{"as_of":"2026-08-19T15:19:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:90b9de0b41ab7f47d025d077ba54142b5809eaa5f451dfd4c731cdbd0a716008","coverage":[{"denominator":80,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":80,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T16:42:09.940464Z","state":"measured"},{"denominator":80,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":80,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-19T06:32:44.657259+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2509.02545/citation-record","integrity":"/paper/2509.02545/integrity","json":"/paper/2509.02545/citation-record.json","paper":"/paper/2509.02545"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T16:42:09.527416Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.527416Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:3514aa23dc99961327d4b993f0d4f6dfa3c3627fb7916f922bf96822bc2503cb","observation_id":"86839f00-29df-4861-8faf-2206bff389fe","resolution":{"observed_at":"2026-08-15T16:42:09.527416Z","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":"2026-08-15T16:42:11.344531Z","title":"Slot-guided adaptation of pre-trained diffusion models for object-centric learning and compositional generation","venue":null,"work_id":"187c460a-0e85-4b91-b401-20c7ef71df4d","year":2025},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.534725Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:7aa8d765b625a1ad2f786ba651d6a80532d8efd261a7922b5d4c62893d34eeee","observation_id":"bc6bd557-b140-42ba-9f8a-3e203e61588b","resolution":{"observed_at":"2026-08-15T16:42:11.355126Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:11.322333Z","title":"An overview of optical flow-based approaches for motion segmentation","venue":null,"work_id":"708fa411-8ab3-44ff-8031-a37e978c7435","year":2019},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.539714Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:c209b7b479f1b31f84fbae32aa3be68807006b18f485349e7b9d189b0a24c111","observation_id":"65207a58-3e2d-4f16-a539-72387dabb2a8","resolution":{"observed_at":"2026-08-15T16:42:11.329737Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:11.301600Z","title":"o rkay Aydemir, Weidi Xie, and Fatma G \\","venue":null,"work_id":"ac3835d0-18ec-401e-9776-af0f643a2b35","year":2023},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.544623Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:311cb39a49eab9bf98699590839e1b8e1e0bd2ddb3698448fea61aaaa53abf2f","observation_id":"818451d0-aae1-45f1-abbd-39c2ac3265b2","resolution":{"observed_at":"2026-08-15T16:42:11.307740Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:11.282990Z","title":"Discovering objects that can move","venue":null,"work_id":"220155a2-0837-415e-9689-d6a2d6f35e08","year":2022},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.548774Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:8175ef4d3aef4d0cf236d8b811b2b3a3ec752a3f4cf0cb33b9280403f6da3953","observation_id":"04bdc8f0-7f54-465e-bfc2-183b95968006","resolution":{"observed_at":"2026-08-15T16:42:11.287762Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:11.268817Z","title":"Object discovery from motion-guided tokens","venue":null,"work_id":"e6d65335-6127-4f20-92a8-803cef5432a8","year":2023},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.552666Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:c70ca95b4ca7848e9dc4c38f3a0827ed45feec5e2089707c09713dc497856720","observation_id":"ace51740-8698-41ed-8302-bb87f48c549c","resolution":{"observed_at":"2026-08-15T16:42:11.273199Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:11.253249Z","title":"Black and David J","venue":null,"work_id":"73fd29b5-33e5-4ac9-887e-e80512ae8803","year":2000},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.558497Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:bdacdbb474e274984a28656251d12cb54d67fa8855c6a16d64a76b7ca4bc9ea6","observation_id":"ee1354dc-fa46-49ce-81ea-662d8030d191","resolution":{"observed_at":"2026-08-15T16:42:11.258866Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:11.234411Z","title":"YOLACT : R eal-time instance segmentation","venue":null,"work_id":"c3881f92-1111-42d2-83d0-a019074272bf","year":2019},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.563380Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:a7f4107626dfa7bb3b36524264ca7328f8f8d9bfd430f63da6ecef8a32574709","observation_id":"a8e4bdbc-f4e6-47c9-b840-cdc8919fb0fe","resolution":{"observed_at":"2026-08-15T16:42:11.241043Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:11.219984Z","title":"o dermann, David Br \\","venue":null,"work_id":"1dc6f113-74be-4f3d-8219-fc1d0ea2a833","year":2024},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.566994Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:ae1b8b6818667c410dc5a0ed02f896c2365896092d4d9946437f8a0aad472824","observation_id":"3ff9bb75-f43f-4d4f-9bf8-c148c468b0a2","resolution":{"observed_at":"2026-08-15T16:42:11.224973Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:11.197767Z","title":"Object segmentation by long term analysis of point trajectories","venue":null,"work_id":"65ece14a-796b-4048-ab45-b2a248b0c00b","year":2010},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.571180Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:20b87cf43e67af97c94782f6302a1028410c9f0c7410dda352c8cc2c8dadabba","observation_id":"39cbfda9-99d6-4f94-8b5e-b811dab0e077","resolution":{"observed_at":"2026-08-15T16:42:11.205229Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1901.11390","last_updated":"2019-01-22T18:55:34Z","snapshot_observed_at":"2026-08-14T17:27:29.664717Z","submitted_at":"2019-01-22T18:55:34Z","title":"MONet: Unsupervised Scene Decomposition and Representation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1901.11390","snapshot_observed_at":"2026-08-15T16:42:09.575272Z","title":"MONet : U nsupervised scene decomposition and representation","venue":null,"work_id":null,"year":1901},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.575272Z"},"links":{"cited_paper":"/paper/1901.11390","citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:93b9227c342b6ff28f09efdca938a2f62132f54e1a20bb9244bab5b0ba9048b0","observation_id":"af3a67f0-1265-4c9b-9770-9db2e0be4d3e","resolution":{"observed_at":"2026-08-15T16:42:09.575272Z","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":"2026-08-15T16:42:11.171501Z","title":"Cascade R-CNN : H igh quality object detection and instance segmentation","venue":null,"work_id":"eb11b250-f901-4107-892e-159195b2864f","year":2019},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.585023Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:528ed2c794f75a20148d4acf4689999802344b554ccb62dfea259df72ac77639","observation_id":"ebb33809-d962-4cdc-9f15-2237ff5674da","resolution":{"observed_at":"2026-08-15T16:42:11.178389Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:11.150738Z","title":null,"venue":null,"work_id":"be6427ee-b52d-48b0-a7db-d166ff6362e9","year":2013},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.589157Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:463a3eb703f73a590a77423c37ef117d355a56643a35009ccfc63d976c88a086","observation_id":"623e36fe-6e8f-4c2b-8799-a3ed3819c6ed","resolution":{"observed_at":"2026-08-15T16:42:11.161712Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:09.593287Z","title":"Emerging properties in self-supervised vision transformers","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.593287Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:d069ef52562cf765611322986b7679b79851df55a2143b2f3db12e0e2a83693d","observation_id":"8c87f7be-24db-4203-9051-cb59dac6d1cc","resolution":{"observed_at":"2026-08-15T16:42:09.593287Z","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":"2026-08-15T16:42:11.123318Z","title":"Guess what moves: U nsupervised video and image segmentation by anticipating motion","venue":null,"work_id":"c539bd65-ebac-448c-906c-5e7da49477db","year":2022},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.597182Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:f2e30429c5c55bb1ecd6fe9a36b6297bc0244fc0b95cca5447d3d81658665142","observation_id":"cf1a3cb7-0bb7-4d9c-a83b-52ab960e8246","resolution":{"observed_at":"2026-08-15T16:42:11.127894Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:11.104720Z","title":"The C ityscapes dataset for semantic urban scene understanding","venue":null,"work_id":"42933885-0f43-41d8-ac38-4b045f7a9cbb","year":null},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.601544Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:c15fae9747760e52e69ff74831253e96c8f4e97a990bd9892faed24adfdb8351","observation_id":"cab7e6ef-b6ce-427e-9898-2ffa564d3bb6","resolution":{"observed_at":"2026-08-15T16:42:11.111500Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:11.083172Z","title":"Motion competition: A variational approach to piecewise parametric motion segmentation","venue":null,"work_id":"649ecdce-644c-4d4f-aff5-5dac0fbb0188","year":2005},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.606412Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:85e156e1c1ee3ad50edf19d7cb73390e1b63d22c44e78dd5b9628eb6d1fc63d1","observation_id":"740623a6-8f0f-428d-9297-0965c0697f83","resolution":{"observed_at":"2026-08-15T16:42:11.090233Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:11.057561Z","title":"Towards segmenting anything that moves","venue":null,"work_id":"8f20c46b-4fd3-429c-8c13-2ebf72d44e73","year":2019},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.610492Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:b7406b03707ad71727cd8aeb278a5e839bf2547c4570c6a8ce9523ba52f34ef5","observation_id":"ea10d2c4-5a0f-4520-8f7b-7dae5dc67086","resolution":{"observed_at":"2026-08-15T16:42:11.065977Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:11.033454Z","title":"A simple and efficient connected components labeling algorithm","venue":null,"work_id":"92ce8f15-cb32-4c2e-bb2f-4013ba4b0713","year":1999},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.615239Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:cd8fcd4c112e5f0b52995685be8e6c8341f9de19ac5c463b96da5a9f6c1f3131","observation_id":"9f16c4d3-e644-41ad-bf6c-b31691c46464","resolution":{"observed_at":"2026-08-15T16:42:11.038562Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:11.011660Z","title":"Mozer, and Thomas Kipf","venue":null,"work_id":"d62f79db-1d41-4b2c-bb66-ef4d944eb777","year":2022},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.626841Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:fa8decc4c44eb2a46d6f7b33bfe2f059fd763079c88d41d39abcb1c7b1175251","observation_id":"74b5cc25-3bd0-4575-8f15-1fd78b2e0d59","resolution":{"observed_at":"2026-08-15T16:42:11.017795Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:10.989672Z","title":"Genesis-v2: Inferring unordered object representations without iterative refinement","venue":null,"work_id":"20c492a4-787d-4f21-9dd7-8dc16616a63e","year":2021},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.632610Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:7a9bdf20146c9f5e3bb9e1cb9e2c2125cf7e89dfb965696497732d34769155e5","observation_id":"a8845471-1062-4c5d-afbe-b2e2967e1233","resolution":{"observed_at":"2026-08-15T16:42:10.995265Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:10.971956Z","title":"Kosiorek, Oiwi Parker Jones, and Ingmar Posner","venue":null,"work_id":"1636fb93-cb32-47a6-a26a-5430b904fb3d","year":2020},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.638416Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:9177971abfaeda0fe504ea8a65bf14321d34b89396551ee80336063c4db638f7","observation_id":"458d1e78-2a4e-4c48-a701-a91f13e72aea","resolution":{"observed_at":"2026-08-15T16:42:10.978039Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:10.952725Z","title":"Obstacle detection by evaluation of optical flow fields from image sequences","venue":null,"work_id":"034ccc47-3bcc-4baa-b17d-c92b576dd819","year":1991},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.643605Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:847c77f1e325e52260a13e5fc3905c42ce85232e4d4ddef838915cd524fe5dbe","observation_id":"91831ebc-e07a-4a20-b5fa-d279d3157cce","resolution":{"observed_at":"2026-08-15T16:42:10.958624Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:10.938740Z","title":null,"venue":null,"work_id":"f3f78ade-3c6a-4089-a845-c700e7783e08","year":2016},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.649516Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:4863e2d5b472c5d48907f32035505cd4f422fdd0720f1aff99beeeed6f91071c","observation_id":"baa808e6-4522-4f9c-9d0e-290641dc8b25","resolution":{"observed_at":"2026-08-15T16:42:10.943009Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:10.923157Z","title":"Vision meets robotics: T he KITTI dataset","venue":null,"work_id":"d0b43070-1fdd-4471-9fee-4c3987915a77","year":2013},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.653788Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:00e75d2a0e967ec3717b06f126bb1974a8bf7fc625b35f214c8cccc225c3d7d0","observation_id":"9a2cecd4-ad96-441f-b37b-361be2b23fc6","resolution":{"observed_at":"2026-08-15T16:42:10.927735Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:10.908811Z","title":"Multi-object representation learning with iterative variational inference","venue":null,"work_id":"be801264-1100-4691-9ec9-b3c353e1c5ee","year":2019},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.657708Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:b94226cb50e9a0fe5d02f68eb0e4555c07525be7368c532771c80989bdc900ce","observation_id":"d7111ae7-7214-4e2d-a0c2-21ebedae8832","resolution":{"observed_at":"2026-08-15T16:42:10.913086Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:10.888562Z","title":"Fuchs, Ingmar Posner, and Andrea Vedaldi","venue":null,"work_id":"ded128be-ae3f-4e8a-9ebe-8bf2010bef47","year":2018},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.661966Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:253a66e76ff3a09def55b765798b62082167a337a8218458e60fd29f502f90f4","observation_id":"0d2f10af-772b-4cec-9e0c-cc46e3bebbd1","resolution":{"observed_at":"2026-08-15T16:42:10.894019Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:10.871928Z","title":"Scene-centric unsupervised panoptic segmentation","venue":null,"work_id":"7e02942b-6b2d-4d0e-bc43-77fd817ee94c","year":2025},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.666121Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:6212b81dac3e0d6aaa7e15e978c3b5af3ea6901468330e152fef95fd6585c2f1","observation_id":"d16d1f42-78ae-491a-94f6-40977bbc7696","resolution":{"observed_at":"2026-08-15T16:42:10.876513Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:10.853622Z","title":"Girshick","venue":null,"work_id":"074a4074-4579-44c4-9fc3-ee1d625f1d35","year":2020},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.671027Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:0e689784c47e26cf86e8d8053fdef8d92d4c76055f6fe5bcf509f0dd0b2807a7","observation_id":"e5c4d05b-522e-4260-831b-64d7dd5245dc","resolution":{"observed_at":"2026-08-15T16:42:10.861325Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:10.838007Z","title":"Object-centric slot diffusion","venue":null,"work_id":"8774a957-5629-4261-ac07-1eeec3c622cb","year":2023},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.675731Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:9fd9e5c77d762ca3590e210315361de57c7eaaac535c0d60c5e7798db09d79bd","observation_id":"79e4ff48-57c7-4a5e-8b88-b5363ec1e737","resolution":{"observed_at":"2026-08-15T16:42:10.843750Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:10.822123Z","title":"Scalor: Generative world models with scalable object representations","venue":null,"work_id":"f5f32daf-9052-4e29-8c9b-de9bc2c52f29","year":2019},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.680261Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:b56381d4f4f524d4836d82d8109417f57c92ff442629c0629ad68428ef8ba888","observation_id":"56c94060-dcf3-4fa9-a52c-a5899535f73a","resolution":{"observed_at":"2026-08-15T16:42:10.828680Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:10.802915Z","title":"SCALOR: G enerative world models with scalable object representations","venue":null,"work_id":"8b7c7680-11aa-42a4-b80b-9703c2eb2d07","year":2020},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.685081Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:a8a5ac9edfc45a0cf9eff04e666375e1d3c7080ee2e9752284036699746a00f2","observation_id":"e5c0cecb-ceeb-47c1-8bfe-6691e92a2f1f","resolution":{"observed_at":"2026-08-15T16:42:10.809157Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:10.784571Z","title":"Lawrence Zitnick, and Ross Girshick","venue":null,"work_id":"6d2e6a0d-1901-4646-82e6-fafadedfedb3","year":2017},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.689325Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:54adc4962fbdc4d0ab2181d6c1f12a7fb0bfcf5484089a598992a5ae0bf602e6","observation_id":"a924023e-dc81-4c3e-9473-91586d55d1ae","resolution":{"observed_at":"2026-08-15T16:42:10.791004Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:10.766763Z","title":"SPOT : S elf-training with patch-order permutation for object-centric learning with autoregressive transformers","venue":null,"work_id":"25bd9826-60ff-4824-bc1e-0f4b5877c7b8","year":2024},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.694955Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:c44869a5cee5a0c13a46ab0e85914d9cd874ae5392d3545f5ab30e60c1e95562","observation_id":"a557f2c6-b3a0-4cc6-8846-c1dfbbccb265","resolution":{"observed_at":"2026-08-15T16:42:10.771674Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:10.752128Z","title":"The background also matters: B ackground-aware motion-guided objects discovery","venue":null,"work_id":"4f4f4ef0-d6d3-4c53-bab5-8752f2c482c4","year":2024},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.701043Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:446490254013e86a31abadc7e1331212e7e187807e59a661429673e218e1012b","observation_id":"3f64568b-a956-4305-a0a2-3281ff222ae8","resolution":{"observed_at":"2026-08-15T16:42:10.756726Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:10.736749Z","title":"DIOD: S elf-distillation meets object discovery","venue":null,"work_id":"ce393773-9369-495f-bba5-4cb70d562a5a","year":2024},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.706552Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:2f0011580e0f170a7467fc7b0dcfe173646ea6f061ec316d6c0002bbe63e07ef","observation_id":"7ee5b3a5-522f-45da-8372-fb95bdff1bfa","resolution":{"observed_at":"2026-08-15T16:42:10.741792Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:10.720019Z","title":"U nsupervised M ulti-object S egmentation by P redicting P robable M otion P atterns","venue":null,"work_id":"8e626e44-f2fb-4add-ad95-2689f2492467","year":2022},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.710886Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:1b98daa893698d6ac427753ca1004427cecc2a7f18cbb28f11bd62f4a04cbd40","observation_id":"8e4f5926-aba5-4b7c-bad0-c00bcef146f1","resolution":{"observed_at":"2026-08-15T16:42:10.724371Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:10.706578Z","title":"Clevrtex: A texture-rich benchmark for unsupervised multi object segmentation","venue":null,"work_id":"f6f54816-9c90-4a90-a07c-ca4684aff428","year":2021},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.715098Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:2e9104b8fe791a11aa4eb5e1eed8ebfa29126f4613ffc4a3a99105c82c89d216","observation_id":"ca916e64-3dad-414d-9143-88913a556b55","resolution":{"observed_at":"2026-08-15T16:42:10.711150Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:09.720192Z","title":"Kingma and Jimmy Ba","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.720192Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:f45f23b4789710b68d5e4f0ff9964a117b932d59c36751b45c7195bd30b64efb","observation_id":"ddeeff86-9d3d-40ff-a6b1-f4b50edacd5e","resolution":{"observed_at":"2026-08-15T16:42:09.720192Z","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":"2026-08-15T16:42:10.683121Z","title":"Elsayed, Aravindh Mahendran, Austin Stone, Sara Sabour, Georg Heigold, Rico Jonschkowski, Alexey Dosovitskiy, and Klaus Greff","venue":null,"work_id":"86b82daa-2846-4004-8653-381417c91272","year":2021},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.725957Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:bd41327cc2ba751f5ab39f3a87d8c0ba1c5e2e93155e2563295118e9e4366e3f","observation_id":"a1e8f2b8-5293-4f63-88f2-36db903f0412","resolution":{"observed_at":"2026-08-15T16:42:10.687941Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:10.667728Z","title":"Berg, Wan-Yen Lo, Piotr Doll \\'a r, and Ross Girshick","venue":null,"work_id":"72deb613-c88c-4dd1-8b21-b4025d37647e","year":2023},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.730782Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:01b9bee47ad37b28aa3d6e5a4509447c6038ecd9cc5e23f2f0d8091564ef89e3","observation_id":"68dc151f-423c-499d-8d7a-89f7d8536975","resolution":{"observed_at":"2026-08-15T16:42:10.671749Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:10.654016Z","title":"Perception: An introduction to the gestalt-theorie","venue":null,"work_id":"9b565b02-810c-4cf9-8e78-fe48de5c2a9b","year":1922},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.736038Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:73fddd2e79b5b6341ad5033812c83aa2d37fa312208497f7a1dd1849603592a0","observation_id":"d39b09ec-8deb-4ab6-9b27-d64ff75ce909","resolution":{"observed_at":"2026-08-15T16:42:10.658387Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:10.638443Z","title":null,"venue":null,"work_id":"3ae2e244-613e-4e26-93d0-a52c93895ad2","year":1955},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.741977Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:1554d6c92b5f7c283ee968dffd84546309e3404750d5574c8db4556c93153d4b","observation_id":"e4e3ae28-f96a-4da3-bf0c-2360a9dc4b95","resolution":{"observed_at":"2026-08-15T16:42:10.643586Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:10.623100Z","title":"Learning object-centric representations of multi-object scenes from multiple views","venue":null,"work_id":"faa25988-77f7-47bf-ae5d-e9ff64b6f620","year":2020},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.750383Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:92414486c4d6910b45f5b34da77c414a580dc4a55c019a74e78916c3235a2b50","observation_id":"7610a8f6-0fec-4b86-bbb8-c468f5240219","resolution":{"observed_at":"2026-08-15T16:42:10.628277Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:10.602421Z","title":"Improving generative imagination in object-centric world models","venue":null,"work_id":"aaea24a1-3b91-43ab-a41a-cc50a7a48a84","year":2020},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.756110Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:a28919096110b23fb82dc1364e1363440a2c3a1467d2c05075b7d05970e5ec50","observation_id":"96e637b4-d7e8-46e5-8d94-269e34c0829e","resolution":{"observed_at":"2026-08-15T16:42:10.607324Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:10.586189Z","title":"Space: Unsupervised object-oriented scene representation via spatial attention and decomposition","venue":null,"work_id":"a1e97dd8-0251-485f-a70e-89fbfeb25a39","year":2020},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.763179Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:2ad3ced984453e58d64bfd11ebb1586b066f4aafd4b9feec79d7f6b7797c4b37","observation_id":"91b2650e-ecd0-43ec-a5d7-6ff5c74fa76f","resolution":{"observed_at":"2026-08-15T16:42:10.591295Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:10.568805Z","title":"Object-centric learning with slot attention","venue":null,"work_id":"29d77180-c775-4145-9956-026892e83301","year":2020},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.768644Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:8b71312885c65c6e3b5fb4521e61e1abb6c476332558c5eae7eceab93506ddd8","observation_id":"cf79f789-d124-448f-844a-1b5ff718a4e6","resolution":{"observed_at":"2026-08-15T16:42:10.575384Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:10.547998Z","title":"Image segmentation using deep learning: A survey","venue":null,"work_id":"08b55176-93c9-4134-90ba-a29b42dca842","year":2022},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.776831Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:7cae2f1ff9f5f6d6b7eabe8fa139022e4d49f6fa535006b55ed5cdef2a876926","observation_id":"8dbcd784-e04e-4fd4-a46f-3220cc452104","resolution":{"observed_at":"2026-08-15T16:42:10.552773Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:10.529964Z","title":"Unsupervised layered image decomposition into object prototypes","venue":null,"work_id":"a19c81be-f8bf-4490-9fdc-fbe4cc00ee20","year":2021},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.781316Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:532608b177bb2cea3ae81526a2b9abf2c84f458e820d1a2107d7e15b11b9581c","observation_id":"80597e11-0a7b-42eb-aec1-c2e43e225ad5","resolution":{"observed_at":"2026-08-15T16:42:10.536401Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:10.510699Z","title":"Higher order motion models and spectral clustering","venue":null,"work_id":"4c530995-a5e0-46e1-8ce5-b56e7f6548dc","year":2012},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.786720Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:978124a951683a62d1dff0e5422310e8b37c4c58a0e771fbe9a8ed2754c7b354","observation_id":"431920f1-0187-49d1-9be9-7831568b76c3","resolution":{"observed_at":"2026-08-15T16:42:10.518553Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:10.494189Z","title":null,"venue":null,"work_id":"1672be40-f007-45ef-9411-82c0d426611f","year":2024},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.792107Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:bcb0fff5ab0fdde641447ea91b3a6c95e04879e22f9d220bf868ea52cd38b26c","observation_id":"9ab5e4e3-0ca0-4482-bf58-ad7a4e26859a","resolution":{"observed_at":"2026-08-15T16:42:10.498921Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:10.473749Z","title":"PyTorch : An imperative style, high-performance deep learning library","venue":null,"work_id":"53951d97-8433-444b-be52-da859c9831ab","year":2019},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.796564Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:6fa70fcd91d2c7eb0fcfba9feab437809e88e17f9c3658761b7631762b38d968","observation_id":"764c848a-36fc-4352-bf53-5feef3b703a2","resolution":{"observed_at":"2026-08-15T16:42:10.479395Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:10.460398Z","title":"Barron, Ferran Marqu \\'e s, and Jitendra Malik","venue":null,"work_id":"da2d14e9-58bc-4b38-b35d-dc3c6865c278","year":2015},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.800776Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:46197f64bceafeff2b1539096392b13b9119f9b3a89c4de26a39171dc8da2526","observation_id":"eaf72a85-6dff-411c-86d1-2c256c0d9a65","resolution":{"observed_at":"2026-08-15T16:42:10.465156Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:10.443617Z","title":"Bernstein, Alexander C","venue":null,"work_id":"85e00a3e-bc17-4168-a24e-f7675ad537cb","year":2015},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.804702Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:29b1342ea87170ec2793bee6183bef0f2c882dd4af49ce2493783c6b7deb3c3d","observation_id":"4d695226-595c-4b89-bfa9-4343617a4205","resolution":{"observed_at":"2026-08-15T16:42:10.449174Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:10.426733Z","title":"Multi-object discovery by low-dimensional object motion","venue":null,"work_id":"66f1a540-4b49-43a0-8001-b9b8a42809bc","year":2023},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.808551Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:53d85b14020d6bd82fb8ceb60bfaa049786a0a4d5ab9472822bee2c37ea8382a","observation_id":"4c625e84-16de-4191-8086-97dc9312c53c","resolution":{"observed_at":"2026-08-15T16:42:10.432191Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:10.410753Z","title":null,"venue":null,"work_id":"35eef2a6-158c-4264-8381-e71112887f34","year":1989},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":56,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.813195Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:63885d176028528f09f4b3fe207609923395ec8ee551a3d7039a174563daba2b","observation_id":"a97c8bce-dec2-4913-9ba9-89714d736447","resolution":{"observed_at":"2026-08-15T16:42:10.415937Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:10.394041Z","title":"Bridging the gap to real-world object-centric learning","venue":null,"work_id":"53442e3e-3dcc-4a60-85ad-4f5e7afc3987","year":2023},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":57,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.818371Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:845123aaf02676349811a8190ee9fe1e0ae648d95b3e4d450320363ee8859daf","observation_id":"27da2a58-4896-4f39-a25f-00ec0d97d1f6","resolution":{"observed_at":"2026-08-15T16:42:10.400793Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:10.373760Z","title":"Simple unsupervised object-centric learning for complex and naturalistic videos","venue":null,"work_id":"63b6b469-14ba-405d-bcc9-2fa72ddeffd2","year":2022},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":58,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.824726Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:8993919ab20279f0877176aa8b300aa3bf24e95841c090b846fa6ed98deee61b","observation_id":"70eec0e7-5988-441c-b038-36a6f32a77f2","resolution":{"observed_at":"2026-08-15T16:42:10.379162Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.17929","last_updated":"2025-06-07T03:45:15Z","snapshot_observed_at":"2026-08-17T09:18:08.435072Z","submitted_at":"2024-07-25T10:38:32Z","title":"GLASS: Guided Latent Slot Diffusion for Object-Centric Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.17929","snapshot_observed_at":"2026-08-15T16:42:09.832279Z","title":"Guided latent slot diffusion for object-centric learning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":59,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.832279Z"},"links":{"cited_paper":"/paper/2407.17929","citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:84832c6d1a7a35f3e20ce8ab449bc9541bb10441c87d779c3ec79af949ab26ae","observation_id":"38d1114f-68e8-4fbb-834e-69106e383e6b","resolution":{"observed_at":"2026-08-15T16:42:09.832279Z","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":"2026-08-15T16:42:10.357817Z","title":"SF2SE3: C lustering scene flow into SE(3) -motions via proposal and selection","venue":null,"work_id":"fd0e00bb-9fe9-421b-913b-abf138472cf3","year":2022},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":60,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.841832Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:ac50192b413b5a1f6ff011d42f517da0a9a945cc390f1c92f2514c5c5884a08c","observation_id":"0d369dc6-4b3d-4678-8abf-907f927b45a7","resolution":{"observed_at":"2026-08-15T16:42:10.363445Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:10.341881Z","title":"SMURF : S elf-teaching multi-frame unsupervised RAFT with full-image warping","venue":null,"work_id":"0c15c7c0-032d-4792-a74b-6742a0df562b","year":2021},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":61,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.845820Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:03ec8075427183ea6001b0ea79575f0328e9bd0aabaeae29f8579fb2ad7ad15c","observation_id":"9a0b9d47-7ca0-4336-8661-3ba6e1f90bce","resolution":{"observed_at":"2026-08-15T16:42:10.347551Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:09.850031Z","title":"RAFT : R ecurrent all-pairs field transforms for optical flow","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":62,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.850031Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:aeaf16946f45f1012ffc52e62b4c88c792fe3bb9efc1e930516648c9116e0c16","observation_id":"2d46c6b3-444d-4c35-9122-4f5f2fe17cbb","resolution":{"observed_at":"2026-08-15T16:42:09.850031Z","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":"2026-08-15T16:42:10.313578Z","title":"Thompson, Kathleen M Mutch, and Valdis A Berzins","venue":null,"work_id":"a0923635-9c49-4987-90e4-1e2830fbf3e0","year":1985},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":63,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.855563Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:99bc72dd47637cc6b791986604e92add0126844beccac15ed7978d07441e7277","observation_id":"c336bee4-f7bb-49f9-9b72-882e348c69e8","resolution":{"observed_at":"2026-08-15T16:42:10.317883Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:10.299030Z","title":"Geometric motion segmentation and model selection","venue":null,"work_id":"82bf7172-395c-4188-826c-1f9b6e7bdbc7","year":1998},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":64,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.860557Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:2c9f9eb03bf559ce15ca819b8c938e100f479fec22e8a4c9a7bfe0f67a3efb96","observation_id":"2ec26d4e-234b-4221-b1a6-151baffbf595","resolution":{"observed_at":"2026-08-15T16:42:10.303057Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:10.283804Z","title":"Gomez, ukasz Kaiser, and Illia Polosukhin","venue":null,"work_id":"62e9ae41-f617-405b-a8dd-f8b407e888fd","year":2017},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":65,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.865043Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:5e37053945ec21a4aa6bb8873d1c980b8fcee01c943fd17b51ef860ad662628d","observation_id":"431b4ee9-0c00-4164-95ff-8bc210021e04","resolution":{"observed_at":"2026-08-15T16:42:10.289026Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2411.00868","last_updated":"2024-10-30T21:22:48Z","snapshot_observed_at":"2026-08-17T07:46:03.552175Z","submitted_at":"2024-10-30T21:22:48Z","title":"Unsupervised Object Discovery: A Comprehensive Survey and Unified Taxonomy","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.00868","snapshot_observed_at":"2026-08-15T16:42:09.870430Z","title":"Unsupervised object discovery: A comprehensive survey and unified taxonomy","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":66,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.870430Z"},"links":{"cited_paper":"/paper/2411.00868","citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:c1c2dad27045a258257511f173096bc11542110b105d43ea7357708225a481b5","observation_id":"3696fbc2-7814-48bb-8997-091ed9fb24ff","resolution":{"observed_at":"2026-08-15T16:42:09.870430Z","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":"2026-08-15T16:42:10.269883Z","title":"Yu, and Ishan Misra","venue":null,"work_id":"2b67f6c7-1705-4a6d-95b5-5a32457a2898","year":2023},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":67,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.876318Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:49b6c574c0f5b55367e36839c28e43731c7c7829c4030950805beeb6c6881dc1","observation_id":"e0fd0331-2e72-42b5-9345-40706789dc82","resolution":{"observed_at":"2026-08-15T16:42:10.274987Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:10.255643Z","title":"Videocutler: Surprisingly simple unsupervised video instance segmentation","venue":null,"work_id":"956cd800-5613-4682-abb9-31a8c6309d85","year":2024},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":68,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.881831Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:b5846fc3380bdf39d923fd7fa69b3ce1d73540aff22b8c19fada210a7bb65a69","observation_id":"f3c83eaa-703b-44a6-b127-2301f7c83e7b","resolution":{"observed_at":"2026-08-15T16:42:10.260378Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:10.238090Z","title":"Crowley, and Dominique Vaufreydaz","venue":null,"work_id":"5a3d5ecc-a9ac-4222-8e85-2f4bbb14e398","year":2023},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":69,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.886508Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:90d5c18ab6196edb0947a4b3b9fc5408635d5bb31aaab1b24092ae2bb33c13de","observation_id":"15b9004b-c994-4372-b6d7-dffbf0035655","resolution":{"observed_at":"2026-08-15T16:42:10.242112Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:10.217880Z","title":"Experimentelle studien \\\"u ber das sehen von bewegung","venue":null,"work_id":"42be4018-14fa-47e8-bdcf-453cb49bbe56","year":1912},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":70,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.890328Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:84d0f9488e22d2c16a3a01a9468998bca4edaa7c1a93468fbd289f3d0918d839","observation_id":"9ad42ec1-1798-41dc-9c61-0e6862435e44","resolution":{"observed_at":"2026-08-15T16:42:10.222710Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:10.203622Z","title":"SlotDiffusion : O bject-centric generative modeling with diffusion models","venue":null,"work_id":"29d8a1d8-73a7-4385-b09e-c7925d17796d","year":2023},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":71,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.894788Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:b4885a9f8f588ef4a1c4d37db5f791cec38325664429f829abef93fafba785d7","observation_id":"117eccda-97d6-493e-b8ce-0bd095925dc5","resolution":{"observed_at":"2026-08-15T16:42:10.208869Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:10.188556Z","title":"Slotformer: Unsupervised visual dynamics simulation with object-centric models","venue":null,"work_id":"867c9bbd-770f-4865-bda1-f15ac77a76fb","year":2023},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":72,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.898752Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:ad4fe6ea4114897c4d885e8d1f30d34709de314505568269e4dde0fd1836699a","observation_id":"57f11ae4-f899-4baf-b5c8-a142ebbd3a1a","resolution":{"observed_at":"2026-08-15T16:42:10.193665Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:10.168961Z","title":"Moving object segmentation: A ll you need is SAM (and flow)","venue":null,"work_id":"d1aea13b-0da5-41a0-8a5a-9531e56787f2","year":2024},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":73,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.903922Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:14824f00111631f1626af53a79c11b29fa6bbab1dd8e3b3d43cb5d2efbcc2854","observation_id":"d219e8ef-3e20-4c1f-bb4f-58f9f1c2b770","resolution":{"observed_at":"2026-08-15T16:42:10.174858Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:10.148803Z","title":"Motion segmentation: A review","venue":null,"work_id":"2b42f456-bbdd-4240-9bf7-6d665a2e08ba","year":2008},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":74,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.908285Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:f1a3c74d468327b7fdb8b7a11173be33968e88d990941cf6425091ce834ba12b","observation_id":"dbef7e73-a41d-4b94-be92-4d610645604f","resolution":{"observed_at":"2026-08-15T16:42:10.154383Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:10.126354Z","title":"Segmentation of moving objects in image sequence: A review","venue":null,"work_id":"565c6a5b-03ce-4680-adf0-deffe01c6a99","year":2001},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":75,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.912314Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:9d5baf74644a5abd602986ab28e66b48c83109b85869189166209004c9939a68","observation_id":"fd774409-3b16-4de7-bacf-e2063b391e10","resolution":{"observed_at":"2026-08-15T16:42:10.132919Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2408.12957","last_updated":"2024-11-27T09:54:05Z","snapshot_observed_at":"2026-08-16T13:24:22.934921Z","submitted_at":"2024-08-23T10:07:59Z","title":"Image Segmentation in Foundation Model Era: A Survey","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.12957","snapshot_observed_at":"2026-08-15T16:42:09.917041Z","title":"Image segmentation in foundation model era: A survey","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":76,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.917041Z"},"links":{"cited_paper":"/paper/2408.12957","citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:147d559579a172a24a82b2d554437a1c6ca4dddf8c7dc006d489cad045c0f297","observation_id":"9739d1c5-3db8-4ae7-beaa-cb79c79da873","resolution":{"observed_at":"2026-08-15T16:42:09.917041Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.18890","last_updated":"2023-05-30T09:44:12Z","snapshot_observed_at":"2026-08-16T15:28:23.865687Z","submitted_at":"2023-05-30T09:44:12Z","title":"Sensitivity of Slot-Based Object-Centric Models to their Number of Slots","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.18890","snapshot_observed_at":"2026-08-15T16:42:09.924194Z","title":"Zimmermann, Sjoerd van Steenkiste, Mehdi S","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":77,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.924194Z"},"links":{"cited_paper":"/paper/2305.18890","citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:113c3e47a029c9abcadcfb65f95bd52d159cc6ef2fd39d76ea990c853ea33863","observation_id":"bda876c6-612a-47cd-89ab-1c94e16db638","resolution":{"observed_at":"2026-08-15T16:42:09.924194Z","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":"2026-08-15T16:42:10.110725Z","title":"https://paralleldomain.com/","venue":null,"work_id":"a8006e88-87c5-4a30-b6d8-454c2de6550b","year":2025},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":78,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.930719Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:46c08039dd5901847b9a57e89484cf96946db417c14c37157810c1a02434cbaf","observation_id":"062742b4-d52f-4855-b00d-1a82ee6661b8","resolution":{"observed_at":"2026-08-15T16:42:10.115151Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:10.091090Z","title":"Fleet, Dan Gnanapragasam, Florian Golemo, Charles Herrmann, Thomas Kipf, Abhijit Kundu, Dmitry Lagun, Issam H","venue":null,"work_id":"3a7c8857-fe2e-4e8f-9ff7-32190c0ee503","year":2022},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":79,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.934966Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:738144a7acff6153a9edce1172adb0cf0aaed290a4c58bf5c544770f6de3abca","observation_id":"7e475713-c55c-43c7-bf25-8dd466f73761","resolution":{"observed_at":"2026-08-15T16:42:10.098724Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T16:42:10.071150Z","title":"Object-centric learning for real-world videos by predicting temporal feature similarities","venue":null,"work_id":"03fa41f3-5994-4903-a053-c68c56767856","year":2023},"citing_paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery","version":1},"reference_index":80,"source":"arxiv_source","source_observed_at":"2026-08-15T16:42:09.940464Z"},"links":{"citing_paper":"/paper/2509.02545"},"observation_digest":"sha256:1919f5ca2188ff5e002da72df43ab9db2e2636b6be36777d2f6fa68d9117d801","observation_id":"2299413b-0572-4563-8a77-e734bc31a80d","resolution":{"observed_at":"2026-08-15T16:42:10.078745Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2509.02545","last_updated":"2025-09-02T17:44:49Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-17T14:22:21.371673Z","submitted_at":"2025-09-02T17:44:49Z","title":"Motion-Refined DINOSAUR for Unsupervised Multi-Object Discovery"},"reference_resolution":{"displayed":80,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":14,"verified_exact":0,"verified_fuzzy":66},"total_outbound_references":80},"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":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 80 of 80 outbound references and 0 inbound Pith citation observations for arXiv:2509.02545."}