{"as_of":"2026-08-18T08:42:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:39d0ccfc3c98e99ffe85f3882def9fc448ac60fd9c02e767f71ba4360f13fae0","coverage":[{"denominator":52,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":52,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T21:35:18.613716Z","state":"measured"},{"denominator":56,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":56,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T19:29:42.169335Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-07T00:47:53.340867Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2412.04307","last_updated":"2025-09-02T07:20:33Z","snapshot_observed_at":"2026-08-15T07:39:33.926647Z","submitted_at":"2024-12-05T16:26:37Z","title":"Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.04307","snapshot_observed_at":"2026-08-07T05:39:11.838893Z","title":"arXiv preprint arXiv:2412.04307 (2024)","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.07412","last_updated":"2025-09-02T08:58:40Z","snapshot_observed_at":"2026-08-17T22:56:56.524797Z","submitted_at":"2025-06-09T04:16:39Z","title":"Compressed Feature Quality Assessment: Dataset and Baselines","version":2},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-07T05:39:11.838893Z"},"links":{"cited_paper":"/paper/2412.04307","citing_paper":"/paper/2506.07412"},"observation_digest":"sha256:5f9483569ca8949690d48bc5b02003fb8747e3cf7375e14fce15ffa085a485f3","observation_id":"eded7399-e123-41fd-b622-61fe4d44e953","resolution":{"observed_at":"2026-08-07T05:39:11.838893Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.04307","last_updated":"2025-09-02T07:20:33Z","snapshot_observed_at":"2026-08-15T07:39:33.926647Z","submitted_at":"2024-12-05T16:26:37Z","title":"Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark","version":4},"cited_work":{"arxiv_id":"2412.04307","doi":null,"metadata_source":"pith","pith_arxiv_id":"2412.04307","snapshot_observed_at":"2026-08-07T00:47:53.340867Z","title":"Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark","venue":"cs.MM","work_id":"79350797-06a2-4180-837f-61170eb2efc3","year":2024},"citing_paper":{"arxiv_id":"2506.12737","last_updated":"2025-06-15T06:14:02Z","snapshot_observed_at":"2026-08-13T21:44:22.513374Z","submitted_at":"2025-06-15T06:14:02Z","title":"Cross-architecture universal feature coding via distribution alignment","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T00:47:53.283503Z"},"links":{"cited_paper":"/paper/2412.04307","citing_paper":"/paper/2506.12737"},"observation_digest":"sha256:f312183e12b737ae044b6474bffc056478425aa80f068e0bb44b9be4993acbe3","observation_id":"795e52ae-b18f-41e3-892f-437a221b8c3f","resolution":{"observed_at":"2026-08-07T00:47:53.347796Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.04307","last_updated":"2025-09-02T07:20:33Z","snapshot_observed_at":"2026-08-15T07:39:33.926647Z","submitted_at":"2024-12-05T16:26:37Z","title":"Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.04307","snapshot_observed_at":"2026-08-15T19:29:42.169335Z","title":"arXiv preprint arXiv:2412.04307 (2024)","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.16495","last_updated":"2025-09-02T08:47:06Z","snapshot_observed_at":"2026-08-17T18:31:50.808396Z","submitted_at":"2025-06-19T17:43:32Z","title":"DT-UFC: Universal Large Model Feature Coding via Peaky-to-Balanced Distribution Transformation","version":2},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-15T19:29:42.169335Z"},"links":{"cited_paper":"/paper/2412.04307","citing_paper":"/paper/2506.16495"},"observation_digest":"sha256:50ed50e15468e3a5a0a954e52f0e30267808f2847464e840d12a4ad83f777854","observation_id":"fdff1977-a93c-492c-bde2-fa3c9260f00e","resolution":{"observed_at":"2026-08-15T19:29:42.169335Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.04307","last_updated":"2025-09-02T07:20:33Z","snapshot_observed_at":"2026-08-15T07:39:33.926647Z","submitted_at":"2024-12-05T16:26:37Z","title":"Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.04307","snapshot_observed_at":"2026-08-14T04:28:16.862213Z","title":"Feature coding in the era of large models: Dataset, test conditions, and benchmark,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.08832","last_updated":"2026-08-09T17:32:04Z","snapshot_observed_at":"2026-08-16T18:38:36.052667Z","submitted_at":"2026-08-09T17:32:04Z","title":"Visual Token Codec: Unleashing Spatial Redundancy for ViT Feature Coding","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-14T04:28:16.862213Z"},"links":{"cited_paper":"/paper/2412.04307","citing_paper":"/paper/2608.08832"},"observation_digest":"sha256:a592d37072e368bb848ca746d02a26c571c9525db77a779aeda3f4931e9bf884","observation_id":"939425c4-6526-47c3-9d9f-523d5baae060","resolution":{"observed_at":"2026-08-14T04:28:16.862213Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2412.04307/citation-record","integrity":"/paper/2412.04307/integrity","json":"/paper/2412.04307/citation-record.json","paper":"/paper/2412.04307"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"1802.01436","last_updated":"2018-05-01T05:30:29Z","snapshot_observed_at":"2026-08-14T19:50:03.273877Z","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":"2026-08-11T21:35:18.353552Z","title":"Minnen, Saurabh Singh, Sung Jin Hwang, and Nick Johnston","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.04307","last_updated":"2025-09-02T07:20:33Z","snapshot_observed_at":"2026-08-15T07:39:33.926647Z","submitted_at":"2024-12-05T16:26:37Z","title":"Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark","version":4},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-11T21:35:18.353552Z"},"links":{"cited_paper":"/paper/1802.01436","citing_paper":"/paper/2412.04307"},"observation_digest":"sha256:1a3bcd988d63035a32a2235bf9751cfded08d4e3a4777bf64c3135f69831764d","observation_id":"99487b15-c6fe-4ea8-8d67-95c6a660c7bd","resolution":{"observed_at":"2026-08-11T21:35:18.353552Z","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":"2026-08-11T21:35:19.717483Z","title":"Sullivan, and Jens-Rainer Ohm","venue":null,"work_id":"e1c37cba-1409-4fd0-8fcd-be8991164ce6","year":2021},"citing_paper":{"arxiv_id":"2412.04307","last_updated":"2025-09-02T07:20:33Z","snapshot_observed_at":"2026-08-15T07:39:33.926647Z","submitted_at":"2024-12-05T16:26:37Z","title":"Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark","version":4},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-11T21:35:18.360250Z"},"links":{"citing_paper":"/paper/2412.04307"},"observation_digest":"sha256:3ec8b1de87057f733e13d7d1dfb7d9e919b33a805d45189ebb7f5d74e6b2367c","observation_id":"32cab4a8-ef7b-4a67-ba94-e1b4e6799e7c","resolution":{"observed_at":"2026-08-11T21:35:19.722215Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T21:35:19.701213Z","title":"High efficient 3D convolution feature compression","venue":null,"work_id":"7851cfae-4909-483f-9dc9-b3ded3e60045","year":2022},"citing_paper":{"arxiv_id":"2412.04307","last_updated":"2025-09-02T07:20:33Z","snapshot_observed_at":"2026-08-15T07:39:33.926647Z","submitted_at":"2024-12-05T16:26:37Z","title":"Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark","version":4},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-11T21:35:18.365457Z"},"links":{"citing_paper":"/paper/2412.04307"},"observation_digest":"sha256:ed7c63cd8d2c306f89f374808602e906d70d02593768cf0e656e20d95126e18e","observation_id":"3027d47b-9b4c-42d1-b51d-079474c5287d","resolution":{"observed_at":"2026-08-11T21:35:19.706481Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T21:35:19.684440Z","title":"When federated learning meets privacy- preserving computation","venue":null,"work_id":"29feec6e-b1eb-4867-bc92-78c0802acb3a","year":2024},"citing_paper":{"arxiv_id":"2412.04307","last_updated":"2025-09-02T07:20:33Z","snapshot_observed_at":"2026-08-15T07:39:33.926647Z","submitted_at":"2024-12-05T16:26:37Z","title":"Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark","version":4},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-11T21:35:18.371324Z"},"links":{"citing_paper":"/paper/2412.04307"},"observation_digest":"sha256:ed34a58bfe696fc68c05d2910a1a386fb0fe7b818424e48711e4e082ba23096f","observation_id":"d8e0c3dc-e149-4acf-92a2-a0e5fbdfa2ed","resolution":{"observed_at":"2026-08-11T21:35:19.689652Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T21:35:19.666468Z","title":"End-to-end learned scalable multilayer feature compression for machine vision tasks","venue":null,"work_id":"b0180f14-2156-4bd8-9ac2-60e3582eab95","year":2024},"citing_paper":{"arxiv_id":"2412.04307","last_updated":"2025-09-02T07:20:33Z","snapshot_observed_at":"2026-08-15T07:39:33.926647Z","submitted_at":"2024-12-05T16:26:37Z","title":"Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark","version":4},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-11T21:35:18.376465Z"},"links":{"citing_paper":"/paper/2412.04307"},"observation_digest":"sha256:5af3e8760879e8555c13890cbc210b1ac79d865146007e9868580607078e0443","observation_id":"e133e5b0-c530-44d7-bef0-2adae5aa9ea5","resolution":{"observed_at":"2026-08-11T21:35:19.672197Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T21:35:19.645486Z","title":"Toward intelligent sensing: Inter- mediate deep feature compression","venue":null,"work_id":"96a01f80-3652-439d-9802-ca18228b7917","year":2020},"citing_paper":{"arxiv_id":"2412.04307","last_updated":"2025-09-02T07:20:33Z","snapshot_observed_at":"2026-08-15T07:39:33.926647Z","submitted_at":"2024-12-05T16:26:37Z","title":"Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark","version":4},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-11T21:35:18.381793Z"},"links":{"citing_paper":"/paper/2412.04307"},"observation_digest":"sha256:0e327caf84717949add4c6b6d33dd3183437ab850a1df7f0a8f53a49dc88987d","observation_id":"e4c84828-083d-497a-8358-185ad5cb6cee","resolution":{"observed_at":"2026-08-11T21:35:19.651079Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T21:35:19.629821Z","title":null,"venue":null,"work_id":"d4192e28-2d83-48ba-8671-2d18c02f7931","year":2021},"citing_paper":{"arxiv_id":"2412.04307","last_updated":"2025-09-02T07:20:33Z","snapshot_observed_at":"2026-08-15T07:39:33.926647Z","submitted_at":"2024-12-05T16:26:37Z","title":"Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark","version":4},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-11T21:35:18.387703Z"},"links":{"citing_paper":"/paper/2412.04307"},"observation_digest":"sha256:faf3960f62ba8abff92fe3f17dede114c9f45e71e1851e10a2622009cc4009d8","observation_id":"13baf8ea-f96b-479e-b792-5d196c317e0c","resolution":{"observed_at":"2026-08-11T21:35:19.634784Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T21:35:19.614163Z","title":"ImageNet: a large-scale hierarchical image database","venue":null,"work_id":"0d19f98e-74c2-44da-a45b-f4b71770fb5b","year":2009},"citing_paper":{"arxiv_id":"2412.04307","last_updated":"2025-09-02T07:20:33Z","snapshot_observed_at":"2026-08-15T07:39:33.926647Z","submitted_at":"2024-12-05T16:26:37Z","title":"Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark","version":4},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-11T21:35:18.393044Z"},"links":{"citing_paper":"/paper/2412.04307"},"observation_digest":"sha256:d63d0feb7d5e85fcc5dab4f8374f2d9865443dfdab9b97f51d56483415af614f","observation_id":"fa7d2122-959d-422d-a3aa-16926db30ea6","resolution":{"observed_at":"2026-08-11T21:35:19.619235Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.19836","last_updated":"2025-08-06T10:05:27Z","snapshot_observed_at":"2026-08-16T13:47:19.828921Z","submitted_at":"2024-10-20T13:01:53Z","title":"Upsampling DINOv2 features for unsupervised vision tasks and weakly supervised materials segmentation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.19836","snapshot_observed_at":"2026-08-11T21:35:18.398152Z","title":"Upsampling DINOv2 features for unsupervised vi- sion tasks and weakly supervised materials segmentation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.04307","last_updated":"2025-09-02T07:20:33Z","snapshot_observed_at":"2026-08-15T07:39:33.926647Z","submitted_at":"2024-12-05T16:26:37Z","title":"Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark","version":4},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-11T21:35:18.398152Z"},"links":{"cited_paper":"/paper/2410.19836","citing_paper":"/paper/2412.04307"},"observation_digest":"sha256:cd072d7f5411507db6ab1b505cf13bdc1599e4c72db915ca920a0049b9ace296","observation_id":"657682d1-132f-4d1c-97fa-9a8db120a33b","resolution":{"observed_at":"2026-08-11T21:35:18.398152Z","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":"2026-08-11T21:35:19.597366Z","title":"Video coding for machines: A paradigm of collab- orative compression and intelligent analytics.IEEE Transac- tions on Image Processing, 29:8680–8695, 2020","venue":null,"work_id":"b1b1321f-5c5e-4a9c-87e7-4db6dc2cb560","year":2020},"citing_paper":{"arxiv_id":"2412.04307","last_updated":"2025-09-02T07:20:33Z","snapshot_observed_at":"2026-08-15T07:39:33.926647Z","submitted_at":"2024-12-05T16:26:37Z","title":"Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark","version":4},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-11T21:35:18.403190Z"},"links":{"citing_paper":"/paper/2412.04307"},"observation_digest":"sha256:6c578c958bb6fd32286873dd1a9fb2c25039b6d678a2c088c89147d391aea2ab","observation_id":"5f891cc7-7635-417f-a9f7-270443e906ca","resolution":{"observed_at":"2026-08-11T21:35:19.602963Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.21783","last_updated":"2024-11-23T23:27:33Z","snapshot_observed_at":"2026-08-13T17:20:44.002518Z","submitted_at":"2024-07-31T17:54:27Z","title":"The Llama 3 Herd of Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.21783","snapshot_observed_at":"2026-08-11T21:35:18.408068Z","title":"The Llama 3 herd of models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.04307","last_updated":"2025-09-02T07:20:33Z","snapshot_observed_at":"2026-08-15T07:39:33.926647Z","submitted_at":"2024-12-05T16:26:37Z","title":"Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark","version":4},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-11T21:35:18.408068Z"},"links":{"cited_paper":"/paper/2407.21783","citing_paper":"/paper/2412.04307"},"observation_digest":"sha256:b784ce30247e80f436dff6c5c3dc768f945fe852ecec82a02961210fe4669648","observation_id":"2ddf5411-4f61-4fb2-8388-d6d81d4a0cb5","resolution":{"observed_at":"2026-08-11T21:35:18.408068Z","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":"2026-08-11T21:35:19.582223Z","title":"Scaling recti- fied flow transformers for high-resolution image synthesis","venue":null,"work_id":"54294473-5a0d-4d22-bc8b-f99bb163362e","year":2024},"citing_paper":{"arxiv_id":"2412.04307","last_updated":"2025-09-02T07:20:33Z","snapshot_observed_at":"2026-08-15T07:39:33.926647Z","submitted_at":"2024-12-05T16:26:37Z","title":"Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark","version":4},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-11T21:35:18.413149Z"},"links":{"citing_paper":"/paper/2412.04307"},"observation_digest":"sha256:6ae80a90f376dcf78697b6b9870178f4f12717870583dfe656d2fbe429e5a985","observation_id":"8c86a9a8-83f1-44d4-9418-3546f255f588","resolution":{"observed_at":"2026-08-11T21:35:19.587303Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T21:35:19.564861Z","title":"Image coding for machines with omnipotent feature learn- ing","venue":null,"work_id":"d9d5ae7d-9a65-4232-a4e3-676f918b0e8a","year":2022},"citing_paper":{"arxiv_id":"2412.04307","last_updated":"2025-09-02T07:20:33Z","snapshot_observed_at":"2026-08-15T07:39:33.926647Z","submitted_at":"2024-12-05T16:26:37Z","title":"Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark","version":4},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-11T21:35:18.417992Z"},"links":{"citing_paper":"/paper/2412.04307"},"observation_digest":"sha256:08974b3a11cf4b627cb49d157667b337fa98a1ccc68d9cde2f6ad49725c8ce97","observation_id":"3cd24b9f-4927-4663-86f1-b988b762fcb8","resolution":{"observed_at":"2026-08-11T21:35:19.571230Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T21:35:19.547182Z","title":"LLM-based edge intelligence: A comprehensive survey on architectures, applications, security and trustworthiness","venue":null,"work_id":"a769180d-f17d-4a96-b72f-b816ded456ad","year":2024},"citing_paper":{"arxiv_id":"2412.04307","last_updated":"2025-09-02T07:20:33Z","snapshot_observed_at":"2026-08-15T07:39:33.926647Z","submitted_at":"2024-12-05T16:26:37Z","title":"Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark","version":4},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-11T21:35:18.422579Z"},"links":{"citing_paper":"/paper/2412.04307"},"observation_digest":"sha256:887b84ac8ff7e5c383bb94d58a5457fecc15040fbbfba2cab043ced4534cbaf9","observation_id":"23e70fe8-a20f-4ec5-9828-f1385f3cbeb9","resolution":{"observed_at":"2026-08-11T21:35:19.552343Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T21:35:19.530561Z","title":"Towards task-generic image compression: A study of semantics- oriented metrics","venue":null,"work_id":"0a0b9dc2-4a70-4504-bd64-4314097e79dc","year":2023},"citing_paper":{"arxiv_id":"2412.04307","last_updated":"2025-09-02T07:20:33Z","snapshot_observed_at":"2026-08-15T07:39:33.926647Z","submitted_at":"2024-12-05T16:26:37Z","title":"Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark","version":4},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-11T21:35:18.427253Z"},"links":{"citing_paper":"/paper/2412.04307"},"observation_digest":"sha256:3deb3ed83e6a6160104a8c389f5a54574ba2b569d2675bca8fae0d7a8549f7f7","observation_id":"5eecdd70-20f5-47a4-b5ad-a85fd3e57093","resolution":{"observed_at":"2026-08-11T21:35:19.535957Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T21:35:19.514658Z","title":"DMOFC: discrimination metric-optimized feature com- pression","venue":null,"work_id":"0f2450c2-b9b5-4a22-9b21-64a7a605473e","year":2024},"citing_paper":{"arxiv_id":"2412.04307","last_updated":"2025-09-02T07:20:33Z","snapshot_observed_at":"2026-08-15T07:39:33.926647Z","submitted_at":"2024-12-05T16:26:37Z","title":"Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark","version":4},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-11T21:35:18.432018Z"},"links":{"citing_paper":"/paper/2412.04307"},"observation_digest":"sha256:d08dc1b4796e056f68fd13f2c853207e46949a757e4a78508713e01621c7c5f9","observation_id":"e513e774-52e9-44d0-a900-19d016d1aab1","resolution":{"observed_at":"2026-08-11T21:35:19.520181Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T21:35:19.497332Z","title":"Rethinking the joint optimization in video coding for machines: A case study","venue":null,"work_id":"914ba0f9-478f-495a-bc03-081e65933574","year":2024},"citing_paper":{"arxiv_id":"2412.04307","last_updated":"2025-09-02T07:20:33Z","snapshot_observed_at":"2026-08-15T07:39:33.926647Z","submitted_at":"2024-12-05T16:26:37Z","title":"Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark","version":4},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-11T21:35:18.436584Z"},"links":{"citing_paper":"/paper/2412.04307"},"observation_digest":"sha256:ccf877af874571b281f6ed292d8c77eacc44ce19eaf9e2504011b168994e2fce","observation_id":"3aadc8ff-5a4d-4590-a9a4-360e06ed887c","resolution":{"observed_at":"2026-08-11T21:35:19.503321Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T21:35:19.479907Z","title":"IMOFC: identity-level metric optimized fea- ture compression for identification tasks","venue":null,"work_id":"f86d4138-1984-469c-a674-183a62b6c339","year":2025},"citing_paper":{"arxiv_id":"2412.04307","last_updated":"2025-09-02T07:20:33Z","snapshot_observed_at":"2026-08-15T07:39:33.926647Z","submitted_at":"2024-12-05T16:26:37Z","title":"Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark","version":4},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-11T21:35:18.441213Z"},"links":{"citing_paper":"/paper/2412.04307"},"observation_digest":"sha256:26dcbac2976654f3f8fa0c56b6adc178883e53666bcda39cb576e0fc06071321","observation_id":"8b33e129-4650-4615-b91d-dfeba398981f","resolution":{"observed_at":"2026-08-11T21:35:19.485344Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.10169","last_updated":"2023-07-19T17:55:13Z","snapshot_observed_at":"2026-08-16T15:14:55.081059Z","submitted_at":"2023-07-19T17:55:13Z","title":"Challenges and Applications of Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.10169","snapshot_observed_at":"2026-08-11T21:35:18.445870Z","title":"Chal- lenges and applications of large language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.04307","last_updated":"2025-09-02T07:20:33Z","snapshot_observed_at":"2026-08-15T07:39:33.926647Z","submitted_at":"2024-12-05T16:26:37Z","title":"Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark","version":4},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-11T21:35:18.445870Z"},"links":{"cited_paper":"/paper/2307.10169","citing_paper":"/paper/2412.04307"},"observation_digest":"sha256:23ba822fb11d23c2936f396a9742b0e8425c1fc4c2be9e4002bcf338bc35018f","observation_id":"71406baa-9c09-4e46-91e4-0d4c975429d0","resolution":{"observed_at":"2026-08-11T21:35:18.445870Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.19651","last_updated":"2025-02-17T15:29:40Z","snapshot_observed_at":"2026-08-16T13:30:23.871553Z","submitted_at":"2024-07-29T02:32:44Z","title":"Bridging Compressed Image Latents and Multimodal Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.19651","snapshot_observed_at":"2026-08-11T21:35:18.451096Z","title":"Bridging compressed image latents and multimodal large language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.04307","last_updated":"2025-09-02T07:20:33Z","snapshot_observed_at":"2026-08-15T07:39:33.926647Z","submitted_at":"2024-12-05T16:26:37Z","title":"Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark","version":4},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-11T21:35:18.451096Z"},"links":{"cited_paper":"/paper/2407.19651","citing_paper":"/paper/2412.04307"},"observation_digest":"sha256:619e34efac820a96e5208ef7235b10f6b5b1d748abf1209809fd18a92e31e75e","observation_id":"652000b9-2845-4945-b882-34adcae3130e","resolution":{"observed_at":"2026-08-11T21:35:18.451096Z","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":"2026-08-11T21:35:19.462606Z","title":"End-to-end learnable multi-scale feature compression for VCM","venue":null,"work_id":"a4a302fd-8d57-4399-b9fc-b6edafc708c6","year":2023},"citing_paper":{"arxiv_id":"2412.04307","last_updated":"2025-09-02T07:20:33Z","snapshot_observed_at":"2026-08-15T07:39:33.926647Z","submitted_at":"2024-12-05T16:26:37Z","title":"Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark","version":4},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-11T21:35:18.455954Z"},"links":{"citing_paper":"/paper/2412.04307"},"observation_digest":"sha256:a85ffba97ebd008005343c3c9bb273c708a4890dbb1cbbe28ed9fa546e54b080","observation_id":"4c194054-61d9-4520-8b79-babb70fd103b","resolution":{"observed_at":"2026-08-11T21:35:19.467665Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1907.10326","last_updated":"2021-09-23T10:23:51Z","snapshot_observed_at":"2026-08-14T16:02:58.912669Z","submitted_at":"2019-07-24T09:31:24Z","title":"From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimation","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1907.10326","snapshot_observed_at":"2026-08-11T21:35:18.460700Z","title":"From big to small: Multi-scale local planar guidance for monocular depth estimation","venue":null,"work_id":null,"year":1907},"citing_paper":{"arxiv_id":"2412.04307","last_updated":"2025-09-02T07:20:33Z","snapshot_observed_at":"2026-08-15T07:39:33.926647Z","submitted_at":"2024-12-05T16:26:37Z","title":"Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark","version":4},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-11T21:35:18.460700Z"},"links":{"cited_paper":"/paper/1907.10326","citing_paper":"/paper/2412.04307"},"observation_digest":"sha256:182a9a108d6deb874612b5536318648ae89ef5b11f005a378b60b700b1798341","observation_id":"2460614b-f65a-42e7-98cc-58d6d7ef9e82","resolution":{"observed_at":"2026-08-11T21:35:18.460700Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.16668","last_updated":"2020-06-30T10:42:02Z","snapshot_observed_at":"2026-08-07T09:27:36.420559Z","submitted_at":"2020-06-30T10:42:02Z","title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.16668","snapshot_observed_at":"2026-08-11T21:35:18.467323Z","title":"GShard: Scaling giant models with conditional computation and automatic sharding","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2412.04307","last_updated":"2025-09-02T07:20:33Z","snapshot_observed_at":"2026-08-15T07:39:33.926647Z","submitted_at":"2024-12-05T16:26:37Z","title":"Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark","version":4},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-11T21:35:18.467323Z"},"links":{"cited_paper":"/paper/2006.16668","citing_paper":"/paper/2412.04307"},"observation_digest":"sha256:d94785470b1f64b4cbd62993000c9de4e8b32fc549dd671d86e6ee44ef099f67","observation_id":"1f9cd648-ab54-4582-a62b-06e935128c74","resolution":{"observed_at":"2026-08-11T21:35:18.467323Z","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":"2026-08-11T21:35:19.446529Z","title":"Attention-based variable-size feature compression module for edge inference","venue":null,"work_id":"3615eb24-1f1d-4932-8151-632624879653","year":2023},"citing_paper":{"arxiv_id":"2412.04307","last_updated":"2025-09-02T07:20:33Z","snapshot_observed_at":"2026-08-15T07:39:33.926647Z","submitted_at":"2024-12-05T16:26:37Z","title":"Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark","version":4},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-11T21:35:18.473383Z"},"links":{"citing_paper":"/paper/2412.04307"},"observation_digest":"sha256:c5764272ef3817373557eb5f9db9946d2606fba1683888447194153e55a3c61f","observation_id":"bb83025b-f64d-410d-84c5-c32b4019d31f","resolution":{"observed_at":"2026-08-11T21:35:19.451610Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2409.08481","last_updated":"2025-03-16T02:09:46Z","snapshot_observed_at":"2026-08-16T13:18:57.819824Z","submitted_at":"2024-09-13T02:13:11Z","title":"USTC-TD: A Test Dataset and Benchmark for Image and Video Coding in 2020s","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.08481","snapshot_observed_at":"2026-08-11T21:35:18.478740Z","title":"Ustc-td: A test dataset and bench- mark for image and video coding in 2020s","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.04307","last_updated":"2025-09-02T07:20:33Z","snapshot_observed_at":"2026-08-15T07:39:33.926647Z","submitted_at":"2024-12-05T16:26:37Z","title":"Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark","version":4},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-11T21:35:18.478740Z"},"links":{"cited_paper":"/paper/2409.08481","citing_paper":"/paper/2412.04307"},"observation_digest":"sha256:a8df616c5b7cec01416c90aa94d2078e3c735a1e68c331331df397adfc8b345a","observation_id":"79119655-497b-428d-b072-b04790f28e19","resolution":{"observed_at":"2026-08-11T21:35:18.478740Z","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":"2026-08-11T21:35:19.430587Z","title":"Object segmentation-assisted inter prediction for versatile video coding","venue":null,"work_id":"c03d97ce-107b-4709-8785-8a74fa183b52","year":2024},"citing_paper":{"arxiv_id":"2412.04307","last_updated":"2025-09-02T07:20:33Z","snapshot_observed_at":"2026-08-15T07:39:33.926647Z","submitted_at":"2024-12-05T16:26:37Z","title":"Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark","version":4},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-11T21:35:18.483921Z"},"links":{"citing_paper":"/paper/2412.04307"},"observation_digest":"sha256:59ceb1aeb3bad69aab93f302a9665526ff6c9938cf318df871c86eaf3b785505","observation_id":"e4ac328c-9a18-45fe-80a4-4e066c6abe30","resolution":{"observed_at":"2026-08-11T21:35:19.435860Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T21:35:19.413370Z","title":"Learnt mutual feature compression for machine vision","venue":null,"work_id":"726f46f9-f2f0-41f5-a208-c29b5ee228fe","year":2023},"citing_paper":{"arxiv_id":"2412.04307","last_updated":"2025-09-02T07:20:33Z","snapshot_observed_at":"2026-08-15T07:39:33.926647Z","submitted_at":"2024-12-05T16:26:37Z","title":"Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark","version":4},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-11T21:35:18.488755Z"},"links":{"citing_paper":"/paper/2412.04307"},"observation_digest":"sha256:0f96f06e6f0ad110dd160f8b91e6a272993d17794cae2bc8735b492f44306a78","observation_id":"65d77563-c5fe-424b-8b5a-9ecf870dfd36","resolution":{"observed_at":"2026-08-11T21:35:19.419054Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T21:35:19.396083Z","title":"Preprocessing enhanced image compression for ma- chine vision","venue":null,"work_id":"bae89aad-6866-40ea-8e8c-ee0351c65af3","year":2024},"citing_paper":{"arxiv_id":"2412.04307","last_updated":"2025-09-02T07:20:33Z","snapshot_observed_at":"2026-08-15T07:39:33.926647Z","submitted_at":"2024-12-05T16:26:37Z","title":"Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark","version":4},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-11T21:35:18.493936Z"},"links":{"citing_paper":"/paper/2412.04307"},"observation_digest":"sha256:994c4b218541cef39c436d8e5966d4c67ac3174d18f703aa3958139e4702c44d","observation_id":"9ed152ec-a9fe-492a-b143-2c4604c51af0","resolution":{"observed_at":"2026-08-11T21:35:19.401042Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T21:35:19.379702Z","title":null,"venue":null,"work_id":"ee6fb586-6f72-4d38-8493-067dcbf2a179","year":2024},"citing_paper":{"arxiv_id":"2412.04307","last_updated":"2025-09-02T07:20:33Z","snapshot_observed_at":"2026-08-15T07:39:33.926647Z","submitted_at":"2024-12-05T16:26:37Z","title":"Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark","version":4},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-11T21:35:18.500783Z"},"links":{"citing_paper":"/paper/2412.04307"},"observation_digest":"sha256:11569f173cb0a55921234b47adfa0706171d405d703efcab6800d02669a81788","observation_id":"f9662900-9549-4541-bbbb-e8b4349ad21a","resolution":{"observed_at":"2026-08-11T21:35:19.385082Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T21:35:19.361439Z","title":"Feature compression with 3d sparse con- volution","venue":null,"work_id":"a1ba9133-1ed7-4a64-851a-558103d390dc","year":2024},"citing_paper":{"arxiv_id":"2412.04307","last_updated":"2025-09-02T07:20:33Z","snapshot_observed_at":"2026-08-15T07:39:33.926647Z","submitted_at":"2024-12-05T16:26:37Z","title":"Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark","version":4},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-11T21:35:18.506162Z"},"links":{"citing_paper":"/paper/2412.04307"},"observation_digest":"sha256:d4af0321a11f392e5d69984da153c2e15a25d23c75cc4a3ae1fb49fe49d73e45","observation_id":"21690aa1-ce98-488c-87c8-e739aff32c05","resolution":{"observed_at":"2026-08-11T21:35:19.367027Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T21:35:19.344006Z","title":"Perceptual image compression with con- ditional diffusion transformers","venue":null,"work_id":"29c85e74-be7a-4648-bd62-72076d5cafff","year":2024},"citing_paper":{"arxiv_id":"2412.04307","last_updated":"2025-09-02T07:20:33Z","snapshot_observed_at":"2026-08-15T07:39:33.926647Z","submitted_at":"2024-12-05T16:26:37Z","title":"Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark","version":4},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-11T21:35:18.511005Z"},"links":{"citing_paper":"/paper/2412.04307"},"observation_digest":"sha256:5e9899c49c073ffbe82261f3c257ba2ed67fed8bca8ce52fa6fc6f16b472345e","observation_id":"c4cce007-b889-406c-bf44-0963b5d140c9","resolution":{"observed_at":"2026-08-11T21:35:19.350247Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T21:35:19.326303Z","title":"Video feature compression for machine tasks","venue":null,"work_id":"61addfeb-d4d1-4823-90ac-d1273cb79baa","year":2022},"citing_paper":{"arxiv_id":"2412.04307","last_updated":"2025-09-02T07:20:33Z","snapshot_observed_at":"2026-08-15T07:39:33.926647Z","submitted_at":"2024-12-05T16:26:37Z","title":"Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark","version":4},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-11T21:35:18.516179Z"},"links":{"citing_paper":"/paper/2412.04307"},"observation_digest":"sha256:e64b3028907cf6e546e2bc325028dece389f1a0176b563851f2ce0aa7f46e173","observation_id":"58b68250-f0a4-4bec-88fd-01ab21dac0f2","resolution":{"observed_at":"2026-08-11T21:35:19.331484Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2304.07193","last_updated":"2024-02-02T10:24:09Z","snapshot_observed_at":"2026-08-17T13:03:40.359628Z","submitted_at":"2023-04-14T15:12:19Z","title":"DINOv2: Learning Robust Visual Features without Supervision","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.07193","snapshot_observed_at":"2026-08-11T21:35:18.520798Z","title":"DINOv2: Learning robust visual features without supervi- sion","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.04307","last_updated":"2025-09-02T07:20:33Z","snapshot_observed_at":"2026-08-15T07:39:33.926647Z","submitted_at":"2024-12-05T16:26:37Z","title":"Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark","version":4},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-11T21:35:18.520798Z"},"links":{"cited_paper":"/paper/2304.07193","citing_paper":"/paper/2412.04307"},"observation_digest":"sha256:ecfc8fa2edda79df4b53a710aa110ccb64604f439a9d2efac09f3e8055a3e45f","observation_id":"ef2fdf8e-b4c0-4ced-9418-b5add2537cbf","resolution":{"observed_at":"2026-08-11T21:35:18.520798Z","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":"2026-08-11T21:35:18.525940Z","title":"Learn- ing transferable visual models from natural language super- vision","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.04307","last_updated":"2025-09-02T07:20:33Z","snapshot_observed_at":"2026-08-15T07:39:33.926647Z","submitted_at":"2024-12-05T16:26:37Z","title":"Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark","version":4},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-11T21:35:18.525940Z"},"links":{"citing_paper":"/paper/2412.04307"},"observation_digest":"sha256:9c58be54a8a24bf9c9e401e7908dc5a4188dfec118e491cd71d890d446404f31","observation_id":"5da21e00-ef04-4a8f-8250-b07c1e43086c","resolution":{"observed_at":"2026-08-11T21:35:18.525940Z","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":"2026-08-11T21:35:19.299322Z","title":"Vnvc: A versatile neural video coding framework for efficient human- machine vision","venue":null,"work_id":"6f1a965d-76df-4e42-ab68-b7b317a36e6e","year":2024},"citing_paper":{"arxiv_id":"2412.04307","last_updated":"2025-09-02T07:20:33Z","snapshot_observed_at":"2026-08-15T07:39:33.926647Z","submitted_at":"2024-12-05T16:26:37Z","title":"Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark","version":4},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-11T21:35:18.530616Z"},"links":{"citing_paper":"/paper/2412.04307"},"observation_digest":"sha256:da67d28c3a38ad88bd78200c8482ab2afcce002f92ceb1c754184cfc1742fdd4","observation_id":"544f4252-0e2e-4607-a139-4ee2bfd80a71","resolution":{"observed_at":"2026-08-11T21:35:19.304410Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.15389","last_updated":"2023-03-27T17:02:21Z","snapshot_observed_at":"2026-08-16T07:24:08.156932Z","submitted_at":"2023-03-27T17:02:21Z","title":"EVA-CLIP: Improved Training Techniques for CLIP at Scale","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.15389","snapshot_observed_at":"2026-08-11T21:35:18.535656Z","title":"Eva-CLIP: improved training techniques for clip at scale","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.04307","last_updated":"2025-09-02T07:20:33Z","snapshot_observed_at":"2026-08-15T07:39:33.926647Z","submitted_at":"2024-12-05T16:26:37Z","title":"Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark","version":4},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-11T21:35:18.535656Z"},"links":{"cited_paper":"/paper/2303.15389","citing_paper":"/paper/2412.04307"},"observation_digest":"sha256:0d49739014eb961977a57cf5aac03e6f526eafd6a9c2021b5387257d1dceb823","observation_id":"adde24bf-ae11-437a-a1e3-2ef7d3cb2aaa","resolution":{"observed_at":"2026-08-11T21:35:18.535656Z","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":"2026-08-11T21:35:19.281592Z","title":"Deep feature compression using spatio-temporal arrangement toward col- laborative intelligent world","venue":null,"work_id":"478fa222-f051-4c17-975b-02da2b1c785f","year":2022},"citing_paper":{"arxiv_id":"2412.04307","last_updated":"2025-09-02T07:20:33Z","snapshot_observed_at":"2026-08-15T07:39:33.926647Z","submitted_at":"2024-12-05T16:26:37Z","title":"Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark","version":4},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-11T21:35:18.540567Z"},"links":{"citing_paper":"/paper/2412.04307"},"observation_digest":"sha256:8f7ab8ec9bfb2957c864221adc2f29b3003866a942deb2d59acb650ccb47d9c7","observation_id":"36693ca7-b02b-4933-827e-2ed1c842d27b","resolution":{"observed_at":"2026-08-11T21:35:19.287256Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T21:35:19.259000Z","title":"FedBERT: when federated learning meets pre-training","venue":null,"work_id":"e4e77e75-bc18-4a98-ad88-5020c63574e9","year":2022},"citing_paper":{"arxiv_id":"2412.04307","last_updated":"2025-09-02T07:20:33Z","snapshot_observed_at":"2026-08-15T07:39:33.926647Z","submitted_at":"2024-12-05T16:26:37Z","title":"Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark","version":4},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-11T21:35:18.545426Z"},"links":{"citing_paper":"/paper/2412.04307"},"observation_digest":"sha256:0fd6a2f24b9a0d92a51f807ad4827c3ad762fd344fc6e870d433d4708d887ac5","observation_id":"0f6419bc-1130-4d03-a3ae-b581c08ee2db","resolution":{"observed_at":"2026-08-11T21:35:19.265506Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T21:35:19.242187Z","title":"Non- semantics suppressed mask learning for unsupervised video semantic compression","venue":null,"work_id":"b82829ad-7c12-45a4-bf57-8aa3e36df496","year":2023},"citing_paper":{"arxiv_id":"2412.04307","last_updated":"2025-09-02T07:20:33Z","snapshot_observed_at":"2026-08-15T07:39:33.926647Z","submitted_at":"2024-12-05T16:26:37Z","title":"Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark","version":4},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-11T21:35:18.550076Z"},"links":{"citing_paper":"/paper/2412.04307"},"observation_digest":"sha256:5edb2eca6510dc2959e64a6ca0e28b5308f603837b17151e52d2c9be2de04d69","observation_id":"9211fb04-248a-4100-96ff-5820370817af","resolution":{"observed_at":"2026-08-11T21:35:19.247620Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T21:35:18.554637Z","title":"SMC++: masked learning of unsupervised video semantic compression","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.04307","last_updated":"2025-09-02T07:20:33Z","snapshot_observed_at":"2026-08-15T07:39:33.926647Z","submitted_at":"2024-12-05T16:26:37Z","title":"Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark","version":4},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-11T21:35:18.554637Z"},"links":{"citing_paper":"/paper/2412.04307"},"observation_digest":"sha256:e2126f8da0684079c1be0cd5c3d12e12cb5c5131a880946d94e09d8763488e97","observation_id":"bbef0549-ff8b-482c-a97d-aacd2eebb858","resolution":{"observed_at":"2026-08-11T21:35:18.554637Z","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":"2026-08-11T21:35:19.226358Z","title":"Free-VSC: free semantics from visual foundation models for unsupervised video semantic compression","venue":null,"work_id":"702ca136-d784-421e-9e44-23cd3d4e1612","year":null},"citing_paper":{"arxiv_id":"2412.04307","last_updated":"2025-09-02T07:20:33Z","snapshot_observed_at":"2026-08-15T07:39:33.926647Z","submitted_at":"2024-12-05T16:26:37Z","title":"Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark","version":4},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-11T21:35:18.559422Z"},"links":{"citing_paper":"/paper/2412.04307"},"observation_digest":"sha256:c994e55ea8db27977f0c8de2d1fc5037907dec85676752fded0692878bdbd85b","observation_id":"7371f485-d2d1-431f-9954-0ea147cde79a","resolution":{"observed_at":"2026-08-11T21:35:19.231392Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2302.13971","last_updated":"2023-02-27T17:11:15Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-02-27T17:11:15Z","title":"LLaMA: Open and Efficient Foundation Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.13971","snapshot_observed_at":"2026-08-11T21:35:18.564652Z","title":"Llama: Open and efficient foundation language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.04307","last_updated":"2025-09-02T07:20:33Z","snapshot_observed_at":"2026-08-15T07:39:33.926647Z","submitted_at":"2024-12-05T16:26:37Z","title":"Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark","version":4},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-11T21:35:18.564652Z"},"links":{"cited_paper":"/paper/2302.13971","citing_paper":"/paper/2412.04307"},"observation_digest":"sha256:dfa7139a89e90c1c9afed3a612ec113109c58344edab640d672db3f915c51741","observation_id":"38947c6c-4682-4d64-b8ba-e839e3178d82","resolution":{"observed_at":"2026-08-11T21:35:18.564652Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1812.00564","last_updated":"2018-12-03T05:43:20Z","snapshot_observed_at":"2026-08-14T23:16:38.988686Z","submitted_at":"2018-12-03T05:43:20Z","title":"Split learning for health: Distributed deep learning without sharing raw patient data","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1812.00564","snapshot_observed_at":"2026-08-11T21:35:18.569442Z","title":"Split learning for health: Distributed deep learning without sharing raw patient data","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.04307","last_updated":"2025-09-02T07:20:33Z","snapshot_observed_at":"2026-08-15T07:39:33.926647Z","submitted_at":"2024-12-05T16:26:37Z","title":"Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark","version":4},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-11T21:35:18.569442Z"},"links":{"cited_paper":"/paper/1812.00564","citing_paper":"/paper/2412.04307"},"observation_digest":"sha256:45a8803e14e4867b3496cec7fb6987d21a2e519d23346392971ca1f917831602","observation_id":"4a1c0f70-b1c6-4ca3-94af-cd2c8af82a59","resolution":{"observed_at":"2026-08-11T21:35:18.569442Z","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":"2026-08-11T21:35:19.209482Z","title":"Towards analysis- friendly face representation with scalable feature and texture compression","venue":null,"work_id":"17a327b4-2635-49ac-8826-5d97c45b1c2a","year":2022},"citing_paper":{"arxiv_id":"2412.04307","last_updated":"2025-09-02T07:20:33Z","snapshot_observed_at":"2026-08-15T07:39:33.926647Z","submitted_at":"2024-12-05T16:26:37Z","title":"Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark","version":4},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-11T21:35:18.574647Z"},"links":{"citing_paper":"/paper/2412.04307"},"observation_digest":"sha256:07795bbe74149c838b65ccfea88debd71eee36b50d596a3bcf2b4af9acd0a4bb","observation_id":"da51212f-f06e-46af-93ba-526bc4dc1e14","resolution":{"observed_at":"2026-08-11T21:35:19.215250Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T21:35:19.188591Z","title":"NExT-GPT: Any-to-any multimodal LLM","venue":null,"work_id":"768d89d5-28cc-4138-b295-99de87856d86","year":2024},"citing_paper":{"arxiv_id":"2412.04307","last_updated":"2025-09-02T07:20:33Z","snapshot_observed_at":"2026-08-15T07:39:33.926647Z","submitted_at":"2024-12-05T16:26:37Z","title":"Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark","version":4},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-11T21:35:18.579318Z"},"links":{"citing_paper":"/paper/2412.04307"},"observation_digest":"sha256:0898332cda1c8db02fa8690cde23011c75d49e05bbe1911f88252efb1ea07d4d","observation_id":"cacb124f-f7ed-4fa9-b60c-ead2c7b59276","resolution":{"observed_at":"2026-08-11T21:35:19.193958Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.05156","last_updated":"2024-03-14T14:17:57Z","snapshot_observed_at":"2026-08-16T16:58:33.981360Z","submitted_at":"2024-03-08T08:47:48Z","title":"On Protecting the Data Privacy of Large Language Models (LLMs): A Survey","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.05156","snapshot_observed_at":"2026-08-11T21:35:18.584227Z","title":"On protecting the data privacy of large language models (LLMs): A survey","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.04307","last_updated":"2025-09-02T07:20:33Z","snapshot_observed_at":"2026-08-15T07:39:33.926647Z","submitted_at":"2024-12-05T16:26:37Z","title":"Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark","version":4},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-11T21:35:18.584227Z"},"links":{"cited_paper":"/paper/2403.05156","citing_paper":"/paper/2412.04307"},"observation_digest":"sha256:8d13b3caaed84aa1ada90a381c5e964faaad00db3fba21517d6fa81e92126630","observation_id":"f737fd03-f90b-41c6-a697-d360daa64c00","resolution":{"observed_at":"2026-08-11T21:35:18.584227Z","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":"2026-08-11T21:35:19.170335Z","title":"SSSIC: Semantics-to-signal scalable image coding with learned structural representations","venue":null,"work_id":"69250b6b-b8b9-45d0-b03d-7b53ae1603ae","year":2021},"citing_paper":{"arxiv_id":"2412.04307","last_updated":"2025-09-02T07:20:33Z","snapshot_observed_at":"2026-08-15T07:39:33.926647Z","submitted_at":"2024-12-05T16:26:37Z","title":"Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark","version":4},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-11T21:35:18.589149Z"},"links":{"citing_paper":"/paper/2412.04307"},"observation_digest":"sha256:4949cc5795b53000606348adc2ff755de2f19ae25652852de5f28e45a6f68397","observation_id":"0d586331-b01d-4fc1-993b-822478be20a3","resolution":{"observed_at":"2026-08-11T21:35:19.176219Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T21:35:19.153476Z","title":"Video coding for machines: Compact vi- sual representation compression for intelligent collaborative analytics","venue":null,"work_id":"f0ba8240-0dea-4bab-9522-7051041b511a","year":2024},"citing_paper":{"arxiv_id":"2412.04307","last_updated":"2025-09-02T07:20:33Z","snapshot_observed_at":"2026-08-15T07:39:33.926647Z","submitted_at":"2024-12-05T16:26:37Z","title":"Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark","version":4},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-11T21:35:18.593854Z"},"links":{"citing_paper":"/paper/2412.04307"},"observation_digest":"sha256:ca5a3958af0614d80513bf515017171b6afc7d44135120db615edc83ec7c277f","observation_id":"604c9c4f-433b-4b78-a078-e9c433f4f74a","resolution":{"observed_at":"2026-08-11T21:35:19.158452Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T21:35:19.134098Z","title":"Open- FedLLM: Training large language models on decentralized private data via federated learning","venue":null,"work_id":"9b3f1d3e-58b3-4081-bd7f-e08edc374e20","year":2024},"citing_paper":{"arxiv_id":"2412.04307","last_updated":"2025-09-02T07:20:33Z","snapshot_observed_at":"2026-08-15T07:39:33.926647Z","submitted_at":"2024-12-05T16:26:37Z","title":"Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark","version":4},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-11T21:35:18.598406Z"},"links":{"citing_paper":"/paper/2412.04307"},"observation_digest":"sha256:f8f3a23ef2c2a9dc00e4e06f8a17efb162431aeebc70ff919295b851b9400dd5","observation_id":"1e49bf37-9a9b-4688-a850-c5c51cfaca26","resolution":{"observed_at":"2026-08-11T21:35:19.141377Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2409.19660","last_updated":"2024-09-29T11:14:21Z","snapshot_observed_at":"2026-08-16T13:14:24.357788Z","submitted_at":"2024-09-29T11:14:21Z","title":"All-in-One Image Coding for Joint Human-Machine Vision with Multi-Path Aggregation","version":1},"cited_work":{"arxiv_id":"2409.19660","doi":null,"metadata_source":"pith","pith_arxiv_id":"2409.19660","snapshot_observed_at":"2026-08-11T21:35:18.672820Z","title":"All-in-One Image Coding for Joint Human-Machine Vision with Multi-Path Aggregation","venue":"cs.CV","work_id":"7ceca072-c856-4f98-80f3-d292d59514f1","year":2024},"citing_paper":{"arxiv_id":"2412.04307","last_updated":"2025-09-02T07:20:33Z","snapshot_observed_at":"2026-08-15T07:39:33.926647Z","submitted_at":"2024-12-05T16:26:37Z","title":"Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark","version":4},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-11T21:35:18.603045Z"},"links":{"cited_paper":"/paper/2409.19660","citing_paper":"/paper/2412.04307"},"observation_digest":"sha256:bf8ee241b38e7d285b787fb83fc6f696f0276aed81c1a53505ed7f93bf54e624","observation_id":"48f523cd-3651-4804-a8ab-3680459f06b7","resolution":{"observed_at":"2026-08-11T21:35:18.680184Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-11T21:35:19.116814Z","title":"MSFC: Deep feature compression in multi-task network","venue":null,"work_id":"d24c02cd-ae9e-427b-afcf-af91c88cde6f","year":2021},"citing_paper":{"arxiv_id":"2412.04307","last_updated":"2025-09-02T07:20:33Z","snapshot_observed_at":"2026-08-15T07:39:33.926647Z","submitted_at":"2024-12-05T16:26:37Z","title":"Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark","version":4},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-11T21:35:18.608088Z"},"links":{"citing_paper":"/paper/2412.04307"},"observation_digest":"sha256:09b9635721fcc1d0bbeacd344711fda3660fa0fe3547eb804c274d0f51efdef1","observation_id":"97cddd22-723c-4197-9dde-d43fcee2815b","resolution":{"observed_at":"2026-08-11T21:35:19.122631Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.14898","last_updated":"2024-12-22T08:16:28Z","snapshot_observed_at":"2026-08-16T13:40:51.352220Z","submitted_at":"2024-06-21T06:43:15Z","title":"Safely Learning with Private Data: A Federated Learning Framework for Large Language Model","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.14898","snapshot_observed_at":"2026-08-11T21:35:18.613716Z","title":"Safely learning with private data: A federated learning framework for large language model","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.04307","last_updated":"2025-09-02T07:20:33Z","snapshot_observed_at":"2026-08-15T07:39:33.926647Z","submitted_at":"2024-12-05T16:26:37Z","title":"Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark","version":4},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-11T21:35:18.613716Z"},"links":{"cited_paper":"/paper/2406.14898","citing_paper":"/paper/2412.04307"},"observation_digest":"sha256:0273e49d5f7ef5a66fa84c226798ffed3fc444907b51fe59246cea674466e2e6","observation_id":"d8a27910-f0f6-4e67-922e-a959fd8db579","resolution":{"observed_at":"2026-08-11T21:35:18.613716Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2412.04307","last_updated":"2025-09-02T07:20:33Z","latest_version":4,"primary_category":"cs.MM","snapshot_observed_at":"2026-08-15T07:39:33.926647Z","submitted_at":"2024-12-05T16:26:37Z","title":"Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark"},"reference_resolution":{"displayed":52,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":18,"verified_exact":1,"verified_fuzzy":33},"total_outbound_references":52},"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":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 52 of 52 outbound references and 4 inbound Pith citation observations for arXiv:2412.04307."}