{"as_of":"2026-08-17T05:53:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3045c2a52dc1a335cc2c24f846053bc408f9e267d618b38e262bcb83805ce8f1","coverage":[{"denominator":95,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":95,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-07T17:54:09.140773Z","state":"measured"},{"denominator":95,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":95,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-16T06:30:59.297886+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/2607.05319/citation-record","integrity":"/paper/2607.05319/integrity","json":"/paper/2607.05319/citation-record.json","paper":"/paper/2607.05319"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-07T18:04:01.073857Z","title":"Rezero is all you need: Fast convergence at large depth","venue":null,"work_id":"2630b7d9-4080-4933-9fbb-875593eb39d3","year":2021},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:7603f98b5b3e88e20e21957808472d15f9a720eb79b14f29d3e62d07fa1f8c3d","observation_id":"024fdea8-18bf-4f4c-ad39-026c9bb9ae3f","resolution":{"observed_at":"2026-07-07T18:04:01.075053Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-07-07T18:04:01.051994Z","title":"Representation learning: A review and new perspectives","venue":null,"work_id":"6e1d2b75-99c8-43a0-b3b3-babe2d7ec012","year":2013},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:f4f37e246f6ad92f240db741245bd1cf8afc1ec786e6ba63bf34be73217e79f3","observation_id":"4e619a42-5605-4627-89c8-4e1a41ea4f0c","resolution":{"observed_at":"2026-07-07T18:04:01.053283Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-07-07T18:04:01.087808Z","title":"Zimmermann, Yash Sharma, Bernhard Schölkopf, Julius V on Kügelgen, and Wieland Brendel","venue":null,"work_id":"26735087-3d52-47d6-937c-09c29bbd7f52","year":2023},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:5585268d2509cd75bec03c70bbc518edce24734f1c38fde957da59fec9df8b51","observation_id":"f2406ba8-47a3-4212-a5f8-8a60ffd08350","resolution":{"observed_at":"2026-07-07T18:04:01.089305Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2411.07784","last_updated":"2024-11-12T13:33:26Z","snapshot_observed_at":"2026-08-16T21:18:23.553917Z","submitted_at":"2024-11-12T13:33:26Z","title":"Interaction Asymmetry: A General Principle for Learning Composable Abstractions","version":1},"cited_work":{"arxiv_id":"2411.07784","doi":null,"metadata_source":"pith","pith_arxiv_id":"2411.07784","snapshot_observed_at":"2026-07-07T18:04:00.509951Z","title":"Interaction asymmetry: A general principle for learning composable abstrac- tions.arXiv","venue":"cs.LG","work_id":"603ad223-c093-4ab0-8850-3306d31c3068","year":2024},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"cited_paper":"/paper/2411.07784","citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:0e9cc03ba8e6a270195f5d161cb0071f63df667a2c95f58420a9b806cf5b7115","observation_id":"174ca791-b3bb-48c0-89c7-2d7f83360673","resolution":{"observed_at":"2026-07-07T18:04:00.511414Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1804.03599","last_updated":"2018-04-10T15:48:18Z","snapshot_observed_at":"2026-08-14T19:27:23.675013Z","submitted_at":"2018-04-10T15:48:18Z","title":"Understanding disentangling in $\\beta$-VAE","version":1},"cited_work":{"arxiv_id":"1804.03599","doi":null,"metadata_source":"pith","pith_arxiv_id":"1804.03599","snapshot_observed_at":"2026-07-07T18:04:00.565090Z","title":"Understanding disentangling in $\\beta$-VAE","venue":"stat.ML","work_id":"f6c67226-d4af-423d-9a12-877de69325da","year":2018},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"cited_paper":"/paper/1804.03599","citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:0f722f5828591ba3c715eafb1c7358847100f0458a6863b3ab5e685fd2eaedcf","observation_id":"e44a522e-06b1-4410-8bef-77f3c443a5e6","resolution":{"observed_at":"2026-07-07T18:04:00.566732Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1901.11390","last_updated":"2019-01-22T18:55:34Z","snapshot_observed_at":"2026-08-14T17:27:29.664717Z","submitted_at":"2019-01-22T18:55:34Z","title":"MONet: Unsupervised Scene Decomposition and Representation","version":1},"cited_work":{"arxiv_id":"1901.11390","doi":null,"metadata_source":"pith","pith_arxiv_id":"1901.11390","snapshot_observed_at":"2026-07-10T10:47:02.138605Z","title":"MONet: Unsupervised Scene Decomposition and Representation","venue":"cs.CV","work_id":"01a34599-2679-4d94-a0d0-4995da762d8c","year":2019},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"cited_paper":"/paper/1901.11390","citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:9238098c7554062fb0fa92de90a23d4fcbe8f22099dedf574c9ceee3a7e6034d","observation_id":"d72e55fe-642b-4f55-ba72-e88736b3d687","resolution":{"observed_at":"2026-07-07T18:04:00.556604Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2211.12737","last_updated":"2022-11-23T06:58:09Z","snapshot_observed_at":"2026-08-16T16:13:58.976523Z","submitted_at":"2022-11-23T06:58:09Z","title":"RoentGen: Vision-Language Foundation Model for Chest X-ray Generation","version":1},"cited_work":{"arxiv_id":"2211.12737","doi":null,"metadata_source":"pith","pith_arxiv_id":"2211.12737","snapshot_observed_at":"2026-07-07T18:04:00.558144Z","title":"Roentgen: vision-language foundation model for chest x-ray generation","venue":"cs.CV","work_id":"a516c793-b325-4494-a4be-dea871e98458","year":2022},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"cited_paper":"/paper/2211.12737","citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:b33d0a6cadb41183e485a1058fde80dff642880a7cdf1bf03c0941ccc566f175","observation_id":"4e6df1f1-baa2-470f-a1c4-a2cf41d751e0","resolution":{"observed_at":"2026-07-07T18:04:00.563306Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-07-07T18:04:01.059557Z","title":"Attend-and-excite: Attention-based semantic guidance for text-to-image diffusion models","venue":null,"work_id":"aa52c54c-7c6d-4899-873a-62144b615ae2","year":2023},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:c87f7412e35587546eaa0540179fd3721b9bed8d98a90fdc84eb79e351b513c8","observation_id":"61672977-f633-4bef-ac1c-b6956139044c","resolution":{"observed_at":"2026-07-07T18:04:01.060769Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-07-07T18:04:01.081078Z","title":"Towards stabilized and efficient diffusion transformers through long-skip-connections with spectral constraints","venue":null,"work_id":"4d25d79b-663e-4dec-b726-28ce790ecc42","year":2025},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:7374453f3793658b77f027f47a3b2516244f257b0c17d636c03350164882d860","observation_id":"b934f9fc-4220-4afc-b0ff-6040be4e2a1a","resolution":{"observed_at":"2026-07-07T18:04:01.082995Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-07-07T18:04:01.092435Z","title":"Isolating sources of disentanglement in variational autoencoders","venue":null,"work_id":"a7d9d7bc-be0c-4ee7-a409-2ae6e68288a0","year":2018},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:45953ee39b52acb15d59e024878b3d4f8a18671e6f77896053ca07f48dbe7d55","observation_id":"73a09c8a-4291-4939-9476-da8eea5a3c36","resolution":{"observed_at":"2026-07-07T18:04:01.093988Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2301.10972","last_updated":"2023-05-21T07:07:55Z","snapshot_observed_at":"2026-08-16T16:00:04.166629Z","submitted_at":"2023-01-26T07:37:22Z","title":"On the Importance of Noise Scheduling for Diffusion Models","version":4},"cited_work":{"arxiv_id":"2301.10972","doi":null,"metadata_source":"pith","pith_arxiv_id":"2301.10972","snapshot_observed_at":"2026-07-07T18:04:00.522746Z","title":"On the importance of noise scheduling for diffu- sion models","venue":"cs.CV","work_id":"1783cbc7-505c-4ebc-82f3-86877ef131b3","year":2023},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"cited_paper":"/paper/2301.10972","citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:8d78933e115a2ca371785b441b06feed05134841d78552dd7006e9055b8a8626","observation_id":"cd4334f6-67f9-4aef-8834-18fdad19b943","resolution":{"observed_at":"2026-07-07T18:04:00.525703Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-07-07T18:04:00.992692Z","title":"Infogan: Interpretable representation learning by information maximizing generative adversarial nets","venue":null,"work_id":"c81e2632-871f-4764-b17d-2ca9c47090f9","year":2016},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:c23172ea9cf9921ed34705a5dc5a515df516363226c705ead67c4804f49ca772","observation_id":"f311d332-59fe-4fda-8046-1c25f5a183d8","resolution":{"observed_at":"2026-07-07T18:04:00.993927Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2602.05214","last_updated":"2026-05-10T15:23:37Z","snapshot_observed_at":"2026-07-06T22:44:37.993093Z","submitted_at":"2026-02-05T02:14:36Z","title":"Disentangled Representation Learning via Flow Matching","version":2},"cited_work":{"arxiv_id":"2602.05214","doi":null,"metadata_source":"pith","pith_arxiv_id":"2602.05214","snapshot_observed_at":"2026-07-07T18:04:00.592375Z","title":"Disentangled Representation Learning via Flow Matching","venue":"cs.LG","work_id":"4a3a2441-4616-427f-8d6d-109ce9a10bfc","year":2026},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"cited_paper":"/paper/2602.05214","citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:32456e3266c5dfbb8367183b09ee127d96070e2128cd25cc1a8359643b78b8c3","observation_id":"df7ccafd-69ae-4038-9b0b-35654b1aa2f4","resolution":{"observed_at":"2026-07-07T18:04:00.593902Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1904.10509","last_updated":"2019-04-23T19:29:47Z","snapshot_observed_at":"2026-08-16T10:03:03.268538Z","submitted_at":"2019-04-23T19:29:47Z","title":"Generating Long Sequences with Sparse Transformers","version":1},"cited_work":{"arxiv_id":"1904.10509","doi":"10.48550/arxiv.1904.10509","metadata_source":"pith","pith_arxiv_id":"1904.10509","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Generating Long Sequences with Sparse Transformers","venue":"cs.LG","work_id":"c5b81688-45ee-4a9a-b095-e6290f45cb6c","year":2019},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"cited_paper":"/paper/1904.10509","citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:20d39aabe7dc0b79359e05aa34cea8e45a2c26c831e5d6ac32d4145abdddab84","observation_id":"aaecf261-e93a-463a-917a-f84147d07d52","resolution":{"observed_at":"2026-07-07T18:04:00.612345Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-07-12T21:49:59.71041+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-12T21:49:59.71041+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-07-07T18:04:00.983640Z","title":"Perception prioritized training of diffusion models","venue":null,"work_id":"ed73e282-be75-4b3d-8b54-011f6c4ca73b","year":2022},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:14488b4386c0a47044f630d8ca2cd810e0de8f784d00e38b759587719daccfd1","observation_id":"a7c6252f-8e66-4438-a436-cebc733d7b43","resolution":{"observed_at":"2026-07-07T18:04:00.984775Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-07-07T18:04:00.996409Z","title":"Building machines that learn and think with people","venue":null,"work_id":"f894c096-44c3-4f4e-afbf-9d4979422ed9","year":2024},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:2845a098a54e6d41b479106472bc3ee2ecf5abe1f609b7f3b6613d1948b9273a","observation_id":"00742720-91f3-4904-9537-ca153b1fb368","resolution":{"observed_at":"2026-07-07T18:04:00.997598Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-07-07T18:04:01.053909Z","title":null,"venue":null,"work_id":"a0f12393-6f40-4701-ae44-184c1b678bac","year":2018},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:b1b2c2e0ab8bdf5c321a7d45d3da345ad01fe31744aacd2f180043ab4a89d557","observation_id":"6897e83a-3d76-44cd-93ae-71e81b365a21","resolution":{"observed_at":"2026-07-07T18:04:01.055222Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1907.13052","last_updated":"2020-11-23T10:31:22Z","snapshot_observed_at":"2026-08-14T16:00:14.713839Z","submitted_at":"2019-07-30T16:22:39Z","title":"GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations","version":4},"cited_work":{"arxiv_id":"1907.13052","doi":null,"metadata_source":"pith","pith_arxiv_id":"1907.13052","snapshot_observed_at":"2026-07-07T18:04:00.614585Z","title":"arXiv , Author =:1907.13052 , Primaryclass =","venue":"cs.LG","work_id":"0baeb5ba-7db3-4bc4-84e0-8d71094ae6ed","year":2019},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"cited_paper":"/paper/1907.13052","citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:7fc4b1999536e88255da396add6e660f05005c044a08eab890cd05d5f76c6a68","observation_id":"efc50de7-96b4-401f-8752-dd0468465d50","resolution":{"observed_at":"2026-07-07T18:04:00.615984Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-07-07T18:04:00.999777Z","title":"Taming transformers for high-resolution image synthesis","venue":null,"work_id":"78c48128-f71d-483e-a835-f5f08e80afd7","year":2021},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:844a33bf8d8034e8ef3428c4c53b828176969c09b6105e3e3a8fe31157681752","observation_id":"71f03a2e-6da4-45c4-86bd-e5265df08402","resolution":{"observed_at":"2026-07-07T18:04:01.001045Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-07-07T18:04:01.048617Z","title":null,"venue":null,"work_id":"3a71e235-93d5-4446-acbe-02cedbe67872","year":2010},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:f4c0b020c05c1f71ec442622e12d91fbeafbbd762c38912011a851deaad1a22e","observation_id":"053f425c-1530-4b27-85c5-1d7b68d0586e","resolution":{"observed_at":"2026-07-07T18:04:01.049698Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-07-07T18:04:01.032838Z","title":"On the transfer of inductive bias from simulation to the real world: a new disen- tanglement dataset","venue":null,"work_id":"28470dea-82e7-46ee-9e6f-b309bdc70b04","year":2019},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:85047c7e0ce1268422b5e0d751a813b0a67a030f45ed33133b996eedc5f3ce1f","observation_id":"db3b8cac-fa19-486e-9117-45c305d9c328","resolution":{"observed_at":"2026-07-07T18:04:01.034017Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-07-07T18:04:01.016764Z","title":"Multi-object repre- sentation learning with iterative variational inference","venue":null,"work_id":"29576be6-902b-4b01-9cd9-45e259600292","year":2019},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:ee7906bf0e25a092705d85dbf7854a8911a4e299dd98582d6cd576b5234bdb28","observation_id":"b0d157cf-9e2b-4f71-9bbc-be1e5f66ad6f","resolution":{"observed_at":"2026-07-07T18:04:01.017932Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-07-07T18:04:01.013090Z","title":"Efficient diffusion training via min-snr weighting strategy","venue":null,"work_id":"a2598ae3-3679-48b4-9a4b-498afa044766","year":2023},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:9a5985fa539d2b3a6d52d8f05847c40a40d04c269f7545360ae2a98a5c013641","observation_id":"83744c04-96fa-4deb-8fc0-7da857f4fa0c","resolution":{"observed_at":"2026-07-07T18:04:01.014220Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2602.17270","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-07T18:04:00.620880Z","title":"Unified latents (ul): How to train your latents","venue":null,"work_id":"633bf0a2-f752-4228-b608-e4221dc39438","year":2026},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:21d242707e6f86b17bcdf8ec6571984c9fb4444972f349eda421299108566f65","observation_id":"232f7a6b-9229-4cd7-b003-9c09fb6761f3","resolution":{"observed_at":"2026-07-07T18:04:00.622429Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2208.01626","last_updated":"2022-08-02T17:55:41Z","snapshot_observed_at":"2026-08-17T00:44:11.103098Z","submitted_at":"2022-08-02T17:55:41Z","title":"Prompt-to-Prompt Image Editing with Cross Attention Control","version":1},"cited_work":{"arxiv_id":"2208.01626","doi":"10.48500/arxiv.2208.01626","metadata_source":"pith","pith_arxiv_id":"2208.01626","snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"Prompt-to-Prompt Image Editing with Cross Attention Control","venue":"cs.CV","work_id":"196f7eef-d65a-47e4-b815-9a188f6aedcf","year":2022},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"cited_paper":"/paper/2208.01626","citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:8989514c170e8f91032f58706f1f7f8724e80d6311fdb2605fad75842af9bd74","observation_id":"4e33d1b5-fae8-490a-be9b-bdcf778b5c79","resolution":{"observed_at":"2026-07-07T18:04:00.609130Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-07-07T18:04:01.083713Z","title":"beta-V AE: Learning basic visual concepts with a constrained variational framework","venue":null,"work_id":"420cce49-cb5a-4453-98ed-9ad5bacdcd6e","year":null},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:64f23ab61b8ca6fc4f5deff65c6fea805b8a138ffda70df298932a62a3523852","observation_id":"9a1fef3a-7403-4faf-bdc9-2c8d6e99c58e","resolution":{"observed_at":"2026-07-07T18:04:01.085058Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-07-07T18:04:01.090067Z","title":null,"venue":null,"work_id":"0b33e3f4-43ea-4036-b6d7-c86ce356ca33","year":null},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:a6e234f97a0ad7db8e880f43706e27f0faddf00d3b961feb8ddc8376e494b634","observation_id":"7127c59b-d6a6-497b-8bc3-b1d3f892f6df","resolution":{"observed_at":"2026-07-07T18:04:01.091516Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-07-08T13:14:53.388480Z","title":"Denoising diffusion probabilistic models","venue":null,"work_id":"80d27c68-54aa-49bf-b4e5-f94cb73ea612","year":2020},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:8f25c975a2b8660fead24be24fc7355a823bf92f20370e97c80ccd809877e80a","observation_id":"a41f3242-0f6f-4500-923a-c2e31c3b7a55","resolution":{"observed_at":"2026-07-07T18:04:01.087051Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-07-07T18:04:01.066598Z","title":"simple diffusion: End-to-end diffusion for high resolution images","venue":null,"work_id":"8b055113-5974-4bdf-b47d-144c7f412b71","year":2023},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:8d5465a898e4fb4371e0f3ec347f2e2ff8ca461132e60216ea76ad71b108166e","observation_id":"977115df-8c4d-4432-a7d7-c55b5493ba5c","resolution":{"observed_at":"2026-07-07T18:04:01.067808Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.19324","last_updated":"2025-03-22T19:42:20Z","snapshot_observed_at":"2026-08-16T13:06:02.643386Z","submitted_at":"2024-10-25T06:20:06Z","title":"Simpler Diffusion (SiD2): 1.5 FID on ImageNet512 with pixel-space diffusion","version":2},"cited_work":{"arxiv_id":"2410.19324","doi":null,"metadata_source":"pith","pith_arxiv_id":"2410.19324","snapshot_observed_at":"2026-07-07T18:04:00.512591Z","title":"Simpler diffusion (SiD2): 1.5 FID on ImageNet512 with pixel-space diffusion","venue":"cs.CV","work_id":"745ef26a-c245-4843-a44d-629a12795773","year":2024},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"cited_paper":"/paper/2410.19324","citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:8c1c576becba16a4028dca3ba2a96b5b7696b5af8c17b56286b6c0e1fa587f68","observation_id":"cccc7ebf-e69d-4c89-bf76-89f0dac1663a","resolution":{"observed_at":"2026-07-07T18:04:00.514723Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1007/bf01908075","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Comparing partitions","venue":"Journal of Classification","work_id":"44070bd0-e39d-4a62-93c0-49701460af4e","year":1985},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:312f5220f5fbb231143e568ab851c5281cbf52a6b43ecc18eb63915f57346179","observation_id":"1db3ed77-8423-453e-b4ef-c98d9adacf20","resolution":{"observed_at":"2026-07-07T18:04:00.446789Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-07-11T17:19:03.933703+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-11T17:19:03.933703+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-07-07T18:04:01.072146Z","title":"Soda: Bottleneck diffusion models for representation learning","venue":null,"work_id":"a272ac28-cd29-40ec-89d8-2ada8c2e7c25","year":2024},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:70541ae165cd46e979f08aa722f271f09571915a66aa41b47a1e426f654fc0fa","observation_id":"77921ac0-91f8-4380-9915-f92e5f0ed352","resolution":{"observed_at":"2026-07-07T18:04:01.073269Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.10834","last_updated":"2023-11-03T04:28:59Z","snapshot_observed_at":"2026-08-16T15:47:01.149971Z","submitted_at":"2023-03-20T02:40:16Z","title":"Object-Centric Slot Diffusion","version":5},"cited_work":{"arxiv_id":"2303.10834","doi":null,"metadata_source":"pith","pith_arxiv_id":"2303.10834","snapshot_observed_at":"2026-07-07T18:04:00.496460Z","title":"Object-centric slot diffusion","venue":"cs.CV","work_id":"5f76cd94-839b-41b0-b1f8-b66a345fe551","year":2023},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"cited_paper":"/paper/2303.10834","citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:249855fad8e0d2bf6e1e6c3d9b9e1e8904316d10c56e86d01a03efcc5694adfe","observation_id":"fd3c8af0-0d63-4174-b54d-0e416b751d43","resolution":{"observed_at":"2026-07-07T18:04:00.497867Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-07-07T18:04:01.070403Z","title":"Disentangling disentangled representations: Towards improved latent units via diffusion models","venue":null,"work_id":"a72da97c-e185-4fa7-a292-1cd5df5e9fb6","year":2025},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:b621ab47b6513ce9697c2b71d6c23a3756563fdbac5afbe7f9190bf6326ee1e9","observation_id":"3285b1e5-8c26-4bc2-bcc2-f6b643c91cc9","resolution":{"observed_at":"2026-07-07T18:04:01.071587Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2405.00646","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-07T18:04:00.526874Z","title":"Learning to compose: Improving object centric learning by injecting compositionality","venue":null,"work_id":"fdd793ff-80a3-44c0-9768-fe50b098bca5","year":2024},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:363ae8c46c170d08522a9f937f6ad5705ff08735f837647560dd6c58e4ca64f2","observation_id":"f23e17c7-5337-4469-9cc5-9ddf22db24f1","resolution":{"observed_at":"2026-07-07T18:04:00.528697Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2510.21402","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-07T18:04:00.499388Z","title":"Disentangled representation learning via modular compositional bias","venue":null,"work_id":"b9da7c47-505f-4104-97a2-c6f00b03b98f","year":2025},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:b7b66cec9f5d42a0312cb8a6c6bbc8af37d43a047a665f205f430b7542455206","observation_id":"9e5d6abd-6a49-4f90-a5cf-9ffc7a144dc5","resolution":{"observed_at":"2026-07-07T18:04:00.500998Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-07-07T18:04:01.068626Z","title":"ClevrTex: A Texture-Rich Benchmark for Unsupervised Multi-Object Segmentation","venue":null,"work_id":"b3b3c9ed-d987-4336-a829-a2103bfba66a","year":2021},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:908c6dd280f929f0c805bd73884cd42d2d99959dde5cec64299ebd99467e5c94","observation_id":"cfe077f5-0168-4192-9342-4a650b12e350","resolution":{"observed_at":"2026-07-07T18:04:01.069835Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-07-07T18:04:01.077423Z","title":"Elucidating the design space of diffusion-based generative models","venue":null,"work_id":"a153926e-f774-4f44-b2c7-d32d51338933","year":2022},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:1d56af75187ee6b55ae149f7dadb729950c8dfa303000b382ef51491705f3c54","observation_id":"f7cf1494-275a-48a0-83d1-6370da04ed56","resolution":{"observed_at":"2026-07-07T18:04:01.078646Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.03606","last_updated":"2024-05-25T16:44:12Z","snapshot_observed_at":"2026-08-16T14:37:06.072203Z","submitted_at":"2023-12-06T16:53:17Z","title":"DiffusionSat: A Generative Foundation Model for Satellite Imagery","version":2},"cited_work":{"arxiv_id":"2312.03606","doi":null,"metadata_source":"pith","pith_arxiv_id":"2312.03606","snapshot_observed_at":"2026-07-07T18:04:00.542859Z","title":"Diffusionsat: A generative foundation model for satellite imagery","venue":"cs.CV","work_id":"e5198af3-50e3-404f-9692-3416ce4f3b6d","year":2023},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"cited_paper":"/paper/2312.03606","citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:4a1ba27a9fad85954feaf19683fa397f75efc0231e9b8b9d5e0daa877043f8c2","observation_id":"b19aeb88-ec70-4204-9606-f99d989b0d66","resolution":{"observed_at":"2026-07-07T18:04:00.546663Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-07-07T18:04:01.057917Z","title":"Disentangling by factorising","venue":null,"work_id":"9381dc12-0b3e-4776-8533-a57a3e4db4e0","year":2018},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:c0d8287b88c0d109c8ef31cd927b29fc837268046cd71a7bc7f10460f92b83aa","observation_id":"bcbab0ab-886e-4623-a544-9056ae5902b7","resolution":{"observed_at":"2026-07-07T18:04:01.058971Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-07-07T18:04:01.063051Z","title":"Denoising task difficulty- based curriculum for training diffusion models","venue":null,"work_id":"e046a01c-551f-4209-9fff-235e12b56177","year":2025},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:0ebb90a35a6e988d31bbeb7cb8f92f5fe8faa2791d99ff85e23b813a09da4973","observation_id":"4c00b3a9-651a-49f3-9db4-4d5e064c4fe2","resolution":{"observed_at":"2026-07-07T18:04:01.064217Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2411.09998","doi":"10.48550/arxiv.2411.09998","metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Huiwen Chang, Han Zhang, Lu Jiang, Ce Liu, and William T","venue":"arXiv (Cornell University)","work_id":"92bc619a-4ec9-4d24-810b-890236580024","year":2024},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:d8c15a9a2aa78fcee642d87cb7b2a852aa34eba672dad3c55eee28a573a04cda","observation_id":"012be067-4dd4-448d-8cc7-d0b60e0a2657","resolution":{"observed_at":"2026-07-07T18:04:00.531663Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-07-07T18:04:01.055916Z","title":"Understanding diffusion objectives as the elbo with simple data augmentation","venue":null,"work_id":"fb3538d3-f799-44ea-bc0d-f4f8e667c699","year":2023},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:996bfaca08200bc4246ba2a99ae0cbe9226165e58d3110945ec1b4036930d2af","observation_id":"b00ad3b6-f4e3-424e-b4d5-6c78dba86039","resolution":{"observed_at":"2026-07-07T18:04:01.057306Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-07-07T18:04:01.079263Z","title":"Variational diffusion models","venue":null,"work_id":"84d291bc-d860-481b-8cd3-6c05cc4293ab","year":2021},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:3e58fd75a29b68b080eeee864b174c44de9f7699b42544b8e74d409df646915a","observation_id":"34aa4697-fa34-4405-be9e-fc553c6b7780","resolution":{"observed_at":"2026-07-07T18:04:01.080396Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.15742","last_updated":"2025-06-24T05:31:03Z","snapshot_observed_at":"2026-08-14T01:48:52.921086Z","submitted_at":"2025-06-17T20:18:23Z","title":"FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space","version":2},"cited_work":{"arxiv_id":"2506.15742","doi":"10.48550/arxiv.2506.15742","metadata_source":"pith","pith_arxiv_id":"2506.15742","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space","venue":"cs.GR","work_id":"5dfe19d5-3541-4803-8fe9-3c8b9e29b281","year":2025},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"cited_paper":"/paper/2506.15742","citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:3887ba594927d570f9bdeeabde398bc225f01bd0f148d06a0f18238bfa6ba814","observation_id":"5a574eab-a4e3-4e54-9e0e-cc1520298484","resolution":{"observed_at":"2026-07-07T18:04:00.540670Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-05-25T00:53:20.581238+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-25T00:53:20.581238+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-07-07T18:04:01.061356Z","title":"Repa-e: Unlocking vae for end-to-end tuning of latent diffusion transformers","venue":null,"work_id":"fbd3049c-8814-4ae7-9c1d-e35559ab065e","year":2025},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:618c954302a546d3ee1e2763f122739abc27e884d3e337fae69f438a19b9a563","observation_id":"6687e6c8-5ea3-4eda-97d4-727918db02b0","resolution":{"observed_at":"2026-07-07T18:04:01.062480Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2511.13720","last_updated":"2026-01-07T05:36:57Z","snapshot_observed_at":"2026-07-06T22:36:08.495952Z","submitted_at":"2025-11-17T18:59:57Z","title":"Back to Basics: Let Denoising Generative Models Denoise","version":2},"cited_work":{"arxiv_id":"2511.13720","doi":"10.48550/arxiv.2511.13720","metadata_source":"pith","pith_arxiv_id":"2511.13720","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Back to Basics: Let Denoising Generative Models Denoise","venue":"cs.CV","work_id":"37973de8-a5e6-4d92-897b-a98fa9f7f2f3","year":2025},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"cited_paper":"/paper/2511.13720","citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:8217568ffac67171cc3ca202e5dc5bfb085acdc0997f0a7d9618674aa1f2519d","observation_id":"93e5497b-56b7-4405-95c4-065f2d76876d","resolution":{"observed_at":"2026-07-07T18:04:00.503653Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2502.05743","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-07T18:04:00.548813Z","title":"Understand- ing representation dynamics of diffusion models via low-dimensional modeling","venue":null,"work_id":"05905920-d3cf-41cb-b063-05674caf71ce","year":2025},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:6c2ad8d7b3347a9e48c204ba765a5b9107014d0ae7100904b096e9e500978920","observation_id":"97004347-88dd-4d4d-a269-9873c235e63d","resolution":{"observed_at":"2026-07-07T18:04:00.551608Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2210.02747","last_updated":"2023-02-08T15:46:05Z","snapshot_observed_at":"2026-08-16T02:30:42.660030Z","submitted_at":"2022-10-06T08:32:20Z","title":"Flow Matching for Generative Modeling","version":2},"cited_work":{"arxiv_id":"2210.02747","doi":"10.1038/s41467-024-47656-z","metadata_source":"pith","pith_arxiv_id":"2210.02747","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Flow Matching for Generative Modeling","venue":"cs.LG","work_id":"6edb71c4-5d64-40af-a394-9757ea051a36","year":2022},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"cited_paper":"/paper/2210.02747","citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:1495f54c8a5524ac1de65de313bd3b07c48844533768441e0ed541a901ba6d72","observation_id":"8b824e02-93d7-4bce-8caf-58427ac007a9","resolution":{"observed_at":"2026-07-07T18:04:00.521405Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-06-01T22:57:59.860918+00:00","source":"crossref_status_cache"},{"observed_at":"2026-06-01T22:57:59.860918+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.02747","last_updated":"2025-02-26T10:49:33Z","snapshot_observed_at":"2026-08-16T14:03:56.951368Z","submitted_at":"2024-04-03T13:44:41Z","title":"Faster Diffusion via Temporal Attention Decomposition","version":3},"cited_work":{"arxiv_id":"2404.02747","doi":null,"metadata_source":"pith","pith_arxiv_id":"2404.02747","snapshot_observed_at":"2026-07-07T18:04:00.516299Z","title":"Faster diffu- sion via temporal attention decomposition","venue":"cs.CV","work_id":"8284a147-7818-43f4-ae61-e7da648212d6","year":2024},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"cited_paper":"/paper/2404.02747","citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:8badbb958c0e0ccddfe9d455a456e1f36d50850b705dd9b26f74f5e5d7f4db84","observation_id":"4fc5ad68-dcf1-414b-a1bd-ec863c6e63f0","resolution":{"observed_at":"2026-07-07T18:04:00.518677Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2505.20772","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-07T18:04:00.533774Z","title":"Metaslot: Break through the fixed number of slots in object-centric learning","venue":null,"work_id":"b652e943-b344-4def-8db2-a2133a43aea1","year":2025},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:076ab93de90514c578e2db02da50f5f68a265334742995a22efccb0bf7337611","observation_id":"3171119a-94c0-4dec-8bf1-b8ff64d2e7f5","resolution":{"observed_at":"2026-07-07T18:04:00.535462Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-07-07T18:04:01.075627Z","title":"Challenging common assumptions in the unsupervised learning of disentangled representations","venue":null,"work_id":"56e088b8-9c3c-4ad0-8aac-cb5d61a2ebc7","year":null},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:da9f9c92b0f34fcac615fb4bf6d3faa20d92a32065ac832d30dae1eda2001ae2","observation_id":"8a9db000-f757-4c6c-9501-a0d548929632","resolution":{"observed_at":"2026-07-07T18:04:01.076829Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-07-07T18:04:01.034559Z","title":"Object-centric learning with slot attention","venue":null,"work_id":"e1a86156-4af0-40ab-a766-90231dfa9d20","year":2020},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:16e9c628d04afbce7a9cba5a3e1469a92dee1c2c320f18038c1999cdac065d1b","observation_id":"0c9a8bdf-8848-4d6e-bd72-80291bc12c29","resolution":{"observed_at":"2026-07-07T18:04:01.035730Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.15170","last_updated":"2024-02-23T08:05:23Z","snapshot_observed_at":"2026-08-16T14:15:59.292419Z","submitted_at":"2024-02-23T08:05:23Z","title":"The Surprising Effectiveness of Skip-Tuning in Diffusion Sampling","version":1},"cited_work":{"arxiv_id":"2402.15170","doi":null,"metadata_source":"pith","pith_arxiv_id":"2402.15170","snapshot_observed_at":"2026-07-07T18:04:00.583514Z","title":"The Surprising Effectiveness of Skip-Tuning in Diffusion Sampling","venue":"cs.LG","work_id":"c679e6d1-090f-4225-9bb2-1ae7d146e09d","year":2024},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"cited_paper":"/paper/2402.15170","citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:a7851fd9a89e0b94697737db2385e56845813a01fed8235d48462baaf19afbdd","observation_id":"6a52c363-3f14-479b-9eda-df2aa5c870e6","resolution":{"observed_at":"2026-07-07T18:04:00.585860Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-07-10T01:46:41.692083Z","title":"Sit: Exploring flow and diffusion-based generative models with scalable interpolant transformers","venue":null,"work_id":"a08d2a16-a0ba-4b60-afd1-b5ffb9f4de4f","year":2024},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:9b9314660a1b8d7eb98e548943d4e3c6b9183bfe1b27d51e38f74b0511c742a4","observation_id":"a950b1b4-b178-4c62-9ad8-f99684974102","resolution":{"observed_at":"2026-07-07T18:04:01.048053Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-07-07T18:04:01.029475Z","title":"Improved denoising diffusion probabilistic models","venue":null,"work_id":"78c2a00a-5834-4ddc-88e9-b6dd7bca3887","year":2021},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:80c9d352398e64e3d4e8897de69befff66587e5b15d0e594c7256d751aaad6c2","observation_id":"86be7f4a-b53f-4f0a-8c20-58bdb41a2aa5","resolution":{"observed_at":"2026-07-07T18:04:01.030578Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-07-07T18:04:01.027597Z","title":"Compositional abilities emerge multiplicatively: Exploring diffusion models on a synthetic task","venue":null,"work_id":"976b04be-e31e-4f8d-8d42-e4275924224b","year":2023},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:7b35af963b16fb5b4cca322521e17279c89cf584594981f602ca0825f1c6b3c6","observation_id":"617c2141-d666-4d24-9fa2-5bbd9c4f8165","resolution":{"observed_at":"2026-07-07T18:04:01.028905Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2304.07193","last_updated":"2024-02-02T10:24:09Z","snapshot_observed_at":"2026-08-11T10:12:11.384939Z","submitted_at":"2023-04-14T15:12:19Z","title":"DINOv2: Learning Robust Visual Features without Supervision","version":2},"cited_work":{"arxiv_id":"2304.07193","doi":"10.48550/arxiv.2304.07193","metadata_source":"pith","pith_arxiv_id":"2304.07193","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"DINOv2: Learning Robust Visual Features without Supervision","venue":"cs.CV","work_id":"26b304e5-b54a-4f26-be7e-83299eca52e4","year":2023},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"cited_paper":"/paper/2304.07193","citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:dd2a3665215fe6351a4a772574f95a9815891c66fa10a73a4efe27aee20babe3","observation_id":"5cad4b2a-c550-4926-8d84-3c7398308290","resolution":{"observed_at":"2026-07-07T18:04:00.574699Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-07-07T18:04:00.990700Z","title":"Scikit- learn: Machine learning in python","venue":null,"work_id":"c5039a47-3344-4402-8ea3-c5146bfc7fab","year":2011},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:2fa14ca317947ccc55c177c009b41a3803dc296a7c90c08d969bbb0d005bf34d","observation_id":"f5326fe4-1563-43b7-872f-ed00ee5b0ae7","resolution":{"observed_at":"2026-07-07T18:04:00.992131Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-07-07T18:04:00.987123Z","title":"Scalable diffusion models with transformers","venue":null,"work_id":"37d0e719-864c-45b0-9652-1e73f06e260a","year":2023},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:d0e62aaff1318469c4ebc9dceaee91827cbb710f556bb9e16a85cf44b0ddb606","observation_id":"906cf5a1-4ac0-42bf-9ac3-dc59e8549b08","resolution":{"observed_at":"2026-07-07T18:04:00.988308Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-07-07T18:04:01.036320Z","title":"Film: Visual reasoning with a general conditioning layer","venue":null,"work_id":"b0ae75e0-8e63-4a82-a889-6637cc42d57e","year":2018},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:f83baab8f6993ab79400e2cb8d2badfc250ff95fbc71bd50039bc354558e6df0","observation_id":"8460b9c1-eaa5-4b71-b0ab-1cf28c4753f1","resolution":{"observed_at":"2026-07-07T18:04:01.037516Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-07-07T18:04:01.011246Z","title":"The logical primitives of thought: Empirical foundations for compositional cognitive models","venue":null,"work_id":"b2a0f295-6306-4b24-be92-b6df8d65a8c3","year":2016},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:63d172cc1a729a9fe764f72dce8b6c64687228625f06a19af770fc3e6a250909","observation_id":"6dc3b331-625b-4fd5-8419-2394a6d2ed26","resolution":{"observed_at":"2026-07-07T18:04:01.012533Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-07-07T18:04:01.039826Z","title":"Diffusion autoencoders: Toward a meaningful and decodable representation","venue":null,"work_id":"62be2b7e-2c10-44ff-93d0-5fd6c5d15abb","year":2022},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:822357df458fd210b4442cad57fcb2b696905a3e2ee767ee355ba9d15e2da874","observation_id":"e5475ba0-9405-4ce4-9b12-1e6b2badceb5","resolution":{"observed_at":"2026-07-07T18:04:01.040945Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-07-07T18:04:01.041689Z","title":null,"venue":null,"work_id":"fcf059d4-1ec3-4259-b08d-fc87e615c408","year":1971},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:c9ce4319c38aec04d69803a4cfe4adaa59f7e2c440b8499174e09e3a9fb5c66e","observation_id":"93a08c0e-155d-4117-823d-aecb6ce0b28a","resolution":{"observed_at":"2026-07-07T18:04:01.042770Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-07-07T18:04:00.998198Z","title":"Deep visual analogy- making","venue":null,"work_id":"b5d25016-221c-41a1-b9d8-a9dfcac039ae","year":2015},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:7909392d4ae64b9e7bd1065f768da2d6d2cec2af7e68696308517cbb00a3e994","observation_id":"fc6d13a5-0575-4e0a-9b87-1dbaedc846cf","resolution":{"observed_at":"2026-07-07T18:04:00.999233Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-07-07T18:04:00.985328Z","title":"Learning disentangled representation by exploiting pretrained generative models: A contrastive learning view","venue":null,"work_id":"e7ccd2e2-524c-4e72-b9c8-aef7d07c20c5","year":2022},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:be236205448972de10d20a7e35f4bbc337cef9c7ccb2e01a0ea73ef60f2a9709","observation_id":"cdca0c91-15b7-4b2a-98e0-2570217371fc","resolution":{"observed_at":"2026-07-07T18:04:00.986548Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-07-07T18:04:01.043320Z","title":"Demystifying variational diffusion models","venue":null,"work_id":"59f0b28c-9845-48eb-b3b8-b0896280dca5","year":2025},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:cd664e9be4caef91754ae148108cad1e75bc1e5cd94e280727668f40bb3b56ed","observation_id":"a1882e54-01aa-498f-9fbd-a2bfb155fe4d","resolution":{"observed_at":"2026-07-07T18:04:01.044457Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-07-07T18:04:01.022008Z","title":"High- resolution image synthesis with latent diffusion models","venue":null,"work_id":"512e89af-0b17-4696-9249-68c37e6eb68b","year":2022},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:1712f8d72f1aa3289af5a505c47d1280bb83fc8298d266d7b415315e8b7d1100","observation_id":"1d793b57-d4cc-4868-bfb6-c6b29e59ac47","resolution":{"observed_at":"2026-07-07T18:04:01.023167Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-07-10T01:46:41.705184Z","title":"U-net: Convolutional networks for biomedical image segmentation","venue":null,"work_id":"b114346e-512c-4e00-a712-991c1c5df538","year":2015},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:2748af3e962c2cd3165f1691c07cbf4b41b11d31f8ccc8561bbaafdddd2902d9","observation_id":"b5fa00f8-ab70-4fce-97fa-eefbd7c11b46","resolution":{"observed_at":"2026-07-07T18:04:00.990123Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-07-07T18:04:01.094745Z","title":"Image super-resolution via iterative refinement","venue":null,"work_id":"00168652-21c7-484a-8205-7888ad475276","year":2022},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:b8b1e4bbf264ba0edaa1d7723fa045867e6de7fe29f38cf0d43a3dfefc07e8d3","observation_id":"0ba2d691-1d33-4fb7-af52-bdefd963e28c","resolution":{"observed_at":"2026-07-07T18:04:01.096503Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2202.00512","last_updated":"2022-06-07T09:17:35Z","snapshot_observed_at":"2026-08-12T01:14:44.484432Z","submitted_at":"2022-02-01T16:07:25Z","title":"Progressive Distillation for Fast Sampling of Diffusion Models","version":2},"cited_work":{"arxiv_id":"2202.00512","doi":"10.48550/arxiv.2202.00512","metadata_source":"pith","pith_arxiv_id":"2202.00512","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Progressive Distillation for Fast Sampling of Diffusion Models","venue":"cs.LG","work_id":"fd04f498-ff85-4de3-bcc7-31ef072b2ceb","year":2022},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"cited_paper":"/paper/2202.00512","citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:f115483218ab6e9248cc1698cce6d5a03c8f16ab9d3fd2f4f26175357407bbb0","observation_id":"1100aad1-dabd-4a91-9d11-50a358c18c47","resolution":{"observed_at":"2026-07-07T18:04:00.508306Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-07-07T18:04:01.064800Z","title":"Learning factorial codes by predictability minimization","venue":null,"work_id":"6724af25-251c-4d13-b728-4456d9ce3186","year":1992},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:01ce96b7999694fc1f052edd2da5d3db997a0bc16f349914d8f0c8e5ab5993fb","observation_id":"895e49da-b6a9-46d9-8fa7-9e68df931790","resolution":{"observed_at":"2026-07-07T18:04:01.065958Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-07-07T18:04:01.001582Z","title":"Bridging the gap to real-world object-centric learning","venue":null,"work_id":"96437430-d69f-4554-b1d6-5f40080461c2","year":2023},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:123541cc76cd7a699668633163ec58d0a5bf8e39342f3738a4ae95db8eb84545","observation_id":"e8cd994b-d76a-4a9f-b009-6e5ae2f53a34","resolution":{"observed_at":"2026-07-07T18:04:01.002846Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1703.00810","last_updated":"2017-04-29T17:32:47Z","snapshot_observed_at":"2026-08-14T21:13:52.487817Z","submitted_at":"2017-03-02T14:53:14Z","title":"Opening the Black Box of Deep Neural Networks via Information","version":3},"cited_work":{"arxiv_id":"1703.00810","doi":"10.48550/arxiv.1703.00810","metadata_source":"pith","pith_arxiv_id":"1703.00810","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Opening the Black Box of Deep Neural Networks via Information","venue":"cs.LG","work_id":"3b14f412-2206-469d-bfd3-c387c75ea711","year":2017},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"cited_paper":"/paper/1703.00810","citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:1a0f245924de17198fe206f704ab4f432675c9bda9fa3a18205e962109db4c81","observation_id":"4c315775-67bb-4dab-a16a-20d4e037b0dd","resolution":{"observed_at":"2026-07-07T18:04:00.605363Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-07-11T19:50:18.979424+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-11T19:50:18.979424+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-07-07T18:04:01.007347Z","title":"Illiterate DALL-e learns to compose","venue":null,"work_id":"4ef4fc58-d489-486e-840b-49272e7c2ea5","year":2022},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:310569e78898894fe0e7ac78c5ab63a297c200bf0ee61a7c7b266271e5ec8566","observation_id":"4e8ded3c-b56c-43ba-a232-467081708f95","resolution":{"observed_at":"2026-07-07T18:04:01.008816Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-07-07T18:04:01.014962Z","title":"Glass: Guided latent slot diffusion for object-centric learning","venue":null,"work_id":"86291e41-8b98-4a4a-8beb-af6a1f27a54f","year":2025},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:1994da849d9df590eb19c00aff8195dab52e3c1e271388a70cd0bac1ccca5af7","observation_id":"006c155d-3b54-4f4d-9579-d690936a03ff","resolution":{"observed_at":"2026-07-07T18:04:01.016155Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-07-07T18:04:01.038076Z","title":"What the daam: Interpreting stable diffusion using cross attention","venue":null,"work_id":"1df60d52-9514-4c50-88fc-703e82f2043a","year":2023},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:a40ff304258c9fe6c239bb90caed7fa752508a5c963c3cb68952f9e1705fcd17","observation_id":"bfcd489d-026c-4ffb-b095-d4283b48a9b9","resolution":{"observed_at":"2026-07-07T18:04:01.039257Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-07-07T18:04:01.031108Z","title":"Zhang, Fanqing Meng, Chao Hong, Xiaotong Xie, Shaowei Liu, Enzhe Lu, Yunpeng Tai, Yanru Chen, Xin Men, Haiqing Guo, Y","venue":null,"work_id":"629aac09-2008-43d0-8600-71e9661956d2","year":2026},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:d06d01c5c4f33af6187d83f3373934ff9277d3ccbd9aa1a5878e7b4b2f4e96d3","observation_id":"a584053e-204c-4bff-bb5b-0d5195f40487","resolution":{"observed_at":"2026-07-07T18:04:01.032279Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"physics/0004057","last_updated":"2000-04-24T15:22:30Z","snapshot_observed_at":"2026-08-16T09:10:10.815975Z","submitted_at":"2000-04-24T15:22:30Z","title":"The information bottleneck method","version":1},"cited_work":{"arxiv_id":"physics/0004057","doi":"10.48550/arxiv.physics/0004057","metadata_source":"pith","pith_arxiv_id":"physics/0004057","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"The information bottleneck method","venue":"physics.data-an","work_id":"72655a80-0724-45ad-a330-1f4ed7aa613b","year":2000},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"cited_paper":"/paper/physics/0004057","citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:681e47c743003436d82010591c08d61cf68a6dbfa2be814d7ccfbd48b2025b42","observation_id":"39340bfa-137d-4839-a61e-3dc6d10e667b","resolution":{"observed_at":"2026-07-07T18:04:00.602844Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-07-10T23:49:06.793856+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-10T23:49:06.793856+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-07-07T18:04:01.018463Z","title":"Go- ing deeper with image transformers","venue":null,"work_id":"63c88ed3-479d-43ed-82d6-9835812b71d1","year":2021},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:8be5c858e4251f48445e7b8bf7dfe117f5555c0ff1277a5bb230ff6a3f759cd5","observation_id":"b44a989b-b2be-45cd-906c-4f0234d64e08","resolution":{"observed_at":"2026-07-07T18:04:01.019527Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.02490","last_updated":"2024-03-26T03:41:26Z","snapshot_observed_at":"2026-08-16T15:50:47.894244Z","submitted_at":"2023-03-04T20:08:57Z","title":"Diffusion Models Generate Images Like Painters: an Analytical Theory of Outline First, Details Later","version":2},"cited_work":{"arxiv_id":"2303.02490","doi":null,"metadata_source":"pith","pith_arxiv_id":"2303.02490","snapshot_observed_at":"2026-07-07T18:04:00.568780Z","title":"Diffusion models generate images like painters: an analytical theory of outline first, details later","venue":"cs.CV","work_id":"2c2866bb-28a3-45a1-a3c0-e63c86ee8ea3","year":2023},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"cited_paper":"/paper/2303.02490","citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:c9a182e7264cbde750ac2fdf757a863af7fc8cea969c654c2808a03d2dd1307f","observation_id":"53944533-c31c-4bdc-814b-49456bb31fe7","resolution":{"observed_at":"2026-07-07T18:04:00.570678Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-07-07T18:04:01.005213Z","title":"A closer look at time steps is worthy of triple speed-up for diffusion model training","venue":null,"work_id":"a49d00b2-4246-4f45-b27c-feb19bc67d64","year":2025},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:5e956c8626cf7fbb6fbc67c46eeca60927e78ed7d344aea733ca00e0326b7e5b","observation_id":"a5dd0bfd-2b92-40a4-80e4-8c4509350faf","resolution":{"observed_at":"2026-07-07T18:04:01.006700Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-07-07T18:04:01.020270Z","title":"Tracey, Katerina Placek, Marco Vilela, and James R","venue":null,"work_id":"1457d10e-8649-442d-941b-c59ddf5ec3a8","year":2025},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:0676c677de17fc7cac5dc64374320f3a7742cca1e618e796114c0defc27ecb3b","observation_id":"5e6d7ba4-13b9-4a3e-b56b-fa7dac91a061","resolution":{"observed_at":"2026-07-07T18:04:01.021457Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-07-07T18:04:01.045013Z","title":"Infodiffusion: Representation learning using information maximizing diffusion models","venue":null,"work_id":"fa05e121-caf0-4483-871f-cf5721c3f1e1","year":2023},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:b9445c509f666f609f3d709043c5350f2b3da222bd187a0e803cf016f302cd5a","observation_id":"6721749e-7080-4753-a03f-c0755f66ca9c","resolution":{"observed_at":"2026-07-07T18:04:01.046227Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1609/aaai.v38i6.28407","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Factorized diffusion autoencoder for unsupervised disentangled representation learning","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","work_id":"72965bb8-ce0c-405a-bd9e-198ff9265046","year":2024},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:ce5e10f42c980f127a542e0d6699edda2b39e6482fe83bfd0d072ea0e6e9ecf0","observation_id":"22b41ed9-1bcd-426a-a0c8-515b0c1d0358","resolution":{"observed_at":"2026-07-07T18:04:00.444344Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-07-11T17:19:04.241711+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-11T17:19:04.241711+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-07-07T18:04:01.009365Z","title":"Slotdiffusion: Object- centric generative modeling with diffusion models","venue":null,"work_id":"d6ae0eb6-ae1d-4fdc-9f06-da3ad092af84","year":2023},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:3a01e37a81b252f086a069bd2f4703b1439edd2b9979ddac8f6871f3a2db0252","observation_id":"45eac165-ee4b-4043-b0f5-8ebd36841281","resolution":{"observed_at":"2026-07-07T18:04:01.010682Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.07946","last_updated":"2024-03-14T13:27:04Z","snapshot_observed_at":"2026-08-16T14:09:50.246262Z","submitted_at":"2024-03-14T13:27:04Z","title":"Towards Faster Training of Diffusion Models: An Inspiration of A Consistency Phenomenon","version":1},"cited_work":{"arxiv_id":"2404.07946","doi":null,"metadata_source":"pith","pith_arxiv_id":"2404.07946","snapshot_observed_at":"2026-07-07T18:04:00.595239Z","title":"Towards faster training of diffusion models: An inspiration of a consistency phenomenon","venue":"cs.LG","work_id":"9cc3ebb1-9c4a-4ac3-8674-4b2afe5d1d88","year":2024},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"cited_paper":"/paper/2404.07946","citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:2fe33f16e24af1bb8fcb60c168d93c68caaa85c68b6ef443b3eb91add83c9854","observation_id":"b5d65c27-f2fa-448c-a4bb-afac0d8e655d","resolution":{"observed_at":"2026-07-07T18:04:00.597942Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2301.13721","last_updated":"2023-10-28T11:21:47Z","snapshot_observed_at":"2026-08-16T15:58:48.230855Z","submitted_at":"2023-01-31T15:58:32Z","title":"DisDiff: Unsupervised Disentanglement of Diffusion Probabilistic Models","version":3},"cited_work":{"arxiv_id":"2301.13721","doi":null,"metadata_source":"pith","pith_arxiv_id":"2301.13721","snapshot_observed_at":"2026-07-07T18:04:00.617658Z","title":"DisDiff: Unsupervised Disentanglement of Diffusion Probabilistic Models","venue":"cs.CV","work_id":"0b6c4cca-93d9-4076-9b77-0ac96fa2c6a3","year":2023},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"cited_paper":"/paper/2301.13721","citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:59e35121594fb30ff872dfeb9bc54ab9c1a3e3cba1b90b308bcba8bcef31335d","observation_id":"dc7a9cd8-ea1e-4185-9196-b99e346f67d5","resolution":{"observed_at":"2026-07-07T18:04:00.619182Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-07-07T18:04:00.994653Z","title":"Diffusion model with cross attention as an inductive bias for disentanglement","venue":null,"work_id":"7af7ce2a-e121-4f89-b5bd-5b647e96cd57","year":2024},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:cfb7f9dcc9926543f57a57f7b156d8335505d45b8ca00557738ec4935190f49d","observation_id":"1a61e4e0-7e6d-4c66-aa61-dac94f35c8df","resolution":{"observed_at":"2026-07-07T18:04:00.995831Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.06940","last_updated":"2025-06-18T04:35:42Z","snapshot_observed_at":"2026-07-06T19:30:26.233621Z","submitted_at":"2024-10-09T14:34:53Z","title":"Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think","version":4},"cited_work":{"arxiv_id":"2410.06940","doi":"10.48550/arxiv.2410.06940","metadata_source":"pith","pith_arxiv_id":"2410.06940","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think","venue":"cs.CV","work_id":"1aff8ef8-079b-4afe-9e6a-148e6fd08e6a","year":2024},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"cited_paper":"/paper/2410.06940","citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:59dd75f359c0d3756ca5a67adb32eff6f4bfbbbca3bbfe9396aa7db2da853158","observation_id":"970b99ae-20d4-45a5-a87f-760c1352d907","resolution":{"observed_at":"2026-07-07T18:04:00.590562Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-07-07T18:04:01.050271Z","title":"Representation alignment for generation: Training diffusion transformers is easier than you think","venue":null,"work_id":"2a0a4a3d-119c-48fe-abc6-6011f23ccd95","year":2025},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:1e1548b2ff891d8ae8e04f2f2e828a045a324a8a40dad72b0ed4c20fcabd6456","observation_id":"9eb1c6ab-f9e3-4d05-a4ea-754bfd285c53","resolution":{"observed_at":"2026-07-07T18:04:01.051445Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-07-07T18:04:01.025661Z","title":"Exploring diffusion time-steps for unsupervised representation learning","venue":null,"work_id":"14dc2d9b-ab5a-4be9-9d7f-2f06d4573d2d","year":2024},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:ee593f8759b3ddfa2a050131ff7676064cdda3f527c774da47a3a355670713ca","observation_id":"80628394-73e0-4d72-b64b-d9fbed2906c3","resolution":{"observed_at":"2026-07-07T18:04:01.027010Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1901.09321","last_updated":"2019-03-12T00:31:18Z","snapshot_observed_at":"2026-08-14T17:25:25.486314Z","submitted_at":"2019-01-27T05:30:11Z","title":"Fixup Initialization: Residual Learning Without Normalization","version":2},"cited_work":{"arxiv_id":"1901.09321","doi":null,"metadata_source":"pith","pith_arxiv_id":"1901.09321","snapshot_observed_at":"2026-07-09T05:05:58.924762Z","title":"Fixup Initialization: Residual Learning Without Normalization","venue":"cs.LG","work_id":"ef06ce50-5be2-49a7-86bf-86d72a11a7a4","year":2019},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"cited_paper":"/paper/1901.09321","citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:9b977e4a86012dac6076e03c42241457cd765fa5a500fa65a370f71ff4f6a3f9","observation_id":"d16ba375-b11c-4627-90d2-33165de4236b","resolution":{"observed_at":"2026-07-07T18:04:00.581015Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-07-07T18:04:01.023758Z","title":"The unrea- sonable effectiveness of deep features as a perceptual metric","venue":null,"work_id":"e0592bb2-6c0c-48b9-9c2d-1ca4cacf289b","year":2018},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":94,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:558da8665feae34da3e7575efb28f2a151103012cef52d152b3dd350b2fc765f","observation_id":"158ddafe-657b-468f-ac70-2e0217dd0876","resolution":{"observed_at":"2026-07-07T18:04:01.024949Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-07-07T18:04:01.003522Z","title":"Unsupervised representation learning from pre- trained diffusion probabilistic models","venue":null,"work_id":"8ccc9144-1f7b-4da0-9166-959f212785a8","year":2022},"citing_paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning","version":1},"reference_index":95,"source":"pdf_text","source_observed_at":"2026-07-07T17:54:09.140773Z"},"links":{"citing_paper":"/paper/2607.05319"},"observation_digest":"sha256:f3b1c4c9e682c5b5b89643e6ba7b47ae1d812d1b5ea950f90d3067e2bf40f611","observation_id":"4f102395-7a36-4ad6-88fc-9a4da3f03b18","resolution":{"observed_at":"2026-07-07T18:04:01.004696Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2607.05319","last_updated":"2026-07-06T16:58:05Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-14T06:37:17.480944Z","submitted_at":"2026-07-06T16:58:05Z","title":"Steering Optimisation Trajectories in Diffusion Representation Learning"},"reference_resolution":{"displayed":95,"state_counts":{"malformed_identifier":0,"metadata_mismatch":2,"parse_uncertain":0,"unresolved":4,"verified_exact":32,"verified_fuzzy":57},"total_outbound_references":95},"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":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 95 of 95 outbound references and 0 inbound Pith citation observations for arXiv:2607.05319."}