{"as_of":"2026-08-17T22:57:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:b05082024622cd0ef458adf7d652696dc541c968ecae95027aa4e5b1fc1819f3","coverage":[{"denominator":66,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":66,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T20:53:05.020228Z","state":"measured"},{"denominator":66,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":66,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-17T06:30:58.91139+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2505.11703/citation-record","integrity":"/paper/2505.11703/integrity","json":"/paper/2505.11703/citation-record.json","paper":"/paper/2505.11703"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:53:05.825029Z","title":"Self-consuming gen- erative models go mad","venue":null,"work_id":"afc28e54-d7f1-4564-8e65-5715a8b5114b","year":2023},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:04.757099Z"},"links":{"citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:4c738be9388bca3595b4eb9cd1a231eda5a27da1df049e5785e2774afc887422","observation_id":"70076c1b-d8be-4249-9a63-7fba4f9f3f28","resolution":{"observed_at":"2026-08-15T20:53:05.829227Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:53:05.812134Z","title":null,"venue":null,"work_id":"ee9b39bf-d035-4853-9a38-26676167f095","year":null},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:04.761820Z"},"links":{"citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:b08c8daae5c5e1314c3ede219ea18833c4ff03c51285c4066c835f1fedb3c19b","observation_id":"31715068-a5a4-4239-9a97-b24221234c85","resolution":{"observed_at":"2026-08-15T20:53:05.815961Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2302.02503","last_updated":"2023-05-24T01:39:41Z","snapshot_observed_at":"2026-08-16T15:57:33.881679Z","submitted_at":"2023-02-05T22:49:33Z","title":"Leaving Reality to Imagination: Robust Classification via Generated Datasets","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.02503","snapshot_observed_at":"2026-08-15T20:53:04.766220Z","title":"Leaving reality to imag- ination: Robust classification via generated datasets","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:04.766220Z"},"links":{"cited_paper":"/paper/2302.02503","citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:023d229ad7198d4a2980678a6b62616e42839f452735d25d749f5aa7aad618c3","observation_id":"93ea507b-2b19-4f06-99d8-e6e3a8900749","resolution":{"observed_at":"2026-08-15T20:53:04.766220Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:53:05.799302Z","title":"On the stability of iterative retraining of generative models on their own data","venue":null,"work_id":"39c2cacf-f847-45ff-881f-f25dc5e791b4","year":2024},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:04.770596Z"},"links":{"citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:e6086c2a6b47f79e6ffaa214300d4be2839812e6f135ba60d1e44a089648c099","observation_id":"86c337d9-f70f-4886-b395-9032a2e44485","resolution":{"observed_at":"2026-08-15T20:53:05.803612Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:53:04.774642Z","title":"Improving image generation with better captions","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:04.774642Z"},"links":{"citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:5d4bbd34b047c98a14761f80c982c5182c6a0e04bdbfeaed4add6ad6e42501be","observation_id":"a0a1c8c7-a24e-4055-a6b0-1d1682123532","resolution":{"observed_at":"2026-08-15T20:53:04.774642Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.07726","last_updated":"2024-10-10T17:28:23Z","snapshot_observed_at":"2026-08-08T07:16:45.596308Z","submitted_at":"2024-07-10T14:57:46Z","title":"PaliGemma: A versatile 3B VLM for transfer","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.07726","snapshot_observed_at":"2026-08-15T20:53:04.778746Z","title":"Paligemma: A versatile 3b vlm for trans- fer","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:04.778746Z"},"links":{"cited_paper":"/paper/2407.07726","citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:6407dda2dc4ca46c9591ff6075fae505847d745e8c3a866cc14112054d822ad1","observation_id":"395cc0bf-1758-47a5-89e0-dac2267c5f8b","resolution":{"observed_at":"2026-08-15T20:53:04.778746Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:53:04.783256Z","title":"Food-101–mining discriminative components with random forests","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:04.783256Z"},"links":{"citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:57e5a574933404ac3faa9d99be48aef92f0af9cfcc1fed8521ec3bb05718e6fa","observation_id":"da68096b-f9d5-4ab5-941d-a0c478f11e66","resolution":{"observed_at":"2026-08-15T20:53:04.783256Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:53:05.769439Z","title":"An empiri- cal study of training self-supervised vision transformers","venue":null,"work_id":"c3e36fbe-fa27-4849-a3fa-56e1edd1d234","year":2021},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:04.787921Z"},"links":{"citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:c4e794e3ee0cce86fb36769603297bd0deb17f55ae260e995ef51bce37083bd4","observation_id":"15ec1cb4-232d-4be0-912c-bb5f41e1aa0a","resolution":{"observed_at":"2026-08-15T20:53:05.773942Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:53:05.756706Z","title":"Cimpoi, S","venue":null,"work_id":"070e0dc6-3ba0-4d6a-b64f-dbfb62409765","year":2014},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:04.791855Z"},"links":{"citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:20950d1986cc599e55e1800187d771c3f64f12d7ce8a842cb4a71a989b048cfc","observation_id":"4c79e6aa-f379-424e-b9dc-b1d6bfe80798","resolution":{"observed_at":"2026-08-15T20:53:05.760932Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:53:05.743206Z","title":"Turrisi da Costa, Nicola Dall’Asen, Yiming Wang, Nicu Sebe, and Elisa Ricci","venue":null,"work_id":"6cf41aea-7014-427a-8d03-5a3e063d782f","year":2023},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:04.795691Z"},"links":{"citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:b380fad559426e933125a8788b47b7ab2e353ae3bcf37f39fea48c53d882b675","observation_id":"ab21438e-e6fc-4e01-ad96-b840350418b5","resolution":{"observed_at":"2026-08-15T20:53:05.747600Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.09413","last_updated":"2024-11-22T05:12:30Z","snapshot_observed_at":"2026-08-17T19:32:47.224015Z","submitted_at":"2024-06-13T17:59:56Z","title":"Interpreting the Weight Space of Customized Diffusion Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.09413","snapshot_observed_at":"2026-08-15T20:53:04.799911Z","title":"Interpreting the weight space of customized dif- fusion models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:04.799911Z"},"links":{"cited_paper":"/paper/2406.09413","citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:eb6640d8f32d1f01c47ea744e3f61e62840863e4ddaa1d344ddb0b0aef662f3d","observation_id":"45762109-6d49-49be-b964-5f78c9d17d9d","resolution":{"observed_at":"2026-08-15T20:53:04.799911Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:53:05.730350Z","title":"Dream the impossible: Outlier imagination with diffusion models","venue":null,"work_id":"1783c60b-7bad-4328-913d-a5403c4aacaa","year":2023},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:04.803904Z"},"links":{"citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:658564bb5a69bf82a3534d5ffca5095785900c99d389bedead057f2a2a3d2d57","observation_id":"81e69eeb-8b64-4d1b-99f6-b4b031673a9c","resolution":{"observed_at":"2026-08-15T20:53:05.734540Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:53:05.717078Z","title":"Gonzalez, and Trevor Darrell","venue":null,"work_id":"67662dbc-b042-48d7-84f8-9b902330f2fd","year":null},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:04.807640Z"},"links":{"citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:2097833d041b9743a2e383b427a71e1f2dcd3f2edd44f77e915d4d5f537fdc40","observation_id":"634af2dc-54cd-4095-9385-ee03df976b67","resolution":{"observed_at":"2026-08-15T20:53:05.721320Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:53:05.703272Z","title":"Scaling laws of synthetic images for model training","venue":null,"work_id":"71373099-6904-4ac1-94a0-37a67d970bf9","year":2024},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:04.811516Z"},"links":{"citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:a605d39a2f87e9219856ff85ec5a593dc36f5374927aa6772a195604842f8b9f","observation_id":"5bda285f-aaf2-4a8a-bb81-8ae1a0f52df4","resolution":{"observed_at":"2026-08-15T20:53:05.708463Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.12803","last_updated":"2024-03-19T15:04:35Z","snapshot_observed_at":"2026-08-16T14:08:22.046906Z","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":"2026-08-15T20:53:04.815647Z","title":"Dreamda: Generative data augmentation with diffusion mod- els","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:04.815647Z"},"links":{"cited_paper":"/paper/2403.12803","citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:df06f23c2cc667690bc5378e8580cccaeb3a7279954ead5d2e5fadf4e4aebfa4","observation_id":"3c247fd9-c74a-4f40-bfe2-dca4c9e0df1f","resolution":{"observed_at":"2026-08-15T20:53:04.815647Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:53:05.690388Z","title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","venue":null,"work_id":"d8bf537a-5082-4b42-b742-48de47fcd1ec","year":2022},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:04.819749Z"},"links":{"citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:5d9d5243b220b4cc50eeee0d2a60da175f58c447924ebf933a4bb7440095412f","observation_id":"6e50f182-3856-4a58-adfc-b760778c24e4","resolution":{"observed_at":"2026-08-15T20:53:05.694636Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.01832","last_updated":"2024-07-18T10:21:29Z","snapshot_observed_at":"2026-08-16T14:22:02.043874Z","submitted_at":"2024-02-02T18:59:58Z","title":"SynthCLIP: Are We Ready for a Fully Synthetic CLIP Training?","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.01832","snapshot_observed_at":"2026-08-15T20:53:04.823604Z","title":"Synthclip: Are we ready for a fully synthetic clip training? arXiv preprint arXiv:2402.01832, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:04.823604Z"},"links":{"cited_paper":"/paper/2402.01832","citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:7fb69218fee98ee11196226e76568fb186c2077e9b07691d6512c5589a27f1fd","observation_id":"f189a9a1-a2f0-40c3-a29b-22b4c06021fe","resolution":{"observed_at":"2026-08-15T20:53:04.823604Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:53:04.827929Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:04.827929Z"},"links":{"citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:49327a0cc7454f4e6a5b0bf40805babf9e39ffbc1a293895a0fecc7fcbeba57e","observation_id":"cf5debda-e651-412b-85fb-ff963cc6c11f","resolution":{"observed_at":"2026-08-15T20:53:04.827929Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:53:05.663647Z","title":"Is syn- thetic data from generative models ready for image recogni- tion? In ICLR, 2023","venue":null,"work_id":"3911fd06-b8d8-454e-a4b5-ef5960356c73","year":2023},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:04.832111Z"},"links":{"citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:58ce1c69e8bcb39215bc90d958a28429a64106f4cbd1458348d7388664496607","observation_id":"ee8077fe-deae-4533-ace4-7226549d89df","resolution":{"observed_at":"2026-08-15T20:53:05.668035Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:53:05.650376Z","title":"Eurosat: A novel dataset and deep learn- ing benchmark for land use and land cover classification","venue":null,"work_id":"234d27cd-8e61-407c-a843-2861e3d31412","year":2019},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:04.837020Z"},"links":{"citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:7b87d8efdc47e886a60bdb4cbc50a3b5c0e40fe0f7faf0b4e9673616e38c8213","observation_id":"c3eb720a-407a-49f3-9210-1cbab4ce222e","resolution":{"observed_at":"2026-08-15T20:53:05.654912Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.00158","last_updated":"2024-09-09T22:06:05Z","snapshot_observed_at":"2026-08-16T14:56:22.584041Z","submitted_at":"2023-09-29T21:47:57Z","title":"Feedback-guided Data Synthesis for Imbalanced Classification","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.00158","snapshot_observed_at":"2026-08-15T20:53:04.841466Z","title":"Feedback-guided data synthesis for imbalanced classifica- tion","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:04.841466Z"},"links":{"cited_paper":"/paper/2310.00158","citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:d7ce274e30c2bd220b805870d06e6da5b233cd3fdbbe87bb3892dcfe401cae80","observation_id":"2fd39d07-ad19-49b1-9763-13cabd9db94d","resolution":{"observed_at":"2026-08-15T20:53:04.841466Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:53:05.637401Z","title":"Gans trained by a two time-scale update rule converge to a local nash equilib- rium","venue":null,"work_id":"3e53aaf8-66f0-4495-babc-7a612dfdb833","year":2017},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:04.845670Z"},"links":{"citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:165c2cae6b1e2407d4cb32597dd283864e526e004ebf72686b1247d590543273","observation_id":"3420ba80-0db6-46f0-b054-c1cf2dfcae4f","resolution":{"observed_at":"2026-08-15T20:53:05.641661Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:53:04.849401Z","title":"Denoising diffu- sion probabilistic models","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:04.849401Z"},"links":{"citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:321544cd3bd3eba3f0650a5884ab816274bcb588076d5b205f1402a3403e81de","observation_id":"26a40825-96b8-4281-bebd-777d95372643","resolution":{"observed_at":"2026-08-15T20:53:04.849401Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:53:05.614936Z","title":"LoRA: Low-rank adaptation of large language models","venue":null,"work_id":"ca0dd0c7-106d-4db1-9dc1-bd2fe713d95c","year":2022},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:04.853124Z"},"links":{"citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:8bde55f8e36268a6842b18bda482c9beb8580237d9d091a3639a36be5d970f08","observation_id":"42d3fd0e-f010-4b1e-82e8-09b749338daf","resolution":{"observed_at":"2026-08-15T20:53:05.619614Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:53:05.601106Z","title":"Datadream: Few-shot guided dataset generation","venue":null,"work_id":"67302f99-e482-4c16-a38d-5860f5a9d138","year":2024},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:04.856878Z"},"links":{"citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:be96e578289382be5ac81835a3d2272d2e7a701561c51e3ae142b7091215957c","observation_id":"7cc8ca14-f8f3-470c-b1bf-a3f10d0b0bcb","resolution":{"observed_at":"2026-08-15T20:53:05.605318Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:53:05.587744Z","title":"3d object representations for fine-grained categorization","venue":null,"work_id":"36aa5816-801f-4cd6-87d2-d4bb32c8e955","year":2013},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:04.860743Z"},"links":{"citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:48ad3c496adf5df3ee2abf75f4e2c7c130e905ca533312e2bafd454225982bf3","observation_id":"8ab087e5-b77b-424c-b70c-a2032e9e969f","resolution":{"observed_at":"2026-08-15T20:53:05.592474Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.08526","last_updated":"2025-06-23T16:21:02Z","snapshot_observed_at":"2026-08-16T15:15:40.107841Z","submitted_at":"2023-07-17T14:38:11Z","title":"Image Captions are Natural Prompts for Text-to-Image Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.08526","snapshot_observed_at":"2026-08-15T20:53:04.864602Z","title":"Image captions are natural prompts for text-to-image models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:04.864602Z"},"links":{"cited_paper":"/paper/2307.08526","citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:8b7e7bd4510cedf29bc6324abfad75666584f415969256e628deff7c8c369da4","observation_id":"3330322b-5bd3-4116-b5c8-c7a8698d2763","resolution":{"observed_at":"2026-08-15T20:53:04.864602Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:53:05.575054Z","title":"Caltech 101, 2022","venue":null,"work_id":"dccf2abd-b1bd-4fbc-877f-64d46aeb0d67","year":2022},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:04.868704Z"},"links":{"citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:fab67282ed7a0a3214f5fc87a5e5f4bcc81f37a54cf3226a434e5fc230b144e4","observation_id":"b561c00b-5dc0-4208-8f3d-3c5b3414f6d0","resolution":{"observed_at":"2026-08-15T20:53:05.579155Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:53:05.562524Z","title":"Ex- plore the power of synthetic data on few-shot object detec- tion","venue":null,"work_id":"c29b700b-1752-4e33-92ed-e465125a61b4","year":2023},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:04.872488Z"},"links":{"citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:2736480fc215fb2097de83b877978605f69263c26ae0955840a9d277ce9a5903","observation_id":"2207f15e-0b50-4cdc-a68c-919145c4635b","resolution":{"observed_at":"2026-08-15T20:53:05.566686Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:53:05.550018Z","title":"Does feasi- bility matter? understanding the impact of feasibility on syn- thetic training data","venue":null,"work_id":"4d53a893-c09f-4f36-a302-689a88b255f9","year":2025},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:04.876326Z"},"links":{"citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:d7453f3009a67db5d6bcf82d0bed8ad930433f6ad6f7bc5f6f606a23e94e52e7","observation_id":"b3e06172-6d22-406c-ab05-9c278bb25656","resolution":{"observed_at":"2026-08-15T20:53:05.554434Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:53:04.880593Z","title":"Decoupled weight decay regularization","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:04.880593Z"},"links":{"citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:f345d0c3a07d7ab8008fdd2b55b4bed8d20f8fa09f10a6e69b0bd1ed3a15fcc4","observation_id":"06076546-30dc-4951-b147-31755e0a58fd","resolution":{"observed_at":"2026-08-15T20:53:04.880593Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:53:05.529705Z","title":null,"venue":null,"work_id":"56a8c647-7ca5-4052-b4b3-e015251660dc","year":2013},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:04.885140Z"},"links":{"citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:dae9f593df5356c5caad6bae778c94656c9747b2ef3e3f4c575049eecc0c3f87","observation_id":"f510e01b-1dbb-4eb0-9722-23ea36779656","resolution":{"observed_at":"2026-08-15T20:53:05.533632Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"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":"2026-08-15T20:53:04.888934Z","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":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:04.888934Z"},"links":{"cited_paper":"/paper/2112.10741","citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:95248c6f9dab0c1c18008cf82e55ac241fd22fc3d519f45de0f98c996d3196f6","observation_id":"6486b04e-2f17-49f9-8ec1-758560f2eac5","resolution":{"observed_at":"2026-08-15T20:53:04.888934Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:53:05.516930Z","title":"Automated flower classification over a large number of classes","venue":null,"work_id":"f852b265-58f2-4141-ac6d-cbcffad190f4","year":2008},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:04.892846Z"},"links":{"citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:63b780ed57a59f98e4ee12e33cd0c64a5b8e2c22bb8c62394bfb4df31a56af40","observation_id":"bcad27cb-6e79-4a7b-82ea-58b07da361d1","resolution":{"observed_at":"2026-08-15T20:53:05.521082Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:53:05.504600Z","title":"Parkhi, Andrea Vedaldi, Andrew Zisserman, and C","venue":null,"work_id":"5ecaae64-ab1d-4c15-a9e1-286037580910","year":2012},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:04.897378Z"},"links":{"citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:0d9b3a83b22f8948b418908b96a6b2682d0c7df0047db58814cc640ae7376bc0","observation_id":"2e3ba0c7-4347-4d33-b94c-cb0e68f085a4","resolution":{"observed_at":"2026-08-15T20:53:05.508601Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:53:04.901284Z","title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:04.901284Z"},"links":{"citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:bc51cccdb89c82d1ce91f130a4bf1cad03a2fda2a9a0672c40e19c047d8bba62","observation_id":"33fb6d28-44d5-4198-83ba-4527c45fe010","resolution":{"observed_at":"2026-08-15T20:53:04.901284Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:53:05.484350Z","title":"Controlling text-to-image diffusion by orthogo- nal finetuning","venue":null,"work_id":"f06118d2-7fc8-4316-af99-d05302ea3b05","year":2023},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:04.904914Z"},"links":{"citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:598b09ce490f8649df573cfbdd0465af59a5e0905c5aa0f4259ac7fde1c28dbd","observation_id":"7d6d1fda-c4f9-440e-b12c-0a0e273fd3cf","resolution":{"observed_at":"2026-08-15T20:53:05.488431Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:53:04.908751Z","title":"Learn- ing transferable visual models from natural language super- vision","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:04.908751Z"},"links":{"citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:1c6e9644da5d1f313545b15d8b18e7676fbbb26b3808edbe344daa12fe9e6436","observation_id":"25ad4f08-12d8-4ad7-a094-eeb1920268fb","resolution":{"observed_at":"2026-08-15T20:53:04.908751Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2204.06125","last_updated":"2022-04-13T01:10:33Z","snapshot_observed_at":"2026-08-15T12:50:58.405488Z","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":"2026-08-15T20:53:04.912732Z","title":"Hierarchical text-conditional image gener- ation with clip latents","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:04.912732Z"},"links":{"cited_paper":"/paper/2204.06125","citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:edd6db36b7abcd0ef95ef6679176e94ffbdf4a3c3abebc7979f71cc8021c197f","observation_id":"94701490-0b80-4af3-ae05-74c0e0187f46","resolution":{"observed_at":"2026-08-15T20:53:04.912732Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:53:05.464516Z","title":"High-resolution image syn- thesis with latent diffusion models","venue":null,"work_id":"8ff169de-56f7-4abe-9a8c-cff631ceb1d4","year":2022},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:04.916459Z"},"links":{"citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:2b0cb212e801a02ad1604b1dac751d59e39f1c67220ea8c0041eb695634feb67","observation_id":"702039bf-0e5c-4261-a25c-237d9e2560f6","resolution":{"observed_at":"2026-08-15T20:53:05.468753Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:53:04.920371Z","title":"Dreambooth: Fine tuning text-to-image diffusion models for subject-driven generation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:04.920371Z"},"links":{"citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:7b9252280fd496671e34342f3c13fe0fb1a4c438b8af473113464145372fa154","observation_id":"494cc6d6-7b30-4f64-b1a0-0ac7e677c23b","resolution":{"observed_at":"2026-08-15T20:53:04.920371Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:53:05.444157Z","title":"Hyperdreambooth: Hypernetworks for fast personalization of text-to-image models","venue":null,"work_id":"7e992325-0809-4c4a-a36e-cc69ebf8001c","year":2024},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:04.924281Z"},"links":{"citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:7b1eec4eb6be5c0f8bbaee262af3725e5000e8e98edb87eaac3410497f706e7b","observation_id":"f5c56aa1-7254-426b-b8c9-e0a3b3a863e4","resolution":{"observed_at":"2026-08-15T20:53:05.448240Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:53:04.928283Z","title":"Imagenet large scale visual recognition challenge","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:04.928283Z"},"links":{"citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:8ce413c300fcb858823fad7c68505ed94dbc9362d8d487cb41ee0b7976cccfb7","observation_id":"c8adb78f-24e2-413b-bb21-fc9c23c94d66","resolution":{"observed_at":"2026-08-15T20:53:04.928283Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:53:04.932031Z","title":"Photorealistic text-to-image diffusion models with deep language understanding","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:04.932031Z"},"links":{"citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:89c659b41de2019441f4561cced3c792932fa716c37fcabb709f53b86628fd65","observation_id":"02d39add-e894-46f4-a0f1-ae45b22725fa","resolution":{"observed_at":"2026-08-15T20:53:04.932031Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:53:05.414695Z","title":"Fake it till you make it: Learning trans- ferable representations from synthetic imagenet clones","venue":null,"work_id":"75c93de1-4609-4a52-b366-cd6739c3dfeb","year":2023},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:04.935797Z"},"links":{"citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:3e9b8e3eb0350bc9c7faf0b74e908914d7179a5b8b6d3c1fa8782877a33a7bf1","observation_id":"d1a88023-4b31-4f94-a7f2-c31c351ee178","resolution":{"observed_at":"2026-08-15T20:53:05.418836Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.07750","last_updated":"2024-06-07T12:10:47Z","snapshot_observed_at":"2026-08-17T01:15:51.942260Z","submitted_at":"2024-03-12T15:36:42Z","title":"Synth$^2$: Boosting Visual-Language Models with Synthetic Captions and Image Embeddings","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.07750","snapshot_observed_at":"2026-08-15T20:53:04.939884Z","title":"Synth2: Boosting visual-language models with synthetic captions and image embeddings","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:04.939884Z"},"links":{"cited_paper":"/paper/2403.07750","citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:71ca3e95e9e8d6bf67f896332fd244f3f0b7173d91f640be6746a4636ce96f5c","observation_id":"800043fb-8e38-4df4-baa3-8aec5c4a1828","resolution":{"observed_at":"2026-08-15T20:53:04.939884Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:53:05.401607Z","title":"Instant- booth: Personalized text-to-image generation without test- time finetuning","venue":null,"work_id":"1267b58c-1701-48a4-af4b-ec4c97c06489","year":2024},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:04.944148Z"},"links":{"citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:7793ceca0dd9f2128b3202b334297d7c1761cffda796d036b5ede105fb2d4c65","observation_id":"922d5fcb-3c8b-4133-9ca7-9664fcfbec90","resolution":{"observed_at":"2026-08-15T20:53:05.405945Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.07200","last_updated":"2023-06-12T16:01:20Z","snapshot_observed_at":"2026-08-16T15:24:33.388850Z","submitted_at":"2023-06-12T16:01:20Z","title":"Fill-Up: Balancing Long-Tailed Data with Generative Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.07200","snapshot_observed_at":"2026-08-15T20:53:04.948108Z","title":"Fill-up: Balancing long-tailed data with generative models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:04.948108Z"},"links":{"cited_paper":"/paper/2306.07200","citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:62a70ac8f3b1a6cdf4a549f2e9233f216bf35f0aacfa846767436f792ad07403","observation_id":"cababd4a-882d-45c4-98fe-c28f827eaef7","resolution":{"observed_at":"2026-08-15T20:53:04.948108Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:53:05.388970Z","title":"Diversity is definitely needed: 10 Improving model-agnostic zero-shot classification via stable diffusion, 2023","venue":null,"work_id":"81270c67-93e9-45e1-a18e-8c6749b08244","year":2023},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:04.952244Z"},"links":{"citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:49179e4b78d6356cbd585f18da214b24643a635849d2ce23f43980c7280693c1","observation_id":"154dce92-0d79-4900-9814-e0f3183c0504","resolution":{"observed_at":"2026-08-15T20:53:05.393292Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:53:05.374701Z","title":"Semantic-aware data augmentation for text-to-image synthesis","venue":null,"work_id":"2e960f59-e468-4d01-890d-6da78d648615","year":null},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:04.957113Z"},"links":{"citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:2bfaaeb2af732605e74e3642c8c130b861e0ed61bd072a1c233a598a9255fc42","observation_id":"e9d721fe-2d37-40f1-9d77-b0bf7ee933b2","resolution":{"observed_at":"2026-08-15T20:53:05.380379Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:53:05.361987Z","title":"Amu-tuning: Effective logit bias for clip-based few-shot learning","venue":null,"work_id":"143dcbfe-116c-43b7-8449-7addb57f07f4","year":2024},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:04.961518Z"},"links":{"citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:5a411ad7c22e0b61d465b48b8a5daa38787237ecc656f63d920373226837d1da","observation_id":"8a5fa428-9961-44cc-a27f-537a6b0b71dc","resolution":{"observed_at":"2026-08-15T20:53:05.366248Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:53:04.965409Z","title":"Stablerep: Synthetic images from text-to- image models make strong visual representation learners","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:04.965409Z"},"links":{"citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:bbe6c66e096c468c0aa93083a3a6a26e47c31ea578c48d6106cc3fabc58807e3","observation_id":"ec6fbb9a-fff4-4e7c-84c2-924c56e04385","resolution":{"observed_at":"2026-08-15T20:53:04.965409Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:53:04.969221Z","title":"Learning vision from mod- els rivals learning vision from data","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:04.969221Z"},"links":{"citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:7225875ee8bc59f0262de37d21c2184347b9da00f7101d0b5ad8bd0b26dd9d85","observation_id":"29463b6d-6da0-45c6-9ce4-1a06c2b66a1e","resolution":{"observed_at":"2026-08-15T20:53:04.969221Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:53:05.332689Z","title":"Anti-dreambooth: Pro- tecting users from personalized text-to-image synthesis","venue":null,"work_id":"3fb8a880-5a32-4b4b-85ee-0ad9c12509f8","year":2023},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:04.973190Z"},"links":{"citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:7ed0cd01e9cba0bfcd31351eca468c25f9250b7500fee6f6df2b522b867d71e6","observation_id":"da1631ba-6971-40ac-9e63-fb03a87ecf25","resolution":{"observed_at":"2026-08-15T20:53:05.336956Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:53:04.977012Z","title":"Sun database: Large-scale scene recognition from abbey to zoo","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:04.977012Z"},"links":{"citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:25a3d87001c67fa96d5c8a59b682d7632f93cb65e4f0be335ad68b96531d4a80","observation_id":"1b6ea53b-9b72-4f79-ad16-e94d404d902b","resolution":{"observed_at":"2026-08-15T20:53:04.977012Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.00994","last_updated":"2024-04-25T09:53:33Z","snapshot_observed_at":"2026-08-16T15:11:25.029490Z","submitted_at":"2023-08-02T07:59:25Z","title":"SYNAuG: Exploiting Synthetic Data for Data Imbalance Problems","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.00994","snapshot_observed_at":"2026-08-15T20:53:04.980967Z","title":"Synaug: Exploiting synthetic data for data imbalance problems","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:04.980967Z"},"links":{"cited_paper":"/paper/2308.00994","citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:c02e0f9736e148ebcbd6aa6cf27c57716a675d501bb3005502e8bcb81e70e7f3","observation_id":"e471f688-1fee-4e16-91b7-78795466130f","resolution":{"observed_at":"2026-08-15T20:53:04.980967Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.15309","last_updated":"2025-05-19T14:28:42Z","snapshot_observed_at":"2026-08-16T14:07:17.567811Z","submitted_at":"2024-03-22T15:59:24Z","title":"Controlled Training Data Generation with Diffusion Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.15309","snapshot_observed_at":"2026-08-15T20:53:04.984842Z","title":"Controlled training data generation with diffusion mod- els","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:04.984842Z"},"links":{"cited_paper":"/paper/2403.15309","citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:9493d8bb27c5518d3359953effdcba11e1604ac6d43bc943d8ef34241f1eecfc","observation_id":"165588f0-e299-458f-92ad-82e59fcc3cbc","resolution":{"observed_at":"2026-08-15T20:53:04.984842Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:53:05.311092Z","title":"Diffusion models and semi-supervised learners benefit mutually with few labels","venue":null,"work_id":"4324149c-9abe-4b86-bd6d-b75e0b5a3046","year":2023},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:04.988948Z"},"links":{"citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:01c413023ce013e40cc4df74f67f081e467bfbf89fe5e584beb6dd0d673f5346","observation_id":"b727bcd6-f244-458b-b172-e7c12c574b74","resolution":{"observed_at":"2026-08-15T20:53:05.315668Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.02253","last_updated":"2025-01-21T06:03:07Z","snapshot_observed_at":"2026-08-16T14:37:45.910275Z","submitted_at":"2023-12-04T18:35:27Z","title":"Diversify, Don't Fine-Tune: Scaling Up Visual Recognition Training with Synthetic Images","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.02253","snapshot_observed_at":"2026-08-15T20:53:04.992833Z","title":"Diversify, don’t fine-tune: Scaling up visual recognition training with synthetic images","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:04.992833Z"},"links":{"cited_paper":"/paper/2312.02253","citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:3dcb8819a7f8f627a953ca9a6e75f49d5d72111e157303782a32440ac5492a53","observation_id":"27172c52-211f-4524-91ff-fb07fb9170c5","resolution":{"observed_at":"2026-08-15T20:53:04.992833Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:53:05.297527Z","title":"Real-fake: Effective training data synthesis through distribution matching","venue":null,"work_id":"38cef2a5-0424-4ad8-897f-6fa35b1d057d","year":2024},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:04.996817Z"},"links":{"citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:bd1d5716b1e8db26707781dc75624a4229f6d3ae32f5fe03cfd440a77dc83791","observation_id":"d128ec8c-37d7-4f34-b059-697364e83f86","resolution":{"observed_at":"2026-08-15T20:53:05.301619Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:53:05.284579Z","title":"Diffmorpher: Unleashing the capability of diffu- sion models for image morphing","venue":null,"work_id":"bcadce7e-7374-4efc-aac1-89352bc46070","year":2024},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:05.000727Z"},"links":{"citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:54961d1bfd4a0617500067e23692ac176aa717d47ef22177228ae3ff6273b41d","observation_id":"2ced5517-3a8d-4b83-8eb8-2e2fd8795a4e","resolution":{"observed_at":"2026-08-15T20:53:05.288995Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:53:05.272374Z","title":"Tip- adapter: Training-free adaption of clip for few-shot classi- fication","venue":null,"work_id":"f0df8c35-6cdc-4e44-868a-ab94ad95a62d","year":2022},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:05.004368Z"},"links":{"citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:22037293c0c5922b00ae360fe0375d12fd597a9cacf72b5daa9ebbf7e825f927","observation_id":"632be87f-fd78-4027-9dd9-e3df649c78af","resolution":{"observed_at":"2026-08-15T20:53:05.276461Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:53:05.259114Z","title":"Prompt, generate, then cache: Cascade of foundation models makes strong few-shot learners","venue":null,"work_id":"5286dd5b-72b8-486f-8353-df0e91ff291c","year":2023},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:05.008307Z"},"links":{"citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:2dfb14b705795f8e8fee32cdaa873c2bab45908c5afccd85c14a4dfa70150255","observation_id":"60838e96-e510-48fc-8d35-dd10d02bf59f","resolution":{"observed_at":"2026-08-15T20:53:05.263330Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:53:05.243670Z","title":"Toward understanding generative data augmentation.NeurIPS, 2023","venue":null,"work_id":"29f94fd2-721e-4cfa-a9d8-3470290eed29","year":2023},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:05.012137Z"},"links":{"citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:b702f44a47eed85e01b8991aa79d0948952ab8ca55180d5085a0a0db596e2f2c","observation_id":"eb3f13e5-0957-41b7-b9f3-0b9bdbd0f567","resolution":{"observed_at":"2026-08-15T20:53:05.249570Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:53:05.016175Z","title":"Learning to prompt for vision-language models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:05.016175Z"},"links":{"citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:25b45b87ae8ff8e3be85e345072b189040251be9d6f158a684c5abb4a30d874f","observation_id":"f089ea6f-bf94-41a5-bafa-93792fbc4eac","resolution":{"observed_at":"2026-08-15T20:53:05.016175Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.15316","last_updated":"2023-05-24T16:33:02Z","snapshot_observed_at":"2026-08-16T15:30:04.650501Z","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":"2026-08-15T20:53:05.020228Z","title":"Jeep Wrangler SUV 2012","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-15T20:53:05.020228Z"},"links":{"cited_paper":"/paper/2305.15316","citing_paper":"/paper/2505.11703"},"observation_digest":"sha256:ab2e8a1f2c191ae81cc340df1a09195817000474ef83fa3ed61252932753cff4","observation_id":"f060881f-da87-4c79-b29d-4d91993eb39b","resolution":{"observed_at":"2026-08-15T20:53:05.020228Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2505.11703","last_updated":"2025-05-16T21:17:55Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-17T01:14:24.183885Z","submitted_at":"2025-05-16T21:17:55Z","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance"},"reference_resolution":{"displayed":66,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":31,"verified_exact":0,"verified_fuzzy":35},"total_outbound_references":66},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 66 of 66 outbound references and 0 inbound Pith citation observations for arXiv:2505.11703."}