{"as_of":"2026-08-16T16:53:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:10aec84937972104a776897817d5c617c2caa9be316641623230334ebedc3352","coverage":[{"denominator":43,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":43,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T19:32:44.358848Z","state":"measured"},{"denominator":43,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":43,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-16T06:30:59.297886+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2412.06875/citation-record","integrity":"/paper/2412.06875/integrity","json":"/paper/2412.06875/citation-record.json","paper":"/paper/2412.06875"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T19:32:44.840144Z","title":"Metaquant: Learning to quantize by learning to penetrate non-differentiable quantization","venue":null,"work_id":"cca1a18a-fda6-4dd0-9f0d-402cdebfb684","year":2019},"citing_paper":{"arxiv_id":"2412.06875","last_updated":"2024-12-09T16:17:22Z","snapshot_observed_at":"2026-08-16T10:16:47.085316Z","submitted_at":"2024-12-09T16:17:22Z","title":"VQ4ALL: Efficient Neural Network Representation via a Universal Codebook","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-11T19:32:44.199114Z"},"links":{"citing_paper":"/paper/2412.06875"},"observation_digest":"sha256:25b849255a17bbfd5faa608d0eb64ad43d2e48bea2c6325f4be5a84046ae66b3","observation_id":"947eccc3-b64a-4b40-8711-1acd7ee3e520","resolution":{"observed_at":"2026-08-11T19:32:44.844044Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2108.12659","last_updated":"2022-02-20T16:47:22Z","snapshot_observed_at":"2026-08-16T11:30:06.861135Z","submitted_at":"2021-08-28T14:35:41Z","title":"DKM: Differentiable K-Means Clustering Layer for Neural Network Compression","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.12659","snapshot_observed_at":"2026-08-11T19:32:44.203028Z","title":"Dkm: Differentiable k-means cluster- ing layer for neural network compression","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.06875","last_updated":"2024-12-09T16:17:22Z","snapshot_observed_at":"2026-08-16T10:16:47.085316Z","submitted_at":"2024-12-09T16:17:22Z","title":"VQ4ALL: Efficient Neural Network Representation via a Universal Codebook","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-11T19:32:44.203028Z"},"links":{"cited_paper":"/paper/2108.12659","citing_paper":"/paper/2412.06875"},"observation_digest":"sha256:281711129c00c251031d645e718226728c69db2ddb565effa4d395e2dec4ee97","observation_id":"5ece04c2-c9f9-4e66-84a8-c3498454a5c8","resolution":{"observed_at":"2026-08-11T19:32:44.203028Z","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":"2026-08-11T19:32:44.206644Z","title":"Imagenet: A large-scale hierarchical image database","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2412.06875","last_updated":"2024-12-09T16:17:22Z","snapshot_observed_at":"2026-08-16T10:16:47.085316Z","submitted_at":"2024-12-09T16:17:22Z","title":"VQ4ALL: Efficient Neural Network Representation via a Universal Codebook","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-11T19:32:44.206644Z"},"links":{"citing_paper":"/paper/2412.06875"},"observation_digest":"sha256:a9067ace02fc379a20bc3d87a3dd80d9cc7b1ba7ff536740e814480f7fa3f476","observation_id":"3e5adb19-976d-4e9f-aaa7-43811b0da268","resolution":{"observed_at":"2026-08-11T19:32:44.206644Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.17131","last_updated":"2024-08-30T09:15:54Z","snapshot_observed_at":"2026-08-16T13:22:41.971390Z","submitted_at":"2024-08-30T09:15:54Z","title":"VQ4DiT: Efficient Post-Training Vector Quantization for Diffusion Transformers","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.17131","snapshot_observed_at":"2026-08-11T19:32:44.210234Z","title":"Vq4dit: Efficient post-training vec- tor quantization for diffusion transformers","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.06875","last_updated":"2024-12-09T16:17:22Z","snapshot_observed_at":"2026-08-16T10:16:47.085316Z","submitted_at":"2024-12-09T16:17:22Z","title":"VQ4ALL: Efficient Neural Network Representation via a Universal Codebook","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-11T19:32:44.210234Z"},"links":{"cited_paper":"/paper/2408.17131","citing_paper":"/paper/2412.06875"},"observation_digest":"sha256:b3f19bf916f2ca6f3b887757c0177eaff906d98b9ce94f76d7f6d98888bcd5b4","observation_id":"7ffc83a7-313b-4f01-9841-e2bdc6c53a12","resolution":{"observed_at":"2026-08-11T19:32:44.210234Z","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":"2026-08-11T19:32:44.822639Z","title":"Hawq-v2: Hessian aware trace-weighted quantization of neural networks","venue":null,"work_id":"8a69979d-ee4c-4616-8429-e451f8a8881a","year":2020},"citing_paper":{"arxiv_id":"2412.06875","last_updated":"2024-12-09T16:17:22Z","snapshot_observed_at":"2026-08-16T10:16:47.085316Z","submitted_at":"2024-12-09T16:17:22Z","title":"VQ4ALL: Efficient Neural Network Representation via a Universal Codebook","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-11T19:32:44.214284Z"},"links":{"citing_paper":"/paper/2412.06875"},"observation_digest":"sha256:162f5791ecb734c8793a0873b5c3fe512011814eb06cbf8210bcf8d992f39517","observation_id":"ff75e391-63f5-4fad-a1d6-0d5f20288dc6","resolution":{"observed_at":"2026-08-11T19:32:44.826502Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T19:32:44.811009Z","title":"Training with quantization noise for extreme model com- pression","venue":null,"work_id":"3d7631c0-71d9-4a63-aa2c-6783f5db4cbc","year":2021},"citing_paper":{"arxiv_id":"2412.06875","last_updated":"2024-12-09T16:17:22Z","snapshot_observed_at":"2026-08-16T10:16:47.085316Z","submitted_at":"2024-12-09T16:17:22Z","title":"VQ4ALL: Efficient Neural Network Representation via a Universal Codebook","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-11T19:32:44.218090Z"},"links":{"citing_paper":"/paper/2412.06875"},"observation_digest":"sha256:4e6f6ed0d5bf4087cbfae73acb4c2a8baa4e4ce9555f31a9ffaf4f904be99667","observation_id":"4a89bcf7-a78b-48bc-9f1a-3b0b7c8c1cd5","resolution":{"observed_at":"2026-08-11T19:32:44.815126Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T19:32:44.798474Z","title":"Deep neural network com- pression by in-parallel pruning-quantization","venue":null,"work_id":"ca5bd24f-e6ac-47d6-9522-d2d1c44a4f3f","year":2018},"citing_paper":{"arxiv_id":"2412.06875","last_updated":"2024-12-09T16:17:22Z","snapshot_observed_at":"2026-08-16T10:16:47.085316Z","submitted_at":"2024-12-09T16:17:22Z","title":"VQ4ALL: Efficient Neural Network Representation via a Universal Codebook","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-11T19:32:44.222081Z"},"links":{"citing_paper":"/paper/2412.06875"},"observation_digest":"sha256:1f498d90c6c09f12b9a0230829525902b35f77f71cc55c4caae47597d2a9d10d","observation_id":"d1c6958f-2951-40d0-b759-42759093d662","resolution":{"observed_at":"2026-08-11T19:32:44.803285Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6115","last_updated":"2014-12-18T21:09:01Z","snapshot_observed_at":"2026-08-14T23:06:53.533484Z","submitted_at":"2014-12-18T21:09:01Z","title":"Compressing Deep Convolutional Networks using Vector Quantization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6115","snapshot_observed_at":"2026-08-11T19:32:44.225592Z","title":"Compressing deep convolutional networks using vector quantization","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2412.06875","last_updated":"2024-12-09T16:17:22Z","snapshot_observed_at":"2026-08-16T10:16:47.085316Z","submitted_at":"2024-12-09T16:17:22Z","title":"VQ4ALL: Efficient Neural Network Representation via a Universal Codebook","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-11T19:32:44.225592Z"},"links":{"cited_paper":"/paper/1412.6115","citing_paper":"/paper/2412.06875"},"observation_digest":"sha256:3a14c666ba97e465bf82a99b08d47cf2f23a9a0cc926aace8af67f2fda77d474","observation_id":"b68703e9-4b60-44f7-9db6-ab341b9e95b4","resolution":{"observed_at":"2026-08-11T19:32:44.225592Z","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":"2026-08-11T19:32:44.786803Z","title":null,"venue":null,"work_id":"e0215ed6-4c84-4ce6-98e1-2aaf85013ef3","year":2016},"citing_paper":{"arxiv_id":"2412.06875","last_updated":"2024-12-09T16:17:22Z","snapshot_observed_at":"2026-08-16T10:16:47.085316Z","submitted_at":"2024-12-09T16:17:22Z","title":"VQ4ALL: Efficient Neural Network Representation via a Universal Codebook","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-11T19:32:44.229516Z"},"links":{"citing_paper":"/paper/2412.06875"},"observation_digest":"sha256:5703b5d12cb8ece07d31c2f6bcd1196170858426f21e23ee3e196446e30c1068","observation_id":"dab58ec3-f606-4aad-8abf-04104ed0c9d9","resolution":{"observed_at":"2026-08-11T19:32:44.790632Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T19:32:44.233568Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.06875","last_updated":"2024-12-09T16:17:22Z","snapshot_observed_at":"2026-08-16T10:16:47.085316Z","submitted_at":"2024-12-09T16:17:22Z","title":"VQ4ALL: Efficient Neural Network Representation via a Universal Codebook","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-11T19:32:44.233568Z"},"links":{"citing_paper":"/paper/2412.06875"},"observation_digest":"sha256:285425eabf07da1952cef23acb346c9a90d166a996797fbd62d681a356aab29d","observation_id":"7da2b822-67c8-4b58-bc72-30241fb23b2e","resolution":{"observed_at":"2026-08-11T19:32:44.233568Z","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":"2026-08-11T19:32:44.238134Z","title":"Mask r-cnn","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.06875","last_updated":"2024-12-09T16:17:22Z","snapshot_observed_at":"2026-08-16T10:16:47.085316Z","submitted_at":"2024-12-09T16:17:22Z","title":"VQ4ALL: Efficient Neural Network Representation via a Universal Codebook","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-11T19:32:44.238134Z"},"links":{"citing_paper":"/paper/2412.06875"},"observation_digest":"sha256:9df7a9dee27e0312080bfe28ee757ef7f1b2bbf969bb19bcd01cfb9ddf82e470","observation_id":"d8230678-3c32-4d0e-9c87-b9e38053e0d2","resolution":{"observed_at":"2026-08-11T19:32:44.238134Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.08718","last_updated":"2022-03-23T19:47:21Z","snapshot_observed_at":"2026-07-06T11:01:02.207193Z","submitted_at":"2021-04-18T05:00:29Z","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.08718","snapshot_observed_at":"2026-08-11T19:32:44.241948Z","title":"Clipscore: A reference-free evaluation met- ric for image captioning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.06875","last_updated":"2024-12-09T16:17:22Z","snapshot_observed_at":"2026-08-16T10:16:47.085316Z","submitted_at":"2024-12-09T16:17:22Z","title":"VQ4ALL: Efficient Neural Network Representation via a Universal Codebook","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-11T19:32:44.241948Z"},"links":{"cited_paper":"/paper/2104.08718","citing_paper":"/paper/2412.06875"},"observation_digest":"sha256:7efeede72c2c161a2ba65340c4d5275066416d75db226a52d0de888a1259779c","observation_id":"081dbb8d-9b5c-47a5-8233-7bf0f3baa3d3","resolution":{"observed_at":"2026-08-11T19:32:44.241948Z","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":"2026-08-11T19:32:44.245891Z","title":"Gans trained by a two time-scale update rule converge to a local nash equilib- rium","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.06875","last_updated":"2024-12-09T16:17:22Z","snapshot_observed_at":"2026-08-16T10:16:47.085316Z","submitted_at":"2024-12-09T16:17:22Z","title":"VQ4ALL: Efficient Neural Network Representation via a Universal Codebook","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-11T19:32:44.245891Z"},"links":{"citing_paper":"/paper/2412.06875"},"observation_digest":"sha256:91db1c5290e79926fc82126dff27350910f8600bb1c8ac4456dc0cc7df15da66","observation_id":"dffc4793-13cb-41fe-96de-39c75b412df7","resolution":{"observed_at":"2026-08-11T19:32:44.245891Z","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":"2026-08-11T19:32:44.754108Z","title":null,"venue":null,"work_id":"124ec190-2eb6-4f3a-a420-be2098c79da6","year":2021},"citing_paper":{"arxiv_id":"2412.06875","last_updated":"2024-12-09T16:17:22Z","snapshot_observed_at":"2026-08-16T10:16:47.085316Z","submitted_at":"2024-12-09T16:17:22Z","title":"VQ4ALL: Efficient Neural Network Representation via a Universal Codebook","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-11T19:32:44.249335Z"},"links":{"citing_paper":"/paper/2412.06875"},"observation_digest":"sha256:09fe87facb31570ee85a693e8eaea8f539a4afc57716338ae9f3fc599c66216a","observation_id":"7f671b8f-92b4-4d81-9b52-27ecf2018a70","resolution":{"observed_at":"2026-08-11T19:32:44.758147Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1611.01144","last_updated":"2017-08-05T22:45:19Z","snapshot_observed_at":"2026-08-15T03:05:41.956181Z","submitted_at":"2016-11-03T19:48:08Z","title":"Categorical Reparameterization with Gumbel-Softmax","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1611.01144","snapshot_observed_at":"2026-08-11T19:32:44.252836Z","title":"Categorical reparameterization with gumbel-softmax","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.06875","last_updated":"2024-12-09T16:17:22Z","snapshot_observed_at":"2026-08-16T10:16:47.085316Z","submitted_at":"2024-12-09T16:17:22Z","title":"VQ4ALL: Efficient Neural Network Representation via a Universal Codebook","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-11T19:32:44.252836Z"},"links":{"cited_paper":"/paper/1611.01144","citing_paper":"/paper/2412.06875"},"observation_digest":"sha256:c07624229239b4c6ede7638fa029ab7d4682ad6952774132551d5b00b0a1cb3a","observation_id":"dddd57c4-ee4e-4ea6-b4ae-26c7e2fa895d","resolution":{"observed_at":"2026-08-11T19:32:44.252836Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6980","last_updated":"2017-01-30T01:27:54Z","snapshot_observed_at":"2026-08-14T18:51:16.666127Z","submitted_at":"2014-12-22T13:54:29Z","title":"Adam: A Method for Stochastic Optimization","version":9},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6980","snapshot_observed_at":"2026-08-11T19:32:44.256694Z","title":"Adam: A method for stochastic opti- mization","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2412.06875","last_updated":"2024-12-09T16:17:22Z","snapshot_observed_at":"2026-08-16T10:16:47.085316Z","submitted_at":"2024-12-09T16:17:22Z","title":"VQ4ALL: Efficient Neural Network Representation via a Universal Codebook","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-11T19:32:44.256694Z"},"links":{"cited_paper":"/paper/1412.6980","citing_paper":"/paper/2412.06875"},"observation_digest":"sha256:999e6f2908570228415828c601adf8b2c33e357311fbd5b76011d40dab748a0e","observation_id":"62c91e27-1796-4ecc-8c14-51b36abdff11","resolution":{"observed_at":"2026-08-11T19:32:44.256694Z","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":"2026-08-11T19:32:44.742596Z","title":"Fully quantized network for object detection","venue":null,"work_id":"c26ed4c6-8b9b-4b55-b255-ee694f004669","year":null},"citing_paper":{"arxiv_id":"2412.06875","last_updated":"2024-12-09T16:17:22Z","snapshot_observed_at":"2026-08-16T10:16:47.085316Z","submitted_at":"2024-12-09T16:17:22Z","title":"VQ4ALL: Efficient Neural Network Representation via a Universal Codebook","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-11T19:32:44.260690Z"},"links":{"citing_paper":"/paper/2412.06875"},"observation_digest":"sha256:5ad66b09b46ec6dac68a9409894a68494e2be8eefdbafdda4938478eb03df902","observation_id":"9bb9cc10-aa5d-4c8f-8886-56ae3a94413b","resolution":{"observed_at":"2026-08-11T19:32:44.746614Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T19:32:44.730915Z","title":"Q-diffusion: Quantizing diffusion models","venue":null,"work_id":"0dba0402-90ce-4149-8780-b742950120a9","year":2023},"citing_paper":{"arxiv_id":"2412.06875","last_updated":"2024-12-09T16:17:22Z","snapshot_observed_at":"2026-08-16T10:16:47.085316Z","submitted_at":"2024-12-09T16:17:22Z","title":"VQ4ALL: Efficient Neural Network Representation via a Universal Codebook","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-11T19:32:44.264395Z"},"links":{"citing_paper":"/paper/2412.06875"},"observation_digest":"sha256:7d77fccacd4d7c506e188199de99eec54cc46f8200bbefe98abf1554b60005a9","observation_id":"034217a5-3c92-4211-8437-6b4dbb33e7f8","resolution":{"observed_at":"2026-08-11T19:32:44.734904Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1708.02002","last_updated":"2018-02-07T18:44:44Z","snapshot_observed_at":"2026-08-14T20:42:52.429547Z","submitted_at":"2017-08-07T06:32:42Z","title":"Focal Loss for Dense Object Detection","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1708.02002","snapshot_observed_at":"2026-08-11T19:32:44.267670Z","title":"Focal loss for dense object detection","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.06875","last_updated":"2024-12-09T16:17:22Z","snapshot_observed_at":"2026-08-16T10:16:47.085316Z","submitted_at":"2024-12-09T16:17:22Z","title":"VQ4ALL: Efficient Neural Network Representation via a Universal Codebook","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-11T19:32:44.267670Z"},"links":{"cited_paper":"/paper/1708.02002","citing_paper":"/paper/2412.06875"},"observation_digest":"sha256:1fb0ee0905faeecc81368280fd0f9f908194148a1643de6a8b98de22c827ba2e","observation_id":"5c3c254b-5429-44d4-8d65-f8b7f197b4c3","resolution":{"observed_at":"2026-08-11T19:32:44.267670Z","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":"2026-08-11T19:32:44.271697Z","title":"Microsoft coco: Common objects in context","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2412.06875","last_updated":"2024-12-09T16:17:22Z","snapshot_observed_at":"2026-08-16T10:16:47.085316Z","submitted_at":"2024-12-09T16:17:22Z","title":"VQ4ALL: Efficient Neural Network Representation via a Universal Codebook","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-11T19:32:44.271697Z"},"links":{"citing_paper":"/paper/2412.06875"},"observation_digest":"sha256:62cc98934a9e1b4787bfbf5798a086568f5db488ed7b5117b109c704a5802479","observation_id":"f8973057-3c29-47f9-9b3b-9c5a1c4f3861","resolution":{"observed_at":"2026-08-11T19:32:44.271697Z","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":"2026-08-11T19:32:44.713273Z","title":"Towards accurate binary convolutional neural network","venue":null,"work_id":"40bf9b0e-215e-4279-9e33-d7ed84936a9e","year":2017},"citing_paper":{"arxiv_id":"2412.06875","last_updated":"2024-12-09T16:17:22Z","snapshot_observed_at":"2026-08-16T10:16:47.085316Z","submitted_at":"2024-12-09T16:17:22Z","title":"VQ4ALL: Efficient Neural Network Representation via a Universal Codebook","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-11T19:32:44.275572Z"},"links":{"citing_paper":"/paper/2412.06875"},"observation_digest":"sha256:accab3d46ccbd616b96be8eaaba9f85c4ab46856b15967f85e3325ffb0499d72","observation_id":"e3dc2b82-4f13-485d-b377-8fae4886ae35","resolution":{"observed_at":"2026-08-11T19:32:44.717206Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1608.03983","last_updated":"2017-05-03T16:28:09Z","snapshot_observed_at":"2026-07-06T05:06:55.589962Z","submitted_at":"2016-08-13T13:46:05Z","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1608.03983","snapshot_observed_at":"2026-08-11T19:32:44.279290Z","title":"Sgdr: Stochas- tic gradient descent with warm restarts","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.06875","last_updated":"2024-12-09T16:17:22Z","snapshot_observed_at":"2026-08-16T10:16:47.085316Z","submitted_at":"2024-12-09T16:17:22Z","title":"VQ4ALL: Efficient Neural Network Representation via a Universal Codebook","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-11T19:32:44.279290Z"},"links":{"cited_paper":"/paper/1608.03983","citing_paper":"/paper/2412.06875"},"observation_digest":"sha256:180a848ad731c927d295b07248fe804956cb00d4d39da63616903094fba8c8a0","observation_id":"60992459-198f-4539-abab-80698bb0272a","resolution":{"observed_at":"2026-08-11T19:32:44.279290Z","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":"2026-08-11T19:32:44.701421Z","title":"Permute, quantize, and fine-tune: Efficient compression of neural networks","venue":null,"work_id":"7e96d3bc-b54f-4e25-a4ac-1240dc35e09e","year":2021},"citing_paper":{"arxiv_id":"2412.06875","last_updated":"2024-12-09T16:17:22Z","snapshot_observed_at":"2026-08-16T10:16:47.085316Z","submitted_at":"2024-12-09T16:17:22Z","title":"VQ4ALL: Efficient Neural Network Representation via a Universal Codebook","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-11T19:32:44.283233Z"},"links":{"citing_paper":"/paper/2412.06875"},"observation_digest":"sha256:3af328669d67d90e339f61171f20d5c0518790ed90755304c86563036524ede7","observation_id":"5f79d98e-9c88-40f7-97f5-a61b65a9feee","resolution":{"observed_at":"2026-08-11T19:32:44.705495Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T19:32:44.688754Z","title":"Profit: A novel training method for sub-4-bit mobilenet models","venue":null,"work_id":"dbb125a6-e3bc-44b6-b0d4-8509af05e84d","year":2020},"citing_paper":{"arxiv_id":"2412.06875","last_updated":"2024-12-09T16:17:22Z","snapshot_observed_at":"2026-08-16T10:16:47.085316Z","submitted_at":"2024-12-09T16:17:22Z","title":"VQ4ALL: Efficient Neural Network Representation via a Universal Codebook","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-11T19:32:44.287321Z"},"links":{"citing_paper":"/paper/2412.06875"},"observation_digest":"sha256:5224289fdc2f361d086e957e8c8b95e25c02a774b972b69d468d5a6d1a6e8632","observation_id":"4f334094-fc35-4519-8aba-941d0d962187","resolution":{"observed_at":"2026-08-11T19:32:44.693084Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T19:32:44.290898Z","title":"Learning transferable visual models from natural language supervi- sion","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.06875","last_updated":"2024-12-09T16:17:22Z","snapshot_observed_at":"2026-08-16T10:16:47.085316Z","submitted_at":"2024-12-09T16:17:22Z","title":"VQ4ALL: Efficient Neural Network Representation via a Universal Codebook","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-11T19:32:44.290898Z"},"links":{"citing_paper":"/paper/2412.06875"},"observation_digest":"sha256:65b55dfbb35e57b02d95b35ea3e3c0fb71f7998be5f606ee4be14c1cfe58e7cc","observation_id":"02e01b34-5458-476a-9287-bc3378099909","resolution":{"observed_at":"2026-08-11T19:32:44.290898Z","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":"2026-08-11T19:32:44.669653Z","title":"Xnor-net: Imagenet classification using bi- nary convolutional neural networks","venue":null,"work_id":"545049bd-f81b-4472-ac28-772186c4e64d","year":2016},"citing_paper":{"arxiv_id":"2412.06875","last_updated":"2024-12-09T16:17:22Z","snapshot_observed_at":"2026-08-16T10:16:47.085316Z","submitted_at":"2024-12-09T16:17:22Z","title":"VQ4ALL: Efficient Neural Network Representation via a Universal Codebook","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-11T19:32:44.294405Z"},"links":{"citing_paper":"/paper/2412.06875"},"observation_digest":"sha256:860ba01c75285c68c1e40a23b1b6b8d029b47dccadbf1f3b79edd0ab2e046297","observation_id":"0a2163b2-6e28-4182-b3e6-30e4ffe24cd2","resolution":{"observed_at":"2026-08-11T19:32:44.674168Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T19:32:44.297894Z","title":"High-resolution image synthesis with latent diffusion models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.06875","last_updated":"2024-12-09T16:17:22Z","snapshot_observed_at":"2026-08-16T10:16:47.085316Z","submitted_at":"2024-12-09T16:17:22Z","title":"VQ4ALL: Efficient Neural Network Representation via a Universal Codebook","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-11T19:32:44.297894Z"},"links":{"citing_paper":"/paper/2412.06875"},"observation_digest":"sha256:8f7ab287f1a1842e722977395d53c06a374b7be2c48d3188765888acf5a86437","observation_id":"0c4bf894-aaf3-45fc-a99f-edb8012365dc","resolution":{"observed_at":"2026-08-11T19:32:44.297894Z","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":"2026-08-11T19:32:44.301992Z","title":"Improved techniques for training gans","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.06875","last_updated":"2024-12-09T16:17:22Z","snapshot_observed_at":"2026-08-16T10:16:47.085316Z","submitted_at":"2024-12-09T16:17:22Z","title":"VQ4ALL: Efficient Neural Network Representation via a Universal Codebook","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-11T19:32:44.301992Z"},"links":{"citing_paper":"/paper/2412.06875"},"observation_digest":"sha256:50e81bd196aef4ad97c4b7c4a0001b6935a725ad34c6d2160c3e787c0339398f","observation_id":"ffb220a3-1aa2-499d-9983-d79c86871e43","resolution":{"observed_at":"2026-08-11T19:32:44.301992Z","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":"2026-08-11T19:32:44.643934Z","title":"Mobilenetv2: Inverted residuals and linear bottlenecks","venue":null,"work_id":"320a41a4-c966-4a92-81e7-41400f6a30be","year":null},"citing_paper":{"arxiv_id":"2412.06875","last_updated":"2024-12-09T16:17:22Z","snapshot_observed_at":"2026-08-16T10:16:47.085316Z","submitted_at":"2024-12-09T16:17:22Z","title":"VQ4ALL: Efficient Neural Network Representation via a Universal Codebook","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-11T19:32:44.305557Z"},"links":{"citing_paper":"/paper/2412.06875"},"observation_digest":"sha256:3fb5b162b838f03addb65effd1805c7d815824b8d47e86b110de79a75731084d","observation_id":"2f5be09f-dcae-4e58-a3b8-0edb98e158c5","resolution":{"observed_at":"2026-08-11T19:32:44.647858Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1710.07739","last_updated":"2018-02-02T12:20:03Z","snapshot_observed_at":"2026-08-14T20:21:41.574544Z","submitted_at":"2017-10-21T02:06:09Z","title":"Learning Discrete Weights Using the Local Reparameterization Trick","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.07739","snapshot_observed_at":"2026-08-11T19:32:44.309324Z","title":"Learning dis- crete weights using the local reparameterization trick","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.06875","last_updated":"2024-12-09T16:17:22Z","snapshot_observed_at":"2026-08-16T10:16:47.085316Z","submitted_at":"2024-12-09T16:17:22Z","title":"VQ4ALL: Efficient Neural Network Representation via a Universal Codebook","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-11T19:32:44.309324Z"},"links":{"cited_paper":"/paper/1710.07739","citing_paper":"/paper/2412.06875"},"observation_digest":"sha256:e792ddd66d8fd079f0ccb4ef49c7b827a3cf6ef7899978ed1d175d337d91fc34","observation_id":"6e460636-3f39-4e66-bcb6-4e4c8ff0faa3","resolution":{"observed_at":"2026-08-11T19:32:44.309324Z","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":"2026-08-11T19:32:44.631196Z","title":"Cluster- ing convolutional kernels to compress deep neural networks","venue":null,"work_id":"a9be1aba-49a7-48cd-aa26-d67e8919fa6e","year":2018},"citing_paper":{"arxiv_id":"2412.06875","last_updated":"2024-12-09T16:17:22Z","snapshot_observed_at":"2026-08-16T10:16:47.085316Z","submitted_at":"2024-12-09T16:17:22Z","title":"VQ4ALL: Efficient Neural Network Representation via a Universal Codebook","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-11T19:32:44.313034Z"},"links":{"citing_paper":"/paper/2412.06875"},"observation_digest":"sha256:996f0d23667b40b7775d82ef0e051e204642321a8938494388b2441318d26c3c","observation_id":"93cf53a5-9ce0-4804-b33e-bee748d723eb","resolution":{"observed_at":"2026-08-11T19:32:44.635425Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1907.05686","last_updated":"2020-11-09T10:11:15Z","snapshot_observed_at":"2026-08-14T16:06:26.545683Z","submitted_at":"2019-07-12T11:52:54Z","title":"And the Bit Goes Down: Revisiting the Quantization of Neural Networks","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1907.05686","snapshot_observed_at":"2026-08-11T19:32:44.316534Z","title":"And the bit goes down: Re- visiting the quantization of neural networks","venue":null,"work_id":null,"year":1907},"citing_paper":{"arxiv_id":"2412.06875","last_updated":"2024-12-09T16:17:22Z","snapshot_observed_at":"2026-08-16T10:16:47.085316Z","submitted_at":"2024-12-09T16:17:22Z","title":"VQ4ALL: Efficient Neural Network Representation via a Universal Codebook","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-11T19:32:44.316534Z"},"links":{"cited_paper":"/paper/1907.05686","citing_paper":"/paper/2412.06875"},"observation_digest":"sha256:0a2347fe8041699a4c4b609f8d7dad5ee67147f4728d02a3bb038d8d07cae992","observation_id":"5fdfdc41-a20e-42bf-9f3f-03e04a9ad90d","resolution":{"observed_at":"2026-08-11T19:32:44.316534Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.06322","last_updated":"2024-07-08T11:02:47Z","snapshot_observed_at":"2026-08-16T14:44:25.101786Z","submitted_at":"2023-11-10T09:10:09Z","title":"Post-training Quantization for Text-to-Image Diffusion Models with Progressive Calibration and Activation Relaxing","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.06322","snapshot_observed_at":"2026-08-11T19:32:44.321142Z","title":"Post-training quan- tization with progressive calibration and activation relax- ing for text-to-image diffusion models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.06875","last_updated":"2024-12-09T16:17:22Z","snapshot_observed_at":"2026-08-16T10:16:47.085316Z","submitted_at":"2024-12-09T16:17:22Z","title":"VQ4ALL: Efficient Neural Network Representation via a Universal Codebook","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-11T19:32:44.321142Z"},"links":{"cited_paper":"/paper/2311.06322","citing_paper":"/paper/2412.06875"},"observation_digest":"sha256:610289be09e7eac7e260747a2570e73cd1a96b60a1498d6653e136c923aa6dcd","observation_id":"b56ec7ba-1412-4f73-b5d4-9ed0564e8722","resolution":{"observed_at":"2026-08-11T19:32:44.321142Z","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":"2026-08-11T19:32:44.618671Z","title":"Haq: Hardware-aware automated quantization with mixed precision","venue":null,"work_id":"cf3f4a5e-6114-4bd6-a550-9851fbac3de3","year":2019},"citing_paper":{"arxiv_id":"2412.06875","last_updated":"2024-12-09T16:17:22Z","snapshot_observed_at":"2026-08-16T10:16:47.085316Z","submitted_at":"2024-12-09T16:17:22Z","title":"VQ4ALL: Efficient Neural Network Representation via a Universal Codebook","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-11T19:32:44.324893Z"},"links":{"citing_paper":"/paper/2412.06875"},"observation_digest":"sha256:fd2d2a88a2be6763b256f2f6b8a41265d4d4a3005a01862f3513acc678753689","observation_id":"fefca84e-3e9a-4563-8138-98e339936e7a","resolution":{"observed_at":"2026-08-11T19:32:44.623335Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T19:32:44.606225Z","title":"Quantized convolutional neural networks for mobile devices","venue":null,"work_id":"85acbbda-0c4d-4f65-82b3-e8af3d48aaac","year":null},"citing_paper":{"arxiv_id":"2412.06875","last_updated":"2024-12-09T16:17:22Z","snapshot_observed_at":"2026-08-16T10:16:47.085316Z","submitted_at":"2024-12-09T16:17:22Z","title":"VQ4ALL: Efficient Neural Network Representation via a Universal Codebook","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-11T19:32:44.328144Z"},"links":{"citing_paper":"/paper/2412.06875"},"observation_digest":"sha256:7af69d78eaa5a33001483e9485d6a5d562c8f3003661be369d20d7d3c7c68de9","observation_id":"753d8860-e761-4223-b9aa-f3e5ba4157fa","resolution":{"observed_at":"2026-08-11T19:32:44.610562Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T19:32:44.594615Z","title":"Gobo: Quantizing attention-based nlp models for low latency and energy efficient inference","venue":null,"work_id":"affb429e-b019-45cb-a4b4-d730b4f47d5f","year":2020},"citing_paper":{"arxiv_id":"2412.06875","last_updated":"2024-12-09T16:17:22Z","snapshot_observed_at":"2026-08-16T10:16:47.085316Z","submitted_at":"2024-12-09T16:17:22Z","title":"VQ4ALL: Efficient Neural Network Representation via a Universal Codebook","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-11T19:32:44.331820Z"},"links":{"citing_paper":"/paper/2412.06875"},"observation_digest":"sha256:61bd28dbd04881ee95b29c1bd1fe4b557acd3739a20dde3dae2add39bc8a4812","observation_id":"c322cf6d-48eb-45f4-9adc-dac3d82d3865","resolution":{"observed_at":"2026-08-11T19:32:44.598952Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1612.01064","last_updated":"2017-02-23T06:52:28Z","snapshot_observed_at":"2026-08-14T21:27:15.285323Z","submitted_at":"2016-12-04T05:00:22Z","title":"Trained Ternary Quantization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1612.01064","snapshot_observed_at":"2026-08-11T19:32:44.334963Z","title":"Trained ternary quantization","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.06875","last_updated":"2024-12-09T16:17:22Z","snapshot_observed_at":"2026-08-16T10:16:47.085316Z","submitted_at":"2024-12-09T16:17:22Z","title":"VQ4ALL: Efficient Neural Network Representation via a Universal Codebook","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-11T19:32:44.334963Z"},"links":{"cited_paper":"/paper/1612.01064","citing_paper":"/paper/2412.06875"},"observation_digest":"sha256:8eb97c1d52d03496465c09b1b9bda566198abe5e1b19c27603683bc19a3db908","observation_id":"2249ee6b-4fff-41c2-94fd-8de8b9ce173e","resolution":{"observed_at":"2026-08-11T19:32:44.334963Z","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":"2026-08-11T19:32:44.581819Z","title":null,"venue":null,"work_id":"5aa1fd82-5e79-403c-b01d-3915fac02c73","year":null},"citing_paper":{"arxiv_id":"2412.06875","last_updated":"2024-12-09T16:17:22Z","snapshot_observed_at":"2026-08-16T10:16:47.085316Z","submitted_at":"2024-12-09T16:17:22Z","title":"VQ4ALL: Efficient Neural Network Representation via a Universal Codebook","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-11T19:32:44.338758Z"},"links":{"citing_paper":"/paper/2412.06875"},"observation_digest":"sha256:ee8ee32487009407ffebd3e20446b49e32703628569498245ec21728e85e7e9e","observation_id":"45525b1f-b930-4c6d-8295-be3f6512a568","resolution":{"observed_at":"2026-08-11T19:32:44.586836Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T19:32:44.568948Z","title":"As shown in Figure 5, each type of low-bit network is evenly composed of differ- ent codewords of the same universal codebook","venue":null,"work_id":"2074cf14-5b3d-4077-85d3-e18909f7590a","year":null},"citing_paper":{"arxiv_id":"2412.06875","last_updated":"2024-12-09T16:17:22Z","snapshot_observed_at":"2026-08-16T10:16:47.085316Z","submitted_at":"2024-12-09T16:17:22Z","title":"VQ4ALL: Efficient Neural Network Representation via a Universal Codebook","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-11T19:32:44.342494Z"},"links":{"citing_paper":"/paper/2412.06875"},"observation_digest":"sha256:fa6f7e5ca9360a8259461fd80a64b54d52343fd22117f27d07aba2f042dea88c","observation_id":"65fec3dc-1f44-4dc7-85b7-e9ccc2dd75a0","resolution":{"observed_at":"2026-08-11T19:32:44.573087Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T19:32:44.555223Z","title":"We then evaluate the impact of these codebooks on network performance","venue":null,"work_id":"a5da91cf-5a67-41ed-b9b6-a7dda44d7884","year":null},"citing_paper":{"arxiv_id":"2412.06875","last_updated":"2024-12-09T16:17:22Z","snapshot_observed_at":"2026-08-16T10:16:47.085316Z","submitted_at":"2024-12-09T16:17:22Z","title":"VQ4ALL: Efficient Neural Network Representation via a Universal Codebook","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-11T19:32:44.346322Z"},"links":{"citing_paper":"/paper/2412.06875"},"observation_digest":"sha256:2ea690ff69448d0615b6872c9c7a3b6914f4aac2577001c0b1a00408f451cb07","observation_id":"be4644f8-2cec-41ec-91c7-2a6ea144f69d","resolution":{"observed_at":"2026-08-11T19:32:44.560028Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T19:32:44.541393Z","title":"Random candidate assignments yield the poorest performance, with the accuracy of 2-bit ResNet-18 and 2-bit ResNet-50 dropping to only 39.97% and 44.36%, respec- tively","venue":null,"work_id":"cd85a705-371c-4699-8454-99b5ed852e2d","year":null},"citing_paper":{"arxiv_id":"2412.06875","last_updated":"2024-12-09T16:17:22Z","snapshot_observed_at":"2026-08-16T10:16:47.085316Z","submitted_at":"2024-12-09T16:17:22Z","title":"VQ4ALL: Efficient Neural Network Representation via a Universal Codebook","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-11T19:32:44.349976Z"},"links":{"citing_paper":"/paper/2412.06875"},"observation_digest":"sha256:62fe4f55aea0e11850f63bd23f9751ca19023cac8349a7e68cce970a47d6a844","observation_id":"702520ef-7002-493d-a803-05fe2bbf7878","resolution":{"observed_at":"2026-08-11T19:32:44.545417Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T19:32:44.528797Z","title":"For ResNet-18/50, the primary blocks are ’Ba- sicBlock’ and ’Bottleneck’","venue":null,"work_id":"c5fc6a98-3994-459c-889c-b8b75b0547a7","year":null},"citing_paper":{"arxiv_id":"2412.06875","last_updated":"2024-12-09T16:17:22Z","snapshot_observed_at":"2026-08-16T10:16:47.085316Z","submitted_at":"2024-12-09T16:17:22Z","title":"VQ4ALL: Efficient Neural Network Representation via a Universal Codebook","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-11T19:32:44.354477Z"},"links":{"citing_paper":"/paper/2412.06875"},"observation_digest":"sha256:bd5434c3d3f72c7246e9958fcc958120ed3136b57be90bf81717eb3f06d5ce49","observation_id":"0bf46b52-4f47-427d-992b-40d58cbc9f4c","resolution":{"observed_at":"2026-08-11T19:32:44.532666Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T19:32:44.513452Z","title":"Compared to other state-of-the-art uniform quan- tization methods, the images generated by VQ4ALL are more similar to those produced by the floating-point net- work","venue":null,"work_id":"5f4bb8f6-3f56-4025-bbf7-c23283abe3a6","year":2000},"citing_paper":{"arxiv_id":"2412.06875","last_updated":"2024-12-09T16:17:22Z","snapshot_observed_at":"2026-08-16T10:16:47.085316Z","submitted_at":"2024-12-09T16:17:22Z","title":"VQ4ALL: Efficient Neural Network Representation via a Universal Codebook","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-11T19:32:44.358848Z"},"links":{"citing_paper":"/paper/2412.06875"},"observation_digest":"sha256:600ec1125161b8b29600e05ac8410564aa72fc1eab6fd02869eec4c5f0a35cd1","observation_id":"4bee6268-7e30-4d48-bdf8-7ca003a1ccaf","resolution":{"observed_at":"2026-08-11T19:32:44.520176Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2412.06875","last_updated":"2024-12-09T16:17:22Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-16T10:16:47.085316Z","submitted_at":"2024-12-09T16:17:22Z","title":"VQ4ALL: Efficient Neural Network Representation via a Universal Codebook"},"reference_resolution":{"displayed":43,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":23,"verified_exact":0,"verified_fuzzy":20},"total_outbound_references":43},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 43 of 43 outbound references and 0 inbound Pith citation observations for arXiv:2412.06875."}