{"as_of":"2026-08-17T19:06:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c4cd07a96634b4f8001683439307d2bb0a846399479f93672956fcc516f24bad","coverage":[{"denominator":38,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":38,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T20:25:36.289108Z","state":"measured"},{"denominator":38,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":38,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-17T06:30:58.91139+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/2505.13099/citation-record","integrity":"/paper/2505.13099/integrity","json":"/paper/2505.13099/citation-record.json","paper":"/paper/2505.13099"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:25:36.887632Z","title":"Synthseg: Segmentation of brain mri scans of any contrast and resolution without retraining","venue":null,"work_id":"7b4fefab-0dc3-4952-8b84-12264942ebec","year":2023},"citing_paper":{"arxiv_id":"2505.13099","last_updated":"2025-05-20T05:42:28Z","snapshot_observed_at":"2026-08-16T05:06:32.096250Z","submitted_at":"2025-05-19T13:29:40Z","title":"Industrial Synthetic Segment Pre-training","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T20:25:36.140188Z"},"links":{"citing_paper":"/paper/2505.13099"},"observation_digest":"sha256:2753f0a651b82d9acf45b31c28e83c566288c768b8ace3f17df2dc88ed729d90","observation_id":"87d0b158-e064-4cba-805f-526317c04d5d","resolution":{"observed_at":"2026-08-15T20:25:36.891669Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:25:36.874658Z","title":"Into the laion’s den: Investigating hate in multimodal datasets","venue":null,"work_id":"039df8c1-9508-4fc8-a106-a0d3d7790881","year":2023},"citing_paper":{"arxiv_id":"2505.13099","last_updated":"2025-05-20T05:42:28Z","snapshot_observed_at":"2026-08-16T05:06:32.096250Z","submitted_at":"2025-05-19T13:29:40Z","title":"Industrial Synthetic Segment Pre-training","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T20:25:36.145043Z"},"links":{"citing_paper":"/paper/2505.13099"},"observation_digest":"sha256:772e305a28344053d9a9b1ff6c20733b26aae7ebfe1d6f9103023c6a36d2cc32","observation_id":"1f36d1d7-eaa4-4195-a6fc-0cfad93b1469","resolution":{"observed_at":"2026-08-15T20:25:36.878925Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:25:36.861371Z","title":"Yolact: Real-time instance seg- mentation","venue":null,"work_id":"1a518b65-8f10-4457-a6df-dfd655d9bbe4","year":2019},"citing_paper":{"arxiv_id":"2505.13099","last_updated":"2025-05-20T05:42:28Z","snapshot_observed_at":"2026-08-16T05:06:32.096250Z","submitted_at":"2025-05-19T13:29:40Z","title":"Industrial Synthetic Segment Pre-training","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T20:25:36.149243Z"},"links":{"citing_paper":"/paper/2505.13099"},"observation_digest":"sha256:1ca5cc0e4981e45b44cb29bcb724127d4414af536757da87956186866593c475","observation_id":"68ab61bb-b4c3-456e-8b13-cfa19bb7bf01","resolution":{"observed_at":"2026-08-15T20:25:36.865512Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:25:36.153578Z","title":"Emerging properties in self-supervised vision transformers","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.13099","last_updated":"2025-05-20T05:42:28Z","snapshot_observed_at":"2026-08-16T05:06:32.096250Z","submitted_at":"2025-05-19T13:29:40Z","title":"Industrial Synthetic Segment Pre-training","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T20:25:36.153578Z"},"links":{"citing_paper":"/paper/2505.13099"},"observation_digest":"sha256:206e9c2a2c636afb0e05312bf39f76c751de70f84e1713d529a619a9a3656e2d","observation_id":"ab8332a7-548e-416d-bea3-70db8929bfe5","resolution":{"observed_at":"2026-08-15T20:25:36.153578Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1906.07155","last_updated":"2019-06-17T17:58:12Z","snapshot_observed_at":"2026-08-16T03:32:25.570081Z","submitted_at":"2019-06-17T17:58:12Z","title":"MMDetection: Open MMLab Detection Toolbox and Benchmark","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1906.07155","snapshot_observed_at":"2026-08-15T20:25:36.157935Z","title":"MMDetection: Open mmlab detection toolbox and benchmark","venue":null,"work_id":null,"year":1906},"citing_paper":{"arxiv_id":"2505.13099","last_updated":"2025-05-20T05:42:28Z","snapshot_observed_at":"2026-08-16T05:06:32.096250Z","submitted_at":"2025-05-19T13:29:40Z","title":"Industrial Synthetic Segment Pre-training","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T20:25:36.157935Z"},"links":{"cited_paper":"/paper/1906.07155","citing_paper":"/paper/2505.13099"},"observation_digest":"sha256:345894543d20d0aca0d955a06c3a6decdc28ba6d36a0759c3d54fd01fd3f961a","observation_id":"c5292151-a0f4-477b-a412-f615426d6ef1","resolution":{"observed_at":"2026-08-15T20:25:36.157935Z","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":"2026-08-15T20:25:36.838087Z","title":"Learning semantic segmentation from synthetic data: A geometrically guided input-output adaptation approach","venue":null,"work_id":"797b0620-54e8-4db4-b962-612377512e0d","year":2019},"citing_paper":{"arxiv_id":"2505.13099","last_updated":"2025-05-20T05:42:28Z","snapshot_observed_at":"2026-08-16T05:06:32.096250Z","submitted_at":"2025-05-19T13:29:40Z","title":"Industrial Synthetic Segment Pre-training","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T20:25:36.162445Z"},"links":{"citing_paper":"/paper/2505.13099"},"observation_digest":"sha256:9d1c6eeae5e84e8a46bb76eae413f7c80437dd8c5edb947fcbef6596824a130d","observation_id":"d861481e-db08-44df-b1a3-41ad6eddba69","resolution":{"observed_at":"2026-08-15T20:25:36.842678Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:25:36.824944Z","title":"Masked-attention mask transformer for universal image segmentation","venue":null,"work_id":"dd6c6e9d-38aa-48f3-acc3-acc1a3df6adc","year":2022},"citing_paper":{"arxiv_id":"2505.13099","last_updated":"2025-05-20T05:42:28Z","snapshot_observed_at":"2026-08-16T05:06:32.096250Z","submitted_at":"2025-05-19T13:29:40Z","title":"Industrial Synthetic Segment Pre-training","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T20:25:36.166974Z"},"links":{"citing_paper":"/paper/2505.13099"},"observation_digest":"sha256:fa0a77c3d5eec0e0ece5eabe61f670472716efbed318e6b21d2a29d2063e2f90","observation_id":"f2d3be73-bd73-4090-bf7f-cfdfd371dffb","resolution":{"observed_at":"2026-08-15T20:25:36.829353Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:25:36.171090Z","title":"Imagenet: A large- scale hierarchical image database","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2505.13099","last_updated":"2025-05-20T05:42:28Z","snapshot_observed_at":"2026-08-16T05:06:32.096250Z","submitted_at":"2025-05-19T13:29:40Z","title":"Industrial Synthetic Segment Pre-training","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T20:25:36.171090Z"},"links":{"citing_paper":"/paper/2505.13099"},"observation_digest":"sha256:9c695b75ab23eda4b5a7f7f56d5edb3aab20b83f6ccc129738a80dab13521dcb","observation_id":"fc8d747c-b318-45c3-8c6c-39b8411101d6","resolution":{"observed_at":"2026-08-15T20:25:36.171090Z","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":"2026-08-15T20:25:36.803587Z","title":"Decaf: A deep convolutional activation feature for generic visual recognition","venue":null,"work_id":"e806efbb-597a-47b6-ab4d-f7e196287d6c","year":2014},"citing_paper":{"arxiv_id":"2505.13099","last_updated":"2025-05-20T05:42:28Z","snapshot_observed_at":"2026-08-16T05:06:32.096250Z","submitted_at":"2025-05-19T13:29:40Z","title":"Industrial Synthetic Segment Pre-training","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T20:25:36.174896Z"},"links":{"citing_paper":"/paper/2505.13099"},"observation_digest":"sha256:0d421d360ef6a49fcefd050fbbc3bc1c3444f6e0aa4ccafea8372e4bd9d29559","observation_id":"7d91baed-1703-4b46-b5fd-fbd1008c08d3","resolution":{"observed_at":"2026-08-15T20:25:36.807674Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:25:36.790912Z","title":"Livecell—a large-scale dataset for label-free live cell segmentation","venue":null,"work_id":"462d09d7-52b6-4d79-bd66-57d774f3bc1e","year":2021},"citing_paper":{"arxiv_id":"2505.13099","last_updated":"2025-05-20T05:42:28Z","snapshot_observed_at":"2026-08-16T05:06:32.096250Z","submitted_at":"2025-05-19T13:29:40Z","title":"Industrial Synthetic Segment Pre-training","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T20:25:36.178990Z"},"links":{"citing_paper":"/paper/2505.13099"},"observation_digest":"sha256:a12b39f52b3fb9c89748e3ec261bc2ec52d2437d72c231030d7ec5c02df3e4bd","observation_id":"3d156b0c-655a-4258-a9e0-d4655d8a9867","resolution":{"observed_at":"2026-08-15T20:25:36.795062Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:25:36.182615Z","title":"Mask r-cnn","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.13099","last_updated":"2025-05-20T05:42:28Z","snapshot_observed_at":"2026-08-16T05:06:32.096250Z","submitted_at":"2025-05-19T13:29:40Z","title":"Industrial Synthetic Segment Pre-training","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T20:25:36.182615Z"},"links":{"citing_paper":"/paper/2505.13099"},"observation_digest":"sha256:bf8b11ca3a6184e3f2ae1442833322a429b25e9922416ca4ec43135ffd9b2015","observation_id":"8f6826ac-170d-48a1-a647-3e7cd05d4796","resolution":{"observed_at":"2026-08-15T20:25:36.182615Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.09324","last_updated":"2023-05-05T18:58:52Z","snapshot_observed_at":"2026-08-17T14:25:32.657046Z","submitted_at":"2023-04-18T22:16:49Z","title":"Computer-Vision Benchmark Segment-Anything Model (SAM) in Medical Images: Accuracy in 12 Datasets","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.09324","snapshot_observed_at":"2026-08-15T20:25:36.186543Z","title":"Computer-vision benchmark segment-anything model (sam) in medical images: Accuracy in 12 datasets","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.13099","last_updated":"2025-05-20T05:42:28Z","snapshot_observed_at":"2026-08-16T05:06:32.096250Z","submitted_at":"2025-05-19T13:29:40Z","title":"Industrial Synthetic Segment Pre-training","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T20:25:36.186543Z"},"links":{"cited_paper":"/paper/2304.09324","citing_paper":"/paper/2505.13099"},"observation_digest":"sha256:b7aadea2582fba33107f851841d92298bdc828b7386f7e6b7acf7a00ec0e3190","observation_id":"2c49b033-75dd-438d-9c78-b6b1bf83a6f4","resolution":{"observed_at":"2026-08-15T20:25:36.186543Z","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":"2026-08-15T20:25:36.768101Z","title":"Segment anything is not always perfect: An investigation of sam on different real-world applications, 2024","venue":null,"work_id":"7baec5e1-70b2-4194-b6c4-44c3950437db","year":2024},"citing_paper":{"arxiv_id":"2505.13099","last_updated":"2025-05-20T05:42:28Z","snapshot_observed_at":"2026-08-16T05:06:32.096250Z","submitted_at":"2025-05-19T13:29:40Z","title":"Industrial Synthetic Segment Pre-training","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T20:25:36.190726Z"},"links":{"citing_paper":"/paper/2505.13099"},"observation_digest":"sha256:3973b45f5f67122ac26f8bc8a550e34e71ac0788ef78fb3fac9591571e6687df","observation_id":"ef2b773e-e28d-4b2d-a044-c70b24721a08","resolution":{"observed_at":"2026-08-15T20:25:36.772457Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:25:36.755171Z","title":"Pre-training without natural images","venue":null,"work_id":"287e0fa7-9066-4d13-b9a6-ba8ccb0e568b","year":2020},"citing_paper":{"arxiv_id":"2505.13099","last_updated":"2025-05-20T05:42:28Z","snapshot_observed_at":"2026-08-16T05:06:32.096250Z","submitted_at":"2025-05-19T13:29:40Z","title":"Industrial Synthetic Segment Pre-training","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T20:25:36.194392Z"},"links":{"citing_paper":"/paper/2505.13099"},"observation_digest":"sha256:e37fb449f1643eec5c0ace005bfbb6a7bbd12515a92fb8e8074397fca6d7826b","observation_id":"6d10c17c-a93c-481d-8ed3-bd682f2ba01c","resolution":{"observed_at":"2026-08-15T20:25:36.759367Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:25:36.741718Z","title":"Pre-training without natural images","venue":null,"work_id":"a23db54f-d8af-4510-abb7-bdd9eff8a778","year":2020},"citing_paper":{"arxiv_id":"2505.13099","last_updated":"2025-05-20T05:42:28Z","snapshot_observed_at":"2026-08-16T05:06:32.096250Z","submitted_at":"2025-05-19T13:29:40Z","title":"Industrial Synthetic Segment Pre-training","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T20:25:36.198260Z"},"links":{"citing_paper":"/paper/2505.13099"},"observation_digest":"sha256:63d0142d1b7932ec8d4abc17f8cbd35fd56743862d3ef74d1dd7d6f8941defdb","observation_id":"4be97f9a-fa91-47c2-b305-5a40494b11b5","resolution":{"observed_at":"2026-08-15T20:25:36.746231Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:25:36.728544Z","title":"Formula-driven supervised learning with recursive tiling patterns","venue":null,"work_id":"51840604-44f9-430e-83e3-d82bcb760c03","year":2021},"citing_paper":{"arxiv_id":"2505.13099","last_updated":"2025-05-20T05:42:28Z","snapshot_observed_at":"2026-08-16T05:06:32.096250Z","submitted_at":"2025-05-19T13:29:40Z","title":"Industrial Synthetic Segment Pre-training","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T20:25:36.202150Z"},"links":{"citing_paper":"/paper/2505.13099"},"observation_digest":"sha256:d030761cab4c762be4ef8f7a42aeffa4894eee2f1694f23f4ce2b2bcc0d9bffc","observation_id":"8ffbffae-03ad-41a8-b6d7-9fcb5ea56f46","resolution":{"observed_at":"2026-08-15T20:25:36.732811Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:25:36.715456Z","title":"Replacing labeled real-image datasets with auto-generated contours","venue":null,"work_id":"e332c961-497f-413b-83a8-1662e261aa66","year":2022},"citing_paper":{"arxiv_id":"2505.13099","last_updated":"2025-05-20T05:42:28Z","snapshot_observed_at":"2026-08-16T05:06:32.096250Z","submitted_at":"2025-05-19T13:29:40Z","title":"Industrial Synthetic Segment Pre-training","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T20:25:36.206081Z"},"links":{"citing_paper":"/paper/2505.13099"},"observation_digest":"sha256:210507cd3f559060ac1d689779825a429833c1291d9274f7258cd63874d28cad","observation_id":"06cb3762-b067-44a3-a21b-7ec74d6a1f57","resolution":{"observed_at":"2026-08-15T20:25:36.719741Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:25:36.209958Z","title":"Segment anything","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.13099","last_updated":"2025-05-20T05:42:28Z","snapshot_observed_at":"2026-08-16T05:06:32.096250Z","submitted_at":"2025-05-19T13:29:40Z","title":"Industrial Synthetic Segment Pre-training","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T20:25:36.209958Z"},"links":{"citing_paper":"/paper/2505.13099"},"observation_digest":"sha256:e2567dd0a1a8665118c4774edb54ca54193d753baa7d090a235a0a2fd9d7d33a","observation_id":"0c209a0a-4d50-4e08-9c05-2858c120b1ab","resolution":{"observed_at":"2026-08-15T20:25:36.209958Z","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":"2026-08-15T20:25:36.693676Z","title":"Industrial-iseg dataset, August 2024","venue":null,"work_id":"075eebde-c8fb-4b9b-9920-fb892b869bd0","year":2024},"citing_paper":{"arxiv_id":"2505.13099","last_updated":"2025-05-20T05:42:28Z","snapshot_observed_at":"2026-08-16T05:06:32.096250Z","submitted_at":"2025-05-19T13:29:40Z","title":"Industrial Synthetic Segment Pre-training","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T20:25:36.213936Z"},"links":{"citing_paper":"/paper/2505.13099"},"observation_digest":"sha256:0c7456b1e581bbdfc9fca87701098b38d8831e3b0b2d9d4583c217a4ee61dee5","observation_id":"c492c97a-007b-4c56-88cb-46f2135da08a","resolution":{"observed_at":"2026-08-15T20:25:36.697641Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:25:36.217832Z","title":"Microsoft coco: Common objects in context","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2505.13099","last_updated":"2025-05-20T05:42:28Z","snapshot_observed_at":"2026-08-16T05:06:32.096250Z","submitted_at":"2025-05-19T13:29:40Z","title":"Industrial Synthetic Segment Pre-training","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T20:25:36.217832Z"},"links":{"citing_paper":"/paper/2505.13099"},"observation_digest":"sha256:882c6ba9c8b475980cfe3ad4cfcb4c785c1b006e1021538d48bb1f5977000642","observation_id":"a9e51dc5-907a-4605-b85f-6a267a5afb35","resolution":{"observed_at":"2026-08-15T20:25:36.217832Z","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":"2026-08-15T20:25:36.221554Z","title":"Swin transformer: Hierarchical vision transformer using shifted windows","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.13099","last_updated":"2025-05-20T05:42:28Z","snapshot_observed_at":"2026-08-16T05:06:32.096250Z","submitted_at":"2025-05-19T13:29:40Z","title":"Industrial Synthetic Segment Pre-training","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T20:25:36.221554Z"},"links":{"citing_paper":"/paper/2505.13099"},"observation_digest":"sha256:1f250c4e7ab0cc88bc83247f20acfec680a54eeff75cae09bf5ebbf1b5eb8e37","observation_id":"50a57b56-e38b-494e-9d1f-ae8174aaef0e","resolution":{"observed_at":"2026-08-15T20:25:36.221554Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2212.07784","last_updated":"2022-12-16T09:47:56Z","snapshot_observed_at":"2026-08-16T16:08:37.538344Z","submitted_at":"2022-12-14T18:50:20Z","title":"RTMDet: An Empirical Study of Designing Real-Time Object Detectors","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.07784","snapshot_observed_at":"2026-08-15T20:25:36.225452Z","title":"Rtmdet: An empirical study of designing real-time object detectors.arXiv preprint arXiv:2212.07784, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.13099","last_updated":"2025-05-20T05:42:28Z","snapshot_observed_at":"2026-08-16T05:06:32.096250Z","submitted_at":"2025-05-19T13:29:40Z","title":"Industrial Synthetic Segment Pre-training","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T20:25:36.225452Z"},"links":{"cited_paper":"/paper/2212.07784","citing_paper":"/paper/2505.13099"},"observation_digest":"sha256:fca6d4ea71a6925f23e0eaec727dc58eca53da8808e7e85d02da092a1e7ad08c","observation_id":"6d28a545-2a1d-47ae-96e8-ae9d8cc0a0cb","resolution":{"observed_at":"2026-08-15T20:25:36.225452Z","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":"2026-08-15T20:25:36.664342Z","title":"Efficient load interference detection with limited labeled data","venue":null,"work_id":"c7126b8a-76ed-4a99-877c-1fdfe2122054","year":2025},"citing_paper":{"arxiv_id":"2505.13099","last_updated":"2025-05-20T05:42:28Z","snapshot_observed_at":"2026-08-16T05:06:32.096250Z","submitted_at":"2025-05-19T13:29:40Z","title":"Industrial Synthetic Segment Pre-training","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T20:25:36.229797Z"},"links":{"citing_paper":"/paper/2505.13099"},"observation_digest":"sha256:96a87a1133352ab4cb846bca773db5c26d8e551ca4bf66b65ed831c0f387e3cf","observation_id":"c05be703-7972-42a1-be78-7e7716278ca8","resolution":{"observed_at":"2026-08-15T20:25:36.668337Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:25:36.651986Z","title":"lightning-sam","venue":null,"work_id":"11f1c873-9bbf-4c79-9b90-cf61ebb4ae00","year":2023},"citing_paper":{"arxiv_id":"2505.13099","last_updated":"2025-05-20T05:42:28Z","snapshot_observed_at":"2026-08-16T05:06:32.096250Z","submitted_at":"2025-05-19T13:29:40Z","title":"Industrial Synthetic Segment Pre-training","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T20:25:36.233379Z"},"links":{"citing_paper":"/paper/2505.13099"},"observation_digest":"sha256:a833c78d22620e54d59db1671d3a219e338b15356a2e1f1368dba7c215890917","observation_id":"71dd9d13-4f80-43c0-a641-f059885ae11d","resolution":{"observed_at":"2026-08-15T20:25:36.656085Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:25:36.639440Z","title":"Adversarial learn- ing and self-teaching techniques for domain adaptation in semantic segmentation","venue":null,"work_id":"f0cccf01-49f0-49db-bac6-1e0ced74c7f2","year":2020},"citing_paper":{"arxiv_id":"2505.13099","last_updated":"2025-05-20T05:42:28Z","snapshot_observed_at":"2026-08-16T05:06:32.096250Z","submitted_at":"2025-05-19T13:29:40Z","title":"Industrial Synthetic Segment Pre-training","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T20:25:36.237283Z"},"links":{"citing_paper":"/paper/2505.13099"},"observation_digest":"sha256:052ab59e2f4c214c049ee3629cfc7f57eb21d6b9d4beb47cb183abeaad83f3e6","observation_id":"1b99ae5d-5c07-4911-8228-12a08404ddd1","resolution":{"observed_at":"2026-08-15T20:25:36.643589Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:25:36.626808Z","title":"Task2sim: Towards effective pre-training and transfer from synthetic data","venue":null,"work_id":"801ee5f4-4c42-445a-892c-f3f31374418a","year":2022},"citing_paper":{"arxiv_id":"2505.13099","last_updated":"2025-05-20T05:42:28Z","snapshot_observed_at":"2026-08-16T05:06:32.096250Z","submitted_at":"2025-05-19T13:29:40Z","title":"Industrial Synthetic Segment Pre-training","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T20:25:36.241225Z"},"links":{"citing_paper":"/paper/2505.13099"},"observation_digest":"sha256:e5ac813495c9f4ef9923dbf14790049aa430a914a27ce3b7a00f7c7c94a8354f","observation_id":"6bccc9f8-404a-4b0a-93d4-f2c1e7cf1187","resolution":{"observed_at":"2026-08-15T20:25:36.630936Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.12429","last_updated":"2024-10-25T17:28:43Z","snapshot_observed_at":"2026-08-16T14:33:14.319224Z","submitted_at":"2023-12-19T18:56:44Z","title":"The Endoscapes Dataset for Surgical Scene Segmentation, Object Detection, and Critical View of Safety Assessment: Official Splits and Benchmark","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.12429","snapshot_observed_at":"2026-08-15T20:25:36.244982Z","title":"The endoscapes dataset for surgical scene segmentation, object detection, and critical view of safety assessment: official splits and benchmark","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.13099","last_updated":"2025-05-20T05:42:28Z","snapshot_observed_at":"2026-08-16T05:06:32.096250Z","submitted_at":"2025-05-19T13:29:40Z","title":"Industrial Synthetic Segment Pre-training","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T20:25:36.244982Z"},"links":{"cited_paper":"/paper/2312.12429","citing_paper":"/paper/2505.13099"},"observation_digest":"sha256:0d2307d2906288524c9f013fd223f0ef68ee809ab6bdad3f5085f509e21d5c82","observation_id":"498cea29-1615-4638-a888-a79f4f5d0fe1","resolution":{"observed_at":"2026-08-15T20:25:36.244982Z","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":"2026-08-15T20:25:36.613929Z","title":"The segment anything model (sam) for remote sensing applications: From zero to one shot","venue":null,"work_id":"0a7cec8c-9d6b-413f-80ae-0f85810b0dcc","year":2023},"citing_paper":{"arxiv_id":"2505.13099","last_updated":"2025-05-20T05:42:28Z","snapshot_observed_at":"2026-08-16T05:06:32.096250Z","submitted_at":"2025-05-19T13:29:40Z","title":"Industrial Synthetic Segment Pre-training","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-15T20:25:36.249755Z"},"links":{"citing_paper":"/paper/2505.13099"},"observation_digest":"sha256:ec869c628e3e29f9fbff05f606514325e16849993af05e8f04ef1df23a6633b6","observation_id":"46a07838-3024-490e-ae41-c833eea4461b","resolution":{"observed_at":"2026-08-15T20:25:36.617944Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:25:36.600975Z","title":"Segrcdb: Semantic segmentation via formula-driven supervised learning","venue":null,"work_id":"b9f87643-1ad4-4585-b238-982b275b4cbf","year":2023},"citing_paper":{"arxiv_id":"2505.13099","last_updated":"2025-05-20T05:42:28Z","snapshot_observed_at":"2026-08-16T05:06:32.096250Z","submitted_at":"2025-05-19T13:29:40Z","title":"Industrial Synthetic Segment Pre-training","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T20:25:36.253613Z"},"links":{"citing_paper":"/paper/2505.13099"},"observation_digest":"sha256:9929a333a6cfa886f39a1145ae9eaf812563cf52b7f8cf685ac2eef05418ef9a","observation_id":"41186c70-0f3f-4f5f-b67b-08557fecf231","resolution":{"observed_at":"2026-08-15T20:25:36.605216Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:25:36.588276Z","title":"Visual atoms: Pre-training vision transformers with sinusoidal waves","venue":null,"work_id":"fbb5de3f-1e8a-4120-a344-c2b56b220685","year":2023},"citing_paper":{"arxiv_id":"2505.13099","last_updated":"2025-05-20T05:42:28Z","snapshot_observed_at":"2026-08-16T05:06:32.096250Z","submitted_at":"2025-05-19T13:29:40Z","title":"Industrial Synthetic Segment Pre-training","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-15T20:25:36.257412Z"},"links":{"citing_paper":"/paper/2505.13099"},"observation_digest":"sha256:8751148e756a878d3588896c0bd5265cf9aff5b605dce83a6500f16750a6443e","observation_id":"3e8a7a17-5ad5-4769-b4b9-96350388d8a6","resolution":{"observed_at":"2026-08-15T20:25:36.592462Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:25:36.574242Z","title":"Stablerep: Syn- thetic images from text-to-image models make strong visual representation learners.Advances in Neural Information Processing Systems, 36, 2024","venue":null,"work_id":"9ba3d08f-2b87-43c2-b0e6-16d55b8a8395","year":2024},"citing_paper":{"arxiv_id":"2505.13099","last_updated":"2025-05-20T05:42:28Z","snapshot_observed_at":"2026-08-16T05:06:32.096250Z","submitted_at":"2025-05-19T13:29:40Z","title":"Industrial Synthetic Segment Pre-training","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-15T20:25:36.261223Z"},"links":{"citing_paper":"/paper/2505.13099"},"observation_digest":"sha256:aa993070199dcdf2905c212a968cc4599a6b6588afcc83dcd4f4012744630768","observation_id":"f06d993b-4a05-440a-8a54-3ee8c84e7925","resolution":{"observed_at":"2026-08-15T20:25:36.578743Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:25:36.559972Z","title":"Training deep networks with synthetic data: Bridging the reality gap by domain randomization","venue":null,"work_id":"9ca2a063-0fbc-487e-a4fb-d3181c125e55","year":2018},"citing_paper":{"arxiv_id":"2505.13099","last_updated":"2025-05-20T05:42:28Z","snapshot_observed_at":"2026-08-16T05:06:32.096250Z","submitted_at":"2025-05-19T13:29:40Z","title":"Industrial Synthetic Segment Pre-training","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-15T20:25:36.265151Z"},"links":{"citing_paper":"/paper/2505.13099"},"observation_digest":"sha256:ff367220f35722ed11d62d6f48e66061a1c8f0aa6614c359a4c5cbddfe32d2bf","observation_id":"020f0a7d-d132-4947-9821-d0e0943706d6","resolution":{"observed_at":"2026-08-15T20:25:36.564251Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1807.01232","last_updated":"2019-07-15T02:40:55Z","snapshot_observed_at":"2026-08-16T05:05:49.034195Z","submitted_at":"2018-07-03T15:12:59Z","title":"SpaceNet: A Remote Sensing Dataset and Challenge Series","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1807.01232","snapshot_observed_at":"2026-08-15T20:25:36.269333Z","title":"Spacenet: A remote sensing dataset and challenge series","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.13099","last_updated":"2025-05-20T05:42:28Z","snapshot_observed_at":"2026-08-16T05:06:32.096250Z","submitted_at":"2025-05-19T13:29:40Z","title":"Industrial Synthetic Segment Pre-training","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-15T20:25:36.269333Z"},"links":{"cited_paper":"/paper/1807.01232","citing_paper":"/paper/2505.13099"},"observation_digest":"sha256:910020b3972f03f65a1507d937258718722024053d3b6f1542ee3f25faaa7f80","observation_id":"f99aca2f-e816-421e-b13c-9ffdb3b54d3f","resolution":{"observed_at":"2026-08-15T20:25:36.269333Z","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":"2026-08-15T20:25:36.546920Z","title":"Mv-fractaldb: formula-driven supervised learning for multi- view image recognition","venue":null,"work_id":"1c27e326-eadc-4019-b018-8eaa30b6506d","year":2021},"citing_paper":{"arxiv_id":"2505.13099","last_updated":"2025-05-20T05:42:28Z","snapshot_observed_at":"2026-08-16T05:06:32.096250Z","submitted_at":"2025-05-19T13:29:40Z","title":"Industrial Synthetic Segment Pre-training","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-15T20:25:36.273452Z"},"links":{"citing_paper":"/paper/2505.13099"},"observation_digest":"sha256:4cbb540aded43489b7fc3a20983789d456f9f0275832fd64073f6bc7dcfcf326","observation_id":"bf63d9db-a38b-4bd6-bb56-d502e2fe077c","resolution":{"observed_at":"2026-08-15T20:25:36.551316Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:25:36.277349Z","title":"Towards fairer datasets: Filtering and balancing the distribution of the people subtree in the imagenet hierarchy","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.13099","last_updated":"2025-05-20T05:42:28Z","snapshot_observed_at":"2026-08-16T05:06:32.096250Z","submitted_at":"2025-05-19T13:29:40Z","title":"Industrial Synthetic Segment Pre-training","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-15T20:25:36.277349Z"},"links":{"citing_paper":"/paper/2505.13099"},"observation_digest":"sha256:0a1789a29067b711e16de706e3189530838da5c20eedd4839332a561e7932dea","observation_id":"7bb69284-8540-48dd-8419-15da662ae14a","resolution":{"observed_at":"2026-08-15T20:25:36.277349Z","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":"2026-08-15T20:25:36.533891Z","title":"Seggen: Supercharg- ing segmentation models with text2mask and mask2img synthesis","venue":null,"work_id":"c7b42278-631c-4cb1-9431-ac6a120fb3f7","year":2024},"citing_paper":{"arxiv_id":"2505.13099","last_updated":"2025-05-20T05:42:28Z","snapshot_observed_at":"2026-08-16T05:06:32.096250Z","submitted_at":"2025-05-19T13:29:40Z","title":"Industrial Synthetic Segment Pre-training","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-15T20:25:36.281419Z"},"links":{"citing_paper":"/paper/2505.13099"},"observation_digest":"sha256:06506fda1cbed3de1da60d98d00a7d751da3eb6da23e0012ada856b4d0ec737f","observation_id":"f4fdc9f7-e3ad-4fb7-8b26-5e7867c4913c","resolution":{"observed_at":"2026-08-15T20:25:36.538035Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:25:36.520762Z","title":"Ts-sam: Fine-tuning segment-anything model for downstream tasks","venue":null,"work_id":"cc1187a0-b865-42b0-beaa-4d65274a071a","year":2024},"citing_paper":{"arxiv_id":"2505.13099","last_updated":"2025-05-20T05:42:28Z","snapshot_observed_at":"2026-08-16T05:06:32.096250Z","submitted_at":"2025-05-19T13:29:40Z","title":"Industrial Synthetic Segment Pre-training","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-15T20:25:36.285261Z"},"links":{"citing_paper":"/paper/2505.13099"},"observation_digest":"sha256:c66b1993930425dafee7bc5f65c694dddbd752bf5ec7ab67b18d05cd2abaff34","observation_id":"3bebccfd-d740-41f4-a506-358c64303f6f","resolution":{"observed_at":"2026-08-15T20:25:36.525065Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:25:36.505505Z","title":"Scene parsing through ade20k dataset","venue":null,"work_id":"0afe9dde-f2d2-4eee-930f-34f2906251ae","year":2017},"citing_paper":{"arxiv_id":"2505.13099","last_updated":"2025-05-20T05:42:28Z","snapshot_observed_at":"2026-08-16T05:06:32.096250Z","submitted_at":"2025-05-19T13:29:40Z","title":"Industrial Synthetic Segment Pre-training","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-15T20:25:36.289108Z"},"links":{"citing_paper":"/paper/2505.13099"},"observation_digest":"sha256:19516405bdd369e874d5a252ea89af272d50e7d9ea90023ac2b2ce78fe84e431","observation_id":"c8a9cd5a-58a9-4901-b925-27bcd096c5a7","resolution":{"observed_at":"2026-08-15T20:25:36.511457Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2505.13099","last_updated":"2025-05-20T05:42:28Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-16T05:06:32.096250Z","submitted_at":"2025-05-19T13:29:40Z","title":"Industrial Synthetic Segment Pre-training"},"reference_resolution":{"displayed":38,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":12,"verified_exact":0,"verified_fuzzy":26},"total_outbound_references":38},"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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 38 of 38 outbound references and 0 inbound Pith citation observations for arXiv:2505.13099."}