{"as_of":"2026-08-17T13:42:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:44b93feebede4068f9a1c5524845a2c065021deea3a34ee965d303c421ec9a81","coverage":[{"denominator":94,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":94,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T14:40:27.654568Z","state":"measured"},{"denominator":94,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":94,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-17T06:30:58.91139+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/2505.18107/citation-record","integrity":"/paper/2505.18107/integrity","json":"/paper/2505.18107/citation-record.json","paper":"/paper/2505.18107"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:18.969877Z","title":"Intrinsic dimensionality explains the effectiveness of language model fine-tuning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:18.969877Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:634dd6a72e8f204491380e7229c356341be4829aee2642ee7c667e7112e591bb","observation_id":"cfd69840-9bf9-4f01-91b2-86dded7f5e64","resolution":{"observed_at":"2026-08-07T14:40:18.969877Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:19.049076Z","title":"Towards efficient image compression without autoregressive models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:19.049076Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:4d29b78807568b68e8a83b739f1236acecb965bbb29dc8f138364d79f5c32189","observation_id":"6ac0ac8e-6f73-4aca-b87d-d70ad81ca0cb","resolution":{"observed_at":"2026-08-07T14:40:19.049076Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:19.150712Z","title":"Nonlinear transform coding","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:19.150712Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:6ffc362b4394df79da2dbfb3b6ce48cb3dd26191843929ea6e98ae5a9a7d371b","observation_id":"1a55d1bb-6572-40d3-b858-ebfdda7a773d","resolution":{"observed_at":"2026-08-07T14:40:19.150712Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:19.228836Z","title":"Variational image compression with a scale hyperprior","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:19.228836Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:0438ebb4ecfb57c4fee99f7c4ec3e263d336fe8594b0ae404c237c470172e7e6","observation_id":"e7f6eff6-f748-4910-bd60-318ff7c4b48e","resolution":{"observed_at":"2026-08-07T14:40:19.228836Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:19.341417Z","title":"Instereo2k: a large real dataset for stereo matching in indoor scenes","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:19.341417Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:7cfa1d37b23f9b79fc1de6435497db9385096d4e4108f715ca3b22275e58daf2","observation_id":"594793aa-a7e1-47d4-9132-93076e8d8cb0","resolution":{"observed_at":"2026-08-07T14:40:19.341417Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:19.469688Z","title":"Image reconstruction via deep image prior subspaces","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:19.469688Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:ea891ded46194a4a455d1f3497d77a3e0a7867955de0f8809d5d64a3d0e9d854","observation_id":"7b781ee3-573d-4602-a620-64e3fd3d6bb3","resolution":{"observed_at":"2026-08-07T14:40:19.469688Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:19.550713Z","title":"Compressai: a pytorch library and evaluation platform for end-to-end compression research, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:19.550713Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:aa545a3f17dbd0ba8a78111e922d59f5911f962177c1ad7436e4d1251789c3f2","observation_id":"14c07176-b1c1-42f6-be73-482e96cf794d","resolution":{"observed_at":"2026-08-07T14:40:19.550713Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:19.615801Z","title":"Bj ntegaard","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:19.615801Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:aa0596ef354d5beb584c0f431e30d2d89961b922c8fcf0b5bf21408c6c8bc9d3","observation_id":"8af27451-f0e8-41e7-96f0-ea462d466736","resolution":{"observed_at":"2026-08-07T14:40:19.615801Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:19.727682Z","title":"Enhancing neural training via a correlated dynamics model","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:19.727682Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:4c617a9b9fc11c6e59264d7317a9da0db63e68b2be98648ca8ca85751a07189e","observation_id":"32dfc7c7-6dba-424d-ac82-29cdf026e88b","resolution":{"observed_at":"2026-08-07T14:40:19.727682Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:19.840244Z","title":"Brunton, Marko Budi s i\\' c , Eurika Kaiser, and J","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:19.840244Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:edc93c3029cf6fffa777525843dfd8f951932ff8703e8f49bc6c53f5e30e4005","observation_id":"d9bab46d-31ff-46ed-a94a-a6c65129368b","resolution":{"observed_at":"2026-08-07T14:40:19.840244Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:19.923076Z","title":"Robust overfitting may be mitigated by properly learned smoothening","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:19.923076Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:647b01e616eac2d04ba08170882861c03a16842af7f1c11940378d7dabe882e6","observation_id":"e92086ec-b67f-4579-a5cf-a93e61b73691","resolution":{"observed_at":"2026-08-07T14:40:19.923076Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:20.003590Z","title":"Illuminant estimation for color constancy: why spatial-domain methods work and the role of the color distribution","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:20.003590Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:e364e15589f668bf2a70b22f79347132a6de40a2e8213d0d802fef84c10396f8","observation_id":"113f5cd6-6872-4306-9584-90c1e2d1ff8c","resolution":{"observed_at":"2026-08-07T14:40:20.003590Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:20.117222Z","title":"The cityscapes dataset for semantic urban scene understanding","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:20.117222Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:451b04abaee128b23aa7cca4c2395d0e62817daf55229ef4bf3062e26f322069","observation_id":"89ae4ad7-4edf-47dd-94b0-2f751e434911","resolution":{"observed_at":"2026-08-07T14:40:20.117222Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:20.205046Z","title":"Parameter-efficient fine-tuning of large-scale pre-trained language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:20.205046Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:8cacb692d17231abbde6bd80b889ffb0c4dfbc6444a4cbb8905744bd3ac625f4","observation_id":"2eed98e3-3572-466e-9fc6-24577bf2ab98","resolution":{"observed_at":"2026-08-07T14:40:20.205046Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:38.631541Z","title":"Optimizing neural networks via koopman operator theory","venue":null,"work_id":"7df10529-5363-4d4b-90e4-f853ad774db2","year":2020},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:20.287378Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:3e0ce9fa528ec12da0dbf861604f286ac41d1520dea1d3108780fa2d806ac93d","observation_id":"98f7bc4b-7d07-4e94-acbc-dc6a9a3ed72c","resolution":{"observed_at":"2026-08-07T14:40:38.740595Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:38.419156Z","title":"Qarv: Quantization-aware resnet vae for lossy image compression","venue":null,"work_id":"5116576e-3eda-460f-bb03-fe377cd4156f","year":2023},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:20.409513Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:84b5e4fc29a1d4dc7afc8a839901767d95a70a7b61e65296ffd592c3c5d39d3d","observation_id":"438cb2c5-bc74-4595-b367-158d751e3a81","resolution":{"observed_at":"2026-08-07T14:40:38.504477Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:38.224500Z","title":"Asymmetric numeral systems, 2009","venue":null,"work_id":"600616dc-728a-4c3d-8ba7-0c3166395d8e","year":2009},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:20.478950Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:7298e70b4ea74a708d7cafb446db3107d0b030522eb5b6a389ad69ab8a2339aa","observation_id":"56198e04-e6a9-499c-9ec4-b646b6d41030","resolution":{"observed_at":"2026-08-07T14:40:38.325817Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:38.033664Z","title":"Rigging the lottery: Making all tickets winners","venue":null,"work_id":"a5c799b8-53ff-49b3-9518-bbec44258746","year":2020},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:20.588856Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:27a6e755ddcfcad152921e43ca0ab3db9ce7dc68f447afa5efeff76b621ca79f","observation_id":"93d0068a-33c0-4400-a601-ed56cdac8bad","resolution":{"observed_at":"2026-08-07T14:40:38.109912Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:37.810166Z","title":"Understanding the difficulty of training deep feedforward neural networks","venue":null,"work_id":"0cc6c49b-226f-40af-b2cb-d19ae7a766af","year":2010},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:20.691309Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:cfb0b352f21af1a5e2f250098af21d261686e4ca8f72d4e47fa877b0fd28e600","observation_id":"5a77d9fc-d7bb-471b-95fa-01e6d2389673","resolution":{"observed_at":"2026-08-07T14:40:37.907115Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:20.781851Z","title":"Improving neural network training in low dimensional random bases","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:20.781851Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:9460a87eebf7e1c265d83bc6596c97ba9d5c77369e72865063c9d04942a14d07","observation_id":"ae397d78-0cc9-473e-8e28-9daab972184c","resolution":{"observed_at":"2026-08-07T14:40:20.781851Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:37.542981Z","title":"EVC : Towards real-time neural image compression with mask decay","venue":null,"work_id":"0e9e2fbf-0d81-4fd9-897a-66cbab6b1e83","year":2023},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:20.846219Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:449f768be7c825bf4e3b8414dc5087495f23d3d26b374c75447e9f9c5b0c62b9","observation_id":"316b17fa-397e-428a-a9fc-ab87a4a7456d","resolution":{"observed_at":"2026-08-07T14:40:37.665817Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:37.402133Z","title":"Checkerboard context model for efficient learned image compression","venue":null,"work_id":"ff3916dc-755b-4f78-bec9-5c32ff6fa1ec","year":2021},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:20.932758Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:a3b567fe40350c0e36090cc577ed4556287fcceb8a55c2c497ffe43a6cf90b20","observation_id":"e334720b-c5e1-4221-b48c-1beae939edd9","resolution":{"observed_at":"2026-08-07T14:40:37.464997Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:37.248428Z","title":"E LIC : Efficient learned image compression with unevenly grouped space-channel contextual adaptive coding","venue":null,"work_id":"321a8ac6-e7d1-4742-9bde-685ad38aab87","year":2022},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:20.994385Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:b4637affb060c4a315b164219b154b4fa4c4e824adfef17d3cd5e7aa5befb813","observation_id":"36189e10-667e-4124-b29d-07b16dd5b363","resolution":{"observed_at":"2026-08-07T14:40:37.301046Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:37.012077Z","title":"Asymmetric valleys: Beyond sharp and flat local minima","venue":null,"work_id":"d6bc9168-1781-4165-a067-9bbaff9dc4ba","year":2019},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:21.140969Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:83db21bdffde56eee7a7305bb50f2a4b36ef25b7365027da917ea85720a1c5bb","observation_id":"f53ea00c-2223-473a-b1df-e8a18a057171","resolution":{"observed_at":"2026-08-07T14:40:37.118189Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:36.834340Z","title":"Delving deep into rectifiers: Surpassing human-level performance on imagenet classification","venue":null,"work_id":"701d151e-e49c-4fdb-91ca-85405673d972","year":2015},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:21.246588Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:744e31f9ab3135143d84421d648c0d2efe18ef5fd10c18a8cfe39a00e8d47137","observation_id":"620add2b-39ad-4fb5-a8c3-d87a14de07aa","resolution":{"observed_at":"2026-08-07T14:40:36.912838Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:36.641503Z","title":"Momentum contrast for unsupervised visual representation learning","venue":null,"work_id":"9ac0b1ed-887a-4b3b-b92f-7cc33b5bdba8","year":2020},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:21.335872Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:d1e193b98f8947d1b940c31e3e6eba48d25fb846bd34813e6fa9dbd39a3c709d","observation_id":"7cfcdf48-881a-4b49-9403-3331bfeedf68","resolution":{"observed_at":"2026-08-07T14:40:36.705964Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:36.490987Z","title":"Lo RA : Low-rank adaptation of large language models","venue":null,"work_id":"a78191ef-3f29-4ed7-813f-3370c9ecb4aa","year":2022},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:21.414637Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:7d2d166cfa06d97ea5cc4f9587650dd9c0aafbe91d5007c0b337dc67cd2f11f0","observation_id":"66e40b20-cfa7-49ca-848b-925e0c0d76fd","resolution":{"observed_at":"2026-08-07T14:40:36.543278Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:36.301711Z","title":"JPEG AI Common Training & Test Conditions v8.0","venue":null,"work_id":"ed646489-921b-4749-b39d-7a2988ad8568","year":2023},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:21.518719Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:7171b42ed6431361cb84d555a8a25fab0fdb5071a90db89d00f69dfe6c103153","observation_id":"fb5b59e7-104e-4595-b60f-3bb4d16b5c5d","resolution":{"observed_at":"2026-08-07T14:40:36.395418Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:36.107361Z","title":"Garipov, Dmitry P","venue":null,"work_id":"a316b69c-f0e7-49ad-b05f-396c5d683b4a","year":2018},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:21.627105Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:9d9d03a98dea11e90b36fcd93af50db350ebd2bc2e9c725258de5511f52b579f","observation_id":"2c179f03-4e6d-410e-86d5-69619343637f","resolution":{"observed_at":"2026-08-07T14:40:36.189642Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:35.893748Z","title":"Visual prompt tuning","venue":null,"work_id":"b0882fbc-a125-4ee5-9891-56302f078640","year":2022},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:21.684731Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:050d7e9ea139d241f053a3fd90c85bda24fedaf31f483f7240e001343b27739e","observation_id":"722f8335-05c5-488b-8fc7-b403a769db1f","resolution":{"observed_at":"2026-08-07T14:40:36.008896Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.20762","last_updated":"2025-03-18T07:39:00Z","snapshot_observed_at":"2026-08-17T09:28:57.941355Z","submitted_at":"2025-02-28T06:32:23Z","title":"Towards Practical Real-Time Neural Video Compression","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.20762","snapshot_observed_at":"2026-08-07T14:40:21.779590Z","title":"Towards practical real-time neural video compression, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:21.779590Z"},"links":{"cited_paper":"/paper/2502.20762","citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:2608c2e435eb9652a1288df65d5393070a67de7649974c72ea4d655405351039","observation_id":"5eedf0c7-d353-4f77-97eb-1e47d3808805","resolution":{"observed_at":"2026-08-07T14:40:21.779590Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:35.717783Z","title":"Variable-rate learned image compression with multi-objective optimization and quantization-reconstruction offsets","venue":null,"work_id":"5e893899-83e2-4d01-a3e2-f7cddec02044","year":2024},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:21.883067Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:3a8b83642d58f444adc6636409a093a41bc88944a6f11b20d36111e0556f3f74","observation_id":"d7efee76-f2b4-4557-b718-89f940685406","resolution":{"observed_at":"2026-08-07T14:40:35.817946Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:35.567036Z","title":"Multi-layer random perturbation training for improving model generalization efficiently","venue":null,"work_id":"df5e33e6-5e25-46fc-ac6c-9324abf5ff0c","year":2021},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:21.990580Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:a4a3e1da01e1e3e5e456e35569987fae3bce1f90cf289db0c84a4ebb73fd21a4","observation_id":"e9379a74-c636-4272-8eb6-c6b301872862","resolution":{"observed_at":"2026-08-07T14:40:35.624481Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:35.400487Z","title":"A software platform for manipulating the camera imaging pipeline","venue":null,"work_id":"9735cce2-d7dc-459f-b7f5-9ff859099cac","year":2016},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:22.086146Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:648f480cb8ebc7f314268c8aae4fc784a44fb7ac0bb02e1aace50fd2aa34e7d3","observation_id":"786ae922-047d-49da-9315-b0e611e4ed05","resolution":{"observed_at":"2026-08-07T14:40:35.476343Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:35.246243Z","title":"Understanding black-box predictions via influence functions","venue":null,"work_id":"de737563-2ef3-4e4f-9f4e-17dfb0417200","year":2017},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:22.167830Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:d1cb722ed2de59bf465c583be3be53f2cf9926626365ef9dad10d63050ff6b7e","observation_id":"59c40a22-9f44-46d5-92bd-9b494768fd2f","resolution":{"observed_at":"2026-08-07T14:40:35.313958Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:35.098256Z","title":"Dynamic sparse training with structured sparsity","venue":null,"work_id":"b3ff8110-ce38-47b5-8985-85735013d4a4","year":2024},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:22.242703Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:d4fca734fdaf58d8156e67477aca4afc1f9380797475efe493776d7a86bef631","observation_id":"49ae1eaf-8fe4-4231-88a0-0c2995cd310b","resolution":{"observed_at":"2026-08-07T14:40:35.176054Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:34.931040Z","title":"Measuring the intrinsic dimension of objective landscapes","venue":null,"work_id":"d87f2a85-975f-4cd9-9aa7-01ca125e30a4","year":2018},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:22.366149Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:7af4b1269e98197ab8204cb82da857c5b8418b42c165b5f48f9785e1323ed22f","observation_id":"f553e8cd-4157-4585-8886-173f6d730080","resolution":{"observed_at":"2026-08-07T14:40:34.999151Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:34.793591Z","title":"Frequency-aware transformer for learned image compression","venue":null,"work_id":"bdbfc0c9-3d6a-4518-bb07-9c2ed97959c5","year":2024},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:22.483827Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:e21adcabe0d2bb831409dd224a055066b70065973932e5076863a6253b565fa8","observation_id":"1cb84058-ead6-464c-be82-e08e126b33a8","resolution":{"observed_at":"2026-08-07T14:40:34.859917Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:34.685213Z","title":"Deep contextual video compression","venue":null,"work_id":"7686c2d8-c8ef-48a6-a965-3557bb78f8a7","year":2021},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:22.568531Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:e529e394fbb4905039afd3f320e8854008a5d3cf9d57697c05417e9fe2bc0e82","observation_id":"d8856e3c-71c0-4c98-b7b3-de0808c1b698","resolution":{"observed_at":"2026-08-07T14:40:34.740087Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:34.606614Z","title":"Hybrid spatial-temporal entropy modelling for neural video compression","venue":null,"work_id":"24df704f-c51e-4991-8f50-eae3ca2ba010","year":2022},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:22.675889Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:ef8eaaa46bcef16ee82d110b5ad4b54bf9630bc3d2d9cce3ef8e4dca70f01df6","observation_id":"8853efff-f552-4d32-8ca6-09fb1eeed74e","resolution":{"observed_at":"2026-08-07T14:40:34.639781Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:34.478996Z","title":"Neural video compression with diverse contexts","venue":null,"work_id":"e9da43cb-0a32-4bf8-be40-c20dd25adb6e","year":2023},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:22.762142Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:5a2c25b0dd241c41953c20c4d735a7a08bdf7778700409d68eb7691356742e9b","observation_id":"98065066-0fbb-42ec-b803-c9d14258f758","resolution":{"observed_at":"2026-08-07T14:40:34.532421Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:34.350162Z","title":"Neural video compression with feature modulation","venue":null,"work_id":"df459be5-3069-415c-976e-f0be6ed4c5ae","year":2024},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:22.845851Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:e2b8925e67ec2ede06aaf546cc9b56f4bba021393ac3215e2ba13c73a00e2761","observation_id":"b7c5e1f9-48a5-4cc8-ae56-8022f5eb0f3b","resolution":{"observed_at":"2026-08-07T14:40:34.407679Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:34.218163Z","title":"Low dimensional trajectory hypothesis is true: Dnns can be trained in tiny subspaces","venue":null,"work_id":"f75bf85d-f9e8-4c52-ba8c-e9d273ce55ba","year":2022},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:22.948924Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:6328b32665127568df584b6562d889871f20e1a87625b3466928769db65e1792","observation_id":"571f13a1-553c-4ae3-a9d3-d65ed6d9c68a","resolution":{"observed_at":"2026-08-07T14:40:34.277187Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:34.124057Z","title":"Subspace adversarial training","venue":null,"work_id":"57922ee7-58e2-46fd-88b6-a677c2d62eed","year":2022},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:23.071548Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:90b32557e96b893d8a41d5c0ae5ed3b7e9f05cb92db4d04269bd5adb9a4a3c9d","observation_id":"78e8e90f-9742-406c-8bb9-afae4eff7d60","resolution":{"observed_at":"2026-08-07T14:40:34.160780Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:33.960904Z","title":"Trainable weight averaging: Efficient training by optimizing historical solutions","venue":null,"work_id":"f47b9c98-8234-4247-a9ed-120addc4dc13","year":2023},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:23.171024Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:867a784eb9f19b3c7f06159707a9c4371d9e087cf9c2e3e8194202a0622ba49c","observation_id":"9e41822b-38d6-40a4-98da-aecce228320c","resolution":{"observed_at":"2026-08-07T14:40:34.041947Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:33.784417Z","title":"Revisiting random weight perturbation for efficiently improving generalization","venue":null,"work_id":"4a9f7d61-092d-4066-81db-e728cf5a06a9","year":2024},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:23.268800Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:d34e0aa29f2498e45b10ea68e10af4c3e7a01b5d285e03561f457b1688ac8dd9","observation_id":"872dd063-6759-4b7b-8319-fdd6b68cbdde","resolution":{"observed_at":"2026-08-07T14:40:33.861347Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:33.574504Z","title":"Deep model fusion: A survey, 2023 c","venue":null,"work_id":"51e8fb02-4595-46f7-a5ca-b383b1cc7b36","year":2023},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:23.411174Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:cb0afbff29a3eb5d4e687f5e629a9b675c07627e1a055e9925b066a70832d4e3","observation_id":"5660d6f3-d515-446c-82f2-b74260099266","resolution":{"observed_at":"2026-08-07T14:40:33.675318Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:33.408657Z","title":"Microsoft COCO : Common O bjects in C ontext","venue":null,"work_id":"1d729d2b-3e87-4b51-8fc7-28ee8a244b22","year":2014},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:23.514786Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:8216379cbbb5214bd02d4880fb194a7c3ac1773a43aac4c32ad827e44b1bc2bc","observation_id":"e572d4c3-9408-46d1-aab6-8e71c30c4466","resolution":{"observed_at":"2026-08-07T14:40:33.481236Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:33.218683Z","title":"Learned image compression with mixed transformer-cnn architectures","venue":null,"work_id":"e5181a3a-2682-4301-931d-981578947de1","year":2023},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:23.632502Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:3d6fdfc8a48240df631662df15fc5f09debab52462fa710de3c11d56d6623a44","observation_id":"f2935fc9-5b46-447c-bf67-d0bdaa8e220e","resolution":{"observed_at":"2026-08-07T14:40:33.302196Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:33.095004Z","title":"Bidirectional stereo image compression with cross-dimensional entropy model","venue":null,"work_id":"2ca69a93-b888-48a2-a043-b340271bad4e","year":2024},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:23.709971Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:b1866f7450e22facaf43509cbce7958edb33cf40112d4d43972601cb0d7e34e0","observation_id":"19b1ab4e-9b1f-4f99-a19f-51e405d575e2","resolution":{"observed_at":"2026-08-07T14:40:33.147312Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:23.825254Z","title":"Deep learning for universal linear embeddings of nonlinear dynamics","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:23.825254Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:d1c91e9c35b2073bd1125b6acf507a156b41c7727e80adff53cfead4031f7e97","observation_id":"ed019871-7690-40b9-b49b-eeda681d2e86","resolution":{"observed_at":"2026-08-07T14:40:23.825254Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:23.930934Z","title":"New insights and perspectives on the natural gradient method","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:23.930934Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:3116541c32c364cee37ccc610bb078a7ac7f6e78adc8508053e17bf11361199c","observation_id":"c494008d-afee-4ff5-99e2-a4c48d6a778c","resolution":{"observed_at":"2026-08-07T14:40:23.930934Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:32.916830Z","title":"Advancing the rate-distortion-computation frontier for neural image compression","venue":null,"work_id":"d13ff260-2fa6-4436-bd7b-e3b37ff1d4a0","year":2023},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:24.019837Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:e879dcda355d3f88f381331491ca3ce601ed5d1cab7e260c7ef3bbf3e21ae02a","observation_id":"e42376b4-328c-4c72-8c8c-53a64d16e2da","resolution":{"observed_at":"2026-08-07T14:40:32.993180Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:32.767970Z","title":"Channel-wise autoregressive entropy models for learned image compression","venue":null,"work_id":"4e130edf-98ae-4e34-b492-accfab23f19e","year":2020},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:24.126857Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:cb12a1a9de2ee81dd8f2f1050f8586948f1027602266f305a422713c02a27e05","observation_id":"1c308536-1b8a-46f0-a9fd-9411863a19d7","resolution":{"observed_at":"2026-08-07T14:40:32.855079Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:32.645845Z","title":"Importance estimation for neural network pruning","venue":null,"work_id":"780832b2-3404-4cfd-b0c9-efb9e284c039","year":2019},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:24.224873Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:5fb2df10d8abb7665d4468b024cd75c7e54e9c868c574f8f5f3ad446bc5b40ff","observation_id":"787bfb5a-5c26-4369-9905-d6acaf2ea8e1","resolution":{"observed_at":"2026-08-07T14:40:32.682265Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:32.553371Z","title":"Exponential moving average of weights in deep learning: Dynamics and benefits","venue":null,"work_id":"a5f8f4cd-09e2-4829-a47a-f39c88999abe","year":2024},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":56,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:24.341155Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:3f310968938eaf2dd8b3c72d784244e02152361e4b7c1df742f64f1487de158a","observation_id":"08fef050-7eee-4ecf-ae43-caf3f5e3399e","resolution":{"observed_at":"2026-08-07T14:40:32.601547Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:32.453993Z","title":"Decomposed linear dynamical systems (dlds) for learning the latent components of neural dynamics","venue":null,"work_id":"28d591f0-2042-4555-b584-1bc262eb4bfe","year":2024},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":57,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:24.449683Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:aa7d5bb7780fcd9643c135a927090e328cb7c0387178eeb51daf5223e1412dbc","observation_id":"ee599064-b62d-4ae5-bf11-140ab2ee1ffa","resolution":{"observed_at":"2026-08-07T14:40:32.491341Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:32.240617Z","title":"Modern hierarchical, agglomerative clustering algorithms, 2011","venue":null,"work_id":"5feb50c7-db4a-49a6-a49a-b214cf67fb1b","year":2011},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":58,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:24.577057Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:cae4e4d005d88ec485c9faac2b67dbdb945100b23c313ebc032c53fba855907d","observation_id":"8cdadf09-49f7-4faa-8184-97d3ef9a6766","resolution":{"observed_at":"2026-08-07T14:40:32.379893Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:32.079726Z","title":"Learning srgb-to-raw-rgb de-rendering with content-aware metadata","venue":null,"work_id":"2cb82081-9148-4ec7-a47f-7e66b9d4bc93","year":2022},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":59,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:24.660371Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:29510ac58d983b91b9b5dcc39d5a80d0ff90f7b85fadb5ccabc57f94950fb9b7","observation_id":"4dd99bd2-deb6-478e-91b7-c55b36da252b","resolution":{"observed_at":"2026-08-07T14:40:32.104482Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:31.987062Z","title":"A review on weight initialization strategies for neural networks","venue":null,"work_id":"acf98b82-9c9a-433c-8d09-a91ee068c553","year":2022},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":60,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:24.764494Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:66fe2c71f3a6883d9cdba70083565d2c4741c2b425c9e4f3d54bedf24831cbee","observation_id":"0bf1b320-575f-4514-9ba7-6dcbf928c714","resolution":{"observed_at":"2026-08-07T14:40:32.034290Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:31.855312Z","title":"Scid: A database for screen content images quality assessment","venue":null,"work_id":"2342ce8b-023d-481b-a0c6-74d052276db1","year":2017},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":61,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:24.857388Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:9b5756dff546d02f6ac594b1bff2a04c932f3f67ac92394a05381fb1199c5bd6","observation_id":"2b662ab0-f01f-4b99-bae2-fec4b31d630f","resolution":{"observed_at":"2026-08-07T14:40:31.920894Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:31.726397Z","title":"Abolafia, Jeffrey Pennington, and Jascha Sohl-Dickstein","venue":null,"work_id":"61444865-9b13-4687-8b85-439fd195d600","year":2018},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":62,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:24.966457Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:ee2d61772a415f913fb00ffc35a5151c75dc9d84095365e899aec0a3aaf907ee","observation_id":"74465b39-c727-4c93-a6bd-d31e4f9eed0d","resolution":{"observed_at":"2026-08-07T14:40:31.775093Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:31.621820Z","title":"Banach's fixed point theorem for partial metric spaces, 2004","venue":null,"work_id":"b6e2d70d-6682-45b3-af14-57b91d575b6f","year":2004},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":63,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:25.083010Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:e02de5b9e890f4b14ed3523f9198257ca66dd8754416f247c0439b55f672ada2","observation_id":"cf149ebf-e462-4be2-b33f-e7686cbb61f2","resolution":{"observed_at":"2026-08-07T14:40:31.677039Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:25.175436Z","title":"Acceleration of stochastic approximation by averaging","venue":null,"work_id":null,"year":1992},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":64,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:25.175436Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:17f9a8e393f56292a428474dc6d22aacd124ec846d351f5d90a45e51adbc43ee","observation_id":"d10347c9-ba89-48e5-abae-2a951b197c45","resolution":{"observed_at":"2026-08-07T14:40:25.175436Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:31.494514Z","title":"Your transformer is secretly linear, 2024","venue":null,"work_id":"ceae4201-7e29-476b-aea7-dc2409cfaeec","year":2024},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":65,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:25.263332Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:2a6e27293bd9d7f8bd03a789438dbd6a9f29d11938eb207a04a1a81ea7b8d0bb","observation_id":"16d610e2-a9df-46ad-9d0d-fbe3e88d3a2d","resolution":{"observed_at":"2026-08-07T14:40:31.556509Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:31.338201Z","title":"Exact solutions to the nonlinear dynamics of learning in deep linear neural networks, 2013","venue":null,"work_id":"ffd1e745-a276-44ec-8c64-06682d22945e","year":2013},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":66,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:25.365570Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:268696ea4c59bb2a46850c5093e98d88134bc743f5a20cf3b6c42d5b46ead793","observation_id":"54f9f8d7-6819-4824-aae1-ff8a96cab369","resolution":{"observed_at":"2026-08-07T14:40:31.419023Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:31.181118Z","title":"No more pesky learning rates","venue":null,"work_id":"500761fa-95a1-4d74-8d92-f31a09989498","year":2013},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":67,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:25.483866Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:245f704a9af0f670287054d1cb7899cf5d8ae574359b65e1f99ee1afbabb982b","observation_id":"dd1c9917-7f12-48fd-8792-f73d58dac923","resolution":{"observed_at":"2026-08-07T14:40:31.287171Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:30.944283Z","title":"Dynamic mode decomposition of numerical and experimental data","venue":null,"work_id":"eb279af1-9f17-4a9d-a4c2-500989e7ab2c","year":2010},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":68,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:25.600168Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:933e14ed5bb18415e1e73edec1f331882b2c1fe87a8f180cb3f699d1a85b68fa","observation_id":"89c54123-1894-4653-a6ba-028d12ccc12a","resolution":{"observed_at":"2026-08-07T14:40:31.038086Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:30.751591Z","title":"Dynamic mode decomposition and its variants","venue":null,"work_id":"4558f7b7-982b-4f47-844e-2df48f803442","year":2022},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":69,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:25.682208Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:e7a5d1cbf70a75a91a396c3d6d0c5cc03175fbb5c14384b71a6a79fd30f18958","observation_id":"15bddbe3-ca0d-4413-9b5a-2e1534486706","resolution":{"observed_at":"2026-08-07T14:40:30.844742Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:30.532759Z","title":"Temporal context mining for learned video compression","venue":null,"work_id":"a8a9e919-01d7-40c7-9607-d35ed1fc9cf5","year":2022},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":70,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:25.804457Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:7771ff4b7df63d6af76bc9a9c1dec031499de51821877212df76286eb9df1270","observation_id":"101c1d58-e2f5-47e2-af92-28794b88d6fd","resolution":{"observed_at":"2026-08-07T14:40:30.598244Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:30.497117Z","title":"Consistency models","venue":null,"work_id":"907a449e-c65b-4d82-80e7-54eda81a8cdc","year":2023},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":71,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:25.931294Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:d2947c2b9e7d15d3a0e8a6f2af9fe4d24b2570d6a9f282c388b69898e1426fd4","observation_id":"4bc4adb3-6b21-4dad-b9b8-4f853f4a7c42","resolution":{"observed_at":"2026-08-07T14:40:30.516547Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:30.328886Z","title":"Rethinking the inception architecture for computer vision","venue":null,"work_id":"7d298f2f-ad47-44ec-ac13-1c7abcfdcbdb","year":2016},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":72,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:26.026125Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:249afad7754c6b0c04fb0a671e695cfeaf2d4e9beae6eaff93603d18cea33b7f","observation_id":"59b364a1-1d47-4c89-9218-0700c76874d3","resolution":{"observed_at":"2026-08-07T14:40:30.404984Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:30.103589Z","title":"Adanic: Towards practical neural image compression via dynamic transform routing","venue":null,"work_id":"62274056-179d-49cc-8e24-49bdc2a51fa8","year":2023},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":73,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:26.129991Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:bfb127ac3b6daa85ccad3ac651226972b348ba3ef9c29b5d39a8cf1f7f5cb12c","observation_id":"372e46a7-3498-4237-9dcc-80ffcd6b4c3c","resolution":{"observed_at":"2026-08-07T14:40:30.219621Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:29.882867Z","title":"Beyond learned metadata-based raw image reconstruction","venue":null,"work_id":"69f15a1d-ac94-48ae-8bde-3ef111544ea1","year":2024},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":74,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:26.267603Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:2dfcb2859cda4d5fcb0411af76ed51131e88d3d089298d50309ae69eb2060bf9","observation_id":"e8da9bc6-4037-4052-994f-4f11df0c27bd","resolution":{"observed_at":"2026-08-07T14:40:29.996674Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:29.692433Z","title":"Towards certificated model robustness against weight perturbations","venue":null,"work_id":"89ea89b7-ed12-4d05-9d2c-df102871fc7b","year":2020},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":75,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:26.377015Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:9f589c94df2fb390a144966426b87e9959650ddd5666a35a0f0e8587aadf18e7","observation_id":"bfbaf1bf-0e3a-4d58-9c93-c0851c5d8ef4","resolution":{"observed_at":"2026-08-07T14:40:29.780903Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:29.588173Z","title":"Ecsic: Epipolar cross attention for stereo image compression","venue":null,"work_id":"6b659a9a-b16d-4b5f-86ae-0f18a95256bb","year":2024},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":76,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:26.472757Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:b10873c948fc421963df6c1f07cbb8c252154a13e54901c533b045e363790d3f","observation_id":"2b512526-18e2-4977-a210-d1dc8281fcf4","resolution":{"observed_at":"2026-08-07T14:40:29.632323Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:29.486356Z","title":"Understanding short-horizon bias in stochastic meta-optimization","venue":null,"work_id":"dafec2cd-9853-45bc-ab37-f2f572518a47","year":2018},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":77,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:26.582899Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:77822801f62f571cadc3c4fa0daf34002c687b63c23377515b86bd443baea7c7","observation_id":"9abdaaab-f3f7-469d-a87e-037983bf82e4","resolution":{"observed_at":"2026-08-07T14:40:29.528666Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:29.382934Z","title":"Remote sensing image compression based on high-frequency and low-frequency components","venue":null,"work_id":"6c3bb0af-d91e-4f22-8556-4c7291fcb346","year":2024},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":78,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:26.666916Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:4559654f9330e15411d39041ea8b6e30fed43ed26b052765ec49ac8325d84907","observation_id":"980910a2-edd5-4491-b82d-3c6385cd2a95","resolution":{"observed_at":"2026-08-07T14:40:29.420587Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:29.297800Z","title":"Perceptual quality assessment of screen content images","venue":null,"work_id":"6d7c6b1c-65c8-4d32-8153-f8330053b2a0","year":2015},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":79,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:26.714062Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:54ee87bb4a8e5243e700b2b99d6dea1476ff8e14b7d3ec7a4dffd7bc80b04c3b","observation_id":"1dbd9c4f-b3b8-4ae4-8048-3c7007c819c9","resolution":{"observed_at":"2026-08-07T14:40:29.335435Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:29.182202Z","title":"Deep neural network pruning method based on sensitive layers and reinforcement learning","venue":null,"work_id":"604d480b-0c49-435c-8a38-a495b618f611","year":1917},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":80,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:26.759741Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:e7a16b0021167486b18de40d45320b9cec5e90b5abce385566ba3dc609b015af","observation_id":"0a71cccf-cd7c-4d0d-aac3-687b3d260ba3","resolution":{"observed_at":"2026-08-07T14:40:29.238099Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:29.076448Z","title":"Computationally-efficient neural image compression with shallow decoders","venue":null,"work_id":"8110905f-a11e-41d3-98cb-5ef9a18b0d07","year":2023},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":81,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:26.804802Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:5846a660498351bb983c70322e776e2aad7c4aede3e08b15d3b22326cb6068bf","observation_id":"fe6998ff-fa40-465a-b194-f6fb6393cc65","resolution":{"observed_at":"2026-08-07T14:40:29.120583Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:28.972280Z","title":"Safer: Layer-level sensitivity assessment for efficient and robust neural network inference, 2023","venue":null,"work_id":"e469c68b-1c43-4abb-956f-5e3863e11679","year":2023},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":82,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:26.911471Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:e131bd27547421f7174842ba8c04c852a40b9b32c5984471d419af17863a2c45","observation_id":"15a68477-5c10-4e4a-bbc0-9da29c9cd711","resolution":{"observed_at":"2026-08-07T14:40:29.012804Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:28.849343Z","title":"Are all layers created equal? Journal of Machine Learning Research, 23 0 (67): 0 1--28, 2022","venue":null,"work_id":"9ba721f4-1cfb-494c-895a-29b9625a8af1","year":2022},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":83,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:27.044391Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:684ee29ff781facb0db2b59979324c7c7a8079f25005df594c7cb62709c7c4d9","observation_id":"ba371aec-9068-475d-8adb-3ab2d4c61f29","resolution":{"observed_at":"2026-08-07T14:40:28.899412Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:28.743995Z","title":"Which algorithmic choices matter at which batch sizes? insights from a noisy quadratic model","venue":null,"work_id":"88c97721-aa91-4036-96de-53a74127d95a","year":2019},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":84,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:27.119865Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:9e2628fe4372ae282809c5301f24d442c86ea2380d55f4b7a830721819857341","observation_id":"7fd68a0a-2f06-410c-b221-897efcbfbb4f","resolution":{"observed_at":"2026-08-07T14:40:28.792365Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:28.637203Z","title":"Lookaround optimizer: k steps around, 1 step average","venue":null,"work_id":"8bd34549-d317-4f6c-812f-d03a71819537","year":2023},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":85,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:27.173871Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:271033debbc2798c89bda2085037153776156b54cf37f1ebaabb535d97a7971c","observation_id":"845aec60-a30a-4e35-853d-5fa9eba6fcab","resolution":{"observed_at":"2026-08-07T14:40:28.684036Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:28.535734Z","title":"Lookahead optimizer: k steps forward, 1 step back","venue":null,"work_id":"f12c2f8c-873e-4549-8d5c-f5ac6ff07848","year":2019},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":86,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:27.222044Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:3965dd585e570ddaa4df292bed99e63a72e8d57d6062ace140d9d0a90215fc82","observation_id":"d294c5d1-9d3c-4f54-bda2-74f1865a1541","resolution":{"observed_at":"2026-08-07T14:40:28.583776Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:28.441698Z","title":"Theoretical bound-guided hierarchical vae for neural image codecs","venue":null,"work_id":"4a3bbbbf-fe41-48e3-b3e8-492c1205b121","year":2024},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":87,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:27.291133Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:c87d9abde5f44cd2f196ee42f944785263810dc47c912649faf6e17a76184d6d","observation_id":"b1556a4e-f8bb-4b17-ab55-6204ff360efb","resolution":{"observed_at":"2026-08-07T14:40:28.478352Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:28.343357Z","title":"Another way to the top: Exploit contextual clustering in learned image coding","venue":null,"work_id":"cf2d5c69-9dd4-4e55-afaa-f6f2e076a155","year":2024},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":88,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:27.336487Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:debf6c6bf492af4b37addfbf61eec2292a4e9043b295037e35ef336a45beebef","observation_id":"2ec2786e-9028-4d4d-acaa-2417cbbcf371","resolution":{"observed_at":"2026-08-07T14:40:28.391911Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:28.232147Z","title":"On efficient neural network architectures for image compression","venue":null,"work_id":"07fc90b4-8fe6-43ab-8a77-0314e7dee547","year":2024},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":89,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:27.381083Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:810ba54aa1852b0c672af22f5d8e40b668c0cdc84bcdf3b0847962ae3e6f2dcd","observation_id":"b2abd893-95b4-490e-8bf1-fcdca99b1698","resolution":{"observed_at":"2026-08-07T14:40:28.271765Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2502.20161","last_updated":"2025-03-18T17:06:31Z","snapshot_observed_at":"2026-08-16T12:54:37.012106Z","submitted_at":"2025-02-27T15:00:43Z","title":"Balanced Rate-Distortion Optimization in Learned Image Compression","version":2},"cited_work":{"arxiv_id":"2502.20161","doi":null,"metadata_source":"pith","pith_arxiv_id":"2502.20161","snapshot_observed_at":"2026-08-07T14:40:27.730170Z","title":"Balanced Rate-Distortion Optimization in Learned Image Compression","venue":"eess.IV","work_id":"da268c99-2479-4b17-a1d9-8a9660741d41","year":2025},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":90,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:27.435102Z"},"links":{"cited_paper":"/paper/2502.20161","citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:9a54920db7ca4bb7a1a9deac2645ac5b0a8f6d29c113e78c432059396d6c424d","observation_id":"9a8af3fc-9716-4b75-82aa-d9c6f91b6468","resolution":{"observed_at":"2026-08-07T14:40:27.757661Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:28.083915Z","title":"Enhanced screen content image compression: A synergistic approach for structural fidelity and text integrity preservation","venue":null,"work_id":"2aa4db00-4400-40f7-9dd4-48a03d0f62b7","year":2024},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":91,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:27.501730Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:e0edaf33dfe8aefbfc435c40c021b572b9b1efdac8e26e5639280835040a4a21","observation_id":"8daf2183-09fc-473c-98be-e8a9f2850eb2","resolution":{"observed_at":"2026-08-07T14:40:28.162132Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:27.932103Z","title":"Towards understanding why lookahead generalizes better than sgd and beyond","venue":null,"work_id":"32832770-1ebf-4988-9f28-6d3847784e54","year":2021},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":92,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:27.547115Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:1097d0acf8e53f492d45fadbbc88f48970503b7f5a1902fdfc5c0a925a6ceeb6","observation_id":"ff0d83dc-870e-4876-b4cc-57850785ed56","resolution":{"observed_at":"2026-08-07T14:40:27.987058Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:27.841388Z","title":"Efficient neural network training via forward and backward propagation sparsification","venue":null,"work_id":"3664ec59-6ab2-49e3-a3eb-142243343bd1","year":2021},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":93,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:27.599102Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:97988a8912c7ece6d577d6706718f145da9e4a807afd9fa8768f0f9e2d3b6abc","observation_id":"e3ac9312-fbfb-4065-ac84-94895ee0d56c","resolution":{"observed_at":"2026-08-07T14:40:27.880464Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T14:40:27.654568Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics","version":1},"reference_index":94,"source":"arxiv_source","source_observed_at":"2026-08-07T14:40:27.654568Z"},"links":{"citing_paper":"/paper/2505.18107"},"observation_digest":"sha256:8828db169756104a89afb04276e4acb131a241eec63d99623fd60fa58694ea01","observation_id":"bafaa457-efc9-4e13-b75a-65f067d23a27","resolution":{"observed_at":"2026-08-07T14:40:27.654568Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2505.18107","last_updated":"2025-05-23T17:03:13Z","latest_version":1,"primary_category":"eess.IV","snapshot_observed_at":"2026-08-09T08:20:47.531340Z","submitted_at":"2025-05-23T17:03:13Z","title":"Accelerating Learned Image Compression Through Modeling Neural Training Dynamics"},"reference_resolution":{"displayed":94,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":20,"verified_exact":1,"verified_fuzzy":73},"total_outbound_references":94},"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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 94 of 94 outbound references and 0 inbound Pith citation observations for arXiv:2505.18107."}