{"as_of":"2026-08-07T16:43:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:173f72f7b0a8379647aa9dfc69941b98569880b77e1489103787608904d644ff","coverage":[{"denominator":62,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":62,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T20:04:07.964738Z","state":"measured"},{"denominator":63,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":63,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-02T14:42:01.334822Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-02T14:47:03.347932Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2507.04051","last_updated":"2025-07-05T14:20:49Z","snapshot_observed_at":"2026-08-06T19:54:20.560306Z","submitted_at":"2025-07-05T14:20:49Z","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","version":1},"cited_work":{"arxiv_id":"2507.04051","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2507.04051","snapshot_observed_at":"2026-07-02T14:47:03.347932Z","title":"arXiv preprint arXiv:2507.04051 , year=","venue":null,"work_id":"96e2ada6-f287-439b-a1e8-9bc1d1351ada","year":null},"citing_paper":{"arxiv_id":"2607.00620","last_updated":"2026-07-01T08:40:46Z","snapshot_observed_at":"2026-07-07T00:06:14.968413Z","submitted_at":"2026-07-01T08:40:46Z","title":"Identifying Latent Concepts and Structures for Generalized Category Discovery","version":1},"reference_index":65,"source":"arxiv_source","source_observed_at":"2026-07-02T14:42:01.334822Z"},"links":{"cited_paper":"/paper/2507.04051","citing_paper":"/paper/2607.00620"},"observation_digest":"sha256:4cbb5846be43ec5f63b7062e75449ac5a1b2a7c0d0700faf2dbb73b03f22a0a8","observation_id":"8d6f15b2-8580-4531-a5a9-9531450e1ff7","resolution":{"observed_at":"2026-07-02T14:47:03.349247Z","resolver_source":"arxiv_id","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"}}],"links":{"evidence":"/evidence","html":"/paper/2507.04051/citation-record","integrity":"/paper/2507.04051/integrity","json":"/paper/2507.04051/citation-record.json","paper":"/paper/2507.04051"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T20:04:19.902952Z","title":"Generalized category discovery with decoupled prototypical network","venue":null,"work_id":"dd4bf63a-f27d-40ef-a453-c4ab2c061d28","year":2023},"citing_paper":{"arxiv_id":"2507.04051","last_updated":"2025-07-05T14:20:49Z","snapshot_observed_at":"2026-08-06T19:54:20.560306Z","submitted_at":"2025-07-05T14:20:49Z","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T20:04:00.075307Z"},"links":{"citing_paper":"/paper/2507.04051"},"observation_digest":"sha256:c2c526308605b15c1393bc013182baf8dbdc78b18a5c603fdc2f9c9103db64c6","observation_id":"80c62f9a-c4cc-4f2b-a095-5d1a411da381","resolution":{"observed_at":"2026-08-06T20:04:20.003997Z","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":"2026-08-06T20:04:19.636862Z","title":"Emerg- ing properties in self-supervised vision transformers","venue":null,"work_id":"973e0f5b-cfde-4937-b5dd-1b128628c95e","year":2021},"citing_paper":{"arxiv_id":"2507.04051","last_updated":"2025-07-05T14:20:49Z","snapshot_observed_at":"2026-08-06T19:54:20.560306Z","submitted_at":"2025-07-05T14:20:49Z","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T20:04:00.181415Z"},"links":{"citing_paper":"/paper/2507.04051"},"observation_digest":"sha256:246c412d0b3ba32efe1e626a43f8f99890136d6f8674bb15c47aef6928453b2e","observation_id":"be4de4dd-d6b3-4e2a-a1e8-e8938b5fc0ad","resolution":{"observed_at":"2026-08-06T20:04:19.730007Z","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":"2026-08-06T20:04:19.355723Z","title":"Parametric information maxi- mization for generalized category discovery","venue":null,"work_id":"b31d3f21-2b81-4c12-b8af-6d0e831c3579","year":2023},"citing_paper":{"arxiv_id":"2507.04051","last_updated":"2025-07-05T14:20:49Z","snapshot_observed_at":"2026-08-06T19:54:20.560306Z","submitted_at":"2025-07-05T14:20:49Z","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T20:04:00.310105Z"},"links":{"citing_paper":"/paper/2507.04051"},"observation_digest":"sha256:b937cf79e733efdc4b0325704f2d75c5e5b7cb3d73b2e8fe3ec7273ca91be55a","observation_id":"8e51297e-6f00-48aa-995c-1bb72b9e2c0a","resolution":{"observed_at":"2026-08-06T20:04:19.516267Z","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":"2026-08-06T20:04:19.161010Z","title":"Text-to-image diffusion mod- els are zero shot classifiers.NeurIPS, 2024","venue":null,"work_id":"2b5bea1f-8aee-483c-a7f7-dfd7fbeb42b4","year":2024},"citing_paper":{"arxiv_id":"2507.04051","last_updated":"2025-07-05T14:20:49Z","snapshot_observed_at":"2026-08-06T19:54:20.560306Z","submitted_at":"2025-07-05T14:20:49Z","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T20:04:00.408040Z"},"links":{"citing_paper":"/paper/2507.04051"},"observation_digest":"sha256:bd1757fc94ad6094df41b5dea7c31e166d8a1ee142bfb798f60ae2b28608b842","observation_id":"0179b4fc-13ab-4193-a27a-b44ceff7c652","resolution":{"observed_at":"2026-08-06T20:04:19.262340Z","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":"2026-08-06T20:04:18.887147Z","title":"On-the-fly cate- gory discovery","venue":null,"work_id":"4a0c0573-48c4-4281-8713-11856ddf7d31","year":2023},"citing_paper":{"arxiv_id":"2507.04051","last_updated":"2025-07-05T14:20:49Z","snapshot_observed_at":"2026-08-06T19:54:20.560306Z","submitted_at":"2025-07-05T14:20:49Z","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T20:04:00.553886Z"},"links":{"citing_paper":"/paper/2507.04051"},"observation_digest":"sha256:3bdc0163ca8a074817af112f15dddc000159725a7f88430d97b1bdf6ec2e2beb","observation_id":"4861388c-cda4-457d-bd67-de16f0fe6d2b","resolution":{"observed_at":"2026-08-06T20:04:19.009219Z","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":"2026-08-06T20:04:18.659607Z","title":"Diffusion-based probabilistic un- certainty estimation for active domain adaptation.NeurIPS,","venue":null,"work_id":"6ce3f5ad-f168-46e2-9132-714f0d4ba638","year":null},"citing_paper":{"arxiv_id":"2507.04051","last_updated":"2025-07-05T14:20:49Z","snapshot_observed_at":"2026-08-06T19:54:20.560306Z","submitted_at":"2025-07-05T14:20:49Z","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T20:04:00.678955Z"},"links":{"citing_paper":"/paper/2507.04051"},"observation_digest":"sha256:ab8b08080e1d27677cad608d61d71e14a23c1a6d01ae109de152834ec13f7278","observation_id":"b1fb38e7-eeb4-489a-9d81-13dcbb26e304","resolution":{"observed_at":"2026-08-06T20:04:18.756703Z","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":"2026-08-06T20:04:18.441781Z","title":"Diverse data augmentation with diffusions for effective test-time prompt tuning","venue":null,"work_id":"85edd2c1-1924-472b-8714-10d417699784","year":2023},"citing_paper":{"arxiv_id":"2507.04051","last_updated":"2025-07-05T14:20:49Z","snapshot_observed_at":"2026-08-06T19:54:20.560306Z","submitted_at":"2025-07-05T14:20:49Z","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T20:04:00.787139Z"},"links":{"citing_paper":"/paper/2507.04051"},"observation_digest":"sha256:95797bcf614a6250018b37a87dc290c5dca15be61075d1937c6f43b7de9beed1","observation_id":"d162ed97-b4a9-413f-a915-fa147a34d665","resolution":{"observed_at":"2026-08-06T20:04:18.540923Z","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":"2026-08-06T20:04:18.251167Z","title":"A unified objective for novel class discovery","venue":null,"work_id":"50542588-6ccb-4edd-830c-2e113f3abda3","year":2021},"citing_paper":{"arxiv_id":"2507.04051","last_updated":"2025-07-05T14:20:49Z","snapshot_observed_at":"2026-08-06T19:54:20.560306Z","submitted_at":"2025-07-05T14:20:49Z","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T20:04:00.910028Z"},"links":{"citing_paper":"/paper/2507.04051"},"observation_digest":"sha256:10ab318246ab15d93d861d847f2d7937bfaec55fb7431c39fb99075d85e79a3e","observation_id":"d826a0c4-bc77-4310-9dc6-4e57201b8649","resolution":{"observed_at":"2026-08-06T20:04:18.315817Z","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":"2403.12803","last_updated":"2024-03-19T15:04:35Z","snapshot_observed_at":"2026-07-06T17:47:02.560132Z","submitted_at":"2024-03-19T15:04:35Z","title":"DreamDA: Generative Data Augmentation with Diffusion Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.12803","snapshot_observed_at":"2026-08-06T20:04:01.041276Z","title":"Dreamda: Generative data augmentation with diffusion mod- els.arXiv preprint arXiv:2403.12803, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.04051","last_updated":"2025-07-05T14:20:49Z","snapshot_observed_at":"2026-08-06T19:54:20.560306Z","submitted_at":"2025-07-05T14:20:49Z","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T20:04:01.041276Z"},"links":{"cited_paper":"/paper/2403.12803","citing_paper":"/paper/2507.04051"},"observation_digest":"sha256:4d4b8eabb3d1bf69cb9ec651e7ee7401fbb4b6fb0965da6593a69e3a46803593","observation_id":"7da76288-af32-4b69-94cc-25cd4cfb5711","resolution":{"observed_at":"2026-08-06T20:04:01.041276Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2208.01618","last_updated":"2022-08-02T17:50:36Z","snapshot_observed_at":"2026-08-02T23:40:32.342515Z","submitted_at":"2022-08-02T17:50:36Z","title":"An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2208.01618","snapshot_observed_at":"2026-08-06T20:04:01.221791Z","title":"An image is worth one word: Personalizing text-to- image generation using textual inversion.arXiv preprint arXiv:2208.01618, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.04051","last_updated":"2025-07-05T14:20:49Z","snapshot_observed_at":"2026-08-06T19:54:20.560306Z","submitted_at":"2025-07-05T14:20:49Z","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T20:04:01.221791Z"},"links":{"cited_paper":"/paper/2208.01618","citing_paper":"/paper/2507.04051"},"observation_digest":"sha256:0314c15d724259eca335c56205ee63956fdac9f773cbc0bd2f77cb18d95b1602","observation_id":"f9417917-ccfe-4270-846e-d0a19981cade","resolution":{"observed_at":"2026-08-06T20:04:01.221791Z","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":"2026-08-06T20:04:17.985330Z","title":"Learning to discover novel visual categories via deep transfer cluster- ing","venue":null,"work_id":"890e64b9-5a80-4f2f-97f4-1d7b21040e13","year":2019},"citing_paper":{"arxiv_id":"2507.04051","last_updated":"2025-07-05T14:20:49Z","snapshot_observed_at":"2026-08-06T19:54:20.560306Z","submitted_at":"2025-07-05T14:20:49Z","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T20:04:01.359159Z"},"links":{"citing_paper":"/paper/2507.04051"},"observation_digest":"sha256:dac987dd4adf951a9339f59aabdaa321dca11687117857cd1f5838d4c3eedcbb","observation_id":"30fce410-f8ef-45b8-9b41-eca3d80d5499","resolution":{"observed_at":"2026-08-06T20:04:18.134874Z","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":"2026-08-06T20:04:17.668820Z","title":"Autonovel: Automati- cally discovering and learning novel visual categories.IEEE TPAMI, 2021","venue":null,"work_id":"85585798-b73c-4b84-87fe-8257db83bc24","year":2021},"citing_paper":{"arxiv_id":"2507.04051","last_updated":"2025-07-05T14:20:49Z","snapshot_observed_at":"2026-08-06T19:54:20.560306Z","submitted_at":"2025-07-05T14:20:49Z","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T20:04:01.497519Z"},"links":{"citing_paper":"/paper/2507.04051"},"observation_digest":"sha256:3ad9c10ec6889b0246d0d84aa9b03e5c7730c2b4ef2e5d30e8ebde5c8fb6d3c3","observation_id":"c582aab2-070c-4778-876b-a369cb4d43c7","resolution":{"observed_at":"2026-08-06T20:04:17.826990Z","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":"2026-08-06T20:04:17.369328Z","title":"John Wiley & Sons, Inc., 1975","venue":null,"work_id":"33bf3f5e-f8b3-4862-beca-1d8b5dcc65b6","year":1975},"citing_paper":{"arxiv_id":"2507.04051","last_updated":"2025-07-05T14:20:49Z","snapshot_observed_at":"2026-08-06T19:54:20.560306Z","submitted_at":"2025-07-05T14:20:49Z","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T20:04:01.599059Z"},"links":{"citing_paper":"/paper/2507.04051"},"observation_digest":"sha256:9ea384b6ee12d41326c2b5c29c73b1bc0befc56721b568a3212eb706443199c0","observation_id":"e3039c75-7f70-4d7b-a837-bdf4d678dcdd","resolution":{"observed_at":"2026-08-06T20:04:17.482537Z","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":"2210.07574","last_updated":"2023-02-15T06:26:38Z","snapshot_observed_at":"2026-07-06T14:05:10.100398Z","submitted_at":"2022-10-14T06:54:24Z","title":"Is synthetic data from generative models ready for image recognition?","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.07574","snapshot_observed_at":"2026-08-06T20:04:01.714423Z","title":"Is synthetic data from generative models ready for image recognition? arXiv preprint arXiv:2210.07574, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.04051","last_updated":"2025-07-05T14:20:49Z","snapshot_observed_at":"2026-08-06T19:54:20.560306Z","submitted_at":"2025-07-05T14:20:49Z","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T20:04:01.714423Z"},"links":{"cited_paper":"/paper/2210.07574","citing_paper":"/paper/2507.04051"},"observation_digest":"sha256:e3e6f84ce81a3699edd05fd2330da82199c6f2f6fd01137f768fd532fa51b9c4","observation_id":"b5251441-0a8b-4390-8f88-04f93ba1fe46","resolution":{"observed_at":"2026-08-06T20:04:01.714423Z","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":"2026-08-06T20:04:01.832723Z","title":"Denoising diffu- sion probabilistic models.NeurIPS, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.04051","last_updated":"2025-07-05T14:20:49Z","snapshot_observed_at":"2026-08-06T19:54:20.560306Z","submitted_at":"2025-07-05T14:20:49Z","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T20:04:01.832723Z"},"links":{"citing_paper":"/paper/2507.04051"},"observation_digest":"sha256:6038762434faa508669e89af20f5cca65320aea7bf8bfe6ff68de1ad54d76398","observation_id":"6d4fbd5e-afc3-4c1e-91ac-ec7b4e0c7f5e","resolution":{"observed_at":"2026-08-06T20:04:01.832723Z","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":"2026-08-06T20:04:17.137894Z","title":"Diffusemix: Label- preserving data augmentation with diffusion models","venue":null,"work_id":"17734bad-d29b-4252-b125-4d3767d86aff","year":2024},"citing_paper":{"arxiv_id":"2507.04051","last_updated":"2025-07-05T14:20:49Z","snapshot_observed_at":"2026-08-06T19:54:20.560306Z","submitted_at":"2025-07-05T14:20:49Z","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T20:04:01.962004Z"},"links":{"citing_paper":"/paper/2507.04051"},"observation_digest":"sha256:a88e55bf7853b3e261c23570047c4322a24fbda13a1d3624d9653f26410f289a","observation_id":"d3f9ee2f-a393-43b4-b9b2-1c2c4b0c80b7","resolution":{"observed_at":"2026-08-06T20:04:17.240886Z","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":"2026-08-06T20:04:16.833633Z","title":"Joint representation learning and novel category discovery on single-and multi-modal data","venue":null,"work_id":"392b422a-c762-4c39-8018-b509ab7c4d9d","year":2021},"citing_paper":{"arxiv_id":"2507.04051","last_updated":"2025-07-05T14:20:49Z","snapshot_observed_at":"2026-08-06T19:54:20.560306Z","submitted_at":"2025-07-05T14:20:49Z","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T20:04:02.101732Z"},"links":{"citing_paper":"/paper/2507.04051"},"observation_digest":"sha256:4a8b9d29ef7f949141dde7702c5ec6e73e3e19c989d014b8690d8a56c16d3d2e","observation_id":"66087554-248f-40de-a8b5-b3014930b3da","resolution":{"observed_at":"2026-08-06T20:04:16.997108Z","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":"2026-08-06T20:04:16.586507Z","title":"Podia- 3d: Domain adaptation of 3d generative model across large domain gap using pose-preserved text-to-image diffusion","venue":null,"work_id":"df4e897e-38e3-4777-8af5-552715d3dff7","year":2023},"citing_paper":{"arxiv_id":"2507.04051","last_updated":"2025-07-05T14:20:49Z","snapshot_observed_at":"2026-08-06T19:54:20.560306Z","submitted_at":"2025-07-05T14:20:49Z","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T20:04:02.223050Z"},"links":{"citing_paper":"/paper/2507.04051"},"observation_digest":"sha256:60f5ad7486fe9b95e93bc453d44431a4ce7ff9ae1e408460ce004b09803d1adf","observation_id":"0c61d7fc-acb8-4334-94af-e1708b4ab2d7","resolution":{"observed_at":"2026-08-06T20:04:16.699174Z","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":"2026-08-06T20:04:16.342262Z","title":"Proxy anchor-based unsu- pervised learning for continuous generalized category dis- covery","venue":null,"work_id":"2ee25530-d843-4528-af46-99084fb3452d","year":2023},"citing_paper":{"arxiv_id":"2507.04051","last_updated":"2025-07-05T14:20:49Z","snapshot_observed_at":"2026-08-06T19:54:20.560306Z","submitted_at":"2025-07-05T14:20:49Z","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T20:04:02.343138Z"},"links":{"citing_paper":"/paper/2507.04051"},"observation_digest":"sha256:b1cd73a16df1973b45b935bd0ca80a8dc98ba6cc8b1405b92321ece123831bba","observation_id":"224411cd-e925-4919-bbca-bd7776c8fb26","resolution":{"observed_at":"2026-08-06T20:04:16.441761Z","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":"2026-08-06T20:04:16.141860Z","title":"3d object representations for fine-grained categorization","venue":null,"work_id":"61920872-6189-4e22-918e-37ad1329bf4f","year":2013},"citing_paper":{"arxiv_id":"2507.04051","last_updated":"2025-07-05T14:20:49Z","snapshot_observed_at":"2026-08-06T19:54:20.560306Z","submitted_at":"2025-07-05T14:20:49Z","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T20:04:02.453509Z"},"links":{"citing_paper":"/paper/2507.04051"},"observation_digest":"sha256:627469faf088e8c0aa1cea29dd255d9239f83e1f1bc986229912edd6e5b9068d","observation_id":"4533c11d-4873-48d0-b064-7c24d34c2b21","resolution":{"observed_at":"2026-08-06T20:04:16.249270Z","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":"2026-08-06T20:04:15.880638Z","title":"The hungarian method for the assignment problem.Naval research logistics quarterly, 1955","venue":null,"work_id":"71d1cd5d-8a7c-4b61-8f41-d703a20a2306","year":1955},"citing_paper":{"arxiv_id":"2507.04051","last_updated":"2025-07-05T14:20:49Z","snapshot_observed_at":"2026-08-06T19:54:20.560306Z","submitted_at":"2025-07-05T14:20:49Z","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T20:04:02.581436Z"},"links":{"citing_paper":"/paper/2507.04051"},"observation_digest":"sha256:8b0be34985df7896bdabbc968c7b3f4167f5dca4e32dd8fdd6c3fe1b6e259021","observation_id":"79835513-0156-4ede-a922-85cc9b61da0e","resolution":{"observed_at":"2026-08-06T20:04:15.999730Z","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":"2026-08-06T20:04:15.591991Z","title":"Diffusion models already have A semantic latent space","venue":null,"work_id":"6c6251ee-c387-4658-b5d7-15dcceb62db7","year":2023},"citing_paper":{"arxiv_id":"2507.04051","last_updated":"2025-07-05T14:20:49Z","snapshot_observed_at":"2026-08-06T19:54:20.560306Z","submitted_at":"2025-07-05T14:20:49Z","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T20:04:02.710207Z"},"links":{"citing_paper":"/paper/2507.04051"},"observation_digest":"sha256:04647d1f0aee92f69226e9b4bd8ee201db7ed70561550f80c18f2ea744b1943d","observation_id":"73bab13b-4508-4c46-a698-1295150627fa","resolution":{"observed_at":"2026-08-06T20:04:15.731666Z","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":"2026-08-06T20:04:15.260505Z","title":"Your diffusion model is secretly a zero-shot classifier","venue":null,"work_id":"e4846174-2972-47fa-83d4-179d6c0a42d6","year":2023},"citing_paper":{"arxiv_id":"2507.04051","last_updated":"2025-07-05T14:20:49Z","snapshot_observed_at":"2026-08-06T19:54:20.560306Z","submitted_at":"2025-07-05T14:20:49Z","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T20:04:02.828119Z"},"links":{"citing_paper":"/paper/2507.04051"},"observation_digest":"sha256:c7c411bf62587338eee7b35f610c01a052fa5b5260cbfd0d26da87d4a113da30","observation_id":"350dd361-901f-4a69-b8a5-07ce2411b39c","resolution":{"observed_at":"2026-08-06T20:04:15.441681Z","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":"2026-08-06T20:04:14.974288Z","title":"Context-based and diversity-driven specificity in compositional zero-shot learning","venue":null,"work_id":"de77e174-a714-4bfb-b6d7-295aa1d6fe27","year":2024},"citing_paper":{"arxiv_id":"2507.04051","last_updated":"2025-07-05T14:20:49Z","snapshot_observed_at":"2026-08-06T19:54:20.560306Z","submitted_at":"2025-07-05T14:20:49Z","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T20:04:02.940100Z"},"links":{"citing_paper":"/paper/2507.04051"},"observation_digest":"sha256:d59df6fe0450df2f210d9fdf5fc2571bfdcc4789bda38a65dcfcc16413dc6f04","observation_id":"6fc721c7-009a-4829-b5be-000c6877bd50","resolution":{"observed_at":"2026-08-06T20:04:15.152102Z","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":"2026-08-06T20:04:14.783458Z","title":"Novel class discovery for ultra-fine-grained visual categorization","venue":null,"work_id":"d2f63738-8139-4bc2-86aa-d1634ef96000","year":2024},"citing_paper":{"arxiv_id":"2507.04051","last_updated":"2025-07-05T14:20:49Z","snapshot_observed_at":"2026-08-06T19:54:20.560306Z","submitted_at":"2025-07-05T14:20:49Z","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T20:04:03.037390Z"},"links":{"citing_paper":"/paper/2507.04051"},"observation_digest":"sha256:f1de49d252e251b692de4ed15a40c209f7eb73c0fbf60a5c2b55d9e10bf39996","observation_id":"0a20761c-314d-44bd-80e2-3d30f7bef693","resolution":{"observed_at":"2026-08-06T20:04:14.853782Z","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":"2026-08-06T20:04:14.653876Z","title":"Pmgnet: Disentanglement and entanglement benefit mutually for compositional zero-shot learning.Computer Vision and Image Understanding, 249: 104197, 2024","venue":null,"work_id":"6befe896-d990-4260-94fe-14fe8f332e0f","year":2024},"citing_paper":{"arxiv_id":"2507.04051","last_updated":"2025-07-05T14:20:49Z","snapshot_observed_at":"2026-08-06T19:54:20.560306Z","submitted_at":"2025-07-05T14:20:49Z","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T20:04:03.127027Z"},"links":{"citing_paper":"/paper/2507.04051"},"observation_digest":"sha256:edbbc824a274a66f64062d09a651e95e9ef7555c309b56c73decf2e154f47586","observation_id":"df47c484-b619-4c5c-8cc4-14fbf0cd7ebf","resolution":{"observed_at":"2026-08-06T20:04:14.703661Z","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":"2026-08-06T20:04:14.505751Z","title":"Some methods for classification and analysis of multivariate observations","venue":null,"work_id":"00da8a0e-b2ef-4de7-a8e4-74c8c7d368b8","year":1967},"citing_paper":{"arxiv_id":"2507.04051","last_updated":"2025-07-05T14:20:49Z","snapshot_observed_at":"2026-08-06T19:54:20.560306Z","submitted_at":"2025-07-05T14:20:49Z","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T20:04:03.277985Z"},"links":{"citing_paper":"/paper/2507.04051"},"observation_digest":"sha256:2713afe52861bfabe939a33dc59c354a380e216ecf0c7f14a3fad4fd9afe1017","observation_id":"97025a27-6974-41f1-9444-8461a230c050","resolution":{"observed_at":"2026-08-06T20:04:14.567429Z","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":"2112.10741","last_updated":"2022-03-08T18:18:49Z","snapshot_observed_at":"2026-08-07T12:21:17.790675Z","submitted_at":"2021-12-20T18:42:55Z","title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2112.10741","snapshot_observed_at":"2026-08-06T20:04:03.431624Z","title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models.arXiv preprint arXiv:2112.10741, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.04051","last_updated":"2025-07-05T14:20:49Z","snapshot_observed_at":"2026-08-06T19:54:20.560306Z","submitted_at":"2025-07-05T14:20:49Z","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T20:04:03.431624Z"},"links":{"cited_paper":"/paper/2112.10741","citing_paper":"/paper/2507.04051"},"observation_digest":"sha256:8abea5f8eb17a5ff59e4ef9027a71c1adb9903c9f0de691ae74444deae163e14","observation_id":"1958582f-8f0b-4302-b6dc-096ed90e1847","resolution":{"observed_at":"2026-08-06T20:04:03.431624Z","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":"2026-08-06T20:04:14.315366Z","title":"Cats and dogs","venue":null,"work_id":"eeda8e57-1bad-4abe-ba6a-49cf5530fc52","year":2012},"citing_paper":{"arxiv_id":"2507.04051","last_updated":"2025-07-05T14:20:49Z","snapshot_observed_at":"2026-08-06T19:54:20.560306Z","submitted_at":"2025-07-05T14:20:49Z","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T20:04:03.556026Z"},"links":{"citing_paper":"/paper/2507.04051"},"observation_digest":"sha256:fad00e3be21e8491e6a0e711a9cb9ba60c4346507a412f8e4eccc2781145ddfa","observation_id":"5bb501fa-4fde-4d69-8210-a24c9c510626","resolution":{"observed_at":"2026-08-06T20:04:14.387409Z","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":"2026-08-06T20:04:14.157301Z","title":"Unsupervised domain adap- tation via domain-adaptive diffusion.IEEE TIP, 2024","venue":null,"work_id":"9165c2a1-b817-4045-8c0d-4e64b4992207","year":2024},"citing_paper":{"arxiv_id":"2507.04051","last_updated":"2025-07-05T14:20:49Z","snapshot_observed_at":"2026-08-06T19:54:20.560306Z","submitted_at":"2025-07-05T14:20:49Z","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T20:04:03.718700Z"},"links":{"citing_paper":"/paper/2507.04051"},"observation_digest":"sha256:3c2f8cb275fc4fa4dcfefd79b29ff477859e39d0f4da82f8910d32bd0350e855","observation_id":"6566e612-900b-4616-b8e9-e7c3c7748897","resolution":{"observed_at":"2026-08-06T20:04:14.218591Z","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":"2026-08-06T20:04:14.017114Z","title":"Dynamic conceptional contrastive learning for generalized category discovery","venue":null,"work_id":"f1e928a0-ec9e-4a68-aebe-3efe1d53229f","year":2023},"citing_paper":{"arxiv_id":"2507.04051","last_updated":"2025-07-05T14:20:49Z","snapshot_observed_at":"2026-08-06T19:54:20.560306Z","submitted_at":"2025-07-05T14:20:49Z","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T20:04:03.853584Z"},"links":{"citing_paper":"/paper/2507.04051"},"observation_digest":"sha256:5957697304f954965fb77dbca0589607d0340b58e80667d7556fe5195fe4463c","observation_id":"bdf49bb0-1779-4c04-b0fd-79fad2dcebab","resolution":{"observed_at":"2026-08-06T20:04:14.080167Z","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":"2026-08-06T20:04:13.863951Z","title":"Federated generalized category discovery","venue":null,"work_id":"a2f1a274-7ca9-492e-bc3a-98de9f447499","year":2024},"citing_paper":{"arxiv_id":"2507.04051","last_updated":"2025-07-05T14:20:49Z","snapshot_observed_at":"2026-08-06T19:54:20.560306Z","submitted_at":"2025-07-05T14:20:49Z","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T20:04:04.035973Z"},"links":{"citing_paper":"/paper/2507.04051"},"observation_digest":"sha256:a84ea1fac86e12d4f368ff73ca0408f8d4ee2c1895bb4efedb949f598b66450c","observation_id":"3b4c0a5d-ee1b-4d69-98de-29622b3a8873","resolution":{"observed_at":"2026-08-06T20:04:13.921901Z","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":"2026-08-06T20:04:13.696961Z","title":"On the momentum term in gradient descent learning algorithms.Neural networks, 1999","venue":null,"work_id":"0f46f29d-eef1-4232-bbfd-73033511aff1","year":1999},"citing_paper":{"arxiv_id":"2507.04051","last_updated":"2025-07-05T14:20:49Z","snapshot_observed_at":"2026-08-06T19:54:20.560306Z","submitted_at":"2025-07-05T14:20:49Z","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T20:04:04.197531Z"},"links":{"citing_paper":"/paper/2507.04051"},"observation_digest":"sha256:c23675a1dcf75b8105bc9de9d154e481ff5ac3aefdae74dac9739386483e7d84","observation_id":"f83a3c52-96f4-4a0e-a6ff-1ff1afaae9d0","resolution":{"observed_at":"2026-08-06T20:04:13.771841Z","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":"2026-08-06T20:04:13.528054Z","title":"Learn- ing transferable visual models from natural language super- vision","venue":null,"work_id":"f0d8e56c-6338-436b-860b-db3cd54ae96f","year":2021},"citing_paper":{"arxiv_id":"2507.04051","last_updated":"2025-07-05T14:20:49Z","snapshot_observed_at":"2026-08-06T19:54:20.560306Z","submitted_at":"2025-07-05T14:20:49Z","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T20:04:04.330234Z"},"links":{"citing_paper":"/paper/2507.04051"},"observation_digest":"sha256:01b8c8fa1cb74c5fa5ad8df1ea794bc7c5a683e469b3db01a4a8a3a58bcff9da","observation_id":"9781de53-195c-49ab-87d5-fabe524792b2","resolution":{"observed_at":"2026-08-06T20:04:13.595263Z","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":"2204.06125","last_updated":"2022-04-13T01:10:33Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2022-04-13T01:10:33Z","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.06125","snapshot_observed_at":"2026-08-06T20:04:04.408297Z","title":"Hierarchical text-conditional image gener- ation with clip latents.arXiv preprint arXiv:2204.06125, 1 (2):3, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.04051","last_updated":"2025-07-05T14:20:49Z","snapshot_observed_at":"2026-08-06T19:54:20.560306Z","submitted_at":"2025-07-05T14:20:49Z","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T20:04:04.408297Z"},"links":{"cited_paper":"/paper/2204.06125","citing_paper":"/paper/2507.04051"},"observation_digest":"sha256:3b87d481cb37b733a913252c18136bc5b4f9992c8f7391ac2a689cdea4453018","observation_id":"1b28e3d6-570c-496d-9021-10bb2028cf94","resolution":{"observed_at":"2026-08-06T20:04:04.408297Z","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":"2026-08-06T20:04:04.537713Z","title":"High-resolution image syn- thesis with latent diffusion models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.04051","last_updated":"2025-07-05T14:20:49Z","snapshot_observed_at":"2026-08-06T19:54:20.560306Z","submitted_at":"2025-07-05T14:20:49Z","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T20:04:04.537713Z"},"links":{"citing_paper":"/paper/2507.04051"},"observation_digest":"sha256:83a8e548bf0fb529d4539fa3b937c023c929cc0f33e5022a1d4564495ea1bc62","observation_id":"cac759c7-a9bf-46ba-9162-3030441069de","resolution":{"observed_at":"2026-08-06T20:04:04.537713Z","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":"2026-08-06T20:04:13.341835Z","title":"The map equation.The European Physical Journal Special Top- ics, 2009","venue":null,"work_id":"989a6fe6-ad5e-4491-bace-30838ac2febc","year":2009},"citing_paper":{"arxiv_id":"2507.04051","last_updated":"2025-07-05T14:20:49Z","snapshot_observed_at":"2026-08-06T19:54:20.560306Z","submitted_at":"2025-07-05T14:20:49Z","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T20:04:04.689791Z"},"links":{"citing_paper":"/paper/2507.04051"},"observation_digest":"sha256:8d5e59884976dc8a691fe38e4429d7a3c1294b45642225d624dfdfac9c9988cc","observation_id":"26c729fc-8a0f-42dc-86f3-19e64aabf792","resolution":{"observed_at":"2026-08-06T20:04:13.425934Z","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":"2026-08-06T20:04:04.817002Z","title":"Dreambooth: Fine tuning text-to-image diffusion models for subject-driven generation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.04051","last_updated":"2025-07-05T14:20:49Z","snapshot_observed_at":"2026-08-06T19:54:20.560306Z","submitted_at":"2025-07-05T14:20:49Z","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T20:04:04.817002Z"},"links":{"citing_paper":"/paper/2507.04051"},"observation_digest":"sha256:dca30a53d0bc98083ec685e774c1116209ddca913939a6fd97e409e57c046002","observation_id":"fe46bf1e-021e-4396-9efa-68849ebd658f","resolution":{"observed_at":"2026-08-06T20:04:04.817002Z","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":"2026-08-06T20:04:13.014196Z","title":"Diversity is definitely needed: Improving model-agnostic zero-shot classification via stable diffusion","venue":null,"work_id":"18f68686-4168-4812-b05b-92e5261e57fb","year":2023},"citing_paper":{"arxiv_id":"2507.04051","last_updated":"2025-07-05T14:20:49Z","snapshot_observed_at":"2026-08-06T19:54:20.560306Z","submitted_at":"2025-07-05T14:20:49Z","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T20:04:04.977002Z"},"links":{"citing_paper":"/paper/2507.04051"},"observation_digest":"sha256:1081ebc4a1b753dacf9b2dcdd695ad64b5e582e53f1e00a0d903dc07fe681bd3","observation_id":"866cf37a-bb0a-45e4-b3c7-0f1fda380af9","resolution":{"observed_at":"2026-08-06T20:04:13.153079Z","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":"2026-08-06T20:04:12.760003Z","title":"Animating rotation with quaternion curves","venue":null,"work_id":"ede2f62a-192a-4604-a4cc-34faa5a9418d","year":1985},"citing_paper":{"arxiv_id":"2507.04051","last_updated":"2025-07-05T14:20:49Z","snapshot_observed_at":"2026-08-06T19:54:20.560306Z","submitted_at":"2025-07-05T14:20:49Z","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-06T20:04:05.130051Z"},"links":{"citing_paper":"/paper/2507.04051"},"observation_digest":"sha256:4ac383514f6decb64b64ea07044b097cf5da8693bf450a3f51aaacc0907dd9c9","observation_id":"51895fc6-65f3-40bc-8abf-fc87ae72868e","resolution":{"observed_at":"2026-08-06T20:04:12.866118Z","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":"2408.13335","last_updated":"2024-08-23T19:00:52Z","snapshot_observed_at":"2026-08-03T02:23:00.254890Z","submitted_at":"2024-08-23T19:00:52Z","title":"Latent Space Disentanglement in Diffusion Transformers Enables Zero-shot Fine-grained Semantic Editing","version":1},"cited_work":{"arxiv_id":"2408.13335","doi":null,"metadata_source":"pith","pith_arxiv_id":"2408.13335","snapshot_observed_at":"2026-08-06T20:04:08.158556Z","title":"Latent Space Disentanglement in Diffusion Transformers Enables Zero-shot Fine-grained Semantic Editing","venue":"cs.CV","work_id":"d37c4b0e-c5f9-45c7-8ff1-afcbe77c3296","year":2024},"citing_paper":{"arxiv_id":"2507.04051","last_updated":"2025-07-05T14:20:49Z","snapshot_observed_at":"2026-08-06T19:54:20.560306Z","submitted_at":"2025-07-05T14:20:49Z","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-06T20:04:05.259236Z"},"links":{"cited_paper":"/paper/2408.13335","citing_paper":"/paper/2507.04051"},"observation_digest":"sha256:a990b9f020686e7394c5e95141f86dfe9d45d24c2b3d74669cfdb0877d537919","observation_id":"09d7be6e-14a4-48c1-a45c-2be0b997bd8f","resolution":{"observed_at":"2026-08-06T20:04:08.251440Z","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":{"arxiv_id":"2302.07944","last_updated":"2025-06-10T20:01:59Z","snapshot_observed_at":"2026-08-07T10:59:13.865982Z","submitted_at":"2023-02-07T20:42:28Z","title":"Effective Data Augmentation With Diffusion Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.07944","snapshot_observed_at":"2026-08-06T20:04:05.419193Z","title":"Effective data augmentation with diffusion models.arXiv preprint arXiv:2302.07944, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.04051","last_updated":"2025-07-05T14:20:49Z","snapshot_observed_at":"2026-08-06T19:54:20.560306Z","submitted_at":"2025-07-05T14:20:49Z","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-06T20:04:05.419193Z"},"links":{"cited_paper":"/paper/2302.07944","citing_paper":"/paper/2507.04051"},"observation_digest":"sha256:d5d65b833e8b6c2997cbf40b7ecd5123953e48515298d6e87263261b0cb64c99","observation_id":"ad38fcbd-c0f0-405c-ae97-dbd1f786fdfc","resolution":{"observed_at":"2026-08-06T20:04:05.419193Z","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":"2026-08-06T20:04:12.525448Z","title":"Test-time stain adaptation with diffusion models for histopathology image classification","venue":null,"work_id":"d750c42c-9336-481b-aa76-43a61695a8a1","year":2025},"citing_paper":{"arxiv_id":"2507.04051","last_updated":"2025-07-05T14:20:49Z","snapshot_observed_at":"2026-08-06T19:54:20.560306Z","submitted_at":"2025-07-05T14:20:49Z","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-06T20:04:05.547142Z"},"links":{"citing_paper":"/paper/2507.04051"},"observation_digest":"sha256:a81de2d0ac64296b7e7145a6b3a1d87fc1daa9a30bf7c51b87658d792ccabbc7","observation_id":"e2b46b72-91c8-479c-a5d0-ff4c8c9d5ec6","resolution":{"observed_at":"2026-08-06T20:04:12.638097Z","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":"2026-08-06T20:04:12.324663Z","title":"The inaturalist species classification and de- tection dataset","venue":null,"work_id":"e1b46589-c0e0-4545-8af1-ea8b111bd4a1","year":2018},"citing_paper":{"arxiv_id":"2507.04051","last_updated":"2025-07-05T14:20:49Z","snapshot_observed_at":"2026-08-06T19:54:20.560306Z","submitted_at":"2025-07-05T14:20:49Z","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-06T20:04:05.691751Z"},"links":{"citing_paper":"/paper/2507.04051"},"observation_digest":"sha256:c761fc45365366f049b89f95f55745131623aebe7ac595651bb060921bb9822f","observation_id":"97f2a8af-5624-47f1-b06e-e2b882319e87","resolution":{"observed_at":"2026-08-06T20:04:12.416789Z","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":"2026-08-06T20:04:12.042805Z","title":"Generalized category discovery","venue":null,"work_id":"556c2d22-76a1-4bfb-93ba-a2f38b8c76cd","year":2022},"citing_paper":{"arxiv_id":"2507.04051","last_updated":"2025-07-05T14:20:49Z","snapshot_observed_at":"2026-08-06T19:54:20.560306Z","submitted_at":"2025-07-05T14:20:49Z","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-06T20:04:05.819794Z"},"links":{"citing_paper":"/paper/2507.04051"},"observation_digest":"sha256:ea460c699c329f9656a294aa33705c69cdebfd151be849d24b7e021d3578c79b","observation_id":"46bc823c-ec11-448e-90d6-0e899768f7b2","resolution":{"observed_at":"2026-08-06T20:04:12.156459Z","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":"2026-08-06T20:04:11.794653Z","title":"The caltech-ucsd birds-200-2011 dataset.Computation & Neural Systems Technical Report,","venue":null,"work_id":"080a69ff-de86-4bed-ac88-ce4c6d294763","year":2011},"citing_paper":{"arxiv_id":"2507.04051","last_updated":"2025-07-05T14:20:49Z","snapshot_observed_at":"2026-08-06T19:54:20.560306Z","submitted_at":"2025-07-05T14:20:49Z","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-06T20:04:05.960300Z"},"links":{"citing_paper":"/paper/2507.04051"},"observation_digest":"sha256:a4d2bf67a31522337b6f3a8b7990da2b80ee41b181bad06ca0778508b76eb40e","observation_id":"7e3ffabf-8cf9-477d-a1dc-1368d837d1d0","resolution":{"observed_at":"2026-08-06T20:04:11.889115Z","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":"2026-08-06T20:04:11.512522Z","title":"Videocomposer: Compositional video synthesis with motion controllability.NeurIPS, 2023","venue":null,"work_id":"c66b3438-8d3c-4d8b-a433-42face58ce39","year":2023},"citing_paper":{"arxiv_id":"2507.04051","last_updated":"2025-07-05T14:20:49Z","snapshot_observed_at":"2026-08-06T19:54:20.560306Z","submitted_at":"2025-07-05T14:20:49Z","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-06T20:04:06.082693Z"},"links":{"citing_paper":"/paper/2507.04051"},"observation_digest":"sha256:37db5be9701209dea6ad70ab95465798fdf461787409690c7be466497ca81fd2","observation_id":"ed401a11-8064-46fc-ab18-3143c313c745","resolution":{"observed_at":"2026-08-06T20:04:11.655017Z","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":"2026-08-06T20:04:11.245173Z","title":"Enhance im- age classification via inter-class image mixup with diffusion model","venue":null,"work_id":"14e89abe-f719-4d25-b9e9-487575abab92","year":2024},"citing_paper":{"arxiv_id":"2507.04051","last_updated":"2025-07-05T14:20:49Z","snapshot_observed_at":"2026-08-06T19:54:20.560306Z","submitted_at":"2025-07-05T14:20:49Z","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-06T20:04:06.203853Z"},"links":{"citing_paper":"/paper/2507.04051"},"observation_digest":"sha256:8e1924e27aa198bf28770e7066d2c6d2d3f06668c80e78c5d9e1edef9ddaef92","observation_id":"9f2e9c02-d5b1-49dd-8e9e-7ed2020ce9a5","resolution":{"observed_at":"2026-08-06T20:04:11.361450Z","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":"2026-08-06T20:04:10.992961Z","title":"Parametric classification for generalized category discovery: A baseline study","venue":null,"work_id":"24278617-022f-4c52-adff-403da284a439","year":2023},"citing_paper":{"arxiv_id":"2507.04051","last_updated":"2025-07-05T14:20:49Z","snapshot_observed_at":"2026-08-06T19:54:20.560306Z","submitted_at":"2025-07-05T14:20:49Z","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-06T20:04:06.344447Z"},"links":{"citing_paper":"/paper/2507.04051"},"observation_digest":"sha256:a1965ac9e6e79da9dbcdd7d8e23c302c5cd3e726326756b5f898053e853d3b5a","observation_id":"f562bbd3-7510-4d95-a389-958a8b2d2b6b","resolution":{"observed_at":"2026-08-06T20:04:11.120012Z","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":"2026-08-06T20:04:10.758872Z","title":"Metagcd: Learning to continually learn in generalized cat- egory discovery","venue":null,"work_id":"c74364ea-61ca-46d4-9458-b300b3026678","year":2023},"citing_paper":{"arxiv_id":"2507.04051","last_updated":"2025-07-05T14:20:49Z","snapshot_observed_at":"2026-08-06T19:54:20.560306Z","submitted_at":"2025-07-05T14:20:49Z","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-06T20:04:06.457467Z"},"links":{"citing_paper":"/paper/2507.04051"},"observation_digest":"sha256:39111fb5f6b19ade0dfa024a2e54a1dd019f516c7f2ed01e6557b1bc9354c2e2","observation_id":"c9c1cf19-07fe-4f3a-bd99-dec962ca15f8","resolution":{"observed_at":"2026-08-06T20:04:10.849965Z","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":"2026-08-06T20:04:10.484501Z","title":"Learning to distin- guish samples for generalized category discovery","venue":null,"work_id":"30427bf2-b996-442d-a984-432e21e8ae8b","year":null},"citing_paper":{"arxiv_id":"2507.04051","last_updated":"2025-07-05T14:20:49Z","snapshot_observed_at":"2026-08-06T19:54:20.560306Z","submitted_at":"2025-07-05T14:20:49Z","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-06T20:04:06.574681Z"},"links":{"citing_paper":"/paper/2507.04051"},"observation_digest":"sha256:bc0b2cd15872e59105b2911f32ed94ae93421f35367ac37dd763a70c6c5bdd51","observation_id":"f579127e-1524-471b-9b6e-16d61340ee0a","resolution":{"observed_at":"2026-08-06T20:04:10.636275Z","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":"2026-08-06T20:04:10.196426Z","title":"Diffusion models and semi-supervised learners benefit mutually with few labels.NeurIPS, 2024","venue":null,"work_id":"a31bd6bf-2ec1-4856-9709-582abd0692b8","year":2024},"citing_paper":{"arxiv_id":"2507.04051","last_updated":"2025-07-05T14:20:49Z","snapshot_observed_at":"2026-08-06T19:54:20.560306Z","submitted_at":"2025-07-05T14:20:49Z","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-06T20:04:06.692960Z"},"links":{"citing_paper":"/paper/2507.04051"},"observation_digest":"sha256:f1afa3c4888c120081fb0168b769fd7252fe04d2d101c814d788397da8a87e4a","observation_id":"0c4de176-dd14-42b1-8c66-8a00aa86e98f","resolution":{"observed_at":"2026-08-06T20:04:10.342178Z","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":"2205.01917","last_updated":"2022-06-14T00:48:04Z","snapshot_observed_at":"2026-07-06T13:06:27.153765Z","submitted_at":"2022-05-04T07:01:14Z","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.01917","snapshot_observed_at":"2026-08-06T20:04:06.787739Z","title":"Coca: Contrastive captioners are image-text foundation models.arXiv preprint arXiv:2205.01917, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.04051","last_updated":"2025-07-05T14:20:49Z","snapshot_observed_at":"2026-08-06T19:54:20.560306Z","submitted_at":"2025-07-05T14:20:49Z","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-06T20:04:06.787739Z"},"links":{"cited_paper":"/paper/2205.01917","citing_paper":"/paper/2507.04051"},"observation_digest":"sha256:71d4184b4ac47047fe2c42cdc11f813c029602741c5b83cd63b2bb11a0703be4","observation_id":"8737357b-a56a-4ef9-88ad-620086ed9711","resolution":{"observed_at":"2026-08-06T20:04:06.787739Z","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":"2026-08-06T20:04:09.932120Z","title":"Cutmix: Regu- larization strategy to train strong classifiers with localizable features","venue":null,"work_id":"3e805bee-272d-4d7d-a091-2e75341d16b4","year":2019},"citing_paper":{"arxiv_id":"2507.04051","last_updated":"2025-07-05T14:20:49Z","snapshot_observed_at":"2026-08-06T19:54:20.560306Z","submitted_at":"2025-07-05T14:20:49Z","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-06T20:04:06.929243Z"},"links":{"citing_paper":"/paper/2507.04051"},"observation_digest":"sha256:af0ed84375e73af07a553719a7a7affd04543bd7b4d73a51d163388513579e57","observation_id":"396c1e01-357c-4ab7-841a-9e43a28a8afa","resolution":{"observed_at":"2026-08-06T20:04:10.072988Z","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":"2026-08-06T20:04:09.698499Z","title":"mixup: Beyond 903 empirical risk minimization","venue":null,"work_id":"d5287fe1-19ea-4c06-bd55-9895ac9916bb","year":2018},"citing_paper":{"arxiv_id":"2507.04051","last_updated":"2025-07-05T14:20:49Z","snapshot_observed_at":"2026-08-06T19:54:20.560306Z","submitted_at":"2025-07-05T14:20:49Z","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-06T20:04:07.054170Z"},"links":{"citing_paper":"/paper/2507.04051"},"observation_digest":"sha256:e24445b9c803d3b4238acdd0e63568757ba553b288edff08589e5c528fcaf7a0","observation_id":"2c4ecc54-095d-4c20-a6f0-a838a0889318","resolution":{"observed_at":"2026-08-06T20:04:09.799342Z","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":"2026-08-06T20:04:09.488950Z","title":"Incremental general- ized category discovery","venue":null,"work_id":"884a0f57-3d4d-473d-a996-d1712077aa3a","year":2023},"citing_paper":{"arxiv_id":"2507.04051","last_updated":"2025-07-05T14:20:49Z","snapshot_observed_at":"2026-08-06T19:54:20.560306Z","submitted_at":"2025-07-05T14:20:49Z","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-06T20:04:07.197851Z"},"links":{"citing_paper":"/paper/2507.04051"},"observation_digest":"sha256:fd110edc9b013b6f088c97b866f47d63819caca3609502757f22519e3251491b","observation_id":"3bb875e7-3b1b-4ea0-9766-810707e12571","resolution":{"observed_at":"2026-08-06T20:04:09.596879Z","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":"2026-08-06T20:04:09.224393Z","title":"Pyramidal person re-identification via multi-loss dynamic training","venue":null,"work_id":"2cddb3b5-f0a0-4832-b1db-f854ad690984","year":2019},"citing_paper":{"arxiv_id":"2507.04051","last_updated":"2025-07-05T14:20:49Z","snapshot_observed_at":"2026-08-06T19:54:20.560306Z","submitted_at":"2025-07-05T14:20:49Z","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-06T20:04:07.315423Z"},"links":{"citing_paper":"/paper/2507.04051"},"observation_digest":"sha256:8ad093bb454f517f9f2d6d81d322e2c5eff2be0710a762d97e957e38c9f4a2a3","observation_id":"b9e7475f-ed7a-4771-9c45-d968e6663aa8","resolution":{"observed_at":"2026-08-06T20:04:09.369729Z","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":"2026-08-06T20:04:07.445985Z","title":"Textual knowledge matters: Cross-modality co- teaching for generalized visual class discovery","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.04051","last_updated":"2025-07-05T14:20:49Z","snapshot_observed_at":"2026-08-06T19:54:20.560306Z","submitted_at":"2025-07-05T14:20:49Z","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-06T20:04:07.445985Z"},"links":{"citing_paper":"/paper/2507.04051"},"observation_digest":"sha256:b0cb9286144efb46e5eaa94a91b556759dd52b059f3582851a6d8770e6ef26bc","observation_id":"4d56ddc2-dee5-46b1-ba66-8a189ce247ee","resolution":{"observed_at":"2026-08-06T20:04:07.445985Z","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":"2026-08-06T20:04:08.980476Z","title":"Prototypical hash encoding for on-the-fly fine- grained category discovery.NeurIPS, 2025","venue":null,"work_id":"258162a6-38d2-4d9f-8a48-7fb939468ef6","year":2025},"citing_paper":{"arxiv_id":"2507.04051","last_updated":"2025-07-05T14:20:49Z","snapshot_observed_at":"2026-08-06T19:54:20.560306Z","submitted_at":"2025-07-05T14:20:49Z","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-06T20:04:07.584440Z"},"links":{"citing_paper":"/paper/2507.04051"},"observation_digest":"sha256:67b7ba7f66e454344e27cc576d6ccdc84556d6ed819a515c7dff58f7e5e8460b","observation_id":"c8add011-bab9-4d78-9f71-0f1bc9dd011a","resolution":{"observed_at":"2026-08-06T20:04:09.096970Z","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":"2026-08-06T20:04:08.664873Z","title":"Neighborhood contrastive learn- ing for novel class discovery","venue":null,"work_id":"34b5e766-a349-4c9c-a67a-4cb7bde22f1f","year":2021},"citing_paper":{"arxiv_id":"2507.04051","last_updated":"2025-07-05T14:20:49Z","snapshot_observed_at":"2026-08-06T19:54:20.560306Z","submitted_at":"2025-07-05T14:20:49Z","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-06T20:04:07.706157Z"},"links":{"citing_paper":"/paper/2507.04051"},"observation_digest":"sha256:5b8e981e1895c54c8e8d3e1a7f1763ddded263ce4fcea7e14900d658972b53d3","observation_id":"ceb82185-fd62-4e4a-9ac6-b2d57c5e0533","resolution":{"observed_at":"2026-08-06T20:04:08.808728Z","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":"2026-08-06T20:04:08.472904Z","title":"Novel class discovery in chest x-rays via paired images and text","venue":null,"work_id":"d6ec6823-9dbf-4fce-84b8-d319930937ad","year":null},"citing_paper":{"arxiv_id":"2507.04051","last_updated":"2025-07-05T14:20:49Z","snapshot_observed_at":"2026-08-06T19:54:20.560306Z","submitted_at":"2025-07-05T14:20:49Z","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-06T20:04:07.837089Z"},"links":{"citing_paper":"/paper/2507.04051"},"observation_digest":"sha256:752a65e9cf37d75c063aaf1beb88c8e5e5bfc6d5435e0eb9dca62515e24dab81","observation_id":"05a0804e-4bc0-4a52-91a1-1f28d1a408ac","resolution":{"observed_at":"2026-08-06T20:04:08.560625Z","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":"2305.15316","last_updated":"2023-05-24T16:33:02Z","snapshot_observed_at":"2026-08-05T03:25:04.857257Z","submitted_at":"2023-05-24T16:33:02Z","title":"Training on Thin Air: Improve Image Classification with Generated Data","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.15316","snapshot_observed_at":"2026-08-06T20:04:07.964738Z","title":"Up- bound","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.04051","last_updated":"2025-07-05T14:20:49Z","snapshot_observed_at":"2026-08-06T19:54:20.560306Z","submitted_at":"2025-07-05T14:20:49Z","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-06T20:04:07.964738Z"},"links":{"cited_paper":"/paper/2305.15316","citing_paper":"/paper/2507.04051"},"observation_digest":"sha256:7584abea0936a13e13cca06d251ddbcc0b3719d45835f410d4ed4b7e5996aa8f","observation_id":"97141dff-f77c-4606-9e25-ab8659dd7663","resolution":{"observed_at":"2026-08-06T20:04:07.964738Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2507.04051","last_updated":"2025-07-05T14:20:49Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-06T19:54:20.560306Z","submitted_at":"2025-07-05T14:20:49Z","title":"Generate, Refine, and Encode: Leveraging Synthesized Novel Samples for On-the-Fly Fine-Grained Category Discovery"},"reference_resolution":{"displayed":62,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":11,"verified_exact":1,"verified_fuzzy":49},"total_outbound_references":62},"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 7 August 2026, this Paper Citation Record lists 62 of 62 outbound references and 1 inbound Pith citation observation for arXiv:2507.04051."}