{"as_of":"2026-08-11T13:02:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:59565ce722d2df057236fedd161a928670d37254aaae26caee0a5646b04c2633","coverage":[{"denominator":40,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":40,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T14:21:21.112317Z","state":"measured"},{"denominator":40,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":40,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-11T06:34:44.6726+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/2501.15407/citation-record","integrity":"/paper/2501.15407/integrity","json":"/paper/2501.15407/citation-record.json","paper":"/paper/2501.15407"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2303.08774","last_updated":"2024-03-04T06:01:33Z","snapshot_observed_at":"2026-08-07T07:30:12.213965Z","submitted_at":"2023-03-15T17:15:04Z","title":"GPT-4 Technical Report","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.08774","snapshot_observed_at":"2026-08-10T14:21:20.950389Z","title":"Gpt-4 technical report","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.15407","last_updated":"2025-01-26T05:27:38Z","snapshot_observed_at":"2026-08-10T14:17:14.360728Z","submitted_at":"2025-01-26T05:27:38Z","title":"Turn That Frown Upside Down: FaceID Customization via Cross-Training Data","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-10T14:21:20.950389Z"},"links":{"cited_paper":"/paper/2303.08774","citing_paper":"/paper/2501.15407"},"observation_digest":"sha256:f7f43e7bd60bca62f10d18e60ed6862783996a108cc1a322e199189e5de4da2e","observation_id":"5679aaa9-18f9-4fd1-9b02-7e977ee237c7","resolution":{"observed_at":"2026-08-10T14:21:20.950389Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2211.01324","last_updated":"2023-03-14T00:22:14Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2022-11-02T17:43:04Z","title":"eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2211.01324","snapshot_observed_at":"2026-08-10T14:21:20.955046Z","title":"ediff-i: Text-to-image dif- fusion models with an ensemble of expert denoisers","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.15407","last_updated":"2025-01-26T05:27:38Z","snapshot_observed_at":"2026-08-10T14:17:14.360728Z","submitted_at":"2025-01-26T05:27:38Z","title":"Turn That Frown Upside Down: FaceID Customization via Cross-Training Data","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-10T14:21:20.955046Z"},"links":{"cited_paper":"/paper/2211.01324","citing_paper":"/paper/2501.15407"},"observation_digest":"sha256:b2ebcb3d430b593f7baebbbb90adad0df245c4d8af39cac020efe6b178073cde","observation_id":"bce504c2-c3a7-4f3e-812d-2a659b5e3415","resolution":{"observed_at":"2026-08-10T14:21:20.955046Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.05793","last_updated":"2023-09-11T19:59:43Z","snapshot_observed_at":"2026-08-03T16:16:19.476471Z","submitted_at":"2023-09-11T19:59:43Z","title":"PhotoVerse: Tuning-Free Image Customization with Text-to-Image Diffusion Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.05793","snapshot_observed_at":"2026-08-10T14:21:20.958934Z","title":"Photoverse: Tuning-free image customization with text-to-image diffusion models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.15407","last_updated":"2025-01-26T05:27:38Z","snapshot_observed_at":"2026-08-10T14:17:14.360728Z","submitted_at":"2025-01-26T05:27:38Z","title":"Turn That Frown Upside Down: FaceID Customization via Cross-Training Data","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-10T14:21:20.958934Z"},"links":{"cited_paper":"/paper/2309.05793","citing_paper":"/paper/2501.15407"},"observation_digest":"sha256:72fbdf7e06aa38af78ac7fb2ae2cca70035864aaddf7f7594059c79e63c4b090","observation_id":"dfde13b4-9b04-4ea3-8dfe-d7fb379d1ca5","resolution":{"observed_at":"2026-08-10T14:21:20.958934Z","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":"2026-08-10T14:21:21.606348Z","title":"Dreamidentity: Enhanced ed- itability for efficient face-identity preserved image genera- tion","venue":null,"work_id":"337b1cf7-6557-4f9e-a670-6c9353ebcb15","year":2024},"citing_paper":{"arxiv_id":"2501.15407","last_updated":"2025-01-26T05:27:38Z","snapshot_observed_at":"2026-08-10T14:17:14.360728Z","submitted_at":"2025-01-26T05:27:38Z","title":"Turn That Frown Upside Down: FaceID Customization via Cross-Training Data","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-10T14:21:20.963426Z"},"links":{"citing_paper":"/paper/2501.15407"},"observation_digest":"sha256:d5996c73e3784c5263617f36ff3f4d1cf2dd152c2ec0623a19b5e379684e8d84","observation_id":"262f2de2-76bb-4300-9a89-5fd3fb6040fd","resolution":{"observed_at":"2026-08-10T14:21:21.610812Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T14:21:21.594158Z","title":"Diffusion models beat gans on image synthesis","venue":null,"work_id":"09313f1d-6ed2-4de5-afa4-55d2ce8f75f4","year":2021},"citing_paper":{"arxiv_id":"2501.15407","last_updated":"2025-01-26T05:27:38Z","snapshot_observed_at":"2026-08-10T14:17:14.360728Z","submitted_at":"2025-01-26T05:27:38Z","title":"Turn That Frown Upside Down: FaceID Customization via Cross-Training Data","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-10T14:21:20.967645Z"},"links":{"citing_paper":"/paper/2501.15407"},"observation_digest":"sha256:96a8b41cca88bdf687faffa83264fe45cedb07c5e6755bb2b936b0fa75b06b66","observation_id":"5b852a69-1fa5-4daa-b7c5-b38c52954765","resolution":{"observed_at":"2026-08-10T14:21:21.598156Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T14:21:20.971813Z","title":"Cogview: Mastering text-to-image generation via transformers","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.15407","last_updated":"2025-01-26T05:27:38Z","snapshot_observed_at":"2026-08-10T14:17:14.360728Z","submitted_at":"2025-01-26T05:27:38Z","title":"Turn That Frown Upside Down: FaceID Customization via Cross-Training Data","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-10T14:21:20.971813Z"},"links":{"citing_paper":"/paper/2501.15407"},"observation_digest":"sha256:b6d52cc181b35af284b3492164583e50bd877d628059fce8252029a4a74a9fe7","observation_id":"9fe9d027-75a8-4abc-9275-8684ac492270","resolution":{"observed_at":"2026-08-10T14:21:20.971813Z","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":"2026-08-10T14:21:21.574077Z","title":"Cogview2: Faster and better text-to-image generation via hierarchical transformers","venue":null,"work_id":"4a216acc-f9e7-412c-aaa9-fadf33672d9d","year":2022},"citing_paper":{"arxiv_id":"2501.15407","last_updated":"2025-01-26T05:27:38Z","snapshot_observed_at":"2026-08-10T14:17:14.360728Z","submitted_at":"2025-01-26T05:27:38Z","title":"Turn That Frown Upside Down: FaceID Customization via Cross-Training Data","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-10T14:21:20.976136Z"},"links":{"citing_paper":"/paper/2501.15407"},"observation_digest":"sha256:44340645a2242f49040ca1c73cfa37ea098b03ecfecb8af79fe282bc2ff5381c","observation_id":"5cc748a8-9c69-4352-a826-dce035e22419","resolution":{"observed_at":"2026-08-10T14:21:21.578478Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"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":"2026-08-10T14:21:20.980080Z","title":"An image is worth one word: Personalizing text-to- image generation using textual inversion","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.15407","last_updated":"2025-01-26T05:27:38Z","snapshot_observed_at":"2026-08-10T14:17:14.360728Z","submitted_at":"2025-01-26T05:27:38Z","title":"Turn That Frown Upside Down: FaceID Customization via Cross-Training Data","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-10T14:21:20.980080Z"},"links":{"cited_paper":"/paper/2208.01618","citing_paper":"/paper/2501.15407"},"observation_digest":"sha256:bb088c3bdb78cb6eeb2b178d1d46eea657e545ee605655cd5c09693b2725b15d","observation_id":"6c27041e-4eeb-4559-ba62-100ddca41486","resolution":{"observed_at":"2026-08-10T14:21:20.980080Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.03620","last_updated":"2024-04-04T17:43:06Z","snapshot_observed_at":"2026-08-01T21:48:30.999365Z","submitted_at":"2024-04-04T17:43:06Z","title":"LCM-Lookahead for Encoder-based Text-to-Image Personalization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.03620","snapshot_observed_at":"2026-08-10T14:21:20.984484Z","title":"Lcm- lookahead for encoder-based text-to-image personalization","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.15407","last_updated":"2025-01-26T05:27:38Z","snapshot_observed_at":"2026-08-10T14:17:14.360728Z","submitted_at":"2025-01-26T05:27:38Z","title":"Turn That Frown Upside Down: FaceID Customization via Cross-Training Data","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-10T14:21:20.984484Z"},"links":{"cited_paper":"/paper/2404.03620","citing_paper":"/paper/2501.15407"},"observation_digest":"sha256:d9d44a443871a416355d345069b7765a9c2e32b8d7610a89c04c014c16cd40a2","observation_id":"a8016c8f-5aac-4ce0-9e1d-bdb178795419","resolution":{"observed_at":"2026-08-10T14:21:20.984484Z","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":"2026-08-10T14:21:21.561783Z","title":"Deep autoregressive networks","venue":null,"work_id":"26e546fb-2c8e-415e-939a-7ffecda4301f","year":2014},"citing_paper":{"arxiv_id":"2501.15407","last_updated":"2025-01-26T05:27:38Z","snapshot_observed_at":"2026-08-10T14:17:14.360728Z","submitted_at":"2025-01-26T05:27:38Z","title":"Turn That Frown Upside Down: FaceID Customization via Cross-Training Data","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-10T14:21:20.988606Z"},"links":{"citing_paper":"/paper/2501.15407"},"observation_digest":"sha256:c9632d295e7cd19a6c33a94c13322845e6f93426a0435df4b55e19a74ce0f4e4","observation_id":"21156779-49f5-4cf4-bc88-3d92ac57660e","resolution":{"observed_at":"2026-08-10T14:21:21.565499Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1611.05013","last_updated":"2016-11-15T20:16:27Z","snapshot_observed_at":"2026-08-06T20:43:43.665117Z","submitted_at":"2016-11-15T20:16:27Z","title":"PixelVAE: A Latent Variable Model for Natural Images","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1611.05013","snapshot_observed_at":"2026-08-10T14:21:20.992553Z","title":"Pixelvae: A latent variable model for natural im- ages","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2501.15407","last_updated":"2025-01-26T05:27:38Z","snapshot_observed_at":"2026-08-10T14:17:14.360728Z","submitted_at":"2025-01-26T05:27:38Z","title":"Turn That Frown Upside Down: FaceID Customization via Cross-Training Data","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-10T14:21:20.992553Z"},"links":{"cited_paper":"/paper/1611.05013","citing_paper":"/paper/2501.15407"},"observation_digest":"sha256:4fed7787d8fff2f33e5b1165604ee0bc70c8ff5c36353823893fd28a824da0a8","observation_id":"20a5f207-f4aa-48ee-83b4-de71c2284875","resolution":{"observed_at":"2026-08-10T14:21:20.992553Z","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":"2026-08-10T14:21:21.550404Z","title":"Denoising dif- fusion probabilistic models","venue":null,"work_id":"d8614906-cefe-4ff4-b7ba-48ce2b085158","year":2020},"citing_paper":{"arxiv_id":"2501.15407","last_updated":"2025-01-26T05:27:38Z","snapshot_observed_at":"2026-08-10T14:17:14.360728Z","submitted_at":"2025-01-26T05:27:38Z","title":"Turn That Frown Upside Down: FaceID Customization via Cross-Training Data","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-10T14:21:20.996957Z"},"links":{"citing_paper":"/paper/2501.15407"},"observation_digest":"sha256:c96ce13ae4f17381f772ff3d096741e574931b7d18a769ba3277b8789579e49b","observation_id":"3bfc60d0-0bdf-4e51-8848-497b5d31f7dd","resolution":{"observed_at":"2026-08-10T14:21:21.554492Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2302.09778","last_updated":"2023-02-22T02:14:55Z","snapshot_observed_at":"2026-08-10T14:56:32.992285Z","submitted_at":"2023-02-20T05:48:41Z","title":"Composer: Creative and Controllable Image Synthesis with Composable Conditions","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.09778","snapshot_observed_at":"2026-08-10T14:21:21.002068Z","title":"Composer: Creative and controllable im- age synthesis with composable conditions","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.15407","last_updated":"2025-01-26T05:27:38Z","snapshot_observed_at":"2026-08-10T14:17:14.360728Z","submitted_at":"2025-01-26T05:27:38Z","title":"Turn That Frown Upside Down: FaceID Customization via Cross-Training Data","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-10T14:21:21.002068Z"},"links":{"cited_paper":"/paper/2302.09778","citing_paper":"/paper/2501.15407"},"observation_digest":"sha256:51c3dff079eeddbf55ccb99824b20091a658a671b6960a24036a6ecb2f3d9879","observation_id":"b8719205-4f76-4364-ae49-73db97b3412f","resolution":{"observed_at":"2026-08-10T14:21:21.002068Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.21276","last_updated":"2024-10-25T17:43:01Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-10-25T17:43:01Z","title":"GPT-4o System Card","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.21276","snapshot_observed_at":"2026-08-10T14:21:21.007193Z","title":"Gpt-4o system card","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.15407","last_updated":"2025-01-26T05:27:38Z","snapshot_observed_at":"2026-08-10T14:17:14.360728Z","submitted_at":"2025-01-26T05:27:38Z","title":"Turn That Frown Upside Down: FaceID Customization via Cross-Training Data","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-10T14:21:21.007193Z"},"links":{"cited_paper":"/paper/2410.21276","citing_paper":"/paper/2501.15407"},"observation_digest":"sha256:4db69e7d0821b88149a3818af32233f7da23eae6341f966cfb30c210d046706a","observation_id":"e317c8cb-4925-4f03-867b-b314fb4c31a2","resolution":{"observed_at":"2026-08-10T14:21:21.007193Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2212.13344","last_updated":"2022-12-27T02:51:46Z","snapshot_observed_at":"2026-08-10T13:23:18.617286Z","submitted_at":"2022-12-27T02:51:46Z","title":"DiffFace: Diffusion-based Face Swapping with Facial Guidance","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.13344","snapshot_observed_at":"2026-08-10T14:21:21.011832Z","title":"Diffface: Diffusion-based face swapping with facial guid- ance","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.15407","last_updated":"2025-01-26T05:27:38Z","snapshot_observed_at":"2026-08-10T14:17:14.360728Z","submitted_at":"2025-01-26T05:27:38Z","title":"Turn That Frown Upside Down: FaceID Customization via Cross-Training Data","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-10T14:21:21.011832Z"},"links":{"cited_paper":"/paper/2212.13344","citing_paper":"/paper/2501.15407"},"observation_digest":"sha256:61b3523aacc6c75d5ffc2f6565a1339b860c06e73833c3dd50c274d48ce27c25","observation_id":"5f28e703-8957-440f-893b-9f2567272d11","resolution":{"observed_at":"2026-08-10T14:21:21.011832Z","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":"2026-08-10T14:21:21.537061Z","title":"Multi-concept customization of text-to-image diffusion","venue":null,"work_id":"58a8bbd0-b250-43b0-aeac-ac580dc7206a","year":1931},"citing_paper":{"arxiv_id":"2501.15407","last_updated":"2025-01-26T05:27:38Z","snapshot_observed_at":"2026-08-10T14:17:14.360728Z","submitted_at":"2025-01-26T05:27:38Z","title":"Turn That Frown Upside Down: FaceID Customization via Cross-Training Data","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-10T14:21:21.015768Z"},"links":{"citing_paper":"/paper/2501.15407"},"observation_digest":"sha256:3dca1efcd7b0879b6af00ea21b4ec800ad74bb83e4b9f20ef3cf2dfc5f1463ed","observation_id":"646d050e-727b-4da7-91e8-e799c405864e","resolution":{"observed_at":"2026-08-10T14:21:21.541457Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T14:21:21.524293Z","title":"Photomaker: Customizing re- alistic human photos via stacked id embedding","venue":null,"work_id":"819977d5-19a0-4688-ada6-83173d29e075","year":2024},"citing_paper":{"arxiv_id":"2501.15407","last_updated":"2025-01-26T05:27:38Z","snapshot_observed_at":"2026-08-10T14:17:14.360728Z","submitted_at":"2025-01-26T05:27:38Z","title":"Turn That Frown Upside Down: FaceID Customization via Cross-Training Data","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-10T14:21:21.020087Z"},"links":{"citing_paper":"/paper/2501.15407"},"observation_digest":"sha256:fe3c06a6ad9e013ca0ca4eca6ee230c83809f772caedc99e40bb1db9dbad4aec","observation_id":"ef6e322a-51a5-4061-a439-72958143b26a","resolution":{"observed_at":"2026-08-10T14:21:21.528937Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T14:21:21.023708Z","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":"2501.15407","last_updated":"2025-01-26T05:27:38Z","snapshot_observed_at":"2026-08-10T14:17:14.360728Z","submitted_at":"2025-01-26T05:27:38Z","title":"Turn That Frown Upside Down: FaceID Customization via Cross-Training Data","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-10T14:21:21.023708Z"},"links":{"cited_paper":"/paper/2112.10741","citing_paper":"/paper/2501.15407"},"observation_digest":"sha256:7d9c1143827a138f6e5d28a8f82b37a17ee01a1eeba93b766f2cf68d2e9f31a7","observation_id":"dbc647e3-a695-4903-81e1-a7af2f2289d2","resolution":{"observed_at":"2026-08-10T14:21:21.023708Z","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":"2026-08-10T14:21:21.511249Z","title":"Portraitbooth: A versatile portrait model for fast identity-preserved personalization","venue":null,"work_id":"aee90000-331e-43c1-993d-cc5f84c3de2d","year":2024},"citing_paper":{"arxiv_id":"2501.15407","last_updated":"2025-01-26T05:27:38Z","snapshot_observed_at":"2026-08-10T14:17:14.360728Z","submitted_at":"2025-01-26T05:27:38Z","title":"Turn That Frown Upside Down: FaceID Customization via Cross-Training Data","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-10T14:21:21.028782Z"},"links":{"citing_paper":"/paper/2501.15407"},"observation_digest":"sha256:9c0090e5f5843b841e0354b2f3da21cee84847175337311cdb9a92604541aebd","observation_id":"0315b9e7-cc19-4e12-8edc-a7a7bf07e70d","resolution":{"observed_at":"2026-08-10T14:21:21.515805Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.01952","last_updated":"2023-07-04T23:04:57Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-07-04T23:04:57Z","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.01952","snapshot_observed_at":"2026-08-10T14:21:21.033077Z","title":"Sdxl: Improving latent diffusion mod- els for high-resolution image synthesis","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.15407","last_updated":"2025-01-26T05:27:38Z","snapshot_observed_at":"2026-08-10T14:17:14.360728Z","submitted_at":"2025-01-26T05:27:38Z","title":"Turn That Frown Upside Down: FaceID Customization via Cross-Training Data","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-10T14:21:21.033077Z"},"links":{"cited_paper":"/paper/2307.01952","citing_paper":"/paper/2501.15407"},"observation_digest":"sha256:a4f5d175bf7e2d87f11dc4a534806d6cff8dff2cb8860fb456a96ed6a163d578","observation_id":"d701fae2-2383-40dd-a483-d0887367d460","resolution":{"observed_at":"2026-08-10T14:21:21.033077Z","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":"2026-08-10T14:21:21.037562Z","title":"Learning transferable visual models from natural language supervi- sion","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.15407","last_updated":"2025-01-26T05:27:38Z","snapshot_observed_at":"2026-08-10T14:17:14.360728Z","submitted_at":"2025-01-26T05:27:38Z","title":"Turn That Frown Upside Down: FaceID Customization via Cross-Training Data","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-10T14:21:21.037562Z"},"links":{"citing_paper":"/paper/2501.15407"},"observation_digest":"sha256:98c59c11d6e1bda34f4813caa6444ad613e1fc2615a6b99a290e25d37864aaaf","observation_id":"1354e855-349b-46dc-8ee5-2ca2296e3c92","resolution":{"observed_at":"2026-08-10T14:21:21.037562Z","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":"2026-08-10T14:21:21.041377Z","title":"Exploring the limits of transfer learning with a unified text-to-text transformer","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2501.15407","last_updated":"2025-01-26T05:27:38Z","snapshot_observed_at":"2026-08-10T14:17:14.360728Z","submitted_at":"2025-01-26T05:27:38Z","title":"Turn That Frown Upside Down: FaceID Customization via Cross-Training Data","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-10T14:21:21.041377Z"},"links":{"citing_paper":"/paper/2501.15407"},"observation_digest":"sha256:9f6a1b44de64cef6600097295ff0af51eb6c0c7c2cb3820ab49ed9a51b9426e9","observation_id":"fbae58a4-20a2-4f10-a822-cf36453fdb79","resolution":{"observed_at":"2026-08-10T14:21:21.041377Z","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":"2026-07-06T02:11:23.670680Z","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":"2026-08-10T14:21:21.045099Z","title":"Hierarchical text-conditional image gen- eration with clip latents","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.15407","last_updated":"2025-01-26T05:27:38Z","snapshot_observed_at":"2026-08-10T14:17:14.360728Z","submitted_at":"2025-01-26T05:27:38Z","title":"Turn That Frown Upside Down: FaceID Customization via Cross-Training Data","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-10T14:21:21.045099Z"},"links":{"cited_paper":"/paper/2204.06125","citing_paper":"/paper/2501.15407"},"observation_digest":"sha256:95502dd76d5ea1ed1c573b77f818d485fb33be9788d55a5d6f4b24e985073e4f","observation_id":"37c909d3-52ff-470b-8d72-36dd99d7cca6","resolution":{"observed_at":"2026-08-10T14:21:21.045099Z","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":"2026-08-10T14:21:21.477960Z","title":"Zero-shot text-to-image generation","venue":null,"work_id":"c37573ab-92e3-4c68-a46a-d3eb600375dd","year":2021},"citing_paper":{"arxiv_id":"2501.15407","last_updated":"2025-01-26T05:27:38Z","snapshot_observed_at":"2026-08-10T14:17:14.360728Z","submitted_at":"2025-01-26T05:27:38Z","title":"Turn That Frown Upside Down: FaceID Customization via Cross-Training Data","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-10T14:21:21.048828Z"},"links":{"citing_paper":"/paper/2501.15407"},"observation_digest":"sha256:3a4198386f38293a907b063857fcba9c99d5025db9ba1751fc412696a5b0a593","observation_id":"7b6f2ec0-4e6f-4bb7-8a20-e9a2dfbc8910","resolution":{"observed_at":"2026-08-10T14:21:21.482858Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T14:21:21.052801Z","title":"High-resolution image synthesis with latent diffusion models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.15407","last_updated":"2025-01-26T05:27:38Z","snapshot_observed_at":"2026-08-10T14:17:14.360728Z","submitted_at":"2025-01-26T05:27:38Z","title":"Turn That Frown Upside Down: FaceID Customization via Cross-Training Data","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-10T14:21:21.052801Z"},"links":{"citing_paper":"/paper/2501.15407"},"observation_digest":"sha256:b5ca35e255a90048200febc6adbe50afcfaafcce9194a3ef898151245855becf","observation_id":"a93e6822-9ada-4fac-ad4a-0bb8f2dab944","resolution":{"observed_at":"2026-08-10T14:21:21.052801Z","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":"2026-08-10T14:21:21.457362Z","title":"Dreambooth: Fine tuning text-to-image diffusion models for subject-driven generation","venue":null,"work_id":"e8831f8f-78a6-4db4-949e-5fb2c231cf1e","year":2023},"citing_paper":{"arxiv_id":"2501.15407","last_updated":"2025-01-26T05:27:38Z","snapshot_observed_at":"2026-08-10T14:17:14.360728Z","submitted_at":"2025-01-26T05:27:38Z","title":"Turn That Frown Upside Down: FaceID Customization via Cross-Training Data","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-10T14:21:21.056645Z"},"links":{"citing_paper":"/paper/2501.15407"},"observation_digest":"sha256:ebdf1fb87851076d504af947fc9a573846842229b5d509baa45f8d8bae7350d3","observation_id":"7f335a4f-b615-4259-a389-5c37b22dd56a","resolution":{"observed_at":"2026-08-10T14:21:21.461471Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T14:21:21.060629Z","title":"Photorealistic text-to-image diffusion models with deep language understanding","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.15407","last_updated":"2025-01-26T05:27:38Z","snapshot_observed_at":"2026-08-10T14:17:14.360728Z","submitted_at":"2025-01-26T05:27:38Z","title":"Turn That Frown Upside Down: FaceID Customization via Cross-Training Data","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-10T14:21:21.060629Z"},"links":{"citing_paper":"/paper/2501.15407"},"observation_digest":"sha256:c137b9dca7df0446e7561f8663fe45dbd2b566b0c4d516f86cb059466fc6b18b","observation_id":"28d511e6-1376-45f2-9e58-4b46d3df8fd1","resolution":{"observed_at":"2026-08-10T14:21:21.060629Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.02502","last_updated":"2022-10-05T20:19:21Z","snapshot_observed_at":"2026-07-06T10:01:50.133383Z","submitted_at":"2020-10-06T06:15:51Z","title":"Denoising Diffusion Implicit Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.02502","snapshot_observed_at":"2026-08-10T14:21:21.064229Z","title":"Denoising diffusion implicit models","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2501.15407","last_updated":"2025-01-26T05:27:38Z","snapshot_observed_at":"2026-08-10T14:17:14.360728Z","submitted_at":"2025-01-26T05:27:38Z","title":"Turn That Frown Upside Down: FaceID Customization via Cross-Training Data","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-10T14:21:21.064229Z"},"links":{"cited_paper":"/paper/2010.02502","citing_paper":"/paper/2501.15407"},"observation_digest":"sha256:01418126c379bda402f96a0d16b0da02c54dcbc3e9e914fcc685a801ad637ccb","observation_id":"dff8bc9b-4a26-485a-971e-cc560eed6702","resolution":{"observed_at":"2026-08-10T14:21:21.064229Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2011.13456","last_updated":"2021-02-10T18:17:04Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2020-11-26T19:39:10Z","title":"Score-Based Generative Modeling through Stochastic Differential Equations","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2011.13456","snapshot_observed_at":"2026-08-10T14:21:21.068564Z","title":"Score-based generative modeling through stochastic differential equa- tions","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2501.15407","last_updated":"2025-01-26T05:27:38Z","snapshot_observed_at":"2026-08-10T14:17:14.360728Z","submitted_at":"2025-01-26T05:27:38Z","title":"Turn That Frown Upside Down: FaceID Customization via Cross-Training Data","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-10T14:21:21.068564Z"},"links":{"cited_paper":"/paper/2011.13456","citing_paper":"/paper/2501.15407"},"observation_digest":"sha256:6b30fc8574aa4b41abb6d54b5bf4de7694f4ea372b7423ff8284e35414be6d50","observation_id":"d21667f6-69ba-4db0-af2e-26d4e789a5d7","resolution":{"observed_at":"2026-08-10T14:21:21.068564Z","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":"2026-08-10T14:21:21.438886Z","title":"Face0: Instantaneously conditioning a text-to- image model on a face","venue":null,"work_id":"1b738e92-f422-437f-a6e6-b24b0fd7ef10","year":2023},"citing_paper":{"arxiv_id":"2501.15407","last_updated":"2025-01-26T05:27:38Z","snapshot_observed_at":"2026-08-10T14:17:14.360728Z","submitted_at":"2025-01-26T05:27:38Z","title":"Turn That Frown Upside Down: FaceID Customization via Cross-Training Data","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-10T14:21:21.072275Z"},"links":{"citing_paper":"/paper/2501.15407"},"observation_digest":"sha256:ba8b48684cac184ab0b922862d943f1e766869d58e2fe1a5eb96230305e4e957","observation_id":"a5879b9d-6010-4345-9e30-463fcd2e4593","resolution":{"observed_at":"2026-08-10T14:21:21.442708Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T14:21:21.427612Z","title":"Conditional image genera- tion with pixelcnn decoders","venue":null,"work_id":"cab737b9-166d-41ff-a03f-cae9d311eee8","year":2016},"citing_paper":{"arxiv_id":"2501.15407","last_updated":"2025-01-26T05:27:38Z","snapshot_observed_at":"2026-08-10T14:17:14.360728Z","submitted_at":"2025-01-26T05:27:38Z","title":"Turn That Frown Upside Down: FaceID Customization via Cross-Training Data","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-10T14:21:21.076000Z"},"links":{"citing_paper":"/paper/2501.15407"},"observation_digest":"sha256:2e84254f27aecc25ab1743960e75f6fc54aa1f11d05a4271a35dcbbe81ab930e","observation_id":"c95d3b76-47cd-42f0-b29d-009b6bdb2bf3","resolution":{"observed_at":"2026-08-10T14:21:21.431493Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T14:21:21.415015Z","title":"Neural discrete representation learning","venue":null,"work_id":"aa4d2fed-d436-49b3-955b-6c720d51fdb9","year":2017},"citing_paper":{"arxiv_id":"2501.15407","last_updated":"2025-01-26T05:27:38Z","snapshot_observed_at":"2026-08-10T14:17:14.360728Z","submitted_at":"2025-01-26T05:27:38Z","title":"Turn That Frown Upside Down: FaceID Customization via Cross-Training Data","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-10T14:21:21.079811Z"},"links":{"citing_paper":"/paper/2501.15407"},"observation_digest":"sha256:acd81cc35b570d852f5645870beb8b829353b3ec94d0758459d62e10a229bf38","observation_id":"cfe7d41a-fd7e-4832-b5f0-03dc34a45eed","resolution":{"observed_at":"2026-08-10T14:21:21.419244Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T14:21:21.083559Z","title":"Attention is all you need","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2501.15407","last_updated":"2025-01-26T05:27:38Z","snapshot_observed_at":"2026-08-10T14:17:14.360728Z","submitted_at":"2025-01-26T05:27:38Z","title":"Turn That Frown Upside Down: FaceID Customization via Cross-Training Data","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-10T14:21:21.083559Z"},"links":{"citing_paper":"/paper/2501.15407"},"observation_digest":"sha256:f0f076650fbe0f1f00ea69dddd68b8cd19b8ad38e2864241c910a1a5d3e017cb","observation_id":"a1f4a7cd-4e3d-44b7-baec-ca5937d1a716","resolution":{"observed_at":"2026-08-10T14:21:21.083559Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.07519","last_updated":"2024-02-02T16:15:22Z","snapshot_observed_at":"2026-08-06T23:08:20.817133Z","submitted_at":"2024-01-15T07:50:18Z","title":"InstantID: Zero-shot Identity-Preserving Generation in Seconds","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.07519","snapshot_observed_at":"2026-08-10T14:21:21.087965Z","title":"Instantid: Zero-shot identity-preserving generation in seconds","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.15407","last_updated":"2025-01-26T05:27:38Z","snapshot_observed_at":"2026-08-10T14:17:14.360728Z","submitted_at":"2025-01-26T05:27:38Z","title":"Turn That Frown Upside Down: FaceID Customization via Cross-Training Data","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-10T14:21:21.087965Z"},"links":{"cited_paper":"/paper/2401.07519","citing_paper":"/paper/2501.15407"},"observation_digest":"sha256:fe43b3e3ee9ccd79e7a94b7912dfea7f1df202d8e0ac88040946ffd560e2602c","observation_id":"bfa3a024-cd3e-4f7b-a2ff-58c348b1b27a","resolution":{"observed_at":"2026-08-10T14:21:21.087965Z","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":"2026-08-10T14:21:21.394287Z","title":"Fastcomposer: Tuning-free multi- subject image generation with localized attention","venue":null,"work_id":"0142716d-0857-402d-b7c8-1f99bd9a8528","year":2024},"citing_paper":{"arxiv_id":"2501.15407","last_updated":"2025-01-26T05:27:38Z","snapshot_observed_at":"2026-08-10T14:17:14.360728Z","submitted_at":"2025-01-26T05:27:38Z","title":"Turn That Frown Upside Down: FaceID Customization via Cross-Training Data","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-10T14:21:21.091806Z"},"links":{"citing_paper":"/paper/2501.15407"},"observation_digest":"sha256:2139da9b2862567c92febc817e98ae71eb038e804a20c0d0e68f18d9951afc52","observation_id":"97fbd63a-2196-4b29-b1f5-96686b6530bc","resolution":{"observed_at":"2026-08-10T14:21:21.398763Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T14:21:21.381079Z","title":"Imagere- ward: Learning and evaluating human preferences for text- to-image generation","venue":null,"work_id":"05902c27-b58b-4835-a94d-0c586a700a48","year":2024},"citing_paper":{"arxiv_id":"2501.15407","last_updated":"2025-01-26T05:27:38Z","snapshot_observed_at":"2026-08-10T14:17:14.360728Z","submitted_at":"2025-01-26T05:27:38Z","title":"Turn That Frown Upside Down: FaceID Customization via Cross-Training Data","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-10T14:21:21.095685Z"},"links":{"citing_paper":"/paper/2501.15407"},"observation_digest":"sha256:94260dbdd6205bdca3c6c3b6502500f456866176104d462ae679774f6f962827","observation_id":"4df77c1a-778c-4169-b499-c1cc83279670","resolution":{"observed_at":"2026-08-10T14:21:21.385349Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.06721","last_updated":"2023-08-13T08:34:51Z","snapshot_observed_at":"2026-07-06T16:05:39.158819Z","submitted_at":"2023-08-13T08:34:51Z","title":"IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.06721","snapshot_observed_at":"2026-08-10T14:21:21.100068Z","title":"Ip- adapter: Text compatible image prompt adapter for text-to- image diffusion models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.15407","last_updated":"2025-01-26T05:27:38Z","snapshot_observed_at":"2026-08-10T14:17:14.360728Z","submitted_at":"2025-01-26T05:27:38Z","title":"Turn That Frown Upside Down: FaceID Customization via Cross-Training Data","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-10T14:21:21.100068Z"},"links":{"cited_paper":"/paper/2308.06721","citing_paper":"/paper/2501.15407"},"observation_digest":"sha256:469002e024153ff217e7ab006863d7ff0cc09b05fa585d603a751a2c2210522a","observation_id":"7d17c42c-8d77-4042-9dd7-9e255225e99b","resolution":{"observed_at":"2026-08-10T14:21:21.100068Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.00926","last_updated":"2023-06-01T17:30:24Z","snapshot_observed_at":"2026-07-06T15:36:45.014921Z","submitted_at":"2023-06-01T17:30:24Z","title":"Inserting Anybody in Diffusion Models via Celeb Basis","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.00926","snapshot_observed_at":"2026-08-10T14:21:21.104281Z","title":"Inserting anybody in diffusion models via celeb ba- sis","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.15407","last_updated":"2025-01-26T05:27:38Z","snapshot_observed_at":"2026-08-10T14:17:14.360728Z","submitted_at":"2025-01-26T05:27:38Z","title":"Turn That Frown Upside Down: FaceID Customization via Cross-Training Data","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-10T14:21:21.104281Z"},"links":{"cited_paper":"/paper/2306.00926","citing_paper":"/paper/2501.15407"},"observation_digest":"sha256:25f1e90215045e466f696764a9823defdb510b775ee92cde7d268c88243ab5f7","observation_id":"86c4e8ed-c56e-4ac8-a42e-db8a666000a6","resolution":{"observed_at":"2026-08-10T14:21:21.104281Z","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":"2026-08-10T14:21:21.108609Z","title":"Adding conditional control to text-to-image diffusion models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.15407","last_updated":"2025-01-26T05:27:38Z","snapshot_observed_at":"2026-08-10T14:17:14.360728Z","submitted_at":"2025-01-26T05:27:38Z","title":"Turn That Frown Upside Down: FaceID Customization via Cross-Training Data","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-10T14:21:21.108609Z"},"links":{"citing_paper":"/paper/2501.15407"},"observation_digest":"sha256:8114208f32506a93ad633cb88b49d0fa7efeb9f2f83cd36c403a7c650223faa0","observation_id":"8140e776-0dd1-4857-9638-3c087475a896","resolution":{"observed_at":"2026-08-10T14:21:21.108609Z","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":"2026-08-10T14:21:21.357008Z","title":"Diffswap: High-fidelity and con- trollable face swapping via 3d-aware masked diffusion","venue":null,"work_id":"41382174-68ff-437c-b76c-18683e7f7592","year":2023},"citing_paper":{"arxiv_id":"2501.15407","last_updated":"2025-01-26T05:27:38Z","snapshot_observed_at":"2026-08-10T14:17:14.360728Z","submitted_at":"2025-01-26T05:27:38Z","title":"Turn That Frown Upside Down: FaceID Customization via Cross-Training Data","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-10T14:21:21.112317Z"},"links":{"citing_paper":"/paper/2501.15407"},"observation_digest":"sha256:f9829dc0a53018bdc85545a8125eb20d2bd9bd797d729ebe690f0a6a4dbcf323","observation_id":"b039f63b-1d08-48ac-b57e-aa10a9e30908","resolution":{"observed_at":"2026-08-10T14:21:21.363697Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2501.15407","last_updated":"2025-01-26T05:27:38Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-10T14:17:14.360728Z","submitted_at":"2025-01-26T05:27:38Z","title":"Turn That Frown Upside Down: FaceID Customization via Cross-Training Data"},"reference_resolution":{"displayed":40,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":24,"verified_exact":0,"verified_fuzzy":16},"total_outbound_references":40},"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":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"thesis":"As of 11 August 2026, this Paper Citation Record lists 40 of 40 outbound references and 0 inbound Pith citation observations for arXiv:2501.15407."}