a85-b23d62fb6743","year":2021},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.136572Z"},"links":{"citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:986186eff4b2cf83965d2676d6ecadc0ce35cea073f93b1432129ebdaca07111","observation_id":"47c06a2d-94dc-4296-9459-4985c4addb62","resolution":{"observed_at":"2026-08-11T15:13:23.747113Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.07324","last_updated":"2024-07-16T06:14:30Z","snapshot_observed_at":"2026-07-06T18:43:59.807904Z","submitted_at":"2024-07-10T02:37:36Z","title":"Event-Aided Time-to-Collision Estimation for Autonomous Driving","version":2},"cited_work":{"arxiv_id":"2407.07324","doi":null,"metadata_source":"pith","pith_arxiv_id":"2407.07324","snapshot_observed_at":"2026-08-11T15:13:23.411896Z","title":"Event-Aided Time-to-Collision Estimation for Autonomous Driving","venue":"cs.CV","work_id":"d6844f42-1e14-4274-82a3-80328d3ea003","year":2024},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.139856Z"},"links":{"cited_paper":"/paper/2407.07324","citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:f46a6c5d42b9d44d326a832ae7a19f0e0963f777537e77174a53e05dbd1efe48","observation_id":"fdc9d177-c58b-4661-8a6b-7a7cf57e42cc","resolution":{"observed_at":"2026-08-11T15:13:23.415678Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T15:13:23.736142Z","title":"Blinkflow: A dataset to push the limits of event-based optical flow estimation","venue":null,"work_id":"5f8399d8-5939-4cae-a2ee-5eacaa793bc5","year":2023},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.144017Z"},"links":{"citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:a3c9593da85df363c352eeef55fbc049b6d324a0801b08116d52e763f298e03b","observation_id":"a8d6acde-ea27-4656-8868-1c5f44381316","resolution":{"observed_at":"2026-08-11T15:13:23.739365Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T15:13:23.728111Z","title":"Tma: Temporal motion aggregation for event-based optical flow","venue":null,"work_id":"03de0485-e80f-4b84-be52-befe53f23b42","year":2023},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.147972Z"},"links":{"citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:895abbcbd29c704b86d98582ff659032b48aca1fc395c57c5625b19b721c0a57","observation_id":"90c20c9b-a693-40f2-b0fb-5fa766f14b5c","resolution":{"observed_at":"2026-08-11T15:13:23.731109Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T15:13:23.719425Z","title":"Adaptive time-slice block- matching optical flow algorithm for dynamic vision sensors","venue":null,"work_id":"3b3b9b20-c411-48ca-ad74-96129f56ba07","year":2018},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.150918Z"},"links":{"citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:331e344d2c54d1d74418f19ea1e2ff8f1d288dc70b4d07a84d165d21ccd6b6e0","observation_id":"9563011f-9fa3-4785-9f73-5ab9454c8637","resolution":{"observed_at":"2026-08-11T15:13:23.722431Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T15:13:23.710955Z","title":"Edflow: Event driven opti- cal flow camera with keypoint detection and adaptive block matching","venue":null,"work_id":"8d6224ed-73bf-40af-af29-572b9e1edf65","year":2022},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.153885Z"},"links":{"citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:90e0e0282a1c5a59a1e44e6dcef0ce73ad10742eeb5a904b9a646dafead62e3f","observation_id":"76073f0a-2126-4c66-978a-b5a8e9dccd26","resolution":{"observed_at":"2026-08-11T15:13:23.714004Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2311.18189","last_updated":"2024-05-31T01:47:50Z","snapshot_observed_at":"2026-08-07T09:51:57.764063Z","submitted_at":"2023-11-30T02:17:43Z","title":"Event-based Visual Inertial Velometer","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.18189","snapshot_observed_at":"2026-08-11T15:13:23.156723Z","title":"Event-based visual inertial velometer","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.156723Z"},"links":{"cited_paper":"/paper/2311.18189","citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:22b217acb038898a89e856eb98792302ef03064332029358baa4b28de6523560","observation_id":"df318bd9-14b4-4e7d-a26a-765a818791f3","resolution":{"observed_at":"2026-08-11T15:13:23.156723Z","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":"2026-08-11T15:13:23.702286Z","title":"Learning optical flow from event camera with rendered dataset","venue":null,"work_id":"7c4906af-4e58-4a4b-9f9f-4d5225aa5fe0","year":2023},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.159980Z"},"links":{"citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:201f63a96c5c021330ee7eb325fe149a45f3782259e53aa8a52109d471697855","observation_id":"7e3a7904-7186-4842-b1fc-d4a5c1439fae","resolution":{"observed_at":"2026-08-11T15:13:23.705966Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T15:13:23.693489Z","title":"Efficient meshflow and opti- cal flow estimation from event cameras","venue":null,"work_id":"e785e420-dbc2-40de-aad8-a6a369162931","year":2024},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.162972Z"},"links":{"citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:4392b82417ab78e391ec865d45509b81cf9d9f705be01e3460e077c29caf3636","observation_id":"261273da-bae4-4ce2-b888-adb71df54873","resolution":{"observed_at":"2026-08-11T15:13:23.696764Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2202.07123","last_updated":"2022-11-29T07:07:37Z","snapshot_observed_at":"2026-08-11T06:11:03.118654Z","submitted_at":"2022-02-15T01:39:07Z","title":"Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.07123","snapshot_observed_at":"2026-08-11T15:13:23.165906Z","title":"Rethinking network design and local geometry in point cloud: A simple residual mlp framework","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.165906Z"},"links":{"cited_paper":"/paper/2202.07123","citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:e9b15cde61dcb282a71592683c173b3afe99a8ed866cab7385ebc8ecfca4540f","observation_id":"49f9ce32-eb2b-4873-984d-25381a88dbcb","resolution":{"observed_at":"2026-08-11T15:13:23.165906Z","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":"2026-08-11T15:13:23.684770Z","title":"Lifetime estimation of events from dynamic vision sensors","venue":null,"work_id":"c9780b5b-39d6-43db-ae53-5050fbc8496e","year":2015},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.169211Z"},"links":{"citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:54c7f3c423743e549b2c1988a0c583853cd267f9f15ea944805bb4cd7fe38f4b","observation_id":"d8dce70b-e3ea-43c1-8744-0b2612c0df85","resolution":{"observed_at":"2026-08-11T15:13:23.688053Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T15:13:23.676053Z","title":"Diffposenet: Di- rect differentiable camera pose estimation","venue":null,"work_id":"e5435408-8445-48a1-9b50-d6b5ea4533c6","year":2022},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.173008Z"},"links":{"citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:1477b8a5e5a714c2aa9b73c6e7a1b2a63374e8acd406c8877d931a37e8683934","observation_id":"bc9bdf16-1e21-41d9-9e8a-074af9144e97","resolution":{"observed_at":"2026-08-11T15:13:23.679398Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T15:13:23.667727Z","title":"Taming contrast max- imization for learning sequential, low-latency, event-based optical flow","venue":null,"work_id":"4df553f9-e47f-4fd4-b0b2-b04349180c28","year":2023},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.176086Z"},"links":{"citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:cde7774fc67e6705265aa78199cdb97078be6e370c712661b8ef05eb9141c6e2","observation_id":"3a617136-4574-4e14-8e11-5699e3a23827","resolution":{"observed_at":"2026-08-11T15:13:23.670660Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T15:13:23.659397Z","title":"Vertical landing for micro air vehicles using event-based optical flow","venue":null,"work_id":"bfc6bb1c-c971-4c70-83dd-400ece9ae739","year":2018},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.179281Z"},"links":{"citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:e733484fe654c9bda980b76665b6114afecdf45cb06ec6e2f7e38bc4d905ec37","observation_id":"faeb8c0f-8aaf-4c86-8f43-18ea0dc4bbc8","resolution":{"observed_at":"2026-08-11T15:13:23.662442Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T15:13:23.651202Z","title":"Event-based temporally dense optical flow estimation with sequential learning","venue":null,"work_id":"6cb77d50-8ba0-4ddd-9b08-7e966502f1df","year":2023},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.182070Z"},"links":{"citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:633a54e07d2bfd3a45e00f849d4994622ca34513cba40872cc65de2a3ecea222","observation_id":"aeae0475-83df-4eab-9c33-5625abc3d503","resolution":{"observed_at":"2026-08-11T15:13:23.654214Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T15:13:23.184994Z","title":"Pointnet: Deep learning on point sets for 3d classification and segmentation","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.184994Z"},"links":{"citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:0ae752cf106e7481390f6be8f6b0f569e367e83790caffa08c211cbaac395064","observation_id":"14a255a8-62e6-416a-a65a-d2703f2a6414","resolution":{"observed_at":"2026-08-11T15:13:23.184994Z","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":"2026-08-11T15:13:23.188130Z","title":"Pointnet++: Deep hierarchical feature learning on point sets in a metric space","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.188130Z"},"links":{"citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:a4757debdd6c1dc3763e9335d96af98c19babe7e72286a8219bf030901a0137a","observation_id":"08f01142-702b-4d3e-b339-8393b886d706","resolution":{"observed_at":"2026-08-11T15:13:23.188130Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.07189","last_updated":"2024-01-23T08:20:05Z","snapshot_observed_at":"2026-07-06T16:30:55.043821Z","submitted_at":"2023-10-11T04:38:21Z","title":"SpikePoint: An Efficient Point-based Spiking Neural Network for Event Cameras Action Recognition","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.07189","snapshot_observed_at":"2026-08-11T15:13:23.191123Z","title":"Spikepoint: An efficient point-based spiking neural network for event cam- eras action recognition","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.191123Z"},"links":{"cited_paper":"/paper/2310.07189","citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:3e0e4b7cc7335fdbce28b6c7cb7a1583100a22d4373d194fe1c43eef47e8d037","observation_id":"d634d419-b0cf-4a6f-9a15-504fed34e6cd","resolution":{"observed_at":"2026-08-11T15:13:23.191123Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.06116","last_updated":"2025-03-28T14:25:05Z","snapshot_observed_at":"2026-08-04T06:39:27.701558Z","submitted_at":"2024-05-09T21:47:46Z","title":"Rethinking Efficient and Effective Point-based Networks for Event Camera Classification and Regression: EventMamba","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.06116","snapshot_observed_at":"2026-08-11T15:13:23.194515Z","title":"Rethinking efficient and effective point- based networks for event camera classification and regres- sion: Eventmamba","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.194515Z"},"links":{"cited_paper":"/paper/2405.06116","citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:502e1470971128287175881325c7f07349d9e73a9b38ce12780db811080656bc","observation_id":"6678e844-ce8d-4ab8-947d-e697d715ad2e","resolution":{"observed_at":"2026-08-11T15:13:23.194515Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.12239","last_updated":"2024-10-09T12:59:51Z","snapshot_observed_at":"2026-08-05T10:39:44.606648Z","submitted_at":"2024-07-17T01:11:20Z","title":"Motion and Structure from Event-based Normal Flow","version":3},"cited_work":{"arxiv_id":"2407.12239","doi":null,"metadata_source":"pith","pith_arxiv_id":"2407.12239","snapshot_observed_at":"2026-08-11T15:13:23.378515Z","title":"Motion and Structure from Event-based Normal Flow","venue":"cs.CV","work_id":"f60b563b-9356-4ef9-8f79-0e4b2e0bd3d1","year":2024},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.198952Z"},"links":{"cited_paper":"/paper/2407.12239","citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:317910694aa0843c953117574a60079a748f7986bc0f25a500b8c3374820ef8b","observation_id":"98b331b9-0480-4d7d-b593-d76ea8a4eab2","resolution":{"observed_at":"2026-08-11T15:13:23.381691Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T15:13:23.633374Z","title":"Eventnet: Asynchronous recursive event processing","venue":null,"work_id":"490c0d7b-804d-4719-bd26-2d13110d2dd2","year":2019},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.202078Z"},"links":{"citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:990bb01d02f2ffa85d9d364077530c0244e8b36e73424b75822e0dc66fda9a23","observation_id":"b072d879-10b3-4c26-9b13-4191ce0ceb0e","resolution":{"observed_at":"2026-08-11T15:13:23.636858Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T15:13:23.623853Z","title":"Fast event-based optical flow estimation by triplet matching","venue":null,"work_id":"d8bce816-14a6-4a97-9125-b17c4a39f800","year":2022},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.205455Z"},"links":{"citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:e82bcce702dc0c4952d690ecdaae6ea77c3754cea92feefb144dd08e241eb984","observation_id":"56d89dc1-d807-4e75-a2a9-0b79c08d0053","resolution":{"observed_at":"2026-08-11T15:13:23.627348Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T15:13:23.615543Z","title":"Secrets of event-based optical flow","venue":null,"work_id":"dfb82cd2-3bca-4c3b-a27b-247c5422fd59","year":2022},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.208314Z"},"links":{"citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:e8c2658e10dcc0cdd95013ee798c4cd5b7b8c8aa4b731126037212004d37883d","observation_id":"e44256e3-46ab-43bf-b8d1-aa61a8c1beb5","resolution":{"observed_at":"2026-08-11T15:13:23.618758Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1705.09792","last_updated":"2018-02-25T23:42:06Z","snapshot_observed_at":"2026-08-06T05:46:16.150162Z","submitted_at":"2017-05-27T09:04:55Z","title":"Deep Complex Networks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1705.09792","snapshot_observed_at":"2026-08-11T15:13:23.211474Z","title":"Deep complex networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.211474Z"},"links":{"cited_paper":"/paper/1705.09792","citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:8f750f8a55d08806abfa4bc470d6545786d68ee389bbba7ab591b1df2301a2fb","observation_id":"6f462787-b230-492a-95f4-5c863b4fe36d","resolution":{"observed_at":"2026-08-11T15:13:23.211474Z","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":"2026-08-11T15:13:23.606385Z","title":"Learning dense and continuous optical flow from an event camera","venue":null,"work_id":"b595748c-17f3-4093-b76c-a0aff5d5e8b9","year":2022},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.214368Z"},"links":{"citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:62791ebab998b714ae129a7639044067f00ed7ffeaa1a4a2c5830b3ca70758a1","observation_id":"2af4c8c2-a2f0-4087-93ad-782fe672c3bf","resolution":{"observed_at":"2026-08-11T15:13:23.609514Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T15:13:23.597921Z","title":"Rpeflow: Multimodal fusion of rgb-pointcloud-event for joint optical flow and scene flow estimation","venue":null,"work_id":"b17207a7-2c6c-49f9-b3f8-e85954061506","year":2023},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.217039Z"},"links":{"citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:b5485316ca685420703968f2ffd08887958db094d7d044f11f2dce6c66f73c52","observation_id":"f8c783c1-6ec2-4079-bca8-4afe30aab232","resolution":{"observed_at":"2026-08-11T15:13:23.601148Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T15:13:23.589118Z","title":"Event-based optical flow via trans- forming into motion-dependent view","venue":null,"work_id":"9a255261-1566-4c3a-88fc-6c788c1f2dee","year":2024},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.220215Z"},"links":{"citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:3579e1e9e0e2f401c1977e5acb7d1afd140506162441059c87128b8ed0ae1b1b","observation_id":"db56722e-6c55-4379-bfd6-d9c1f5a9e934","resolution":{"observed_at":"2026-08-11T15:13:23.592631Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T15:13:23.222742Z","title":"Space-time event clouds for gesture recognition: From rgb cameras to event cameras","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.222742Z"},"links":{"citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:3d9a3f9aec5122c79b5f4dec7eacb69e9f33f5bf3041e79d6f55ba46439ee376","observation_id":"b6e8ea0b-45be-41d8-a4c8-6cd566dcf861","resolution":{"observed_at":"2026-08-11T15:13:23.222742Z","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":"2026-08-11T15:13:23.575430Z","title":"Mpct: Multiscale point cloud trans- former with a residual network","venue":null,"work_id":"a4df23d2-1cd4-49e1-91fe-42defbb8f24f","year":2023},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.225421Z"},"links":{"citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:3cf72fe516f91190ba016cfb67a009689961cb868ed1bf48b4bdb46ddf653138","observation_id":"d55c98d6-954d-43b4-8ace-08b83f91e4cf","resolution":{"observed_at":"2026-08-11T15:13:23.578769Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T15:13:23.567282Z","title":"Lightweight event-based optical flow estimation via iterative deblurring","venue":null,"work_id":"c6a109eb-2fcb-4b41-bf6d-095556c0be50","year":2024},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.228027Z"},"links":{"citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:92156c75708bb070c30476210e8006a2637051ac67b02600f0d9cf7eed66e284","observation_id":"901473d7-af90-43b5-855a-e81d6d8cac3d","resolution":{"observed_at":"2026-08-11T15:13:23.570427Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.02972","last_updated":"2024-10-14T01:07:01Z","snapshot_observed_at":"2026-08-03T01:34:44.739645Z","submitted_at":"2024-06-05T06:06:03Z","title":"Event3DGS: Event-Based 3D Gaussian Splatting for High-Speed Robot Egomotion","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.02972","snapshot_observed_at":"2026-08-11T15:13:23.230926Z","title":"Event3dgs: Event-based 3d gaussian splatting for fast ego- motion","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.230926Z"},"links":{"cited_paper":"/paper/2406.02972","citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:88b8a920e59c832e647e24ad32e8be20b3d5563b98e27a89cef96851f82355a5","observation_id":"67a5e6b8-f1de-4db0-a47d-b31c1a82a6c3","resolution":{"observed_at":"2026-08-11T15:13:23.230926Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.20421","last_updated":"2024-07-29T21:22:53Z","snapshot_observed_at":"2026-08-07T15:42:15.700723Z","submitted_at":"2024-07-29T21:22:53Z","title":"Event-based Optical Flow on Neuromorphic Processor: ANN vs. SNN Comparison based on Activation Sparsification","version":1},"cited_work":{"arxiv_id":"2407.20421","doi":null,"metadata_source":"pith","pith_arxiv_id":"2407.20421","snapshot_observed_at":"2026-08-11T15:13:23.356386Z","title":"Event-based Optical Flow on Neuromorphic Processor: ANN vs. SNN Comparison based on Activation Sparsification","venue":"cs.NE","work_id":"fc28707e-ab88-4118-9dfd-890469638f46","year":2024},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.234230Z"},"links":{"cited_paper":"/paper/2407.20421","citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:3daca243774f451341ed0541a4fd3354c32cfff9a38c046d6bd4efaae9d47e40","observation_id":"30b67ec6-cef4-482a-9b27-b7d22ec34f7d","resolution":{"observed_at":"2026-08-11T15:13:23.359591Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T15:13:23.557945Z","title":"Modeling point clouds with self-attention and gumbel subset sampling","venue":null,"work_id":"f1549ec5-3323-47e5-897f-515702a665e0","year":2019},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.237175Z"},"links":{"citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:ae2457ba91e6e89d06ecf78a11ba9dd62522e1a29f7d5ec79ebb93df3ce23916","observation_id":"f0a9c13b-c327-4cc0-b5be-98cbb9ae3f67","resolution":{"observed_at":"2026-08-11T15:13:23.561905Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.05033","last_updated":"2025-05-13T12:00:41Z","snapshot_observed_at":"2026-07-06T15:52:28.616834Z","submitted_at":"2023-07-11T06:15:12Z","title":"Towards Anytime Optical Flow Estimation with Event Cameras","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.05033","snapshot_observed_at":"2026-08-11T15:13:23.239764Z","title":"To- wards anytime optical flow estimation with event cameras","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.239764Z"},"links":{"cited_paper":"/paper/2307.05033","citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:f2b18119675ea7fbae20e18a16e9ff5f336aef2fb5808e5ba651debc439d16a2","observation_id":"4e0ee1cf-03c6-41b9-88e3-eedbac71ec3b","resolution":{"observed_at":"2026-08-11T15:13:23.239764Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.08300","last_updated":"2025-01-22T03:19:36Z","snapshot_observed_at":"2026-08-07T22:53:51.055581Z","submitted_at":"2024-05-14T03:50:07Z","title":"Vector-Symbolic Architecture for Event-Based Optical Flow","version":3},"cited_work":{"arxiv_id":"2405.08300","doi":null,"metadata_source":"pith","pith_arxiv_id":"2405.08300","snapshot_observed_at":"2026-08-11T15:13:23.338528Z","title":"Vector-Symbolic Architecture for Event-Based Optical Flow","venue":"cs.CV","work_id":"4277120d-c7f2-4140-8df7-5767ffd51582","year":2024},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.242612Z"},"links":{"cited_paper":"/paper/2405.08300","citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:3307068477def2817544dd81521afec15e17d5a2373b000d750d58e03beee772","observation_id":"472c2bc1-7095-4031-b171-0a3aa59b4590","resolution":{"observed_at":"2026-08-11T15:13:23.341590Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2311.00187","last_updated":"2024-05-07T02:25:01Z","snapshot_observed_at":"2026-07-06T16:41:27.099792Z","submitted_at":"2023-10-31T23:19:30Z","title":"Decodable and Sample Invariant Continuous Object Encoder","version":4},"cited_work":{"arxiv_id":"2311.00187","doi":null,"metadata_source":"pith","pith_arxiv_id":"2311.00187","snapshot_observed_at":"2026-08-11T15:13:23.325827Z","title":"Decodable and Sample Invariant Continuous Object Encoder","venue":"cs.CV","work_id":"be030455-3b49-4fce-b1ec-f174c56f1fb2","year":2023},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.246074Z"},"links":{"cited_paper":"/paper/2311.00187","citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:57a1947d81bd7fc6cb4df40bb73eeaa76e1c72b95efa8d563ce7d9ec8df4703f","observation_id":"1290476e-57c1-4624-a8e5-b9b7cd5db270","resolution":{"observed_at":"2026-08-11T15:13:23.330624Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T15:13:23.549507Z","title":"A linear time and space lo- cal point cloud geometry encoder via vectorized kernel mix- ture (VecKM)","venue":null,"work_id":"2717b867-0da7-4072-999e-01ead0ac9233","year":null},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.249171Z"},"links":{"citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:3133b8017579c18c5c2655a5feca69b636eaaa8c44573826c3f3851c355b54b7","observation_id":"f7b967b2-1ac5-476d-8543-7f65e74c1300","resolution":{"observed_at":"2026-08-11T15:13:23.552630Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T15:13:23.541744Z","title":"Cross-modal learning for optical flow estimation with events","venue":null,"work_id":"e0a23fc8-a3ec-482e-ac98-b8593a877284","year":2024},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.252215Z"},"links":{"citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:d8c7ca297ac95f25a1cb88c7a9d37c0dea140bde0d40b33af579f690fd64a333","observation_id":"4088b887-d09e-4377-934c-e36ffc214779","resolution":{"observed_at":"2026-08-11T15:13:23.544728Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T15:13:23.533394Z","title":"Starting from non-parametric networks for 3d point cloud analysis","venue":null,"work_id":"b6f4be08-9d90-4680-8ffd-83fac7908818","year":2023},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.255941Z"},"links":{"citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:9cdf7036f690366d7979d08638ba24518980101045ac76a9fcd3dd4188d2f574","observation_id":"e8ef57db-9989-4ae0-b178-a312c7c26517","resolution":{"observed_at":"2026-08-11T15:13:23.536427Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T15:13:23.525521Z","title":"Event-based optical flow estimation with spatio-temporal backpropagation trained spiking neural network","venue":null,"work_id":"3492cb46-2a1f-46bb-9aa8-dd415e22f25b","year":2023},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.258829Z"},"links":{"citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:93b9b1c3d3874f87916dd37f5dbffe8c057b4956c12bec0b0271be6cf9f5b386","observation_id":"592d0296-ff2d-483b-8712-545e3648593e","resolution":{"observed_at":"2026-08-11T15:13:23.528425Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T15:13:23.261797Z","title":"Point transformer","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.261797Z"},"links":{"citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:543706359604e233d5563a7351ab274e54118b6830bd5fa4a5336faf5e4da668","observation_id":"e9882cb3-e4e0-4995-bd31-ec543c4554e7","resolution":{"observed_at":"2026-08-11T15:13:23.261797Z","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":"2026-08-11T15:13:23.512821Z","title":"Learning optical flow from continu- ous spike streams","venue":null,"work_id":"c9f6dfbe-b021-4e03-a255-20049586b486","year":2022},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.264632Z"},"links":{"citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:8db0af1501369d6f1495c061cddf933e8b43296fac3d67fe8c1d731386ab44bd","observation_id":"55b83fc9-5368-4798-804b-f8ae4039e2b1","resolution":{"observed_at":"2026-08-11T15:13:23.516514Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T15:13:23.504167Z","title":"The multi- vehicle stereo event camera dataset: An event camera dataset for 3d perception","venue":null,"work_id":"dca12914-40c8-4939-9011-0abdc3c4d5d3","year":2018},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.267532Z"},"links":{"citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:905a5da0846874889391278ab9a05e6bc744411cc3a5f157c7d4331bacbbd87e","observation_id":"6807e95a-c25a-49a8-8502-fb3a3f3c2ef9","resolution":{"observed_at":"2026-08-11T15:13:23.507315Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1802.06898","last_updated":"2018-08-13T15:32:01Z","snapshot_observed_at":"2026-07-06T06:24:15.593553Z","submitted_at":"2018-02-19T22:47:52Z","title":"EV-FlowNet: Self-Supervised Optical Flow Estimation for Event-based Cameras","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1802.06898","snapshot_observed_at":"2026-08-11T15:13:23.270582Z","title":"Ev-flownet: Self-supervised optical flow estimation for event-based cameras","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.270582Z"},"links":{"cited_paper":"/paper/1802.06898","citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:5da26b223f519846a776868b008138c0924a242a4d401c29a62c8e2af2ff28b6","observation_id":"a0a93122-188e-42de-bf8e-32f57e69967e","resolution":{"observed_at":"2026-08-11T15:13:23.270582Z","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":"2026-08-11T15:13:23.496443Z","title":"Unsupervised event-based learning of optical flow, depth, and egomotion","venue":null,"work_id":"f290c2af-3566-4563-ad11-195a00164102","year":2019},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.273935Z"},"links":{"citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:20f30eaf073ac8fdb77fd99ef71e0795ead0f508896de21da07e319e598ab45a","observation_id":"89d282e2-aa03-4a38-b16b-bad895b93234","resolution":{"observed_at":"2026-08-11T15:13:23.499539Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T15:13:23.488407Z","title":"These visualiza- tions showcase predictions from models trained on each of the three datasets","venue":null,"work_id":"a419660f-b69c-4d6b-87a4-18278aac33cd","year":null},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.277356Z"},"links":{"citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:a98069bfa068b38bbcb49def7b4a2f174e8186f62c7adf8c79e645c6129d0f8c","observation_id":"2aa9447f-0667-4edc-aaa5-97eb20a00c5f","resolution":{"observed_at":"2026-08-11T15:13:23.491469Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T15:13:23.480480Z","title":"MVSEC & EVIMO2 both provide frame-based forward optical flows in the distorted camera coordinates","venue":null,"work_id":"8d75d737-33d6-453f-9fab-4b934c4c059d","year":null},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.280313Z"},"links":{"citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:51be6fa1db66fbf21d4e8115accee1739d50386b94e8059e13ec08c31392776c","observation_id":"72efb116-16b8-42b2-a04f-949e8ebc4968","resolution":{"observed_at":"2026-08-11T15:13:23.483436Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T15:13:23.471988Z","title":"The resulting flows are then scaled such that their unit is in pixels per second","venue":null,"work_id":"fa60fe10-9163-4a7f-a069-025470a73d64","year":null},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.283378Z"},"links":{"citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:b2a5a09de39d646a18c4dd7fb24b37d11b2755196fab0bc4a5f2099210024917","observation_id":"bd786f83-976e-40f8-8c5f-af4bddaca4d9","resolution":{"observed_at":"2026-08-11T15:13:23.475828Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T15:13:23.463350Z","title":"The models are trained on EVIMO2-imo training set to better capture the impact of the ablated factors","venue":null,"work_id":"af37d5ef-e1e7-4662-ab86-daea79f7d9f1","year":null},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.287398Z"},"links":{"citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:ac0f1f95e5d7945042799e573b099aac7aad7ceb5ddbb6c2b90b8edc90888b82","observation_id":"f1463c9f-2adb-473e-b0a2-60fd57461032","resolution":{"observed_at":"2026-08-11T15:13:23.466345Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T15:13:23.455986Z","title":null,"venue":null,"work_id":"8955bb96-6b76-4693-be4b-db1fcdb3b0dd","year":null},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.290658Z"},"links":{"citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:6fe077103fb8134e092d44309085ddc577b05d9bd49828eedca58b5cfe465b3c","observation_id":"ebe7a9d8-cb9e-47e8-b29a-eea95be346ec","resolution":{"observed_at":"2026-08-11T15:13:23.458632Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-11T15:13:23.447442Z","title":null,"venue":null,"work_id":"02710ae5-a3f9-497c-bfed-e7884fa27b7a","year":null},"citing_paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-11T15:13:23.293780Z"},"links":{"citing_paper":"/paper/2412.11284"},"observation_digest":"sha256:601b672ff2735b1f31113cc82d2015fd81c1d2ba55ad1ae0bfc41dacbf21759a","observation_id":"9f027222-d304-46a7-b70d-62acb71ddec6","resolution":{"observed_at":"2026-08-11T15:13:23.451044Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2412.11284","last_updated":"2024-12-15T19:09:45Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-11T15:03:59.854106Z","submitted_at":"2024-12-15T19:09:45Z","title":"Learning Normal Flow Directly From Event Neighborhoods"},"reference_resolution":{"displayed":72,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":15,"verified_exact":7,"verified_fuzzy":49},"total_outbound_references":72},"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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 72 of 72 outbound references and 4 inbound Pith citation observations for arXiv:2412.11284."}