{"as_of":"2026-08-12T10:01:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:21902c1b1e1d83755885b1e787b73679c26745ebd5294789eaa5a000f3338826","coverage":[{"denominator":35,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":35,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-21T16:03:52.814346Z","state":"measured"},{"denominator":36,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":36,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-12T06:34:41.77262+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":"2026-05-21T16:03:52.814346Z","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":"2026-05-21T16:04:14.623998Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2601.05639","last_updated":"2026-05-19T20:22:51Z","snapshot_observed_at":"2026-08-05T08:19:09.993989Z","submitted_at":"2026-01-09T08:50:38Z","title":"Efficient training for compact compression models via sequential distillation","version":2},"cited_work":{"arxiv_id":"2601.05639","doi":null,"metadata_source":"pith","pith_arxiv_id":"2601.05639","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Efficient training for compact compression models via sequential distillation","venue":"cs.CV","work_id":"ae92bc19-b768-42d9-845f-41175dcb32be","year":2026},"citing_paper":{"arxiv_id":"2601.05639","last_updated":"2026-05-19T20:22:51Z","snapshot_observed_at":"2026-08-05T08:19:09.993989Z","submitted_at":"2026-01-09T08:50:38Z","title":"Efficient training for compact compression models via sequential distillation","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-21T16:03:52.814346Z"},"links":{"cited_paper":"/paper/2601.05639","citing_paper":"/paper/2601.05639"},"observation_digest":"sha256:d3ab53e48cb303771215587935474b40911f0e05c5dc30b7c2f4dafcd00b3916","observation_id":"2757cc41-b6f0-4503-9ebe-16ba9d8a5a42","resolution":{"observed_at":"2026-05-21T16:04:14.625574Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2601.05639/citation-record","integrity":"/paper/2601.05639/integrity","json":"/paper/2601.05639/citation-record.json","paper":"/paper/2601.05639"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2601.05639","last_updated":"2026-05-19T20:22:51Z","snapshot_observed_at":"2026-08-05T08:19:09.993989Z","submitted_at":"2026-01-09T08:50:38Z","title":"Efficient training for compact compression models via sequential distillation","version":2},"cited_work":{"arxiv_id":"2601.05639","doi":null,"metadata_source":"pith","pith_arxiv_id":"2601.05639","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Efficient training for compact compression models via sequential distillation","venue":"cs.CV","work_id":"ae92bc19-b768-42d9-845f-41175dcb32be","year":2026},"citing_paper":{"arxiv_id":"2601.05639","last_updated":"2026-05-19T20:22:51Z","snapshot_observed_at":"2026-08-05T08:19:09.993989Z","submitted_at":"2026-01-09T08:50:38Z","title":"Efficient training for compact compression models via sequential distillation","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-21T16:03:52.814346Z"},"links":{"cited_paper":"/paper/2601.05639","citing_paper":"/paper/2601.05639"},"observation_digest":"sha256:d3ab53e48cb303771215587935474b40911f0e05c5dc30b7c2f4dafcd00b3916","observation_id":"2757cc41-b6f0-4503-9ebe-16ba9d8a5a42","resolution":{"observed_at":"2026-05-21T16:04:14.625574Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-06-05T21:23:00.469572Z","title":"To support deployment on hardware-constrained devices, we adopt a reduction strategy with lower computa- tional cost in training time and dataset size","venue":null,"work_id":"149b4996-e5db-4955-993a-0be8ac1fe6df","year":null},"citing_paper":{"arxiv_id":"2601.05639","last_updated":"2026-05-19T20:22:51Z","snapshot_observed_at":"2026-08-05T08:19:09.993989Z","submitted_at":"2026-01-09T08:50:38Z","title":"Efficient training for compact compression models via sequential distillation","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-21T16:03:52.814346Z"},"links":{"citing_paper":"/paper/2601.05639"},"observation_digest":"sha256:c254f53d6dbd3ee128013102f1560d655491a467a0de6a12c199d50c7a185e55","observation_id":"4b607579-f778-4e6b-998c-3e306d247ab8","resolution":{"observed_at":"2026-05-21T16:04:14.788032Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-06-05T21:23:00.469572Z","title":"For both architectures, gS s (·) = gT s (·) and EB S (·) = EB T (·), and in the Hyperprior case also hS s (·) = hT s (·)","venue":null,"work_id":"39194a85-8499-4b70-b972-5bbf047dedb7","year":null},"citing_paper":{"arxiv_id":"2601.05639","last_updated":"2026-05-19T20:22:51Z","snapshot_observed_at":"2026-08-05T08:19:09.993989Z","submitted_at":"2026-01-09T08:50:38Z","title":"Efficient training for compact compression models via sequential distillation","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-21T16:03:52.814346Z"},"links":{"citing_paper":"/paper/2601.05639"},"observation_digest":"sha256:cd946f594f230c39e0da436d52c8e980f77c9363776a3a7dce50b202086b76c2","observation_id":"05d4b147-cca7-42bc-8064-eca1c0bc7a52","resolution":{"observed_at":"2026-05-21T16:04:14.783386Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-06-05T21:23:00.469572Z","title":"Under hardware con- straints, storage and training time are challenges","venue":null,"work_id":"cef8b7b7-c321-4d94-9037-f565ff189f67","year":null},"citing_paper":{"arxiv_id":"2601.05639","last_updated":"2026-05-19T20:22:51Z","snapshot_observed_at":"2026-08-05T08:19:09.993989Z","submitted_at":"2026-01-09T08:50:38Z","title":"Efficient training for compact compression models via sequential distillation","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-21T16:03:52.814346Z"},"links":{"citing_paper":"/paper/2601.05639"},"observation_digest":"sha256:48756f1458f56994cf2a5c7ff21632598b4d5daebd9ba756f460d2b87afbac98","observation_id":"79ab4985-4860-431e-864b-05d7d5ebc8ab","resolution":{"observed_at":"2026-05-21T16:04:14.801024Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-06-05T21:23:00.469572Z","title":"This approach decreases training time, addressing a constraint in resource-limited environments","venue":null,"work_id":"a4a5f246-1292-4b58-b9cb-38f3a7f10067","year":null},"citing_paper":{"arxiv_id":"2601.05639","last_updated":"2026-05-19T20:22:51Z","snapshot_observed_at":"2026-08-05T08:19:09.993989Z","submitted_at":"2026-01-09T08:50:38Z","title":"Efficient training for compact compression models via sequential distillation","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-21T16:03:52.814346Z"},"links":{"citing_paper":"/paper/2601.05639"},"observation_digest":"sha256:d82c838b1ea5de320cc023f5c4d126cd4112ee3831df22876e780c5a73e4656e","observation_id":"5e9b03d0-4c05-42ac-8434-560f78c13f48","resolution":{"observed_at":"2026-05-21T16:04:14.794849Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"5c801932-ce0b-4972-b964-c8738306642c","year":null},"citing_paper":{"arxiv_id":"2601.05639","last_updated":"2026-05-19T20:22:51Z","snapshot_observed_at":"2026-08-05T08:19:09.993989Z","submitted_at":"2026-01-09T08:50:38Z","title":"Efficient training for compact compression models via sequential distillation","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-21T16:03:52.814346Z"},"links":{"citing_paper":"/paper/2601.05639"},"observation_digest":"sha256:a6ea0238ea7e6c197c3f1740199fb4135903d56f7a714a9df1b57fd08d9611a4","observation_id":"f60f9f15-ec19-4c1e-abe9-72d37cbc4936","resolution":{"observed_at":"2026-05-21T16:04:14.792306Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2648.4540","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"47171fc0-7c69-4071-a346-71de5bc15d0f","year":1924},"citing_paper":{"arxiv_id":"2601.05639","last_updated":"2026-05-19T20:22:51Z","snapshot_observed_at":"2026-08-05T08:19:09.993989Z","submitted_at":"2026-01-09T08:50:38Z","title":"Efficient training for compact compression models via sequential distillation","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-21T16:03:52.814346Z"},"links":{"citing_paper":"/paper/2601.05639"},"observation_digest":"sha256:a88bd3648be27b2f870e71365d46d39c961074a7ebeb7ac763b6a47cbccb2ed4","observation_id":"7731ae0c-4c40-40ee-8d51-d771f8d7322c","resolution":{"observed_at":"2026-05-21T16:04:14.629954Z","resolver_source":"arxiv_id","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"0c69ea84-b128-43da-91d8-a69e37ff25d9","year":null},"citing_paper":{"arxiv_id":"2601.05639","last_updated":"2026-05-19T20:22:51Z","snapshot_observed_at":"2026-08-05T08:19:09.993989Z","submitted_at":"2026-01-09T08:50:38Z","title":"Efficient training for compact compression models via sequential distillation","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-21T16:03:52.814346Z"},"links":{"citing_paper":"/paper/2601.05639"},"observation_digest":"sha256:0cabdb6d68f53dc2187fa5a5ff779bc65e6cf901a7cb667fdc0ae06689a37a71","observation_id":"a339fa99-9933-4d27-aa45-b847271d36e3","resolution":{"observed_at":"2026-05-21T16:04:14.797136Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-06-05T21:23:00.469572Z","title":"The jpeg still picture compression standard","venue":null,"work_id":"4c5acbca-baba-48ac-95ba-8b54f0aa4da4","year":1992},"citing_paper":{"arxiv_id":"2601.05639","last_updated":"2026-05-19T20:22:51Z","snapshot_observed_at":"2026-08-05T08:19:09.993989Z","submitted_at":"2026-01-09T08:50:38Z","title":"Efficient training for compact compression models via sequential distillation","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-21T16:03:52.814346Z"},"links":{"citing_paper":"/paper/2601.05639"},"observation_digest":"sha256:94808fd46bb4edbb4dc2a1640ef642b7345584b34b46595fbf90f89c62437b9f","observation_id":"0a92bf14-5eaf-4778-b0be-88933592f6b2","resolution":{"observed_at":"2026-05-21T16:04:14.785401Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-06-05T21:23:00.469572Z","title":"Intra coding of the hevc standard","venue":null,"work_id":"92a76ce6-6dc8-4299-895e-dac5092e60fa","year":2012},"citing_paper":{"arxiv_id":"2601.05639","last_updated":"2026-05-19T20:22:51Z","snapshot_observed_at":"2026-08-05T08:19:09.993989Z","submitted_at":"2026-01-09T08:50:38Z","title":"Efficient training for compact compression models via sequential distillation","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-21T16:03:52.814346Z"},"links":{"citing_paper":"/paper/2601.05639"},"observation_digest":"sha256:95843f6af036cac758eae5e5902d92d151b9171fc2dcdff856b263ea1fce1e3a","observation_id":"36f54faf-039e-4b16-ab7d-dc64b6dbb3c7","resolution":{"observed_at":"2026-05-21T16:04:14.798992Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-06-05T21:23:00.469572Z","title":"Intra prediction and mode cod- ing in vvc","venue":null,"work_id":"e4e34aed-d391-4616-9c4a-c276c1e00861","year":2021},"citing_paper":{"arxiv_id":"2601.05639","last_updated":"2026-05-19T20:22:51Z","snapshot_observed_at":"2026-08-05T08:19:09.993989Z","submitted_at":"2026-01-09T08:50:38Z","title":"Efficient training for compact compression models via sequential distillation","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-21T16:03:52.814346Z"},"links":{"citing_paper":"/paper/2601.05639"},"observation_digest":"sha256:566eac6ad3d2e1e31ed7bcc989569c020462ff82aae16e5e777e62a30fe1cb8a","observation_id":"c6c46a39-fe74-4bc4-b675-fc6d96364307","resolution":{"observed_at":"2026-05-21T16:04:14.758886Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-06-05T21:23:00.469572Z","title":"An introduc- tion to neural data compression","venue":null,"work_id":"2f8898bb-0c53-4349-b002-7ecd619b16a1","year":2023},"citing_paper":{"arxiv_id":"2601.05639","last_updated":"2026-05-19T20:22:51Z","snapshot_observed_at":"2026-08-05T08:19:09.993989Z","submitted_at":"2026-01-09T08:50:38Z","title":"Efficient training for compact compression models via sequential distillation","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-21T16:03:52.814346Z"},"links":{"citing_paper":"/paper/2601.05639"},"observation_digest":"sha256:01bcda03b3ee7e434993ff1a835bc2cfb666c424514173c451f3f40d90644c45","observation_id":"1fa48b63-aa50-4c28-ac1f-9add7022491a","resolution":{"observed_at":"2026-05-21T16:04:14.756725Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-06-05T21:23:00.469572Z","title":"End- to-end optimization of nonlinear transform codes for percep- tual quality","venue":null,"work_id":"de604944-5c6f-4e36-9187-326e9a4271b5","year":2016},"citing_paper":{"arxiv_id":"2601.05639","last_updated":"2026-05-19T20:22:51Z","snapshot_observed_at":"2026-08-05T08:19:09.993989Z","submitted_at":"2026-01-09T08:50:38Z","title":"Efficient training for compact compression models via sequential distillation","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-21T16:03:52.814346Z"},"links":{"citing_paper":"/paper/2601.05639"},"observation_digest":"sha256:6ed0031477381c8bf197cdc8085e58c9863b3f54a4fc1b0f180f0f55f7ee2831","observation_id":"dfdb4c3c-7de2-4bbe-97c8-5925436f99cc","resolution":{"observed_at":"2026-05-21T16:04:14.772344Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-06-05T21:23:00.469572Z","title":"End- to-end optimized image compression","venue":null,"work_id":"7a6b9e5d-c73d-4a92-9508-71bb89064831","year":2017},"citing_paper":{"arxiv_id":"2601.05639","last_updated":"2026-05-19T20:22:51Z","snapshot_observed_at":"2026-08-05T08:19:09.993989Z","submitted_at":"2026-01-09T08:50:38Z","title":"Efficient training for compact compression models via sequential distillation","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-21T16:03:52.814346Z"},"links":{"citing_paper":"/paper/2601.05639"},"observation_digest":"sha256:745812ac0e010c714ce5b878517d22a21e9253b02fa3fd096a633953c3d9ba68","observation_id":"dcb5c6cb-28b3-4a0f-95a2-8ec25ef80a11","resolution":{"observed_at":"2026-05-21T16:04:14.741846Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-06-05T21:23:00.469572Z","title":"Variational image compression with a scale hyperprior","venue":null,"work_id":"948f4120-1ace-4fb5-9d8c-77ffd51864a8","year":2018},"citing_paper":{"arxiv_id":"2601.05639","last_updated":"2026-05-19T20:22:51Z","snapshot_observed_at":"2026-08-05T08:19:09.993989Z","submitted_at":"2026-01-09T08:50:38Z","title":"Efficient training for compact compression models via sequential distillation","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-21T16:03:52.814346Z"},"links":{"citing_paper":"/paper/2601.05639"},"observation_digest":"sha256:3d69621678824b959c6bec52f616b39409c7fbedeb6328fc4d0d94212c79ff1e","observation_id":"adbaecd7-a112-4d3e-9c80-920e0639b345","resolution":{"observed_at":"2026-05-21T16:04:14.745986Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-06-05T21:23:00.469572Z","title":"Computationally-efficient neural image compression with shallow decoders","venue":null,"work_id":"a97fea9d-33ce-4980-b80b-1ebdaef44a54","year":2023},"citing_paper":{"arxiv_id":"2601.05639","last_updated":"2026-05-19T20:22:51Z","snapshot_observed_at":"2026-08-05T08:19:09.993989Z","submitted_at":"2026-01-09T08:50:38Z","title":"Efficient training for compact compression models via sequential distillation","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-05-21T16:03:52.814346Z"},"links":{"citing_paper":"/paper/2601.05639"},"observation_digest":"sha256:cf4aa9af7b41b709a0aff0868dd08a43f9a5fbeee0eadd73c691f9992fc3dff5","observation_id":"b33ef6ba-b3a2-4984-9f25-fe4f73639d90","resolution":{"observed_at":"2026-05-21T16:04:14.776698Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2411.19442","last_updated":"2024-11-29T03:00:21Z","snapshot_observed_at":"2026-08-03T22:08:12.503113Z","submitted_at":"2024-11-29T03:00:21Z","title":"MCUCoder: Adaptive Bitrate Learned Video Compression for IoT Devices","version":1},"cited_work":{"arxiv_id":"2411.19442","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2411.19442","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Mcucoder: Adaptive bitrate learned video compression for iot devices","venue":null,"work_id":"75adec8d-3bac-47ac-a460-1688bebb1c46","year":2024},"citing_paper":{"arxiv_id":"2601.05639","last_updated":"2026-05-19T20:22:51Z","snapshot_observed_at":"2026-08-05T08:19:09.993989Z","submitted_at":"2026-01-09T08:50:38Z","title":"Efficient training for compact compression models via sequential distillation","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-05-21T16:03:52.814346Z"},"links":{"cited_paper":"/paper/2411.19442","citing_paper":"/paper/2601.05639"},"observation_digest":"sha256:4272dfec5a93f55a6c848fb8cb7400e7c0bf5a96186be566dd90bcd3edf34c90","observation_id":"ac5a335b-28de-493a-a2a8-5d4e574a3fec","resolution":{"observed_at":"2026-05-21T16:04:14.618873Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-06-05T21:23:00.469572Z","title":"Asymmetric autoencoders: An nn alternative for resource- constrained devices in iot networks","venue":null,"work_id":"e05577f0-525e-4c33-a3ac-af488e573ac6","year":2024},"citing_paper":{"arxiv_id":"2601.05639","last_updated":"2026-05-19T20:22:51Z","snapshot_observed_at":"2026-08-05T08:19:09.993989Z","submitted_at":"2026-01-09T08:50:38Z","title":"Efficient training for compact compression models via sequential distillation","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-21T16:03:52.814346Z"},"links":{"citing_paper":"/paper/2601.05639"},"observation_digest":"sha256:488e7629d444887cea57739cf8ef6da0caf9c89a85b4e2b952e86de9dfc56c07","observation_id":"e4e9b353-99de-455a-80c7-067419e9b5ed","resolution":{"observed_at":"2026-05-21T16:04:14.739715Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-06-05T21:23:00.469572Z","title":"Block modulating video compression: An ultra low complex- ity image compression encoder for resource limited platforms","venue":null,"work_id":"710061c3-b440-45a3-95bb-0b79715f51ed","year":2024},"citing_paper":{"arxiv_id":"2601.05639","last_updated":"2026-05-19T20:22:51Z","snapshot_observed_at":"2026-08-05T08:19:09.993989Z","submitted_at":"2026-01-09T08:50:38Z","title":"Efficient training for compact compression models via sequential distillation","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-05-21T16:03:52.814346Z"},"links":{"citing_paper":"/paper/2601.05639"},"observation_digest":"sha256:cf923be1bc2d2222fac00bc39119a7e99e87a4f16cb2865d446d693d09334a6b","observation_id":"2776b7eb-9247-4457-b229-1be7fab04649","resolution":{"observed_at":"2026-05-21T16:04:14.750365Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-06-05T21:23:00.469572Z","title":"Toward edge-based deep learning in industrial in- ternet of things","venue":null,"work_id":"790559f5-8e76-4d01-a792-05199a970dfc","year":2020},"citing_paper":{"arxiv_id":"2601.05639","last_updated":"2026-05-19T20:22:51Z","snapshot_observed_at":"2026-08-05T08:19:09.993989Z","submitted_at":"2026-01-09T08:50:38Z","title":"Efficient training for compact compression models via sequential distillation","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-05-21T16:03:52.814346Z"},"links":{"citing_paper":"/paper/2601.05639"},"observation_digest":"sha256:83146c17635ee6da59b4bf5d5fb41688c41485e13a472abcb45710a49ed16723","observation_id":"5f1d7ae2-ad19-4d25-b952-e17f7bd89f13","resolution":{"observed_at":"2026-05-21T16:04:14.778625Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-06-05T21:23:00.469572Z","title":"The lottery ticket hy- pothesis: Finding sparse, trainable neural networks","venue":null,"work_id":"90375243-83ec-40a1-81de-f5d8e8989b43","year":2019},"citing_paper":{"arxiv_id":"2601.05639","last_updated":"2026-05-19T20:22:51Z","snapshot_observed_at":"2026-08-05T08:19:09.993989Z","submitted_at":"2026-01-09T08:50:38Z","title":"Efficient training for compact compression models via sequential distillation","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-05-21T16:03:52.814346Z"},"links":{"citing_paper":"/paper/2601.05639"},"observation_digest":"sha256:78e6579cebfd754b2ae122e2fa8156c92d151fb1afc2545c36298c219b59533b","observation_id":"5b62a75d-d6fc-402c-99e9-b387974924df","resolution":{"observed_at":"2026-05-21T16:04:14.754293Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-06-05T21:23:00.469572Z","title":"An improved upper bound on the rate-distortion function of images","venue":null,"work_id":"ee7738b6-9f7d-4004-b277-1402300608c8","year":2023},"citing_paper":{"arxiv_id":"2601.05639","last_updated":"2026-05-19T20:22:51Z","snapshot_observed_at":"2026-08-05T08:19:09.993989Z","submitted_at":"2026-01-09T08:50:38Z","title":"Efficient training for compact compression models via sequential distillation","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-05-21T16:03:52.814346Z"},"links":{"citing_paper":"/paper/2601.05639"},"observation_digest":"sha256:47fa3c0f9e8987b6faf93e0cd2dbff1f6c8bf6a03ac7c905a6207d499f4c24c6","observation_id":"1632d2e0-048f-4df2-9255-c7c848fcadd6","resolution":{"observed_at":"2026-05-21T16:04:14.770368Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1503.02531","last_updated":"2015-03-09T15:44:49Z","snapshot_observed_at":"2026-07-06T04:11:24.157003Z","submitted_at":"2015-03-09T15:44:49Z","title":"Distilling the Knowledge in a Neural Network","version":1},"cited_work":{"arxiv_id":"1503.02531","doi":"10.1109/cvpr52733.2024.01515","metadata_source":"pith","pith_arxiv_id":"1503.02531","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Distilling the Knowledge in a Neural Network","venue":"stat.ML","work_id":"d927ab1f-17b8-4002-9d09-c3d55764fbad","year":2015},"citing_paper":{"arxiv_id":"2601.05639","last_updated":"2026-05-19T20:22:51Z","snapshot_observed_at":"2026-08-05T08:19:09.993989Z","submitted_at":"2026-01-09T08:50:38Z","title":"Efficient training for compact compression models via sequential distillation","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-05-21T16:03:52.814346Z"},"links":{"cited_paper":"/paper/1503.02531","citing_paper":"/paper/2601.05639"},"observation_digest":"sha256:8d9ef3a3590e3c03b1bcb07d4acd2db7f743b3a555d125bb2210ebce0bff4ac7","observation_id":"4213f936-4356-41e1-b599-2eccc3f600d1","resolution":{"observed_at":"2026-05-21T16:04:14.622347Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-06-05T21:23:00.469572Z","title":"Sar im- age compression with inherent denoising capability through knowledge distillation","venue":null,"work_id":"af200856-5152-4e18-afe7-3fd216ba4cbc","year":2024},"citing_paper":{"arxiv_id":"2601.05639","last_updated":"2026-05-19T20:22:51Z","snapshot_observed_at":"2026-08-05T08:19:09.993989Z","submitted_at":"2026-01-09T08:50:38Z","title":"Efficient training for compact compression models via sequential distillation","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-05-21T16:03:52.814346Z"},"links":{"citing_paper":"/paper/2601.05639"},"observation_digest":"sha256:06ca892bb48149501e5b69d9f72504035b460eba04394adf37eb35365c1083dc","observation_id":"c2240618-261b-41b9-926b-d3b87e242d2f","resolution":{"observed_at":"2026-05-21T16:04:14.764792Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-06-05T21:23:00.469572Z","title":"Learning-driven lossy image compression: A compre- hensive survey","venue":null,"work_id":"b97ecf28-fd39-48bf-8306-5c380744fb13","year":2023},"citing_paper":{"arxiv_id":"2601.05639","last_updated":"2026-05-19T20:22:51Z","snapshot_observed_at":"2026-08-05T08:19:09.993989Z","submitted_at":"2026-01-09T08:50:38Z","title":"Efficient training for compact compression models via sequential distillation","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-05-21T16:03:52.814346Z"},"links":{"citing_paper":"/paper/2601.05639"},"observation_digest":"sha256:34df3c4b61c0f6964dff1f7a7b9f8ec719b21297d1c68c86b7819e613ab40e39","observation_id":"62272624-e589-4719-9b66-0b6584965b14","resolution":{"observed_at":"2026-05-21T16:04:14.790046Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-06-05T21:23:00.469572Z","title":"Fitnets: Hints for thin deep nets","venue":null,"work_id":"fdc56de1-81d7-415c-a9e3-139fb6a5b958","year":2015},"citing_paper":{"arxiv_id":"2601.05639","last_updated":"2026-05-19T20:22:51Z","snapshot_observed_at":"2026-08-05T08:19:09.993989Z","submitted_at":"2026-01-09T08:50:38Z","title":"Efficient training for compact compression models via sequential distillation","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-05-21T16:03:52.814346Z"},"links":{"citing_paper":"/paper/2601.05639"},"observation_digest":"sha256:da757d6c9edd3ac25215153b6f1270dde19a1a07c5a79a8094ae54ef27385cb0","observation_id":"620c53af-2fc3-4e74-a367-5055b5a1a9ba","resolution":{"observed_at":"2026-05-21T16:04:14.762794Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-06-05T21:23:00.469572Z","title":"Improving statistical fi- delity for neural image compression with implicit local like- lihood models","venue":null,"work_id":"9fe5aeef-7928-4203-9786-cd850a447422","year":2023},"citing_paper":{"arxiv_id":"2601.05639","last_updated":"2026-05-19T20:22:51Z","snapshot_observed_at":"2026-08-05T08:19:09.993989Z","submitted_at":"2026-01-09T08:50:38Z","title":"Efficient training for compact compression models via sequential distillation","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-05-21T16:03:52.814346Z"},"links":{"citing_paper":"/paper/2601.05639"},"observation_digest":"sha256:16fc28d80b150a40b40ae3357c916a8e39dc31b8711475cf12538be41700f0fd","observation_id":"dba12c19-583d-4070-8d7f-64d4597ffe55","resolution":{"observed_at":"2026-05-21T16:04:14.743787Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-06-05T21:23:00.469572Z","title":"High-fidelity generative image compres- sion","venue":null,"work_id":"5b2230a2-afbe-489d-8454-8a79a30de406","year":2020},"citing_paper":{"arxiv_id":"2601.05639","last_updated":"2026-05-19T20:22:51Z","snapshot_observed_at":"2026-08-05T08:19:09.993989Z","submitted_at":"2026-01-09T08:50:38Z","title":"Efficient training for compact compression models via sequential distillation","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-05-21T16:03:52.814346Z"},"links":{"citing_paper":"/paper/2601.05639"},"observation_digest":"sha256:c00832a323dc68da9e827c2e152470ff10ce7bf04c88eaa0772a0b3b1da280ee","observation_id":"659a7454-f586-4a00-b583-d33278e6b462","resolution":{"observed_at":"2026-05-21T16:04:14.766563Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2011.03029","last_updated":"2020-11-05T18:40:50Z","snapshot_observed_at":"2026-08-10T03:37:02.318287Z","submitted_at":"2020-11-05T18:40:50Z","title":"CompressAI: a PyTorch library and evaluation platform for end-to-end compression research","version":1},"cited_work":{"arxiv_id":"2011.03029","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2011.03029","snapshot_observed_at":"2026-07-04T07:29:38.439715Z","title":"CompressAI: a pytorch libra ry and evaluation platform for end -to-end compression research","venue":null,"work_id":"8fda31f2-b319-4214-81c8-a9bd2fcb60c4","year":2011},"citing_paper":{"arxiv_id":"2601.05639","last_updated":"2026-05-19T20:22:51Z","snapshot_observed_at":"2026-08-05T08:19:09.993989Z","submitted_at":"2026-01-09T08:50:38Z","title":"Efficient training for compact compression models via sequential distillation","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-05-21T16:03:52.814346Z"},"links":{"cited_paper":"/paper/2011.03029","citing_paper":"/paper/2601.05639"},"observation_digest":"sha256:5216913e67baf46c3d9b375a82f32431c88bb56518c6ad2ca29baa2f16dc2a8b","observation_id":"7254636d-b937-4845-adf7-5ca5b33492dc","resolution":{"observed_at":"2026-05-21T16:04:14.615656Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-06-05T21:23:00.469572Z","title":"Neuralcompres- sion","venue":null,"work_id":"62673fff-a031-4432-9299-98f892b4095f","year":2021},"citing_paper":{"arxiv_id":"2601.05639","last_updated":"2026-05-19T20:22:51Z","snapshot_observed_at":"2026-08-05T08:19:09.993989Z","submitted_at":"2026-01-09T08:50:38Z","title":"Efficient training for compact compression models via sequential distillation","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-05-21T16:03:52.814346Z"},"links":{"citing_paper":"/paper/2601.05639"},"observation_digest":"sha256:6c3ed2ea50f4846ac926d2b863d3ff28a21ea33a088be32ce2728efe4f971a18","observation_id":"18779d0b-9d9f-42eb-a178-fd92b22ace4a","resolution":{"observed_at":"2026-05-21T16:04:14.774377Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-06-05T21:23:00.469572Z","title":"vimeo 90k 7","venue":null,"work_id":"09c829d0-9402-4bf2-9250-20018c5243bd","year":2022},"citing_paper":{"arxiv_id":"2601.05639","last_updated":"2026-05-19T20:22:51Z","snapshot_observed_at":"2026-08-05T08:19:09.993989Z","submitted_at":"2026-01-09T08:50:38Z","title":"Efficient training for compact compression models via sequential distillation","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-05-21T16:03:52.814346Z"},"links":{"citing_paper":"/paper/2601.05639"},"observation_digest":"sha256:2005483697b676daae919a0ffa894b6c2132b0b05c7c96e1f29953824d9990e0","observation_id":"2ebe613d-8dd4-4823-8a19-5e48c35c4135","resolution":{"observed_at":"2026-05-21T16:04:14.780679Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-06-05T21:23:00.469572Z","title":"Kodak lossless true color image suite","venue":null,"work_id":"257e864c-d46b-4050-9afa-de67ea55034b","year":1999},"citing_paper":{"arxiv_id":"2601.05639","last_updated":"2026-05-19T20:22:51Z","snapshot_observed_at":"2026-08-05T08:19:09.993989Z","submitted_at":"2026-01-09T08:50:38Z","title":"Efficient training for compact compression models via sequential distillation","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-05-21T16:03:52.814346Z"},"links":{"citing_paper":"/paper/2601.05639"},"observation_digest":"sha256:0f237f64fd5e6d068cd71c603aec0ab4ee01ddb40a05837d16de51692bf42c84","observation_id":"1f88d4e3-9eb4-482a-88aa-811f165e7439","resolution":{"observed_at":"2026-05-21T16:04:14.768561Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-06-05T21:23:00.469572Z","title":"Clic 2020: Challenge on learned image compression","venue":null,"work_id":"795240ef-05db-47ae-b361-9b6d44e5df4f","year":2020},"citing_paper":{"arxiv_id":"2601.05639","last_updated":"2026-05-19T20:22:51Z","snapshot_observed_at":"2026-08-05T08:19:09.993989Z","submitted_at":"2026-01-09T08:50:38Z","title":"Efficient training for compact compression models via sequential distillation","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-05-21T16:03:52.814346Z"},"links":{"citing_paper":"/paper/2601.05639"},"observation_digest":"sha256:8285d02e1bb4faa68a7d4e4b74e7a97fa34bdea26467ccd51ed2020b9ba19a76","observation_id":"33aea56c-abf5-4666-af3a-c9acddbd677b","resolution":{"observed_at":"2026-05-21T16:04:14.748270Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-06-05T21:23:00.469572Z","title":"Video enhancement with task-oriented flow","venue":null,"work_id":"dad59f7e-8dc7-4616-af45-ae3d8025eebb","year":2019},"citing_paper":{"arxiv_id":"2601.05639","last_updated":"2026-05-19T20:22:51Z","snapshot_observed_at":"2026-08-05T08:19:09.993989Z","submitted_at":"2026-01-09T08:50:38Z","title":"Efficient training for compact compression models via sequential distillation","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-05-21T16:03:52.814346Z"},"links":{"citing_paper":"/paper/2601.05639"},"observation_digest":"sha256:eb04731a0acdff44a4361ce3ce9189acc7084f366b5b66a31717b172fdb9bb69","observation_id":"6a53f2cb-f769-47f0-919d-d0c310a7a696","resolution":{"observed_at":"2026-05-21T16:04:14.760870Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-06-05T21:23:00.469572Z","title":"The open images dataset v4","venue":null,"work_id":"663a251b-d57d-4348-8431-6be0167c0b75","year":1956},"citing_paper":{"arxiv_id":"2601.05639","last_updated":"2026-05-19T20:22:51Z","snapshot_observed_at":"2026-08-05T08:19:09.993989Z","submitted_at":"2026-01-09T08:50:38Z","title":"Efficient training for compact compression models via sequential distillation","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-05-21T16:03:52.814346Z"},"links":{"citing_paper":"/paper/2601.05639"},"observation_digest":"sha256:0c24ab616f96a5df23cf9334595f4d5cc3aa8266aa05c8c138f4dba053320774","observation_id":"107022f8-3f89-40ef-b343-848b53061e21","resolution":{"observed_at":"2026-05-21T16:04:14.752295Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2601.05639","last_updated":"2026-05-19T20:22:51Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-05T08:19:09.993989Z","submitted_at":"2026-01-09T08:50:38Z","title":"Efficient training for compact compression models via sequential distillation"},"reference_resolution":{"displayed":35,"state_counts":{"malformed_identifier":1,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":2,"verified_exact":3,"verified_fuzzy":28},"total_outbound_references":35},"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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 35 of 35 outbound references and 1 inbound Pith citation observation for arXiv:2601.05639."}