{"as_of":"2026-08-10T11:51:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:777839361df5344fc49b1b5c98df6689c1a46f3303546e807a372113acc084fb","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":58,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":58,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":58,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":58,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-09T16:22:12.514507Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":1,"source":"arxiv_reference","source_observed_at":"2026-08-05T02:28:24.338817Z","state":"measured"}],"external_citation_measurements":[{"count":296,"observed_at":"2026-08-05T02:28:24.338817Z","source":"arxiv_reference"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1902.08153","last_updated":"2020-05-07T03:30:49Z","snapshot_observed_at":"2026-08-07T23:40:04.424513Z","submitted_at":"2019-02-21T17:31:32Z","title":"Learned Step Size Quantization","version":3},"cited_work":{"arxiv_id":"1902.08153","doi":"10.48550/arxiv.1902.08153","metadata_source":"arxiv_reference","pith_arxiv_id":"1902.08153","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"K., McKinstry, J","venue":"arXiv (Cornell University)","work_id":"87dd0e40-bfbe-4de6-8d30-65c5a87d97dd","year":1902},"citing_paper":{"arxiv_id":"2208.07339","last_updated":"2022-11-10T18:14:31Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2022-08-15T17:08:50Z","title":"LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale","version":2},"reference_index":131,"source":"arxiv_source","source_observed_at":"2026-05-13T13:35:35.972596Z"},"links":{"cited_paper":"/paper/1902.08153","citing_paper":"/paper/2208.07339"},"observation_digest":"sha256:49dc32b800aa506cc22a4c05b1051e7569c48f5b6f088c56c0185e3556e4cbf1","observation_id":"31971a76-fc2c-4c49-9eb1-4b2ec9453ef5","resolution":{"observed_at":"2026-05-13T13:35:36.073220Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1902.08153","last_updated":"2020-05-07T03:30:49Z","snapshot_observed_at":"2026-08-07T23:40:04.424513Z","submitted_at":"2019-02-21T17:31:32Z","title":"Learned Step Size Quantization","version":3},"cited_work":{"arxiv_id":"1902.08153","doi":"10.48550/arxiv.1902.08153","metadata_source":"arxiv_reference","pith_arxiv_id":"1902.08153","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"K., McKinstry, J","venue":"arXiv (Cornell University)","work_id":"87dd0e40-bfbe-4de6-8d30-65c5a87d97dd","year":1902},"citing_paper":{"arxiv_id":"2306.00978","last_updated":"2026-04-25T06:58:16Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-06-01T17:59:10Z","title":"AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration","version":6},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-24T08:27:35.798991Z"},"links":{"cited_paper":"/paper/1902.08153","citing_paper":"/paper/2306.00978"},"observation_digest":"sha256:e4f133749536a69a59e0b05fc46cb4f14aeb699c6a18da3280bd491053a07d3d","observation_id":"44c1c523-db5d-4199-9746-6dce1c83ad7c","resolution":{"observed_at":"2026-05-24T08:29:11.362464Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1902.08153","last_updated":"2020-05-07T03:30:49Z","snapshot_observed_at":"2026-08-07T23:40:04.424513Z","submitted_at":"2019-02-21T17:31:32Z","title":"Learned Step Size Quantization","version":3},"cited_work":{"arxiv_id":"1902.08153","doi":"10.48550/arxiv.1902.08153","metadata_source":"arxiv_reference","pith_arxiv_id":"1902.08153","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"K., McKinstry, J","venue":"arXiv (Cornell University)","work_id":"87dd0e40-bfbe-4de6-8d30-65c5a87d97dd","year":1902},"citing_paper":{"arxiv_id":"2408.00923","last_updated":"2026-04-27T12:17:56Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-08-01T21:27:31Z","title":"Reclaiming Residual Knowledge: A Novel Paradigm to Low-Bit Quantization","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-23T22:25:53.700079Z"},"links":{"cited_paper":"/paper/1902.08153","citing_paper":"/paper/2408.00923"},"observation_digest":"sha256:ee41fc1c5bb9e4ba7ae11bbb9204ce1254496cc65d01bd7081324bb8655daaf4","observation_id":"1680614d-ac59-48fc-ab79-bc3cefb9a1c6","resolution":{"observed_at":"2026-05-23T22:28:31.067884Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1902.08153","last_updated":"2020-05-07T03:30:49Z","snapshot_observed_at":"2026-08-07T23:40:04.424513Z","submitted_at":"2019-02-21T17:31:32Z","title":"Learned Step Size Quantization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.08153","snapshot_observed_at":"2026-08-09T16:22:12.514507Z","title":"Learned step size quantization,","venue":null,"work_id":null,"year":1902},"citing_paper":{"arxiv_id":"2502.01199","last_updated":"2025-02-03T09:46:26Z","snapshot_observed_at":"2026-08-09T16:12:17.215540Z","submitted_at":"2025-02-03T09:46:26Z","title":"Nearly Lossless Adaptive Bit Switching","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-09T16:22:12.514507Z"},"links":{"cited_paper":"/paper/1902.08153","citing_paper":"/paper/2502.01199"},"observation_digest":"sha256:08dc8b2bc6cf9b5f2e37a00e516f90ad773ea412692e5b8c615fb91a3fb6212a","observation_id":"53e7adea-934e-45a3-9350-eb09fae0bc33","resolution":{"observed_at":"2026-08-09T16:22:12.514507Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1902.08153","last_updated":"2020-05-07T03:30:49Z","snapshot_observed_at":"2026-08-07T23:40:04.424513Z","submitted_at":"2019-02-21T17:31:32Z","title":"Learned Step Size Quantization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.08153","snapshot_observed_at":"2026-08-09T16:13:35.860096Z","title":"Learned step size quantization.arXiv preprint arXiv:1902.08153,","venue":null,"work_id":null,"year":1902},"citing_paper":{"arxiv_id":"2502.06805","last_updated":"2025-06-06T14:57:09Z","snapshot_observed_at":"2026-08-09T15:58:29.865832Z","submitted_at":"2025-02-03T10:15:08Z","title":"Efficient Diffusion Models: A Survey","version":3},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-09T16:13:35.860096Z"},"links":{"cited_paper":"/paper/1902.08153","citing_paper":"/paper/2502.06805"},"observation_digest":"sha256:11d01f9219d2c35d86a6e8b3f365666ba73b116f890e2f65f3c8650135ab8ac6","observation_id":"d4f1fefe-c81d-44d3-84d5-d63e70f665ba","resolution":{"observed_at":"2026-08-09T16:13:35.860096Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1902.08153","last_updated":"2020-05-07T03:30:49Z","snapshot_observed_at":"2026-08-07T23:40:04.424513Z","submitted_at":"2019-02-21T17:31:32Z","title":"Learned Step Size Quantization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.08153","snapshot_observed_at":"2026-08-08T10:26:45.429133Z","title":"Learned step size quantization","venue":null,"work_id":null,"year":1902},"citing_paper":{"arxiv_id":"2502.08141","last_updated":"2025-02-12T05:48:26Z","snapshot_observed_at":"2026-08-09T22:29:11.492006Z","submitted_at":"2025-02-12T05:48:26Z","title":"LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-08T10:26:45.429133Z"},"links":{"cited_paper":"/paper/1902.08153","citing_paper":"/paper/2502.08141"},"observation_digest":"sha256:a005ec45c933909332bd4b9c790ca5450ccf4e331fb82f9ba745469fe9f10ff8","observation_id":"a684b590-357e-4f2b-823d-84224357e7ff","resolution":{"observed_at":"2026-08-08T10:26:45.429133Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1902.08153","last_updated":"2020-05-07T03:30:49Z","snapshot_observed_at":"2026-08-07T23:40:04.424513Z","submitted_at":"2019-02-21T17:31:32Z","title":"Learned Step Size Quantization","version":3},"cited_work":{"arxiv_id":"1902.08153","doi":"10.48550/arxiv.1902.08153","metadata_source":"arxiv_reference","pith_arxiv_id":"1902.08153","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"K., McKinstry, J","venue":"arXiv (Cornell University)","work_id":"87dd0e40-bfbe-4de6-8d30-65c5a87d97dd","year":1902},"citing_paper":{"arxiv_id":"2503.03088","last_updated":"2026-04-08T13:11:29Z","snapshot_observed_at":"2026-07-31T21:51:41.767129Z","submitted_at":"2025-03-05T01:04:45Z","title":"AHCQ-SAM: Toward Accurate and Hardware-Compatible Post-Training Segment Anything Model Quantization","version":4},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-23T01:48:34.562325Z"},"links":{"cited_paper":"/paper/1902.08153","citing_paper":"/paper/2503.03088"},"observation_digest":"sha256:66263794fc427e907597aa212980b06ab38a14f749d98038864ad3d4b56fa926","observation_id":"6b9dac8b-19f0-4c22-9bbe-e23ddb94b25c","resolution":{"observed_at":"2026-05-23T01:52:23.036648Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1902.08153","last_updated":"2020-05-07T03:30:49Z","snapshot_observed_at":"2026-08-07T23:40:04.424513Z","submitted_at":"2019-02-21T17:31:32Z","title":"Learned Step Size Quantization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.08153","snapshot_observed_at":"2026-08-07T15:41:06.036806Z","title":"Learned step size quantization.arXiv preprint arXiv:1902.08153, 2019","venue":null,"work_id":null,"year":1902},"citing_paper":{"arxiv_id":"2505.14302","last_updated":"2025-05-20T12:54:43Z","snapshot_observed_at":"2026-08-07T15:43:23.244437Z","submitted_at":"2025-05-20T12:54:43Z","title":"Scaling Law for Quantization-Aware Training","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T15:41:06.036806Z"},"links":{"cited_paper":"/paper/1902.08153","citing_paper":"/paper/2505.14302"},"observation_digest":"sha256:eab829bdc324085130026303ee21617e522e9400ed9fca1c66c3d43afc0ef201","observation_id":"39e43c9c-7f1a-448c-8ae6-bde3be19a16c","resolution":{"observed_at":"2026-08-07T15:41:06.036806Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1902.08153","last_updated":"2020-05-07T03:30:49Z","snapshot_observed_at":"2026-08-07T23:40:04.424513Z","submitted_at":"2019-02-21T17:31:32Z","title":"Learned Step Size Quantization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.08153","snapshot_observed_at":"2026-08-07T15:36:05.491210Z","title":"Learned step size quantization,","venue":null,"work_id":null,"year":1902},"citing_paper":{"arxiv_id":"2505.14638","last_updated":"2025-05-20T17:26:12Z","snapshot_observed_at":"2026-08-07T23:40:41.352977Z","submitted_at":"2025-05-20T17:26:12Z","title":"Dual Precision Quantization for Efficient and Accurate Deep Neural Networks Inference","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T15:36:05.491210Z"},"links":{"cited_paper":"/paper/1902.08153","citing_paper":"/paper/2505.14638"},"observation_digest":"sha256:9132b217fa77473a132b3ce8c0f7e1397f405c67f8fc7d8c7a150b51b171eb4a","observation_id":"236c17b8-9918-47c9-aa7d-3e09aa1d7f80","resolution":{"observed_at":"2026-08-07T15:36:05.491210Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1902.08153","last_updated":"2020-05-07T03:30:49Z","snapshot_observed_at":"2026-08-07T23:40:04.424513Z","submitted_at":"2019-02-21T17:31:32Z","title":"Learned Step Size Quantization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.08153","snapshot_observed_at":"2026-08-07T15:07:22.600554Z","title":"Learned step size quantization","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.16332","last_updated":"2025-08-14T05:38:23Z","snapshot_observed_at":"2026-08-10T03:16:41.532667Z","submitted_at":"2025-05-22T07:40:23Z","title":"Is Quantum Optimization Ready? An Effort Towards Neural Network Compression using Adiabatic Quantum Computing","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T15:07:22.600554Z"},"links":{"cited_paper":"/paper/1902.08153","citing_paper":"/paper/2505.16332"},"observation_digest":"sha256:fa5325e8771d027ac967ca4bc1d4a2fe1aa585d6c8c44038f80d03af2cf8c1e5","observation_id":"96c378ab-2551-4677-8817-b454a008e5d2","resolution":{"observed_at":"2026-08-07T15:07:22.600554Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1902.08153","last_updated":"2020-05-07T03:30:49Z","snapshot_observed_at":"2026-08-07T23:40:04.424513Z","submitted_at":"2019-02-21T17:31:32Z","title":"Learned Step Size Quantization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.08153","snapshot_observed_at":"2026-08-07T13:50:34.125519Z","title":"Learned step size quantization.arXiv preprint arXiv:1902.08153, 2019","venue":null,"work_id":null,"year":1902},"citing_paper":{"arxiv_id":"2505.20890","last_updated":"2025-05-27T08:33:04Z","snapshot_observed_at":"2026-08-10T07:36:19.294909Z","submitted_at":"2025-05-27T08:33:04Z","title":"Frequency Composition for Compressed and Domain-Adaptive Neural Networks","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T13:50:34.125519Z"},"links":{"cited_paper":"/paper/1902.08153","citing_paper":"/paper/2505.20890"},"observation_digest":"sha256:024bf4d59365376d50183ae831b2449dc2784debd0970dddb8f0279541127f8a","observation_id":"71d6a732-72b7-470d-b92c-21e7eb3600e3","resolution":{"observed_at":"2026-08-07T13:50:34.125519Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1902.08153","last_updated":"2020-05-07T03:30:49Z","snapshot_observed_at":"2026-08-07T23:40:04.424513Z","submitted_at":"2019-02-21T17:31:32Z","title":"Learned Step Size Quantization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.08153","snapshot_observed_at":"2026-08-07T11:52:58.474593Z","title":"Learned step size quantiza- tion,","venue":null,"work_id":null,"year":1902},"citing_paper":{"arxiv_id":"2506.01221","last_updated":"2025-06-02T00:12:50Z","snapshot_observed_at":"2026-08-10T03:20:38.089760Z","submitted_at":"2025-06-02T00:12:50Z","title":"Flexible Mixed Precision Quantization for Learned Image Compression","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T11:52:58.474593Z"},"links":{"cited_paper":"/paper/1902.08153","citing_paper":"/paper/2506.01221"},"observation_digest":"sha256:acc9a8344e69317405b4fa6cfe16da697b2d1b9cdc12164608febb19ddec94e3","observation_id":"c3481ddd-bf17-490d-863f-34eecde84714","resolution":{"observed_at":"2026-08-07T11:52:58.474593Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1902.08153","last_updated":"2020-05-07T03:30:49Z","snapshot_observed_at":"2026-08-07T23:40:04.424513Z","submitted_at":"2019-02-21T17:31:32Z","title":"Learned Step Size Quantization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.08153","snapshot_observed_at":"2026-08-07T11:51:38.003222Z","title":"Learned step size quantiza- tion,","venue":null,"work_id":null,"year":1902},"citing_paper":{"arxiv_id":"2506.01229","last_updated":"2025-06-02T00:40:53Z","snapshot_observed_at":"2026-08-08T13:14:35.815700Z","submitted_at":"2025-06-02T00:40:53Z","title":"Structured Pruning and Quantization for Learned Image Compression","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T11:51:38.003222Z"},"links":{"cited_paper":"/paper/1902.08153","citing_paper":"/paper/2506.01229"},"observation_digest":"sha256:02eff234e3b4d01ce558e2b9b74aa187174656fa7a94776d12d03503704ac609","observation_id":"40d849c3-31e1-42ab-8cce-2d293def07e2","resolution":{"observed_at":"2026-08-07T11:51:38.003222Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1902.08153","last_updated":"2020-05-07T03:30:49Z","snapshot_observed_at":"2026-08-07T23:40:04.424513Z","submitted_at":"2019-02-21T17:31:32Z","title":"Learned Step Size Quantization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.08153","snapshot_observed_at":"2026-08-07T11:39:52.179507Z","title":"K., McKinstry, J","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.01863","last_updated":"2025-06-02T16:52:51Z","snapshot_observed_at":"2026-08-07T23:41:22.236547Z","submitted_at":"2025-06-02T16:52:51Z","title":"Unified Scaling Laws for Compressed Representations","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T11:39:52.179507Z"},"links":{"cited_paper":"/paper/1902.08153","citing_paper":"/paper/2506.01863"},"observation_digest":"sha256:8b9a8fd60aadb8470337df4247a78bd0f579d948f389872d194ed77b78a41b86","observation_id":"9768d41f-423b-434f-94b1-129a3380f40e","resolution":{"observed_at":"2026-08-07T11:39:52.179507Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1902.08153","last_updated":"2020-05-07T03:30:49Z","snapshot_observed_at":"2026-08-07T23:40:04.424513Z","submitted_at":"2019-02-21T17:31:32Z","title":"Learned Step Size Quantization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.08153","snapshot_observed_at":"2026-08-07T04:56:57.249212Z","title":"Learned step size quantization,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.09282","last_updated":"2025-06-10T22:46:12Z","snapshot_observed_at":"2026-08-09T21:13:37.637731Z","submitted_at":"2025-06-10T22:46:12Z","title":"ScalableHD: Scalable and High-Throughput Hyperdimensional Computing Inference on Multi-Core CPUs","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-07T04:56:57.249212Z"},"links":{"cited_paper":"/paper/1902.08153","citing_paper":"/paper/2506.09282"},"observation_digest":"sha256:4cc5c2e8b6fd2ae4bc06ae7a858ce784b1591058e951c12201141e82dd0a5d4f","observation_id":"7c51df52-81ac-42bb-a7a1-992de9239ea5","resolution":{"observed_at":"2026-08-07T04:56:57.249212Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1902.08153","last_updated":"2020-05-07T03:30:49Z","snapshot_observed_at":"2026-08-07T23:40:04.424513Z","submitted_at":"2019-02-21T17:31:32Z","title":"Learned Step Size Quantization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.08153","snapshot_observed_at":"2026-08-07T04:18:09.205283Z","title":"Learned step size quantization,","venue":null,"work_id":null,"year":1902},"citing_paper":{"arxiv_id":"2506.11431","last_updated":"2025-06-13T03:08:18Z","snapshot_observed_at":"2026-08-07T09:18:52.566169Z","submitted_at":"2025-06-13T03:08:18Z","title":"TruncQuant: Truncation-Ready Quantization for DNNs with Flexible Weight Bit Precision","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T04:18:09.205283Z"},"links":{"cited_paper":"/paper/1902.08153","citing_paper":"/paper/2506.11431"},"observation_digest":"sha256:aadac637e168cd44345478c58e56e2182c0b0c528e58f610e68dabc5f337a376","observation_id":"07d7a2a6-20c0-47b9-939c-faf30ae1bf2e","resolution":{"observed_at":"2026-08-07T04:18:09.205283Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1902.08153","last_updated":"2020-05-07T03:30:49Z","snapshot_observed_at":"2026-08-07T23:40:04.424513Z","submitted_at":"2019-02-21T17:31:32Z","title":"Learned Step Size Quantization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.08153","snapshot_observed_at":"2026-08-07T04:10:24.991159Z","title":"Learned step size quantization.arXiv preprint arXiv:1902.08153, 2019","venue":null,"work_id":null,"year":1902},"citing_paper":{"arxiv_id":"2506.11784","last_updated":"2025-06-13T13:45:17Z","snapshot_observed_at":"2026-08-09T09:04:46.646980Z","submitted_at":"2025-06-13T13:45:17Z","title":"GPLQ: A General, Practical, and Lightning QAT Method for Vision Transformers","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T04:10:24.991159Z"},"links":{"cited_paper":"/paper/1902.08153","citing_paper":"/paper/2506.11784"},"observation_digest":"sha256:671d9eebc34318da9caf4d188df37ebec09062506aaa58d092f0a974f522a6ee","observation_id":"290b2395-8c77-4bbb-b477-f9a3d3714391","resolution":{"observed_at":"2026-08-07T04:10:24.991159Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1902.08153","last_updated":"2020-05-07T03:30:49Z","snapshot_observed_at":"2026-08-07T23:40:04.424513Z","submitted_at":"2019-02-21T17:31:32Z","title":"Learned Step Size Quantization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.08153","snapshot_observed_at":"2026-08-07T01:07:47.498768Z","title":"Esser, Jeffrey L","venue":null,"work_id":null,"year":1902},"citing_paper":{"arxiv_id":"2506.11992","last_updated":"2025-06-13T17:48:50Z","snapshot_observed_at":"2026-08-07T23:41:28.461732Z","submitted_at":"2025-06-13T17:48:50Z","title":"Compression Aware Certified Training","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T01:07:47.498768Z"},"links":{"cited_paper":"/paper/1902.08153","citing_paper":"/paper/2506.11992"},"observation_digest":"sha256:31242b60aa674e09f14551ec9bd92ac0d63048a55cb0389769010c932d844de4","observation_id":"8307382a-9527-4d6a-bbfc-f6b9999c0c6f","resolution":{"observed_at":"2026-08-07T01:07:47.498768Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1902.08153","last_updated":"2020-05-07T03:30:49Z","snapshot_observed_at":"2026-08-07T23:40:04.424513Z","submitted_at":"2019-02-21T17:31:32Z","title":"Learned Step Size Quantization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.08153","snapshot_observed_at":"2026-08-06T23:42:35.252934Z","title":"Learned step size quantiza- tion,","venue":null,"work_id":null,"year":1902},"citing_paper":{"arxiv_id":"2506.16776","last_updated":"2025-06-20T06:43:27Z","snapshot_observed_at":"2026-08-07T23:40:38.128814Z","submitted_at":"2025-06-20T06:43:27Z","title":"PQCAD-DM: Progressive Quantization and Calibration-Assisted Distillation for Extremely Efficient Diffusion Model","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T23:42:35.252934Z"},"links":{"cited_paper":"/paper/1902.08153","citing_paper":"/paper/2506.16776"},"observation_digest":"sha256:b17a149e2c5d3274fe42bf44f6e2f5d574bbf7e51aff10f0590621e2fbba3720","observation_id":"dccd5cfe-54e6-427a-9325-b1addcea781f","resolution":{"observed_at":"2026-08-06T23:42:35.252934Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1902.08153","last_updated":"2020-05-07T03:30:49Z","snapshot_observed_at":"2026-08-07T23:40:04.424513Z","submitted_at":"2019-02-21T17:31:32Z","title":"Learned Step Size Quantization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.08153","snapshot_observed_at":"2026-08-06T19:57:19.426181Z","title":"Learned step size quantization,","venue":null,"work_id":null,"year":1902},"citing_paper":{"arxiv_id":"2507.04290","last_updated":"2025-07-06T08:16:50Z","snapshot_observed_at":"2026-08-08T08:13:06.170937Z","submitted_at":"2025-07-06T08:16:50Z","title":"MPQ-DMv2: Flexible Residual Mixed Precision Quantization for Low-Bit Diffusion Models with Temporal Distillation","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T19:57:19.426181Z"},"links":{"cited_paper":"/paper/1902.08153","citing_paper":"/paper/2507.04290"},"observation_digest":"sha256:f715292b48e44243d6ceffde2257031acd55a68cd6d44c2b5863fdb9ae51578e","observation_id":"1764b4e4-73de-4d2d-9015-b1c14d93593c","resolution":{"observed_at":"2026-08-06T19:57:19.426181Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1902.08153","last_updated":"2020-05-07T03:30:49Z","snapshot_observed_at":"2026-08-07T23:40:04.424513Z","submitted_at":"2019-02-21T17:31:32Z","title":"Learned Step Size Quantization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.08153","snapshot_observed_at":"2026-08-06T17:56:21.315395Z","title":"Learned step size quantization,","venue":null,"work_id":null,"year":1902},"citing_paper":{"arxiv_id":"2507.09665","last_updated":"2025-07-13T14:58:19Z","snapshot_observed_at":"2026-08-08T22:10:15.646478Z","submitted_at":"2025-07-13T14:58:19Z","title":"Is Quantization a Deal-breaker? Empirical Insights from Large Code Models","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T17:56:21.315395Z"},"links":{"cited_paper":"/paper/1902.08153","citing_paper":"/paper/2507.09665"},"observation_digest":"sha256:88b753ad201e11090478b7b69514e28a1e05ea06556877d56848a713bd8c644b","observation_id":"b4ac89f9-5cec-46f8-8778-f0398913346f","resolution":{"observed_at":"2026-08-06T17:56:21.315395Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1902.08153","last_updated":"2020-05-07T03:30:49Z","snapshot_observed_at":"2026-08-07T23:40:04.424513Z","submitted_at":"2019-02-21T17:31:32Z","title":"Learned Step Size Quantization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.08153","snapshot_observed_at":"2026-08-06T17:55:14.139337Z","title":"Learned step size quantization","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.09687","last_updated":"2025-07-13T15:48:16Z","snapshot_observed_at":"2026-08-09T05:06:24.215334Z","submitted_at":"2025-07-13T15:48:16Z","title":"Post-Training Quantization of Generative and Discriminative LSTM Text Classifiers: A Study of Calibration, Class Balance, and Robustness","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T17:55:14.139337Z"},"links":{"cited_paper":"/paper/1902.08153","citing_paper":"/paper/2507.09687"},"observation_digest":"sha256:1b03509a4d6831495eb4000ad0611afd6b98e9bd6ed82c60fad776312cf88347","observation_id":"8b6f505e-be6e-4521-be51-583d6161aa85","resolution":{"observed_at":"2026-08-06T17:55:14.139337Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1902.08153","last_updated":"2020-05-07T03:30:49Z","snapshot_observed_at":"2026-08-07T23:40:04.424513Z","submitted_at":"2019-02-21T17:31:32Z","title":"Learned Step Size Quantization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.08153","snapshot_observed_at":"2026-08-06T16:42:11.799216Z","title":"Learned step size quantization.arXiv preprint arXiv:1902.08153, 2019","venue":null,"work_id":null,"year":1902},"citing_paper":{"arxiv_id":"2507.12933","last_updated":"2025-07-17T09:15:29Z","snapshot_observed_at":"2026-08-07T03:07:45.280876Z","submitted_at":"2025-07-17T09:15:29Z","title":"DMQ: Dissecting Outliers of Diffusion Models for Post-Training Quantization","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T16:42:11.799216Z"},"links":{"cited_paper":"/paper/1902.08153","citing_paper":"/paper/2507.12933"},"observation_digest":"sha256:1d4784c47b9768bfb699cbdb0d27c28dc9c818e7525e76e7bb2e82745fe70ccc","observation_id":"cbfc8fdb-1a46-43e1-b2ad-11d343256647","resolution":{"observed_at":"2026-08-06T16:42:11.799216Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1902.08153","last_updated":"2020-05-07T03:30:49Z","snapshot_observed_at":"2026-08-07T23:40:04.424513Z","submitted_at":"2019-02-21T17:31:32Z","title":"Learned Step Size Quantization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.08153","snapshot_observed_at":"2026-08-06T16:09:07.022111Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.14481","last_updated":"2025-07-19T04:32:04Z","snapshot_observed_at":"2026-08-09T01:41:09.088488Z","submitted_at":"2025-07-19T04:32:04Z","title":"DFQ-ViT: Data-Free Quantization for Vision Transformers without Fine-tuning","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T16:09:07.022111Z"},"links":{"cited_paper":"/paper/1902.08153","citing_paper":"/paper/2507.14481"},"observation_digest":"sha256:b7fb3a5f396ccc0c5836e1fbaaa2895301d27c6c274bdbf6394a303721ad336c","observation_id":"a237aaf0-7e3c-4e3e-b092-3296471d6481","resolution":{"observed_at":"2026-08-06T16:09:07.022111Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1902.08153","last_updated":"2020-05-07T03:30:49Z","snapshot_observed_at":"2026-08-07T23:40:04.424513Z","submitted_at":"2019-02-21T17:31:32Z","title":"Learned Step Size Quantization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.08153","snapshot_observed_at":"2026-08-06T15:05:21.429063Z","title":"Learned step size quantization","venue":null,"work_id":null,"year":1902},"citing_paper":{"arxiv_id":"2507.16782","last_updated":"2025-07-22T17:28:29Z","snapshot_observed_at":"2026-08-09T09:17:15.730805Z","submitted_at":"2025-07-22T17:28:29Z","title":"Task-Specific Zero-shot Quantization-Aware Training for Object Detection","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T15:05:21.429063Z"},"links":{"cited_paper":"/paper/1902.08153","citing_paper":"/paper/2507.16782"},"observation_digest":"sha256:a51a95a22486fdbc8173e7972ba596b8db966e5f083be3a3ecfc33c50f01f40f","observation_id":"dd440759-04de-4927-a98b-eb4bca742f94","resolution":{"observed_at":"2026-08-06T15:05:21.429063Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1902.08153","last_updated":"2020-05-07T03:30:49Z","snapshot_observed_at":"2026-08-07T23:40:04.424513Z","submitted_at":"2019-02-21T17:31:32Z","title":"Learned Step Size Quantization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.08153","snapshot_observed_at":"2026-08-06T11:56:59.780872Z","title":"Esser, John L","venue":null,"work_id":null,"year":1902},"citing_paper":{"arxiv_id":"2507.22349","last_updated":"2025-07-30T03:21:29Z","snapshot_observed_at":"2026-08-07T23:42:10.255138Z","submitted_at":"2025-07-30T03:21:29Z","title":"MSQ: Memory-Efficient Bit Sparsification Quantization","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T11:56:59.780872Z"},"links":{"cited_paper":"/paper/1902.08153","citing_paper":"/paper/2507.22349"},"observation_digest":"sha256:cb4e610bdb4743451782d45be4fbb8fb281dbe65ed553fb9fb57b7ef49a5ddaf","observation_id":"4a647b1d-9898-4422-b763-fdba6849a14c","resolution":{"observed_at":"2026-08-06T11:56:59.780872Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1902.08153","last_updated":"2020-05-07T03:30:49Z","snapshot_observed_at":"2026-08-07T23:40:04.424513Z","submitted_at":"2019-02-21T17:31:32Z","title":"Learned Step Size Quantization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.08153","snapshot_observed_at":"2026-08-05T15:16:58.407678Z","title":"Learned step size quantization","venue":null,"work_id":null,"year":1902},"citing_paper":{"arxiv_id":"2509.00097","last_updated":"2025-08-27T15:59:36Z","snapshot_observed_at":"2026-08-05T15:16:57.243095Z","submitted_at":"2025-08-27T15:59:36Z","title":"Progressive Element-wise Gradient Estimation for Neural Network Quantization","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-05T15:16:58.407678Z"},"links":{"cited_paper":"/paper/1902.08153","citing_paper":"/paper/2509.00097"},"observation_digest":"sha256:224da6e00bbdc241d274cf09f8c211bdf66450d2bb033c8976bf235ba878093e","observation_id":"41d0a812-6b18-4e6d-aa92-aa55a80c09a6","resolution":{"observed_at":"2026-08-05T15:16:58.407678Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1902.08153","last_updated":"2020-05-07T03:30:49Z","snapshot_observed_at":"2026-08-07T23:40:04.424513Z","submitted_at":"2019-02-21T17:31:32Z","title":"Learned Step Size Quantization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.08153","snapshot_observed_at":"2026-08-05T13:12:23.842748Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.00859","last_updated":"2025-08-31T14:05:14Z","snapshot_observed_at":"2026-08-09T07:45:57.458856Z","submitted_at":"2025-08-31T14:05:14Z","title":"Quantization Meets OOD: Generalizable Quantization-aware Training from a Flatness Perspective","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:23.842748Z"},"links":{"cited_paper":"/paper/1902.08153","citing_paper":"/paper/2509.00859"},"observation_digest":"sha256:b057487e5893e01d6a54ff96a1e2f4f0e2d6c4b6a205baefc861a63a5e5bf843","observation_id":"126dd45d-9b93-4862-a571-8cf62f5229ee","resolution":{"observed_at":"2026-08-05T13:12:23.842748Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1902.08153","last_updated":"2020-05-07T03:30:49Z","snapshot_observed_at":"2026-08-07T23:40:04.424513Z","submitted_at":"2019-02-21T17:31:32Z","title":"Learned Step Size Quantization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.08153","snapshot_observed_at":"2026-08-05T13:12:14.403164Z","title":"Learned step size quantization","venue":null,"work_id":null,"year":1902},"citing_paper":{"arxiv_id":"2509.00914","last_updated":"2025-08-31T15:57:13Z","snapshot_observed_at":"2026-08-09T09:56:48.034006Z","submitted_at":"2025-08-31T15:57:13Z","title":"TinyMusician: On-Device Music Generation with Knowledge Distillation and Mixed Precision Quantization","version":1},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-05T13:12:14.403164Z"},"links":{"cited_paper":"/paper/1902.08153","citing_paper":"/paper/2509.00914"},"observation_digest":"sha256:b56b7f75d8c9ddc31ba67dffc549f3b92a564f5d57fc279e6e895df1371c2e11","observation_id":"f612e707-561c-4ce3-94d2-17ee752e2e2e","resolution":{"observed_at":"2026-08-05T13:12:14.403164Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1902.08153","last_updated":"2020-05-07T03:30:49Z","snapshot_observed_at":"2026-08-07T23:40:04.424513Z","submitted_at":"2019-02-21T17:31:32Z","title":"Learned Step Size Quantization","version":3},"cited_work":{"arxiv_id":"1902.08153","doi":"10.48550/arxiv.1902.08153","metadata_source":"arxiv_reference","pith_arxiv_id":"1902.08153","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"K., McKinstry, J","venue":"arXiv (Cornell University)","work_id":"87dd0e40-bfbe-4de6-8d30-65c5a87d97dd","year":1902},"citing_paper":{"arxiv_id":"2509.03472","last_updated":"2026-04-15T20:18:20Z","snapshot_observed_at":"2026-07-06T22:23:00.681940Z","submitted_at":"2025-09-03T16:51:26Z","title":"DPQuant: Efficient and Differentially-Private Model Training via Dynamic Quantization Scheduling","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-05-18T19:09:04.217591Z"},"links":{"cited_paper":"/paper/1902.08153","citing_paper":"/paper/2509.03472"},"observation_digest":"sha256:7175c5d5a959aa0697e44d8ad345371bcf90a94e0cbd1eb9cdf7ad20e194f2b7","observation_id":"cd70e39b-ba15-4377-b2c1-3dc24d5e704e","resolution":{"observed_at":"2026-05-18T19:11:46.648023Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1902.08153","last_updated":"2020-05-07T03:30:49Z","snapshot_observed_at":"2026-08-07T23:40:04.424513Z","submitted_at":"2019-02-21T17:31:32Z","title":"Learned Step Size Quantization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.08153","snapshot_observed_at":"2026-08-05T10:50:16.862305Z","title":"Learned step size quantization","venue":null,"work_id":null,"year":1902},"citing_paper":{"arxiv_id":"2509.03704","last_updated":"2026-06-25T20:51:47Z","snapshot_observed_at":"2026-08-05T10:50:15.494219Z","submitted_at":"2025-09-03T20:39:03Z","title":"QuantV2X: A Fully Quantized Multi-Agent System for Cooperative Perception","version":2},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-05T10:50:16.862305Z"},"links":{"cited_paper":"/paper/1902.08153","citing_paper":"/paper/2509.03704"},"observation_digest":"sha256:067101be76e07bd11a8e811e3470aa697655fde3ae0ca34386824935b3a9768d","observation_id":"9b2ee982-5da9-4f62-a49b-3e11bbd87699","resolution":{"observed_at":"2026-08-05T10:50:16.862305Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1902.08153","last_updated":"2020-05-07T03:30:49Z","snapshot_observed_at":"2026-08-07T23:40:04.424513Z","submitted_at":"2019-02-21T17:31:32Z","title":"Learned Step Size Quantization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.08153","snapshot_observed_at":"2026-08-04T08:50:45.221727Z","title":null,"venue":null,"work_id":null,"year":1902},"citing_paper":{"arxiv_id":"2510.18784","last_updated":"2026-06-18T13:37:57Z","snapshot_observed_at":"2026-08-09T19:05:45.771678Z","submitted_at":"2025-10-21T16:33:57Z","title":"CAGE: Curvature-Aware Gradient Estimation For Accurate Quantization-Aware Training","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-04T08:50:45.221727Z"},"links":{"cited_paper":"/paper/1902.08153","citing_paper":"/paper/2510.18784"},"observation_digest":"sha256:b3ccd68b9e0374da5a3f702125e1f8c86f461fe9777182d9e655c82c664f88a7","observation_id":"998955bc-b234-451d-960a-ae836362f91a","resolution":{"observed_at":"2026-08-04T08:50:45.221727Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1902.08153","last_updated":"2020-05-07T03:30:49Z","snapshot_observed_at":"2026-08-07T23:40:04.424513Z","submitted_at":"2019-02-21T17:31:32Z","title":"Learned Step Size Quantization","version":3},"cited_work":{"arxiv_id":"1902.08153","doi":"10.48550/arxiv.1902.08153","metadata_source":"arxiv_reference","pith_arxiv_id":"1902.08153","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"K., McKinstry, J","venue":"arXiv (Cornell University)","work_id":"87dd0e40-bfbe-4de6-8d30-65c5a87d97dd","year":1902},"citing_paper":{"arxiv_id":"2604.03957","last_updated":"2026-04-05T04:25:07Z","snapshot_observed_at":"2026-07-06T22:53:01.835843Z","submitted_at":"2026-04-05T04:25:07Z","title":"BWTA: Accurate and Efficient Binarized Transformer by Algorithm-Hardware Co-design","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-05-13T17:26:54.609595Z"},"links":{"cited_paper":"/paper/1902.08153","citing_paper":"/paper/2604.03957"},"observation_digest":"sha256:692c34b83da694b787b6b2645d9fde215ee40729b449f9b36a5cb19526895699","observation_id":"dea28714-5f1f-4ccc-b9e7-446ab3ec1a20","resolution":{"observed_at":"2026-05-13T17:28:02.202298Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1902.08153","last_updated":"2020-05-07T03:30:49Z","snapshot_observed_at":"2026-08-07T23:40:04.424513Z","submitted_at":"2019-02-21T17:31:32Z","title":"Learned Step Size Quantization","version":3},"cited_work":{"arxiv_id":"1902.08153","doi":"10.48550/arxiv.1902.08153","metadata_source":"arxiv_reference","pith_arxiv_id":"1902.08153","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"K., McKinstry, J","venue":"arXiv (Cornell University)","work_id":"87dd0e40-bfbe-4de6-8d30-65c5a87d97dd","year":1902},"citing_paper":{"arxiv_id":"2604.04988","last_updated":"2026-04-05T06:13:47Z","snapshot_observed_at":"2026-07-06T22:53:51.418227Z","submitted_at":"2026-04-05T06:13:47Z","title":"Prune-Quantize-Distill: An Ordered Pipeline for Efficient Neural Network Compression","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-13T17:03:48.689643Z"},"links":{"cited_paper":"/paper/1902.08153","citing_paper":"/paper/2604.04988"},"observation_digest":"sha256:0025817209a42abfea91978c0756cd73e1ffb0e58721d696f9daf479da3e00e9","observation_id":"0153782f-2b55-49d7-902f-5212e6ee5eec","resolution":{"observed_at":"2026-05-13T17:08:01.005812Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1902.08153","last_updated":"2020-05-07T03:30:49Z","snapshot_observed_at":"2026-08-07T23:40:04.424513Z","submitted_at":"2019-02-21T17:31:32Z","title":"Learned Step Size Quantization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.08153","snapshot_observed_at":"2026-07-13T10:56:59.609600Z","title":"Learned step size quantization,","venue":null,"work_id":null,"year":1902},"citing_paper":{"arxiv_id":"2604.04995","last_updated":"2026-04-05T17:45:16Z","snapshot_observed_at":"2026-08-04T15:47:07.524816Z","submitted_at":"2026-04-05T17:45:16Z","title":"Streaming Chain","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-07-13T10:56:59.609600Z"},"links":{"cited_paper":"/paper/1902.08153","citing_paper":"/paper/2604.04995"},"observation_digest":"sha256:b32ee7bf81bda5fde1a0a3de28f5d6e98fa1651a19471d510f388bd738157e55","observation_id":"c81116b7-85bc-4a43-a97a-565e43699293","resolution":{"observed_at":"2026-07-13T10:56:59.609600Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1902.08153","last_updated":"2020-05-07T03:30:49Z","snapshot_observed_at":"2026-08-07T23:40:04.424513Z","submitted_at":"2019-02-21T17:31:32Z","title":"Learned Step Size Quantization","version":3},"cited_work":{"arxiv_id":"1902.08153","doi":"10.48550/arxiv.1902.08153","metadata_source":"arxiv_reference","pith_arxiv_id":"1902.08153","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"K., McKinstry, J","venue":"arXiv (Cornell University)","work_id":"87dd0e40-bfbe-4de6-8d30-65c5a87d97dd","year":1902},"citing_paper":{"arxiv_id":"2604.18556","last_updated":"2026-05-15T09:34:30Z","snapshot_observed_at":"2026-07-06T23:05:21.974248Z","submitted_at":"2026-04-20T17:45:47Z","title":"GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-10T05:29:51.182114Z"},"links":{"cited_paper":"/paper/1902.08153","citing_paper":"/paper/2604.18556"},"observation_digest":"sha256:df4fcbc042c5ed0045364e615ac335bd391678aa1e5f08e4782ac29d7b6c85b4","observation_id":"42685933-42af-4882-96c2-39ca4de5a61d","resolution":{"observed_at":"2026-05-10T05:36:02.318550Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1902.08153","last_updated":"2020-05-07T03:30:49Z","snapshot_observed_at":"2026-08-07T23:40:04.424513Z","submitted_at":"2019-02-21T17:31:32Z","title":"Learned Step Size Quantization","version":3},"cited_work":{"arxiv_id":"1902.08153","doi":"10.48550/arxiv.1902.08153","metadata_source":"arxiv_reference","pith_arxiv_id":"1902.08153","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"K., McKinstry, J","venue":"arXiv (Cornell University)","work_id":"87dd0e40-bfbe-4de6-8d30-65c5a87d97dd","year":1902},"citing_paper":{"arxiv_id":"2604.18556","last_updated":"2026-05-15T09:34:30Z","snapshot_observed_at":"2026-07-06T23:05:21.974248Z","submitted_at":"2026-04-20T17:45:47Z","title":"GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-19T18:01:08.514022Z"},"links":{"cited_paper":"/paper/1902.08153","citing_paper":"/paper/2604.18556"},"observation_digest":"sha256:72b3c7afb073094177ab761745196bceb975a72d8204659d3b6e444c4f462514","observation_id":"c6a48177-ecae-451d-a973-15c12e2ede31","resolution":{"observed_at":"2026-05-19T18:02:42.262146Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1902.08153","last_updated":"2020-05-07T03:30:49Z","snapshot_observed_at":"2026-08-07T23:40:04.424513Z","submitted_at":"2019-02-21T17:31:32Z","title":"Learned Step Size Quantization","version":3},"cited_work":{"arxiv_id":"1902.08153","doi":"10.48550/arxiv.1902.08153","metadata_source":"arxiv_reference","pith_arxiv_id":"1902.08153","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"K., McKinstry, J","venue":"arXiv (Cornell University)","work_id":"87dd0e40-bfbe-4de6-8d30-65c5a87d97dd","year":1902},"citing_paper":{"arxiv_id":"2604.22906","last_updated":"2026-04-24T16:56:53Z","snapshot_observed_at":"2026-08-07T20:25:38.013655Z","submitted_at":"2026-04-24T16:56:53Z","title":"Network Edge Inference for Large Language Models: Principles, Techniques, and Opportunities","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-05-08T09:45:57.201837Z"},"links":{"cited_paper":"/paper/1902.08153","citing_paper":"/paper/2604.22906"},"observation_digest":"sha256:fe610ee0007178e53d28a3934403395886414d33a849ccee58b69e6b3f95506b","observation_id":"b6e4dcc6-8777-4049-a388-7ac1ff043371","resolution":{"observed_at":"2026-05-11T20:16:10.524889Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1902.08153","last_updated":"2020-05-07T03:30:49Z","snapshot_observed_at":"2026-08-07T23:40:04.424513Z","submitted_at":"2019-02-21T17:31:32Z","title":"Learned Step Size Quantization","version":3},"cited_work":{"arxiv_id":"1902.08153","doi":"10.48550/arxiv.1902.08153","metadata_source":"arxiv_reference","pith_arxiv_id":"1902.08153","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"K., McKinstry, J","venue":"arXiv (Cornell University)","work_id":"87dd0e40-bfbe-4de6-8d30-65c5a87d97dd","year":1902},"citing_paper":{"arxiv_id":"2605.01330","last_updated":"2026-05-02T08:49:51Z","snapshot_observed_at":"2026-07-06T23:14:33.653260Z","submitted_at":"2026-05-02T08:49:51Z","title":"Colinearity Decay: Training Quantization-Friendly ViTs with Outlier Decay","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-09T14:24:54.946996Z"},"links":{"cited_paper":"/paper/1902.08153","citing_paper":"/paper/2605.01330"},"observation_digest":"sha256:013bafeeceac9987fb96ae8a442994c1cf8e74df4fd4c1f9629f7c808e69f83b","observation_id":"67e0fdd0-457d-4a87-b0d2-48b67d6c06ad","resolution":{"observed_at":"2026-05-11T16:56:07.915496Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1902.08153","last_updated":"2020-05-07T03:30:49Z","snapshot_observed_at":"2026-08-07T23:40:04.424513Z","submitted_at":"2019-02-21T17:31:32Z","title":"Learned Step Size Quantization","version":3},"cited_work":{"arxiv_id":"1902.08153","doi":"10.48550/arxiv.1902.08153","metadata_source":"arxiv_reference","pith_arxiv_id":"1902.08153","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"K., McKinstry, J","venue":"arXiv (Cornell University)","work_id":"87dd0e40-bfbe-4de6-8d30-65c5a87d97dd","year":1902},"citing_paper":{"arxiv_id":"2605.04738","last_updated":"2026-05-09T08:06:42Z","snapshot_observed_at":"2026-07-06T23:17:28.583202Z","submitted_at":"2026-05-06T10:35:25Z","title":"OSAQ: Outlier Self-Absorption for Accurate Low-bit LLM Quantization","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-08T18:23:14.935801Z"},"links":{"cited_paper":"/paper/1902.08153","citing_paper":"/paper/2605.04738"},"observation_digest":"sha256:6a637b6041d87e809dcfa3cd06c5f35039a4ba9f60860e6d1e5bebcb85dae2d4","observation_id":"32018b6c-027a-49b0-ab6f-4a5177c8507a","resolution":{"observed_at":"2026-05-09T06:30:44.070205Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1902.08153","last_updated":"2020-05-07T03:30:49Z","snapshot_observed_at":"2026-08-07T23:40:04.424513Z","submitted_at":"2019-02-21T17:31:32Z","title":"Learned Step Size Quantization","version":3},"cited_work":{"arxiv_id":"1902.08153","doi":"10.48550/arxiv.1902.08153","metadata_source":"arxiv_reference","pith_arxiv_id":"1902.08153","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"K., McKinstry, J","venue":"arXiv (Cornell University)","work_id":"87dd0e40-bfbe-4de6-8d30-65c5a87d97dd","year":1902},"citing_paper":{"arxiv_id":"2605.04738","last_updated":"2026-05-09T08:06:42Z","snapshot_observed_at":"2026-07-06T23:17:28.583202Z","submitted_at":"2026-05-06T10:35:25Z","title":"OSAQ: Outlier Self-Absorption for Accurate Low-bit LLM Quantization","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-12T02:59:00.997742Z"},"links":{"cited_paper":"/paper/1902.08153","citing_paper":"/paper/2605.04738"},"observation_digest":"sha256:c1541955e32674b6f6379c2cb6241bf1348b952801a394698d495a2167b8c335","observation_id":"df43dc13-4ab7-4605-a063-e0f1984e1f4c","resolution":{"observed_at":"2026-05-12T03:01:18.227436Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1902.08153","last_updated":"2020-05-07T03:30:49Z","snapshot_observed_at":"2026-08-07T23:40:04.424513Z","submitted_at":"2019-02-21T17:31:32Z","title":"Learned Step Size Quantization","version":3},"cited_work":{"arxiv_id":"1902.08153","doi":"10.48550/arxiv.1902.08153","metadata_source":"arxiv_reference","pith_arxiv_id":"1902.08153","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"K., McKinstry, J","venue":"arXiv (Cornell University)","work_id":"87dd0e40-bfbe-4de6-8d30-65c5a87d97dd","year":1902},"citing_paper":{"arxiv_id":"2605.10886","last_updated":"2026-07-09T02:30:06Z","snapshot_observed_at":"2026-07-12T23:17:31.243229Z","submitted_at":"2026-05-11T17:32:29Z","title":"LoKA: Low-precision Kernel Applications for Recommendation Models At Scale","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-05-12T04:33:41.411292Z"},"links":{"cited_paper":"/paper/1902.08153","citing_paper":"/paper/2605.10886"},"observation_digest":"sha256:f65baa8821b7a7650c5f2813e524a857d1329167e83f12ee310f0b58e03ca005","observation_id":"5d7ecf12-a9f5-44a5-915a-50a6b3a33633","resolution":{"observed_at":"2026-05-12T06:06:28.066914Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1902.08153","last_updated":"2020-05-07T03:30:49Z","snapshot_observed_at":"2026-08-07T23:40:04.424513Z","submitted_at":"2019-02-21T17:31:32Z","title":"Learned Step Size Quantization","version":3},"cited_work":{"arxiv_id":"1902.08153","doi":"10.48550/arxiv.1902.08153","metadata_source":"arxiv_reference","pith_arxiv_id":"1902.08153","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"K., McKinstry, J","venue":"arXiv (Cornell University)","work_id":"87dd0e40-bfbe-4de6-8d30-65c5a87d97dd","year":1902},"citing_paper":{"arxiv_id":"2605.10886","last_updated":"2026-07-09T02:30:06Z","snapshot_observed_at":"2026-07-12T23:17:31.243229Z","submitted_at":"2026-05-11T17:32:29Z","title":"LoKA: Low-precision Kernel Applications for Recommendation Models At Scale","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-05-15T04:55:01.973832Z"},"links":{"cited_paper":"/paper/1902.08153","citing_paper":"/paper/2605.10886"},"observation_digest":"sha256:e675fd325ba499d483cb74a8999fa773adc2dab5ac0104653aa0e6a1bbb17312","observation_id":"a7bdc49f-cfb2-44af-aec9-66cc197757f5","resolution":{"observed_at":"2026-05-15T04:59:46.115251Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1902.08153","last_updated":"2020-05-07T03:30:49Z","snapshot_observed_at":"2026-08-07T23:40:04.424513Z","submitted_at":"2019-02-21T17:31:32Z","title":"Learned Step Size Quantization","version":3},"cited_work":{"arxiv_id":"1902.08153","doi":"10.48550/arxiv.1902.08153","metadata_source":"arxiv_reference","pith_arxiv_id":"1902.08153","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"K., McKinstry, J","venue":"arXiv (Cornell University)","work_id":"87dd0e40-bfbe-4de6-8d30-65c5a87d97dd","year":1902},"citing_paper":{"arxiv_id":"2605.16423","last_updated":"2026-05-14T14:55:46Z","snapshot_observed_at":"2026-07-06T23:27:34.514541Z","submitted_at":"2026-05-14T14:55:46Z","title":"Nonlinear Bipolar Compensation: Handling Outliers in Post-Training Quantization","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-20T20:55:10.360775Z"},"links":{"cited_paper":"/paper/1902.08153","citing_paper":"/paper/2605.16423"},"observation_digest":"sha256:ef61776480409b06662d8ec342ff34108498c8c8281a31d2ed9f76417aeb40ce","observation_id":"9157aa84-cdcf-4559-af53-99d65bf9047c","resolution":{"observed_at":"2026-05-20T20:59:01.912985Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1902.08153","last_updated":"2020-05-07T03:30:49Z","snapshot_observed_at":"2026-08-07T23:40:04.424513Z","submitted_at":"2019-02-21T17:31:32Z","title":"Learned Step Size Quantization","version":3},"cited_work":{"arxiv_id":"1902.08153","doi":"10.48550/arxiv.1902.08153","metadata_source":"arxiv_reference","pith_arxiv_id":"1902.08153","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"K., McKinstry, J","venue":"arXiv (Cornell University)","work_id":"87dd0e40-bfbe-4de6-8d30-65c5a87d97dd","year":1902},"citing_paper":{"arxiv_id":"2605.16901","last_updated":"2026-05-16T09:25:23Z","snapshot_observed_at":"2026-07-06T23:27:57.805018Z","submitted_at":"2026-05-16T09:25:23Z","title":"CAR-SAM: Cross-Attention Reconstruction for Post-Training Quantization of the Segment Anything Model","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-19T21:30:10.628872Z"},"links":{"cited_paper":"/paper/1902.08153","citing_paper":"/paper/2605.16901"},"observation_digest":"sha256:d57a2da2b63c3a4f5b02119932008445587dc60371fb6c5befa5ecd0f823af0c","observation_id":"68dcdfb4-530a-43d8-b48e-cb0f73ed7839","resolution":{"observed_at":"2026-05-19T21:32:47.912829Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1902.08153","last_updated":"2020-05-07T03:30:49Z","snapshot_observed_at":"2026-08-07T23:40:04.424513Z","submitted_at":"2019-02-21T17:31:32Z","title":"Learned Step Size Quantization","version":3},"cited_work":{"arxiv_id":"1902.08153","doi":"10.48550/arxiv.1902.08153","metadata_source":"arxiv_reference","pith_arxiv_id":"1902.08153","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"K., McKinstry, J","venue":"arXiv (Cornell University)","work_id":"87dd0e40-bfbe-4de6-8d30-65c5a87d97dd","year":1902},"citing_paper":{"arxiv_id":"2605.17160","last_updated":"2026-08-04T20:55:20Z","snapshot_observed_at":"2026-08-08T23:09:33.143239Z","submitted_at":"2026-05-16T21:19:31Z","title":"When Bits Break Recourse: Counterfactual-Faithful Quantization","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-20T14:43:18.182586Z"},"links":{"cited_paper":"/paper/1902.08153","citing_paper":"/paper/2605.17160"},"observation_digest":"sha256:c7735cd6271676d050d02e4b497d6273b7305895944e124602fcd6fa74ab479a","observation_id":"03739a84-7a2e-490c-b52f-6047627a4e30","resolution":{"observed_at":"2026-05-20T14:43:22.026533Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1902.08153","last_updated":"2020-05-07T03:30:49Z","snapshot_observed_at":"2026-08-07T23:40:04.424513Z","submitted_at":"2019-02-21T17:31:32Z","title":"Learned Step Size Quantization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.08153","snapshot_observed_at":"2026-08-03T02:20:53.370884Z","title":"Esser, Jeffrey L","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2605.17160","last_updated":"2026-08-04T20:55:20Z","snapshot_observed_at":"2026-08-08T23:09:33.143239Z","submitted_at":"2026-05-16T21:19:31Z","title":"When Bits Break Recourse: Counterfactual-Faithful Quantization","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-03T02:20:53.370884Z"},"links":{"cited_paper":"/paper/1902.08153","citing_paper":"/paper/2605.17160"},"observation_digest":"sha256:04fd51b178a71660de71b9f56406b851f55b8538c2ad9d5683f2ecdf217809f7","observation_id":"bb2c1927-2b61-430c-9cb5-1118c699bc1b","resolution":{"observed_at":"2026-08-03T02:20:53.370884Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1902.08153","last_updated":"2020-05-07T03:30:49Z","snapshot_observed_at":"2026-08-07T23:40:04.424513Z","submitted_at":"2019-02-21T17:31:32Z","title":"Learned Step Size Quantization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.08153","snapshot_observed_at":"2026-08-04T05:08:29.585923Z","title":"Esser, Jeffrey L","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2605.17160","last_updated":"2026-08-04T20:55:20Z","snapshot_observed_at":"2026-08-08T23:09:33.143239Z","submitted_at":"2026-05-16T21:19:31Z","title":"When Bits Break Recourse: Counterfactual-Faithful Quantization","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-04T05:08:29.585923Z"},"links":{"cited_paper":"/paper/1902.08153","citing_paper":"/paper/2605.17160"},"observation_digest":"sha256:da4fb1bcaa3c1068fb99839c3f45cdcd36149b144a2e23b3d5584c840cbbc42e","observation_id":"6362ee4d-a4c7-4c58-a066-077ef16e8c3c","resolution":{"observed_at":"2026-08-04T05:08:29.585923Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1902.08153","last_updated":"2020-05-07T03:30:49Z","snapshot_observed_at":"2026-08-07T23:40:04.424513Z","submitted_at":"2019-02-21T17:31:32Z","title":"Learned Step Size Quantization","version":3},"cited_work":{"arxiv_id":"1902.08153","doi":"10.48550/arxiv.1902.08153","metadata_source":"arxiv_reference","pith_arxiv_id":"1902.08153","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"K., McKinstry, J","venue":"arXiv (Cornell University)","work_id":"87dd0e40-bfbe-4de6-8d30-65c5a87d97dd","year":1902},"citing_paper":{"arxiv_id":"2605.20706","last_updated":"2026-05-20T05:05:10Z","snapshot_observed_at":"2026-08-02T06:31:23.188753Z","submitted_at":"2026-05-20T05:05:10Z","title":"Llamas on the Web: Memory-Efficient, Performance-Portable, and Multi-Precision LLM Inference with WebGPU","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-21T02:52:40.923230Z"},"links":{"cited_paper":"/paper/1902.08153","citing_paper":"/paper/2605.20706"},"observation_digest":"sha256:12ba0e99f30b1077e8c98595667198dd3d44b317dcb00230fdc9072b99989fc3","observation_id":"fbee18d4-50ba-4103-baef-d2f39146fd17","resolution":{"observed_at":"2026-05-21T02:53:55.320139Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1902.08153","last_updated":"2020-05-07T03:30:49Z","snapshot_observed_at":"2026-08-07T23:40:04.424513Z","submitted_at":"2019-02-21T17:31:32Z","title":"Learned Step Size Quantization","version":3},"cited_work":{"arxiv_id":"1902.08153","doi":"10.48550/arxiv.1902.08153","metadata_source":"arxiv_reference","pith_arxiv_id":"1902.08153","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"K., McKinstry, J","venue":"arXiv (Cornell University)","work_id":"87dd0e40-bfbe-4de6-8d30-65c5a87d97dd","year":1902},"citing_paper":{"arxiv_id":"2605.24754","last_updated":"2026-05-23T22:09:34Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-05-23T22:09:34Z","title":"Motion-Compensated Weight Compression","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-06-30T12:58:27.637822Z"},"links":{"cited_paper":"/paper/1902.08153","citing_paper":"/paper/2605.24754"},"observation_digest":"sha256:ec9e350268ca9e52c7254c8aa728dc2eb3b11de68e1a98799ab068be4202513b","observation_id":"a2c54c39-4a01-4aaa-adfb-858f6b5abfa7","resolution":{"observed_at":"2026-06-30T13:04:40.387726Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1902.08153","last_updated":"2020-05-07T03:30:49Z","snapshot_observed_at":"2026-08-07T23:40:04.424513Z","submitted_at":"2019-02-21T17:31:32Z","title":"Learned Step Size Quantization","version":3},"cited_work":{"arxiv_id":"1902.08153","doi":"10.48550/arxiv.1902.08153","metadata_source":"arxiv_reference","pith_arxiv_id":"1902.08153","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"K., McKinstry, J","venue":"arXiv (Cornell University)","work_id":"87dd0e40-bfbe-4de6-8d30-65c5a87d97dd","year":1902},"citing_paper":{"arxiv_id":"2606.09864","last_updated":"2026-06-01T02:02:20Z","snapshot_observed_at":"2026-08-03T01:43:21.917246Z","submitted_at":"2026-06-01T02:02:20Z","title":"Alignment Collapse Under KV Cache Quantization: Diagnosis and Mitigation","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-06-28T15:37:34.129339Z"},"links":{"cited_paper":"/paper/1902.08153","citing_paper":"/paper/2606.09864"},"observation_digest":"sha256:03129c97381e0227f5e9607976ffcf1ba10f58c863c324ee73dfab5a9d60ba67","observation_id":"80f51098-826e-4b32-9554-39700d4458cd","resolution":{"observed_at":"2026-07-01T22:16:16.072130Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1902.08153","last_updated":"2020-05-07T03:30:49Z","snapshot_observed_at":"2026-08-07T23:40:04.424513Z","submitted_at":"2019-02-21T17:31:32Z","title":"Learned Step Size Quantization","version":3},"cited_work":{"arxiv_id":"1902.08153","doi":"10.48550/arxiv.1902.08153","metadata_source":"arxiv_reference","pith_arxiv_id":"1902.08153","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"K., McKinstry, J","venue":"arXiv (Cornell University)","work_id":"87dd0e40-bfbe-4de6-8d30-65c5a87d97dd","year":1902},"citing_paper":{"arxiv_id":"2606.25087","last_updated":"2026-06-23T18:48:45Z","snapshot_observed_at":"2026-07-06T23:59:37.533078Z","submitted_at":"2026-06-23T18:48:45Z","title":"Neural Network Quantization by Learning Low-Loss Subspaces","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-06-26T00:05:03.762579Z"},"links":{"cited_paper":"/paper/1902.08153","citing_paper":"/paper/2606.25087"},"observation_digest":"sha256:fd12d39bf4f180782ea082bc3d8c9342fb43af6eb7633a045028f7c7e2c5b7a2","observation_id":"b99cdcb8-ee70-4299-84cb-3efeb6362a89","resolution":{"observed_at":"2026-07-04T16:59:58.458592Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1902.08153","last_updated":"2020-05-07T03:30:49Z","snapshot_observed_at":"2026-08-07T23:40:04.424513Z","submitted_at":"2019-02-21T17:31:32Z","title":"Learned Step Size Quantization","version":3},"cited_work":{"arxiv_id":"1902.08153","doi":"10.48550/arxiv.1902.08153","metadata_source":"arxiv_reference","pith_arxiv_id":"1902.08153","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"K., McKinstry, J","venue":"arXiv (Cornell University)","work_id":"87dd0e40-bfbe-4de6-8d30-65c5a87d97dd","year":1902},"citing_paper":{"arxiv_id":"2606.27759","last_updated":"2026-06-26T06:37:57Z","snapshot_observed_at":"2026-08-08T03:10:33.776132Z","submitted_at":"2026-06-26T06:37:57Z","title":"Layerwise Progressive Freezing: A Training Scaffold for Depth-Scalable Binary Networks","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-06-29T05:08:23.176105Z"},"links":{"cited_paper":"/paper/1902.08153","citing_paper":"/paper/2606.27759"},"observation_digest":"sha256:6168542b58245794c5cb94d690aa0e873c9069e14b4209a46126bd89150ab4f7","observation_id":"039dfd3a-41b3-40b8-862e-476ed7c348e9","resolution":{"observed_at":"2026-06-29T05:13:06.464635Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1902.08153","last_updated":"2020-05-07T03:30:49Z","snapshot_observed_at":"2026-08-07T23:40:04.424513Z","submitted_at":"2019-02-21T17:31:32Z","title":"Learned Step Size Quantization","version":3},"cited_work":{"arxiv_id":"1902.08153","doi":"10.48550/arxiv.1902.08153","metadata_source":"arxiv_reference","pith_arxiv_id":"1902.08153","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"K., McKinstry, J","venue":"arXiv (Cornell University)","work_id":"87dd0e40-bfbe-4de6-8d30-65c5a87d97dd","year":1902},"citing_paper":{"arxiv_id":"2606.31456","last_updated":"2026-07-16T05:27:27Z","snapshot_observed_at":"2026-08-02T09:19:30.228773Z","submitted_at":"2026-06-30T10:29:15Z","title":"Zero-Shot Quantization for Object Detectors using Off-the-Shelf Generative Models","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-07-01T06:47:12.273391Z"},"links":{"cited_paper":"/paper/1902.08153","citing_paper":"/paper/2606.31456"},"observation_digest":"sha256:54dc25bf12ffc547da052bc8a64f68b52db8df6cb3de77b9713f181779d299d7","observation_id":"5af4991f-3a88-4d89-92cd-e4d247ad68a1","resolution":{"observed_at":"2026-07-01T09:05:37.356845Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1902.08153","last_updated":"2020-05-07T03:30:49Z","snapshot_observed_at":"2026-08-07T23:40:04.424513Z","submitted_at":"2019-02-21T17:31:32Z","title":"Learned Step Size Quantization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.08153","snapshot_observed_at":"2026-08-02T09:19:34.334377Z","title":"arXiv preprint arXiv:1902.08153 (2019)","venue":null,"work_id":null,"year":1902},"citing_paper":{"arxiv_id":"2606.31456","last_updated":"2026-07-16T05:27:27Z","snapshot_observed_at":"2026-08-02T09:19:30.228773Z","submitted_at":"2026-06-30T10:29:15Z","title":"Zero-Shot Quantization for Object Detectors using Off-the-Shelf Generative Models","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-02T09:19:34.334377Z"},"links":{"cited_paper":"/paper/1902.08153","citing_paper":"/paper/2606.31456"},"observation_digest":"sha256:8e04d666f5b7950e13941b0eba967e817ee75955d6c0972a850cb9e2b2b4f07a","observation_id":"309faec2-c6d1-4dcb-ab1b-a5cd1144c729","resolution":{"observed_at":"2026-08-02T09:19:34.334377Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1902.08153","last_updated":"2020-05-07T03:30:49Z","snapshot_observed_at":"2026-08-07T23:40:04.424513Z","submitted_at":"2019-02-21T17:31:32Z","title":"Learned Step Size Quantization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.08153","snapshot_observed_at":"2026-08-02T03:32:51.696835Z","title":"Learned step size quantization,","venue":null,"work_id":null,"year":1902},"citing_paper":{"arxiv_id":"2607.14181","last_updated":"2026-07-15T14:05:33Z","snapshot_observed_at":"2026-08-08T17:47:34.090198Z","submitted_at":"2026-07-15T14:05:33Z","title":"Quantize with Confidence? An Empirical Study of Quantization for Code Generation","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-02T03:32:51.696835Z"},"links":{"cited_paper":"/paper/1902.08153","citing_paper":"/paper/2607.14181"},"observation_digest":"sha256:39cc662aecda3c5d03dd910fcda2acfad187df709823ac2adea77165877cfda6","observation_id":"f58b4862-c954-487e-bd95-a35a52059fd7","resolution":{"observed_at":"2026-08-02T03:32:51.696835Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1902.08153","last_updated":"2020-05-07T03:30:49Z","snapshot_observed_at":"2026-08-07T23:40:04.424513Z","submitted_at":"2019-02-21T17:31:32Z","title":"Learned Step Size Quantization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.08153","snapshot_observed_at":"2026-08-01T10:41:37.432929Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.20153","last_updated":"2026-07-22T13:52:42Z","snapshot_observed_at":"2026-08-10T01:02:08.155438Z","submitted_at":"2026-07-22T13:52:42Z","title":"Local Stability and Gaussian Smoothing of Quantized Neural Networks","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-01T10:41:37.432929Z"},"links":{"cited_paper":"/paper/1902.08153","citing_paper":"/paper/2607.20153"},"observation_digest":"sha256:497ff3bf71a20f67c3912664661d8e928563ec7d95e3142e7331781d56e30ef6","observation_id":"4cf1a8e3-2252-4309-8c31-797433b000cb","resolution":{"observed_at":"2026-08-01T10:41:37.432929Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1902.08153","last_updated":"2020-05-07T03:30:49Z","snapshot_observed_at":"2026-08-07T23:40:04.424513Z","submitted_at":"2019-02-21T17:31:32Z","title":"Learned Step Size Quantization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.08153","snapshot_observed_at":"2026-08-06T00:40:38.734813Z","title":"Esser, Jeffrey L","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2608.01034","last_updated":"2026-08-04T01:57:33Z","snapshot_observed_at":"2026-08-10T07:53:12.692148Z","submitted_at":"2026-08-02T06:43:25Z","title":"Opt.Gear Technical Report","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T00:40:38.734813Z"},"links":{"cited_paper":"/paper/1902.08153","citing_paper":"/paper/2608.01034"},"observation_digest":"sha256:0bcd3da0a55c919f0971a4bf7a43ca2e5e5a3100ac3a3a44c7a84ea993c05d86","observation_id":"a211fb2b-3085-45b4-8bf1-583eef5a886f","resolution":{"observed_at":"2026-08-06T00:40:38.734813Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/1902.08153/citation-record","integrity":"/paper/1902.08153/integrity","json":"/paper/1902.08153/citation-record.json","paper":"/paper/1902.08153"},"outbound":[],"paper":{"arxiv_id":"1902.08153","last_updated":"2020-05-07T03:30:49Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T23:40:04.424513Z","submitted_at":"2019-02-21T17:31:32Z","title":"Learned Step Size Quantization"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 58 inbound Pith citation observations for arXiv:1902.08153."}