{"as_of":"2026-08-15T08:43:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:5609e34af322ac63d327b3e47b5b70ec3aec496bc905b4a3271888efbec07e74","coverage":[{"denominator":58,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":58,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T21:01:56.983860Z","state":"measured"},{"denominator":59,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":59,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-15T06:32:42.880941+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":"2026-05-12T02:10:27.595446Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-12T02:11:15.507458Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2501.06655","last_updated":"2025-01-11T22:38:41Z","snapshot_observed_at":"2026-08-15T06:44:07.643409Z","submitted_at":"2025-01-11T22:38:41Z","title":"Personalized Preference Fine-tuning of Diffusion Models","version":1},"cited_work":{"arxiv_id":"2501.06655","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2501.06655","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Personalized preference fine-tuning of diffusion models","venue":null,"work_id":"80934fee-b9e9-442e-92a2-c306fddf06e8","year":2026},"citing_paper":{"arxiv_id":"2605.09433","last_updated":"2026-05-10T09:13:40Z","snapshot_observed_at":"2026-08-13T13:45:00.284853Z","submitted_at":"2026-05-10T09:13:40Z","title":"Offline Preference Optimization for Rectified Flow with Noise-Tracked Pairs","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-12T02:10:27.595446Z"},"links":{"cited_paper":"/paper/2501.06655","citing_paper":"/paper/2605.09433"},"observation_digest":"sha256:87cbde9d51177cf15c18354547dccee61bd2319b5ad9405c75ed79a8ca101ed0","observation_id":"882f1f7b-ade3-489f-9160-f2fce10bf76e","resolution":{"observed_at":"2026-05-12T02:11:15.509543Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2501.06655/citation-record","integrity":"/paper/2501.06655/integrity","json":"/paper/2501.06655/citation-record.json","paper":"/paper/2501.06655"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:01:57.982343Z","title":"Training a helpful and harmless assistant with reinforcement learning from human feedback, 2022","venue":null,"work_id":"791b8087-5854-45ef-8a4b-b13d0c580de7","year":2022},"citing_paper":{"arxiv_id":"2501.06655","last_updated":"2025-01-11T22:38:41Z","snapshot_observed_at":"2026-08-15T06:44:07.643409Z","submitted_at":"2025-01-11T22:38:41Z","title":"Personalized Preference Fine-tuning of Diffusion Models","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-10T21:01:56.705562Z"},"links":{"citing_paper":"/paper/2501.06655"},"observation_digest":"sha256:000c1b99fd75e6000903246a29e096541fbf0e8916d6722c79b412855851a28f","observation_id":"80b4e279-aa31-439a-899a-67d400449641","resolution":{"observed_at":"2026-08-10T21:01:57.987434Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-10T21:01:57.966007Z","title":"Training diffusion models with reinforce- ment learning","venue":null,"work_id":"7cfe3e2b-e51e-4a1a-8fb4-577ec48bf657","year":2024},"citing_paper":{"arxiv_id":"2501.06655","last_updated":"2025-01-11T22:38:41Z","snapshot_observed_at":"2026-08-15T06:44:07.643409Z","submitted_at":"2025-01-11T22:38:41Z","title":"Personalized Preference Fine-tuning of Diffusion Models","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-10T21:01:56.712053Z"},"links":{"citing_paper":"/paper/2501.06655"},"observation_digest":"sha256:477639326dcf2376366dd3e8f65831887fdba15f846434d868d98bad109d31c5","observation_id":"11ccb589-d7bb-403e-88a1-1c13b6dbb5f8","resolution":{"observed_at":"2026-08-10T21:01:57.971304Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-10T21:01:56.717616Z","title":"Rank analysis of incomplete block designs: I","venue":null,"work_id":null,"year":1952},"citing_paper":{"arxiv_id":"2501.06655","last_updated":"2025-01-11T22:38:41Z","snapshot_observed_at":"2026-08-15T06:44:07.643409Z","submitted_at":"2025-01-11T22:38:41Z","title":"Personalized Preference Fine-tuning of Diffusion Models","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-10T21:01:56.717616Z"},"links":{"citing_paper":"/paper/2501.06655"},"observation_digest":"sha256:e478a5fc3fd39042031df753dc5da6b0be757ad6f8c8deab442171b7ab382cb8","observation_id":"0d479af6-b79e-4898-980f-c75eb1d6c8a8","resolution":{"observed_at":"2026-08-10T21:01:56.717616Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.04842","last_updated":"2024-07-05T20:03:16Z","snapshot_observed_at":"2026-08-14T10:14:34.963048Z","submitted_at":"2024-07-05T20:03:16Z","title":"MJ-Bench: Is Your Multimodal Reward Model Really a Good Judge for Text-to-Image Generation?","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.04842","snapshot_observed_at":"2026-08-10T21:01:56.722648Z","title":"MJ- Bench: Is Your Multimodal Reward Model Really a Good Judge for Text-to-Image Generation? arXiv e-prints , art","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.06655","last_updated":"2025-01-11T22:38:41Z","snapshot_observed_at":"2026-08-15T06:44:07.643409Z","submitted_at":"2025-01-11T22:38:41Z","title":"Personalized Preference Fine-tuning of Diffusion Models","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-10T21:01:56.722648Z"},"links":{"cited_paper":"/paper/2407.04842","citing_paper":"/paper/2501.06655"},"observation_digest":"sha256:92721959430c8170c6219a437f70d62ef6379ff5b36762bae856371bcfac5846","observation_id":"02a8b859-bc42-4fbf-af9c-a4a42630185e","resolution":{"observed_at":"2026-08-10T21:01:56.722648Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"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":"2026-08-10T21:01:56.728245Z","title":"Directly fine-tuning diffusion models on differentiable re- wards","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.06655","last_updated":"2025-01-11T22:38:41Z","snapshot_observed_at":"2026-08-15T06:44:07.643409Z","submitted_at":"2025-01-11T22:38:41Z","title":"Personalized Preference Fine-tuning of Diffusion Models","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-10T21:01:56.728245Z"},"links":{"cited_paper":"/paper/2309.17400","citing_paper":"/paper/2501.06655"},"observation_digest":"sha256:ab0dc121cd2222e7262795c556451138dc6f825b67b37acde536adc3911794c9","observation_id":"08d764e2-9357-4438-a47e-8273fdb161d0","resolution":{"observed_at":"2026-08-10T21:01:56.728245Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.15807","last_updated":"2023-09-27T17:30:19Z","snapshot_observed_at":"2026-08-15T07:12:45.000333Z","submitted_at":"2023-09-27T17:30:19Z","title":"Emu: Enhancing Image Generation Models Using Photogenic Needles in a Haystack","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.15807","snapshot_observed_at":"2026-08-10T21:01:56.733403Z","title":"Emu: Enhanc- ing image generation models using photogenic needles in a haystack","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.06655","last_updated":"2025-01-11T22:38:41Z","snapshot_observed_at":"2026-08-15T06:44:07.643409Z","submitted_at":"2025-01-11T22:38:41Z","title":"Personalized Preference Fine-tuning of Diffusion Models","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-10T21:01:56.733403Z"},"links":{"cited_paper":"/paper/2309.15807","citing_paper":"/paper/2501.06655"},"observation_digest":"sha256:b2397bcc178d880f3a67b724fa40db58b1279468669fd4f946ae13508d07b9f4","observation_id":"6335e94c-865a-4728-b1d6-7a6fee45554f","resolution":{"observed_at":"2026-08-10T21:01:56.733403Z","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":"2026-08-10T21:01:57.939174Z","title":"Scaling recti- fied flow transformers for high-resolution image synthesis","venue":null,"work_id":"99ce1f6c-e70e-4f48-b47d-17c4df2eb852","year":2024},"citing_paper":{"arxiv_id":"2501.06655","last_updated":"2025-01-11T22:38:41Z","snapshot_observed_at":"2026-08-15T06:44:07.643409Z","submitted_at":"2025-01-11T22:38:41Z","title":"Personalized Preference Fine-tuning of Diffusion Models","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-10T21:01:56.739346Z"},"links":{"citing_paper":"/paper/2501.06655"},"observation_digest":"sha256:d7a432badf193adfbb72ba1ff59582fb9e56dbc925902bf03cf9b507a00b33bf","observation_id":"9af1c40a-0a4a-4c50-9f01-467a7be47e3e","resolution":{"observed_at":"2026-08-10T21:01:57.944761Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.01306","last_updated":"2024-11-19T18:12:45Z","snapshot_observed_at":"2026-08-12T21:18:02.964833Z","submitted_at":"2024-02-02T10:53:36Z","title":"KTO: Model Alignment as Prospect Theoretic Optimization","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.01306","snapshot_observed_at":"2026-08-10T21:01:56.744123Z","title":"Kto: Model alignment as prospect theoretic optimization","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.06655","last_updated":"2025-01-11T22:38:41Z","snapshot_observed_at":"2026-08-15T06:44:07.643409Z","submitted_at":"2025-01-11T22:38:41Z","title":"Personalized Preference Fine-tuning of Diffusion Models","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-10T21:01:56.744123Z"},"links":{"cited_paper":"/paper/2402.01306","citing_paper":"/paper/2501.06655"},"observation_digest":"sha256:4eed565ed981ffef643fbf51361d741072bbcec2725421be77304687f33ad7a9","observation_id":"b6204bad-1559-4d8a-880a-4a68245e5f9b","resolution":{"observed_at":"2026-08-10T21:01:56.744123Z","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":"2026-08-10T21:01:57.921745Z","title":"Re- inforcement learning for fine-tuning text-to-image diffusion models","venue":null,"work_id":"1140e228-5d57-41a1-9ebb-d10174f00388","year":2024},"citing_paper":{"arxiv_id":"2501.06655","last_updated":"2025-01-11T22:38:41Z","snapshot_observed_at":"2026-08-15T06:44:07.643409Z","submitted_at":"2025-01-11T22:38:41Z","title":"Personalized Preference Fine-tuning of Diffusion Models","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-10T21:01:56.749877Z"},"links":{"citing_paper":"/paper/2501.06655"},"observation_digest":"sha256:45d1b4edaa2ffdf192f29c8945cbab3bba342b0bffb443cd3a202432f76b19cf","observation_id":"aed6b77a-595b-4031-80db-00aba444f1e4","resolution":{"observed_at":"2026-08-10T21:01:57.927090Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.15951","last_updated":"2024-10-11T00:05:03Z","snapshot_observed_at":"2026-08-12T23:36:52.510891Z","submitted_at":"2024-06-22T22:07:40Z","title":"Modular Pluralism: Pluralistic Alignment via Multi-LLM Collaboration","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.15951","snapshot_observed_at":"2026-08-10T21:01:56.754232Z","title":"Modular Pluralism: Pluralistic Alignment via Multi-LLM Collabora- tion","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.06655","last_updated":"2025-01-11T22:38:41Z","snapshot_observed_at":"2026-08-15T06:44:07.643409Z","submitted_at":"2025-01-11T22:38:41Z","title":"Personalized Preference Fine-tuning of Diffusion Models","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-10T21:01:56.754232Z"},"links":{"cited_paper":"/paper/2406.15951","citing_paper":"/paper/2501.06655"},"observation_digest":"sha256:86023574ddd16fd98fa0c445977f0deab3d75edfc31c8511f122d2b605b2c16a","observation_id":"fda3e7df-8b1b-44b4-80fc-a1782413b35b","resolution":{"observed_at":"2026-08-10T21:01:56.754232Z","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":"2026-08-10T21:01:57.906018Z","title":"Improving image generation with better captions","venue":null,"work_id":"4b50a47d-f294-4923-9e59-49830612b57d","year":2023},"citing_paper":{"arxiv_id":"2501.06655","last_updated":"2025-01-11T22:38:41Z","snapshot_observed_at":"2026-08-15T06:44:07.643409Z","submitted_at":"2025-01-11T22:38:41Z","title":"Personalized Preference Fine-tuning of Diffusion Models","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-10T21:01:56.758624Z"},"links":{"citing_paper":"/paper/2501.06655"},"observation_digest":"sha256:08380bbfaae5711e251cb8b853a58106a2fc95050bb69c16694d290d2807b927","observation_id":"524dc754-8756-43cf-88a3-90627a438383","resolution":{"observed_at":"2026-08-10T21:01:57.910761Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-10T21:01:57.890943Z","title":"Denoising diffu- sion probabilistic models","venue":null,"work_id":"280efd3c-88ec-4961-a65e-1474ea99ce3f","year":2020},"citing_paper":{"arxiv_id":"2501.06655","last_updated":"2025-01-11T22:38:41Z","snapshot_observed_at":"2026-08-15T06:44:07.643409Z","submitted_at":"2025-01-11T22:38:41Z","title":"Personalized Preference Fine-tuning of Diffusion Models","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-10T21:01:56.762537Z"},"links":{"citing_paper":"/paper/2501.06655"},"observation_digest":"sha256:252aa434710291d43ec2520a683b367cedbb2243d4b87231451091461d66f3da","observation_id":"e6143af7-6ee1-4957-8053-ce2d57296c04","resolution":{"observed_at":"2026-08-10T21:01:57.895912Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-10T21:01:57.875782Z","title":"Open- clip, 2021","venue":null,"work_id":"72b54b41-9b67-469f-a614-a50269babc10","year":2021},"citing_paper":{"arxiv_id":"2501.06655","last_updated":"2025-01-11T22:38:41Z","snapshot_observed_at":"2026-08-15T06:44:07.643409Z","submitted_at":"2025-01-11T22:38:41Z","title":"Personalized Preference Fine-tuning of Diffusion Models","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-10T21:01:56.767123Z"},"links":{"citing_paper":"/paper/2501.06655"},"observation_digest":"sha256:63141d6f8f0774c9ae91d663b7ead4afa95ed72b022a66a304b9da9326b3204a","observation_id":"a49d083d-685e-4531-b974-ae449c863abd","resolution":{"observed_at":"2026-08-10T21:01:57.880765Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-10T21:01:57.860131Z","title":"Kingma, Tim Salimans, Ben Poole, and Jonathan Ho","venue":null,"work_id":"20e40e03-e8e7-4ac3-b542-eabcf8169317","year":2021},"citing_paper":{"arxiv_id":"2501.06655","last_updated":"2025-01-11T22:38:41Z","snapshot_observed_at":"2026-08-15T06:44:07.643409Z","submitted_at":"2025-01-11T22:38:41Z","title":"Personalized Preference Fine-tuning of Diffusion Models","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-10T21:01:56.771521Z"},"links":{"citing_paper":"/paper/2501.06655"},"observation_digest":"sha256:934e9b8edf4e38bbb3f06de8624fc2fd52c40a73ecc43330388fe9b62d960d85","observation_id":"18404cea-1de1-4b8f-bd59-57d8f47d9e48","resolution":{"observed_at":"2026-08-10T21:01:57.865091Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.16019","last_updated":"2024-12-03T16:18:10Z","snapshot_observed_at":"2026-08-13T00:22:53.103037Z","submitted_at":"2024-04-24T17:51:36Z","title":"The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.16019","snapshot_observed_at":"2026-08-10T21:01:56.776066Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.06655","last_updated":"2025-01-11T22:38:41Z","snapshot_observed_at":"2026-08-15T06:44:07.643409Z","submitted_at":"2025-01-11T22:38:41Z","title":"Personalized Preference Fine-tuning of Diffusion Models","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-10T21:01:56.776066Z"},"links":{"cited_paper":"/paper/2404.16019","citing_paper":"/paper/2501.06655"},"observation_digest":"sha256:7d6b6c31936c25385d123bb25c82a7474947cca412c9c93fb8d25ef552152a70","observation_id":"8e863f60-8155-4b9e-abb8-db48af3d89c7","resolution":{"observed_at":"2026-08-10T21:01:56.776066Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.01569","last_updated":"2023-11-23T17:07:58Z","snapshot_observed_at":"2026-08-15T07:55:17.482955Z","submitted_at":"2023-05-02T16:18:11Z","title":"Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.01569","snapshot_observed_at":"2026-08-10T21:01:56.780887Z","title":"Pick-a-pic: An open dataset of user preferences for text-to-image generation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.06655","last_updated":"2025-01-11T22:38:41Z","snapshot_observed_at":"2026-08-15T06:44:07.643409Z","submitted_at":"2025-01-11T22:38:41Z","title":"Personalized Preference Fine-tuning of Diffusion Models","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-10T21:01:56.780887Z"},"links":{"cited_paper":"/paper/2305.01569","citing_paper":"/paper/2501.06655"},"observation_digest":"sha256:60de42a121dd10cfe68c7abaa0a2a6458348e9f0e547026a0469a83a659218dd","observation_id":"ac6f5f4f-50c2-45bc-9594-ea151d361e4e","resolution":{"observed_at":"2026-08-10T21:01:56.780887Z","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":"2026-08-10T21:01:57.844744Z","title":"Large language models are zero-shot reasoners, 2023","venue":null,"work_id":"364bf449-04d1-4cb2-802e-91a6cec1670f","year":2023},"citing_paper":{"arxiv_id":"2501.06655","last_updated":"2025-01-11T22:38:41Z","snapshot_observed_at":"2026-08-15T06:44:07.643409Z","submitted_at":"2025-01-11T22:38:41Z","title":"Personalized Preference Fine-tuning of Diffusion Models","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-10T21:01:56.785428Z"},"links":{"citing_paper":"/paper/2501.06655"},"observation_digest":"sha256:09198cff52e9b04e013356e9834a6b8625f5b314328f0bde888ac546d6e9dd70","observation_id":"a378b1e1-b689-4496-a5bc-8965658db3ca","resolution":{"observed_at":"2026-08-10T21:01:57.849573Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2302.12192","last_updated":"2023-02-23T17:34:53Z","snapshot_observed_at":"2026-07-06T14:55:12.100148Z","submitted_at":"2023-02-23T17:34:53Z","title":"Aligning Text-to-Image Models using Human Feedback","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.12192","snapshot_observed_at":"2026-08-10T21:01:56.789825Z","title":"Aligning text- to-image models using human feedback","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.06655","last_updated":"2025-01-11T22:38:41Z","snapshot_observed_at":"2026-08-15T06:44:07.643409Z","submitted_at":"2025-01-11T22:38:41Z","title":"Personalized Preference Fine-tuning of Diffusion Models","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-10T21:01:56.789825Z"},"links":{"cited_paper":"/paper/2302.12192","citing_paper":"/paper/2501.06655"},"observation_digest":"sha256:7819ae287208bf37b8677df43f67c2056982477dee38c11b8078ce12efc0dd4b","observation_id":"f1ceb44e-e509-4680-a7cb-f7e7039c58ff","resolution":{"observed_at":"2026-08-10T21:01:56.789825Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.06591","last_updated":"2024-01-12T14:19:23Z","snapshot_observed_at":"2026-08-13T04:43:56.652988Z","submitted_at":"2024-01-12T14:19:23Z","title":"Prometheus-Vision: Vision-Language Model as a Judge for Fine-Grained Evaluation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.06591","snapshot_observed_at":"2026-08-10T21:01:56.794859Z","title":"Prometheus-Vision: Vision- Language Model as a Judge for Fine-Grained Evaluation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.06655","last_updated":"2025-01-11T22:38:41Z","snapshot_observed_at":"2026-08-15T06:44:07.643409Z","submitted_at":"2025-01-11T22:38:41Z","title":"Personalized Preference Fine-tuning of Diffusion Models","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-10T21:01:56.794859Z"},"links":{"cited_paper":"/paper/2401.06591","citing_paper":"/paper/2501.06655"},"observation_digest":"sha256:ebc9bb32e13b488c38731edce690051dbde34235c54f015fe6c1a2c4d93426cc","observation_id":"46a4ea93-30a3-4a98-a285-c7706f219412","resolution":{"observed_at":"2026-08-10T21:01:56.794859Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.03326","last_updated":"2024-10-26T16:35:13Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-08-06T17:59:44Z","title":"LLaVA-OneVision: Easy Visual Task Transfer","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.03326","snapshot_observed_at":"2026-08-10T21:01:56.804272Z","title":"LLaV A-OneVision: Easy Visual Task Transfer","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.06655","last_updated":"2025-01-11T22:38:41Z","snapshot_observed_at":"2026-08-15T06:44:07.643409Z","submitted_at":"2025-01-11T22:38:41Z","title":"Personalized Preference Fine-tuning of Diffusion Models","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-10T21:01:56.804272Z"},"links":{"cited_paper":"/paper/2408.03326","citing_paper":"/paper/2501.06655"},"observation_digest":"sha256:e05f45f3a7bbb7a9f566399dccc28274983ad16948d8e6f8b5a0f4585303446a","observation_id":"88d7ab99-7b94-4b1d-b854-299054cfac5a","resolution":{"observed_at":"2026-08-10T21:01:56.804272Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.04465","last_updated":"2024-10-11T19:43:11Z","snapshot_observed_at":"2026-08-13T00:36:44.636118Z","submitted_at":"2024-04-06T01:23:23Z","title":"Aligning Diffusion Models by Optimizing Human Utility","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.04465","snapshot_observed_at":"2026-08-10T21:01:56.808855Z","title":"Aligning diffusion models by optimizing human utility","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.06655","last_updated":"2025-01-11T22:38:41Z","snapshot_observed_at":"2026-08-15T06:44:07.643409Z","submitted_at":"2025-01-11T22:38:41Z","title":"Personalized Preference Fine-tuning of Diffusion Models","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-10T21:01:56.808855Z"},"links":{"cited_paper":"/paper/2404.04465","citing_paper":"/paper/2501.06655"},"observation_digest":"sha256:44396ea308e7200acdd687ece851ce61c785337cd545d349fba67602a133e599","observation_id":"83b40789-fa98-4c24-b8ea-1383e607eeec","resolution":{"observed_at":"2026-08-10T21:01:56.808855Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.05133","last_updated":"2024-12-09T04:21:08Z","snapshot_observed_at":"2026-08-13T04:25:30.919897Z","submitted_at":"2024-02-06T04:18:58Z","title":"Personalized Language Modeling from Personalized Human Feedback","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.05133","snapshot_observed_at":"2026-08-10T21:01:56.813712Z","title":"Personalized lan- guage modeling from personalized human feedback","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.06655","last_updated":"2025-01-11T22:38:41Z","snapshot_observed_at":"2026-08-15T06:44:07.643409Z","submitted_at":"2025-01-11T22:38:41Z","title":"Personalized Preference Fine-tuning of Diffusion Models","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-10T21:01:56.813712Z"},"links":{"cited_paper":"/paper/2402.05133","citing_paper":"/paper/2501.06655"},"observation_digest":"sha256:dcebe5eb4b05becf7aa748da0cadede1c5ca2b611a481505a6b6d3c772306dca","observation_id":"86bcab01-244e-41f2-9e0d-f48c4995ccfa","resolution":{"observed_at":"2026-08-10T21:01:56.813712Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"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":"2026-08-10T21:01:56.818049Z","title":"Decoupled weight decay regularization","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2501.06655","last_updated":"2025-01-11T22:38:41Z","snapshot_observed_at":"2026-08-15T06:44:07.643409Z","submitted_at":"2025-01-11T22:38:41Z","title":"Personalized Preference Fine-tuning of Diffusion Models","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-10T21:01:56.818049Z"},"links":{"cited_paper":"/paper/1711.05101","citing_paper":"/paper/2501.06655"},"observation_digest":"sha256:fdba9277dafaeed57ee00ee3728ae113a62822809d85f2b10786f496d98d1594","observation_id":"6865cb0c-5ecb-4c54-acb8-dc7a061c702e","resolution":{"observed_at":"2026-08-10T21:01:56.818049Z","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":"2026-08-10T21:01:56.822486Z","title":"T2i-adapter: Learning adapters to dig out more controllable ability for text-to-image diffusion models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.06655","last_updated":"2025-01-11T22:38:41Z","snapshot_observed_at":"2026-08-15T06:44:07.643409Z","submitted_at":"2025-01-11T22:38:41Z","title":"Personalized Preference Fine-tuning of Diffusion Models","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-10T21:01:56.822486Z"},"links":{"citing_paper":"/paper/2501.06655"},"observation_digest":"sha256:1382c401d1eca0cde6bb012eb33b50c9f6c3dd2df581242323a5d6641f2e69dd","observation_id":"da66c3f9-2f68-4797-af64-5cff0a030d07","resolution":{"observed_at":"2026-08-10T21:01:56.822486Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"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":"2026-08-10T21:01:56.826380Z","title":"Gpt-4 technical report","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.06655","last_updated":"2025-01-11T22:38:41Z","snapshot_observed_at":"2026-08-15T06:44:07.643409Z","submitted_at":"2025-01-11T22:38:41Z","title":"Personalized Preference Fine-tuning of Diffusion Models","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-10T21:01:56.826380Z"},"links":{"cited_paper":"/paper/2303.08774","citing_paper":"/paper/2501.06655"},"observation_digest":"sha256:4c25c4003fe72cf6a6160c8d0c9dfdfeb2ad77e94cd62ea7635322382ae1f7b7","observation_id":"a16e1da8-2401-473e-85c0-e84831260cfd","resolution":{"observed_at":"2026-08-10T21:01:56.826380Z","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":"2026-08-10T21:01:57.819584Z","title":"W ¨urstchen: An ef- ficient architecture for large-scale text-to-image diffusion models","venue":null,"work_id":"f4c3dcdd-39e2-4489-80bc-2e1aed0215f7","year":2024},"citing_paper":{"arxiv_id":"2501.06655","last_updated":"2025-01-11T22:38:41Z","snapshot_observed_at":"2026-08-15T06:44:07.643409Z","submitted_at":"2025-01-11T22:38:41Z","title":"Personalized Preference Fine-tuning of Diffusion Models","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-10T21:01:56.830734Z"},"links":{"citing_paper":"/paper/2501.06655"},"observation_digest":"sha256:1f2d8cb24c7168a0af15c7a4df1efd478f8220c8ef33bcad1ec331cc11f1ed10","observation_id":"02ef3304-89c5-46ef-bd92-e3f48cba8832","resolution":{"observed_at":"2026-08-10T21:01:57.824750Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2408.10075","last_updated":"2024-08-19T15:18:30Z","snapshot_observed_at":"2026-08-12T23:01:21.775751Z","submitted_at":"2024-08-19T15:18:30Z","title":"Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.10075","snapshot_observed_at":"2026-08-10T21:01:56.835342Z","title":"Personalizing reinforcement learning from human feedback with variational preference learning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.06655","last_updated":"2025-01-11T22:38:41Z","snapshot_observed_at":"2026-08-15T06:44:07.643409Z","submitted_at":"2025-01-11T22:38:41Z","title":"Personalized Preference Fine-tuning of Diffusion Models","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-10T21:01:56.835342Z"},"links":{"cited_paper":"/paper/2408.10075","citing_paper":"/paper/2501.06655"},"observation_digest":"sha256:abb48e041f542f5b2cb13da010608169a925eff6b5ab0c617bc295139d782e4f","observation_id":"4034e8cc-46fe-49a3-ae4d-b29d5d13c1bc","resolution":{"observed_at":"2026-08-10T21:01:56.835342Z","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":"2026-08-10T21:01:56.840150Z","title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.06655","last_updated":"2025-01-11T22:38:41Z","snapshot_observed_at":"2026-08-15T06:44:07.643409Z","submitted_at":"2025-01-11T22:38:41Z","title":"Personalized Preference Fine-tuning of Diffusion Models","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-10T21:01:56.840150Z"},"links":{"citing_paper":"/paper/2501.06655"},"observation_digest":"sha256:e2e17f080406a0afc348658f3683f9d78431d1b2526d720b22f4b9ff20c39d86","observation_id":"c615ca92-8839-4e91-985e-a66306c22b1a","resolution":{"observed_at":"2026-08-10T21:01:56.840150Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.03739","last_updated":"2024-11-07T03:54:22Z","snapshot_observed_at":"2026-07-06T16:28:22.350574Z","submitted_at":"2023-10-05T17:59:18Z","title":"Aligning Text-to-Image Diffusion Models with Reward Backpropagation","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.03739","snapshot_observed_at":"2026-08-10T21:01:56.844853Z","title":"Aligning text-to-image diffusion models with reward backpropagation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.06655","last_updated":"2025-01-11T22:38:41Z","snapshot_observed_at":"2026-08-15T06:44:07.643409Z","submitted_at":"2025-01-11T22:38:41Z","title":"Personalized Preference Fine-tuning of Diffusion Models","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-10T21:01:56.844853Z"},"links":{"cited_paper":"/paper/2310.03739","citing_paper":"/paper/2501.06655"},"observation_digest":"sha256:317acc3cff3e301bd68f52d88cd664222a731669d7a84b81a0a052cfcddc6d71","observation_id":"aeba61ac-9706-4aa7-a86d-e6cdd596d963","resolution":{"observed_at":"2026-08-10T21:01:56.844853Z","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":"2026-08-10T21:01:57.792663Z","title":"Learning transferable visual models from natural language supervi- sion","venue":null,"work_id":"15a22211-2176-47b9-b11d-abe868c36bf8","year":2021},"citing_paper":{"arxiv_id":"2501.06655","last_updated":"2025-01-11T22:38:41Z","snapshot_observed_at":"2026-08-15T06:44:07.643409Z","submitted_at":"2025-01-11T22:38:41Z","title":"Personalized Preference Fine-tuning of Diffusion Models","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-10T21:01:56.850059Z"},"links":{"citing_paper":"/paper/2501.06655"},"observation_digest":"sha256:c594eefd55b05c101d8af69f139f8e23dc788dd8d4c04c43090fc03936cbdca0","observation_id":"8f3d906d-6eac-4439-915c-bff9d6643479","resolution":{"observed_at":"2026-08-10T21:01:57.798238Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-10T21:01:57.776760Z","title":"Direct preference optimization: Your language model is secretly a reward model","venue":null,"work_id":"91ab2dce-9c75-460f-a887-60a2eb7efb49","year":2024},"citing_paper":{"arxiv_id":"2501.06655","last_updated":"2025-01-11T22:38:41Z","snapshot_observed_at":"2026-08-15T06:44:07.643409Z","submitted_at":"2025-01-11T22:38:41Z","title":"Personalized Preference Fine-tuning of Diffusion Models","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-10T21:01:56.855442Z"},"links":{"citing_paper":"/paper/2501.06655"},"observation_digest":"sha256:ff06d484e9e1ee6d62ee5f780a330c0c07ff0fc45a1c8c9b3963a556561fdb59","observation_id":"2aacc67d-0c1a-4a9a-8d15-96493a439e55","resolution":{"observed_at":"2026-08-10T21:01:57.781987Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2204.06125","last_updated":"2022-04-13T01:10:33Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2022-04-13T01:10:33Z","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.06125","snapshot_observed_at":"2026-08-10T21:01:56.860097Z","title":"Hierarchical text-conditional image gen- eration with clip latents","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.06655","last_updated":"2025-01-11T22:38:41Z","snapshot_observed_at":"2026-08-15T06:44:07.643409Z","submitted_at":"2025-01-11T22:38:41Z","title":"Personalized Preference Fine-tuning of Diffusion Models","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-10T21:01:56.860097Z"},"links":{"cited_paper":"/paper/2204.06125","citing_paper":"/paper/2501.06655"},"observation_digest":"sha256:0dfda91f772231182b22f1a97b0266081b12c054297f07926c4b01c28da6db48","observation_id":"6aa7b3b5-f885-46e8-b93c-c0a771725732","resolution":{"observed_at":"2026-08-10T21:01:56.860097Z","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":"2026-08-10T21:01:57.759809Z","title":"High-resolution image synthesis with latent diffusion models","venue":null,"work_id":"62f91206-1ed0-4971-8302-e71d5b4de4a7","year":2022},"citing_paper":{"arxiv_id":"2501.06655","last_updated":"2025-01-11T22:38:41Z","snapshot_observed_at":"2026-08-15T06:44:07.643409Z","submitted_at":"2025-01-11T22:38:41Z","title":"Personalized Preference Fine-tuning of Diffusion Models","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-10T21:01:56.865910Z"},"links":{"citing_paper":"/paper/2501.06655"},"observation_digest":"sha256:0aa933ab1b81548549b07c14e5ad6600776bfaf121d027d6ba741b87c4449e1e","observation_id":"fc84ea47-ccb3-45ff-b42a-397fa5dea7fd","resolution":{"observed_at":"2026-08-10T21:01:57.765184Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-10T21:01:57.744261Z","title":"Photorealistic text-to-image diffusion models with deep lan- guage understanding","venue":null,"work_id":"3e154c3d-36e9-4dc9-a076-ea0594f3b660","year":2022},"citing_paper":{"arxiv_id":"2501.06655","last_updated":"2025-01-11T22:38:41Z","snapshot_observed_at":"2026-08-15T06:44:07.643409Z","submitted_at":"2025-01-11T22:38:41Z","title":"Personalized Preference Fine-tuning of Diffusion Models","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-10T21:01:56.870549Z"},"links":{"citing_paper":"/paper/2501.06655"},"observation_digest":"sha256:ae8020d6f1c8de603caadff12af7c53ea5b15cdf80363b26eefaab682c84e802","observation_id":"d4409820-6666-40d9-b545-3deb632950dd","resolution":{"observed_at":"2026-08-10T21:01:57.749335Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.17548","last_updated":"2023-03-30T17:17:08Z","snapshot_observed_at":"2026-08-14T22:31:22.931950Z","submitted_at":"2023-03-30T17:17:08Z","title":"Whose Opinions Do Language Models Reflect?","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.17548","snapshot_observed_at":"2026-08-10T21:01:56.875126Z","title":"Whose Opin- ions Do Language Models Reflect? arXiv e-prints , art","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.06655","last_updated":"2025-01-11T22:38:41Z","snapshot_observed_at":"2026-08-15T06:44:07.643409Z","submitted_at":"2025-01-11T22:38:41Z","title":"Personalized Preference Fine-tuning of Diffusion Models","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-10T21:01:56.875126Z"},"links":{"cited_paper":"/paper/2303.17548","citing_paper":"/paper/2501.06655"},"observation_digest":"sha256:c139a4f84b30088d49660c01658451eab8d099f3ecccb0622048415a3a197a1f","observation_id":"8dd029ff-d460-4ea2-873a-6f0bcaac5c7a","resolution":{"observed_at":"2026-08-10T21:01:56.875126Z","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":"2026-08-10T21:01:57.728151Z","title":"CLIP MLP aesthetic score predictor","venue":null,"work_id":"02f31c4d-8d9e-4a24-9cb1-0894a971b9a3","year":2022},"citing_paper":{"arxiv_id":"2501.06655","last_updated":"2025-01-11T22:38:41Z","snapshot_observed_at":"2026-08-15T06:44:07.643409Z","submitted_at":"2025-01-11T22:38:41Z","title":"Personalized Preference Fine-tuning of Diffusion Models","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-10T21:01:56.879851Z"},"links":{"citing_paper":"/paper/2501.06655"},"observation_digest":"sha256:5068f2733e2226d8c83735bbefc03954663ad40415f8f1f0ec748b4aef714283","observation_id":"cfe83f1f-ade2-4d78-a5af-6a0ab5375020","resolution":{"observed_at":"2026-08-10T21:01:57.733283Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-10T21:01:57.712514Z","title":"LAION-5b: An open large-scale dataset for train- ing next generation image-text models","venue":null,"work_id":"aa73383f-18b7-4322-bcf1-d1d7e65f28bb","year":null},"citing_paper":{"arxiv_id":"2501.06655","last_updated":"2025-01-11T22:38:41Z","snapshot_observed_at":"2026-08-15T06:44:07.643409Z","submitted_at":"2025-01-11T22:38:41Z","title":"Personalized Preference Fine-tuning of Diffusion Models","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-10T21:01:56.884521Z"},"links":{"citing_paper":"/paper/2501.06655"},"observation_digest":"sha256:f52249462762ac6b9125dfa42a88ffb4724d4d82fef07800ffc37f691ce7df0e","observation_id":"5231e0be-bdf6-4613-a306-5e81d1aaf13c","resolution":{"observed_at":"2026-08-10T21:01:57.717597Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.16656","last_updated":"2023-10-25T14:10:08Z","snapshot_observed_at":"2026-08-13T05:40:39.961511Z","submitted_at":"2023-10-25T14:10:08Z","title":"A Picture is Worth a Thousand Words: Principled Recaptioning Improves Image Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.16656","snapshot_observed_at":"2026-08-10T21:01:56.889256Z","title":"A picture is worth a thousand words: Principled recaptioning improves image generation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.06655","last_updated":"2025-01-11T22:38:41Z","snapshot_observed_at":"2026-08-15T06:44:07.643409Z","submitted_at":"2025-01-11T22:38:41Z","title":"Personalized Preference Fine-tuning of Diffusion Models","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-10T21:01:56.889256Z"},"links":{"cited_paper":"/paper/2310.16656","citing_paper":"/paper/2501.06655"},"observation_digest":"sha256:b9b2a138772c3c5614876b54c2e9c0fc04803731af2c66cf07df2f073de4eabb","observation_id":"8476dc06-cd52-4c78-a179-abe04cb59243","resolution":{"observed_at":"2026-08-10T21:01:56.889256Z","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":"2026-08-10T21:01:57.696726Z","title":"Deep unsupervised learning using nonequilibrium thermodynamics","venue":null,"work_id":"da446e3b-4656-43ec-b02d-00ac6c34de3b","year":2015},"citing_paper":{"arxiv_id":"2501.06655","last_updated":"2025-01-11T22:38:41Z","snapshot_observed_at":"2026-08-15T06:44:07.643409Z","submitted_at":"2025-01-11T22:38:41Z","title":"Personalized Preference Fine-tuning of Diffusion Models","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-10T21:01:56.893847Z"},"links":{"citing_paper":"/paper/2501.06655"},"observation_digest":"sha256:8fd4c512c50911bd00176a91e61d1addeeeb8a2fbba489d35e246a52342445e8","observation_id":"2a830a45-3a21-45e2-aa5a-549b75beaeb6","resolution":{"observed_at":"2026-08-10T21:01:57.701996Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-10T21:01:56.898759Z","title":"Denois- ing diffusion implicit models","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.06655","last_updated":"2025-01-11T22:38:41Z","snapshot_observed_at":"2026-08-15T06:44:07.643409Z","submitted_at":"2025-01-11T22:38:41Z","title":"Personalized Preference Fine-tuning of Diffusion Models","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-10T21:01:56.898759Z"},"links":{"citing_paper":"/paper/2501.06655"},"observation_digest":"sha256:4b99fa49b86225922e78262d0372451674c243cb13dd8de9ed3b83a7d82223ad","observation_id":"b5e90beb-16ef-41d4-af4c-39db589a22d2","resolution":{"observed_at":"2026-08-10T21:01:56.898759Z","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":"2026-08-10T21:01:57.673024Z","title":"Generative modeling by esti- mating gradients of the data distribution","venue":null,"work_id":"057a7549-7a09-4715-81e0-fa76e5bbcc1a","year":2019},"citing_paper":{"arxiv_id":"2501.06655","last_updated":"2025-01-11T22:38:41Z","snapshot_observed_at":"2026-08-15T06:44:07.643409Z","submitted_at":"2025-01-11T22:38:41Z","title":"Personalized Preference Fine-tuning of Diffusion Models","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-10T21:01:56.903010Z"},"links":{"citing_paper":"/paper/2501.06655"},"observation_digest":"sha256:bde609604970b2dd651b5ef334ec5cd03aa87ce0da6590d234d74f8433f5556a","observation_id":"2b1d275a-60e7-4050-9467-a3eb51371a04","resolution":{"observed_at":"2026-08-10T21:01:57.677377Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-10T21:01:56.907150Z","title":"Score-based generative modeling through stochastic differential equa- tions","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.06655","last_updated":"2025-01-11T22:38:41Z","snapshot_observed_at":"2026-08-15T06:44:07.643409Z","submitted_at":"2025-01-11T22:38:41Z","title":"Personalized Preference Fine-tuning of Diffusion Models","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-10T21:01:56.907150Z"},"links":{"citing_paper":"/paper/2501.06655"},"observation_digest":"sha256:fc723e0c6ec2315dfeb346fe7c62a754d1d355ae1550f6972085a8c4ce1624ec","observation_id":"dfbbc879-061c-4f23-bac5-973bf4f9b080","resolution":{"observed_at":"2026-08-10T21:01:56.907150Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.05070","last_updated":"2024-08-20T19:14:31Z","snapshot_observed_at":"2026-08-14T17:53:51.886327Z","submitted_at":"2024-02-07T18:21:17Z","title":"A Roadmap to Pluralistic Alignment","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.05070","snapshot_observed_at":"2026-08-10T21:01:56.911101Z","title":"A Roadmap to Pluralistic Alignment","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.06655","last_updated":"2025-01-11T22:38:41Z","snapshot_observed_at":"2026-08-15T06:44:07.643409Z","submitted_at":"2025-01-11T22:38:41Z","title":"Personalized Preference Fine-tuning of Diffusion Models","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-10T21:01:56.911101Z"},"links":{"cited_paper":"/paper/2402.05070","citing_paper":"/paper/2501.06655"},"observation_digest":"sha256:150dc88c225c655b2c7652a3ab926476a3485a7aca23560f78efa0855a495589","observation_id":"aeee4f92-ef5b-4ec5-b1e3-b1c92cebc0b1","resolution":{"observed_at":"2026-08-10T21:01:56.911101Z","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":"2026-08-10T21:01:57.648537Z","title":"Diffusion model align- ment using direct preference optimization","venue":null,"work_id":"dd527fb3-a5e0-4d6c-ac3f-6e6d1c86efe9","year":2024},"citing_paper":{"arxiv_id":"2501.06655","last_updated":"2025-01-11T22:38:41Z","snapshot_observed_at":"2026-08-15T06:44:07.643409Z","submitted_at":"2025-01-11T22:38:41Z","title":"Personalized Preference Fine-tuning of Diffusion Models","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-10T21:01:56.915421Z"},"links":{"citing_paper":"/paper/2501.06655"},"observation_digest":"sha256:2a90dbba3624c10847989b2684bc6921482a3fa499d8b5d28ebd1504fb13b72e","observation_id":"222a98ed-3a63-41a6-8326-106447c762ff","resolution":{"observed_at":"2026-08-10T21:01:57.653093Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-10T21:01:57.634347Z","title":"Chain-of-thought prompting elicits reasoning in large language models, 2023","venue":null,"work_id":"66ddf7da-f9f8-4a9e-8617-3b4cdca0d20c","year":2023},"citing_paper":{"arxiv_id":"2501.06655","last_updated":"2025-01-11T22:38:41Z","snapshot_observed_at":"2026-08-15T06:44:07.643409Z","submitted_at":"2025-01-11T22:38:41Z","title":"Personalized Preference Fine-tuning of Diffusion Models","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-10T21:01:56.920112Z"},"links":{"citing_paper":"/paper/2501.06655"},"observation_digest":"sha256:9b11e01a47caf1395346d2160d16bb439b8c3af41a8919126878cd0d5e6daccf","observation_id":"299e4aa0-90f1-497c-b147-ef34c4314a61","resolution":{"observed_at":"2026-08-10T21:01:57.638711Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"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":"2026-08-10T21:01:56.924729Z","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":"2501.06655","last_updated":"2025-01-11T22:38:41Z","snapshot_observed_at":"2026-08-15T06:44:07.643409Z","submitted_at":"2025-01-11T22:38:41Z","title":"Personalized Preference Fine-tuning of Diffusion Models","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-10T21:01:56.924729Z"},"links":{"cited_paper":"/paper/2306.09341","citing_paper":"/paper/2501.06655"},"observation_digest":"sha256:8b1c827cb5ff396c932e17064023ef8e54f5282b26065527d90126d0b21110e4","observation_id":"871f6e3e-2752-41e5-8522-c5f82234f8bc","resolution":{"observed_at":"2026-08-10T21:01:56.924729Z","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":"2026-08-10T21:01:56.929711Z","title":"Human preference score: Better aligning text- to-image models with human preference","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.06655","last_updated":"2025-01-11T22:38:41Z","snapshot_observed_at":"2026-08-15T06:44:07.643409Z","submitted_at":"2025-01-11T22:38:41Z","title":"Personalized Preference Fine-tuning of Diffusion Models","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-10T21:01:56.929711Z"},"links":{"citing_paper":"/paper/2501.06655"},"observation_digest":"sha256:afc919f762e0d03659cb38476590aa39b5a92d2cdb4a0ac13f0036d47ad3edbd","observation_id":"289fad82-be6f-45fb-8ef8-6361f9dac48d","resolution":{"observed_at":"2026-08-10T21:01:56.929711Z","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":"2026-08-10T21:01:57.609068Z","title":"Imagere- ward: Learning and evaluating human preferences for text- to-image generation","venue":null,"work_id":"2bebe6bc-5662-49b6-88e3-c814091486dc","year":2024},"citing_paper":{"arxiv_id":"2501.06655","last_updated":"2025-01-11T22:38:41Z","snapshot_observed_at":"2026-08-15T06:44:07.643409Z","submitted_at":"2025-01-11T22:38:41Z","title":"Personalized Preference Fine-tuning of Diffusion Models","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-10T21:01:56.934202Z"},"links":{"citing_paper":"/paper/2501.06655"},"observation_digest":"sha256:4c0e875b13824d5d817115e4ffa85ccbb477deb8412f924fb5e26f7deb1381d6","observation_id":"6fb11692-9152-4890-b325-52296eef6e4d","resolution":{"observed_at":"2026-08-10T21:01:57.613892Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-10T21:01:57.594376Z","title":"Using human feedback to fine-tune diffusion models without any reward model","venue":null,"work_id":"7cafad58-4ac6-4f15-9103-0c1a90c05eee","year":2024},"citing_paper":{"arxiv_id":"2501.06655","last_updated":"2025-01-11T22:38:41Z","snapshot_observed_at":"2026-08-15T06:44:07.643409Z","submitted_at":"2025-01-11T22:38:41Z","title":"Personalized Preference Fine-tuning of Diffusion Models","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-10T21:01:56.938811Z"},"links":{"citing_paper":"/paper/2501.06655"},"observation_digest":"sha256:01d25f5ae8a52e518b609bf8ccb8a0d434f137f38a4bebe0f47a2fa56b2c4053","observation_id":"c0cf1e38-e6b8-4c1d-9ec1-0443a7fa99e4","resolution":{"observed_at":"2026-08-10T21:01:57.599422Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-10T21:01:56.943620Z","title":"Ip- adapter: Text compatible image prompt adapter for text-to- image diffusion models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2501.06655","last_updated":"2025-01-11T22:38:41Z","snapshot_observed_at":"2026-08-15T06:44:07.643409Z","submitted_at":"2025-01-11T22:38:41Z","title":"Personalized Preference Fine-tuning of Diffusion Models","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-10T21:01:56.943620Z"},"links":{"cited_paper":"/paper/2308.06721","citing_paper":"/paper/2501.06655"},"observation_digest":"sha256:00f51c5a835d8af8a65f0295ccb2afb1eda901074622c7496a017f9b33d1e9c4","observation_id":"1109cb91-8a6a-4f91-b330-f7dea52aa003","resolution":{"observed_at":"2026-08-10T21:01:56.943620Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.17233","last_updated":"2025-04-03T08:27:46Z","snapshot_observed_at":"2026-08-12T22:17:20.573722Z","submitted_at":"2024-10-22T17:53:34Z","title":"ICPL: Few-shot In-context Preference Learning via LLMs","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.17233","snapshot_observed_at":"2026-08-10T21:01:56.949383Z","title":"Few-shot in-context preference learning using large language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.06655","last_updated":"2025-01-11T22:38:41Z","snapshot_observed_at":"2026-08-15T06:44:07.643409Z","submitted_at":"2025-01-11T22:38:41Z","title":"Personalized Preference Fine-tuning of Diffusion Models","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-10T21:01:56.949383Z"},"links":{"cited_paper":"/paper/2410.17233","citing_paper":"/paper/2501.06655"},"observation_digest":"sha256:30c722932bb0b35cc60b39ef4efe468e8db3dd17d904a18f78cca52b49290bdc","observation_id":"077b493e-a7b1-489c-a24e-310db0ceb52b","resolution":{"observed_at":"2026-08-10T21:01:56.949383Z","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":"2026-08-10T21:01:57.577895Z","title":"Scaling autoregressive models for content-rich text-to-image generation","venue":null,"work_id":"18a9d3bc-469e-4f5c-9f15-75e2c82cf788","year":2022},"citing_paper":{"arxiv_id":"2501.06655","last_updated":"2025-01-11T22:38:41Z","snapshot_observed_at":"2026-08-15T06:44:07.643409Z","submitted_at":"2025-01-11T22:38:41Z","title":"Personalized Preference Fine-tuning of Diffusion Models","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-10T21:01:56.954001Z"},"links":{"citing_paper":"/paper/2501.06655"},"observation_digest":"sha256:07e77a2ed05abf302fe59f79e6fea8672d15155b247b30a14f32b809b402d21d","observation_id":"c891da6f-6487-4356-a079-34f42ecff92f","resolution":{"observed_at":"2026-08-10T21:01:57.582967Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-10T21:01:57.560816Z","title":"Adding conditional control to text-to-image diffusion models","venue":null,"work_id":"364a3180-2be8-4c05-8f81-64b60af99f0a","year":2023},"citing_paper":{"arxiv_id":"2501.06655","last_updated":"2025-01-11T22:38:41Z","snapshot_observed_at":"2026-08-15T06:44:07.643409Z","submitted_at":"2025-01-11T22:38:41Z","title":"Personalized Preference Fine-tuning of Diffusion Models","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-10T21:01:56.958615Z"},"links":{"citing_paper":"/paper/2501.06655"},"observation_digest":"sha256:9a5836a4c7f4783ea669032f26c0d4bb71fb5c115a3485a798bbe52516648cb8","observation_id":"6f23cb91-b839-4e24-82b9-8d3f5b50fe93","resolution":{"observed_at":"2026-08-10T21:01:57.566426Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.12244","last_updated":"2024-01-20T08:10:43Z","snapshot_observed_at":"2026-08-13T14:21:01.223732Z","submitted_at":"2024-01-20T08:10:43Z","title":"Large-scale Reinforcement Learning for Diffusion Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.12244","snapshot_observed_at":"2026-08-10T21:01:56.963375Z","title":"Large-scale reinforcement learning for diffusion models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2501.06655","last_updated":"2025-01-11T22:38:41Z","snapshot_observed_at":"2026-08-15T06:44:07.643409Z","submitted_at":"2025-01-11T22:38:41Z","title":"Personalized Preference Fine-tuning of Diffusion Models","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-10T21:01:56.963375Z"},"links":{"cited_paper":"/paper/2401.12244","citing_paper":"/paper/2501.06655"},"observation_digest":"sha256:9ad91bba381cfb01bab43bdcab0590b58a1c1a0661b5a368b47752fd534f4b06","observation_id":"ff086758-53aa-410a-abbe-2f37949eecce","resolution":{"observed_at":"2026-08-10T21:01:56.963375Z","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":"2026-08-10T21:01:57.545472Z","title":"TX t=1 log pθ(x+ t−1|x+ t ) pref(x+ t−1|x+ t ) − log pθ(x− t−1|x− t ) pref(x− t−1|xt) #! = − log σ βEx+ 1:T ,x− 1:T T Et","venue":null,"work_id":"400d29a1-7b9d-484e-ae92-03915bee030e","year":2023},"citing_paper":{"arxiv_id":"2501.06655","last_updated":"2025-01-11T22:38:41Z","snapshot_observed_at":"2026-08-15T06:44:07.643409Z","submitted_at":"2025-01-11T22:38:41Z","title":"Personalized Preference Fine-tuning of Diffusion Models","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-10T21:01:56.968088Z"},"links":{"citing_paper":"/paper/2501.06655"},"observation_digest":"sha256:f4cc375a0398c88fa3f94c6ba7bee09472dd6cafa1a124af329cec8ca23c8c5c","observation_id":"d316001c-b380-4dbb-ba79-7e425421dcbe","resolution":{"observed_at":"2026-08-10T21:01:57.550424Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-10T21:01:57.529933Z","title":null,"venue":null,"work_id":"b5d304af-472e-42e5-86e7-381b54d2e729","year":null},"citing_paper":{"arxiv_id":"2501.06655","last_updated":"2025-01-11T22:38:41Z","snapshot_observed_at":"2026-08-15T06:44:07.643409Z","submitted_at":"2025-01-11T22:38:41Z","title":"Personalized Preference Fine-tuning of Diffusion Models","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-10T21:01:56.974087Z"},"links":{"citing_paper":"/paper/2501.06655"},"observation_digest":"sha256:ca4ba2836149012306385c754a676541c0b31f5cd2f7c4b4a311ffcece4e1255","observation_id":"7fb4377c-1456-45e4-b20d-396eae00f1c5","resolution":{"observed_at":"2026-08-10T21:01:57.534823Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-10T21:01:57.514566Z","title":null,"venue":null,"work_id":"286db9d3-868c-4d04-b58e-231b21b76c67","year":null},"citing_paper":{"arxiv_id":"2501.06655","last_updated":"2025-01-11T22:38:41Z","snapshot_observed_at":"2026-08-15T06:44:07.643409Z","submitted_at":"2025-01-11T22:38:41Z","title":"Personalized Preference Fine-tuning of Diffusion Models","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-10T21:01:56.978924Z"},"links":{"citing_paper":"/paper/2501.06655"},"observation_digest":"sha256:822b79d90eb4d06fdd15e466adba957701ca4d80181fac6379d10e263bd07aed","observation_id":"f6834884-e3c5-4bd4-ad58-56520aa54465","resolution":{"observed_at":"2026-08-10T21:01:57.519451Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-10T21:01:57.497081Z","title":null,"venue":null,"work_id":"ffd071a5-0c5d-4898-95b1-8cd39776cac8","year":null},"citing_paper":{"arxiv_id":"2501.06655","last_updated":"2025-01-11T22:38:41Z","snapshot_observed_at":"2026-08-15T06:44:07.643409Z","submitted_at":"2025-01-11T22:38:41Z","title":"Personalized Preference Fine-tuning of Diffusion Models","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-10T21:01:56.983860Z"},"links":{"citing_paper":"/paper/2501.06655"},"observation_digest":"sha256:2742371aeb4aede7c651350e0230005e48f3d247bfe82b4bae72fffad0f31ae1","observation_id":"0650e29e-e9dc-4a68-ae18-18312eabdeb1","resolution":{"observed_at":"2026-08-10T21:01:57.503218Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2501.06655","last_updated":"2025-01-11T22:38:41Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-15T06:44:07.643409Z","submitted_at":"2025-01-11T22:38:41Z","title":"Personalized Preference Fine-tuning of Diffusion Models"},"reference_resolution":{"displayed":58,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":33,"verified_exact":0,"verified_fuzzy":25},"total_outbound_references":58},"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":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 58 of 58 outbound references and 1 inbound Pith citation observation for arXiv:2501.06655."}