{"as_of":"2026-08-10T15:02:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:90e6a9dda3f416dcb26506540df7ed961c8fe3fe70d73256715250627b0ce3f2","coverage":[{"denominator":96,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":96,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T13:18:08.685205Z","state":"measured"},{"denominator":96,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":96,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+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/2507.20860/citation-record","integrity":"/paper/2507.20860/integrity","json":"/paper/2507.20860/citation-record.json","paper":"/paper/2507.20860"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:07.685615Z","title":"Detreg: Unsupervised pretrain- ing with region priors for object detection","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:07.685615Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:aa57c643519f49b9c2dc8dfc20d6d89cfcedc1fc6e5026e0012022fb735d0293","observation_id":"82993cb6-d9d7-4fc6-a1dc-e442eff9e7a1","resolution":{"observed_at":"2026-08-06T13:18:07.685615Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:07.783615Z","title":"An experimental comparison of min-cut/max-flow algorithms for energy min- imization in vision.IEEE transactions on pattern analysis and machine intelligence, 26(9):1124–1137, 2004","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:07.783615Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:9cbd7025e9d16f99d1a5a285a20ee0879479787dd3ca2c4dc6f21530c6881d93","observation_id":"f0651565-ff36-46e0-bc46-49836f4080e8","resolution":{"observed_at":"2026-08-06T13:18:07.783615Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:07.851906Z","title":"Interactive graph cuts for optimal boundary & region segmentation of objects in nd images","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:07.851906Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:e1229e553a1c8aed6d4ef0575e30c23524e308c2609b8cbca786a5288323bfec","observation_id":"d9e5d5bd-ec4c-4a9c-bc67-84e93584c43d","resolution":{"observed_at":"2026-08-06T13:18:07.851906Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:07.952495Z","title":"Bagging predictors.Machine learning, 24: 123–140, 1996","venue":null,"work_id":null,"year":1996},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:07.952495Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:531936bc54075eb0fa0435e6f292f406c2d195de3beff85dab27550724e7fbf0","observation_id":"31bae2a5-54cb-484b-8546-336a6e897dc5","resolution":{"observed_at":"2026-08-06T13:18:07.952495Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:08.062490Z","title":"Pasting small votes for classification in large databases and on-line.Machine learning, 36:85–103, 1999","venue":null,"work_id":null,"year":1999},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.062490Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:133bb812ba93f0b03acbffe806474ffa10e1394a74d3acedf521f2e1ea659e6e","observation_id":"796228bc-05bd-4a74-af2b-9b9dcc34b3e2","resolution":{"observed_at":"2026-08-06T13:18:08.062490Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:08.184486Z","title":"Random forests.Machine learning, 45:5–32,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.184486Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:6545d8aad1d41d479b3ec3aac60a4c83d3f88c41c55b38b84bd5b4c7d814c1c6","observation_id":"269452c3-dd58-4422-9453-8346737b3e4e","resolution":{"observed_at":"2026-08-06T13:18:08.184486Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:08.284190Z","title":"Cascade r-cnn: Delv- ing into high quality object detection","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.284190Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:07f8cb6a32a35ce87f9067989ee8c6fffbba4765abc1dfe92c32eb55feba28e5","observation_id":"b5dd0e78-8241-4210-9ab6-c7d666b59874","resolution":{"observed_at":"2026-08-06T13:18:08.284190Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:08.343250Z","title":"Unsupervised learning of visual features by contrasting cluster assignments.Ad- vances in neural information processing systems, 33:9912– 9924, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.343250Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:59b9d17d1323ae6dc43dd7fd35f2548c33f8c2512eb65cf660572f30bff32612","observation_id":"400fa310-305c-4fb6-b082-9a2e5e40fd36","resolution":{"observed_at":"2026-08-06T13:18:08.343250Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:08.363017Z","title":"Emerg- ing properties in self-supervised vision transformers","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.363017Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:3054d779f877d605c7232d6f1cd8227f55f49ba5c693bcd508143a9bf521f221","observation_id":"80203f79-12ce-447e-bde0-eefa18bf7e1e","resolution":{"observed_at":"2026-08-06T13:18:08.363017Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:08.366805Z","title":"A simple framework for contrastive learning of visual representations","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.366805Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:ac5f4cc7e605c7d70658885f247a79549c6e1140496f450100cfd1395e2f9c5d","observation_id":"2556c040-1774-4ca1-a2a8-07f5d35f23c2","resolution":{"observed_at":"2026-08-06T13:18:08.366805Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:08.370751Z","title":"Exploring simple siamese rep- resentation learning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.370751Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:38661f26f3783d4cc264ebf2a2c399de0d049fff6fd56e2572954d5974f43a4a","observation_id":"d89d3154-9339-4459-86b1-bdac41446a37","resolution":{"observed_at":"2026-08-06T13:18:08.370751Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:08.374493Z","title":"Semi-supervised semantic segmentation with cross pseudo supervision","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.374493Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:4dced22b2b43f16203f791c89b6fadc8b77564735bb1c5609f0c06fd314dfa21","observation_id":"fdd4c47b-d65e-403d-97f9-458cbfbfc604","resolution":{"observed_at":"2026-08-06T13:18:08.374493Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:08.378133Z","title":"Class re-activation maps for weakly-supervised semantic segmentation","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.378133Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:8cea95cd5d5529bcbc915e847ef8914456b28bdc45d582222a9eba7137ddb2e7","observation_id":"f1eba3b3-e157-4a69-a957-930334fb87cd","resolution":{"observed_at":"2026-08-06T13:18:08.378133Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:08.381726Z","title":"The cityscapes dataset for semantic urban scene understanding","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.381726Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:45cf9315e4be9aa096802f03cb97ee70e4e8ef8a12f5bc126d718f556b23006c","observation_id":"98075003-7c84-40f3-a8f7-ebed7fe5a56d","resolution":{"observed_at":"2026-08-06T13:18:08.381726Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:08.385807Z","title":"Unsupervised learning from video to de- tect foreground objects in single images","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.385807Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:a2b81210ce23aceda0abcd6531078a65756fd04ab39c70d7782859c6766456ce","observation_id":"7567411a-b491-42ea-9d8e-4e940925d466","resolution":{"observed_at":"2026-08-06T13:18:08.385807Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:08.389246Z","title":"Unsupervised learning of foreground ob- ject segmentation.International Journal of Computer Vision, 127:1279–1302, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.389246Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:6d6d78711b65c1ae209c88ef4a96ff98ca133aab6e070e17e2ba1e306fbbbcad","observation_id":"5ca12e8b-37f6-44a7-9f50-ca6730cae2ad","resolution":{"observed_at":"2026-08-06T13:18:08.389246Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:08.393006Z","title":"Imagenet: A large-scale hierarchical image database","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.393006Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:7574785ef2536cf11844dce0b8046ee36fd1e6a8d7d06e865e8fa119dc19bb18","observation_id":"4cd87a63-ac66-4bca-aa6f-1865c1d1bd2c","resolution":{"observed_at":"2026-08-06T13:18:08.393006Z","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":"2026-08-06T13:18:09.696529Z","title":"Ensemble methods in machine learn- ing","venue":null,"work_id":"7297be28-6a0d-4f63-9fbb-3f95d58696f3","year":2000},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.396880Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:4aa293daba12d7ee6ae586f38bf048fdd3af6537b28c3443d30620c13b617966","observation_id":"21eac819-6c2d-4415-9a17-89e299034c13","resolution":{"observed_at":"2026-08-06T13:18:09.700377Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:09.682826Z","title":"An image is worth 16x16 words: Trans- formers for image recognition at scale","venue":null,"work_id":"2a8ef1e8-260d-4285-8bad-bf4e7dea9e26","year":2020},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.400931Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:2be55fcc57bdae75f067dcddf3740e0570cb32c008d577578c46f0de65c43889","observation_id":"23fa3fb8-03b8-49e6-9189-89b95bc034cc","resolution":{"observed_at":"2026-08-06T13:18:09.687313Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:09.669441Z","title":"Bb-unet: U-net with bounding box prior.IEEE Journal of Selected Topics in Signal Processing, 14(6):1189– 1198, 2020","venue":null,"work_id":"7c1cdf9d-c3b4-46cc-ae0a-a04bd50fade0","year":2020},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.404537Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:eca8fbd337af6e3ccb8a3ecfb67b1a3404bd9b4e937a5c332dddd42dd706b12c","observation_id":"c3c1eba5-9a13-4233-90d0-83ad82bebeda","resolution":{"observed_at":"2026-08-06T13:18:09.673382Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:09.656323Z","title":"Wanget al","venue":null,"work_id":"a2724bff-a0be-47ed-9495-32308c276d35","year":2022},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.408298Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:8b453d0b063fcbe41d622be1a78fbd5a9b8e434d5bdf75ab0a16cd69ad8b1e8f","observation_id":"d8694297-6158-47f0-beed-0255ce953631","resolution":{"observed_at":"2026-08-06T13:18:09.660011Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:09.643314Z","title":"The pascal visual object classes (voc) challenge.International journal of computer vision, 88(2):303–338, 2010","venue":null,"work_id":"4809bc7f-48f2-4e77-ae04-dd173c62de77","year":2010},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.411779Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:fb7261e9f882d414907f5fdb5d14d486a7ddfaebc8b848507e44483f6e88f396","observation_id":"440cabfd-c578-4e2f-8192-7ee987abf96d","resolution":{"observed_at":"2026-08-06T13:18:09.647666Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:09.630582Z","title":"A decision-theoretic generalization of on-line learning and an application to boosting.Journal of computer and system sciences, 55(1): 119–139, 1997","venue":null,"work_id":"f57492e9-1613-49ac-bace-72ee05c4c2ef","year":1997},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.415518Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:c047916a7f9c68527bcef2f747f53e3f86b965ecffe75c3758543241a14c583c","observation_id":"5e70b19a-1076-44c6-91df-dd4d93d6badc","resolution":{"observed_at":"2026-08-06T13:18:09.634761Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:09.617878Z","title":"The estimation of the gradient of a density function, with applications in pat- tern recognition.IEEE Transactions on information theory, 21(1):32–40, 1975","venue":null,"work_id":"07d67b93-920e-4f8f-8454-75a1e30525f7","year":1975},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.419772Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:270a9e91bda86844e5be9114a23fbfc87cda62e94272547d9a9411a50c2808d2","observation_id":"63ed05a7-1414-4107-857a-0a2e0136f199","resolution":{"observed_at":"2026-08-06T13:18:09.621971Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:08.423394Z","title":"Bootstrap your own latent-a new approach to self-supervised learning.Advances in neural information processing systems, 33:21271–21284, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.423394Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:f45cc99f7eb040d3dda3c1616932e7fee7f184d942d01cceb6cf424b4fcc4d6c","observation_id":"ecb400df-37e5-4207-b9f1-b10ff435c3c5","resolution":{"observed_at":"2026-08-06T13:18:08.423394Z","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":"2026-08-06T13:18:09.596924Z","title":null,"venue":null,"work_id":"241fefef-e601-4a99-807e-5a4c1054ebed","year":2021},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.426875Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:3f19d36e3747b3d9db4a8b0e764363cbd190461561fe0c7a58f79d81ca3b4542","observation_id":"c0e351cb-6e58-47b6-be9c-fff5fca198b1","resolution":{"observed_at":"2026-08-06T13:18:09.600488Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:09.584031Z","title":"Mask r-cnn","venue":null,"work_id":"93ba0c49-0b30-421c-8f76-a6267ebac47b","year":2017},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.430572Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:57f7dec3b1024609de03cb9dbc5d07ec78ee68c9a28c9be6e24fc63345c3be70","observation_id":"b8d6ff1f-55fe-48a1-919c-e447e1895f46","resolution":{"observed_at":"2026-08-06T13:18:09.588362Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:09.571047Z","title":"Momentum contrast for unsupervised visual rep- resentation learning","venue":null,"work_id":"f5f026bd-fdbf-4140-a385-faa0768bb9cf","year":2020},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.434179Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:ae7279b5331b4dbe6a2bb3601123c760019c2645bf50337b2698692118c62eeb","observation_id":"c6dfeca9-67d4-483b-86ef-db078b3f5421","resolution":{"observed_at":"2026-08-06T13:18:09.574960Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1802.07934","last_updated":"2018-07-24T22:56:44Z","snapshot_observed_at":"2026-08-04T08:58:37.214443Z","submitted_at":"2018-02-22T08:13:20Z","title":"Adversarial Learning for Semi-Supervised Semantic Segmentation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1802.07934","snapshot_observed_at":"2026-08-06T13:18:08.437593Z","title":"Adversarial learning for semi-supervised semantic segmentation.arXiv preprint arXiv:1802.07934, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.437593Z"},"links":{"cited_paper":"/paper/1802.07934","citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:b92ccd9956ff99c11f83568cdc4698dd2dae0065ce48cdaf819282d04a33d9fa","observation_id":"2c6b2f3e-0cb3-4d36-80c0-eda31f309ea8","resolution":{"observed_at":"2026-08-06T13:18:08.437593Z","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":"2026-08-06T13:18:09.557966Z","title":"Unsupervised detection of regions of interest using iterative link analysis.Advances in neural information processing systems, 22, 2009","venue":null,"work_id":"b1b660ec-dfad-434c-b65e-57ff7c17bb4c","year":2009},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.441475Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:efa5fb80e81bb1b11d74c95f531d972b35d2bc0467c5bdc7f5b1dd50eec504b6","observation_id":"11f9fb75-a9b1-4c1a-943e-f402571f94f8","resolution":{"observed_at":"2026-08-06T13:18:09.562198Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6980","last_updated":"2017-01-30T01:27:54Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2014-12-22T13:54:29Z","title":"Adam: A Method for Stochastic Optimization","version":9},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6980","snapshot_observed_at":"2026-08-06T13:18:08.444826Z","title":"Adam: A method for stochastic optimization.arXiv preprint arXiv:1412.6980,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.444826Z"},"links":{"cited_paper":"/paper/1412.6980","citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:cc3e1ac98f4c63ac38fd5e24520b0d7225b70642346b0b7bbb4d26f033a560c8","observation_id":"d221cef8-2f77-4666-9ab1-3d7a143126f1","resolution":{"observed_at":"2026-08-06T13:18:08.444826Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:08.448664Z","title":"Segment any- thing","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.448664Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:f5e37f1670afe0fc7bcf56528431451babba0efd0fc313ed15f949cfad6770db","observation_id":"c37e630e-8bd3-4c85-806c-7290caa451ed","resolution":{"observed_at":"2026-08-06T13:18:08.448664Z","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":"2026-08-06T13:18:09.536689Z","title":"Box2seg: Attention weighted loss and discriminative feature learning for weakly supervised segmentation","venue":null,"work_id":"7779e948-e29b-4619-8990-007210d2d552","year":2020},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.452084Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:8fe76e7256e7c67f80d3a6483625fd6e432b51876209afa3f18fcd5bc5b85995","observation_id":"87789ba0-34ca-4427-8026-3a5daeb7f7bb","resolution":{"observed_at":"2026-08-06T13:18:09.540744Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:09.524040Z","title":"Bbam: Bounding box attribution map for weakly super- vised semantic and instance segmentation","venue":null,"work_id":"ed29997a-3473-490b-8ba2-4ee3901fa711","year":2021},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.455567Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:7098f7815ca3cb69fb160ccb947359838040e9a36e652e286816e3f73e5a7194","observation_id":"d86c0597-eb1b-4261-90ec-f920cd2ee3fa","resolution":{"observed_at":"2026-08-06T13:18:09.527896Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:09.511676Z","title":"Promerge: Prompt and merge for unsupervised instance segmentation","venue":null,"work_id":"946ecc8c-4a4b-450f-a7f2-e9b02a92e118","year":2024},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.459341Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:2cd59197db822cea1f96acccb78bae590c3d9fa46149eef89fa098669f877b97","observation_id":"a2912b4b-0d76-4bcd-ad17-01e682e255db","resolution":{"observed_at":"2026-08-06T13:18:09.515604Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:09.499190Z","title":"A weighted sparse cod- ing framework for saliency detection","venue":null,"work_id":"e0ec8e8a-da43-4b49-850e-65785d07a229","year":2015},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.462902Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:5ed97b37a3b8675dc638ddc60310fdef982b187e0db1236ff7880d53c669a9f0","observation_id":"a65a57c6-768a-4cb4-9d9c-78264c7a83f5","resolution":{"observed_at":"2026-08-06T13:18:09.502954Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:09.487166Z","title":"Microsoft coco: Common objects in context","venue":null,"work_id":"2008e9b1-2d68-47e0-925d-78046a2dbd14","year":2014},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.466297Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:4af4423844adcac5d87e4879d5e91161bf0a0092e9044c960a6dca22c403c57d","observation_id":"488362ce-71c8-4fbf-98f0-11f381c4dd5f","resolution":{"observed_at":"2026-08-06T13:18:09.491013Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1711.05101","last_updated":"2019-01-04T21:01:49Z","snapshot_observed_at":"2026-08-09T20:34:52.923500Z","submitted_at":"2017-11-14T14:24:06Z","title":"Decoupled Weight Decay Regularization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.05101","snapshot_observed_at":"2026-08-06T13:18:08.469538Z","title":"Decoupled weight decay regularization.arXiv preprint arXiv:1711.05101, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.469538Z"},"links":{"cited_paper":"/paper/1711.05101","citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:2e37f25c2bbaeee4641504f736cdeaaaed469a1cb94b869526f36d7c0a8ef2c4","observation_id":"e758c2ed-dc39-4da3-bd59-6c8994fd7d33","resolution":{"observed_at":"2026-08-06T13:18:08.469538Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2007.05615","last_updated":"2020-07-10T21:25:27Z","snapshot_observed_at":"2026-08-06T10:45:31.084689Z","submitted_at":"2020-07-10T21:25:27Z","title":"PCAMs: Weakly Supervised Semantic Segmentation Using Point Supervision","version":1},"cited_work":{"arxiv_id":"2007.05615","doi":null,"metadata_source":"pith","pith_arxiv_id":"2007.05615","snapshot_observed_at":"2026-08-06T13:18:08.747284Z","title":"PCAMs: Weakly Supervised Semantic Segmentation Using Point Supervision","venue":"cs.CV","work_id":"861aa760-8a90-4922-821b-743e45785891","year":2020},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.473411Z"},"links":{"cited_paper":"/paper/2007.05615","citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:11139b6272d7967689f1a11099cbcf01bab9e7ed65d491611921387ba1f55cb9","observation_id":"d291e0ca-15c8-44d1-a07e-97a2e1588b16","resolution":{"observed_at":"2026-08-06T13:18:08.753188Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:09.475215Z","title":"Deep spectral methods: A surprisingly strong baseline for unsupervised semantic segmentation and localization","venue":null,"work_id":"75539806-16a9-4019-b42e-9bf35fa1ac21","year":2022},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.477218Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:3288c1da83ba383438a717f5be97ba05255efc2eff35d49cbfc766795ecadd0b","observation_id":"cfccd0ee-610b-47de-b12e-53e9c3725e2d","resolution":{"observed_at":"2026-08-06T13:18:09.478975Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:09.463149Z","title":"Deepusps: Deep robust unsupervised saliency prediction via self-supervision.Advances in Neu- ral Information Processing Systems, 32, 2019","venue":null,"work_id":"a79e56b7-2727-4d9f-85a5-6bbbf61c96cc","year":2019},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.480761Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:16a063fa162f031dd63d7e74b04ef82e8ecb7ea188fb7844243645f6282ba420","observation_id":"af7f3ec6-31bc-4008-aa6e-e2a1306c6255","resolution":{"observed_at":"2026-08-06T13:18:09.466860Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:09.451447Z","title":"Dinov2: Learning robust visual features without super- vision.Transactions on Machine Learning Research, 2023","venue":null,"work_id":"4b545dab-158d-47db-b1eb-fa6f13c148d4","year":2023},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.484498Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:276ceaea796f63817182c450c11d62e267ad9bf0734e513f9931fc31467a59d8","observation_id":"7b9be554-c052-448a-99dc-ec486f0a479b","resolution":{"observed_at":"2026-08-06T13:18:09.455231Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:09.439455Z","title":"Semi- supervised semantic segmentation with cross-consistency training","venue":null,"work_id":"4271589c-c3ba-4f12-8815-1510e6cef657","year":2020},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.488225Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:5d6f7ce3c4829f9bf21718696f0be08c44251026c00987107cf874290548d31d","observation_id":"dfa2b44f-3c97-466c-b51e-24180fc1008e","resolution":{"observed_at":"2026-08-06T13:18:09.443371Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:09.427126Z","title":"Weakly supervised scene parsing with point-based distance metric learning","venue":null,"work_id":"a8696aa2-a01b-40c6-a049-cb5078a0a192","year":2019},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.492237Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:ef42c845c7ab92ab0e8714f1624a0c9e3ab37723153f4e1922d7321cf5bddb01","observation_id":"b98ff353-f436-407f-9848-13a33750fe30","resolution":{"observed_at":"2026-08-06T13:18:09.430805Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:09.415009Z","title":"Most: Multiple object localization with self-supervised transformers for object discovery","venue":null,"work_id":"124c24c3-7b5a-4fbd-8a40-9c48cffd643d","year":2023},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.495755Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:cc6eb97a8879da3e4b0f31c8ab8ac1669200a4e73d3c084d6178e36cfebce8e6","observation_id":"b4dd8959-dbc0-44d0-bdf6-ee63f0ac45fb","resolution":{"observed_at":"2026-08-06T13:18:09.418864Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:09.402508Z","title":"Mudit Adityaja, Saurabh J","venue":null,"work_id":"9f8af2f5-2a77-411b-914c-12b5ec122955","year":2024},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.499340Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:7eca30809345f6a59a44bcb6570527ae161b14d7305d34bb28432fae60d0d168","observation_id":"7a9c0d53-36bf-420a-80e1-80cff21ff795","resolution":{"observed_at":"2026-08-06T13:18:09.406174Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:09.390468Z","title":"Faster r-cnn: Towards real-time object detection with region proposal networks.IEEE transactions on pattern analysis and machine intelligence, 39(6):1137–1149, 2016","venue":null,"work_id":"e771bd2c-da92-42b7-817a-2d20678dddc1","year":2016},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.502795Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:1a75002ad75bfb7963c82b8d870f87bac5f4ad8f70ef1f9dab479444f683d16d","observation_id":"6b022822-5250-487c-9e41-85ea0d688e3e","resolution":{"observed_at":"2026-08-06T13:18:09.394406Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:09.378294Z","title":"U- net: Convolutional networks for biomedical image segmen- tation","venue":null,"work_id":"b860194d-4ed5-4df6-87cd-d6ffca77a16f","year":2015},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.506372Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:0268b647e22f079b738284ca5eeed505e8be8157ceeca1c250ee38b8fd9de4c0","observation_id":"88ac89b6-a615-4aa3-9445-20da7a10832b","resolution":{"observed_at":"2026-08-06T13:18:09.381969Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:09.365369Z","title":"” grabcut” interactive foreground extraction using iterated graph cuts.ACM transactions on graphics (TOG), 23(3): 309–314, 2004","venue":null,"work_id":"2b24eb9a-2432-4c2c-9bed-d719a3f767c3","year":2004},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.509847Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:08d4942cc9231747290ba1d7fcc7b3686235652879a955aa9393fd802a36a7e7","observation_id":"a88b71f6-d830-4051-ab2b-f68c3d5eb555","resolution":{"observed_at":"2026-08-06T13:18:09.369854Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:09.353073Z","title":"Normalized cuts and image segmentation.IEEE Transactions on pattern analysis and machine intelligence, 22(8):888–905, 2000","venue":null,"work_id":"2f09f3c4-6926-49cf-954a-4236a0f95b7c","year":2000},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.513333Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:1b6f2f8ba05ec7f49caec37a5b2290753ac12402522aebb337dd5d1093f4ec7c","observation_id":"6cb5e04f-caed-430f-99d3-bb67e43d317a","resolution":{"observed_at":"2026-08-06T13:18:09.356825Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:09.340893Z","title":"Hierarchical image saliency detection on extended cssd.IEEE transac- tions on pattern analysis and machine intelligence, 38(4): 717–729, 2015","venue":null,"work_id":"c5937497-1a5d-4817-9c15-0bab97d1fc6b","year":2015},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.516975Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:3572f3ce85c1ed02f0117e544546178b961a20ee3e850851ddc7293ce686eb4c","observation_id":"8e112b96-9446-4b93-8d7b-f0af73e72e26","resolution":{"observed_at":"2026-08-06T13:18:09.344837Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:09.328806Z","title":"Unsuper- vised salient object detection with spectral cluster voting","venue":null,"work_id":"9dab0d53-9b98-4208-a141-65101f45446c","year":2022},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.520337Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:a57e58398a15e559c4caaf593d24b4adcf4951c0e526d71516f6d851ed91f0bb","observation_id":"97ba2deb-cf0b-4028-89f6-288b232ed58f","resolution":{"observed_at":"2026-08-06T13:18:09.332786Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:09.316426Z","title":"Localizing objects with self-supervised transformers and no labels","venue":null,"work_id":"71f32faa-ede9-497c-999b-eab8dc78e77d","year":2021},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.523831Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:ad5732c44c164b8906f6115a0fab0c40e639b51d98ef23600f50ba35e81a4fec","observation_id":"cea2322f-8429-4837-8ea2-8f0cd73987aa","resolution":{"observed_at":"2026-08-06T13:18:09.320237Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:09.303775Z","title":"Unsupervised object localization: Observing the background to discover objects","venue":null,"work_id":"cdda5e13-a3c0-4c11-96a9-a4a2a15957f8","year":2023},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.527423Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:c455ec1023c2f5666b9b020db1065b1cc13666ee9c46de4268d932f9b63d57e8","observation_id":"914831e8-1d57-4a57-a3cb-62cd9d58b32e","resolution":{"observed_at":"2026-08-06T13:18:09.307658Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:09.291940Z","title":"Semi supervised semantic segmentation using generative ad- versarial network","venue":null,"work_id":"0cf868c1-6d63-4690-86e4-c92a4c0cb004","year":2017},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.531365Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:8f16c19a839ccc29417d2c7e6bdb0c838ae8435ed5569d05765a74862d7e7893","observation_id":"63a76484-2100-47b0-ad25-1755be3ac47b","resolution":{"observed_at":"2026-08-06T13:18:09.295684Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:09.279553Z","title":"Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results.Advances in neural information processing systems, 30, 2017","venue":null,"work_id":"b7e68a3e-8dac-48a8-9329-aa1c41798ea6","year":2017},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.534826Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:d7f2100928dcbe91c4808c85f5c2dae8ca0d10c757fd8ed382bb8031c0f45805","observation_id":"bf511a1a-423a-466b-8302-18e83e8de8de","resolution":{"observed_at":"2026-08-06T13:18:09.283557Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:09.267115Z","title":"Boxinst: High-performance instance segmentation with box annotations","venue":null,"work_id":"00976ae1-ef46-4e07-9f04-a78c50e4eed7","year":2021},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.538242Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:700c13980ac7fcc9aa4fdd32021d46f1174fb3e763ce4258c3885ee5fec38f8a","observation_id":"b82c114a-1eb4-442c-98fe-447279e43b73","resolution":{"observed_at":"2026-08-06T13:18:09.271121Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:09.254604Z","title":"Selective search for object recognition.International journal of computer vision, 104: 154–171, 2013","venue":null,"work_id":"738bbfd6-2d44-411b-97d9-70b81e45d931","year":2013},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.541657Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:444d061f140675c7efcb2d668298284185caa66f6ba467bcdbcc66b94e0bf6c2","observation_id":"b5b5b91f-206f-4f20-9d7f-cfc4b0053f21","resolution":{"observed_at":"2026-08-06T13:18:09.258733Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.06363","last_updated":"2022-06-13T17:59:43Z","snapshot_observed_at":"2026-08-10T14:18:49.914171Z","submitted_at":"2022-06-13T17:59:43Z","title":"Discovering Object Masks with Transformers for Unsupervised Semantic Segmentation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.06363","snapshot_observed_at":"2026-08-06T13:18:08.545528Z","title":"Discovering object masks with transformers for unsupervised semantic segmentation.arXiv preprint arXiv:2206.06363, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.545528Z"},"links":{"cited_paper":"/paper/2206.06363","citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:edd3896f5fd4a14ec0816f0ba2b556cbef15ec78a439207a141e539726da1cb7","observation_id":"bf92eded-4d86-491e-b3f2-3a962ecd9672","resolution":{"observed_at":"2026-08-06T13:18:08.545528Z","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":"2026-08-06T13:18:09.242276Z","title":"Rapid object detection using a boosted cascade of simple features","venue":null,"work_id":"0321ebcc-b7d9-449f-97c2-41eb4c6de431","year":2001},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.549698Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:a5fd3c82b6aae2680bc68967dc51322fc81bf9925dd4ef802e21cfa284ed1db4","observation_id":"7ee7d15f-b747-4ec3-a142-4af546084042","resolution":{"observed_at":"2026-08-06T13:18:09.246242Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:09.230172Z","title":"Toward unsu- pervised, multi-object discovery in large-scale image col- lections","venue":null,"work_id":"7b9c05af-e1b0-4124-8275-72f9e033036a","year":2020},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.553317Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:6fb87b033aeb09d0c8246c461b3eae60da38c007ed660b71fc37e4f8f9778a00","observation_id":"ae2f3267-ad87-4c4e-9561-a87288dfab45","resolution":{"observed_at":"2026-08-06T13:18:09.234042Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:09.217286Z","title":"Large-scale unsupervised object dis- covery.Advances in Neural Information Processing Systems, 34:16764–16778, 2021","venue":null,"work_id":"e8fabb42-eca6-4ac4-af38-5e2470f6da20","year":2021},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.556841Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:6c781a5ec7a5c5bf0fcfe541212e7301c3b0396324439d680d6870f53148a06f","observation_id":"f9f3f308-61ba-4f58-a001-cbc1ea114b26","resolution":{"observed_at":"2026-08-06T13:18:09.221449Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:09.204339Z","title":"Object segmentation without labels with large-scale genera- tive models","venue":null,"work_id":"5039a708-a13b-4c05-85e6-495faa394b1e","year":2021},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.560490Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:71cb4b64a1c22c7ed3a95a77b2d862f4dd568214239ea6741068445e5c75cdbc","observation_id":"cb543b58-3813-487f-aee9-33fca4efd61e","resolution":{"observed_at":"2026-08-06T13:18:09.208239Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:09.192123Z","title":"Learning to de- tect salient objects with image-level supervision","venue":null,"work_id":"a20ed6bd-3324-4370-a626-25c5a7b163c6","year":2017},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.563954Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:edace1cf8f4371fc64af01afa2ec7aa80fcfcadf98e6d6a605063e36b0a2bdcb","observation_id":"3ec41961-2581-441e-a127-2c0b59f22e11","resolution":{"observed_at":"2026-08-06T13:18:09.196041Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:09.179462Z","title":"Solov2: Dynamic and fast instance segmenta- tion.Advances in Neural information processing systems, 33:17721–17732, 2020","venue":null,"work_id":"8ee8c3ca-09de-4b30-b7f5-cce007baa5c5","year":2020},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.567373Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:e0c7155c14ce46e44c64a3c96678252010bed603c101ae8ffab26878f090996e","observation_id":"385725d8-7e1b-42a1-8a5b-c3a0868e5576","resolution":{"observed_at":"2026-08-06T13:18:09.183509Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:09.166921Z","title":"Dense contrastive learning for self-supervised visual pre-training","venue":null,"work_id":"728d9282-f72a-4fad-b011-7e83bd90824d","year":2021},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.571769Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:3a4d24163a1eda26de1f38e1fcbaf7a40343743dda789825cf7d2670c71e730a","observation_id":"72e9125d-3227-4e25-a5fa-4bd7c68af005","resolution":{"observed_at":"2026-08-06T13:18:09.170657Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:09.154431Z","title":"Freesolo: Learning to segment objects without annotations","venue":null,"work_id":"0d845336-cd56-4657-ab1a-2523b5d090d1","year":2022},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.576528Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:2f3f7ff81bd25d5de62c51eef1616acfcacac25889fd0e7da6bed664e605f2fa","observation_id":"4ded3660-d566-4742-bb0f-fcb9267835ca","resolution":{"observed_at":"2026-08-06T13:18:09.158634Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:09.141683Z","title":"Contrastmask: Contrastive learn- ing to segment every thing","venue":null,"work_id":"efd19764-d828-43a5-af6b-4362140e4969","year":2022},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.580031Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:663884c151f22eb2e9609e391c3330834e591b8f2760f17263dad6558985b73f","observation_id":"89d75a68-dc5b-4126-84a9-4ccd2ab4133f","resolution":{"observed_at":"2026-08-06T13:18:09.145760Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:09.129827Z","title":"Cut and learn for unsupervised object detection and instance segmentation","venue":null,"work_id":"463ff957-5330-44a0-b2d5-06e2729b31e3","year":2023},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.583693Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:791ae93f59c3c1a5356dd735b5054f7469c300908d0b2432fefb9e645b161296","observation_id":"08db6020-82ba-4c77-9412-eed633d65dc4","resolution":{"observed_at":"2026-08-06T13:18:09.133555Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:09.117465Z","title":"Unsupervised object discovery and co-localization by deep descriptor transformation.Pattern Recognition, 88:113–126, 2019","venue":null,"work_id":"80b4bd2b-76f9-4d46-a962-ccad1e105cd7","year":2019},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.587338Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:c6a1cec520757a7101976953ad8ac3b97c705e2d2484007ecdb37e4b7d12ccf9","observation_id":"f1ad8362-020a-4218-9e20-2c8ee26a0b8e","resolution":{"observed_at":"2026-08-06T13:18:09.121422Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:09.105149Z","title":"Perturbation consistency and mutual information regularization for semi-supervised semantic seg- mentation.Multimedia Systems, 29(2):511–523, 2023","venue":null,"work_id":"00c5a4b0-355f-4bba-b4e5-c2eae3988cd0","year":2023},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.591502Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:772c65ca49ee17e180423923903297e3d352b8bde1c153f0954eb15cd5856649","observation_id":"86909480-c093-4a77-8cf2-c0e5fb5ffe46","resolution":{"observed_at":"2026-08-06T13:18:09.109132Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:09.092503Z","title":"Leveraging auxiliary tasks with affinity learning for weakly supervised semantic segmentation","venue":null,"work_id":"2a16c713-0733-4cc7-994e-f2330af1878c","year":2021},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.595406Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:22f01dada3a668a3b3f2fc68a9f3fa3f3f483a8d7f341bdceedd50c144c766c3","observation_id":"f856ac65-206a-4920-9c1e-25a77bc45b50","resolution":{"observed_at":"2026-08-06T13:18:09.096822Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:09.080343Z","title":"Hierarchical saliency detection","venue":null,"work_id":"d219bc65-a743-4cc5-a3a1-1cde3fec1cdb","year":null},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.598825Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:a462a9ab583ff60c6b8e05dda10d9e4b059e2977692a5bc5acd9ff5148df1538","observation_id":"e42c63ad-c5dd-4106-abd0-3794e35c339e","resolution":{"observed_at":"2026-08-06T13:18:09.083904Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:09.067962Z","title":"Saliency detection via graph-based man- ifold ranking","venue":null,"work_id":"79c508c7-9364-4693-9894-e2b397570b23","year":null},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.602436Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:a70d7c0bb417f1bc762cc16672e82ef3b3153f17a22930a7912e3ba7963e49d1","observation_id":"a688f42f-9353-4afe-8631-ba4509915a91","resolution":{"observed_at":"2026-08-06T13:18:09.071997Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:09.055616Z","title":"Object discovery from a single unlabeled image by mining frequent itemsets with multi-scale features.IEEE Transactions on Image Pro- cessing, 29:8606–8621, 2020","venue":null,"work_id":"a233fb45-e583-430b-93b7-3484ac61e1fd","year":2020},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.606502Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:8f735031392c8c1e6ec52e25a87efdb0822a2ba4638f1d2c96baec6de283973a","observation_id":"eec3c238-89bd-4c5b-8bf3-5d968ff6bab8","resolution":{"observed_at":"2026-08-06T13:18:09.059558Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:09.043164Z","title":"Image bert pre-training with online tokenizer","venue":null,"work_id":"c15e9249-9980-461d-a7c5-7852892206f7","year":2021},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.610096Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:6a3c5df26aad83455380ec3e1d96964180a944839fe8e00e65862847ec70facb","observation_id":"0bef04c6-f30d-4536-8497-8245f2f48c99","resolution":{"observed_at":"2026-08-06T13:18:09.047520Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:09.031236Z","title":"Saliency optimization from robust background detection","venue":null,"work_id":"607e64ec-579e-4cfe-ba71-94484f3bc04e","year":2014},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.614191Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:49b67bf5e9d56393eb710055f86b24a0aa40223afe6510ae412d069254cdd651","observation_id":"16b898de-aedc-451e-80bc-95d90ef962e3","resolution":{"observed_at":"2026-08-06T13:18:09.035091Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2010.04159","last_updated":"2021-03-18T03:14:26Z","snapshot_observed_at":"2026-07-06T10:02:45.105181Z","submitted_at":"2020-10-08T17:59:21Z","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.04159","snapshot_observed_at":"2026-08-06T13:18:08.617684Z","title":"Deformable detr: Deformable trans- formers for end-to-end object detection.arXiv preprint arXiv:2010.04159, 2020","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.617684Z"},"links":{"cited_paper":"/paper/2010.04159","citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:f0199c840d0daf3d579f0b7b151895987b36f637ae70ea6ce49c7d5f482c8496","observation_id":"a0150376-10e2-4948-83f1-86b17b0246a1","resolution":{"observed_at":"2026-08-06T13:18:08.617684Z","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":"2026-08-06T13:18:09.019366Z","title":"Deep learning in remote sensing: A comprehensive review and list of resources.IEEE geoscience and remote sensing magazine, 5(4):8–36, 2017","venue":null,"work_id":"9a9d04d9-3ea7-4d2e-9693-4fe166e310f4","year":2017},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.621543Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:868bddc3f89c9a76d917284fc92f3128085d5ac84189a6a8d9c2ab3502ece539","observation_id":"5fb20a3b-5a79-4b5e-9b1f-ccda56d2a3e4","resolution":{"observed_at":"2026-08-06T13:18:09.023247Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:09.005787Z","title":"Edge boxes: Lo- cating object proposals from edges","venue":null,"work_id":"8d7aa90b-1bb1-41c9-ab35-729e3ec721e3","year":2014},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.625101Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:7e8f53b82e25ecf197505829b0e78f0c45140e261589bbd731593bb85da4c5e5","observation_id":"77f7fbd6-e01e-4359-96d1-ea145961ffc3","resolution":{"observed_at":"2026-08-06T13:18:09.009761Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:08.993728Z","title":null,"venue":null,"work_id":"089edab6-5a17-4637-9c13-f6c7871c097d","year":1981},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.628645Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:e65acd8f4e8df5cf198ee7ff8863b2c1f63c002d1fdd11a3e4a5a02af5a3be7a","observation_id":"6e468e4f-8d83-48db-a936-0fdf0478205b","resolution":{"observed_at":"2026-08-06T13:18:08.997529Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:08.981456Z","title":"3.2 that UnionCut can stay effective on images of large foreground areas","venue":null,"work_id":"ac04d892-7aec-4e2b-b8b4-4031689e8c16","year":1968},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.632512Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:49a0978f3762ce26e9182cfc79489883f5c1bbdeafc6fac0713d0de7fa561048","observation_id":"e3211b32-7f20-49ee-8076-f39275f5cc8e","resolution":{"observed_at":"2026-08-06T13:18:08.985534Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:08.968783Z","title":"Here, we make matching similar patches with cosine similarity used by [53, 54, 59] as an example","venue":null,"work_id":"c5f492e8-8eb4-42c5-a824-b02aff675441","year":null},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.636988Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:e5d604465493a3bca8a5b642b73aa9561a479b404c38613f851b1b3cca9a9e7f","observation_id":"e409d31d-222a-43b9-87c2-8ca609e0b90d","resolution":{"observed_at":"2026-08-06T13:18:08.972872Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:08.956018Z","title":"Specifically, we calculate the success rate by assessing the proportion of images in each dataset where the union of the ground truth occupies less than four corners of the image","venue":null,"work_id":"b1f48960-fdc2-430a-b8b8-a25a66f6f3ad","year":null},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.640899Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:ba2a83dbe93d1ce1f767b271fb76fb6c929c08908a659ff16efb4cadb144e8bf","observation_id":"b274ad02-1d71-408c-8a88-a1b90b6e7074","resolution":{"observed_at":"2026-08-06T13:18:08.960188Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:08.944084Z","title":"UnionSeg Fig","venue":null,"work_id":"d444d8af-f7b1-4bdf-872d-f2ca9bcb7830","year":null},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.645443Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:4394b945e7d522a6a1e8dcc6068e58066476e667287868b3302c0da8648a9f92","observation_id":"85929d07-2381-4941-a527-390bd06d9330","resolution":{"observed_at":"2026-08-06T13:18:08.947965Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:08.932408Z","title":null,"venue":null,"work_id":"da9aa0d8-a961-48bf-8b44-756b5692ad2a","year":null},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.649025Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:f06ab140521430fccd1e4653596b56096d22d11b4b4a6e3f332763c210e24ad5","observation_id":"1de7836f-8f10-48fe-946d-ce3c4a0e886d","resolution":{"observed_at":"2026-08-06T13:18:08.935952Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:08.919636Z","title":"In contrast, UnionSeg's pseudo- labels are generated by UnionCut and are designed to cover most of the object regions in the image, i.e., the foreground union","venue":null,"work_id":"33132562-2f1e-43fc-bc2a-fde912c0c322","year":null},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.652999Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:8c9afdfafe6e16c8b005f4e070f6453aa2f4de435dd02e14700aa2fe305d3fad","observation_id":"f5bbe58a-c912-4ddf-b57d-37ac172c4c52","resolution":{"observed_at":"2026-08-06T13:18:08.923928Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:08.906936Z","title":"The comparison of the framework between FOUND [54] and UnionSeg","venue":null,"work_id":"d562d4a3-9a1b-4ae6-8936-d19c46cedf81","year":null},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.656538Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:46748c3b0c4c2cd4eb8656e6641eab0b8c0a39210fb15c09a38a66e18ddfa5d2","observation_id":"2e161d54-2417-4e6c-8756-8f58f9452253","resolution":{"observed_at":"2026-08-06T13:18:08.910974Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:08.894262Z","title":"In this section, we intro- duce how to apply UnionCut/UnionSeg to existing UOD methods","venue":null,"work_id":"04bf5983-7b9b-446c-9c3a-10f055d39d22","year":null},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.659976Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:58cb146b7afd74f8f642ab254dab4aaebd55f9f843479366009ca1b6fc13ffaf","observation_id":"e694fa2b-9805-4262-a835-0f14b11996fd","resolution":{"observed_at":"2026-08-06T13:18:08.898097Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:08.882342Z","title":null,"venue":null,"work_id":"a3fbc816-689e-4c89-b86e-d69fc7cb7b4c","year":null},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.663590Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:cd0d55c75856618bbb73e5c51a75cbcfcfe2b1d1d9e65716e16de664f783d00e","observation_id":"5c2ca03f-1566-44a8-ad72-87313e6f59ef","resolution":{"observed_at":"2026-08-06T13:18:08.885861Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:08.868841Z","title":"80% area) of the foreground union given by UnionCut or UnionSeg has been discovered","venue":null,"work_id":"abdb63ac-6ad8-477c-90e8-2f5a3c8e30b0","year":null},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.667204Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:995397618624009ddaceecba6d73c5141a6a2a56c61035b9a67da7e9f049aca6","observation_id":"776a8290-3432-4408-a319-354dddf1604f","resolution":{"observed_at":"2026-08-06T13:18:08.873198Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:08.855231Z","title":"the num- ber of links connected to a patch) in ascending order, and the first patch after being sorted is made as the foreground seed based on the assumption made by Sim ´eoniet al","venue":null,"work_id":"1010309f-9c53-4489-aca6-84e2a7380583","year":null},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.670511Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:aa77aa70335b88b363e7cd312601b584039068a5c69be3965801d7a5f0a1edf6","observation_id":"116741e1-2526-425d-9351-1f257e3b5f34","resolution":{"observed_at":"2026-08-06T13:18:08.859345Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:08.842771Z","title":null,"venue":null,"work_id":"125349f8-6dbc-4a7d-804b-047cdcf92281","year":null},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.674156Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:7f2410568d7ed58096c4c34d32cbe88fa44f2de779704d0cc3e38c88360b59b9","observation_id":"bca4f03d-4d88-42d9-958f-6daae3a0ae12","resolution":{"observed_at":"2026-08-06T13:18:08.846669Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:08.829549Z","title":"After that, these pseudo- labels are used to train a class-agnostic SOLOv2 [65] model","venue":null,"work_id":"c09b4235-6099-483b-974b-1159d6c06438","year":null},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":94,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.678155Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:ad6f5d7b610599cba034fcfeebe6cc6d9ee8566bfaa7f145b1906133985d22f7","observation_id":"10041892-7bac-44ae-9513-2d729d6abfbd","resolution":{"observed_at":"2026-08-06T13:18:08.833606Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:08.817067Z","title":"As shown in Fig","venue":null,"work_id":"768296e3-7536-461c-a076-d132854f2390","year":null},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":95,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.681682Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:b64c6b44d5416c2cde218006fb424fdbf59c869c0a7a765c2d912099b1ec06ae","observation_id":"c9bf6dd3-87a3-4139-90b4-4ecf8cc5bd83","resolution":{"observed_at":"2026-08-06T13:18:08.820823Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T13:18:08.804123Z","title":"TokenCut and MaskCut, and provide more visualization","venue":null,"work_id":"b65b41a3-36c6-497c-97e4-5e5304fca172","year":null},"citing_paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery","version":1},"reference_index":96,"source":"pdf_text","source_observed_at":"2026-08-06T13:18:08.685205Z"},"links":{"citing_paper":"/paper/2507.20860"},"observation_digest":"sha256:bf71db28e0517f415a3a1b75208dd4de0226913cca856501546d5821275fffcc","observation_id":"9f5796ef-dbd9-4516-958a-71ae51dcabef","resolution":{"observed_at":"2026-08-06T13:18:08.808124Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2507.20860","last_updated":"2025-07-28T14:14:06Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-06T13:18:06.612066Z","submitted_at":"2025-07-28T14:14:06Z","title":"Ensemble Foreground Management for Unsupervised Object Discovery"},"reference_resolution":{"displayed":96,"state_counts":{"malformed_identifier":2,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":29,"verified_exact":1,"verified_fuzzy":64},"total_outbound_references":96},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 96 of 96 outbound references and 0 inbound Pith citation observations for arXiv:2507.20860."}