{"as_of":"2026-08-10T14:36:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:70ead7fd4bf9f9a24c2e40be40a3f67343e90d3891b519967cfe09eb4a9e9ffe","coverage":[{"denominator":58,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":58,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-09T18:05:27.738703Z","state":"measured"},{"denominator":59,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":59,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-21T10:46:21.138722Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-21T10:50:01.537726Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2502.00700","last_updated":"2025-03-24T09:19:16Z","snapshot_observed_at":"2026-08-09T17:59:16.046441Z","submitted_at":"2025-02-02T07:15:51Z","title":"S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression","version":3},"cited_work":{"arxiv_id":"2502.00700","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2502.00700","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"S2cformer: Reorienting learned image compression from spatial interaction to channel aggregation","venue":null,"work_id":"bff9ae6b-cd47-4eac-a546-73efbbf8dc1e","year":2025},"citing_paper":{"arxiv_id":"2603.13864","last_updated":"2026-05-15T03:19:24Z","snapshot_observed_at":"2026-07-06T22:49:01.769027Z","submitted_at":"2026-03-14T09:45:59Z","title":"Inevitable Encounters: Backdoor Attacks Involving Lossy Compression","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-05-21T10:46:21.138722Z"},"links":{"cited_paper":"/paper/2502.00700","citing_paper":"/paper/2603.13864"},"observation_digest":"sha256:7f22efbacfdb453d46c4ed422cee09abdb4b4981b51bfb567c75fa5807bac285","observation_id":"ad8c8e30-9c8a-4faa-b5ee-98a25d5209f6","resolution":{"observed_at":"2026-05-21T10:50:01.539547Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2502.00700/citation-record","integrity":"/paper/2502.00700/integrity","json":"/paper/2502.00700/citation-record.json","paper":"/paper/2502.00700"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T18:05:28.828173Z","title":"Testimages: a large- scale archive for testing visual devices and basic image pro- cessing algorithms","venue":null,"work_id":"ad3f1be7-9d32-4e4e-ba6a-3118f23589b8","year":2014},"citing_paper":{"arxiv_id":"2502.00700","last_updated":"2025-03-24T09:19:16Z","snapshot_observed_at":"2026-08-09T17:59:16.046441Z","submitted_at":"2025-02-02T07:15:51Z","title":"S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression","version":3},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-09T18:05:27.467546Z"},"links":{"citing_paper":"/paper/2502.00700"},"observation_digest":"sha256:7ad0002c18418444552f1ce4a899680aaece57f87497bd10d96a983d5d4905a1","observation_id":"8c80cc19-efbb-4145-993f-3438e9f5deef","resolution":{"observed_at":"2026-08-09T18:05:28.832861Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1611.01704","last_updated":"2017-03-03T14:53:13Z","snapshot_observed_at":"2026-08-06T14:10:12.161882Z","submitted_at":"2016-11-05T21:39:53Z","title":"End-to-end Optimized Image Compression","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1611.01704","snapshot_observed_at":"2026-08-09T18:05:27.473509Z","title":"End-to-end optimized image compression","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2502.00700","last_updated":"2025-03-24T09:19:16Z","snapshot_observed_at":"2026-08-09T17:59:16.046441Z","submitted_at":"2025-02-02T07:15:51Z","title":"S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression","version":3},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-09T18:05:27.473509Z"},"links":{"cited_paper":"/paper/1611.01704","citing_paper":"/paper/2502.00700"},"observation_digest":"sha256:ff7ff64663541a4465a19051fb3c3a542c7b28ca1a0d36edc0bca4bb1f397a8f","observation_id":"a8f999a9-631a-4924-85fd-8aa22789ee6d","resolution":{"observed_at":"2026-08-09T18:05:27.473509Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1802.01436","last_updated":"2018-05-01T05:30:29Z","snapshot_observed_at":"2026-08-02T09:34:56.255411Z","submitted_at":"2018-02-01T00:42:29Z","title":"Variational image compression with a scale hyperprior","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1802.01436","snapshot_observed_at":"2026-08-09T18:05:27.478951Z","title":"Variational image compression with a scale hyperprior","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.00700","last_updated":"2025-03-24T09:19:16Z","snapshot_observed_at":"2026-08-09T17:59:16.046441Z","submitted_at":"2025-02-02T07:15:51Z","title":"S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression","version":3},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-09T18:05:27.478951Z"},"links":{"cited_paper":"/paper/1802.01436","citing_paper":"/paper/2502.00700"},"observation_digest":"sha256:45b67a3d0f126b3c51ab7ef1ba5ae8d50147d12c24c5c8ca36bdbc998b486204","observation_id":"0598800e-5aed-42f9-bd4d-5aaa5d67f779","resolution":{"observed_at":"2026-08-09T18:05:27.478951Z","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":"2026-08-09T18:05:28.813411Z","title":"Compressai: a pytorch library and evaluation platform for end-to-end compression research","venue":null,"work_id":"d38e3d24-80dd-419d-a502-05ca6d910df4","year":2011},"citing_paper":{"arxiv_id":"2502.00700","last_updated":"2025-03-24T09:19:16Z","snapshot_observed_at":"2026-08-09T17:59:16.046441Z","submitted_at":"2025-02-02T07:15:51Z","title":"S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression","version":3},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-09T18:05:27.484501Z"},"links":{"citing_paper":"/paper/2502.00700"},"observation_digest":"sha256:fad6804990da6f0354270be38386a69d6394a12af8766c3376bdbe19c1732437","observation_id":"b7f5a400-c3fd-455c-a568-e23132493cc9","resolution":{"observed_at":"2026-08-09T18:05:28.818281Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-09T18:05:28.798520Z","title":"Calculation of average psnr differences between rd-curves","venue":null,"work_id":"97b73e8b-e096-4199-a0d3-b4de6c8e54f1","year":2001},"citing_paper":{"arxiv_id":"2502.00700","last_updated":"2025-03-24T09:19:16Z","snapshot_observed_at":"2026-08-09T17:59:16.046441Z","submitted_at":"2025-02-02T07:15:51Z","title":"S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression","version":3},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-09T18:05:27.489130Z"},"links":{"citing_paper":"/paper/2502.00700"},"observation_digest":"sha256:7e7077f25bfe528bca5b4444ee59755105973dd8b1715d54b0fbd81f5d88dd18","observation_id":"7881d80f-0b7b-42a5-aac6-22a056ff8c9e","resolution":{"observed_at":"2026-08-09T18:05:28.803390Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-09T18:05:28.782830Z","title":"Overview of the versatile video coding (vvc) standard and its applica- tions","venue":null,"work_id":"be7c411f-e7dd-4ca6-8cd8-c2c8c663d9c9","year":2021},"citing_paper":{"arxiv_id":"2502.00700","last_updated":"2025-03-24T09:19:16Z","snapshot_observed_at":"2026-08-09T17:59:16.046441Z","submitted_at":"2025-02-02T07:15:51Z","title":"S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression","version":3},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-09T18:05:27.493770Z"},"links":{"citing_paper":"/paper/2502.00700"},"observation_digest":"sha256:92134d2e80a9105273190d56f9f54c38729f66f8593a9c049879ca8ff1691ffb","observation_id":"da493452-fc3c-4862-a7d0-4add37feca8a","resolution":{"observed_at":"2026-08-09T18:05:28.788041Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-09T18:05:28.767968Z","title":"Browne, Y","venue":null,"work_id":"15835b1e-48c7-43aa-a7a6-3df78cd6b3f2","year":null},"citing_paper":{"arxiv_id":"2502.00700","last_updated":"2025-03-24T09:19:16Z","snapshot_observed_at":"2026-08-09T17:59:16.046441Z","submitted_at":"2025-02-02T07:15:51Z","title":"S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression","version":3},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-09T18:05:27.498362Z"},"links":{"citing_paper":"/paper/2502.00700"},"observation_digest":"sha256:b52eee556dde0033a7b2e98507b40189c8ad152af093b7a190e964e1813e4e0b","observation_id":"9abdfdad-edb8-4a99-a104-4c2deb97729d","resolution":{"observed_at":"2026-08-09T18:05:28.772808Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-09T18:05:28.753172Z","title":"Two-stage octave residual network for end-to-end image compres- sion","venue":null,"work_id":"21517167-c3de-4e64-a034-b71f4caafcee","year":2022},"citing_paper":{"arxiv_id":"2502.00700","last_updated":"2025-03-24T09:19:16Z","snapshot_observed_at":"2026-08-09T17:59:16.046441Z","submitted_at":"2025-02-02T07:15:51Z","title":"S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression","version":3},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-09T18:05:27.502747Z"},"links":{"citing_paper":"/paper/2502.00700"},"observation_digest":"sha256:48dfd791d164bf0c3990de8a7cb2046f65da4a2bf68eb2f35e91ab5ec5d86ee6","observation_id":"ada350bb-a099-4e13-83bb-237fe9f100de","resolution":{"observed_at":"2026-08-09T18:05:28.757990Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-09T18:05:28.739059Z","title":"Simple baselines for image restoration","venue":null,"work_id":"bdadd41b-e748-43f2-b80c-71ad3e0748cb","year":2022},"citing_paper":{"arxiv_id":"2502.00700","last_updated":"2025-03-24T09:19:16Z","snapshot_observed_at":"2026-08-09T17:59:16.046441Z","submitted_at":"2025-02-02T07:15:51Z","title":"S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-09T18:05:27.507643Z"},"links":{"citing_paper":"/paper/2502.00700"},"observation_digest":"sha256:8c1ee05fdfd5a53b9be703b3ba2b8633b4ab3a1701bdd033221c7fb23d396f55","observation_id":"6d045076-97fd-4de5-a08e-111e97031be4","resolution":{"observed_at":"2026-08-09T18:05:28.743799Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-09T18:05:28.725570Z","title":"Learned image compression with discretized gaussian mixture likelihoods and attention modules","venue":null,"work_id":"2b19dd2a-109c-4420-88aa-1b3ba488c607","year":2020},"citing_paper":{"arxiv_id":"2502.00700","last_updated":"2025-03-24T09:19:16Z","snapshot_observed_at":"2026-08-09T17:59:16.046441Z","submitted_at":"2025-02-02T07:15:51Z","title":"S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-09T18:05:27.511965Z"},"links":{"citing_paper":"/paper/2502.00700"},"observation_digest":"sha256:7fae4485caf097b86e9da1d404c26e573efcdb175dc61a201336feac6e5cf4ef","observation_id":"b419c288-e220-4270-85ec-1baec95799af","resolution":{"observed_at":"2026-08-09T18:05:28.730151Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-09T18:05:28.711838Z","title":"Xception: Deep learning with depth- wise separable convolutions","venue":null,"work_id":"360265e7-89ce-4d0b-bf8e-0e119637895b","year":2017},"citing_paper":{"arxiv_id":"2502.00700","last_updated":"2025-03-24T09:19:16Z","snapshot_observed_at":"2026-08-09T17:59:16.046441Z","submitted_at":"2025-02-02T07:15:51Z","title":"S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-09T18:05:27.516263Z"},"links":{"citing_paper":"/paper/2502.00700"},"observation_digest":"sha256:f1a5a73b853e9aec8a7bc939f1fa4979c7d0925a56e25cd4728994a52e158e6e","observation_id":"4ebcb032-e33c-49ef-a543-5a30532f24ca","resolution":{"observed_at":"2026-08-09T18:05:28.716356Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-09T18:05:28.697349Z","title":"Workshop and challenge on learned image com- pression","venue":null,"work_id":"a48cb672-88c2-405e-bed1-83519cb9394f","year":2021},"citing_paper":{"arxiv_id":"2502.00700","last_updated":"2025-03-24T09:19:16Z","snapshot_observed_at":"2026-08-09T17:59:16.046441Z","submitted_at":"2025-02-02T07:15:51Z","title":"S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression","version":3},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-09T18:05:27.520982Z"},"links":{"citing_paper":"/paper/2502.00700"},"observation_digest":"sha256:e37d5f7de1d9fee5a34a4b99160f21f1718449f8034caa9476aa889d919e95b6","observation_id":"ee2812b6-6843-48e2-b291-f78cd82deb47","resolution":{"observed_at":"2026-08-09T18:05:28.701991Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-09T18:05:28.682553Z","title":"Language modeling with gated convolutional networks","venue":null,"work_id":"6830dfc2-b1ff-4696-9c26-20a6e1f45a62","year":2017},"citing_paper":{"arxiv_id":"2502.00700","last_updated":"2025-03-24T09:19:16Z","snapshot_observed_at":"2026-08-09T17:59:16.046441Z","submitted_at":"2025-02-02T07:15:51Z","title":"S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression","version":3},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-09T18:05:27.525469Z"},"links":{"citing_paper":"/paper/2502.00700"},"observation_digest":"sha256:ded863bc64693dd8f10eb4f136ad41ca625756b975bd8b169ce6743eaecc4949","observation_id":"f765eb80-1c44-4129-bac2-b4c8adbab0dd","resolution":{"observed_at":"2026-08-09T18:05:28.687467Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-09T18:05:28.666285Z","title":"Cswin transformer: A general vision transformer backbone with cross-shaped windows","venue":null,"work_id":"6fe710b0-9e4c-4de8-8bf2-ce56e404c845","year":2022},"citing_paper":{"arxiv_id":"2502.00700","last_updated":"2025-03-24T09:19:16Z","snapshot_observed_at":"2026-08-09T17:59:16.046441Z","submitted_at":"2025-02-02T07:15:51Z","title":"S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression","version":3},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-09T18:05:27.529942Z"},"links":{"citing_paper":"/paper/2502.00700"},"observation_digest":"sha256:cfcea08bf8f6701cfc863856df2231fc76fde76f909690958056124c2078118f","observation_id":"31e60e1f-c9b2-41c8-b4c7-0ff7ff9fd64f","resolution":{"observed_at":"2026-08-09T18:05:28.671623Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2010.11929","last_updated":"2021-06-03T13:08:56Z","snapshot_observed_at":"2026-08-10T01:12:16.468283Z","submitted_at":"2020-10-22T17:55:59Z","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.11929","snapshot_observed_at":"2026-08-09T18:05:27.534358Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2502.00700","last_updated":"2025-03-24T09:19:16Z","snapshot_observed_at":"2026-08-09T17:59:16.046441Z","submitted_at":"2025-02-02T07:15:51Z","title":"S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression","version":3},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-09T18:05:27.534358Z"},"links":{"cited_paper":"/paper/2010.11929","citing_paper":"/paper/2502.00700"},"observation_digest":"sha256:9adf3c9e0579834258af6ee7ca6c997803eee10439941e12b1116e2daf6c23f0","observation_id":"5c8f9403-746b-4213-b39f-8b4ebf1b0a53","resolution":{"observed_at":"2026-08-09T18:05:27.534358Z","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":"2026-08-09T18:05:28.649925Z","title":"Asymmetric learned image com- pression with multi-scale residual block, importance scal- ing, and post-quantization filtering","venue":null,"work_id":"a6e82cc7-123f-40f3-8d8a-ab735fdcbaae","year":2023},"citing_paper":{"arxiv_id":"2502.00700","last_updated":"2025-03-24T09:19:16Z","snapshot_observed_at":"2026-08-09T17:59:16.046441Z","submitted_at":"2025-02-02T07:15:51Z","title":"S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression","version":3},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-09T18:05:27.538863Z"},"links":{"citing_paper":"/paper/2502.00700"},"observation_digest":"sha256:d99eaa214aebd465cbf927d72784c28fbb01a7451117ca104374d0b794964c46","observation_id":"86b4268a-9d5e-48fc-9375-197c4706449d","resolution":{"observed_at":"2026-08-09T18:05:28.655368Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-09T18:05:28.634641Z","title":"Neural image compression via attentional multi-scale back projection and frequency de- composition","venue":null,"work_id":"a64de774-de39-46cf-9ccc-3c7879fa0c1a","year":2021},"citing_paper":{"arxiv_id":"2502.00700","last_updated":"2025-03-24T09:19:16Z","snapshot_observed_at":"2026-08-09T17:59:16.046441Z","submitted_at":"2025-02-02T07:15:51Z","title":"S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression","version":3},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-09T18:05:27.543333Z"},"links":{"citing_paper":"/paper/2502.00700"},"observation_digest":"sha256:4399fd06ec4aa75626203c957a4bfe55b7830051117dc41f8cf6071dfaa6f8a8","observation_id":"a310faf6-741b-4008-909c-640180c2edf0","resolution":{"observed_at":"2026-08-09T18:05:28.639518Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-09T18:05:28.619139Z","title":"Causal context adjustment loss for learned image compression","venue":null,"work_id":"10c45faf-5933-473e-b1bc-302239c36e49","year":null},"citing_paper":{"arxiv_id":"2502.00700","last_updated":"2025-03-24T09:19:16Z","snapshot_observed_at":"2026-08-09T17:59:16.046441Z","submitted_at":"2025-02-02T07:15:51Z","title":"S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression","version":3},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-09T18:05:27.547493Z"},"links":{"citing_paper":"/paper/2502.00700"},"observation_digest":"sha256:36b2cb3ce4de9dfe0c9105850f243356a71f17af0f55637edf7d2b2d4da29ce0","observation_id":"e575881d-a3b9-4d1b-b0f1-b8902eea1439","resolution":{"observed_at":"2026-08-09T18:05:28.624353Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-09T18:05:27.552404Z","title":"S4d: Streaming 4d real-world reconstruction with gaussians and 3d control points","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.00700","last_updated":"2025-03-24T09:19:16Z","snapshot_observed_at":"2026-08-09T17:59:16.046441Z","submitted_at":"2025-02-02T07:15:51Z","title":"S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression","version":3},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-09T18:05:27.552404Z"},"links":{"citing_paper":"/paper/2502.00700"},"observation_digest":"sha256:e33c5a9897f24c8e4bf9b4dc9dd2851f02eda80708cbb9b1abba96d566dbacc4","observation_id":"cb2b1851-4164-43d1-83e0-11c421adf4bd","resolution":{"observed_at":"2026-08-09T18:05:27.552404Z","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":"2026-08-09T18:05:28.603891Z","title":"Checkerboard context model for efficient learned image compression","venue":null,"work_id":"d6dd8691-1f43-4669-bc63-a0ed234e5520","year":2021},"citing_paper":{"arxiv_id":"2502.00700","last_updated":"2025-03-24T09:19:16Z","snapshot_observed_at":"2026-08-09T17:59:16.046441Z","submitted_at":"2025-02-02T07:15:51Z","title":"S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression","version":3},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-09T18:05:27.557233Z"},"links":{"citing_paper":"/paper/2502.00700"},"observation_digest":"sha256:5c59caa6fc684b6f8bc33e0c5a850317f188db2734de90a9bdd17d38434dd60a","observation_id":"f32f78a3-d089-4a45-84dc-02a9aa29b3da","resolution":{"observed_at":"2026-08-09T18:05:28.608639Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-09T18:05:28.589193Z","title":"Elic: Efficient learned image compres- sion with unevenly grouped space-channel contextual adap- tive coding","venue":null,"work_id":"57342d09-be1a-406a-905b-aff1b373dad3","year":null},"citing_paper":{"arxiv_id":"2502.00700","last_updated":"2025-03-24T09:19:16Z","snapshot_observed_at":"2026-08-09T17:59:16.046441Z","submitted_at":"2025-02-02T07:15:51Z","title":"S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression","version":3},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-09T18:05:27.561887Z"},"links":{"citing_paper":"/paper/2502.00700"},"observation_digest":"sha256:0298e084f9f5965210c568a2a2225cd5830559290364e52ff2a77bad33a41b45","observation_id":"44afa33f-a9e2-49d1-9a0d-ef158c451539","resolution":{"observed_at":"2026-08-09T18:05:28.594264Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-09T18:05:28.573424Z","title":"MLIC$^{++}$: Linear com- plexity multi-reference entropy modeling for learned image compression","venue":null,"work_id":"481259c1-e845-4837-aab5-b35d93e8c2f8","year":2023},"citing_paper":{"arxiv_id":"2502.00700","last_updated":"2025-03-24T09:19:16Z","snapshot_observed_at":"2026-08-09T17:59:16.046441Z","submitted_at":"2025-02-02T07:15:51Z","title":"S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression","version":3},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-09T18:05:27.567148Z"},"links":{"citing_paper":"/paper/2502.00700"},"observation_digest":"sha256:f43bc291faeaf09a03031a416d06db017253742758852e167789143a3265e03b","observation_id":"ad47bcbd-4f6d-4627-a23b-bce867f9d9bd","resolution":{"observed_at":"2026-08-09T18:05:28.578349Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-09T18:05:28.558159Z","title":"Mlic: Multi-reference entropy model for learned image compression","venue":null,"work_id":"8b6371a2-2563-46ec-ad04-44bfa75f5f1f","year":2023},"citing_paper":{"arxiv_id":"2502.00700","last_updated":"2025-03-24T09:19:16Z","snapshot_observed_at":"2026-08-09T17:59:16.046441Z","submitted_at":"2025-02-02T07:15:51Z","title":"S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression","version":3},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-09T18:05:27.575750Z"},"links":{"citing_paper":"/paper/2502.00700"},"observation_digest":"sha256:b32685efdafa2c5c3219808488a6788422f23a5ac02ab594ab573e6a4a1c7633","observation_id":"924b0852-3abc-4bbf-be10-4af1c84ae1c6","resolution":{"observed_at":"2026-08-09T18:05:28.563550Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6980","last_updated":"2017-01-30T01:27:54Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2014-12-22T13:54:29Z","title":"Adam: A Method for Stochastic Optimization","version":9},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6980","snapshot_observed_at":"2026-08-09T18:05:27.580586Z","title":"Adam: A method for stochastic opti- mization","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2502.00700","last_updated":"2025-03-24T09:19:16Z","snapshot_observed_at":"2026-08-09T17:59:16.046441Z","submitted_at":"2025-02-02T07:15:51Z","title":"S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression","version":3},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-09T18:05:27.580586Z"},"links":{"cited_paper":"/paper/1412.6980","citing_paper":"/paper/2502.00700"},"observation_digest":"sha256:85fcdc576bbe89f2d03ca6c3da67b59662416533f17e35847976e768eb5408df","observation_id":"3ee63fb5-ff07-41ca-a905-839834d692aa","resolution":{"observed_at":"2026-08-09T18:05:27.580586Z","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":"2026-08-09T18:05:28.542735Z","title":"Kodak lossless true color im- age suite (photocd pcd0992), 1993","venue":null,"work_id":"8b1045dc-44c1-481f-b181-4e4978e7d32a","year":1993},"citing_paper":{"arxiv_id":"2502.00700","last_updated":"2025-03-24T09:19:16Z","snapshot_observed_at":"2026-08-09T17:59:16.046441Z","submitted_at":"2025-02-02T07:15:51Z","title":"S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression","version":3},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-09T18:05:27.585711Z"},"links":{"citing_paper":"/paper/2502.00700"},"observation_digest":"sha256:8ac441767a14e384a2069e7632632b1a5722b1d6dd8f7b138efa53cadbd95949","observation_id":"c2e056d3-13a8-45b3-8ab9-017aa99261a7","resolution":{"observed_at":"2026-08-09T18:05:28.547349Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-09T18:05:28.526988Z","title":"Con- textformer: A transformer with spatio-channel attention for context modeling in learned image compression","venue":null,"work_id":"9a7f8c52-851c-49b5-bb53-3c2fc8cee644","year":null},"citing_paper":{"arxiv_id":"2502.00700","last_updated":"2025-03-24T09:19:16Z","snapshot_observed_at":"2026-08-09T17:59:16.046441Z","submitted_at":"2025-02-02T07:15:51Z","title":"S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression","version":3},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-09T18:05:27.591665Z"},"links":{"citing_paper":"/paper/2502.00700"},"observation_digest":"sha256:e9ebe46e1af37e796b61f9c7e96adfcd16d831d9704393ec06fde8e1a13f4ded","observation_id":"23eeba52-dcb0-40f1-b630-76816dce48f0","resolution":{"observed_at":"2026-08-09T18:05:28.531808Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2105.03824","last_updated":"2022-05-26T18:50:20Z","snapshot_observed_at":"2026-08-03T17:35:52.520891Z","submitted_at":"2021-05-09T03:32:48Z","title":"FNet: Mixing Tokens with Fourier Transforms","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2105.03824","snapshot_observed_at":"2026-08-09T18:05:27.596530Z","title":"Fnet: Mixing tokens with fourier transforms","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.00700","last_updated":"2025-03-24T09:19:16Z","snapshot_observed_at":"2026-08-09T17:59:16.046441Z","submitted_at":"2025-02-02T07:15:51Z","title":"S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression","version":3},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-09T18:05:27.596530Z"},"links":{"cited_paper":"/paper/2105.03824","citing_paper":"/paper/2502.00700"},"observation_digest":"sha256:65eb5f0febc875fa64a43f09223c103fbffb2ea39ccd926d021f03b52423685b","observation_id":"1be46fd0-ba96-4bf3-92b1-7543455eb050","resolution":{"observed_at":"2026-08-09T18:05:27.596530Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.16387","last_updated":"2024-12-16T06:09:40Z","snapshot_observed_at":"2026-08-07T21:32:22.547363Z","submitted_at":"2023-10-25T05:59:25Z","title":"Frequency-Aware Transformer for Learned Image Compression","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.16387","snapshot_observed_at":"2026-08-09T18:05:27.601551Z","title":"Frequency-aware transformer for learned image compression","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.00700","last_updated":"2025-03-24T09:19:16Z","snapshot_observed_at":"2026-08-09T17:59:16.046441Z","submitted_at":"2025-02-02T07:15:51Z","title":"S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression","version":3},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-09T18:05:27.601551Z"},"links":{"cited_paper":"/paper/2310.16387","citing_paper":"/paper/2502.00700"},"observation_digest":"sha256:d2ffc4d9e00075c6f2b4e8baffc3f43f79bd6fef367a8ccdea65f7e4b06883d0","observation_id":"f082d866-eacd-4a43-9e7e-777b79ae1ecf","resolution":{"observed_at":"2026-08-09T18:05:27.601551Z","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":"2026-08-09T18:05:28.512136Z","title":"Hybrid spatial-temporal en- tropy modelling for neural video compression","venue":null,"work_id":"219d2ad5-a64a-4bb8-97a6-6308bce57008","year":2022},"citing_paper":{"arxiv_id":"2502.00700","last_updated":"2025-03-24T09:19:16Z","snapshot_observed_at":"2026-08-09T17:59:16.046441Z","submitted_at":"2025-02-02T07:15:51Z","title":"S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression","version":3},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-09T18:05:27.606313Z"},"links":{"citing_paper":"/paper/2502.00700"},"observation_digest":"sha256:c85dbafd4ad40d13bb944ae7357a90f97b7387f2b6b52fb1b8e4cb329c7b0946","observation_id":"64cd2929-471c-4dc3-b9e3-2d50d4b05916","resolution":{"observed_at":"2026-08-09T18:05:28.516925Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-09T18:05:28.497291Z","title":"Neural video compression with diverse contexts","venue":null,"work_id":"2c9c1c72-92bb-4f0a-a310-91c90d134525","year":2023},"citing_paper":{"arxiv_id":"2502.00700","last_updated":"2025-03-24T09:19:16Z","snapshot_observed_at":"2026-08-09T17:59:16.046441Z","submitted_at":"2025-02-02T07:15:51Z","title":"S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression","version":3},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-09T18:05:27.610730Z"},"links":{"citing_paper":"/paper/2502.00700"},"observation_digest":"sha256:f48824cac9b8302992ef37c2a34fd8461adca649a76fcb0b3df08619ea1e5d43","observation_id":"1eb388bf-17bc-475f-bd80-462fd1cbe92d","resolution":{"observed_at":"2026-08-09T18:05:28.502343Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-09T18:05:28.482231Z","title":"Swinir: Image restoration using swin transformer","venue":null,"work_id":"950f58e9-e6f8-42f7-abd4-33ee05db9e80","year":2021},"citing_paper":{"arxiv_id":"2502.00700","last_updated":"2025-03-24T09:19:16Z","snapshot_observed_at":"2026-08-09T17:59:16.046441Z","submitted_at":"2025-02-02T07:15:51Z","title":"S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression","version":3},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-09T18:05:27.614964Z"},"links":{"citing_paper":"/paper/2502.00700"},"observation_digest":"sha256:ab69d5437188cae1c07cbe4d144ee7b58aeda900e79090b1a5dfdc6767bff5f3","observation_id":"8f1168da-2518-40ef-9aa9-1deb02ec5768","resolution":{"observed_at":"2026-08-09T18:05:28.487222Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2002.03370","last_updated":"2020-05-23T22:41:06Z","snapshot_observed_at":"2026-08-09T18:57:43.242349Z","submitted_at":"2020-02-09T14:21:08Z","title":"A Unified End-to-End Framework for Efficient Deep Image Compression","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.03370","snapshot_observed_at":"2026-08-09T18:05:27.619207Z","title":"A unified end-to-end framework for efficient deep image compression","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2502.00700","last_updated":"2025-03-24T09:19:16Z","snapshot_observed_at":"2026-08-09T17:59:16.046441Z","submitted_at":"2025-02-02T07:15:51Z","title":"S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression","version":3},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-09T18:05:27.619207Z"},"links":{"cited_paper":"/paper/2002.03370","citing_paper":"/paper/2502.00700"},"observation_digest":"sha256:507e5762692d3bcf6b189f75b1a5966a25767163bfcb1fb9ddfe379081738f85","observation_id":"b3217583-dee4-49a7-80bb-8a61b82e50d6","resolution":{"observed_at":"2026-08-09T18:05:27.619207Z","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":"2026-08-09T18:05:28.466158Z","title":"Learned im- age compression with mixed transformer-cnn architectures","venue":null,"work_id":"9083c321-3e0f-449b-b1c4-b01d0d2193ec","year":2023},"citing_paper":{"arxiv_id":"2502.00700","last_updated":"2025-03-24T09:19:16Z","snapshot_observed_at":"2026-08-09T17:59:16.046441Z","submitted_at":"2025-02-02T07:15:51Z","title":"S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression","version":3},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-09T18:05:27.623711Z"},"links":{"citing_paper":"/paper/2502.00700"},"observation_digest":"sha256:290ad9eea302277502e472c833b26b966a920fabe7455f460bc1cb0c8452f9cd","observation_id":"b5de1da3-a622-4169-a7c7-abf09169f69b","resolution":{"observed_at":"2026-08-09T18:05:28.471206Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-09T18:05:27.628012Z","title":"Swin transformer: Hierarchical vision transformer using shifted windows","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.00700","last_updated":"2025-03-24T09:19:16Z","snapshot_observed_at":"2026-08-09T17:59:16.046441Z","submitted_at":"2025-02-02T07:15:51Z","title":"S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression","version":3},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-09T18:05:27.628012Z"},"links":{"citing_paper":"/paper/2502.00700"},"observation_digest":"sha256:5ffeebcc92fd350db3d1d7dc208edd24292b6f94f35b5f5a32d7b9a6f4d3c8d8","observation_id":"3346c8fa-9aa0-4781-b903-351a1ee20248","resolution":{"observed_at":"2026-08-09T18:05:27.628012Z","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":"2026-08-09T18:05:28.439980Z","title":"Swin transformer v2: Scaling up capacity and resolution","venue":null,"work_id":"dd06c364-99f0-45bf-b5dc-f26a88eda5b0","year":2022},"citing_paper":{"arxiv_id":"2502.00700","last_updated":"2025-03-24T09:19:16Z","snapshot_observed_at":"2026-08-09T17:59:16.046441Z","submitted_at":"2025-02-02T07:15:51Z","title":"S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression","version":3},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-09T18:05:27.632401Z"},"links":{"citing_paper":"/paper/2502.00700"},"observation_digest":"sha256:449fc7b789d4f799383c10bb018a6f0a16e57bc33de0257fdc99bc16f4361127","observation_id":"a42f18d2-7b3d-4067-a9aa-2de3663e2336","resolution":{"observed_at":"2026-08-09T18:05:28.444783Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-09T18:05:28.425364Z","title":"Transformer-based image compression","venue":null,"work_id":"461439c1-af0c-4e1d-9fa2-42866b64635f","year":2022},"citing_paper":{"arxiv_id":"2502.00700","last_updated":"2025-03-24T09:19:16Z","snapshot_observed_at":"2026-08-09T17:59:16.046441Z","submitted_at":"2025-02-02T07:15:51Z","title":"S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression","version":3},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-09T18:05:27.637102Z"},"links":{"citing_paper":"/paper/2502.00700"},"observation_digest":"sha256:2dcd925c99d441fb92359008760ea8956b4ce81e8a00122c18da31c312f91694","observation_id":"d23d02e5-674a-4170-a1af-58605d5e1b83","resolution":{"observed_at":"2026-08-09T18:05:28.430060Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-09T18:05:28.410994Z","title":"Understanding the effective receptive field in deep convo- lutional neural networks","venue":null,"work_id":"d240848a-10a9-4c25-b439-03328d78bb17","year":2016},"citing_paper":{"arxiv_id":"2502.00700","last_updated":"2025-03-24T09:19:16Z","snapshot_observed_at":"2026-08-09T17:59:16.046441Z","submitted_at":"2025-02-02T07:15:51Z","title":"S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression","version":3},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-09T18:05:27.641652Z"},"links":{"citing_paper":"/paper/2502.00700"},"observation_digest":"sha256:7b35dc406b3db8809bf20f7b543b8f3f80b3adb1430105f7527ffa46d8d29515","observation_id":"92136ad1-b464-4447-934d-c687609b08e5","resolution":{"observed_at":"2026-08-09T18:05:28.415516Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-09T18:05:28.397106Z","title":"iwave: Cnn-based wavelet-like transform for image compression","venue":null,"work_id":"fe98423e-784c-490d-9c78-3219c9429c8c","year":2019},"citing_paper":{"arxiv_id":"2502.00700","last_updated":"2025-03-24T09:19:16Z","snapshot_observed_at":"2026-08-09T17:59:16.046441Z","submitted_at":"2025-02-02T07:15:51Z","title":"S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression","version":3},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-09T18:05:27.646035Z"},"links":{"citing_paper":"/paper/2502.00700"},"observation_digest":"sha256:a7d7df9d0e914ad432901dcad5cc084843c30601961cdcbefa15dcbc21e058c6","observation_id":"9a1a6ecc-221e-4b4d-8ca0-f58bf58fbb6c","resolution":{"observed_at":"2026-08-09T18:05:28.401655Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-09T18:05:28.381798Z","title":"End-to-end optimized versatile image compression with wavelet-like transform","venue":null,"work_id":"99030932-68b7-439c-a571-b0ae39552c31","year":2020},"citing_paper":{"arxiv_id":"2502.00700","last_updated":"2025-03-24T09:19:16Z","snapshot_observed_at":"2026-08-09T17:59:16.046441Z","submitted_at":"2025-02-02T07:15:51Z","title":"S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression","version":3},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-09T18:05:27.650650Z"},"links":{"citing_paper":"/paper/2502.00700"},"observation_digest":"sha256:75335b420b8d06347c4618a6335c3a822b30e8aafc569c69215348a7b9e989ef","observation_id":"3411c965-a360-46c7-b5bc-fd5bf19b406a","resolution":{"observed_at":"2026-08-09T18:05:28.387188Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.07307","last_updated":"2022-10-12T09:01:27Z","snapshot_observed_at":"2026-08-10T04:58:35.967285Z","submitted_at":"2022-06-15T05:31:32Z","title":"VCT: A Video Compression Transformer","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.07307","snapshot_observed_at":"2026-08-09T18:05:27.655137Z","title":"Vct: A video compression transformer","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.00700","last_updated":"2025-03-24T09:19:16Z","snapshot_observed_at":"2026-08-09T17:59:16.046441Z","submitted_at":"2025-02-02T07:15:51Z","title":"S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression","version":3},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-09T18:05:27.655137Z"},"links":{"cited_paper":"/paper/2206.07307","citing_paper":"/paper/2502.00700"},"observation_digest":"sha256:76d31174e3073013dfd6bd3c590c0128ccea6fc8884b204a451fa92b1a569ce8","observation_id":"ef76807d-6c10-4db6-b168-cc997d8b7101","resolution":{"observed_at":"2026-08-09T18:05:27.655137Z","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":"2026-08-09T18:05:28.366368Z","title":"Channel-wise autoregres- sive entropy models for learned image compression","venue":null,"work_id":"c1feaee7-571e-4685-927d-c18d9daff75c","year":2020},"citing_paper":{"arxiv_id":"2502.00700","last_updated":"2025-03-24T09:19:16Z","snapshot_observed_at":"2026-08-09T17:59:16.046441Z","submitted_at":"2025-02-02T07:15:51Z","title":"S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression","version":3},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-09T18:05:27.660353Z"},"links":{"citing_paper":"/paper/2502.00700"},"observation_digest":"sha256:5fe399dc572ac74494c87895c6312614549e3ad6f3ceed65c5448d87b07ae337","observation_id":"07a08c51-1984-4bf9-b16b-b2d20dbc06c5","resolution":{"observed_at":"2026-08-09T18:05:28.370916Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-09T18:05:28.351880Z","title":"Joint autoregressive and hierarchical priors for learned im- age compression","venue":null,"work_id":"52b1c706-1f92-4094-b2c1-325c453feb71","year":2018},"citing_paper":{"arxiv_id":"2502.00700","last_updated":"2025-03-24T09:19:16Z","snapshot_observed_at":"2026-08-09T17:59:16.046441Z","submitted_at":"2025-02-02T07:15:51Z","title":"S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression","version":3},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-09T18:05:27.665230Z"},"links":{"citing_paper":"/paper/2502.00700"},"observation_digest":"sha256:11bfa3934d51c8e2985167555fee5d579eaef8805746484d5f523ab5d002837c","observation_id":"b50574cd-7951-4765-9658-860bf66785ad","resolution":{"observed_at":"2026-08-09T18:05:28.356667Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2202.05492","last_updated":"2022-03-14T08:20:55Z","snapshot_observed_at":"2026-08-01T13:55:27.734375Z","submitted_at":"2022-02-11T08:03:31Z","title":"Entroformer: A Transformer-based Entropy Model for Learned Image Compression","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.05492","snapshot_observed_at":"2026-08-09T18:05:27.669917Z","title":"Entroformer: A transformer-based entropy model for learned image compression","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.00700","last_updated":"2025-03-24T09:19:16Z","snapshot_observed_at":"2026-08-09T17:59:16.046441Z","submitted_at":"2025-02-02T07:15:51Z","title":"S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression","version":3},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-09T18:05:27.669917Z"},"links":{"cited_paper":"/paper/2202.05492","citing_paper":"/paper/2502.00700"},"observation_digest":"sha256:74c7a309f21b9d920d001ae56f9a125d2707ffc4ea75867ccbbfaf1c51f53517","observation_id":"a6dc7549-ea9a-491a-87e3-5a68896e5512","resolution":{"observed_at":"2026-08-09T18:05:27.669917Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.15413","last_updated":"2024-05-28T13:58:14Z","snapshot_observed_at":"2026-07-06T18:19:17.573250Z","submitted_at":"2024-05-24T10:24:30Z","title":"MambaVC: Learned Visual Compression with Selective State Spaces","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.15413","snapshot_observed_at":"2026-08-09T18:05:27.674871Z","title":"Mambavc: Learned visual compression with selective state spaces","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.00700","last_updated":"2025-03-24T09:19:16Z","snapshot_observed_at":"2026-08-09T17:59:16.046441Z","submitted_at":"2025-02-02T07:15:51Z","title":"S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression","version":3},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-09T18:05:27.674871Z"},"links":{"cited_paper":"/paper/2405.15413","citing_paper":"/paper/2502.00700"},"observation_digest":"sha256:ee1bb4b3a5b07eff28969c948bd95d991e2ae9784477e68c7515ed7832003d33","observation_id":"6eb7e687-678c-4464-ac87-0d0fac05e233","resolution":{"observed_at":"2026-08-09T18:05:27.674871Z","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":"2026-08-09T18:05:28.337429Z","title":"Bayesian neural networks avoid encoding com- plex and perturbation-sensitive concepts","venue":null,"work_id":"2dcd1278-0c5a-4b32-9885-78ded47c93d6","year":2023},"citing_paper":{"arxiv_id":"2502.00700","last_updated":"2025-03-24T09:19:16Z","snapshot_observed_at":"2026-08-09T17:59:16.046441Z","submitted_at":"2025-02-02T07:15:51Z","title":"S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression","version":3},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-09T18:05:27.679867Z"},"links":{"citing_paper":"/paper/2502.00700"},"observation_digest":"sha256:c77ff567ddddc56e525c101da37e93aab7f13e0a69ce7f84845fabe4f40114e6","observation_id":"ce40436c-7508-40fc-ae6c-8e4915f8a2d3","resolution":{"observed_at":"2026-08-09T18:05:28.342075Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-09T18:05:28.323397Z","title":"Mobilenetv2: Inverted residuals and linear bottlenecks","venue":null,"work_id":"c914b234-cb22-46c0-a5cf-7205b5ff4f73","year":2018},"citing_paper":{"arxiv_id":"2502.00700","last_updated":"2025-03-24T09:19:16Z","snapshot_observed_at":"2026-08-09T17:59:16.046441Z","submitted_at":"2025-02-02T07:15:51Z","title":"S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression","version":3},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-09T18:05:27.684500Z"},"links":{"citing_paper":"/paper/2502.00700"},"observation_digest":"sha256:f86b1fb5a6dab4ec751d6d520cb13d34d4a068585cf3c00ec7cdc6a85ca6e085","observation_id":"8a13e6c4-d356-427c-8ba6-552bc5d5f55a","resolution":{"observed_at":"2026-08-09T18:05:28.327939Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-09T18:05:28.309399Z","title":"Training data-efficient image transformers & distillation through atten- tion","venue":null,"work_id":"8e085948-561d-4a73-854a-51a13a99d00a","year":2021},"citing_paper":{"arxiv_id":"2502.00700","last_updated":"2025-03-24T09:19:16Z","snapshot_observed_at":"2026-08-09T17:59:16.046441Z","submitted_at":"2025-02-02T07:15:51Z","title":"S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression","version":3},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-09T18:05:27.689209Z"},"links":{"citing_paper":"/paper/2502.00700"},"observation_digest":"sha256:62fa495eff9064eac9bd9e266275632fc6e6437e594f45e372932b7c3f12599b","observation_id":"e2d3c1fc-30ae-479f-9241-d55e6b43ea91","resolution":{"observed_at":"2026-08-09T18:05:28.314033Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-09T18:05:27.694031Z","title":"Attention is all you need","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2502.00700","last_updated":"2025-03-24T09:19:16Z","snapshot_observed_at":"2026-08-09T17:59:16.046441Z","submitted_at":"2025-02-02T07:15:51Z","title":"S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression","version":3},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-09T18:05:27.694031Z"},"links":{"citing_paper":"/paper/2502.00700"},"observation_digest":"sha256:3680bae84ac6639b62d86a54379ac27bfaea3c027c7c3f15006b2c3d3b2a2c8e","observation_id":"2be156e3-f5df-4232-8ae6-2397f75d68a6","resolution":{"observed_at":"2026-08-09T18:05:27.694031Z","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":"2026-08-09T18:05:28.284652Z","title":"Vision transformer with deformable attention","venue":null,"work_id":"c06e9523-2e6b-4738-a5ba-9e0d1fa37e34","year":2022},"citing_paper":{"arxiv_id":"2502.00700","last_updated":"2025-03-24T09:19:16Z","snapshot_observed_at":"2026-08-09T17:59:16.046441Z","submitted_at":"2025-02-02T07:15:51Z","title":"S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression","version":3},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-09T18:05:27.698592Z"},"links":{"citing_paper":"/paper/2502.00700"},"observation_digest":"sha256:692894d4218fe56ce77cd695b7c75b2ab6252e6c736ec77ad3dcc9a0f2f57cce","observation_id":"f5973ba8-28ab-4d3d-8c35-06a9f873b6c5","resolution":{"observed_at":"2026-08-09T18:05:28.289406Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-09T18:05:28.269523Z","title":"Enhanced invertible encoding for learned image compression","venue":null,"work_id":"1a1decc6-d6ba-4201-9829-5a8cfdeb904a","year":2021},"citing_paper":{"arxiv_id":"2502.00700","last_updated":"2025-03-24T09:19:16Z","snapshot_observed_at":"2026-08-09T17:59:16.046441Z","submitted_at":"2025-02-02T07:15:51Z","title":"S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression","version":3},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-09T18:05:27.702929Z"},"links":{"citing_paper":"/paper/2502.00700"},"observation_digest":"sha256:080fff5f95e85aad63d6d155581a4707e90594ef1c9636fa87de79d593a74664","observation_id":"17a79e18-614f-4896-8122-bae99b361cbc","resolution":{"observed_at":"2026-08-09T18:05:28.274700Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-09T18:05:28.252838Z","title":"Metaformer is actually what you need for vision","venue":null,"work_id":"90107200-1029-440b-a05c-85b17f07736c","year":2022},"citing_paper":{"arxiv_id":"2502.00700","last_updated":"2025-03-24T09:19:16Z","snapshot_observed_at":"2026-08-09T17:59:16.046441Z","submitted_at":"2025-02-02T07:15:51Z","title":"S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression","version":3},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-09T18:05:27.707331Z"},"links":{"citing_paper":"/paper/2502.00700"},"observation_digest":"sha256:78e313fcfd3cfebf4a2f0bf627beb4da7a989b43dcb64f274e2de72365e30ea8","observation_id":"d4834d6a-ee30-46d7-ab81-1d0cc859ff23","resolution":{"observed_at":"2026-08-09T18:05:28.258323Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-09T18:05:28.238206Z","title":"Metaformer baselines for vision","venue":null,"work_id":"65a0b023-7cc9-4f28-a3c4-5dc394952e02","year":2023},"citing_paper":{"arxiv_id":"2502.00700","last_updated":"2025-03-24T09:19:16Z","snapshot_observed_at":"2026-08-09T17:59:16.046441Z","submitted_at":"2025-02-02T07:15:51Z","title":"S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression","version":3},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-09T18:05:27.711932Z"},"links":{"citing_paper":"/paper/2502.00700"},"observation_digest":"sha256:d57c280d7e831a67f2bbdccea6f326f3073c3d0efadc92c26251b6b8e5cd453e","observation_id":"6986612c-1ed1-42a6-a4dd-df6568ea6a48","resolution":{"observed_at":"2026-08-09T18:05:28.242723Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-09T18:05:28.223270Z","title":"Frequency disentangled features in 10 neural image compression","venue":null,"work_id":"1687e0b0-0cf5-4c6b-b337-6b64bccc8a44","year":2023},"citing_paper":{"arxiv_id":"2502.00700","last_updated":"2025-03-24T09:19:16Z","snapshot_observed_at":"2026-08-09T17:59:16.046441Z","submitted_at":"2025-02-02T07:15:51Z","title":"S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression","version":3},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-09T18:05:27.716220Z"},"links":{"citing_paper":"/paper/2502.00700"},"observation_digest":"sha256:a60bf2de7352f7569e3998ebed7ec800fe185cd42526de1d0e01a612f082c872","observation_id":"7e69885b-6815-4a62-97b7-9b5bc3dc1703","resolution":{"observed_at":"2026-08-09T18:05:28.227877Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-09T18:05:27.720783Z","title":"Restormer: Efficient transformer for high-resolution image restoration","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.00700","last_updated":"2025-03-24T09:19:16Z","snapshot_observed_at":"2026-08-09T17:59:16.046441Z","submitted_at":"2025-02-02T07:15:51Z","title":"S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression","version":3},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-09T18:05:27.720783Z"},"links":{"citing_paper":"/paper/2502.00700"},"observation_digest":"sha256:4270e532f3bff3d15a651d92f3fba2a7fb23675a03299d5a498b7b8dc58a997a","observation_id":"f2169e34-67be-46d1-82d0-76316e644b2b","resolution":{"observed_at":"2026-08-09T18:05:27.720783Z","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":"2026-08-09T18:05:28.200107Z","title":"Practical blind denoising via swin-conv-unet and data synthesis","venue":null,"work_id":"da3e3ef4-42c6-48c7-80aa-e667f2b9d0c1","year":2022},"citing_paper":{"arxiv_id":"2502.00700","last_updated":"2025-03-24T09:19:16Z","snapshot_observed_at":"2026-08-09T17:59:16.046441Z","submitted_at":"2025-02-02T07:15:51Z","title":"S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression","version":3},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-09T18:05:27.725492Z"},"links":{"citing_paper":"/paper/2502.00700"},"observation_digest":"sha256:33344350bb4d2498e398a39fb36da6034ce554eb029c1027902608bb9a4de6e4","observation_id":"cd7504ec-b542-4146-8393-ede96be9b6dd","resolution":{"observed_at":"2026-08-09T18:05:28.204795Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-09T18:05:28.184995Z","title":"Neural rate control for learned video compression","venue":null,"work_id":"0bce7680-3105-408d-9921-81d1e2c695f8","year":2023},"citing_paper":{"arxiv_id":"2502.00700","last_updated":"2025-03-24T09:19:16Z","snapshot_observed_at":"2026-08-09T17:59:16.046441Z","submitted_at":"2025-02-02T07:15:51Z","title":"S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression","version":3},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-09T18:05:27.730131Z"},"links":{"citing_paper":"/paper/2502.00700"},"observation_digest":"sha256:f15c7450152465a6a80ae86142c37e90f4768add0858dc69735cc061192f5d8a","observation_id":"cfe3f9d7-6b92-4ced-b1a2-2ef859730585","resolution":{"observed_at":"2026-08-09T18:05:28.189754Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-09T18:05:28.169810Z","title":"Transformer-based transform coding","venue":null,"work_id":"a8b8138d-3ba4-4817-9263-3e90a5e39e70","year":2022},"citing_paper":{"arxiv_id":"2502.00700","last_updated":"2025-03-24T09:19:16Z","snapshot_observed_at":"2026-08-09T17:59:16.046441Z","submitted_at":"2025-02-02T07:15:51Z","title":"S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression","version":3},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-09T18:05:27.734421Z"},"links":{"citing_paper":"/paper/2502.00700"},"observation_digest":"sha256:6b85327d16587d575c455004c62ce6886ca7770c117361b7415b2ec0facae2f9","observation_id":"588eef0f-ef55-4d09-97d6-33b18e475851","resolution":{"observed_at":"2026-08-09T18:05:28.174740Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+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":"2026-08-09T18:05:28.151525Z","title":"The devil is in the details: Window-based attention for image compression","venue":null,"work_id":"66b486dd-391f-4a69-b5e1-a2082c296cd9","year":2022},"citing_paper":{"arxiv_id":"2502.00700","last_updated":"2025-03-24T09:19:16Z","snapshot_observed_at":"2026-08-09T17:59:16.046441Z","submitted_at":"2025-02-02T07:15:51Z","title":"S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression","version":3},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-09T18:05:27.738703Z"},"links":{"citing_paper":"/paper/2502.00700"},"observation_digest":"sha256:1dfd5fa2590a55c605e3f41fe19f23ba5ff0bf01aee264fae3e79c882623ec35","observation_id":"5ae4e721-f41b-4da9-9ed9-1d7fc95011ef","resolution":{"observed_at":"2026-08-09T18:05:28.158880Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2502.00700","last_updated":"2025-03-24T09:19:16Z","latest_version":3,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-09T17:59:16.046441Z","submitted_at":"2025-02-02T07:15:51Z","title":"S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compression"},"reference_resolution":{"displayed":58,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":14,"verified_exact":0,"verified_fuzzy":44},"total_outbound_references":58},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 58 of 58 outbound references and 1 inbound Pith citation observation for arXiv:2502.00700."}