{"as_of":"2026-08-18T08:51:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:60da0015e9be58c6770eea4a779ced287639fa310bd29dfd91feb94bfbc4fffe","coverage":[{"denominator":39,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":39,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T04:18:09.241612Z","state":"measured"},{"denominator":41,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":41,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-02T21:53:20.211127Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-10T11:30:18.609532Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2506.11431","last_updated":"2025-06-13T03:08:18Z","snapshot_observed_at":"2026-08-17T14:32:20.188230Z","submitted_at":"2025-06-13T03:08:18Z","title":"TruncQuant: Truncation-Ready Quantization for DNNs with Flexible Weight Bit Precision","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.11431","snapshot_observed_at":"2026-08-02T21:53:20.211127Z","title":"C., Jeon, K","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.20191","last_updated":"2026-05-25T16:17:59Z","snapshot_observed_at":"2026-08-15T08:45:42.070449Z","submitted_at":"2026-02-21T21:11:08Z","title":"MoBiQuant: Mixture-of-Bits Quantization for Token-Adaptive Any-Precision LLM","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-02T21:53:20.211127Z"},"links":{"cited_paper":"/paper/2506.11431","citing_paper":"/paper/2602.20191"},"observation_digest":"sha256:b73390c6e472493e55aca9593663afc02547030aeece1a3cc2480946396a77ec","observation_id":"79cde160-0886-48e4-bcac-3135eb5ff04c","resolution":{"observed_at":"2026-08-02T21:53:20.211127Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.11431","last_updated":"2025-06-13T03:08:18Z","snapshot_observed_at":"2026-08-17T14:32:20.188230Z","submitted_at":"2025-06-13T03:08:18Z","title":"TruncQuant: Truncation-Ready Quantization for DNNs with Flexible Weight Bit Precision","version":1},"cited_work":{"arxiv_id":"2506.11431","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2506.11431","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"0b276982-589a-4881-a482-b0d24dee9664","year":2025},"citing_paper":{"arxiv_id":"2604.14626","last_updated":"2026-04-23T01:19:26Z","snapshot_observed_at":"2026-08-13T05:36:02.355780Z","submitted_at":"2026-04-16T05:12:51Z","title":"ELMoE-3D: Leveraging Intrinsic Elasticity of MoE for Hybrid-Bonding-Enabled Self-Speculative Decoding in On-Premises Serving","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-05-10T11:28:26.169161Z"},"links":{"cited_paper":"/paper/2506.11431","citing_paper":"/paper/2604.14626"},"observation_digest":"sha256:1133e69bfce42da37bc71109ba398fb9cde1899598e5a1003f76ce7b22cb4327","observation_id":"16f7baf3-70d3-48b2-8da9-70652c4fd8c3","resolution":{"observed_at":"2026-05-10T11:30:18.611449Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2506.11431/citation-record","integrity":"/paper/2506.11431/integrity","json":"/paper/2506.11431/citation-record.json","paper":"/paper/2506.11431"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T04:18:09.616170Z","title":"Dory: Automatic end-to-end deployment of real-world dnns on low-cost iot mcus,","venue":null,"work_id":"0c8fafe0-e014-468e-ba89-35b4125b44f6","year":2021},"citing_paper":{"arxiv_id":"2506.11431","last_updated":"2025-06-13T03:08:18Z","snapshot_observed_at":"2026-08-17T14:32:20.188230Z","submitted_at":"2025-06-13T03:08:18Z","title":"TruncQuant: Truncation-Ready Quantization for DNNs with Flexible Weight Bit Precision","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T04:18:09.133723Z"},"links":{"citing_paper":"/paper/2506.11431"},"observation_digest":"sha256:9df576afdfdd8a6f007d00f03611c945f0fe4f380f3779b817f88922ca07bb61","observation_id":"009e068a-e6ee-4451-b549-8b5281906e30","resolution":{"observed_at":"2026-08-07T04:18:09.619750Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T04:18:09.137281Z","title":"Quantization networks,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.11431","last_updated":"2025-06-13T03:08:18Z","snapshot_observed_at":"2026-08-17T14:32:20.188230Z","submitted_at":"2025-06-13T03:08:18Z","title":"TruncQuant: Truncation-Ready Quantization for DNNs with Flexible Weight Bit Precision","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T04:18:09.137281Z"},"links":{"citing_paper":"/paper/2506.11431"},"observation_digest":"sha256:fd3db7a7bde58d733ef00c3f12be67c1cec66f3a0b19e89ee49e4f458c2eb640","observation_id":"c412955f-981d-4708-8289-9b1f03fbe8eb","resolution":{"observed_at":"2026-08-07T04:18:09.137281Z","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":"2026-08-07T04:18:09.599795Z","title":"Post training 4-bit quantization of convolutional networks for rapid-deployment,","venue":null,"work_id":"bb834b73-3e7c-40f6-b85f-9ae9f6871a4b","year":2019},"citing_paper":{"arxiv_id":"2506.11431","last_updated":"2025-06-13T03:08:18Z","snapshot_observed_at":"2026-08-17T14:32:20.188230Z","submitted_at":"2025-06-13T03:08:18Z","title":"TruncQuant: Truncation-Ready Quantization for DNNs with Flexible Weight Bit Precision","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T04:18:09.140074Z"},"links":{"citing_paper":"/paper/2506.11431"},"observation_digest":"sha256:3205ea2a6304beb15e83350ad9935ba0003c5c108d68e381bdf3f7822c90f0c8","observation_id":"293db58b-fc4d-4683-beba-d4052bee30c5","resolution":{"observed_at":"2026-08-07T04:18:09.603640Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T04:18:09.589502Z","title":"Up or down? adaptive rounding for post-training quantization,","venue":null,"work_id":"964cedea-1323-48fe-8559-5fd3c46d0a57","year":2020},"citing_paper":{"arxiv_id":"2506.11431","last_updated":"2025-06-13T03:08:18Z","snapshot_observed_at":"2026-08-17T14:32:20.188230Z","submitted_at":"2025-06-13T03:08:18Z","title":"TruncQuant: Truncation-Ready Quantization for DNNs with Flexible Weight Bit Precision","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T04:18:09.143266Z"},"links":{"citing_paper":"/paper/2506.11431"},"observation_digest":"sha256:d32bffb4f46f251580b175b1c0ac57b043d80b8933b1e1904bed40b23c326047","observation_id":"12b79af7-02bf-474d-8f5d-6a7c418d90f7","resolution":{"observed_at":"2026-08-07T04:18:09.593184Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2102.05426","last_updated":"2021-07-25T09:34:39Z","snapshot_observed_at":"2026-08-16T18:46:30.310486Z","submitted_at":"2021-02-10T13:46:16Z","title":"BRECQ: Pushing the Limit of Post-Training Quantization by Block Reconstruction","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2102.05426","snapshot_observed_at":"2026-08-07T04:18:09.146393Z","title":"Brecq: Pushing the limit of post-training quantization by block reconstruction,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.11431","last_updated":"2025-06-13T03:08:18Z","snapshot_observed_at":"2026-08-17T14:32:20.188230Z","submitted_at":"2025-06-13T03:08:18Z","title":"TruncQuant: Truncation-Ready Quantization for DNNs with Flexible Weight Bit Precision","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T04:18:09.146393Z"},"links":{"cited_paper":"/paper/2102.05426","citing_paper":"/paper/2506.11431"},"observation_digest":"sha256:a7ba3e009596325c297745570eb8fe68b34973a4ce03a47491d6a30cc0204a56","observation_id":"c0af4064-7763-49bd-a0dc-a212fd890eb2","resolution":{"observed_at":"2026-08-07T04:18:09.146393Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1812.08928","last_updated":"2018-12-21T03:36:48Z","snapshot_observed_at":"2026-08-14T17:40:05.995607Z","submitted_at":"2018-12-21T03:36:48Z","title":"Slimmable Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1812.08928","snapshot_observed_at":"2026-08-07T04:18:09.149665Z","title":"Slimmable neural networks,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.11431","last_updated":"2025-06-13T03:08:18Z","snapshot_observed_at":"2026-08-17T14:32:20.188230Z","submitted_at":"2025-06-13T03:08:18Z","title":"TruncQuant: Truncation-Ready Quantization for DNNs with Flexible Weight Bit Precision","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T04:18:09.149665Z"},"links":{"cited_paper":"/paper/1812.08928","citing_paper":"/paper/2506.11431"},"observation_digest":"sha256:cdcdbe586cb70a41c65cc717e78fa9cd3eb422f35c4e61e77cd5a55d19006c07","observation_id":"708b18e9-3c20-4499-89a8-c51c6f1a3ed5","resolution":{"observed_at":"2026-08-07T04:18:09.149665Z","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":"2026-08-07T04:18:09.153209Z","title":"Universally slimmable networks and improved training techniques,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.11431","last_updated":"2025-06-13T03:08:18Z","snapshot_observed_at":"2026-08-17T14:32:20.188230Z","submitted_at":"2025-06-13T03:08:18Z","title":"TruncQuant: Truncation-Ready Quantization for DNNs with Flexible Weight Bit Precision","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T04:18:09.153209Z"},"links":{"citing_paper":"/paper/2506.11431"},"observation_digest":"sha256:725d21043c20a006c0cf5ed3b7679405d100baef2a4be71fd8f9b4143ed5003a","observation_id":"0c7d70f5-063f-40ca-9950-038764374171","resolution":{"observed_at":"2026-08-07T04:18:09.153209Z","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":"2026-08-07T04:18:09.155920Z","title":"Efficientnet: Rethinking model scaling for con- volutional neural networks,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.11431","last_updated":"2025-06-13T03:08:18Z","snapshot_observed_at":"2026-08-17T14:32:20.188230Z","submitted_at":"2025-06-13T03:08:18Z","title":"TruncQuant: Truncation-Ready Quantization for DNNs with Flexible Weight Bit Precision","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T04:18:09.155920Z"},"links":{"citing_paper":"/paper/2506.11431"},"observation_digest":"sha256:69b7af9c6f4fc698b81e84c1f0ff9227fd21d1ce7ccd083e9d4c9bcd2afbc0f8","observation_id":"9c598bbb-7478-48e6-8778-bbe945903b5d","resolution":{"observed_at":"2026-08-07T04:18:09.155920Z","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":"2026-08-07T04:18:09.565915Z","title":"BranchyNet: Fast inference via early exiting from deep neural networks,","venue":null,"work_id":"f9bfa24d-2092-41f4-a674-b6ff368737ed","year":2016},"citing_paper":{"arxiv_id":"2506.11431","last_updated":"2025-06-13T03:08:18Z","snapshot_observed_at":"2026-08-17T14:32:20.188230Z","submitted_at":"2025-06-13T03:08:18Z","title":"TruncQuant: Truncation-Ready Quantization for DNNs with Flexible Weight Bit Precision","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T04:18:09.158648Z"},"links":{"citing_paper":"/paper/2506.11431"},"observation_digest":"sha256:fb279bd420364ed512d7674177fd3e319a27a29d7dad69f44b48b0420b4283f2","observation_id":"4d054e4a-d393-486c-a47e-e858b689fcea","resolution":{"observed_at":"2026-08-07T04:18:09.570172Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T04:18:09.554608Z","title":"Adaptive inference through early-exit networks: Design, challenges and directions,","venue":null,"work_id":"0c9ce326-b2e1-4e7e-9df4-6f797f21e665","year":2021},"citing_paper":{"arxiv_id":"2506.11431","last_updated":"2025-06-13T03:08:18Z","snapshot_observed_at":"2026-08-17T14:32:20.188230Z","submitted_at":"2025-06-13T03:08:18Z","title":"TruncQuant: Truncation-Ready Quantization for DNNs with Flexible Weight Bit Precision","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T04:18:09.161226Z"},"links":{"citing_paper":"/paper/2506.11431"},"observation_digest":"sha256:1aeb7e9b936fbfec84e96c3249425de070aa1b2819038eee258444191eda425a","observation_id":"a9515d5b-6285-4a4a-a381-8333eecc97f8","resolution":{"observed_at":"2026-08-07T04:18:09.559325Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T04:18:09.543762Z","title":"Review and analysis of variable bit-precision mac microarchi- tectures for energy-efficient ai computation,","venue":null,"work_id":"d33c9566-6189-410d-a893-ffdcaf7b6ad6","year":2022},"citing_paper":{"arxiv_id":"2506.11431","last_updated":"2025-06-13T03:08:18Z","snapshot_observed_at":"2026-08-17T14:32:20.188230Z","submitted_at":"2025-06-13T03:08:18Z","title":"TruncQuant: Truncation-Ready Quantization for DNNs with Flexible Weight Bit Precision","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T04:18:09.163832Z"},"links":{"citing_paper":"/paper/2506.11431"},"observation_digest":"sha256:f12a4f133a8e122a290804a587a27e421e265e230a8f45e2fc165d3e2b4b000b","observation_id":"d695a3d8-ea7e-415f-81bd-b1229ce219d1","resolution":{"observed_at":"2026-08-07T04:18:09.547451Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T04:18:09.533040Z","title":"Review and bench- marking of precision-scalable multiply-accumulate unit architectures for embedded neural-network processing,","venue":null,"work_id":"2ccf792b-bcb5-4c6e-a6e9-11049ae0d5a2","year":2019},"citing_paper":{"arxiv_id":"2506.11431","last_updated":"2025-06-13T03:08:18Z","snapshot_observed_at":"2026-08-17T14:32:20.188230Z","submitted_at":"2025-06-13T03:08:18Z","title":"TruncQuant: Truncation-Ready Quantization for DNNs with Flexible Weight Bit Precision","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T04:18:09.166734Z"},"links":{"citing_paper":"/paper/2506.11431"},"observation_digest":"sha256:0b46ff2f4e11981d132ceef27ae8734e1de55f6f3daaac9ecf576131cb35f36d","observation_id":"bc9c030a-df58-4451-9f69-3ce26fda9247","resolution":{"observed_at":"2026-08-07T04:18:09.536672Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T04:18:09.522416Z","title":"Bit fusion: Bit-level dynamically composable architecture for accelerating deep neural network,","venue":null,"work_id":"5774a33e-c60f-42c1-a6af-e2e82ceb8ea8","year":2018},"citing_paper":{"arxiv_id":"2506.11431","last_updated":"2025-06-13T03:08:18Z","snapshot_observed_at":"2026-08-17T14:32:20.188230Z","submitted_at":"2025-06-13T03:08:18Z","title":"TruncQuant: Truncation-Ready Quantization for DNNs with Flexible Weight Bit Precision","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T04:18:09.169286Z"},"links":{"citing_paper":"/paper/2506.11431"},"observation_digest":"sha256:4f8ad41a73fef83c28bff4b09ffb42d5b26ddbb2d4c98423b0cb0028cf1caf14","observation_id":"11d34c85-6ec6-4c2a-8aac-7af75f069184","resolution":{"observed_at":"2026-08-07T04:18:09.525937Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T04:18:09.512067Z","title":"14.5 en- vision: A 0.26-to-10tops/w subword-parallel dynamic-voltage-accuracy- frequency-scalable convolutional neural network processor in 28nm fdsoi,","venue":null,"work_id":"3f59c9f6-d454-405c-96c8-6fd3d6bb5cca","year":2017},"citing_paper":{"arxiv_id":"2506.11431","last_updated":"2025-06-13T03:08:18Z","snapshot_observed_at":"2026-08-17T14:32:20.188230Z","submitted_at":"2025-06-13T03:08:18Z","title":"TruncQuant: Truncation-Ready Quantization for DNNs with Flexible Weight Bit Precision","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T04:18:09.171794Z"},"links":{"citing_paper":"/paper/2506.11431"},"observation_digest":"sha256:ddbaa98da515e19ec381cbf454db79805933e939019c160d9f781199be8e0430","observation_id":"6658da27-9c92-4dc0-b91f-ad7127843c3f","resolution":{"observed_at":"2026-08-07T04:18:09.515767Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T04:18:09.500815Z","title":"Bitblade: Area and energy- efficient precision-scalable neural network accelerator with bitwise summation,","venue":null,"work_id":"3febc2fb-b971-4a5e-8a1b-c132fcc69df7","year":2019},"citing_paper":{"arxiv_id":"2506.11431","last_updated":"2025-06-13T03:08:18Z","snapshot_observed_at":"2026-08-17T14:32:20.188230Z","submitted_at":"2025-06-13T03:08:18Z","title":"TruncQuant: Truncation-Ready Quantization for DNNs with Flexible Weight Bit Precision","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T04:18:09.174225Z"},"links":{"citing_paper":"/paper/2506.11431"},"observation_digest":"sha256:a06ce26b6146edd64d7e1aeac3b9eba5a293b8991c65df5fa9107c4a60deaa37","observation_id":"c514425f-2a2b-408d-bfc8-f9a40e3ac869","resolution":{"observed_at":"2026-08-07T04:18:09.504664Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2411.18065","last_updated":"2025-06-04T01:25:53Z","snapshot_observed_at":"2026-08-18T00:56:41.084253Z","submitted_at":"2024-11-27T05:16:26Z","title":"FlexiBit: Fully Flexible Precision Bit-parallel Accelerator Architecture for Arbitrary Mixed Precision AI","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.18065","snapshot_observed_at":"2026-08-07T04:18:09.176823Z","title":"Flexibit: Fully flexible precision bit-parallel accelerator architecture for arbitrary mixed precision ai,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.11431","last_updated":"2025-06-13T03:08:18Z","snapshot_observed_at":"2026-08-17T14:32:20.188230Z","submitted_at":"2025-06-13T03:08:18Z","title":"TruncQuant: Truncation-Ready Quantization for DNNs with Flexible Weight Bit Precision","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T04:18:09.176823Z"},"links":{"cited_paper":"/paper/2411.18065","citing_paper":"/paper/2506.11431"},"observation_digest":"sha256:85a1b097cda0d1d379806ec2862fb17a3bbce1e3e211e6343da32579ded86b70","observation_id":"236c6347-cb0a-4dcb-be34-6043129a8d1b","resolution":{"observed_at":"2026-08-07T04:18:09.176823Z","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":"2026-08-07T04:18:09.490133Z","title":"Eq-net: Elastic quanti- zation neural networks,","venue":null,"work_id":"ebe3272f-09f8-4eb1-ad61-8c1a2d0f73e3","year":2023},"citing_paper":{"arxiv_id":"2506.11431","last_updated":"2025-06-13T03:08:18Z","snapshot_observed_at":"2026-08-17T14:32:20.188230Z","submitted_at":"2025-06-13T03:08:18Z","title":"TruncQuant: Truncation-Ready Quantization for DNNs with Flexible Weight Bit Precision","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T04:18:09.180139Z"},"links":{"citing_paper":"/paper/2506.11431"},"observation_digest":"sha256:690ef21cab33402ba0ea9865c2c0ef83955768776c2c32e23b50eed9813f1eb1","observation_id":"ec638b13-6959-404a-ab7f-efa21b503cd9","resolution":{"observed_at":"2026-08-07T04:18:09.493717Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T04:18:09.480363Z","title":"Robust quantization: One model to rule them all,","venue":null,"work_id":"1790fd5e-c0ac-44de-999a-b68d0b415a99","year":2020},"citing_paper":{"arxiv_id":"2506.11431","last_updated":"2025-06-13T03:08:18Z","snapshot_observed_at":"2026-08-17T14:32:20.188230Z","submitted_at":"2025-06-13T03:08:18Z","title":"TruncQuant: Truncation-Ready Quantization for DNNs with Flexible Weight Bit Precision","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T04:18:09.182848Z"},"links":{"citing_paper":"/paper/2506.11431"},"observation_digest":"sha256:74d2d370d1f088485bebe9f75b5a44622154b8b5c26a5ae37d2ff3034a6d368f","observation_id":"3322023e-6574-4cc8-aaed-388d9ae8e31c","resolution":{"observed_at":"2026-08-07T04:18:09.483799Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T04:18:09.468499Z","title":"Multiquant: Training once for multi-bit quantization of neural networks","venue":null,"work_id":"72f8e698-fe66-4f26-b9e8-44fe50e5343e","year":2022},"citing_paper":{"arxiv_id":"2506.11431","last_updated":"2025-06-13T03:08:18Z","snapshot_observed_at":"2026-08-17T14:32:20.188230Z","submitted_at":"2025-06-13T03:08:18Z","title":"TruncQuant: Truncation-Ready Quantization for DNNs with Flexible Weight Bit Precision","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T04:18:09.185520Z"},"links":{"citing_paper":"/paper/2506.11431"},"observation_digest":"sha256:2e9f8da1f9326534d176de66ae51608576aa7d9ef871c1b7e0251b719a9000e3","observation_id":"0c0c90fc-570c-4a23-b9a9-d21ef2481861","resolution":{"observed_at":"2026-08-07T04:18:09.473005Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.08117","last_updated":"2024-06-02T08:30:21Z","snapshot_observed_at":"2026-08-16T19:20:20.069507Z","submitted_at":"2023-05-14T10:17:09Z","title":"MBQuant: A Novel Multi-Branch Topology Method for Arbitrary Bit-width Network Quantization","version":2},"cited_work":{"arxiv_id":"2305.08117","doi":null,"metadata_source":"pith","pith_arxiv_id":"2305.08117","snapshot_observed_at":"2026-08-07T04:18:09.310004Z","title":"MBQuant: A Novel Multi-Branch Topology Method for Arbitrary Bit-width Network Quantization","venue":"cs.CV","work_id":"84f20d24-0760-4053-8961-a258c00521fd","year":2023},"citing_paper":{"arxiv_id":"2506.11431","last_updated":"2025-06-13T03:08:18Z","snapshot_observed_at":"2026-08-17T14:32:20.188230Z","submitted_at":"2025-06-13T03:08:18Z","title":"TruncQuant: Truncation-Ready Quantization for DNNs with Flexible Weight Bit Precision","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T04:18:09.188613Z"},"links":{"cited_paper":"/paper/2305.08117","citing_paper":"/paper/2506.11431"},"observation_digest":"sha256:b75b59feff7ef0ef53e1c9ef4fa758e02855ab2d379a77d92ee09228dea38363","observation_id":"d29c4167-84b6-4e85-93e2-8e83e223750f","resolution":{"observed_at":"2026-08-07T04:18:09.315344Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T04:18:09.456745Z","title":"FlashAttention: Fast and memory-efficient exact attention with IO-awareness,","venue":null,"work_id":"f7a2ad74-d6c7-41e6-b323-cbfbf0194195","year":2022},"citing_paper":{"arxiv_id":"2506.11431","last_updated":"2025-06-13T03:08:18Z","snapshot_observed_at":"2026-08-17T14:32:20.188230Z","submitted_at":"2025-06-13T03:08:18Z","title":"TruncQuant: Truncation-Ready Quantization for DNNs with Flexible Weight Bit Precision","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T04:18:09.191328Z"},"links":{"citing_paper":"/paper/2506.11431"},"observation_digest":"sha256:a085d7cf36827e2af9d3a6ecdfca0f8ebeef65894a4c268910e0e6211ed46b5c","observation_id":"1fdfce46-69d7-4bf6-865c-dc59015834b5","resolution":{"observed_at":"2026-08-07T04:18:09.461375Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T04:18:09.446490Z","title":"Any- precision deep neural networks,","venue":null,"work_id":"d932d6a9-ad5b-4405-a1b0-424e68a83f3e","year":2021},"citing_paper":{"arxiv_id":"2506.11431","last_updated":"2025-06-13T03:08:18Z","snapshot_observed_at":"2026-08-17T14:32:20.188230Z","submitted_at":"2025-06-13T03:08:18Z","title":"TruncQuant: Truncation-Ready Quantization for DNNs with Flexible Weight Bit Precision","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T04:18:09.193985Z"},"links":{"citing_paper":"/paper/2506.11431"},"observation_digest":"sha256:45668b829e37de7a4c4a52748b7fe567fa76f5c4ed0dce7927caaaaf230f91d5","observation_id":"88fc9793-0bb3-4ca5-82e5-32409f794e7b","resolution":{"observed_at":"2026-08-07T04:18:09.449966Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T04:18:09.196719Z","title":"A survey of quantization methods for efficient neural network infer- ence,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.11431","last_updated":"2025-06-13T03:08:18Z","snapshot_observed_at":"2026-08-17T14:32:20.188230Z","submitted_at":"2025-06-13T03:08:18Z","title":"TruncQuant: Truncation-Ready Quantization for DNNs with Flexible Weight Bit Precision","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T04:18:09.196719Z"},"links":{"citing_paper":"/paper/2506.11431"},"observation_digest":"sha256:a1553a9fd4a747b76d377c81ae1a5919b83a996cf87427f328af1bf0bac862ba","observation_id":"fafb3ea0-5ba4-4b2d-843a-ee794a5fcb9e","resolution":{"observed_at":"2026-08-07T04:18:09.196719Z","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":"2026-08-07T04:18:09.199506Z","title":"Binary neural networks: A survey,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.11431","last_updated":"2025-06-13T03:08:18Z","snapshot_observed_at":"2026-08-17T14:32:20.188230Z","submitted_at":"2025-06-13T03:08:18Z","title":"TruncQuant: Truncation-Ready Quantization for DNNs with Flexible Weight Bit Precision","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T04:18:09.199506Z"},"links":{"citing_paper":"/paper/2506.11431"},"observation_digest":"sha256:caea67aeea61d1c25fd40b3239e96f3cb50b1121682b78957cab52c4192d95f2","observation_id":"0d7957d6-890d-47ae-a223-a8036f7542ba","resolution":{"observed_at":"2026-08-07T04:18:09.199506Z","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":"2026-08-07T04:18:09.202141Z","title":"Quantization and training of neural networks for efficient integer-arithmetic-only inference,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.11431","last_updated":"2025-06-13T03:08:18Z","snapshot_observed_at":"2026-08-17T14:32:20.188230Z","submitted_at":"2025-06-13T03:08:18Z","title":"TruncQuant: Truncation-Ready Quantization for DNNs with Flexible Weight Bit Precision","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T04:18:09.202141Z"},"links":{"citing_paper":"/paper/2506.11431"},"observation_digest":"sha256:801846de37bd30e4293d8ad52593e258a7f340d5a682cbf5f08e42f642f2f661","observation_id":"10229167-7a88-45be-b36c-ae94d34200c7","resolution":{"observed_at":"2026-08-07T04:18:09.202141Z","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":"2026-08-14T17:13:05.593256Z","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":"2026-08-17T14:32:20.188230Z","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":"sha256:2ab8aaacc8d22a1bde823a8c5089fd090536ca9123b5396738ffea5747c9be57","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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T04:18:09.417382Z","title":"Once quantization-aware training: High performance extremely low-bit architecture search,","venue":null,"work_id":"120f2c94-69ab-4270-ac1d-0768e1b1b1d2","year":2021},"citing_paper":{"arxiv_id":"2506.11431","last_updated":"2025-06-13T03:08:18Z","snapshot_observed_at":"2026-08-17T14:32:20.188230Z","submitted_at":"2025-06-13T03:08:18Z","title":"TruncQuant: Truncation-Ready Quantization for DNNs with Flexible Weight Bit Precision","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T04:18:09.208316Z"},"links":{"citing_paper":"/paper/2506.11431"},"observation_digest":"sha256:1efeb8ab29f20bbae1bf580d8dc1c780fe129975793675b99b135fafa23c799c","observation_id":"21210e79-6066-488d-9a86-36ef99899a42","resolution":{"observed_at":"2026-08-07T04:18:09.421349Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1308.3432","last_updated":"2013-08-15T15:19:34Z","snapshot_observed_at":"2026-08-14T04:51:04.817737Z","submitted_at":"2013-08-15T15:19:34Z","title":"Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1308.3432","snapshot_observed_at":"2026-08-07T04:18:09.211387Z","title":"Estimating or propagating gradients through stochastic neurons for conditional computation,","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2506.11431","last_updated":"2025-06-13T03:08:18Z","snapshot_observed_at":"2026-08-17T14:32:20.188230Z","submitted_at":"2025-06-13T03:08:18Z","title":"TruncQuant: Truncation-Ready Quantization for DNNs with Flexible Weight Bit Precision","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T04:18:09.211387Z"},"links":{"cited_paper":"/paper/1308.3432","citing_paper":"/paper/2506.11431"},"observation_digest":"sha256:dfd37475b9900f429c1dcf83d0e66d07eef2a301822a913f0a433351874b67f1","observation_id":"450e82b8-c9dd-481f-8417-b85e2d0218b1","resolution":{"observed_at":"2026-08-07T04:18:09.211387Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1606.06160","last_updated":"2018-02-02T01:43:54Z","snapshot_observed_at":"2026-08-15T08:38:24.917341Z","submitted_at":"2016-06-20T15:02:31Z","title":"DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1606.06160","snapshot_observed_at":"2026-08-07T04:18:09.214845Z","title":"Dorefa-net: Training low bitwidth convolutional neural networks with low bitwidth gradients,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.11431","last_updated":"2025-06-13T03:08:18Z","snapshot_observed_at":"2026-08-17T14:32:20.188230Z","submitted_at":"2025-06-13T03:08:18Z","title":"TruncQuant: Truncation-Ready Quantization for DNNs with Flexible Weight Bit Precision","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T04:18:09.214845Z"},"links":{"cited_paper":"/paper/1606.06160","citing_paper":"/paper/2506.11431"},"observation_digest":"sha256:c0e614eb9ded910284ab55c697012a559bfabc8d57cf5f882f6ca813d30eb134","observation_id":"fd1ac299-7625-4f9d-83ee-d294e03bfee2","resolution":{"observed_at":"2026-08-07T04:18:09.214845Z","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":"2026-08-07T04:18:09.406672Z","title":"Nonuniform- to-uniform quantization: Towards accurate quantization via generalized straight-through estimation,","venue":null,"work_id":"d552ce68-a6df-4a74-a6f9-0b46e211d5f5","year":2022},"citing_paper":{"arxiv_id":"2506.11431","last_updated":"2025-06-13T03:08:18Z","snapshot_observed_at":"2026-08-17T14:32:20.188230Z","submitted_at":"2025-06-13T03:08:18Z","title":"TruncQuant: Truncation-Ready Quantization for DNNs with Flexible Weight Bit Precision","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T04:18:09.217855Z"},"links":{"citing_paper":"/paper/2506.11431"},"observation_digest":"sha256:efa60ac1b21a4650b10a2845685d196405e37f663d4d0f1d019c3961774e3220","observation_id":"fc4904b4-e7cc-46ce-8c23-edbed74bdbd9","resolution":{"observed_at":"2026-08-07T04:18:09.410651Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1903.05662","last_updated":"2019-09-25T14:33:44Z","snapshot_observed_at":"2026-08-14T17:02:42.244835Z","submitted_at":"2019-03-13T18:23:43Z","title":"Understanding Straight-Through Estimator in Training Activation Quantized Neural Nets","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.05662","snapshot_observed_at":"2026-08-07T04:18:09.220417Z","title":"Understanding straight-through estimator in training activation quantized neural nets,","venue":null,"work_id":null,"year":1903},"citing_paper":{"arxiv_id":"2506.11431","last_updated":"2025-06-13T03:08:18Z","snapshot_observed_at":"2026-08-17T14:32:20.188230Z","submitted_at":"2025-06-13T03:08:18Z","title":"TruncQuant: Truncation-Ready Quantization for DNNs with Flexible Weight Bit Precision","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T04:18:09.220417Z"},"links":{"cited_paper":"/paper/1903.05662","citing_paper":"/paper/2506.11431"},"observation_digest":"sha256:d99f14fe06dc5f948d01286073eb41fd8ad430d907e2a5a90ccce8da42a59628","observation_id":"cb82b2b3-a395-4cdd-b3b6-fa12e57b52c8","resolution":{"observed_at":"2026-08-07T04:18:09.220417Z","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":"2026-08-07T04:18:09.223232Z","title":"Deep residual learning for image recognition,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.11431","last_updated":"2025-06-13T03:08:18Z","snapshot_observed_at":"2026-08-17T14:32:20.188230Z","submitted_at":"2025-06-13T03:08:18Z","title":"TruncQuant: Truncation-Ready Quantization for DNNs with Flexible Weight Bit Precision","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T04:18:09.223232Z"},"links":{"citing_paper":"/paper/2506.11431"},"observation_digest":"sha256:65a98102aad14b8c9d42f9354a2bf17f7ba6c3ebd8cbe8dd6e7ff08b6f56105f","observation_id":"d07b5b94-fbfb-47e2-8849-17e4da35ba56","resolution":{"observed_at":"2026-08-07T04:18:09.223232Z","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":"2026-08-07T04:18:09.225709Z","title":"Mobilenetv2: Inverted residuals and linear bottlenecks,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.11431","last_updated":"2025-06-13T03:08:18Z","snapshot_observed_at":"2026-08-17T14:32:20.188230Z","submitted_at":"2025-06-13T03:08:18Z","title":"TruncQuant: Truncation-Ready Quantization for DNNs with Flexible Weight Bit Precision","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T04:18:09.225709Z"},"links":{"citing_paper":"/paper/2506.11431"},"observation_digest":"sha256:dcb6300665ee083a405d74b23e1f6de1fd9d084af9ed5174b3d4a286168a586f","observation_id":"029ef405-26a3-4ea1-bcc3-881bd26d8c51","resolution":{"observed_at":"2026-08-07T04:18:09.225709Z","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":"2026-08-07T04:18:09.228335Z","title":"Imagenet classification with deep convolutional neural networks,","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2506.11431","last_updated":"2025-06-13T03:08:18Z","snapshot_observed_at":"2026-08-17T14:32:20.188230Z","submitted_at":"2025-06-13T03:08:18Z","title":"TruncQuant: Truncation-Ready Quantization for DNNs with Flexible Weight Bit Precision","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T04:18:09.228335Z"},"links":{"citing_paper":"/paper/2506.11431"},"observation_digest":"sha256:ba1e945f3822257c9019ba5a503aa0e7a31f189beb43a38b1b99a289fe79a28c","observation_id":"61ac0a70-cb23-493e-a70f-66173a628f8c","resolution":{"observed_at":"2026-08-07T04:18:09.228335Z","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":"2026-08-07T04:18:09.231011Z","title":"Learning multiple layers of features from tiny images,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2506.11431","last_updated":"2025-06-13T03:08:18Z","snapshot_observed_at":"2026-08-17T14:32:20.188230Z","submitted_at":"2025-06-13T03:08:18Z","title":"TruncQuant: Truncation-Ready Quantization for DNNs with Flexible Weight Bit Precision","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T04:18:09.231011Z"},"links":{"citing_paper":"/paper/2506.11431"},"observation_digest":"sha256:92a73cfe97fd2706c447be896bef5b15692324ac30d0d31eb7527f1b8e428162","observation_id":"10e8cf68-0f24-44b3-a2ad-9bea25e7e1e8","resolution":{"observed_at":"2026-08-07T04:18:09.231011Z","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":"2026-08-07T04:18:09.233778Z","title":"Imagenet: A large-scale hierarchical image database,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2506.11431","last_updated":"2025-06-13T03:08:18Z","snapshot_observed_at":"2026-08-17T14:32:20.188230Z","submitted_at":"2025-06-13T03:08:18Z","title":"TruncQuant: Truncation-Ready Quantization for DNNs with Flexible Weight Bit Precision","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T04:18:09.233778Z"},"links":{"citing_paper":"/paper/2506.11431"},"observation_digest":"sha256:fc8da982b8891afb46ef945db7b032fc532e0ffa8468ca37ced413f1053e79b8","observation_id":"d890329a-72ce-437d-bc77-fde5f4be5058","resolution":{"observed_at":"2026-08-07T04:18:09.233778Z","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":"2026-08-07T04:18:09.366074Z","title":"Reading digits in natural images with unsupervised feature learning,","venue":null,"work_id":"a4fce74c-068a-4086-827b-49334cf98cda","year":2011},"citing_paper":{"arxiv_id":"2506.11431","last_updated":"2025-06-13T03:08:18Z","snapshot_observed_at":"2026-08-17T14:32:20.188230Z","submitted_at":"2025-06-13T03:08:18Z","title":"TruncQuant: Truncation-Ready Quantization for DNNs with Flexible Weight Bit Precision","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T04:18:09.236280Z"},"links":{"citing_paper":"/paper/2506.11431"},"observation_digest":"sha256:2fbadf2834bc3c45d8b43ad2ff81ca8764e9217483855b4e89ed51896effadea","observation_id":"1e2494c5-e261-48bb-ad11-bb4ad4df2fc5","resolution":{"observed_at":"2026-08-07T04:18:09.369286Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T04:18:09.238875Z","title":"Timeloop: A systematic approach to dnn accelerator evaluation,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.11431","last_updated":"2025-06-13T03:08:18Z","snapshot_observed_at":"2026-08-17T14:32:20.188230Z","submitted_at":"2025-06-13T03:08:18Z","title":"TruncQuant: Truncation-Ready Quantization for DNNs with Flexible Weight Bit Precision","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T04:18:09.238875Z"},"links":{"citing_paper":"/paper/2506.11431"},"observation_digest":"sha256:84d73cbb61147319f0e7c102f9faf8aba2220812e906d828907e6872691c111f","observation_id":"05fd65b7-17fa-4326-aa0e-682933ec30bb","resolution":{"observed_at":"2026-08-07T04:18:09.238875Z","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":"2026-08-07T04:18:09.349412Z","title":"Eyeriss: An energy- efficient reconfigurable accelerator for deep convolutional neural net- works,","venue":null,"work_id":"19164508-d89b-4b5a-bcdd-5f5a534e5fc8","year":2016},"citing_paper":{"arxiv_id":"2506.11431","last_updated":"2025-06-13T03:08:18Z","snapshot_observed_at":"2026-08-17T14:32:20.188230Z","submitted_at":"2025-06-13T03:08:18Z","title":"TruncQuant: Truncation-Ready Quantization for DNNs with Flexible Weight Bit Precision","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T04:18:09.241612Z"},"links":{"citing_paper":"/paper/2506.11431"},"observation_digest":"sha256:ea96afea0494bb3323428bd9f7ecf8ba26e4362f6b2a28c3d037302d6b15a60a","observation_id":"85843974-2048-4caf-a94a-072ff4db6bff","resolution":{"observed_at":"2026-08-07T04:18:09.352527Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2506.11431","last_updated":"2025-06-13T03:08:18Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-17T14:32:20.188230Z","submitted_at":"2025-06-13T03:08:18Z","title":"TruncQuant: Truncation-Ready Quantization for DNNs with Flexible Weight Bit Precision"},"reference_resolution":{"displayed":39,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":19,"verified_exact":1,"verified_fuzzy":19},"total_outbound_references":39},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 39 of 39 outbound references and 2 inbound Pith citation observations for arXiv:2506.11431."}