{"as_of":"2026-08-08T04:46:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f6a9d233fa51bd86f4268004fc145f81d78313e382c71f87a37729c30c8be81c","coverage":[{"denominator":32,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":32,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T12:02:50.959883Z","state":"measured"},{"denominator":32,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":32,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2509.02029/citation-record","integrity":"/paper/2509.02029/integrity","json":"/paper/2509.02029/citation-record.json","paper":"/paper/2509.02029"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T12:02:50.479914Z","title":"A theoretical analysis of contrastive unsupervised representation learning, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.02029","last_updated":"2025-09-02T07:17:46Z","snapshot_observed_at":"2026-08-06T13:45:03.402406Z","submitted_at":"2025-09-02T07:17:46Z","title":"Fake & Square: Training Self-Supervised Vision Transformers with Synthetic Data and Synthetic Hard Negatives","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-05T12:02:50.479914Z"},"links":{"citing_paper":"/paper/2509.02029"},"observation_digest":"sha256:9876477d5112901e375978e72f64903be9827321e76d7bed9a919ad017e0d2f5","observation_id":"fdf3793c-2b47-4f62-a0f1-fe15224781e3","resolution":{"observed_at":"2026-08-05T12:02:50.479914Z","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":"2026-08-05T12:02:52.921791Z","title":"This dataset does not exist: training models from generated images","venue":null,"work_id":"39102546-93fa-44ee-81b8-5e39e94670ac","year":2020},"citing_paper":{"arxiv_id":"2509.02029","last_updated":"2025-09-02T07:17:46Z","snapshot_observed_at":"2026-08-06T13:45:03.402406Z","submitted_at":"2025-09-02T07:17:46Z","title":"Fake & Square: Training Self-Supervised Vision Transformers with Synthetic Data and Synthetic Hard Negatives","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-05T12:02:50.490970Z"},"links":{"citing_paper":"/paper/2509.02029"},"observation_digest":"sha256:00501a32886cbb2195c6f4a96f4d5c35b107d3fc1b3441b7d06e46530dba8229","observation_id":"b605460c-4fb7-456a-8a94-8c0b3eafa626","resolution":{"observed_at":"2026-08-05T12:02:52.934715Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T12:02:52.837682Z","title":"Deep clustering for unsupervised learning of visual features, 2019","venue":null,"work_id":"da3b43b0-dbc2-49ea-85c5-e25bd47d79d3","year":2019},"citing_paper":{"arxiv_id":"2509.02029","last_updated":"2025-09-02T07:17:46Z","snapshot_observed_at":"2026-08-06T13:45:03.402406Z","submitted_at":"2025-09-02T07:17:46Z","title":"Fake & Square: Training Self-Supervised Vision Transformers with Synthetic Data and Synthetic Hard Negatives","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-05T12:02:50.496228Z"},"links":{"citing_paper":"/paper/2509.02029"},"observation_digest":"sha256:ef161cfd1680974b2e58edbbb89371619e4b4432eb6e7f4f14b91f8adb593549","observation_id":"bff3d71f-7849-419a-abcd-ea330d0940e6","resolution":{"observed_at":"2026-08-05T12:02:52.850007Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T12:02:52.796404Z","title":"Unsupervised learn- ing of visual features by contrasting cluster assignments","venue":null,"work_id":"4fbca663-b191-4100-b36e-9e4359a90c21","year":2020},"citing_paper":{"arxiv_id":"2509.02029","last_updated":"2025-09-02T07:17:46Z","snapshot_observed_at":"2026-08-06T13:45:03.402406Z","submitted_at":"2025-09-02T07:17:46Z","title":"Fake & Square: Training Self-Supervised Vision Transformers with Synthetic Data and Synthetic Hard Negatives","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-05T12:02:50.523435Z"},"links":{"citing_paper":"/paper/2509.02029"},"observation_digest":"sha256:05f7ea19e0bcc71e5f1771476a0b9a5f1ed066319e0306ddd0e2ed1bf02715db","observation_id":"7a6a780c-3e72-4d70-88fb-6adfc109a591","resolution":{"observed_at":"2026-08-05T12:02:52.810016Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T12:02:52.745103Z","title":"Emerg- ing properties in self-supervised vision transformers, 2021","venue":null,"work_id":"7a2d5ead-5aa9-41a4-b798-99894803df0d","year":2021},"citing_paper":{"arxiv_id":"2509.02029","last_updated":"2025-09-02T07:17:46Z","snapshot_observed_at":"2026-08-06T13:45:03.402406Z","submitted_at":"2025-09-02T07:17:46Z","title":"Fake & Square: Training Self-Supervised Vision Transformers with Synthetic Data and Synthetic Hard Negatives","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-05T12:02:50.539308Z"},"links":{"citing_paper":"/paper/2509.02029"},"observation_digest":"sha256:87a58e337299b85e6a5118825dc4fc2bf3021f2046c05ba2a6675869c0af90a4","observation_id":"d5774887-06a9-485a-9659-b7f945d3c9a7","resolution":{"observed_at":"2026-08-05T12:02:52.758084Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T12:02:50.561381Z","title":"A simple framework for contrastive learning of visual representations, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.02029","last_updated":"2025-09-02T07:17:46Z","snapshot_observed_at":"2026-08-06T13:45:03.402406Z","submitted_at":"2025-09-02T07:17:46Z","title":"Fake & Square: Training Self-Supervised Vision Transformers with Synthetic Data and Synthetic Hard Negatives","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-05T12:02:50.561381Z"},"links":{"citing_paper":"/paper/2509.02029"},"observation_digest":"sha256:9d252cdb4f631f1c56dd17796723dadc3e138420f258e30d67cc2c26fde103bc","observation_id":"6bc9e068-bb37-462c-822a-dbb09901535a","resolution":{"observed_at":"2026-08-05T12:02:50.561381Z","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":"2026-08-05T12:02:52.662577Z","title":"An empirical study of training self-supervised vision transformers, 2021","venue":null,"work_id":"39b82499-1d69-4bfa-ac0a-ae8ea372597f","year":2021},"citing_paper":{"arxiv_id":"2509.02029","last_updated":"2025-09-02T07:17:46Z","snapshot_observed_at":"2026-08-06T13:45:03.402406Z","submitted_at":"2025-09-02T07:17:46Z","title":"Fake & Square: Training Self-Supervised Vision Transformers with Synthetic Data and Synthetic Hard Negatives","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-05T12:02:50.572183Z"},"links":{"citing_paper":"/paper/2509.02029"},"observation_digest":"sha256:463e4f6712f176fe84d2124265e56f70c57f449b9b8b32548e74d631928557b2","observation_id":"22e4b90d-7775-43a3-b18d-8117bd833b52","resolution":{"observed_at":"2026-08-05T12:02:52.672548Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T12:02:52.599203Z","title":"When vision transformers outperform resnets without pre-training or strong data augmentations, 2022","venue":null,"work_id":"c3e18aa9-293b-4045-a892-d381c13bfe57","year":2022},"citing_paper":{"arxiv_id":"2509.02029","last_updated":"2025-09-02T07:17:46Z","snapshot_observed_at":"2026-08-06T13:45:03.402406Z","submitted_at":"2025-09-02T07:17:46Z","title":"Fake & Square: Training Self-Supervised Vision Transformers with Synthetic Data and Synthetic Hard Negatives","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-05T12:02:50.592525Z"},"links":{"citing_paper":"/paper/2509.02029"},"observation_digest":"sha256:66a109de333a1a65aa4a04c850ce67525f3c94d3437f228e86a91666bcd7845d","observation_id":"974e7d1b-fbcf-4b51-8afc-5df5a2b52c90","resolution":{"observed_at":"2026-08-05T12:02:52.612541Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T12:02:52.537659Z","title":"Li, and Li Fei-Fei","venue":null,"work_id":"0c38b476-1b31-446f-82b1-a27d4821566a","year":2009},"citing_paper":{"arxiv_id":"2509.02029","last_updated":"2025-09-02T07:17:46Z","snapshot_observed_at":"2026-08-06T13:45:03.402406Z","submitted_at":"2025-09-02T07:17:46Z","title":"Fake & Square: Training Self-Supervised Vision Transformers with Synthetic Data and Synthetic Hard Negatives","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-05T12:02:50.605683Z"},"links":{"citing_paper":"/paper/2509.02029"},"observation_digest":"sha256:0082ac812462a9a5fd874587cc245c0da3983d944aacd054155f64dc9c284ac1","observation_id":"d607a86c-76d2-4e9a-8c27-3698e0ad753a","resolution":{"observed_at":"2026-08-05T12:02:52.566936Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T12:02:50.627244Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.02029","last_updated":"2025-09-02T07:17:46Z","snapshot_observed_at":"2026-08-06T13:45:03.402406Z","submitted_at":"2025-09-02T07:17:46Z","title":"Fake & Square: Training Self-Supervised Vision Transformers with Synthetic Data and Synthetic Hard Negatives","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-05T12:02:50.627244Z"},"links":{"citing_paper":"/paper/2509.02029"},"observation_digest":"sha256:189ceb36ecee480d636af5c7eba34117b0c7f060a8a3c5347b455ceb4b07bf8c","observation_id":"cb91acf9-0d52-401b-bd20-efb2d62f8e18","resolution":{"observed_at":"2026-08-05T12:02:50.627244Z","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":"2026-08-05T12:02:52.393835Z","title":"A review on discriminative self-supervised learning methods, 2024","venue":null,"work_id":"0397281c-ce81-4b96-8b6b-560f2dc3980f","year":2024},"citing_paper":{"arxiv_id":"2509.02029","last_updated":"2025-09-02T07:17:46Z","snapshot_observed_at":"2026-08-06T13:45:03.402406Z","submitted_at":"2025-09-02T07:17:46Z","title":"Fake & Square: Training Self-Supervised Vision Transformers with Synthetic Data and Synthetic Hard Negatives","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-05T12:02:50.639264Z"},"links":{"citing_paper":"/paper/2509.02029"},"observation_digest":"sha256:eb16ce463e73bfdc26d64d5f5e270d4d6f61b55043c757cca86867210598af93","observation_id":"15d4a801-6c9f-409c-b7d1-45453967c18f","resolution":{"observed_at":"2026-08-05T12:02:52.410357Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T12:02:52.326727Z","title":"Synco: Synthetic hard negatives in contrastive learning for better unsupervised visual representations, 2024","venue":null,"work_id":"4472b4f6-195b-4a4a-bc08-7ed0646b8820","year":2024},"citing_paper":{"arxiv_id":"2509.02029","last_updated":"2025-09-02T07:17:46Z","snapshot_observed_at":"2026-08-06T13:45:03.402406Z","submitted_at":"2025-09-02T07:17:46Z","title":"Fake & Square: Training Self-Supervised Vision Transformers with Synthetic Data and Synthetic Hard Negatives","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-05T12:02:50.649318Z"},"links":{"citing_paper":"/paper/2509.02029"},"observation_digest":"sha256:88b7aa2bca07f4bab0630e0c8e75fc5a1ba3ebc3d2755ad16e64bf3a8d594fd8","observation_id":"d589fe28-c940-415c-b5e6-d860464cb04b","resolution":{"observed_at":"2026-08-05T12:02:52.343787Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T12:02:52.266117Z","title":"Richemond, Elena Buchatskaya, Carl Do- ersch, Bernardo Avila Pires, Zhaohan Daniel Guo, Moham- mad Gheshlaghi Azar, Bilal Piot, Koray Kavukcuoglu, R´emi Munos, and Michal Valko","venue":null,"work_id":"55ce6b46-7a81-4aa4-add0-6bdf1b53fdb6","year":2020},"citing_paper":{"arxiv_id":"2509.02029","last_updated":"2025-09-02T07:17:46Z","snapshot_observed_at":"2026-08-06T13:45:03.402406Z","submitted_at":"2025-09-02T07:17:46Z","title":"Fake & Square: Training Self-Supervised Vision Transformers with Synthetic Data and Synthetic Hard Negatives","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-05T12:02:50.683556Z"},"links":{"citing_paper":"/paper/2509.02029"},"observation_digest":"sha256:974daf9baf01a7d4bb157c044269b6f373cb3f97d7b90bd1b88c71da76d75778","observation_id":"743f9d65-562a-4014-acb8-a95297b3e840","resolution":{"observed_at":"2026-08-05T12:02:52.279459Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T12:02:52.225908Z","title":"Momentum contrast for unsupervised visual repre- sentation learning, 2020","venue":null,"work_id":"39f16e7c-23cd-4381-aa14-4ac2f9438ed0","year":2020},"citing_paper":{"arxiv_id":"2509.02029","last_updated":"2025-09-02T07:17:46Z","snapshot_observed_at":"2026-08-06T13:45:03.402406Z","submitted_at":"2025-09-02T07:17:46Z","title":"Fake & Square: Training Self-Supervised Vision Transformers with Synthetic Data and Synthetic Hard Negatives","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-05T12:02:50.695328Z"},"links":{"citing_paper":"/paper/2509.02029"},"observation_digest":"sha256:bf321e0777edb1535bd8ce70ee04ac861fe8d4c09ababd628930b692ddbea263","observation_id":"5ddba3a7-e89b-4a83-92e7-b1e57b1074f6","resolution":{"observed_at":"2026-08-05T12:02:52.239313Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T12:02:50.709180Z","title":"Masked autoencoders are scalable vision learners, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.02029","last_updated":"2025-09-02T07:17:46Z","snapshot_observed_at":"2026-08-06T13:45:03.402406Z","submitted_at":"2025-09-02T07:17:46Z","title":"Fake & Square: Training Self-Supervised Vision Transformers with Synthetic Data and Synthetic Hard Negatives","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-05T12:02:50.709180Z"},"links":{"citing_paper":"/paper/2509.02029"},"observation_digest":"sha256:05535a7e6089778e6f52e8d60dea17b2fc7791b165f23c8fc077d8dff43f38f8","observation_id":"6d5fffee-70bb-4b18-b875-267235e7c9a1","resolution":{"observed_at":"2026-08-05T12:02:50.709180Z","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":"2026-08-05T12:02:52.144265Z","title":"Hard negative mixing for contrastive learning, 2020","venue":null,"work_id":"dcfafcc3-8489-428d-96fc-c88055c65268","year":2020},"citing_paper":{"arxiv_id":"2509.02029","last_updated":"2025-09-02T07:17:46Z","snapshot_observed_at":"2026-08-06T13:45:03.402406Z","submitted_at":"2025-09-02T07:17:46Z","title":"Fake & Square: Training Self-Supervised Vision Transformers with Synthetic Data and Synthetic Hard Negatives","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-05T12:02:50.719451Z"},"links":{"citing_paper":"/paper/2509.02029"},"observation_digest":"sha256:4fab86afdc0903495a196a37ff7fa3f9b8ac70e59ea5755fd2a61f5985861fdd","observation_id":"41fdc6e0-a8ff-4a83-9862-13a3caeba4f0","resolution":{"observed_at":"2026-08-05T12:02:52.152619Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T12:02:52.079481Z","title":"A style-based generator architecture for generative adversarial networks","venue":null,"work_id":"260bdae3-7220-4fa0-b258-43cab4dc113c","year":2019},"citing_paper":{"arxiv_id":"2509.02029","last_updated":"2025-09-02T07:17:46Z","snapshot_observed_at":"2026-08-06T13:45:03.402406Z","submitted_at":"2025-09-02T07:17:46Z","title":"Fake & Square: Training Self-Supervised Vision Transformers with Synthetic Data and Synthetic Hard Negatives","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-05T12:02:50.725399Z"},"links":{"citing_paper":"/paper/2509.02029"},"observation_digest":"sha256:77f911981a481b07439119a9abb94192b2d65d3f270b5679e799dd0c94d76757","observation_id":"c1ee930a-54f4-4474-9216-0c2fbebc8480","resolution":{"observed_at":"2026-08-05T12:02:52.110761Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T12:02:50.730756Z","title":"Self-supervised learning: Generative or contrastive","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.02029","last_updated":"2025-09-02T07:17:46Z","snapshot_observed_at":"2026-08-06T13:45:03.402406Z","submitted_at":"2025-09-02T07:17:46Z","title":"Fake & Square: Training Self-Supervised Vision Transformers with Synthetic Data and Synthetic Hard Negatives","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-05T12:02:50.730756Z"},"links":{"citing_paper":"/paper/2509.02029"},"observation_digest":"sha256:8093e8a2c8c655758226e652d90196c5e48bf4b1050740a8acc6cb02ced505cd","observation_id":"cd9c12ad-0da0-47c8-a437-38d503b07a3c","resolution":{"observed_at":"2026-08-05T12:02:50.730756Z","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":"2026-08-05T12:02:51.959249Z","title":"Swin transformer: Hierarchical vision transformer using shifted windows, 2021","venue":null,"work_id":"07677cfb-6a22-4530-82c4-f2123be9d8e5","year":2021},"citing_paper":{"arxiv_id":"2509.02029","last_updated":"2025-09-02T07:17:46Z","snapshot_observed_at":"2026-08-06T13:45:03.402406Z","submitted_at":"2025-09-02T07:17:46Z","title":"Fake & Square: Training Self-Supervised Vision Transformers with Synthetic Data and Synthetic Hard Negatives","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-05T12:02:50.737132Z"},"links":{"citing_paper":"/paper/2509.02029"},"observation_digest":"sha256:d31aa44311a0eaf31397d583cb9a0d597b861d8d70e46a18f0f2637de69f23a6","observation_id":"d1ea7023-c444-44ce-ba87-a0e608cb44b5","resolution":{"observed_at":"2026-08-05T12:02:51.973973Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1909.11512","last_updated":"2019-09-25T14:20:57Z","snapshot_observed_at":"2026-07-06T08:24:29.472112Z","submitted_at":"2019-09-25T14:20:57Z","title":"Synthetic Data for Deep Learning","version":1},"cited_work":{"arxiv_id":"1909.11512","doi":null,"metadata_source":"pith","pith_arxiv_id":"1909.11512","snapshot_observed_at":"2026-08-05T12:02:51.209954Z","title":"Synthetic Data for Deep Learning","venue":"cs.LG","work_id":"847aebd0-0c81-4338-9bec-44fd74d3e1d7","year":2019},"citing_paper":{"arxiv_id":"2509.02029","last_updated":"2025-09-02T07:17:46Z","snapshot_observed_at":"2026-08-06T13:45:03.402406Z","submitted_at":"2025-09-02T07:17:46Z","title":"Fake & Square: Training Self-Supervised Vision Transformers with Synthetic Data and Synthetic Hard Negatives","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-05T12:02:50.747663Z"},"links":{"cited_paper":"/paper/1909.11512","citing_paper":"/paper/2509.02029"},"observation_digest":"sha256:ed72d45f035c4ad98bc4bc981381d0ffd19d27331819b79b53065f865e500529","observation_id":"62723b2b-88fd-425c-9d77-4f58f86c3bbc","resolution":{"observed_at":"2026-08-05T12:02:51.235981Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T12:02:51.890895Z","title":"Fake it till you make it: Learning trans- ferable representations from synthetic imagenet clones","venue":null,"work_id":"39f10840-0e41-4cba-9cb9-c061e9fa9c37","year":2023},"citing_paper":{"arxiv_id":"2509.02029","last_updated":"2025-09-02T07:17:46Z","snapshot_observed_at":"2026-08-06T13:45:03.402406Z","submitted_at":"2025-09-02T07:17:46Z","title":"Fake & Square: Training Self-Supervised Vision Transformers with Synthetic Data and Synthetic Hard Negatives","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-05T12:02:50.765697Z"},"links":{"citing_paper":"/paper/2509.02029"},"observation_digest":"sha256:666d32b62d688a180e16ca6d35c61f509e3db8e96d3ca1ed973253eb2b4e5626","observation_id":"c905ed95-5269-4a6b-92f6-afeeaca4563a","resolution":{"observed_at":"2026-08-05T12:02:51.906989Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T12:02:51.829206Z","title":"Relay diffusion: Unifying diffusion process across resolutions for image syn- thesis","venue":null,"work_id":"6c5bceac-f9d4-476b-be41-bc7598d7e29b","year":2024},"citing_paper":{"arxiv_id":"2509.02029","last_updated":"2025-09-02T07:17:46Z","snapshot_observed_at":"2026-08-06T13:45:03.402406Z","submitted_at":"2025-09-02T07:17:46Z","title":"Fake & Square: Training Self-Supervised Vision Transformers with Synthetic Data and Synthetic Hard Negatives","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-05T12:02:50.793042Z"},"links":{"citing_paper":"/paper/2509.02029"},"observation_digest":"sha256:ab36e3c71072cd3261e97395ba1d1ce9e442e945a41f8e8660ddaf10fc309623","observation_id":"3343c7d2-6231-4a96-9197-a685a2dfdeb3","resolution":{"observed_at":"2026-08-05T12:02:51.847238Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T12:02:51.781055Z","title":"Contrastive multiview coding, 2020","venue":null,"work_id":"7887c380-d13a-4e4d-b7ee-af2d3de95e61","year":2020},"citing_paper":{"arxiv_id":"2509.02029","last_updated":"2025-09-02T07:17:46Z","snapshot_observed_at":"2026-08-06T13:45:03.402406Z","submitted_at":"2025-09-02T07:17:46Z","title":"Fake & Square: Training Self-Supervised Vision Transformers with Synthetic Data and Synthetic Hard Negatives","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-05T12:02:50.807238Z"},"links":{"citing_paper":"/paper/2509.02029"},"observation_digest":"sha256:e7db33880a7a3ec29cc59fb087ecf5a938bc481f588519cc8979ff79381a7445","observation_id":"5f267c3c-d8de-46bf-8286-dfbd9dc426b8","resolution":{"observed_at":"2026-08-05T12:02:51.787956Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.17742","last_updated":"2023-12-28T18:59:55Z","snapshot_observed_at":"2026-07-06T17:09:59.848387Z","submitted_at":"2023-12-28T18:59:55Z","title":"Learning Vision from Models Rivals Learning Vision from Data","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.17742","snapshot_observed_at":"2026-08-05T12:02:50.827971Z","title":"Learning vision from models rivals learning vision from data","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.02029","last_updated":"2025-09-02T07:17:46Z","snapshot_observed_at":"2026-08-06T13:45:03.402406Z","submitted_at":"2025-09-02T07:17:46Z","title":"Fake & Square: Training Self-Supervised Vision Transformers with Synthetic Data and Synthetic Hard Negatives","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-05T12:02:50.827971Z"},"links":{"cited_paper":"/paper/2312.17742","citing_paper":"/paper/2509.02029"},"observation_digest":"sha256:4e69abd75219f2eaf968ea5de1dbdb6892134eb3f2191332216fb8b631ae67d7","observation_id":"0deb7d05-6ff4-4b51-94d9-8e0f5975617f","resolution":{"observed_at":"2026-08-05T12:02:50.827971Z","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":"2026-08-05T12:02:51.728048Z","title":"Training data-efficient image transformers & distillation through atten- tion, 2021","venue":null,"work_id":"56ddceaf-56c9-4c9f-9086-eea7dd9bd0f9","year":2021},"citing_paper":{"arxiv_id":"2509.02029","last_updated":"2025-09-02T07:17:46Z","snapshot_observed_at":"2026-08-06T13:45:03.402406Z","submitted_at":"2025-09-02T07:17:46Z","title":"Fake & Square: Training Self-Supervised Vision Transformers with Synthetic Data and Synthetic Hard Negatives","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-05T12:02:50.840743Z"},"links":{"citing_paper":"/paper/2509.02029"},"observation_digest":"sha256:8e767a805aaa3e049f95ffd3a41881e0778a625a68ea238ccd5a9a62a0b0a031","observation_id":"67cd7243-9d3f-4767-8b75-5821c6865826","resolution":{"observed_at":"2026-08-05T12:02:51.741553Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T12:02:51.661026Z","title":"Repre- sentation learning with contrastive predictive coding, 2019","venue":null,"work_id":"3e5f03f7-8879-48b6-8d4e-b96cb98a7033","year":2019},"citing_paper":{"arxiv_id":"2509.02029","last_updated":"2025-09-02T07:17:46Z","snapshot_observed_at":"2026-08-06T13:45:03.402406Z","submitted_at":"2025-09-02T07:17:46Z","title":"Fake & Square: Training Self-Supervised Vision Transformers with Synthetic Data and Synthetic Hard Negatives","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-05T12:02:50.871997Z"},"links":{"citing_paper":"/paper/2509.02029"},"observation_digest":"sha256:ae0bc10905e976c2ba882b276ce27e12965f6aecd6b357a689ae33e2db998cfe","observation_id":"3a2ca74c-4613-4b3f-ad7b-894b3fefee29","resolution":{"observed_at":"2026-08-05T12:02:51.674737Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T12:02:51.596231Z","title":"Attention is all you need","venue":null,"work_id":"0129ccd0-ba31-4159-a907-13277b565490","year":2017},"citing_paper":{"arxiv_id":"2509.02029","last_updated":"2025-09-02T07:17:46Z","snapshot_observed_at":"2026-08-06T13:45:03.402406Z","submitted_at":"2025-09-02T07:17:46Z","title":"Fake & Square: Training Self-Supervised Vision Transformers with Synthetic Data and Synthetic Hard Negatives","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-05T12:02:50.879378Z"},"links":{"citing_paper":"/paper/2509.02029"},"observation_digest":"sha256:5041b9b5d6369c4234ddf96da4476bc9ff9a48e52c7cf717666c44c1da83713a","observation_id":"2851d934-420a-448b-8e60-75122109d61a","resolution":{"observed_at":"2026-08-05T12:02:51.605302Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T12:02:51.523061Z","title":"Un- supervised feature learning via non-parametric instance-level discrimination, 2018","venue":null,"work_id":"485e4a1b-b5a0-4d47-83ca-7015a11858d1","year":2018},"citing_paper":{"arxiv_id":"2509.02029","last_updated":"2025-09-02T07:17:46Z","snapshot_observed_at":"2026-08-06T13:45:03.402406Z","submitted_at":"2025-09-02T07:17:46Z","title":"Fake & Square: Training Self-Supervised Vision Transformers with Synthetic Data and Synthetic Hard Negatives","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-05T12:02:50.886959Z"},"links":{"citing_paper":"/paper/2509.02029"},"observation_digest":"sha256:caf38e1053fad44e51585fb3af08991882283a35bf042c247ef87519e62a7b29","observation_id":"c6c2c9fe-f2c0-4380-b5ba-588838c5fa07","resolution":{"observed_at":"2026-08-05T12:02:51.546627Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T12:02:51.469470Z","title":"Self-supervised learning with swin transformers, 2021","venue":null,"work_id":"7e598d1f-e2ae-4511-baa1-d91c7d34e5d1","year":2021},"citing_paper":{"arxiv_id":"2509.02029","last_updated":"2025-09-02T07:17:46Z","snapshot_observed_at":"2026-08-06T13:45:03.402406Z","submitted_at":"2025-09-02T07:17:46Z","title":"Fake & Square: Training Self-Supervised Vision Transformers with Synthetic Data and Synthetic Hard Negatives","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-05T12:02:50.902138Z"},"links":{"citing_paper":"/paper/2509.02029"},"observation_digest":"sha256:d9f1a456af9274b130488deeb5a120d822c69bcea398102e2c038a936a71aef1","observation_id":"94132d5f-870d-48bd-bddf-378324cdd83b","resolution":{"observed_at":"2026-08-05T12:02:51.478955Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T12:02:51.387878Z","title":"Decoupled contrastive learning, 2022","venue":null,"work_id":"30c6a0c1-c282-40c6-806f-001a189c919f","year":2022},"citing_paper":{"arxiv_id":"2509.02029","last_updated":"2025-09-02T07:17:46Z","snapshot_observed_at":"2026-08-06T13:45:03.402406Z","submitted_at":"2025-09-02T07:17:46Z","title":"Fake & Square: Training Self-Supervised Vision Transformers with Synthetic Data and Synthetic Hard Negatives","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-05T12:02:50.916832Z"},"links":{"citing_paper":"/paper/2509.02029"},"observation_digest":"sha256:9a48ff3546d7a35587de46108a9aec5d6bd7515fe3c27c20b1b271b833ab10b9","observation_id":"09a8ef39-daf4-4725-aded-3b263f5e4506","resolution":{"observed_at":"2026-08-05T12:02:51.399157Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T12:02:51.318338Z","title":"Understanding hard nega- tives in noise contrastive estimation, 2021","venue":null,"work_id":"000c4835-2d31-49b2-bc8e-b941d428b207","year":2021},"citing_paper":{"arxiv_id":"2509.02029","last_updated":"2025-09-02T07:17:46Z","snapshot_observed_at":"2026-08-06T13:45:03.402406Z","submitted_at":"2025-09-02T07:17:46Z","title":"Fake & Square: Training Self-Supervised Vision Transformers with Synthetic Data and Synthetic Hard Negatives","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-05T12:02:50.934020Z"},"links":{"citing_paper":"/paper/2509.02029"},"observation_digest":"sha256:6f4d692b649e10d7b77fbed14c283c57829eb3a43cb55664fc7712b42b0de0f6","observation_id":"f6dd6f3f-1f94-4cb4-838d-501904e19857","resolution":{"observed_at":"2026-08-05T12:02:51.329421Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-05T12:02:51.279191Z","title":"ibot: Image bert pre-training with online tokenizer, 2022","venue":null,"work_id":"c08a8985-9929-4702-adac-ef087d34c7dc","year":2022},"citing_paper":{"arxiv_id":"2509.02029","last_updated":"2025-09-02T07:17:46Z","snapshot_observed_at":"2026-08-06T13:45:03.402406Z","submitted_at":"2025-09-02T07:17:46Z","title":"Fake & Square: Training Self-Supervised Vision Transformers with Synthetic Data and Synthetic Hard Negatives","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-05T12:02:50.959883Z"},"links":{"citing_paper":"/paper/2509.02029"},"observation_digest":"sha256:a5ba2e9129d6361d9e0d67df5743fbee59815400fb0b33836a9c43f20564ace7","observation_id":"d027f34a-b86a-43d4-820c-f461c80f43d9","resolution":{"observed_at":"2026-08-05T12:02:51.289193Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2509.02029","last_updated":"2025-09-02T07:17:46Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-06T13:45:03.402406Z","submitted_at":"2025-09-02T07:17:46Z","title":"Fake & Square: Training Self-Supervised Vision Transformers with Synthetic Data and Synthetic Hard Negatives"},"reference_resolution":{"displayed":32,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":6,"verified_exact":1,"verified_fuzzy":25},"total_outbound_references":32},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 32 of 32 outbound references and 0 inbound Pith citation observations for arXiv:2509.02029."}