{"as_of":"2026-08-05T13:09:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:27caba7167ee25675708995a09c221411c7932d12943d56d75eff4e977c22928","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":11,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":11,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-05T06:32:48.257954+00:00","state":"measured"},{"denominator":11,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":11,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-04T17:57:54.355880Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":1,"source":"pith","source_observed_at":"2026-08-05T02:28:24.338817Z","state":"measured"}],"external_citation_measurements":[{"count":1425,"observed_at":"2026-08-05T02:28:24.338817Z","source":"pith"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1609.07061","last_updated":"2016-09-22T16:48:03Z","snapshot_observed_at":"2026-07-06T05:11:50.145502Z","submitted_at":"2016-09-22T16:48:03Z","title":"Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations","version":1},"cited_work":{"arxiv_id":"1609.07061","doi":"10.48550/arxiv.1609.07061","metadata_source":"pith","pith_arxiv_id":"1609.07061","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations","venue":"cs.NE","work_id":"ecdf87ee-5847-49b3-b239-59dad63c30a5","year":2016},"citing_paper":{"arxiv_id":"1704.04861","last_updated":"2017-04-17T03:57:34Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2017-04-17T03:57:34Z","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-11T02:50:40.222229Z"},"links":{"cited_paper":"/paper/1609.07061","citing_paper":"/paper/1704.04861"},"observation_digest":"sha256:aaf6154824fb96aee7eded9421b85cf1ff5ff4763351e2dc0e95d047f496c333","observation_id":"2927e1ac-948d-4c86-b4c5-705189225048","resolution":{"observed_at":"2026-05-11T02:50:40.305343Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1609.07061","last_updated":"2016-09-22T16:48:03Z","snapshot_observed_at":"2026-07-06T05:11:50.145502Z","submitted_at":"2016-09-22T16:48:03Z","title":"Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations","version":1},"cited_work":{"arxiv_id":"1609.07061","doi":"10.48550/arxiv.1609.07061","metadata_source":"pith","pith_arxiv_id":"1609.07061","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations","venue":"cs.NE","work_id":"ecdf87ee-5847-49b3-b239-59dad63c30a5","year":2016},"citing_paper":{"arxiv_id":"1710.03740","last_updated":"2018-02-15T20:04:02Z","snapshot_observed_at":"2026-07-06T06:03:37.247241Z","submitted_at":"2017-10-10T17:42:04Z","title":"Mixed Precision Training","version":3},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-05-12T10:47:18.426912Z"},"links":{"cited_paper":"/paper/1609.07061","citing_paper":"/paper/1710.03740"},"observation_digest":"sha256:85e3f76dd7135b93754de5385d0c7ddd0d93340bc1343d4910f2eb6650bcc285","observation_id":"c8008e1c-343e-4a5a-a9c0-7e557a4c2420","resolution":{"observed_at":"2026-05-12T10:47:18.487769Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1609.07061","last_updated":"2016-09-22T16:48:03Z","snapshot_observed_at":"2026-07-06T05:11:50.145502Z","submitted_at":"2016-09-22T16:48:03Z","title":"Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations","version":1},"cited_work":{"arxiv_id":"1609.07061","doi":"10.48550/arxiv.1609.07061","metadata_source":"pith","pith_arxiv_id":"1609.07061","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations","venue":"cs.NE","work_id":"ecdf87ee-5847-49b3-b239-59dad63c30a5","year":2016},"citing_paper":{"arxiv_id":"1906.12172","last_updated":"2019-06-25T10:47:08Z","snapshot_observed_at":"2026-07-06T08:03:36.058571Z","submitted_at":"2019-06-25T10:47:08Z","title":"New pointwise convolution in Deep Neural Networks through Extremely Fast and Non Parametric Transforms","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-25T16:54:52.543890Z"},"links":{"cited_paper":"/paper/1609.07061","citing_paper":"/paper/1906.12172"},"observation_digest":"sha256:ca5d152bad1d5dc6246ba3007229191a04d0d4e0d25c5f2eb2a1c0152c39f592","observation_id":"a088b7c4-4a45-457d-81ee-21916419d794","resolution":{"observed_at":"2026-05-25T16:56:04.223594Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1609.07061","last_updated":"2016-09-22T16:48:03Z","snapshot_observed_at":"2026-07-06T05:11:50.145502Z","submitted_at":"2016-09-22T16:48:03Z","title":"Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations","version":1},"cited_work":{"arxiv_id":"1609.07061","doi":"10.48550/arxiv.1609.07061","metadata_source":"pith","pith_arxiv_id":"1609.07061","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations","venue":"cs.NE","work_id":"ecdf87ee-5847-49b3-b239-59dad63c30a5","year":2016},"citing_paper":{"arxiv_id":"1907.04648","last_updated":"2019-07-07T03:50:42Z","snapshot_observed_at":"2026-07-06T08:06:46.800927Z","submitted_at":"2019-07-07T03:50:42Z","title":"EPNAS: Efficient Progressive Neural Architecture Search","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-05-25T01:15:41.635247Z"},"links":{"cited_paper":"/paper/1609.07061","citing_paper":"/paper/1907.04648"},"observation_digest":"sha256:c7f7fc8f0015b45b9804e08a48444f5a9bfaa043ce0b422c1a80427b02b58abb","observation_id":"8f42592a-3bc7-4d45-b1f4-b561b0858ea7","resolution":{"observed_at":"2026-05-25T01:16:31.729807Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1609.07061","last_updated":"2016-09-22T16:48:03Z","snapshot_observed_at":"2026-07-06T05:11:50.145502Z","submitted_at":"2016-09-22T16:48:03Z","title":"Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations","version":1},"cited_work":{"arxiv_id":"1609.07061","doi":"10.48550/arxiv.1609.07061","metadata_source":"pith","pith_arxiv_id":"1609.07061","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations","venue":"cs.NE","work_id":"ecdf87ee-5847-49b3-b239-59dad63c30a5","year":2016},"citing_paper":{"arxiv_id":"2211.17192","last_updated":"2023-05-18T20:28:20Z","snapshot_observed_at":"2026-07-06T14:25:12.946406Z","submitted_at":"2022-11-30T17:33:28Z","title":"Fast Inference from Transformers via Speculative Decoding","version":2},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-05-17T22:52:00.101612Z"},"links":{"cited_paper":"/paper/1609.07061","citing_paper":"/paper/2211.17192"},"observation_digest":"sha256:c20bc95c52cd9305727dfc17ca5ec12f84af4a12af47fa65e90895397dd92e6e","observation_id":"a6088260-eb03-481f-85e8-37891d31882e","resolution":{"observed_at":"2026-05-17T22:52:00.149105Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1609.07061","last_updated":"2016-09-22T16:48:03Z","snapshot_observed_at":"2026-07-06T05:11:50.145502Z","submitted_at":"2016-09-22T16:48:03Z","title":"Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1609.07061","snapshot_observed_at":"2026-08-04T17:57:54.355880Z","title":"Hubara, M","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2509.10367","last_updated":"2025-09-12T16:00:49Z","snapshot_observed_at":"2026-08-04T17:57:44.856181Z","submitted_at":"2025-09-12T16:00:49Z","title":"A Discrepancy-Based Perspective on Dataset Condensation","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-04T17:57:54.355880Z"},"links":{"cited_paper":"/paper/1609.07061","citing_paper":"/paper/2509.10367"},"observation_digest":"sha256:1a0adb10e9adb631447c122354f0dfbd81880f0416c5c8f578271ead2a71c04a","observation_id":"243fb917-ee67-446c-b2b1-6edba1a2a6be","resolution":{"observed_at":"2026-08-04T17:57:54.355880Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1609.07061","last_updated":"2016-09-22T16:48:03Z","snapshot_observed_at":"2026-07-06T05:11:50.145502Z","submitted_at":"2016-09-22T16:48:03Z","title":"Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations","version":1},"cited_work":{"arxiv_id":"1609.07061","doi":"10.48550/arxiv.1609.07061","metadata_source":"pith","pith_arxiv_id":"1609.07061","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations","venue":"cs.NE","work_id":"ecdf87ee-5847-49b3-b239-59dad63c30a5","year":2016},"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":38,"source":"pdf_text","source_observed_at":"2026-05-12T04:33:41.411292Z"},"links":{"cited_paper":"/paper/1609.07061","citing_paper":"/paper/2605.10886"},"observation_digest":"sha256:ef9a8bf6d8906fe1daca4b7a1d7450104d436f8261b7a7ffcbe4f5c1e7a8c303","observation_id":"0a1c2500-c551-42b9-8ff2-3780de76e3fc","resolution":{"observed_at":"2026-05-12T06:06:27.874626Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1609.07061","last_updated":"2016-09-22T16:48:03Z","snapshot_observed_at":"2026-07-06T05:11:50.145502Z","submitted_at":"2016-09-22T16:48:03Z","title":"Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations","version":1},"cited_work":{"arxiv_id":"1609.07061","doi":"10.48550/arxiv.1609.07061","metadata_source":"pith","pith_arxiv_id":"1609.07061","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations","venue":"cs.NE","work_id":"ecdf87ee-5847-49b3-b239-59dad63c30a5","year":2016},"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":38,"source":"pdf_text","source_observed_at":"2026-05-15T04:55:01.973832Z"},"links":{"cited_paper":"/paper/1609.07061","citing_paper":"/paper/2605.10886"},"observation_digest":"sha256:b80f1513e4257e991e5088b2c9b2eb9b29d782e7b9a797f7ec3aa7f0828dae21","observation_id":"dd85d3f2-a0e2-4914-94b4-e413ea4ac591","resolution":{"observed_at":"2026-05-15T04:59:46.157213Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1609.07061","last_updated":"2016-09-22T16:48:03Z","snapshot_observed_at":"2026-07-06T05:11:50.145502Z","submitted_at":"2016-09-22T16:48:03Z","title":"Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations","version":1},"cited_work":{"arxiv_id":"1609.07061","doi":"10.48550/arxiv.1609.07061","metadata_source":"pith","pith_arxiv_id":"1609.07061","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations","venue":"cs.NE","work_id":"ecdf87ee-5847-49b3-b239-59dad63c30a5","year":2016},"citing_paper":{"arxiv_id":"2605.18933","last_updated":"2026-05-18T15:36:33Z","snapshot_observed_at":"2026-07-06T23:29:42.583875Z","submitted_at":"2026-05-18T15:36:33Z","title":"A Geometric Analysis of Sign-Magnitude Asymmetry in a ReLU + RMSNorm Block under Ternary Quantization","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-20T13:05:50.518189Z"},"links":{"cited_paper":"/paper/1609.07061","citing_paper":"/paper/2605.18933"},"observation_digest":"sha256:d67a938f0f625301965ea8e7dfa8430d61c0cac9b18e1b30b60fd09fdd425a08","observation_id":"b982565f-d86a-4ef5-bec1-a8602af04148","resolution":{"observed_at":"2026-05-20T13:08:17.794531Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1609.07061","last_updated":"2016-09-22T16:48:03Z","snapshot_observed_at":"2026-07-06T05:11:50.145502Z","submitted_at":"2016-09-22T16:48:03Z","title":"Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations","version":1},"cited_work":{"arxiv_id":"1609.07061","doi":"10.48550/arxiv.1609.07061","metadata_source":"pith","pith_arxiv_id":"1609.07061","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations","venue":"cs.NE","work_id":"ecdf87ee-5847-49b3-b239-59dad63c30a5","year":2016},"citing_paper":{"arxiv_id":"2606.27759","last_updated":"2026-06-26T06:37:57Z","snapshot_observed_at":"2026-08-04T17:59:21.217757Z","submitted_at":"2026-06-26T06:37:57Z","title":"Layerwise Progressive Freezing: A Training Scaffold for Depth-Scalable Binary Networks","version":1},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-06-29T05:08:23.176105Z"},"links":{"cited_paper":"/paper/1609.07061","citing_paper":"/paper/2606.27759"},"observation_digest":"sha256:5f950eb2951d81f017dde679c45a1080e736cac1a8b02bf1991f7bc3ab8b2f3c","observation_id":"6a55fdd6-ae4b-447d-b0cc-55f6c8106252","resolution":{"observed_at":"2026-06-29T05:13:06.499241Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1609.07061","last_updated":"2016-09-22T16:48:03Z","snapshot_observed_at":"2026-07-06T05:11:50.145502Z","submitted_at":"2016-09-22T16:48:03Z","title":"Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1609.07061","snapshot_observed_at":"2026-08-01T15:11:09.153754Z","title":"Quantized neural networks: Training neural networks with low precision weights and activations,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.18540","last_updated":"2026-07-20T22:14:04Z","snapshot_observed_at":"2026-08-05T08:44:32.897834Z","submitted_at":"2026-07-20T22:14:04Z","title":"Recti-Q: Feature-Space Rectification for Out-of-Distribution-Robust Quantized Perception in Edge Robotics","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-01T15:11:09.153754Z"},"links":{"cited_paper":"/paper/1609.07061","citing_paper":"/paper/2607.18540"},"observation_digest":"sha256:7234ecf9d17b94d05fe134d030591b5eb26416d31fa60bbadffd8d474d247536","observation_id":"5abe070d-6ecb-48ec-9ad8-cacbec2843f0","resolution":{"observed_at":"2026-08-01T15:11:09.153754Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/1609.07061/citation-record","integrity":"/paper/1609.07061/integrity","json":"/paper/1609.07061/citation-record.json","paper":"/paper/1609.07061"},"outbound":[],"paper":{"arxiv_id":"1609.07061","last_updated":"2016-09-22T16:48:03Z","latest_version":1,"primary_category":"cs.NE","snapshot_observed_at":"2026-07-06T05:11:50.145502Z","submitted_at":"2016-09-22T16:48:03Z","title":"Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations"},"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":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"thesis":"As of 5 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 11 inbound Pith citation observations for arXiv:1609.07061."}