{"as_of":"2026-08-07T23:34:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:2431f07356087c6cc97c69d5e6c37efccacc7dfab75d9dc1c3d8ca0cb3c571e8","coverage":[{"denominator":102,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":100,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T04:43:06.293736Z","state":"measured"},{"denominator":100,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":100,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+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/2506.09955/citation-record","integrity":"/paper/2506.09955/integrity","json":"/paper/2506.09955/citation-record.json","paper":"/paper/2506.09955"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T04:43:05.652082Z","title":"Square at- tack: a query-efficient black-box adversarial attack via random search","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:05.652082Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:951e56add33d58a5691420c11986406a35704e490c67fec08e7415886a541512","observation_id":"aefd609a-0447-4b5f-a8f1-ccd5937c0895","resolution":{"observed_at":"2026-08-07T04:43:05.652082Z","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":"2026-08-07T04:43:05.736571Z","title":"Synthetic data from diffusion models improves imagenet classification.Transactions on Machine Learning Research","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:05.736571Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:442b74c8eaecb61741de42e9a60ada5ba59b7e28df93523c388769b8d1c45fcf","observation_id":"125b0769-6754-4b1a-8168-1f8e6827644e","resolution":{"observed_at":"2026-08-07T04:43:05.736571Z","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":"2026-08-07T04:43:05.829324Z","title":"Leaving reality to imagination: Robust classification via generated datasets","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:05.829324Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:f9695f4890f678900c330ac57507a7bbdf873ad949bfaf521e23aa9b449343b5","observation_id":"5c834f5a-2b64-4150-8615-20374e4193fb","resolution":{"observed_at":"2026-08-07T04:43:05.829324Z","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":"2026-08-07T04:43:05.833406Z","title":"All are worth words: A vit backbone for diffusion models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:05.833406Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:de46b1d70560c6189af0180794741fe61d34e60424eaf58f562280164bc92dd7","observation_id":"6818d5e0-542f-40e3-b0f8-388c47374c3b","resolution":{"observed_at":"2026-08-07T04:43:05.833406Z","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":"2026-08-07T04:43:05.836696Z","title":"Label-efficient semantic segmentation with diffusion models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:05.836696Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:de3e48f846eaf65d7c660175bfa0f00283ac6cece55250fdd4fe12bc5c842bd1","observation_id":"c7a9cab1-8665-49ec-b550-57306d4d4dc0","resolution":{"observed_at":"2026-08-07T04:43:05.836696Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.07159","last_updated":"2020-06-12T13:17:25Z","snapshot_observed_at":"2026-08-07T08:01:08.867333Z","submitted_at":"2020-06-12T13:17:25Z","title":"Are we done with ImageNet?","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.07159","snapshot_observed_at":"2026-08-07T04:43:05.840404Z","title":"Are we done with imagenet?arXiv preprint arXiv:2006.07159, 2020","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:05.840404Z"},"links":{"cited_paper":"/paper/2006.07159","citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:d36b1feb024101905eeb72c3f256d3cc0ba66ae56ee2502702ab4865635b4098","observation_id":"ee948ce8-15b9-4e04-bbec-1567b84ed3e7","resolution":{"observed_at":"2026-08-07T04:43:05.840404Z","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":"2026-08-07T04:43:05.844163Z","title":"Towards evaluating the robustness of neural networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:05.844163Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:5f1a94ef008157e1434168d2640b5722a2830641e43cfef45c1954c7e76202a1","observation_id":"0ee4a14b-7e53-4dad-bf55-d5c97f32d1fd","resolution":{"observed_at":"2026-08-07T04:43:05.844163Z","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":"2026-08-07T04:43:05.847901Z","title":"Attend-and-excite: Attention-based semantic guidance for text-to-image diffusion models.ACM Transactions on Graphics (TOG), 42(4):1–10, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:05.847901Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:31856f167037e192fbf21025f2703c5c5c9421cd49b4aff807f2f1a51b4049d5","observation_id":"ced26cfb-ce34-4ffb-9d28-94eb8d71535b","resolution":{"observed_at":"2026-08-07T04:43:05.847901Z","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":"2026-08-07T04:43:05.850869Z","title":"Exploring low- dimensional subspace in diffusion models for controllable image editing","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:05.850869Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:a339709fe02a8a4abf0ac8b3be7d7ec91ee5e14f03bfa10f856b59369c482321","observation_id":"3227b04b-c266-45b6-bfe4-f0e834184a3c","resolution":{"observed_at":"2026-08-07T04:43:05.850869Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.14404","last_updated":"2024-01-25T18:59:57Z","snapshot_observed_at":"2026-08-06T14:37:40.501908Z","submitted_at":"2024-01-25T18:59:57Z","title":"Deconstructing Denoising Diffusion Models for Self-Supervised Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.14404","snapshot_observed_at":"2026-08-07T04:43:05.854243Z","title":"Deconstructing denoising diffusion models for self-supervised learning.arXiv preprint arXiv:2401.14404, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:05.854243Z"},"links":{"cited_paper":"/paper/2401.14404","citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:58c11bb52feaf5d28da40438d4a9fb2b1eb9c8eb0be5aae485e0e70898e91968","observation_id":"9effd71f-db1c-45e4-beac-2033421c43bb","resolution":{"observed_at":"2026-08-07T04:43:05.854243Z","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":"2026-08-07T04:43:05.857794Z","title":"Multilinear operator networks","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:05.857794Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:8c6470501d896b35f1a9ef550d0a9e89212ef24e2e3fcf708ac109e0de83248e","observation_id":"7eeae5a2-6290-4f60-9a37-63f43aae968f","resolution":{"observed_at":"2026-08-07T04:43:05.857794Z","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":"2026-08-07T04:43:05.860940Z","title":"Deep feature factorization for concept discovery","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:05.860940Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:81dff7589cb1808dc9b2107d0ed65dad943dc581178ac416d62ae0534a2602a2","observation_id":"3988629e-b9b8-4031-bae2-648ff882d913","resolution":{"observed_at":"2026-08-07T04:43:05.860940Z","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":"2026-08-07T04:43:05.864244Z","title":"Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:05.864244Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:b3438b0cfb3da193111b21b888cc59e0b7c63e39c6b801b778ccc4d418558148","observation_id":"f3682554-41db-427b-a189-bb4ed0ca17bb","resolution":{"observed_at":"2026-08-07T04:43:05.864244Z","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":"2026-08-07T04:43:05.867141Z","title":"Aligning model and macaque inferior temporal cortex representations improves model-to-human behavioral alignment and adversarial robust- ness","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:05.867141Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:5f38969f15018e9c55737a2a05e0583d9d91108a5b1597983790bca6107e4c0e","observation_id":"67851f18-eec0-49af-8cd3-1ca94cc422ad","resolution":{"observed_at":"2026-08-07T04:43:05.867141Z","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":"2026-08-07T04:43:05.870193Z","title":"ImageNet: A large- scale hierarchical image database","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:05.870193Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:e048cb47b75fcae9ad8f091371eac5688697ba692fb9dd20f35cbf4f1e9d10f5","observation_id":"50b7ac84-1072-4c1a-b00d-a4da6c160023","resolution":{"observed_at":"2026-08-07T04:43:05.870193Z","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":"2026-08-07T04:43:05.873537Z","title":"Diffusion models beat gans on image synthesis","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:05.873537Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:530d9f4861a9e615b956d4fa2634b421f964f6da456b0d7ebb2bf0681c5c13af","observation_id":"9c2bc4f0-a5a8-4269-ba49-0c084238c3d4","resolution":{"observed_at":"2026-08-07T04:43:05.873537Z","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":"2026-08-07T04:43:05.877975Z","title":"On robustness and transferability of convolutional neural networks","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:05.877975Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:b9c19009067a391860de04f9afdbb0e9afea3f9bdb6c57512f64d079e117014b","observation_id":"ea94386f-91f0-4430-bba6-5ca4484b711d","resolution":{"observed_at":"2026-08-07T04:43:05.877975Z","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":"2026-08-07T04:43:05.881296Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:05.881296Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:6057be000fa05415a92a12927dc76ed15bb4a6913ba77af0413ccf0a9f110aca","observation_id":"4e0e7709-6b21-4752-b877-18b2e3aacf15","resolution":{"observed_at":"2026-08-07T04:43:05.881296Z","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":"2026-08-07T04:43:05.885006Z","title":"DyTox: Trans- formers for continual learning with dynamic token expansion","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:05.885006Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:2b406486b09edd482520540edd95928d24e543c4b2e271a2f3677915146f9ec9","observation_id":"845f5a72-458e-4302-b44b-115c09fe19c6","resolution":{"observed_at":"2026-08-07T04:43:05.885006Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.12803","last_updated":"2024-03-19T15:04:35Z","snapshot_observed_at":"2026-07-06T17:47:02.560132Z","submitted_at":"2024-03-19T15:04:35Z","title":"DreamDA: Generative Data Augmentation with Diffusion Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.12803","snapshot_observed_at":"2026-08-07T04:43:05.889147Z","title":"Dreamda: Generative data augmentation with diffusion models.arXiv preprint arXiv:2403.12803, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:05.889147Z"},"links":{"cited_paper":"/paper/2403.12803","citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:6ad393f39f812fada16d369fff3591e0c682900dc5abaa132f573e5e4deec8ab","observation_id":"ed2a13f1-21cb-4cd4-986c-1a86d8f8034c","resolution":{"observed_at":"2026-08-07T04:43:05.889147Z","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":"2026-08-07T04:43:05.893413Z","title":"Improving robustness using generated data.Advances in Neural Information Processing Systems, 34:4218–4233, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:05.893413Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:90884f737c4c87d0ab99e00b1a3bbc6be52970803f5894692f3d935a176cb7f0","observation_id":"9766b5ca-425d-4b0a-ae21-8db12d912a18","resolution":{"observed_at":"2026-08-07T04:43:05.893413Z","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":"2026-08-07T04:43:05.896747Z","title":"Discovering interpretable directions in the semantic latent space of diffusion models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:05.896747Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:b9d03fc9638d282a82443b0ebec59ae53253e0c05eb4cd703d1bcc3f4208be06","observation_id":"95d8f437-023f-41c2-be24-a02637fff5ee","resolution":{"observed_at":"2026-08-07T04:43:05.896747Z","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":"2026-08-07T04:43:05.906496Z","title":"Deep residual learning for im- age recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:05.906496Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:bdff26f887a5d07988247da71f763885233b7f933b143660aa8d2398a1537ba6","observation_id":"aa9bc5f7-c364-4f55-9cbd-c4484930433e","resolution":{"observed_at":"2026-08-07T04:43:05.906496Z","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":"2026-08-07T04:43:05.909926Z","title":"Is synthetic data from generative models ready for image recognition? InThe Eleventh International Conference on Learning Representations, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:05.909926Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:86225781f8beca2db09a7c68b5dd5d31c4b819e2a092f6fdbd85079be4d7a1aa","observation_id":"50462cf0-57bc-436b-a1ce-ab40a0b262cb","resolution":{"observed_at":"2026-08-07T04:43:05.909926Z","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":"2026-08-07T04:43:05.913162Z","title":"Benchmarking neural network robustness to common corruptions and perturbations","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:05.913162Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:72cb2bd9aa0365e5462cf294aeab9655b4d555324cf494959491a28a8da2dc27","observation_id":"68a2cbbc-45c8-4ae7-ac0e-31077011f53a","resolution":{"observed_at":"2026-08-07T04:43:05.913162Z","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":"2026-08-07T04:43:07.061681Z","title":"Prompt-to-prompt image editing with cross-attention control","venue":null,"work_id":"19910df9-9234-472e-a14b-c21d8c46d2c8","year":null},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:05.916591Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:220aafe12ff40d3aa226e0a166f602d76ab41be738df020bea31c291d2268794","observation_id":"35f46db6-8b4d-4567-a125-d411ba5b9966","resolution":{"observed_at":"2026-08-07T04:43:07.065431Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T04:43:05.920638Z","title":"Classifier-free diffusion guidance","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:05.920638Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:b29949e1f99a619130dec0be60ee0bd30142335ae0d28c54cc16503dc220c609","observation_id":"cb087050-c55d-4c84-9f50-d6222e925601","resolution":{"observed_at":"2026-08-07T04:43:05.920638Z","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":"2026-08-07T04:43:05.924658Z","title":"Denoising diffusion probabilistic models.Advances in Neural Information Processing Systems, 33:6840–6851, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:05.924658Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:a8d0a64ebf63078d7952066bccaa81352586314133f7b45d69644c2e3009dd15","observation_id":"c2d60b5d-8e0a-4784-a029-9a66a023f170","resolution":{"observed_at":"2026-08-07T04:43:05.924658Z","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":"2026-08-07T04:43:05.928077Z","title":"Dif- fusemix: Label-preserving data augmentation with diffusion models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:05.928077Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:75944782c809f682d11470625cb4e03cc890007889ca5acdcf267fbbabfaf404","observation_id":"d86e746e-95b9-4014-afc4-1747506fddf1","resolution":{"observed_at":"2026-08-07T04:43:05.928077Z","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":"2026-08-07T04:43:07.030675Z","title":"Training-free content injection using h-space in diffusion models","venue":null,"work_id":"ddce8ac5-c773-406c-be93-65d9d8452463","year":2024},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:05.931144Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:b6296d033071d125ac5ea516db4781cb40840bde769931dd85449b73046098f9","observation_id":"015b3723-2de8-4ca2-9c60-3ea8af17d628","resolution":{"observed_at":"2026-08-07T04:43:07.034271Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T04:43:05.934027Z","title":"Elucidating the design space of diffusion-based generative models.Advances in Neural Information Processing Systems, 35: 26565–26577, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:05.934027Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:1a352168adf61f3487efca5b844ab566f8bcab44c1bc7bd3dfdd43d5c00ca02c","observation_id":"35d1ad5b-15a5-4620-ac9b-5beaf49d22cc","resolution":{"observed_at":"2026-08-07T04:43:05.934027Z","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":"2026-08-07T04:43:07.012641Z","title":"Guiding a diffusion model with a bad version of itself.Advances in Neural Information Processing Systems, 37:52996–53021, 2024","venue":null,"work_id":"e5d8d26f-35f1-4021-9c52-909266477331","year":2024},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:05.937695Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:d961b0aca8102334cdf5f975968f419c1ecf5e7a47b0d6ce480dfd222b81840e","observation_id":"a173b1f5-d8ff-4ed8-b72d-a57b0c70c7a9","resolution":{"observed_at":"2026-08-07T04:43:07.016507Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T04:43:05.941440Z","title":"Analyzing and improving the training dynamics of diffusion models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:05.941440Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:0b0f1772b8f3e4ab6fd1dada4d54fb4a993f8834e039bf6ee73b3dd525edd2f3","observation_id":"9fa14663-c696-45b6-9996-d607bbd26b87","resolution":{"observed_at":"2026-08-07T04:43:05.941440Z","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":"2026-08-07T04:43:06.994178Z","title":"Supervised contrastive learning.Advances in Neural Information Processing Systems, 33:18661–18673, 2020","venue":null,"work_id":"0d6b8a3e-0281-47ab-9447-76adc6ac234b","year":2020},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:05.944819Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:6e8ea5b88db8b90321037789e39af794dbbb77e9738d90da93c51ce97decf6ef","observation_id":"85ee9015-f40e-41c4-b7f1-78ab93da146a","resolution":{"observed_at":"2026-08-07T04:43:06.998569Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2010.01950","last_updated":"2021-02-19T15:42:38Z","snapshot_observed_at":"2026-08-04T22:49:29.740804Z","submitted_at":"2020-09-24T01:34:42Z","title":"Torchattacks: A PyTorch Repository for Adversarial Attacks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.01950","snapshot_observed_at":"2026-08-07T04:43:05.948566Z","title":"Torchattacks: A pytorch repository for adversarial attacks.arXiv preprint arXiv:2010.01950, 2020","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:05.948566Z"},"links":{"cited_paper":"/paper/2010.01950","citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:e4905f1b5e90960920b8b91cdadf4bd9df864548468832b4387885af4f504b19","observation_id":"65cd1191-ea96-446b-92b3-91d6b426a845","resolution":{"observed_at":"2026-08-07T04:43:05.948566Z","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":"2026-08-07T04:43:05.952392Z","title":"Dense text-to-image generation with attention modulation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:05.952392Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:a2e980dfe690b21dd0dc5ae40ed098df9acb645c32b993a330e54521a56948e6","observation_id":"0c34635f-b857-40cf-8b78-c545b826e079","resolution":{"observed_at":"2026-08-07T04:43:05.952392Z","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":"2026-08-07T04:43:06.977213Z","title":"Adam: A method for stochastic optimization","venue":null,"work_id":"30298d94-ceed-4971-8cbb-9f21ab4be2d2","year":2015},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:05.955600Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:c9c90942982c81ad11bb713123223ee8ddfb95ec2c54ac2c35f2afb72336e849","observation_id":"c4dc148c-58e6-4893-b221-aa544c153346","resolution":{"observed_at":"2026-08-07T04:43:06.980719Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1312.6114","last_updated":"2022-12-10T21:04:00Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2013-12-20T20:58:10Z","title":"Auto-Encoding Variational Bayes","version":11},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1312.6114","snapshot_observed_at":"2026-08-07T04:43:05.958794Z","title":"Auto-encoding variational bayes.arXiv preprint arXiv:1312.6114, 2014","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:05.958794Z"},"links":{"cited_paper":"/paper/1312.6114","citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:dd9ac2915ea08c19c50685c2d3cbb57f4679cb7a823805e57709df67d0ad1c4c","observation_id":"e2a95cbf-f45b-410e-8a54-05219704a9ef","resolution":{"observed_at":"2026-08-07T04:43:05.958794Z","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":"2026-08-07T04:43:05.962148Z","title":"Similarity of neural network representations revisited","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:05.962148Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:c6140bd170f2256810cd18a7fda0207a091b70b622adf3d06069bc2689126490","observation_id":"80e078e0-7efb-4062-829a-d8d6eb340fad","resolution":{"observed_at":"2026-08-07T04:43:05.962148Z","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":"2026-08-07T04:43:05.965632Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:05.965632Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:8e4a2cfe0cf415c4d328375f2550c7da6930c97998c863f24207a92ba3720320","observation_id":"10f56f37-5f5b-424a-8699-e965766c99fa","resolution":{"observed_at":"2026-08-07T04:43:05.965632Z","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":"2026-08-07T04:43:06.954447Z","title":"Diffusion models already have a semantic latent space","venue":null,"work_id":"eb5066e1-7057-44fa-b572-14249deccc7d","year":2023},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:05.968813Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:d709d4927f8ebe7b7405cc40293ce56b261cc6664a0d3aaa23e91ebe2bb60d7d","observation_id":"564c4a3e-2a90-4253-9b70-6578bcebcec6","resolution":{"observed_at":"2026-08-07T04:43:06.957996Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T04:43:06.944842Z","title":"Applying guidance in a limited interval improves sample and distribution quality in diffusion models","venue":null,"work_id":"067a4e93-ea3b-4015-b79b-88ed8398930e","year":2024},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:05.971843Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:e97bc6c792bfb93e15697e60be0e0d9eb3827c46a6525fa7c5874038e1bc0fe6","observation_id":"b90a2e36-b5c4-40c0-b805-3b2fdb404417","resolution":{"observed_at":"2026-08-07T04:43:06.948215Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T04:43:06.935325Z","title":"Your diffusion model is secretly a zero-shot classifier","venue":null,"work_id":"6cdcaaae-f9be-41e9-8926-6a3257cd2198","year":2023},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:05.975935Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:bbb37915a4f29bd42d8c101e42f9962f69eff143e8f4b7d5064d0af65ef874ba","observation_id":"357bf731-9233-46d7-a67e-7966ede97e23","resolution":{"observed_at":"2026-08-07T04:43:06.938551Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T04:43:06.924175Z","title":"Dreamteacher: Pretraining image backbones with deep generative models","venue":null,"work_id":"fcfcc9df-dcc0-41fc-a9b0-2b1038c137fe","year":2023},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:05.979793Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:5a5600970cf628ce0a486e0152028db529ed3bef4ee43a20ec2b0cd5a635997d","observation_id":"3b108cd8-0bd3-46b3-9564-b4879e51c54e","resolution":{"observed_at":"2026-08-07T04:43:06.928203Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T04:43:06.913253Z","title":"Towards understanding cross and self-attention in stable diffusion for text-guided image editing","venue":null,"work_id":"a62a8350-18ac-45e9-8e81-5c2f17a58df7","year":2024},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:05.982804Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:9498381b351772acef5593b0d97b2e1e48fe833febebc30af8fdfa55b8c1eecd","observation_id":"293b5864-64b5-4efe-8f1e-5f59f7766fc6","resolution":{"observed_at":"2026-08-07T04:43:06.916711Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T04:43:06.903407Z","title":"Swin Transformer: Hierarchical vision transformer using shifted windows","venue":null,"work_id":"39af4022-9bd4-440d-8f1b-ad7c6e37b707","year":2021},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:05.986564Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:5f25e21e9ce0d83ea1707a0c918fd1395774730d6c686ad2986067ce3ad66eb9","observation_id":"eda7b157-c55e-4d45-88c0-2666c1afea4e","resolution":{"observed_at":"2026-08-07T04:43:06.906704Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T04:43:06.893093Z","title":"Swin Transformer v2: Scaling up capacity and resolution","venue":null,"work_id":"30527499-c8af-4a68-8de7-1788b32101bc","year":2022},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:05.989643Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:15435553d42cce94bcafec1980b024c7e00578932253b061d955e49d4e921a97","observation_id":"b993c358-5730-46f5-b41d-08dcd5beac3a","resolution":{"observed_at":"2026-08-07T04:43:06.896917Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T04:43:06.881780Z","title":"Challenging common assumptions in the unsupervised learning of disentangled representations","venue":null,"work_id":"66e51384-31d8-4bc5-a113-29baf54935db","year":2019},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:05.992991Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:aee213abffcf064c354dd5d9be7af9b87cd7f6f321832fec70e063947d268705","observation_id":"a0c82347-d2bd-4006-a24a-5b2cbe263710","resolution":{"observed_at":"2026-08-07T04:43:06.885411Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T04:43:06.871566Z","title":"Towards deep learning models resistant to adversarial attacks","venue":null,"work_id":"504b941c-0b94-4d92-bdea-5d0a1e4db18c","year":2018},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:05.996234Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:748ba63fe9129fddeb9eca1369e9d5d3b4223078a52f2c68e8eabb59f03aefe1","observation_id":"68b0ddef-2427-4cb6-adde-5c258528b479","resolution":{"observed_at":"2026-08-07T04:43:06.874823Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T04:43:06.000323Z","title":"Umap: Uniform manifold approximation and projection.Journal of Open Source Software, 3(29):861, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:06.000323Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:cbe94c9d584c5603be32c309dd945bdeec02ae16e73c84e16a7252ccb7c4ec1d","observation_id":"5a05246a-b6a7-4904-a399-ad702efc8e0a","resolution":{"observed_at":"2026-08-07T04:43:06.000323Z","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":"2026-08-07T04:43:06.855312Z","title":"Not all diffusion model activations have been evaluated as discriminative features.Advances in Neural Information Processing Systems, 37:55141–55177, 2024","venue":null,"work_id":"0507d996-ce79-4707-888d-5040e441fe70","year":2024},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:06.004028Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:da59f8dec63257bbb3184d5723620298a0abe71dc10c76e447125c94f63c8de2","observation_id":"5f962cac-24a3-443e-9c16-c30482f3a4d0","resolution":{"observed_at":"2026-08-07T04:43:06.858806Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.08702","last_updated":"2023-07-17T17:59:40Z","snapshot_observed_at":"2026-07-06T15:54:58.589775Z","submitted_at":"2023-07-17T17:59:40Z","title":"Diffusion Models Beat GANs on Image Classification","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.08702","snapshot_observed_at":"2026-08-07T04:43:06.007017Z","title":"Diffusion models beat gans on image classification.arXiv preprint arXiv:2307.08702, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:06.007017Z"},"links":{"cited_paper":"/paper/2307.08702","citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:9fe80226b501c20e9da7e01af3b69ea5fe03aa2b9adc8ea2b3dc6d8a02664a40","observation_id":"63cb6019-dfd1-4ee5-8645-4bfc14712b81","resolution":{"observed_at":"2026-08-07T04:43:06.007017Z","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":"2026-08-07T04:43:06.844926Z","title":"Do text-free diffusion models learn discriminative visual representations? InEuropean Conference on Computer Vision, pages 253–272","venue":null,"work_id":"0a90be2b-fcc8-4ee6-b642-ee0b66a65c5d","year":2024},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:06.010323Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:4ef5399d7dbdd2e4c67bfadea651c4dc9a2176a2c937bb59c6338247597226dd","observation_id":"98ea5bb0-9187-4590-bb4f-49cf01d3db09","resolution":{"observed_at":"2026-08-07T04:43:06.848806Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T04:43:06.013359Z","title":"Relational knowledge distillation","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:06.013359Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:507e749047457eea13c76b5ee6423c3ddb3d6fa048c56095a2d9062a748eb4b1","observation_id":"fcdd84c4-8723-4a85-bf4c-e3741604fd96","resolution":{"observed_at":"2026-08-07T04:43:06.013359Z","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":"2026-08-07T04:43:06.016712Z","title":"Understanding the latent space of diffusion models through the lens of riemannian geometry.Advances in Neural Information Processing Systems, 36:24129–24142, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:06.016712Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:cf94793cf8564a83e72bc540e90abeb35b86a58baaf250dcfe9913a0771e038c","observation_id":"1cb3a928-2570-4009-8b34-1d0a63ace497","resolution":{"observed_at":"2026-08-07T04:43:06.016712Z","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":"2026-08-07T04:43:06.019983Z","title":"Scalable diffusion models with transformers","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:06.019983Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:e23b6ea7cfadbc3d84eb2279b202f9d7888c8a3dc3e9e0a6941a418eb43880b8","observation_id":"cf113a27-49e0-4fd8-96f1-4a3a6d3aeb99","resolution":{"observed_at":"2026-08-07T04:43:06.019983Z","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":"2026-08-07T04:43:06.023217Z","title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:06.023217Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:9a4098ffd1720e0ce413988087b64768659f33edf1f6ff31397ed184ef9406f3","observation_id":"461e583d-a8de-4d13-914c-d756354db222","resolution":{"observed_at":"2026-08-07T04:43:06.023217Z","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":"2026-08-07T04:43:06.027076Z","title":"High- resolution image synthesis with latent diffusion models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:06.027076Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:55ad659066c31640957180c581f7266ac9c21f87d53873ab48bff54cf6dfaf4a","observation_id":"ff0dd2d6-f606-4d04-902f-b34054f761c5","resolution":{"observed_at":"2026-08-07T04:43:06.027076Z","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":"2026-08-07T04:43:06.799456Z","title":"Fitnets: Hints for thin deep nets","venue":null,"work_id":"0972beaf-4de5-4eef-815f-1015d55c0e49","year":2015},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:06.030786Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:cb77435b94ec8d409ed02ad74efbbb957fe81ccbdcfbfca17c3a4006823ca59e","observation_id":"7ad93a6e-8584-4eba-8ae8-b1c71746ccbb","resolution":{"observed_at":"2026-08-07T04:43:06.803239Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T04:43:06.788326Z","title":"Distilling representational similarity using centered kernel alignment (cka)","venue":null,"work_id":"39315ff2-3c92-4a14-b5bd-18136b2af820","year":2022},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:06.034746Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:7aa9cb6f768ea1eedf364844b9d8890786657d139b8ba10e5da89abde16d3fc8","observation_id":"509087ab-7875-4e7a-b8de-6b56d1097441","resolution":{"observed_at":"2026-08-07T04:43:06.792353Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T04:43:06.776242Z","title":"Fake it till you make it: Learning transferable representations from synthetic imagenet clones","venue":null,"work_id":"442a4a22-4ad0-48ba-9e25-d72c1d07305a","year":2023},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:06.037942Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:d6cf1b17797fb42b7cf2560c99095995924601a6e30813e8f911c9f2556000de","observation_id":"c743abac-aeb0-4911-84eb-fb442a79a0b2","resolution":{"observed_at":"2026-08-07T04:43:06.779855Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T04:43:06.041282Z","title":"Laion- 5b: An open large-scale dataset for training next generation image-text models.Advances in Neural Information Processing Systems, 35:25278–25294, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:06.041282Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:bc0a0f0413e37d80dd440ec7ba9a8295665f77ad82e68c3e690fe93eda8652d5","observation_id":"be0591a2-ca1c-4aa7-9707-2c1b867a86ad","resolution":{"observed_at":"2026-08-07T04:43:06.041282Z","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":"2026-08-07T04:43:06.758715Z","title":"Robust learning meets generative models: Can proxy distributions improve adversarial robustness? InInternational Conference on Learning Representations, 2022","venue":null,"work_id":"9a944b83-6503-43d0-a0d2-d2e6bef4d2f4","year":2022},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:06.044666Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:baf4f7d19d2d81fd940db30763f11ae67d2a9c2c71add3835fb3d8b3396f86ad","observation_id":"61008af7-2e96-4721-9e76-a994a9009922","resolution":{"observed_at":"2026-08-07T04:43:06.762517Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T04:43:06.748245Z","title":"Diffaug: A diffuse-and- denoise augmentation for training robust classifiers.Advances in Neural Information Processing Systems, 37:20745–20785, 2024","venue":null,"work_id":"76bae409-b55f-4292-9caf-06e61ace8133","year":2024},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:06.047888Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:00a1b8793e7b3aad7e989dfc904f9fcf8e6137a6f00d2a1c54168c778557435c","observation_id":"573046e9-ca67-4e24-b713-6ea9a55baa84","resolution":{"observed_at":"2026-08-07T04:43:06.751842Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T04:43:06.738828Z","title":"Denoising diffusion implicit models","venue":null,"work_id":"a8ce5bac-1f8c-4da3-8727-faaa6105a681","year":2021},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:06.051173Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:b3803073f253e86e0361360d913bbd0777de32cf8c51a78a2d4a8d073c574dd6","observation_id":"f1e748f6-a1ea-4f27-9218-e326e1950215","resolution":{"observed_at":"2026-08-07T04:43:06.741966Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T04:43:06.054501Z","title":"Score-based generative modeling through stochastic differential equations","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:06.054501Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:7af49e451ead399c0a12297ccfcf7f133a61ac2e5358df80a0cddea61d364284","observation_id":"ecf59d83-9cd2-4e0e-9acb-f8967132173e","resolution":{"observed_at":"2026-08-07T04:43:06.054501Z","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":"2026-08-07T04:43:06.721970Z","title":"Latent traversals in generative models as potential flows","venue":null,"work_id":"818734e5-22c8-48db-81ff-e963bcb84843","year":2023},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:06.057771Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:8edcd73347c4f78f3dd2791fe7c00e83dc999a6b51d46d83489c0cec9d691489","observation_id":"116b09f5-c4b8-47fc-ad1b-5921b876b4f7","resolution":{"observed_at":"2026-08-07T04:43:06.725280Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T04:43:06.060699Z","title":"Training data-efficient image transformers & distillation through attention","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:06.060699Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:d98948b69c4eab99a5b4e39266040f0c495ff220d74d864787b96c8c146ac0d1","observation_id":"3cc45e03-6942-4e46-9b7f-f6e81b29484f","resolution":{"observed_at":"2026-08-07T04:43:06.060699Z","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":"2026-08-07T04:43:06.705415Z","title":"Deit iii: Revenge of the vit","venue":null,"work_id":"d0f9131f-0535-4e85-9954-7e429a2f27a8","year":2022},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:06.063895Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:a50c25265cfd506c7b2c6ca09ffc9de7520fd4ce4460bc70b4f4f4b85227e746","observation_id":"50513ada-42b4-4778-b9c8-fc869df6cdac","resolution":{"observed_at":"2026-08-07T04:43:06.708676Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T04:43:06.695242Z","title":"Effective data augmentation with diffusion models","venue":null,"work_id":"def9eeef-03f7-4132-81aa-aa7de31273cb","year":2024},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:06.067385Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:a12078dd2f55de7f7e3c0f1fa16f3949aaf26a053d39aeedb3af776e75089e42","observation_id":"d1677e40-8dd5-4a10-9a35-1ebf5d12cfe8","resolution":{"observed_at":"2026-08-07T04:43:06.698602Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T04:43:06.070204Z","title":"Attention is all you need.Advances in Neural Information Processing Systems, 30, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:06.070204Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:85681418aee4e0051aa79a57b7356e9af1bcfd78901ea4b7406adc73296c4ef8","observation_id":"dde83dc1-4f14-49dd-988b-f7edd7a9649e","resolution":{"observed_at":"2026-08-07T04:43:06.070204Z","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":"2026-08-07T04:43:06.678470Z","title":"Diffusion model learns low-dimensional distributions via subspace clustering","venue":null,"work_id":"e81a1507-68b2-42e8-b4dd-ce96d050ed13","year":2024},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:06.073001Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:ac3b54d7e8eafb357d074c8c945fa60e18303e260c7ea5fe087c52548ac53e6d","observation_id":"11b91c10-a927-46b9-a9d1-2dff5351f0dd","resolution":{"observed_at":"2026-08-07T04:43:06.681975Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T04:43:06.668858Z","title":"Better diffusion models further improve adversarial training","venue":null,"work_id":"452fe1cf-ad5a-4424-8221-d30c6adffff2","year":2023},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:06.075836Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:b385120ab0406511ec112c3a4c46dcedcb736e9f0c74b91ef9e69492365f90d4","observation_id":"83b175ba-be99-4681-9159-8ac41b8c34c2","resolution":{"observed_at":"2026-08-07T04:43:06.672287Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T04:43:06.078877Z","title":"Pytorch image models","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:06.078877Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:3de23a212efe5996dd6dfcf97739db1c71902a8b268c5f1daa2b068ba5c74845","observation_id":"1155a7ea-d4db-42e7-b9d8-49ed73df54a9","resolution":{"observed_at":"2026-08-07T04:43:06.078877Z","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":"2026-08-07T04:43:06.652095Z","title":"Simple statistical gradient-following algorithms for connectionist reinforce- ment learning.Machine Learning, 8:229–256, 1992","venue":null,"work_id":"739fb516-f4e7-4f87-a714-cd1892069bfb","year":1992},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:06.082523Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:ab3c1cc35dff5774c43c37de3b256112025cc52367ce3a99274c58800ee38c68","observation_id":"b8e57d0a-cc54-4819-ad29-f0fc818f0195","resolution":{"observed_at":"2026-08-07T04:43:06.655684Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T04:43:06.085389Z","title":"Convnext v2: Co-designing and scaling convnets with masked autoencoders","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:06.085389Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:c548786386dafccfa67d22e64166c6c6b9f521915c9accbc7f10939113d8a972","observation_id":"89cb3aa6-dd05-4962-af96-dc7d32f00c69","resolution":{"observed_at":"2026-08-07T04:43:06.085389Z","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":"2026-08-07T04:43:06.634738Z","title":"Verbs semantics and lexical selection","venue":null,"work_id":"993ac648-4ba2-4966-a719-40b3414f6254","year":1994},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:06.088627Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:9687930265313d0740792a357677049b069383b01f1ec46e90b15157b3b1368f","observation_id":"cfaca2e4-a451-4ca1-b6a2-bfbb0bf247d7","resolution":{"observed_at":"2026-08-07T04:43:06.638051Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T04:43:06.091805Z","title":"Denoising diffusion autoencoders are unified self-supervised learners","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:06.091805Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:c65d91d6f97fc746c507cffad2b02f0c6fdfea1a92ea7ea1e1516739e48e2410","observation_id":"5656eb0c-045b-4206-80f1-9ddaec18c9f4","resolution":{"observed_at":"2026-08-07T04:43:06.091805Z","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":"2026-08-07T04:43:06.617187Z","title":"Noise or signal: The role of image backgrounds in object recognition","venue":null,"work_id":"74fdcc9a-fcc9-43b7-bebb-c83c6ca90373","year":null},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:06.095036Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:868e2443eb677b1f3815a2637363f444a6e92708943c6073c84ea704c71b6351","observation_id":"9c2f70e4-428d-4073-b601-25ee94fa72f2","resolution":{"observed_at":"2026-08-07T04:43:06.620538Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T04:43:06.606595Z","title":"Open-vocabulary panoptic segmentation with text-to-image diffusion models","venue":null,"work_id":"b15f70d4-e520-4378-bda5-75223807630f","year":2023},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:06.098374Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:5c0a1810328e3ff43bcab0c5a738b2344117014daedec431010b38336b62b3b7","observation_id":"45fefd4b-d541-4f05-a7bc-9b599a106462","resolution":{"observed_at":"2026-08-07T04:43:06.610442Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T04:43:06.596294Z","title":"Adanca: Neural cellular automata as adaptors for more robust vision transformer","venue":null,"work_id":"98b0011e-a01e-4df5-a06d-28b1b5437e37","year":2024},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:06.101854Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:1ab7503f2c9b6ae56915d52b10d96b37cebacec65b5bdaba4dd01486e6a2e2b1","observation_id":"73320a96-3d8a-417f-b338-a0670c782b59","resolution":{"observed_at":"2026-08-07T04:43:06.599782Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T04:43:06.585918Z","title":"DER: Dynamically expandable representation for class incremental learning","venue":null,"work_id":"dab73bc9-deff-4127-b115-ea00bec4fb41","year":2021},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:06.105059Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:85552aa1addb4fb447bdd5af91b3072acc3b1900aeb8cc76da6e7e7da283c0d7","observation_id":"b9296880-a071-4eeb-98c2-1c118c331da8","resolution":{"observed_at":"2026-08-07T04:43:06.589288Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T04:43:06.238194Z","title":"Diffusion model as representation learner","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:06.238194Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:b1abf7dd01c9881f41989fe706d70fb02783a22e70060746b608b54a8aa0cfbc","observation_id":"642bafc0-6cd8-42d7-9430-b78643169238","resolution":{"observed_at":"2026-08-07T04:43:06.238194Z","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":"2026-08-07T04:43:06.569797Z","title":"Vitkd: Feature-based knowledge distillation for vision transformers","venue":null,"work_id":"e0474136-1af3-4921-bddd-b17b14e622be","year":2024},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:06.241547Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:845419207f9f036443c9e5a2e08810d7f4f53157817ead03b86858d1d3e657df","observation_id":"b58482f9-96c8-449f-940f-8dd15e0dbd04","resolution":{"observed_at":"2026-08-07T04:43:06.572938Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T04:43:06.559732Z","title":"Distill vision transformers to cnns via low-rank representation approximation","venue":null,"work_id":"6db5eac6-b4e5-4733-8366-d7759cffda82","year":2022},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:06.244720Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:af71c444f0ad0b215bb6f074aeca5e8b20edc813172455e72e69aa8c0ca46230","observation_id":"b444d1ab-c7dd-47de-9e8d-df896be911ef","resolution":{"observed_at":"2026-08-07T04:43:06.563196Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T04:43:06.549421Z","title":"Coca: Contrastive captioners are image-text foundation models.Transactions on Machine Learning Research","venue":null,"work_id":"c2bffbeb-0f5a-43aa-969f-f4e1004247c2","year":null},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:06.247933Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:c1c31b907631c4b3c13f6983b87a5c828248c2de942afb9bea5a40989eb0c2ad","observation_id":"920357cc-84a3-4eef-9ece-143c176b2acd","resolution":{"observed_at":"2026-08-07T04:43:06.552850Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T04:43:06.539564Z","title":"S2-mlp: Spatial-shift mlp architecture for vision","venue":null,"work_id":"c5b9da7e-034c-4cec-a381-5617bce13ee6","year":2022},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:06.250863Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:6835a40f7e0ce8983757e901b3a6b0f42b9572aa178ebae904549c106eeaebad","observation_id":"8c1a68d9-b9c3-4367-a973-69145458d5aa","resolution":{"observed_at":"2026-08-07T04:43:06.542933Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T04:43:06.253704Z","title":"Cutmix: Regularization strategy to train strong classifiers with localizable features","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:06.253704Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:4a689f3f57aeee085e1bde046a4706fb01ef776e3ff7d86b536cd0e8b455c384","observation_id":"a53c44a6-4147-499f-89ce-2facf2cc946a","resolution":{"observed_at":"2026-08-07T04:43:06.253704Z","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":"2026-08-07T04:43:06.256762Z","title":"Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:06.256762Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:09ec56ac7f2bb2ca131a9c9a5484d4f63f4bc7c91e9f89245b0a0513ea919a16","observation_id":"b77088d2-89cb-45f7-b648-592ec4e476dd","resolution":{"observed_at":"2026-08-07T04:43:06.256762Z","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":"2026-08-07T04:43:06.514425Z","title":"Mixup: Beyond empirical risk minimization","venue":null,"work_id":"2bc5428c-ba0d-4360-873c-ae3196fe6b97","year":2018},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:06.259755Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:8251332599dc0229eeee1a3fa374dd74a5d60ead450f42933fd085c7b153480b","observation_id":"5492d291-b192-4cd5-9f92-5eac2bd45be2","resolution":{"observed_at":"2026-08-07T04:43:06.517850Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T04:43:06.504575Z","title":"Three things we need to know about transferring stable diffusion to visual dense prediction tasks","venue":null,"work_id":"5cfc8989-4eeb-4d8e-bacd-436248338307","year":2024},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:06.262873Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:8af1b997af218e33559fa4aa6c1ee2f86aefec45baa6efcd7501a5907de05273","observation_id":"4c04054e-b62e-4ec5-84ed-d0346a0f9262","resolution":{"observed_at":"2026-08-07T04:43:06.508116Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T04:43:06.494903Z","title":"Scalable deep k-subspace clustering","venue":null,"work_id":"1dd08995-c425-43e0-89b9-beaa9523c7e9","year":2018},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:06.265758Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:8fe7976bdf04c9250783657541785ace7a9260125e723be44cd87763683cb193","observation_id":"be462ed3-ab6a-49ec-bade-ebbf90d2bb1a","resolution":{"observed_at":"2026-08-07T04:43:06.498393Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T04:43:06.485112Z","title":"Unsupervised representation learning from pre- trained diffusion probabilistic models.Advances in Neural Information Processing Systems, 35: 22117–22130, 2022","venue":null,"work_id":"e604f34c-876c-4919-b0fb-82ab51383d68","year":2022},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:06.268583Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:9160bc09634c96a6f3926a53a624881af73b2a377d03d1968776e9c1cfa91bc7","observation_id":"7310e204-a4fe-43b3-911e-6409f00779af","resolution":{"observed_at":"2026-08-07T04:43:06.488675Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T04:43:06.474630Z","title":"Unleashing text- to-image diffusion models for visual perception","venue":null,"work_id":"186e3767-983d-4896-9367-613473f92060","year":2023},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":95,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:06.274735Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:991544aa1dfbc3429b12198ff5c5f1bbebf4ea78418dff2e7a75c7a96010c3fa","observation_id":"d102d14a-41d6-4280-9733-1bc5aa52339d","resolution":{"observed_at":"2026-08-07T04:43:06.478175Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T04:43:06.464328Z","title":"Understanding the robustness in vision transformers","venue":null,"work_id":"72627177-19c0-446d-8230-7a906e5e427e","year":2022},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":96,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:06.277639Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:74129245ea27ccd0181ef651a6ba584e00d492f619d125e85ca7ff5018957935","observation_id":"24aa2d01-7d7b-4ffb-a1ac-24c87581810f","resolution":{"observed_at":"2026-08-07T04:43:06.467822Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2411.09502","last_updated":"2025-07-17T03:40:22Z","snapshot_observed_at":"2026-07-06T19:50:24.924617Z","submitted_at":"2024-11-14T15:13:13Z","title":"Golden Noise for Diffusion Models: A Learning Framework","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.09502","snapshot_observed_at":"2026-08-07T04:43:06.280415Z","title":"Golden noise for diffusion models: A learning framework.arXiv preprint arXiv:2411.09502, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":97,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:06.280415Z"},"links":{"cited_paper":"/paper/2411.09502","citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:8ad225cd3f1619da992d74636e7a97dc687a1b26ab78eb4a5711582915aacbea","observation_id":"fac85dd3-593e-4578-8a9f-0b99571ba276","resolution":{"observed_at":"2026-08-07T04:43:06.280415Z","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":"2026-08-07T04:43:06.452498Z","title":"Rethinking centered kernel alignment in knowledge distillation","venue":null,"work_id":"2a2cc369-8718-430a-b1e4-212e3e1be54b","year":2024},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":98,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:06.283299Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:538f8b14b06ce04bb8ea44e49a7d6beffe9e6df3a7f9e266c8466736f2538f25","observation_id":"866980af-5200-462a-9911-ad13787bcfb0","resolution":{"observed_at":"2026-08-07T04:43:06.457244Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T04:43:06.442353Z","title":"converging","venue":null,"work_id":"d6af4939-e0e9-4a36-bedb-b6a402116fdd","year":null},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":99,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:06.286830Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:8cd38a4757a4e654668c7912f19d4e849fcda092d4119ff4bd58fe716007a647","observation_id":"87e83335-3150-4c53-841d-a967306dacab","resolution":{"observed_at":"2026-08-07T04:43:06.445184Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T04:43:06.432556Z","title":"The input size is 224","venue":null,"work_id":"0f8632f0-acb6-4197-a84f-8e5bcbdfed65","year":null},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":100,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:06.290366Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:e635827d5e042016265b63030ecafeea278a0a96b77bc4f317124684b11b5a07","observation_id":"33ce880c-9268-438f-813b-4fe8bae06788","resolution":{"observed_at":"2026-08-07T04:43:06.435875Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T04:43:06.422216Z","title":"The input size is 256","venue":null,"work_id":"523edb77-405d-4b8d-b597-7e6b45cde086","year":null},"citing_paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models","version":1},"reference_index":101,"source":"pdf_text","source_observed_at":"2026-08-07T04:43:06.293736Z"},"links":{"citing_paper":"/paper/2506.09955"},"observation_digest":"sha256:7b327fc445e7279fa30a2514f8ff29d44011c0be1b666239883d96e654516e20","observation_id":"9cfbeec4-22dd-420e-b3aa-a175d89a9edb","resolution":{"observed_at":"2026-08-07T04:43:06.425311Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2506.09955","last_updated":"2025-06-11T17:28:52Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T04:34:33.866301Z","submitted_at":"2025-06-11T17:28:52Z","title":"Canonical Latent Representations in Conditional Diffusion Models"},"reference_resolution":{"displayed":100,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":53,"verified_exact":0,"verified_fuzzy":47},"total_outbound_references":102},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 100 of 102 outbound references and 0 inbound Pith citation observations for arXiv:2506.09955."}