{"as_of":"2026-08-07T05:39:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:86ce3de45716bf9bd00fe40e755fe28798fbd07e79faf495afb5b9976ec0b21e","coverage":[{"denominator":59,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":59,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T11:32:43.042017Z","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":"2026-08-06T06:34:29.942622+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2507.22604/citation-record","integrity":"/paper/2507.22604/integrity","json":"/paper/2507.22604/citation-record.json","paper":"/paper/2507.22604"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2211.01324","last_updated":"2023-03-14T00:22:14Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2022-11-02T17:43:04Z","title":"eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2211.01324","snapshot_observed_at":"2026-08-06T11:32:39.827546Z","title":"ediffi: Text-to-image diffusion models with an ensemble of expert denoisers.arXiv preprint arXiv:2211.01324, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.22604","last_updated":"2025-07-30T12:19:01Z","snapshot_observed_at":"2026-08-06T11:32:38.916172Z","submitted_at":"2025-07-30T12:19:01Z","title":"ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T11:32:39.827546Z"},"links":{"cited_paper":"/paper/2211.01324","citing_paper":"/paper/2507.22604"},"observation_digest":"sha256:338528fc40d50e57e89960a2438e2ca9ee7441b39415bae0c12c1c030d833989","observation_id":"25cbc780-269d-4c77-afc9-00fb10c257ad","resolution":{"observed_at":"2026-08-06T11:32:39.827546Z","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":"2026-08-06T11:32:43.681283Z","title":"Improving image generation with better captions","venue":null,"work_id":"b6524b61-6268-4b1d-8c07-b1b681809df8","year":2023},"citing_paper":{"arxiv_id":"2507.22604","last_updated":"2025-07-30T12:19:01Z","snapshot_observed_at":"2026-08-06T11:32:38.916172Z","submitted_at":"2025-07-30T12:19:01Z","title":"ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T11:32:39.888216Z"},"links":{"citing_paper":"/paper/2507.22604"},"observation_digest":"sha256:093282de1fbd956b6353e0ae32fb48be3a97a8e5548fec3eadbb6d4d8a52e633","observation_id":"c2f1f8cc-5364-402c-bbb0-9c4c6a5d2b24","resolution":{"observed_at":"2026-08-06T11:32:43.684332Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.13301","last_updated":"2024-01-04T19:11:25Z","snapshot_observed_at":"2026-08-01T15:43:51.739518Z","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":"2026-08-06T11:32:39.978762Z","title":"Training diffusion models with reinforce- ment learning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.22604","last_updated":"2025-07-30T12:19:01Z","snapshot_observed_at":"2026-08-06T11:32:38.916172Z","submitted_at":"2025-07-30T12:19:01Z","title":"ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T11:32:39.978762Z"},"links":{"cited_paper":"/paper/2305.13301","citing_paper":"/paper/2507.22604"},"observation_digest":"sha256:7d8e7d27f43022343ebd2f573555b0c351ed3c2215a6693e4842d8bfc0ccfc2a","observation_id":"a7b42432-0e2a-403d-81f6-691c4e6a21d5","resolution":{"observed_at":"2026-08-06T11:32:39.978762Z","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":"2026-08-06T11:32:43.671775Z","title":"Enhancing diffusion models with text-encoder reinforcement learning","venue":null,"work_id":"12304543-93c0-4af6-b55b-cc352812b134","year":null},"citing_paper":{"arxiv_id":"2507.22604","last_updated":"2025-07-30T12:19:01Z","snapshot_observed_at":"2026-08-06T11:32:38.916172Z","submitted_at":"2025-07-30T12:19:01Z","title":"ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T11:32:40.040511Z"},"links":{"citing_paper":"/paper/2507.22604"},"observation_digest":"sha256:31bc02890700839da681a85da11a955334bd19775e22b15b690277d2ef88eb4a","observation_id":"b6b8613f-8cd8-43e9-8f36-421b4ca3bdd0","resolution":{"observed_at":"2026-08-06T11:32:43.675040Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+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":"2026-08-06T11:32:43.662242Z","title":"Deep reinforcement learn- ing from human preferences","venue":null,"work_id":"902bd791-d8f3-44a7-ac70-4b32a2d08341","year":2017},"citing_paper":{"arxiv_id":"2507.22604","last_updated":"2025-07-30T12:19:01Z","snapshot_observed_at":"2026-08-06T11:32:38.916172Z","submitted_at":"2025-07-30T12:19:01Z","title":"ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T11:32:40.099892Z"},"links":{"citing_paper":"/paper/2507.22604"},"observation_digest":"sha256:a383a1c5d2be978762aae1dca277c6a25c97b3107eb0e7b591ad9cffdfd69891","observation_id":"0346f274-1f9a-494c-b17a-f123c494d230","resolution":{"observed_at":"2026-08-06T11:32:43.665536Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+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":"2026-08-06T11:32:43.652182Z","title":"Directly fine-tuning diffusion models on differentiable re- wards","venue":null,"work_id":"75dde4cf-7bc9-480b-bcef-5b4774c2a7cc","year":2024},"citing_paper":{"arxiv_id":"2507.22604","last_updated":"2025-07-30T12:19:01Z","snapshot_observed_at":"2026-08-06T11:32:38.916172Z","submitted_at":"2025-07-30T12:19:01Z","title":"ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T11:32:40.177039Z"},"links":{"citing_paper":"/paper/2507.22604"},"observation_digest":"sha256:548af5228da14cb715e87429253834e92dbfe989ee87cccceddd3cc8274bee37","observation_id":"4da82a2e-73c1-4b52-ac06-c186fda0b48f","resolution":{"observed_at":"2026-08-06T11:32:43.656224Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.15807","last_updated":"2023-09-27T17:30:19Z","snapshot_observed_at":"2026-08-02T11:54:13.342379Z","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":"2026-08-06T11:32:40.241667Z","title":"Emu: Enhanc- ing image generation models using photogenic needles in a haystack","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.22604","last_updated":"2025-07-30T12:19:01Z","snapshot_observed_at":"2026-08-06T11:32:38.916172Z","submitted_at":"2025-07-30T12:19:01Z","title":"ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T11:32:40.241667Z"},"links":{"cited_paper":"/paper/2309.15807","citing_paper":"/paper/2507.22604"},"observation_digest":"sha256:69d4499158de015f7c4902566d8d508fb271ca054440feef6edd80e6554bbb36","observation_id":"865f7677-941a-479e-b69a-653f3781c75c","resolution":{"observed_at":"2026-08-06T11:32:40.241667Z","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":"2026-08-06T11:32:43.641983Z","title":"Prdp: Proximal reward difference prediction for large-scale reward finetuning of diffusion models","venue":null,"work_id":"3fc69a10-b754-4b49-8586-57ad0650840b","year":null},"citing_paper":{"arxiv_id":"2507.22604","last_updated":"2025-07-30T12:19:01Z","snapshot_observed_at":"2026-08-06T11:32:38.916172Z","submitted_at":"2025-07-30T12:19:01Z","title":"ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T11:32:40.330966Z"},"links":{"citing_paper":"/paper/2507.22604"},"observation_digest":"sha256:f65f14c9464354083b568e223a53abbcc829c2fceae5631571b87a9cc0e7b35e","observation_id":"eeb93c00-a8f2-492e-b227-2706a4f3703b","resolution":{"observed_at":"2026-08-06T11:32:43.645466Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+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":"2026-08-06T11:32:43.630879Z","title":"Diffusion models beat gans on image synthesis","venue":null,"work_id":"a57fdde5-498d-4c14-b5ed-0c10eb48dc8a","year":2021},"citing_paper":{"arxiv_id":"2507.22604","last_updated":"2025-07-30T12:19:01Z","snapshot_observed_at":"2026-08-06T11:32:38.916172Z","submitted_at":"2025-07-30T12:19:01Z","title":"ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T11:32:40.389148Z"},"links":{"citing_paper":"/paper/2507.22604"},"observation_digest":"sha256:311a6b9b80ba9adb2735adf3754711a5a21f6f88bc977c0df2871cb7edb4e59c","observation_id":"2c1d864f-f7ab-4155-815e-8529e323f8b4","resolution":{"observed_at":"2026-08-06T11:32:43.634780Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2304.06767","last_updated":"2023-12-01T14:28:06Z","snapshot_observed_at":"2026-08-07T04:02:54.504761Z","submitted_at":"2023-04-13T18:22:40Z","title":"RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.06767","snapshot_observed_at":"2026-08-06T11:32:40.501794Z","title":"Raft: Reward ranked finetuning for generative foundation model alignment","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.22604","last_updated":"2025-07-30T12:19:01Z","snapshot_observed_at":"2026-08-06T11:32:38.916172Z","submitted_at":"2025-07-30T12:19:01Z","title":"ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T11:32:40.501794Z"},"links":{"cited_paper":"/paper/2304.06767","citing_paper":"/paper/2507.22604"},"observation_digest":"sha256:b57c3311c5ffe513edcac225b18cb7932c0136bca9fa3e3f09eabbd2867dd43b","observation_id":"78b6908b-4571-452b-80b3-3388bf9ae5bd","resolution":{"observed_at":"2026-08-06T11:32:40.501794Z","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":"2026-08-06T11:32:43.621077Z","title":"Re- inforcement learning for fine-tuning text-to-image diffusion models","venue":null,"work_id":"3f2aab2d-99a3-4210-93cc-9beaee41c363","year":2023},"citing_paper":{"arxiv_id":"2507.22604","last_updated":"2025-07-30T12:19:01Z","snapshot_observed_at":"2026-08-06T11:32:38.916172Z","submitted_at":"2025-07-30T12:19:01Z","title":"ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T11:32:40.594896Z"},"links":{"citing_paper":"/paper/2507.22604"},"observation_digest":"sha256:ed7ca6a797e9f7c6db6396254ebebd450ead838f45fa294d31809389e3b3afda","observation_id":"2d66365f-b9d6-4385-b70f-0ad6229c4890","resolution":{"observed_at":"2026-08-06T11:32:43.624389Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+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":"2026-08-06T11:32:43.610875Z","title":"Re- inforcement learning for fine-tuning text-to-image diffusion models","venue":null,"work_id":"84b43ce0-f817-4978-958f-bdbb58958b2e","year":2023},"citing_paper":{"arxiv_id":"2507.22604","last_updated":"2025-07-30T12:19:01Z","snapshot_observed_at":"2026-08-06T11:32:38.916172Z","submitted_at":"2025-07-30T12:19:01Z","title":"ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T11:32:40.687256Z"},"links":{"citing_paper":"/paper/2507.22604"},"observation_digest":"sha256:40dca974a3fd787ec5e51aa137b9f038cb2737c670fcd61ea4a462a4b7403981","observation_id":"e102b90d-e08a-4aaa-b9ed-15d73472921f","resolution":{"observed_at":"2026-08-06T11:32:43.614539Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+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":"2026-08-06T11:32:43.600614Z","title":"Policy shaping: Integrating human feedback with reinforcement learning","venue":null,"work_id":"6c739d3d-c677-4f13-bf52-ce7b67541e8f","year":2013},"citing_paper":{"arxiv_id":"2507.22604","last_updated":"2025-07-30T12:19:01Z","snapshot_observed_at":"2026-08-06T11:32:38.916172Z","submitted_at":"2025-07-30T12:19:01Z","title":"ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T11:32:40.803760Z"},"links":{"citing_paper":"/paper/2507.22604"},"observation_digest":"sha256:6d9ce008590a2c6835141edefa5a01eada7cd0b483ff7bcff57de321f4d84ab8","observation_id":"523a8d4c-b929-4bd4-850a-a07c41c1c59f","resolution":{"observed_at":"2026-08-06T11:32:43.604067Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.15111","last_updated":"2024-08-30T19:21:36Z","snapshot_observed_at":"2026-07-06T16:37:19.963994Z","submitted_at":"2023-10-23T17:20:01Z","title":"Matryoshka Diffusion Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.15111","snapshot_observed_at":"2026-08-06T11:32:40.902608Z","title":"Matryoshka diffusion models.arXiv preprint arXiv:2310.15111, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.22604","last_updated":"2025-07-30T12:19:01Z","snapshot_observed_at":"2026-08-06T11:32:38.916172Z","submitted_at":"2025-07-30T12:19:01Z","title":"ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T11:32:40.902608Z"},"links":{"cited_paper":"/paper/2310.15111","citing_paper":"/paper/2507.22604"},"observation_digest":"sha256:0070dc1bfe5eb2fdad6e5ec805d89eb018039695b3c5f492249ff7bd283ecef4","observation_id":"43c608fd-0697-46a1-9f25-16bf587391e6","resolution":{"observed_at":"2026-08-06T11:32:40.902608Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.02230","last_updated":"2024-10-03T06:36:14Z","snapshot_observed_at":"2026-08-05T03:04:56.955941Z","submitted_at":"2024-06-04T11:48:44Z","title":"I4VGen: Image as Free Stepping Stone for Text-to-Video Generation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.02230","snapshot_observed_at":"2026-08-06T11:32:40.982714Z","title":"I4vgen: Image as free stepping stone for text-to- video generation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.22604","last_updated":"2025-07-30T12:19:01Z","snapshot_observed_at":"2026-08-06T11:32:38.916172Z","submitted_at":"2025-07-30T12:19:01Z","title":"ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T11:32:40.982714Z"},"links":{"cited_paper":"/paper/2406.02230","citing_paper":"/paper/2507.22604"},"observation_digest":"sha256:1a38ab6945bbc4c2839904b356d65fd44a09aba6a888c89599c8828536f1ddc6","observation_id":"90028241-a900-423e-a271-7885a9fa2f49","resolution":{"observed_at":"2026-08-06T11:32:40.982714Z","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":"2026-08-06T11:32:43.589574Z","title":"Initno: Boosting text-to-image diffu- sion models via initial noise optimization","venue":null,"work_id":"18fd66b3-747b-4a70-a211-ce5659c52f82","year":2024},"citing_paper":{"arxiv_id":"2507.22604","last_updated":"2025-07-30T12:19:01Z","snapshot_observed_at":"2026-08-06T11:32:38.916172Z","submitted_at":"2025-07-30T12:19:01Z","title":"ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T11:32:41.041431Z"},"links":{"citing_paper":"/paper/2507.22604"},"observation_digest":"sha256:27b7c4aba2591bb18707d546bdca5adfb467c09003a067d70efb8f08d24838a6","observation_id":"44242b4b-a453-45ce-802d-faf065fa2e6a","resolution":{"observed_at":"2026-08-06T11:32:43.593412Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2207.12598","last_updated":"2022-07-26T01:42:07Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","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":"2026-08-06T11:32:41.088672Z","title":"Classifier-free diffusion guidance","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.22604","last_updated":"2025-07-30T12:19:01Z","snapshot_observed_at":"2026-08-06T11:32:38.916172Z","submitted_at":"2025-07-30T12:19:01Z","title":"ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T11:32:41.088672Z"},"links":{"cited_paper":"/paper/2207.12598","citing_paper":"/paper/2507.22604"},"observation_digest":"sha256:b6ea018561f33f8bdeaa21dcab5e317504234a4c5c52f777a7e4fbb1804c99bb","observation_id":"2031fbf8-579e-4113-971d-96fa408288ef","resolution":{"observed_at":"2026-08-06T11:32:41.088672Z","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":"2026-08-06T11:32:41.179323Z","title":"Denoising diffu- sion probabilistic models","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.22604","last_updated":"2025-07-30T12:19:01Z","snapshot_observed_at":"2026-08-06T11:32:38.916172Z","submitted_at":"2025-07-30T12:19:01Z","title":"ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T11:32:41.179323Z"},"links":{"citing_paper":"/paper/2507.22604"},"observation_digest":"sha256:4cc6a6b3249f1a0cac79622390e912764ddcda57f65514d9eee983534a35b556","observation_id":"229f86d2-3386-43f1-ba52-3e4781710952","resolution":{"observed_at":"2026-08-06T11:32:41.179323Z","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":"2026-08-06T11:32:43.574151Z","title":"Lora: Low-rank adaptation of large language models","venue":null,"work_id":"c2ce323d-db7d-44bb-b52d-93e7bfbd6597","year":2022},"citing_paper":{"arxiv_id":"2507.22604","last_updated":"2025-07-30T12:19:01Z","snapshot_observed_at":"2026-08-06T11:32:38.916172Z","submitted_at":"2025-07-30T12:19:01Z","title":"ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T11:32:41.257372Z"},"links":{"citing_paper":"/paper/2507.22604"},"observation_digest":"sha256:10e1fba8f34309cc1e7dfd2f4ae1520b5259d4691795761d3f047b19005155da","observation_id":"8616d157-f3ff-463d-824c-6f918f845753","resolution":{"observed_at":"2026-08-06T11:32:43.577274Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+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":"2026-08-06T11:32:41.327159Z","title":"T2i-compbench: A comprehensive benchmark for open-world compositional text-to-image generation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.22604","last_updated":"2025-07-30T12:19:01Z","snapshot_observed_at":"2026-08-06T11:32:38.916172Z","submitted_at":"2025-07-30T12:19:01Z","title":"ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T11:32:41.327159Z"},"links":{"citing_paper":"/paper/2507.22604"},"observation_digest":"sha256:5d1fe7559b34fb9a13af93e3d64214b0564a6c1f83c5d2e35db4808693576854","observation_id":"8ee13c69-5fd7-4a62-96ac-6e48a7cf4f9a","resolution":{"observed_at":"2026-08-06T11:32:41.327159Z","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":"2026-08-06T11:32:43.559417Z","title":"Distilling diffusion models into condi- tional gans","venue":null,"work_id":"64cbd5e5-6b80-409f-b910-c3ac37b318d4","year":2024},"citing_paper":{"arxiv_id":"2507.22604","last_updated":"2025-07-30T12:19:01Z","snapshot_observed_at":"2026-08-06T11:32:38.916172Z","submitted_at":"2025-07-30T12:19:01Z","title":"ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T11:32:41.352657Z"},"links":{"citing_paper":"/paper/2507.22604"},"observation_digest":"sha256:e984f97421d2be109a8c809b21663267c68157ef2029ed623a0e018a080d999e","observation_id":"e37d7e36-0909-4601-853a-472054a9f789","resolution":{"observed_at":"2026-08-06T11:32:43.562327Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+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":"2026-08-06T11:32:43.550735Z","title":"Elucidating the design space of diffusion-based generative models","venue":null,"work_id":"1461d960-4b12-42ca-b735-7298f82f4221","year":2022},"citing_paper":{"arxiv_id":"2507.22604","last_updated":"2025-07-30T12:19:01Z","snapshot_observed_at":"2026-08-06T11:32:38.916172Z","submitted_at":"2025-07-30T12:19:01Z","title":"ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T11:32:41.441247Z"},"links":{"citing_paper":"/paper/2507.22604"},"observation_digest":"sha256:6860336cb0948ea676696c274615e50f215819c9e8de923d6c3dcbca7a771972","observation_id":"261aef29-6342-49d6-b8ad-595e8c094310","resolution":{"observed_at":"2026-08-06T11:32:43.553697Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.02279","last_updated":"2024-03-30T06:29:48Z","snapshot_observed_at":"2026-07-06T16:27:18.829052Z","submitted_at":"2023-10-01T05:07:17Z","title":"Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.02279","snapshot_observed_at":"2026-08-06T11:32:41.521115Z","title":"Consistency trajectory mod- els: Learning probability flow ode trajectory of diffusion","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.22604","last_updated":"2025-07-30T12:19:01Z","snapshot_observed_at":"2026-08-06T11:32:38.916172Z","submitted_at":"2025-07-30T12:19:01Z","title":"ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T11:32:41.521115Z"},"links":{"cited_paper":"/paper/2310.02279","citing_paper":"/paper/2507.22604"},"observation_digest":"sha256:5f575a9eac8ab6edb041a4083c21e17072a16e400956000afa2440821c3e2f2b","observation_id":"8b6e5a40-a53f-4e7c-a407-9f5ca1dc9b53","resolution":{"observed_at":"2026-08-06T11:32:41.521115Z","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":"2026-08-06T11:32:43.541125Z","title":"Pick-a-pic: An open dataset of user preferences for text-to-image generation","venue":null,"work_id":"03992990-24a1-4c01-a825-ee052aafc1de","year":2023},"citing_paper":{"arxiv_id":"2507.22604","last_updated":"2025-07-30T12:19:01Z","snapshot_observed_at":"2026-08-06T11:32:38.916172Z","submitted_at":"2025-07-30T12:19:01Z","title":"ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T11:32:41.590785Z"},"links":{"citing_paper":"/paper/2507.22604"},"observation_digest":"sha256:629ac3f734ff489c0e20f02ea822479acbb811aa922d0760bbcbc0ba370ca006","observation_id":"919ceb88-56c5-429e-8fc7-599b142fd77e","resolution":{"observed_at":"2026-08-06T11:32:43.544701Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+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":"2026-08-06T11:32:41.627848Z","title":"Aligning text- to-image models using human feedback","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.22604","last_updated":"2025-07-30T12:19:01Z","snapshot_observed_at":"2026-08-06T11:32:38.916172Z","submitted_at":"2025-07-30T12:19:01Z","title":"ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T11:32:41.627848Z"},"links":{"cited_paper":"/paper/2302.12192","citing_paper":"/paper/2507.22604"},"observation_digest":"sha256:b2adb9cfc65f6720e89da1e47124eb89275d021cf85cd71a52c71ff32369fdf9","observation_id":"e7ff8769-1b27-43a3-bfed-01b5d71ea8e5","resolution":{"observed_at":"2026-08-06T11:32:41.627848Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.11027","last_updated":"2024-10-07T18:47:47Z","snapshot_observed_at":"2026-08-06T18:36:51.220617Z","submitted_at":"2024-03-16T22:14:56Z","title":"Reward Guided Latent Consistency Distillation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.11027","snapshot_observed_at":"2026-08-06T11:32:41.740717Z","title":"Reward guided latent consistency distillation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.22604","last_updated":"2025-07-30T12:19:01Z","snapshot_observed_at":"2026-08-06T11:32:38.916172Z","submitted_at":"2025-07-30T12:19:01Z","title":"ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T11:32:41.740717Z"},"links":{"cited_paper":"/paper/2403.11027","citing_paper":"/paper/2507.22604"},"observation_digest":"sha256:99bd7f3cea2686c4492acb1f95ad325434ee16f1ab1c21076de7780b797e5359","observation_id":"17a06130-4c41-4fea-9309-83de37721bb3","resolution":{"observed_at":"2026-08-06T11:32:41.740717Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.18750","last_updated":"2024-10-11T07:50:49Z","snapshot_observed_at":"2026-07-06T18:21:44.232687Z","submitted_at":"2024-05-29T04:26:17Z","title":"T2V-Turbo: Breaking the Quality Bottleneck of Video Consistency Model with Mixed Reward Feedback","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.18750","snapshot_observed_at":"2026-08-06T11:32:41.788635Z","title":"T2v- turbo: Breaking the quality bottleneck of video consis- tency model with mixed reward feedback","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.22604","last_updated":"2025-07-30T12:19:01Z","snapshot_observed_at":"2026-08-06T11:32:38.916172Z","submitted_at":"2025-07-30T12:19:01Z","title":"ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T11:32:41.788635Z"},"links":{"cited_paper":"/paper/2405.18750","citing_paper":"/paper/2507.22604"},"observation_digest":"sha256:6adfd8fc99d700981943acf29c6446262e4a5fbbd818bba1cf2d27a5147fb691","observation_id":"07ef3d34-9444-4738-a6f1-6d3f3f07fe95","resolution":{"observed_at":"2026-08-06T11:32:41.788635Z","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":"2026-08-06T11:32:41.810872Z","title":"T2v- turbo-v2: Enhancing video generation model post-training through data, reward, and conditional guidance design.arXiv preprint arXiv:2410.05677, 2024","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.22604","last_updated":"2025-07-30T12:19:01Z","snapshot_observed_at":"2026-08-06T11:32:38.916172Z","submitted_at":"2025-07-30T12:19:01Z","title":"ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T11:32:41.810872Z"},"links":{"citing_paper":"/paper/2507.22604"},"observation_digest":"sha256:cb4725b27a82cfd50f6109397ef704e347de279610f7a805962d155a89ab22c8","observation_id":"b179a1dd-45bd-406b-9afb-39a360bfd541","resolution":{"observed_at":"2026-08-06T11:32:41.810872Z","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":"2026-08-06T11:32:43.531509Z","title":"Aligning diffusion mod- els by optimizing human utility","venue":null,"work_id":"df3f98d4-ec93-45be-879f-c0479c04068e","year":2024},"citing_paper":{"arxiv_id":"2507.22604","last_updated":"2025-07-30T12:19:01Z","snapshot_observed_at":"2026-08-06T11:32:38.916172Z","submitted_at":"2025-07-30T12:19:01Z","title":"ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T11:32:41.872860Z"},"links":{"citing_paper":"/paper/2507.22604"},"observation_digest":"sha256:b52bc5379a4520713d7f6aea81cb2f43f1804026bb701067e3ad3f303e33134a","observation_id":"bb68dcf6-65f8-4452-85de-9aa11daedf9c","resolution":{"observed_at":"2026-08-06T11:32:43.534686Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.04314","last_updated":"2025-03-25T17:06:27Z","snapshot_observed_at":"2026-08-06T20:07:18.681767Z","submitted_at":"2024-06-06T17:57:09Z","title":"Aesthetic Post-Training Diffusion Models from Generic Preferences with Step-by-step Preference Optimization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.04314","snapshot_observed_at":"2026-08-06T11:32:41.949449Z","title":"Step-aware prefer- ence optimization: Aligning preference with denoising per- formance at each step","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.22604","last_updated":"2025-07-30T12:19:01Z","snapshot_observed_at":"2026-08-06T11:32:38.916172Z","submitted_at":"2025-07-30T12:19:01Z","title":"ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T11:32:41.949449Z"},"links":{"cited_paper":"/paper/2406.04314","citing_paper":"/paper/2507.22604"},"observation_digest":"sha256:6178ce13ad9f0948d59a0178715d1be68ec2ede7867f63e527a997ff44690abb","observation_id":"f277eed4-bd71-49b1-b5b2-b9c8abba75c7","resolution":{"observed_at":"2026-08-06T11:32:41.949449Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.13929","last_updated":"2024-03-02T09:09:32Z","snapshot_observed_at":"2026-07-31T02:56:13.600400Z","submitted_at":"2024-02-21T16:51:05Z","title":"SDXL-Lightning: Progressive Adversarial Diffusion Distillation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.13929","snapshot_observed_at":"2026-08-06T11:32:42.033338Z","title":"Sdxl- lightning: Progressive adversarial diffusion distillation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.22604","last_updated":"2025-07-30T12:19:01Z","snapshot_observed_at":"2026-08-06T11:32:38.916172Z","submitted_at":"2025-07-30T12:19:01Z","title":"ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T11:32:42.033338Z"},"links":{"cited_paper":"/paper/2402.13929","citing_paper":"/paper/2507.22604"},"observation_digest":"sha256:0edc6d45f0d97c333d21d11cdeb318d4ea0b782503e10db8e6856348b4915161","observation_id":"eb2563d1-687b-40c0-94e0-702bff7999db","resolution":{"observed_at":"2026-08-06T11:32:42.033338Z","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":"2026-08-06T11:32:43.521809Z","title":"Improved denoising diffusion probabilistic models","venue":null,"work_id":"ac7c4caf-a6a8-40fe-873c-0b46a2023df2","year":2021},"citing_paper":{"arxiv_id":"2507.22604","last_updated":"2025-07-30T12:19:01Z","snapshot_observed_at":"2026-08-06T11:32:38.916172Z","submitted_at":"2025-07-30T12:19:01Z","title":"ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T11:32:42.127897Z"},"links":{"citing_paper":"/paper/2507.22604"},"observation_digest":"sha256:3b237c33c252429f0d49d3e158753867b9d153407315d2ba685a989c151eb509","observation_id":"5ff8a7eb-d65c-456f-ab9c-1b1936dcf79a","resolution":{"observed_at":"2026-08-06T11:32:43.525362Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+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":"2026-08-06T11:32:43.511690Z","title":"Training lan- guage models to follow instructions with human feedback","venue":null,"work_id":"e6eae62a-4ea1-4b2a-84c6-4ec61364d935","year":2022},"citing_paper":{"arxiv_id":"2507.22604","last_updated":"2025-07-30T12:19:01Z","snapshot_observed_at":"2026-08-06T11:32:38.916172Z","submitted_at":"2025-07-30T12:19:01Z","title":"ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T11:32:42.196458Z"},"links":{"citing_paper":"/paper/2507.22604"},"observation_digest":"sha256:af5ba284f2f5241bde1cb7c0a0f50c9bbbe8d4affb89adb87fed24030dcb6c7c","observation_id":"c516e9ef-c8bd-4b1f-aa5c-59913d658c38","resolution":{"observed_at":"2026-08-06T11:32:43.515629Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"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":"2026-08-06T11:32:42.332939Z","title":"Aligning text-to-image diffusion models with reward backpropagation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.22604","last_updated":"2025-07-30T12:19:01Z","snapshot_observed_at":"2026-08-06T11:32:38.916172Z","submitted_at":"2025-07-30T12:19:01Z","title":"ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T11:32:42.332939Z"},"links":{"cited_paper":"/paper/2310.03739","citing_paper":"/paper/2507.22604"},"observation_digest":"sha256:c32b32b70ed8e442fa2c545de724deeb8e88570596cebac707bf0180ae25e76b","observation_id":"7e5c2d48-2831-46f9-941b-078d87e9a147","resolution":{"observed_at":"2026-08-06T11:32:42.332939Z","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":"2026-08-06T11:32:43.502377Z","title":"Learn- ing transferable visual models from natural language super- vision","venue":null,"work_id":"6bd54bd4-744d-48b0-baeb-faa01c609989","year":2021},"citing_paper":{"arxiv_id":"2507.22604","last_updated":"2025-07-30T12:19:01Z","snapshot_observed_at":"2026-08-06T11:32:38.916172Z","submitted_at":"2025-07-30T12:19:01Z","title":"ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T11:32:42.405313Z"},"links":{"citing_paper":"/paper/2507.22604"},"observation_digest":"sha256:06929bb306daa84fb703504829515584569bb7cd54762330c9d444237039254d","observation_id":"233eac4c-7592-4fc9-bba0-16c5b1df4f88","resolution":{"observed_at":"2026-08-06T11:32:43.505533Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+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":"2026-08-06T11:32:43.491995Z","title":"Direct preference optimization: Your language model is secretly a reward model","venue":null,"work_id":"0291ca2c-e40b-4800-963d-65ca5edffbc1","year":2023},"citing_paper":{"arxiv_id":"2507.22604","last_updated":"2025-07-30T12:19:01Z","snapshot_observed_at":"2026-08-06T11:32:38.916172Z","submitted_at":"2025-07-30T12:19:01Z","title":"ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T11:32:42.517743Z"},"links":{"citing_paper":"/paper/2507.22604"},"observation_digest":"sha256:faedd666d4e882f3705492316ae59bd99299fb29aa7c160a876b56c0701f232a","observation_id":"df07502c-7e7a-46db-b902-a4993d098ec9","resolution":{"observed_at":"2026-08-06T11:32:43.495587Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.13686","last_updated":"2024-11-04T13:24:18Z","snapshot_observed_at":"2026-08-04T05:24:37.569197Z","submitted_at":"2024-04-21T15:16:05Z","title":"Hyper-SD: Trajectory Segmented Consistency Model for Efficient Image Synthesis","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.13686","snapshot_observed_at":"2026-08-06T11:32:42.637511Z","title":"Hyper-sd: Trajectory segmented consistency model for efficient image synthesis","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.22604","last_updated":"2025-07-30T12:19:01Z","snapshot_observed_at":"2026-08-06T11:32:38.916172Z","submitted_at":"2025-07-30T12:19:01Z","title":"ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T11:32:42.637511Z"},"links":{"cited_paper":"/paper/2404.13686","citing_paper":"/paper/2507.22604"},"observation_digest":"sha256:ab3078f40e34a74956607d987cf8b57590fa2e10c89b21516bc6c691ea8af192","observation_id":"43271464-f816-413c-8fa3-08e3100a3f34","resolution":{"observed_at":"2026-08-06T11:32:42.637511Z","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":"2026-08-06T11:32:43.481331Z","title":"High-resolution image syn- thesis with latent diffusion models","venue":null,"work_id":"b27cc194-f137-4225-b112-822eb4db2bb2","year":2022},"citing_paper":{"arxiv_id":"2507.22604","last_updated":"2025-07-30T12:19:01Z","snapshot_observed_at":"2026-08-06T11:32:38.916172Z","submitted_at":"2025-07-30T12:19:01Z","title":"ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T11:32:42.738454Z"},"links":{"citing_paper":"/paper/2507.22604"},"observation_digest":"sha256:df9ae3147602474f5f1b03b3e11e3daf516d6c2a397903a055fefb9406e31daf","observation_id":"c99a38ce-873f-4eef-a5e1-5db250ce477f","resolution":{"observed_at":"2026-08-06T11:32:43.484757Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+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":"2026-08-06T11:32:43.471643Z","title":"Progressive distillation for fast sampling of diffusion models","venue":null,"work_id":"4a05b0ed-97f2-4006-bb9d-b0895c0b2d4a","year":2022},"citing_paper":{"arxiv_id":"2507.22604","last_updated":"2025-07-30T12:19:01Z","snapshot_observed_at":"2026-08-06T11:32:38.916172Z","submitted_at":"2025-07-30T12:19:01Z","title":"ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T11:32:42.789265Z"},"links":{"citing_paper":"/paper/2507.22604"},"observation_digest":"sha256:7289cb7d9acdd5295badf5fa828b18187c1d4ad5808529e71a40b4b813a3a32f","observation_id":"1fde45e0-7978-44bc-8dca-02e92463b17c","resolution":{"observed_at":"2026-08-06T11:32:43.474767Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.12015","last_updated":"2024-03-18T17:51:43Z","snapshot_observed_at":"2026-08-06T10:10:20.333853Z","submitted_at":"2024-03-18T17:51:43Z","title":"Fast High-Resolution Image Synthesis with Latent Adversarial Diffusion Distillation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.12015","snapshot_observed_at":"2026-08-06T11:32:42.881489Z","title":"Fast high- resolution image synthesis with latent adversarial diffusion distillation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.22604","last_updated":"2025-07-30T12:19:01Z","snapshot_observed_at":"2026-08-06T11:32:38.916172Z","submitted_at":"2025-07-30T12:19:01Z","title":"ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-06T11:32:42.881489Z"},"links":{"cited_paper":"/paper/2403.12015","citing_paper":"/paper/2507.22604"},"observation_digest":"sha256:64262fa2df51c1775d6d72d32f6d7c9f4233e60c664d933425b2eb39e2c5eeb2","observation_id":"c2630b46-6348-4a3a-8ff0-c975fe614cf0","resolution":{"observed_at":"2026-08-06T11:32:42.881489Z","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":"2026-08-06T11:32:43.462396Z","title":"Adversarial diffusion distillation","venue":null,"work_id":"929e5cde-d69d-44f9-89a5-aaa55bbad46f","year":2024},"citing_paper":{"arxiv_id":"2507.22604","last_updated":"2025-07-30T12:19:01Z","snapshot_observed_at":"2026-08-06T11:32:38.916172Z","submitted_at":"2025-07-30T12:19:01Z","title":"ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-06T11:32:42.949430Z"},"links":{"citing_paper":"/paper/2507.22604"},"observation_digest":"sha256:2331001512509c37953f923ff61bb04a41ef4c88fd942236940e87cf379bf9a2","observation_id":"30693c5b-509d-4a56-bd04-70cb140f0f94","resolution":{"observed_at":"2026-08-06T11:32:43.465530Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+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":"2026-08-06T11:32:43.453102Z","title":"Laoin aes- thetic predictor","venue":null,"work_id":"ddde45f5-76a5-4482-9f19-e122a8759c48","year":2022},"citing_paper":{"arxiv_id":"2507.22604","last_updated":"2025-07-30T12:19:01Z","snapshot_observed_at":"2026-08-06T11:32:38.916172Z","submitted_at":"2025-07-30T12:19:01Z","title":"ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-06T11:32:42.990133Z"},"links":{"citing_paper":"/paper/2507.22604"},"observation_digest":"sha256:f7a4b4dbe8cf864e95439918639c4528cabea944264cec75559effae607b9c6e","observation_id":"523df69a-7ad3-4927-ab52-2f6eedcac486","resolution":{"observed_at":"2026-08-06T11:32:43.456014Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.16656","last_updated":"2023-10-25T14:10:08Z","snapshot_observed_at":"2026-08-07T02:32:04.042812Z","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":"2026-08-06T11:32:42.993236Z","title":"A picture is worth a thousand words: Principled recaptioning improves image generation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.22604","last_updated":"2025-07-30T12:19:01Z","snapshot_observed_at":"2026-08-06T11:32:38.916172Z","submitted_at":"2025-07-30T12:19:01Z","title":"ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-06T11:32:42.993236Z"},"links":{"cited_paper":"/paper/2310.16656","citing_paper":"/paper/2507.22604"},"observation_digest":"sha256:c315301afd9b1aa0e6e75b33cfd8c2660171b7914b3669deba9093df482b17a3","observation_id":"dbd550c2-0619-40a5-9825-138f9947fe8f","resolution":{"observed_at":"2026-08-06T11:32:42.993236Z","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":"2026-08-06T11:32:43.443804Z","title":"Denois- ing diffusion implicit models","venue":null,"work_id":"6d045e8f-34a1-4c0b-837f-063091665092","year":2021},"citing_paper":{"arxiv_id":"2507.22604","last_updated":"2025-07-30T12:19:01Z","snapshot_observed_at":"2026-08-06T11:32:38.916172Z","submitted_at":"2025-07-30T12:19:01Z","title":"ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-06T11:32:42.996734Z"},"links":{"citing_paper":"/paper/2507.22604"},"observation_digest":"sha256:1d9bbea031d551bc64420163bac06c8058e698fc0b0637fc233b65f28d03628b","observation_id":"5c429a3e-0217-44b1-a135-6be6acdf606c","resolution":{"observed_at":"2026-08-06T11:32:43.446844Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+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":"2026-08-06T11:32:43.000019Z","title":"Score-based generative modeling through stochastic differential equa- tions","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.22604","last_updated":"2025-07-30T12:19:01Z","snapshot_observed_at":"2026-08-06T11:32:38.916172Z","submitted_at":"2025-07-30T12:19:01Z","title":"ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-06T11:32:43.000019Z"},"links":{"citing_paper":"/paper/2507.22604"},"observation_digest":"sha256:23982b36a3f25a676e939fb8c23e4655c98fe58c09390695bd826f2b7ebfdc62","observation_id":"cc57130b-9c09-49ec-ba91-9223f726e7cc","resolution":{"observed_at":"2026-08-06T11:32:43.000019Z","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":"2026-08-06T11:32:43.428457Z","title":"Consistency models","venue":null,"work_id":"e0a5b877-1750-465e-902e-fa12d2616bd5","year":2023},"citing_paper":{"arxiv_id":"2507.22604","last_updated":"2025-07-30T12:19:01Z","snapshot_observed_at":"2026-08-06T11:32:38.916172Z","submitted_at":"2025-07-30T12:19:01Z","title":"ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-06T11:32:43.003738Z"},"links":{"citing_paper":"/paper/2507.22604"},"observation_digest":"sha256:5a092d1a92ab42a43ff0dfeac57285d9833c46af75f18e2161b57fb21494b869","observation_id":"87b22598-2518-45d8-b13c-f9a42126bc2e","resolution":{"observed_at":"2026-08-06T11:32:43.431396Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+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":"2026-08-06T11:32:43.418864Z","title":"Learning to summarize with human feed- back","venue":null,"work_id":"c7efe976-1dda-44f0-a0a9-02e0608cf961","year":2020},"citing_paper":{"arxiv_id":"2507.22604","last_updated":"2025-07-30T12:19:01Z","snapshot_observed_at":"2026-08-06T11:32:38.916172Z","submitted_at":"2025-07-30T12:19:01Z","title":"ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-06T11:32:43.006780Z"},"links":{"citing_paper":"/paper/2507.22604"},"observation_digest":"sha256:14640435abac7d305bbfe209d1d8ab7e9c3c0a99f8ab81edbdb8822c89917109","observation_id":"b8f2c748-b4c8-4f32-9d7f-d25c46aa1e75","resolution":{"observed_at":"2026-08-06T11:32:43.421960Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+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":"2026-08-06T11:32:43.408873Z","title":"Diffusion model align- ment using direct preference optimization","venue":null,"work_id":"8fad8f42-520c-4d1d-9ae5-dd695080f8f7","year":2024},"citing_paper":{"arxiv_id":"2507.22604","last_updated":"2025-07-30T12:19:01Z","snapshot_observed_at":"2026-08-06T11:32:38.916172Z","submitted_at":"2025-07-30T12:19:01Z","title":"ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-06T11:32:43.009674Z"},"links":{"citing_paper":"/paper/2507.22604"},"observation_digest":"sha256:9d1bb221a27bed6b2166c69db1a2d9d8fa747ab3e0980c9fe0e5f904ca3f1686","observation_id":"51c4f1c2-4711-4a17-bd8d-f4b43c001f97","resolution":{"observed_at":"2026-08-06T11:32:43.412138Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.09341","last_updated":"2023-09-25T08:19:23Z","snapshot_observed_at":"2026-07-06T15:43:07.989730Z","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":"2026-08-06T11:32:43.012513Z","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":"2507.22604","last_updated":"2025-07-30T12:19:01Z","snapshot_observed_at":"2026-08-06T11:32:38.916172Z","submitted_at":"2025-07-30T12:19:01Z","title":"ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-06T11:32:43.012513Z"},"links":{"cited_paper":"/paper/2306.09341","citing_paper":"/paper/2507.22604"},"observation_digest":"sha256:1f6b4b66f5354e530f52e58a6d511aa842c8019de95640e45be9f7702c7f2911","observation_id":"99bbd271-ba81-4177-984c-13ecf11a9bb1","resolution":{"observed_at":"2026-08-06T11:32:43.012513Z","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":"2026-08-06T11:32:43.399851Z","title":"Human preference score: Better aligning text-to- image models with human preference","venue":null,"work_id":"897817b0-e728-462e-b82a-d9be70a1870c","year":2023},"citing_paper":{"arxiv_id":"2507.22604","last_updated":"2025-07-30T12:19:01Z","snapshot_observed_at":"2026-08-06T11:32:38.916172Z","submitted_at":"2025-07-30T12:19:01Z","title":"ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-06T11:32:43.016250Z"},"links":{"citing_paper":"/paper/2507.22604"},"observation_digest":"sha256:2fc921c25b24997e4e51b76c2b535a9d187758bcc7d48756806d03f8c4a743ed","observation_id":"8c1114ed-24b9-4407-becf-1cfbc77fcc10","resolution":{"observed_at":"2026-08-06T11:32:43.402812Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+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":"2026-08-06T11:32:43.390234Z","title":"Deep reward supervisions for tuning text-to-image diffusion models","venue":null,"work_id":"a1c73123-1c4f-46ae-bf57-74bdd7c613a1","year":2024},"citing_paper":{"arxiv_id":"2507.22604","last_updated":"2025-07-30T12:19:01Z","snapshot_observed_at":"2026-08-06T11:32:38.916172Z","submitted_at":"2025-07-30T12:19:01Z","title":"ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-06T11:32:43.019078Z"},"links":{"citing_paper":"/paper/2507.22604"},"observation_digest":"sha256:48c11a4d8494a550114b856d10e48b2d660a98296128754e9fad9aaafbdb34c1","observation_id":"e06b552b-3a31-4dc9-bbea-48d295720320","resolution":{"observed_at":"2026-08-06T11:32:43.393293Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+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":"2026-08-06T11:32:43.380327Z","title":"Imagere- ward: Learning and evaluating human preferences for text- to-image generation","venue":null,"work_id":"90cc3dda-5e2a-482e-b63c-44936612ddfa","year":2023},"citing_paper":{"arxiv_id":"2507.22604","last_updated":"2025-07-30T12:19:01Z","snapshot_observed_at":"2026-08-06T11:32:38.916172Z","submitted_at":"2025-07-30T12:19:01Z","title":"ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-06T11:32:43.021975Z"},"links":{"citing_paper":"/paper/2507.22604"},"observation_digest":"sha256:1a468824373f40bc59da149b173622b72d11e572f040791d00be64e282962fc8","observation_id":"ea72b0f4-9254-4442-bdba-df43ddb69120","resolution":{"observed_at":"2026-08-06T11:32:43.383376Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+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":"2026-08-06T11:32:43.371394Z","title":"Raphael: Text-to-image generation via large mixture of diffusion paths","venue":null,"work_id":"6711f083-e7cd-4bd9-9ef8-0a52367484a3","year":null},"citing_paper":{"arxiv_id":"2507.22604","last_updated":"2025-07-30T12:19:01Z","snapshot_observed_at":"2026-08-06T11:32:38.916172Z","submitted_at":"2025-07-30T12:19:01Z","title":"ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-06T11:32:43.024781Z"},"links":{"citing_paper":"/paper/2507.22604"},"observation_digest":"sha256:732e641c85eb5f8364d15064847a9ac00e5cce3f610c2ae544e2ca122937e008","observation_id":"45cc5dd3-f16e-4f4c-b041-08de355b4aec","resolution":{"observed_at":"2026-08-06T11:32:43.374273Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+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":"2026-08-06T11:32:43.361840Z","title":"Using human feedback to fine-tune diffusion models without any reward model","venue":null,"work_id":"20c997ae-932f-41e3-8881-6367d4b592ad","year":2024},"citing_paper":{"arxiv_id":"2507.22604","last_updated":"2025-07-30T12:19:01Z","snapshot_observed_at":"2026-08-06T11:32:38.916172Z","submitted_at":"2025-07-30T12:19:01Z","title":"ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-06T11:32:43.027721Z"},"links":{"citing_paper":"/paper/2507.22604"},"observation_digest":"sha256:b05e0048be559b871f3245475a3510126a7f05a880544b098c2615541fd4ab14","observation_id":"ba402e0d-a5ac-4a1b-8671-46f19cb3604d","resolution":{"observed_at":"2026-08-06T11:32:43.365306Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.08265","last_updated":"2024-05-12T21:02:59Z","snapshot_observed_at":"2026-08-03T17:53:31.825440Z","submitted_at":"2024-02-13T07:37:24Z","title":"A Dense Reward View on Aligning Text-to-Image Diffusion with Preference","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.08265","snapshot_observed_at":"2026-08-06T11:32:43.030529Z","title":"A dense reward view on aligning text-to-image diffusion with prefer- ence","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.22604","last_updated":"2025-07-30T12:19:01Z","snapshot_observed_at":"2026-08-06T11:32:38.916172Z","submitted_at":"2025-07-30T12:19:01Z","title":"ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-06T11:32:43.030529Z"},"links":{"cited_paper":"/paper/2402.08265","citing_paper":"/paper/2507.22604"},"observation_digest":"sha256:e007ccd0c7ed879b74de817357f0f5ff0cf9bc2833cd267085c5c115ebab80d6","observation_id":"63e922f5-96b5-46a3-a6ff-24466acb8031","resolution":{"observed_at":"2026-08-06T11:32:43.030529Z","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":"2026-08-06T11:32:43.351974Z","title":"One-step diffusion with distribution matching distillation","venue":null,"work_id":"9b16c853-78cb-4640-9fad-7c883a7d62d5","year":2024},"citing_paper":{"arxiv_id":"2507.22604","last_updated":"2025-07-30T12:19:01Z","snapshot_observed_at":"2026-08-06T11:32:38.916172Z","submitted_at":"2025-07-30T12:19:01Z","title":"ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-06T11:32:43.033600Z"},"links":{"citing_paper":"/paper/2507.22604"},"observation_digest":"sha256:e2d9d49519aa727acd82c18335805ff6ab67066cb0f94ff264b649d4d679835c","observation_id":"e93f01fd-97cc-46ab-94e8-948efde05d08","resolution":{"observed_at":"2026-08-06T11:32:43.355625Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+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":"2026-08-06T11:32:43.036357Z","title":"Adding conditional control to text-to-image diffusion models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.22604","last_updated":"2025-07-30T12:19:01Z","snapshot_observed_at":"2026-08-06T11:32:38.916172Z","submitted_at":"2025-07-30T12:19:01Z","title":"ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-06T11:32:43.036357Z"},"links":{"citing_paper":"/paper/2507.22604"},"observation_digest":"sha256:b0e88ea9ea08d3d8cb7b3324f5edd36dd32fcf68500bebf75b84e4de7aa52d07","observation_id":"504a4065-4aec-41fa-acca-877216104575","resolution":{"observed_at":"2026-08-06T11:32:43.036357Z","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":"2026-08-06T11:32:43.334389Z","title":"Large-scale reinforcement learning for diffusion models","venue":null,"work_id":"027bef0c-a412-43ed-ad98-5bb6d4640cae","year":2024},"citing_paper":{"arxiv_id":"2507.22604","last_updated":"2025-07-30T12:19:01Z","snapshot_observed_at":"2026-08-06T11:32:38.916172Z","submitted_at":"2025-07-30T12:19:01Z","title":"ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-06T11:32:43.039168Z"},"links":{"citing_paper":"/paper/2507.22604"},"observation_digest":"sha256:32eb445fb576b72fb4d5b3c3cc69e06519f35aa03523487b7b3407a4b40e9fd9","observation_id":"e7b8362d-407e-4037-af34-0cedc226ff6f","resolution":{"observed_at":"2026-08-06T11:32:43.339279Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1909.08593","last_updated":"2020-01-08T23:02:36Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2019-09-18T17:33:39Z","title":"Fine-Tuning Language Models from Human Preferences","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1909.08593","snapshot_observed_at":"2026-08-06T11:32:43.042017Z","title":"Fine-tuning language models from human preferences","venue":null,"work_id":null,"year":1909},"citing_paper":{"arxiv_id":"2507.22604","last_updated":"2025-07-30T12:19:01Z","snapshot_observed_at":"2026-08-06T11:32:38.916172Z","submitted_at":"2025-07-30T12:19:01Z","title":"ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-06T11:32:43.042017Z"},"links":{"cited_paper":"/paper/1909.08593","citing_paper":"/paper/2507.22604"},"observation_digest":"sha256:28f42d9cfb9b5c6750d01d14f2771908fd8f1208bbdd40fbf8e676a52b8aad62","observation_id":"e9373621-7776-4932-a4b3-af79a8b72577","resolution":{"observed_at":"2026-08-06T11:32:43.042017Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2507.22604","last_updated":"2025-07-30T12:19:01Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-06T11:32:38.916172Z","submitted_at":"2025-07-30T12:19:01Z","title":"ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning"},"reference_resolution":{"displayed":59,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":25,"verified_exact":0,"verified_fuzzy":34},"total_outbound_references":59},"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":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 59 of 59 outbound references and 0 inbound Pith citation observations for arXiv:2507.22604."}