{"as_of":"2026-08-22T05:09:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:7f1d62832d9c7980e34f4c9daa8b31d8181115bdd9aa28886a007b6bc45d20d2","coverage":[{"denominator":41,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":41,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T00:13:43.688688Z","state":"measured"},{"denominator":42,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":42,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-21T06:32:19.484+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T14:52:16.704032Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-07T14:52:18.299204Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2412.19637","last_updated":"2025-06-21T13:41:27Z","snapshot_observed_at":"2026-08-19T01:32:48.784739Z","submitted_at":"2024-12-27T13:31:55Z","title":"ReNeg: Learning Negative Embedding with Reward Guidance","version":3},"cited_work":{"arxiv_id":"2412.19637","doi":null,"metadata_source":"pith","pith_arxiv_id":"2412.19637","snapshot_observed_at":"2026-08-07T14:52:18.299204Z","title":"ReNeg: Learning Negative Embedding with Reward Guidance","venue":"cs.CV","work_id":"484f3bde-df5a-4cd4-9bfb-dc4b36e790c1","year":2024},"citing_paper":{"arxiv_id":"2506.12036","last_updated":"2025-07-01T05:46:31Z","snapshot_observed_at":"2026-08-17T13:43:09.193964Z","submitted_at":"2025-05-23T00:01:52Z","title":"A Minimalist Method for Fine-tuning Text-to-Image Diffusion Models","version":3},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-07T14:52:16.704032Z"},"links":{"cited_paper":"/paper/2412.19637","citing_paper":"/paper/2506.12036"},"observation_digest":"sha256:d553a462242a0365faa4e307b5e2a3d20640dafcb370790b9248d5c0e28f44c9","observation_id":"01dcb167-e932-45cc-9985-c688cc3748a5","resolution":{"observed_at":"2026-08-07T14:52:18.369441Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2412.19637/citation-record","integrity":"/paper/2412.19637/integrity","json":"/paper/2412.19637/citation-record.json","paper":"/paper/2412.19637"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2406.02965","last_updated":"2024-06-05T05:42:46Z","snapshot_observed_at":"2026-08-22T04:06:31.220065Z","submitted_at":"2024-06-05T05:42:46Z","title":"Understanding the Impact of Negative Prompts: When and How Do They Take Effect?","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.02965","snapshot_observed_at":"2026-08-11T00:13:43.477075Z","title":"Understanding the im- pact of negative prompts: When and how do they take effect? arXiv preprint arXiv:2406.02965, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.19637","last_updated":"2025-06-21T13:41:27Z","snapshot_observed_at":"2026-08-19T01:32:48.784739Z","submitted_at":"2024-12-27T13:31:55Z","title":"ReNeg: Learning Negative Embedding with Reward Guidance","version":3},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-11T00:13:43.477075Z"},"links":{"cited_paper":"/paper/2406.02965","citing_paper":"/paper/2412.19637"},"observation_digest":"sha256:072820e298e2c4c238f6c341ed9791894d0eec0445d67286b46b57c21ed9a374","observation_id":"a8b80448-5a72-4c8d-9d66-452cc3f2f1a3","resolution":{"observed_at":"2026-08-11T00:13:43.477075Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.13301","last_updated":"2024-01-04T19:11:25Z","snapshot_observed_at":"2026-08-09T16:20:23.732146Z","submitted_at":"2023-05-22T17:57:41Z","title":"Training Diffusion Models with Reinforcement Learning","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.13301","snapshot_observed_at":"2026-08-11T00:13:43.483205Z","title":"Training diffusion models with reinforce- ment learning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.19637","last_updated":"2025-06-21T13:41:27Z","snapshot_observed_at":"2026-08-19T01:32:48.784739Z","submitted_at":"2024-12-27T13:31:55Z","title":"ReNeg: Learning Negative Embedding with Reward Guidance","version":3},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-11T00:13:43.483205Z"},"links":{"cited_paper":"/paper/2305.13301","citing_paper":"/paper/2412.19637"},"observation_digest":"sha256:9fbd963a1cb78922c2a7f0b63c5bee87d2ad9819a0723f1fc13b755352fdce7c","observation_id":"aa69a118-dc78-41aa-8fa2-38f1159269a7","resolution":{"observed_at":"2026-08-11T00:13:43.483205Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.15127","last_updated":"2023-11-25T22:28:38Z","snapshot_observed_at":"2026-08-20T09:39:07.545813Z","submitted_at":"2023-11-25T22:28:38Z","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.15127","snapshot_observed_at":"2026-08-11T00:13:43.488877Z","title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.19637","last_updated":"2025-06-21T13:41:27Z","snapshot_observed_at":"2026-08-19T01:32:48.784739Z","submitted_at":"2024-12-27T13:31:55Z","title":"ReNeg: Learning Negative Embedding with Reward Guidance","version":3},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-11T00:13:43.488877Z"},"links":{"cited_paper":"/paper/2311.15127","citing_paper":"/paper/2412.19637"},"observation_digest":"sha256:06deebaee0d74ce1af3cee1ef53d69bccb4fa431664bba9f6617d1036afc5afd","observation_id":"dda78e18-6acd-48d8-abe7-9fbb1789b6b6","resolution":{"observed_at":"2026-08-11T00:13:43.488877Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.06752","last_updated":"2023-11-12T06:39:00Z","snapshot_observed_at":"2026-08-18T12:02:15.935371Z","submitted_at":"2023-11-12T06:39:00Z","title":"BeautifulPrompt: Towards Automatic Prompt Engineering for Text-to-Image Synthesis","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.06752","snapshot_observed_at":"2026-08-11T00:13:43.494199Z","title":"Beautifulprompt: Towards auto- matic prompt engineering for text-to-image synthesis","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.19637","last_updated":"2025-06-21T13:41:27Z","snapshot_observed_at":"2026-08-19T01:32:48.784739Z","submitted_at":"2024-12-27T13:31:55Z","title":"ReNeg: Learning Negative Embedding with Reward Guidance","version":3},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-11T00:13:43.494199Z"},"links":{"cited_paper":"/paper/2311.06752","citing_paper":"/paper/2412.19637"},"observation_digest":"sha256:86a298b71e9dca2dc814a0f979cc9c969fe51e136aeb6077452abc05fb9d9904","observation_id":"3c08e72a-2de6-47b5-b9da-309af256d076","resolution":{"observed_at":"2026-08-11T00:13:43.494199Z","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":"2026-08-11T00:13:44.382703Z","title":"https : / / huggingface","venue":null,"work_id":"12b3aeee-740f-411e-b910-e8dc208bd4a4","year":2023},"citing_paper":{"arxiv_id":"2412.19637","last_updated":"2025-06-21T13:41:27Z","snapshot_observed_at":"2026-08-19T01:32:48.784739Z","submitted_at":"2024-12-27T13:31:55Z","title":"ReNeg: Learning Negative Embedding with Reward Guidance","version":3},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-11T00:13:43.501751Z"},"links":{"citing_paper":"/paper/2412.19637"},"observation_digest":"sha256:e864f022a484f9c5e0f196024d4a73ce688272faafd0c1d2948e7ba76eec4ca8","observation_id":"352762e3-1079-49ad-a0b4-dd5465eb611f","resolution":{"observed_at":"2026-08-11T00:13:44.387756Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T00:13:43.508418Z","title":"Videocrafter2: Overcoming data limitations for high-quality video diffusion models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.19637","last_updated":"2025-06-21T13:41:27Z","snapshot_observed_at":"2026-08-19T01:32:48.784739Z","submitted_at":"2024-12-27T13:31:55Z","title":"ReNeg: Learning Negative Embedding with Reward Guidance","version":3},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-11T00:13:43.508418Z"},"links":{"citing_paper":"/paper/2412.19637"},"observation_digest":"sha256:af5ec2cd5160851aef0399f74d4ec15ab213c5f8a46c88a5f2408deba048680b","observation_id":"51218b77-8317-47aa-8d60-053d6883cb76","resolution":{"observed_at":"2026-08-11T00:13:43.508418Z","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":"2026-08-11T00:13:44.355591Z","title":"Deep reinforcement learn- ing from human preferences","venue":null,"work_id":"53018658-4f27-451f-85ec-c8f0ff218017","year":2017},"citing_paper":{"arxiv_id":"2412.19637","last_updated":"2025-06-21T13:41:27Z","snapshot_observed_at":"2026-08-19T01:32:48.784739Z","submitted_at":"2024-12-27T13:31:55Z","title":"ReNeg: Learning Negative Embedding with Reward Guidance","version":3},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-11T00:13:43.514096Z"},"links":{"citing_paper":"/paper/2412.19637"},"observation_digest":"sha256:7ed553d12668318414382a870acc40b8f8232b5813a36d358f8da61f0521e665","observation_id":"21c6cac4-e751-4428-ba36-aba1df85a2a0","resolution":{"observed_at":"2026-08-11T00:13:44.360864Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.17400","last_updated":"2024-06-21T16:45:11Z","snapshot_observed_at":"2026-08-06T10:08:54.816113Z","submitted_at":"2023-09-29T17:01:02Z","title":"Directly Fine-Tuning Diffusion Models on Differentiable Rewards","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.17400","snapshot_observed_at":"2026-08-11T00:13:43.519190Z","title":"Directly fine-tuning diffusion models on differentiable re- wards","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.19637","last_updated":"2025-06-21T13:41:27Z","snapshot_observed_at":"2026-08-19T01:32:48.784739Z","submitted_at":"2024-12-27T13:31:55Z","title":"ReNeg: Learning Negative Embedding with Reward Guidance","version":3},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-11T00:13:43.519190Z"},"links":{"cited_paper":"/paper/2309.17400","citing_paper":"/paper/2412.19637"},"observation_digest":"sha256:e89ea400123b586fa029932322de8e0962822c2b00502731d35459e408c25c6f","observation_id":"ccdaeeb7-1ff7-46b1-a5d7-1af66651a600","resolution":{"observed_at":"2026-08-11T00:13:43.519190Z","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":"2026-08-11T00:13:44.340036Z","title":"Improving image syn- thesis with diffusion-negative sampling","venue":null,"work_id":"e80257c4-e9be-40f7-945a-ef182aec4249","year":2025},"citing_paper":{"arxiv_id":"2412.19637","last_updated":"2025-06-21T13:41:27Z","snapshot_observed_at":"2026-08-19T01:32:48.784739Z","submitted_at":"2024-12-27T13:31:55Z","title":"ReNeg: Learning Negative Embedding with Reward Guidance","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-11T00:13:43.524679Z"},"links":{"citing_paper":"/paper/2412.19637"},"observation_digest":"sha256:9224115a626e3b500a0797b349741aec91032c8922fdca514ba70d977e383fb5","observation_id":"a0dd1889-7155-4519-ae9b-d62224b82c3c","resolution":{"observed_at":"2026-08-11T00:13:44.345220Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T00:13:44.324919Z","title":"Diffusion models beat gans on image synthesis","venue":null,"work_id":"49814a0d-71c6-4ddf-9845-5c162de694d6","year":2021},"citing_paper":{"arxiv_id":"2412.19637","last_updated":"2025-06-21T13:41:27Z","snapshot_observed_at":"2026-08-19T01:32:48.784739Z","submitted_at":"2024-12-27T13:31:55Z","title":"ReNeg: Learning Negative Embedding with Reward Guidance","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-11T00:13:43.529555Z"},"links":{"citing_paper":"/paper/2412.19637"},"observation_digest":"sha256:c87addc3813b2aeccf57e79bbf7f5087108a1ab6d92c7c33ce861472c038a1cf","observation_id":"af2c6f64-4bbd-4057-89de-5fd6eb80e824","resolution":{"observed_at":"2026-08-11T00:13:44.329743Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.12980","last_updated":"2023-07-24T17:58:06Z","snapshot_observed_at":"2026-08-20T01:12:48.922315Z","submitted_at":"2023-07-24T17:58:06Z","title":"A Systematic Survey of Prompt Engineering on Vision-Language Foundation Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.12980","snapshot_observed_at":"2026-08-11T00:13:43.534804Z","title":"A systematic survey of prompt engineer- ing on vision-language foundation models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.19637","last_updated":"2025-06-21T13:41:27Z","snapshot_observed_at":"2026-08-19T01:32:48.784739Z","submitted_at":"2024-12-27T13:31:55Z","title":"ReNeg: Learning Negative Embedding with Reward Guidance","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-11T00:13:43.534804Z"},"links":{"cited_paper":"/paper/2307.12980","citing_paper":"/paper/2412.19637"},"observation_digest":"sha256:56da0ed3b7726f239e30ede25f67fc4ea6a57a92096e3786abf51583b9c11e5a","observation_id":"556452ff-d018-4e74-8828-a394b84a5658","resolution":{"observed_at":"2026-08-11T00:13:43.534804Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.04725","last_updated":"2024-02-08T18:08:57Z","snapshot_observed_at":"2026-08-17T14:04:31.230742Z","submitted_at":"2023-07-10T17:34:16Z","title":"AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.04725","snapshot_observed_at":"2026-08-11T00:13:43.540408Z","title":"Animatediff: Animate your personalized text- to-image diffusion models without specific tuning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.19637","last_updated":"2025-06-21T13:41:27Z","snapshot_observed_at":"2026-08-19T01:32:48.784739Z","submitted_at":"2024-12-27T13:31:55Z","title":"ReNeg: Learning Negative Embedding with Reward Guidance","version":3},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-11T00:13:43.540408Z"},"links":{"cited_paper":"/paper/2307.04725","citing_paper":"/paper/2412.19637"},"observation_digest":"sha256:e1a609d2f7bf26c90199fad181b3ed4fa2d0e6a16ec703718ce31170232f8e95","observation_id":"590c8878-1224-4813-82af-ac4ecb460ebd","resolution":{"observed_at":"2026-08-11T00:13:43.540408Z","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":"2026-08-11T00:13:44.309257Z","title":"Optimizing prompts for text-to-image generation","venue":null,"work_id":"8acd6774-b364-4b21-a31f-a7b7380e9b4d","year":2024},"citing_paper":{"arxiv_id":"2412.19637","last_updated":"2025-06-21T13:41:27Z","snapshot_observed_at":"2026-08-19T01:32:48.784739Z","submitted_at":"2024-12-27T13:31:55Z","title":"ReNeg: Learning Negative Embedding with Reward Guidance","version":3},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-11T00:13:43.546339Z"},"links":{"citing_paper":"/paper/2412.19637"},"observation_digest":"sha256:0b37efc5d532031115bd2f1a07f66d5e988a01b914de359b82c094880f70e827","observation_id":"ceaabb5b-5aee-46b5-881f-1a7f4f630ecf","resolution":{"observed_at":"2026-08-11T00:13:44.314435Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2207.12598","last_updated":"2022-07-26T01:42:07Z","snapshot_observed_at":"2026-08-14T06:37:15.299690Z","submitted_at":"2022-07-26T01:42:07Z","title":"Classifier-Free Diffusion Guidance","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2207.12598","snapshot_observed_at":"2026-08-11T00:13:43.551337Z","title":"Classifier-free diffusion guidance","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.19637","last_updated":"2025-06-21T13:41:27Z","snapshot_observed_at":"2026-08-19T01:32:48.784739Z","submitted_at":"2024-12-27T13:31:55Z","title":"ReNeg: Learning Negative Embedding with Reward Guidance","version":3},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-11T00:13:43.551337Z"},"links":{"cited_paper":"/paper/2207.12598","citing_paper":"/paper/2412.19637"},"observation_digest":"sha256:c50ae800e0e312fc269d48361902096ca42b81731d4609732926bc6dde40f980","observation_id":"2522048b-114b-4ada-8b58-2db6e4cd04a6","resolution":{"observed_at":"2026-08-11T00:13:43.551337Z","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":"2026-08-11T00:13:44.293507Z","title":"Denoising diffu- sion probabilistic models","venue":null,"work_id":"67e00f48-7aff-4c02-9bb5-639a47adacfe","year":2020},"citing_paper":{"arxiv_id":"2412.19637","last_updated":"2025-06-21T13:41:27Z","snapshot_observed_at":"2026-08-19T01:32:48.784739Z","submitted_at":"2024-12-27T13:31:55Z","title":"ReNeg: Learning Negative Embedding with Reward Guidance","version":3},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-11T00:13:43.556603Z"},"links":{"citing_paper":"/paper/2412.19637"},"observation_digest":"sha256:0e97edc5f46a9dc0f7d5aa72eb6a58bf5c62e0bc84696b54a2e9089974370dcf","observation_id":"49272171-4e64-4a46-9078-7ef8073276b5","resolution":{"observed_at":"2026-08-11T00:13:44.298523Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2106.09685","last_updated":"2021-10-16T18:40:34Z","snapshot_observed_at":"2026-08-20T11:47:17.477107Z","submitted_at":"2021-06-17T17:37:18Z","title":"LoRA: Low-Rank Adaptation of Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.09685","snapshot_observed_at":"2026-08-11T00:13:43.561260Z","title":"Lora: Low-rank adaptation of large language models","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.19637","last_updated":"2025-06-21T13:41:27Z","snapshot_observed_at":"2026-08-19T01:32:48.784739Z","submitted_at":"2024-12-27T13:31:55Z","title":"ReNeg: Learning Negative Embedding with Reward Guidance","version":3},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-11T00:13:43.561260Z"},"links":{"cited_paper":"/paper/2106.09685","citing_paper":"/paper/2412.19637"},"observation_digest":"sha256:a28d9c0d571c2994fc623b8921f99dad446815fbdb59172af4db3676642b61c0","observation_id":"d7275f3d-bffd-419c-a403-8320b38c0059","resolution":{"observed_at":"2026-08-11T00:13:43.561260Z","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":"2026-08-11T00:13:44.277227Z","title":"VBench: Com- prehensive benchmark suite for video generative models","venue":null,"work_id":"307d1944-7e9c-4467-8348-0025133bad41","year":2024},"citing_paper":{"arxiv_id":"2412.19637","last_updated":"2025-06-21T13:41:27Z","snapshot_observed_at":"2026-08-19T01:32:48.784739Z","submitted_at":"2024-12-27T13:31:55Z","title":"ReNeg: Learning Negative Embedding with Reward Guidance","version":3},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-11T00:13:43.566328Z"},"links":{"citing_paper":"/paper/2412.19637"},"observation_digest":"sha256:2867b035d9c0b22668859c5ab255fab7c1d34876d078fdaf1bb6342f78ac08b4","observation_id":"d955b3d7-efba-4562-9c36-d11c5f76a073","resolution":{"observed_at":"2026-08-11T00:13:44.282368Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T00:13:44.260799Z","title":"Pick-a-pic: An open dataset of user preferences for text-to-image generation","venue":null,"work_id":"1d371bc8-e35b-49a1-9aa6-68177358c507","year":2023},"citing_paper":{"arxiv_id":"2412.19637","last_updated":"2025-06-21T13:41:27Z","snapshot_observed_at":"2026-08-19T01:32:48.784739Z","submitted_at":"2024-12-27T13:31:55Z","title":"ReNeg: Learning Negative Embedding with Reward Guidance","version":3},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-11T00:13:43.571254Z"},"links":{"citing_paper":"/paper/2412.19637"},"observation_digest":"sha256:782d756ebbaf871b668a3e0721890037de82962ec63a3041dca72d3c1381b3c6","observation_id":"507a7a8c-e543-4879-b716-e75d1da8c6b2","resolution":{"observed_at":"2026-08-11T00:13:44.266291Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T00:13:44.243530Z","title":"Bloom: A 176b-parameter open-access multilingual language model","venue":null,"work_id":"001fcb7e-5620-4ac1-b904-24c0fde9baca","year":2023},"citing_paper":{"arxiv_id":"2412.19637","last_updated":"2025-06-21T13:41:27Z","snapshot_observed_at":"2026-08-19T01:32:48.784739Z","submitted_at":"2024-12-27T13:31:55Z","title":"ReNeg: Learning Negative Embedding with Reward Guidance","version":3},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-11T00:13:43.575973Z"},"links":{"citing_paper":"/paper/2412.19637"},"observation_digest":"sha256:6059494646dfaeace7ba82ba6e212472956aa68bddce27e78cd5c4fadf8dfc29","observation_id":"bbce65a5-cef8-4bbd-b143-0f3cc1dfb1ae","resolution":{"observed_at":"2026-08-11T00:13:44.248866Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T00:13:44.226675Z","title":"Motrans: Customized motion transfer with text-driven video diffusion models","venue":null,"work_id":"05e3b552-d1d9-49f1-bf83-4cbe43b872ce","year":2024},"citing_paper":{"arxiv_id":"2412.19637","last_updated":"2025-06-21T13:41:27Z","snapshot_observed_at":"2026-08-19T01:32:48.784739Z","submitted_at":"2024-12-27T13:31:55Z","title":"ReNeg: Learning Negative Embedding with Reward Guidance","version":3},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-11T00:13:43.581771Z"},"links":{"citing_paper":"/paper/2412.19637"},"observation_digest":"sha256:68f593f157600b746bf9052ee90938cbaf145b9bc66f9f15718d96cca96a88e5","observation_id":"15e3e39b-f1df-44b6-b8b1-31e4b62f5b59","resolution":{"observed_at":"2026-08-11T00:13:44.232541Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T00:13:44.209847Z","title":"Textcraftor: Your text encoder can be image quality controller","venue":null,"work_id":"222e07fc-863c-4153-ad08-acd1368de661","year":2024},"citing_paper":{"arxiv_id":"2412.19637","last_updated":"2025-06-21T13:41:27Z","snapshot_observed_at":"2026-08-19T01:32:48.784739Z","submitted_at":"2024-12-27T13:31:55Z","title":"ReNeg: Learning Negative Embedding with Reward Guidance","version":3},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-11T00:13:43.588110Z"},"links":{"citing_paper":"/paper/2412.19637"},"observation_digest":"sha256:768f2c2633200d562eb0c226393c6064398474463c4b503bd883cb39f52ae0cc","observation_id":"f25dab04-5d2c-4be1-8a91-39914d3eee2f","resolution":{"observed_at":"2026-08-11T00:13:44.215168Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1711.05101","last_updated":"2019-01-04T21:01:49Z","snapshot_observed_at":"2026-08-14T20:13:52.872565Z","submitted_at":"2017-11-14T14:24:06Z","title":"Decoupled Weight Decay Regularization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.05101","snapshot_observed_at":"2026-08-11T00:13:43.593907Z","title":"Decoupled weight decay regularization","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.19637","last_updated":"2025-06-21T13:41:27Z","snapshot_observed_at":"2026-08-19T01:32:48.784739Z","submitted_at":"2024-12-27T13:31:55Z","title":"ReNeg: Learning Negative Embedding with Reward Guidance","version":3},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-11T00:13:43.593907Z"},"links":{"cited_paper":"/paper/1711.05101","citing_paper":"/paper/2412.19637"},"observation_digest":"sha256:f4f0111042dd19dab3ebf0fa82b71219e317e2b5345d33c56a30787868c0bbbd","observation_id":"0e9bb5d7-1ea2-43e5-9838-a5574f88e0c9","resolution":{"observed_at":"2026-08-11T00:13:43.593907Z","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":"2026-08-11T00:13:44.194041Z","title":"Training lan- guage models to follow instructions with human feedback","venue":null,"work_id":"6cc62bf1-38d3-47a7-b170-ce03d976b106","year":2022},"citing_paper":{"arxiv_id":"2412.19637","last_updated":"2025-06-21T13:41:27Z","snapshot_observed_at":"2026-08-19T01:32:48.784739Z","submitted_at":"2024-12-27T13:31:55Z","title":"ReNeg: Learning Negative Embedding with Reward Guidance","version":3},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-11T00:13:43.600187Z"},"links":{"citing_paper":"/paper/2412.19637"},"observation_digest":"sha256:b2fa2a9bff489239dd79ad4a0a9505fbeca992ca4c44cc1f2600a83b59ede52b","observation_id":"fc0c5c96-b03c-40d5-8f27-4d0e6e44e8e9","resolution":{"observed_at":"2026-08-11T00:13:44.199213Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T00:13:44.176536Z","title":"Language models are unsu- pervised multitask learners","venue":null,"work_id":"40d7e60d-89a4-4847-bfd7-483993a953fd","year":2019},"citing_paper":{"arxiv_id":"2412.19637","last_updated":"2025-06-21T13:41:27Z","snapshot_observed_at":"2026-08-19T01:32:48.784739Z","submitted_at":"2024-12-27T13:31:55Z","title":"ReNeg: Learning Negative Embedding with Reward Guidance","version":3},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-11T00:13:43.605196Z"},"links":{"citing_paper":"/paper/2412.19637"},"observation_digest":"sha256:45aa882e6c848b961238742656e8b4a42d164d653972854d9aa86b02511a331f","observation_id":"4b93f70c-b0eb-4a09-89e2-f9a08db984a0","resolution":{"observed_at":"2026-08-11T00:13:44.182412Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T00:13:44.159202Z","title":"Direct preference optimization: Your language model is secretly a reward model","venue":null,"work_id":"e5cae05c-28e5-48dd-a03e-76c4141abf0c","year":2024},"citing_paper":{"arxiv_id":"2412.19637","last_updated":"2025-06-21T13:41:27Z","snapshot_observed_at":"2026-08-19T01:32:48.784739Z","submitted_at":"2024-12-27T13:31:55Z","title":"ReNeg: Learning Negative Embedding with Reward Guidance","version":3},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-11T00:13:43.609987Z"},"links":{"citing_paper":"/paper/2412.19637"},"observation_digest":"sha256:07518bef597906d5f65416b0f78cc87257fe674581075265d2d964c16f95cd1b","observation_id":"b5dca8ce-262c-466d-9cee-14b9f34d81eb","resolution":{"observed_at":"2026-08-11T00:13:44.164214Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2204.06125","last_updated":"2022-04-13T01:10:33Z","snapshot_observed_at":"2026-08-15T12:50:58.405488Z","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":"2026-08-11T00:13:43.614666Z","title":"Hierarchical text-conditional image gen- eration with clip latents","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.19637","last_updated":"2025-06-21T13:41:27Z","snapshot_observed_at":"2026-08-19T01:32:48.784739Z","submitted_at":"2024-12-27T13:31:55Z","title":"ReNeg: Learning Negative Embedding with Reward Guidance","version":3},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-11T00:13:43.614666Z"},"links":{"cited_paper":"/paper/2204.06125","citing_paper":"/paper/2412.19637"},"observation_digest":"sha256:58cb24b73324b05b1924d7587a89a63ecad046294dc338fcf899d2d0205898ff","observation_id":"ca2d9597-7d66-4bae-84e0-97d5514ef2ac","resolution":{"observed_at":"2026-08-11T00:13:43.614666Z","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":"2026-08-11T00:13:44.143575Z","title":"High-resolution image syn- thesis with latent diffusion models","venue":null,"work_id":"b5fcedc6-e6a9-49c5-b659-48ea1faa970a","year":2022},"citing_paper":{"arxiv_id":"2412.19637","last_updated":"2025-06-21T13:41:27Z","snapshot_observed_at":"2026-08-19T01:32:48.784739Z","submitted_at":"2024-12-27T13:31:55Z","title":"ReNeg: Learning Negative Embedding with Reward Guidance","version":3},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-11T00:13:43.620045Z"},"links":{"citing_paper":"/paper/2412.19637"},"observation_digest":"sha256:323419812df2aaa5422a844acade8ad05604837c3d859dd9e89afde840eb5296","observation_id":"d477d235-e029-4546-a36f-9f5679b29f84","resolution":{"observed_at":"2026-08-11T00:13:44.148308Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T00:13:44.124357Z","title":"Laion-5b: An open large-scale dataset for training next generation image-text models","venue":null,"work_id":"bd7228f1-d89f-4fcc-ae7e-cf50ab378223","year":2022},"citing_paper":{"arxiv_id":"2412.19637","last_updated":"2025-06-21T13:41:27Z","snapshot_observed_at":"2026-08-19T01:32:48.784739Z","submitted_at":"2024-12-27T13:31:55Z","title":"ReNeg: Learning Negative Embedding with Reward Guidance","version":3},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-11T00:13:43.624873Z"},"links":{"citing_paper":"/paper/2412.19637"},"observation_digest":"sha256:d02764b816cd2184d89f9e658864a03a789f9f0bbf63f119f1d15c7cb5c80fb0","observation_id":"224f7bd2-e049-4b40-8171-3f47fecc71a8","resolution":{"observed_at":"2026-08-11T00:13:44.129825Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2010.02502","last_updated":"2022-10-05T20:19:21Z","snapshot_observed_at":"2026-08-11T15:38:14.931716Z","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":"2026-08-11T00:13:43.629902Z","title":"Denoising diffusion implicit models","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2412.19637","last_updated":"2025-06-21T13:41:27Z","snapshot_observed_at":"2026-08-19T01:32:48.784739Z","submitted_at":"2024-12-27T13:31:55Z","title":"ReNeg: Learning Negative Embedding with Reward Guidance","version":3},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-11T00:13:43.629902Z"},"links":{"cited_paper":"/paper/2010.02502","citing_paper":"/paper/2412.19637"},"observation_digest":"sha256:b236d2dbb7757da589966ea0a5e60d36ef2fd847a2fa3b96933bb8e46fdca561","observation_id":"7d3b4b5d-a5b4-4531-ba5f-72458d9b1dc0","resolution":{"observed_at":"2026-08-11T00:13:43.629902Z","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":"2026-08-11T00:13:43.634287Z","title":"Score-based generative modeling through stochastic differential equa- tions","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2412.19637","last_updated":"2025-06-21T13:41:27Z","snapshot_observed_at":"2026-08-19T01:32:48.784739Z","submitted_at":"2024-12-27T13:31:55Z","title":"ReNeg: Learning Negative Embedding with Reward Guidance","version":3},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-11T00:13:43.634287Z"},"links":{"cited_paper":"/paper/2011.13456","citing_paper":"/paper/2412.19637"},"observation_digest":"sha256:6751d959c3cacc6df56a1303442627df386fc566e8702e9caa85f37fd67a0319","observation_id":"67f71b14-64bd-4a97-ad8a-145ccd7f3d2c","resolution":{"observed_at":"2026-08-11T00:13:43.634287Z","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":"2026-08-11T00:13:44.107288Z","title":"Diffusion model align- ment using direct preference optimization","venue":null,"work_id":"a1e34252-f1e7-42cf-9564-cebb3d6a206b","year":2024},"citing_paper":{"arxiv_id":"2412.19637","last_updated":"2025-06-21T13:41:27Z","snapshot_observed_at":"2026-08-19T01:32:48.784739Z","submitted_at":"2024-12-27T13:31:55Z","title":"ReNeg: Learning Negative Embedding with Reward Guidance","version":3},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-11T00:13:43.638660Z"},"links":{"citing_paper":"/paper/2412.19637"},"observation_digest":"sha256:410ceddb0c0f87e57fda65adb57d605f44964c1b3967e67bc95a3d6ec07d151c","observation_id":"533400d6-004a-4b77-91d3-a66abf2ceabc","resolution":{"observed_at":"2026-08-11T00:13:44.112659Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.01606","last_updated":"2024-06-27T02:53:01Z","snapshot_observed_at":"2026-08-16T13:39:14.156368Z","submitted_at":"2024-06-27T02:53:01Z","title":"On Discrete Prompt Optimization for Diffusion Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.01606","snapshot_observed_at":"2026-08-11T00:13:43.642839Z","title":"On discrete prompt optimization for diffusion models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.19637","last_updated":"2025-06-21T13:41:27Z","snapshot_observed_at":"2026-08-19T01:32:48.784739Z","submitted_at":"2024-12-27T13:31:55Z","title":"ReNeg: Learning Negative Embedding with Reward Guidance","version":3},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-11T00:13:43.642839Z"},"links":{"cited_paper":"/paper/2407.01606","citing_paper":"/paper/2412.19637"},"observation_digest":"sha256:27b539153bd86b6237d7350c5fb23e78785b7ce8b8cc68149ccff505e54a6b14","observation_id":"76a3db19-a823-42a9-a326-1c561a05fcb9","resolution":{"observed_at":"2026-08-11T00:13:43.642839Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2211.15462","last_updated":"2022-11-21T07:07:19Z","snapshot_observed_at":"2026-08-16T16:14:39.476525Z","submitted_at":"2022-11-21T07:07:19Z","title":"Investigating Prompt Engineering in Diffusion Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2211.15462","snapshot_observed_at":"2026-08-11T00:13:43.647701Z","title":"Investigating prompt engineering in diffusion models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.19637","last_updated":"2025-06-21T13:41:27Z","snapshot_observed_at":"2026-08-19T01:32:48.784739Z","submitted_at":"2024-12-27T13:31:55Z","title":"ReNeg: Learning Negative Embedding with Reward Guidance","version":3},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-11T00:13:43.647701Z"},"links":{"cited_paper":"/paper/2211.15462","citing_paper":"/paper/2412.19637"},"observation_digest":"sha256:47ebcea0aba59ac111da5f711a4ebdf6d413f184c8085542b6c79183f41d108a","observation_id":"d957a185-b34e-4d60-a271-a07aa32d33c2","resolution":{"observed_at":"2026-08-11T00:13:43.647701Z","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":"2026-08-11T00:13:44.090033Z","title":"Stable diffusion 2.0 and the importance of negative prompts for good results, 2022","venue":null,"work_id":"08fbe1c6-14be-49a1-91c5-6d9114cf1b83","year":2022},"citing_paper":{"arxiv_id":"2412.19637","last_updated":"2025-06-21T13:41:27Z","snapshot_observed_at":"2026-08-19T01:32:48.784739Z","submitted_at":"2024-12-27T13:31:55Z","title":"ReNeg: Learning Negative Embedding with Reward Guidance","version":3},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-11T00:13:43.653015Z"},"links":{"citing_paper":"/paper/2412.19637"},"observation_digest":"sha256:879f8bdffb3fa28194c0c438f82a0b43cac9c62d3add0f7ee00c141a3ef4d46b","observation_id":"ee2a0264-68bf-47b9-b7a7-95976fc8599a","resolution":{"observed_at":"2026-08-11T00:13:44.095499Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T00:13:43.657804Z","title":"Tune-a-video: One-shot tuning of image diffusion models for text-to-video generation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.19637","last_updated":"2025-06-21T13:41:27Z","snapshot_observed_at":"2026-08-19T01:32:48.784739Z","submitted_at":"2024-12-27T13:31:55Z","title":"ReNeg: Learning Negative Embedding with Reward Guidance","version":3},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-11T00:13:43.657804Z"},"links":{"citing_paper":"/paper/2412.19637"},"observation_digest":"sha256:5cb110c2145fb20ef0446f915a790a21c1976c80c5846725ab5463e7382d77dd","observation_id":"348b8756-4d95-4180-903d-fa64a60313c1","resolution":{"observed_at":"2026-08-11T00:13:43.657804Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.09341","last_updated":"2023-09-25T08:19:23Z","snapshot_observed_at":"2026-08-14T02:46:25.655503Z","submitted_at":"2023-06-15T17:59:31Z","title":"Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.09341","snapshot_observed_at":"2026-08-11T00:13:43.662477Z","title":"Human preference score v2: A solid benchmark for evaluating human preferences of text-to-image synthesis","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.19637","last_updated":"2025-06-21T13:41:27Z","snapshot_observed_at":"2026-08-19T01:32:48.784739Z","submitted_at":"2024-12-27T13:31:55Z","title":"ReNeg: Learning Negative Embedding with Reward Guidance","version":3},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-11T00:13:43.662477Z"},"links":{"cited_paper":"/paper/2306.09341","citing_paper":"/paper/2412.19637"},"observation_digest":"sha256:a71ce294aacf36d9d6118c1f16ae628f0a65f49f2e3dbf8408b7bba8d4361e2a","observation_id":"b5ef638f-fd0a-4e65-b6bb-e98b08825dca","resolution":{"observed_at":"2026-08-11T00:13:43.662477Z","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":"2026-08-11T00:13:44.060901Z","title":"Fastcomposer: Tuning-free multi- subject image generation with localized attention","venue":null,"work_id":"86ad311a-1441-4236-832f-d17b0b6587d4","year":2024},"citing_paper":{"arxiv_id":"2412.19637","last_updated":"2025-06-21T13:41:27Z","snapshot_observed_at":"2026-08-19T01:32:48.784739Z","submitted_at":"2024-12-27T13:31:55Z","title":"ReNeg: Learning Negative Embedding with Reward Guidance","version":3},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-11T00:13:43.668166Z"},"links":{"citing_paper":"/paper/2412.19637"},"observation_digest":"sha256:984e6d76cb1536b8cb276541a42051a4d2cd7e3310297c5bbe3cb6f5ee95961d","observation_id":"525e35fa-fbda-434f-93dc-8941e8c3f434","resolution":{"observed_at":"2026-08-11T00:13:44.066701Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-11T00:13:44.042899Z","title":"Imagere- ward: Learning and evaluating human preferences for text- to-image generation","venue":null,"work_id":"a047d1b7-076b-4a83-84e5-831b8a82a46b","year":2024},"citing_paper":{"arxiv_id":"2412.19637","last_updated":"2025-06-21T13:41:27Z","snapshot_observed_at":"2026-08-19T01:32:48.784739Z","submitted_at":"2024-12-27T13:31:55Z","title":"ReNeg: Learning Negative Embedding with Reward Guidance","version":3},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-11T00:13:43.672900Z"},"links":{"citing_paper":"/paper/2412.19637"},"observation_digest":"sha256:c16f3305493c147d5e799b4b5e8f207ac58466012bcb24e0be3aca7cc9195421","observation_id":"3cb413d2-8392-41e0-afbe-206cbb8e4770","resolution":{"observed_at":"2026-08-11T00:13:44.048372Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.10789","last_updated":"2022-06-22T01:11:29Z","snapshot_observed_at":"2026-08-18T22:18:02.034966Z","submitted_at":"2022-06-22T01:11:29Z","title":"Scaling Autoregressive Models for Content-Rich Text-to-Image Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.10789","snapshot_observed_at":"2026-08-11T00:13:43.677898Z","title":"Scaling autoregres- sive models for content-rich text-to-image generation","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.19637","last_updated":"2025-06-21T13:41:27Z","snapshot_observed_at":"2026-08-19T01:32:48.784739Z","submitted_at":"2024-12-27T13:31:55Z","title":"ReNeg: Learning Negative Embedding with Reward Guidance","version":3},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-11T00:13:43.677898Z"},"links":{"cited_paper":"/paper/2206.10789","citing_paper":"/paper/2412.19637"},"observation_digest":"sha256:8a3c85c571083a3b89a7b06c0ae3644c1beda7bdadbfdae6c585487b4ce95cd8","observation_id":"b81c66ec-e33c-4b39-9591-18074c91767b","resolution":{"observed_at":"2026-08-11T00:13:43.677898Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.15818","last_updated":"2025-05-30T03:55:20Z","snapshot_observed_at":"2026-08-18T15:14:36.068153Z","submitted_at":"2023-09-27T17:44:18Z","title":"Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.15818","snapshot_observed_at":"2026-08-11T00:13:43.683200Z","title":"Show-1: Marrying pixel and latent dif- fusion models for text-to-video generation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.19637","last_updated":"2025-06-21T13:41:27Z","snapshot_observed_at":"2026-08-19T01:32:48.784739Z","submitted_at":"2024-12-27T13:31:55Z","title":"ReNeg: Learning Negative Embedding with Reward Guidance","version":3},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-11T00:13:43.683200Z"},"links":{"cited_paper":"/paper/2309.15818","citing_paper":"/paper/2412.19637"},"observation_digest":"sha256:a22385c064cbaccfc1b8524a0350d50e53af819fdff1b01feb6768d4607bb88d","observation_id":"a8030b84-cd87-45e1-9494-09b01e4fc4bb","resolution":{"observed_at":"2026-08-11T00:13:43.683200Z","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":"2026-08-11T00:13:44.022387Z","title":"Adding conditional control to text-to-image diffusion models","venue":null,"work_id":"c284116b-6f14-4263-906b-575bc065a31a","year":2023},"citing_paper":{"arxiv_id":"2412.19637","last_updated":"2025-06-21T13:41:27Z","snapshot_observed_at":"2026-08-19T01:32:48.784739Z","submitted_at":"2024-12-27T13:31:55Z","title":"ReNeg: Learning Negative Embedding with Reward Guidance","version":3},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-11T00:13:43.688688Z"},"links":{"citing_paper":"/paper/2412.19637"},"observation_digest":"sha256:373b850c8152a458437d0c9a0bce080ab61f37473a93e4e39cdaa9b580561600","observation_id":"9ac36792-18f7-4548-ab40-a46340fe5848","resolution":{"observed_at":"2026-08-11T00:13:44.029983Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2412.19637","last_updated":"2025-06-21T13:41:27Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-19T01:32:48.784739Z","submitted_at":"2024-12-27T13:31:55Z","title":"ReNeg: Learning Negative Embedding with Reward Guidance"},"reference_resolution":{"displayed":41,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":20,"verified_exact":0,"verified_fuzzy":21},"total_outbound_references":41},"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":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"thesis":"As of 22 August 2026, this Paper Citation Record lists 41 of 41 outbound references and 1 inbound Pith citation observation for arXiv:2412.19637."}