{"as_of":"2026-08-12T06:16:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:fe5b051ce7bec2b3299482b51d0601cef15f70bb3f9c3423a68e47125a8bd44d","coverage":[{"denominator":34,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":34,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T15:07:02.505099Z","state":"measured"},{"denominator":34,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":34,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-11T06:34:44.6726+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2501.14531/citation-record","integrity":"/paper/2501.14531/integrity","json":"/paper/2501.14531/citation-record.json","paper":"/paper/2501.14531"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"1308.3432","last_updated":"2013-08-15T15:19:34Z","snapshot_observed_at":"2026-08-11T05:54:56.124984Z","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":"2026-08-10T15:07:02.373947Z","title":"Estimating or propagating gradients through stochastic neurons for conditional computation","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2501.14531","last_updated":"2025-01-24T14:37:24Z","snapshot_observed_at":"2026-08-10T15:01:42.874211Z","submitted_at":"2025-01-24T14:37:24Z","title":"On Hardening DNNs against Noisy Computations","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-10T15:07:02.373947Z"},"links":{"cited_paper":"/paper/1308.3432","citing_paper":"/paper/2501.14531"},"observation_digest":"sha256:5769d20202e01673ce28645836778198a63b071cfbd168be4e50369c942a067b","observation_id":"7bb16a81-0607-4665-9913-014818985aee","resolution":{"observed_at":"2026-08-10T15:07:02.373947Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1606.07786","last_updated":"2020-02-20T06:27:05Z","snapshot_observed_at":"2026-08-10T18:53:25.371548Z","submitted_at":"2016-06-23T18:32:43Z","title":"Precise neural network computation with imprecise analog devices","version":2},"cited_work":{"arxiv_id":"1606.07786","doi":null,"metadata_source":"pith","pith_arxiv_id":"1606.07786","snapshot_observed_at":"2026-08-10T15:07:02.891677Z","title":"Precise neural network computation with imprecise analog devices","venue":"cs.NE","work_id":"d648750a-e748-4a6a-b320-c4e99300ee53","year":2016},"citing_paper":{"arxiv_id":"2501.14531","last_updated":"2025-01-24T14:37:24Z","snapshot_observed_at":"2026-08-10T15:01:42.874211Z","submitted_at":"2025-01-24T14:37:24Z","title":"On Hardening DNNs against Noisy Computations","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-10T15:07:02.378053Z"},"links":{"cited_paper":"/paper/1606.07786","citing_paper":"/paper/2501.14531"},"observation_digest":"sha256:59a9c83386230e718e7e8d83dcc829666696e5f68f358b1affd30214f72c032d","observation_id":"37311bef-3caf-4542-90d9-8e6e628fd8e9","resolution":{"observed_at":"2026-08-10T15:07:02.895783Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T15:07:03.137639Z","title":"Walking Noise: On Layer-Specific Robustness of Neu- ral Architectures against Noisy Computations and Asso- ciated Characteristic Learning Dynamics","venue":null,"work_id":"f341939b-68ff-4d54-b048-90add1fca713","year":2024},"citing_paper":{"arxiv_id":"2501.14531","last_updated":"2025-01-24T14:37:24Z","snapshot_observed_at":"2026-08-10T15:01:42.874211Z","submitted_at":"2025-01-24T14:37:24Z","title":"On Hardening DNNs against Noisy Computations","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-10T15:07:02.382647Z"},"links":{"citing_paper":"/paper/2501.14531"},"observation_digest":"sha256:27a329e92594bc65e407364f420eecf7428071fe6c2bdfeb775e3a25ca8981ea","observation_id":"a4aceae1-1e0c-42b6-8153-68572bea5e28","resolution":{"observed_at":"2026-08-10T15:07:03.140820Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.17915","last_updated":"2024-01-31T15:27:38Z","snapshot_observed_at":"2026-07-06T17:23:10.017122Z","submitted_at":"2024-01-31T15:27:38Z","title":"Probabilistic Photonic Computing with Chaotic Light","version":1},"cited_work":{"arxiv_id":"2401.17915","doi":"10.48550/arxiv.2401.17915","metadata_source":"pith","pith_arxiv_id":"2401.17915","snapshot_observed_at":"2026-08-10T18:16:17.926450Z","title":"Probabilistic Photonic Computing with Chaotic Light","venue":"physics.optics","work_id":"b32f7c2b-5f91-489e-8da8-c682ee3daf00","year":2024},"citing_paper":{"arxiv_id":"2501.14531","last_updated":"2025-01-24T14:37:24Z","snapshot_observed_at":"2026-08-10T15:01:42.874211Z","submitted_at":"2025-01-24T14:37:24Z","title":"On Hardening DNNs against Noisy Computations","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-10T15:07:02.386796Z"},"links":{"cited_paper":"/paper/2401.17915","citing_paper":"/paper/2501.14531"},"observation_digest":"sha256:181bf42ede300dcc991d2b85449359abf4e0163204129393361d3ed1c9cc2fad","observation_id":"e70940b6-f2fd-4a29-988a-8c9a7641a04a","resolution":{"observed_at":"2026-08-10T15:07:02.612083Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T15:07:02.391195Z","title":"Robust quantization: One model to rule them all","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2501.14531","last_updated":"2025-01-24T14:37:24Z","snapshot_observed_at":"2026-08-10T15:01:42.874211Z","submitted_at":"2025-01-24T14:37:24Z","title":"On Hardening DNNs against Noisy Computations","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-10T15:07:02.391195Z"},"links":{"citing_paper":"/paper/2501.14531"},"observation_digest":"sha256:5ed7a860852f1f4b3078822716364280f3cfbfc93e34aa93095644efecd646d3","observation_id":"5302b329-68c5-4ed6-aa02-090d6f0540f6","resolution":{"observed_at":"2026-08-10T15:07:02.391195Z","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":"2026-08-10T15:07:03.127815Z","title":"Exploring the impact of random tele- graph noise-induced accuracy loss on resistive RAM- based deep neural network","venue":null,"work_id":"d76149c9-7b30-4bcd-b9d9-791d0ff2e581","year":2020},"citing_paper":{"arxiv_id":"2501.14531","last_updated":"2025-01-24T14:37:24Z","snapshot_observed_at":"2026-08-10T15:01:42.874211Z","submitted_at":"2025-01-24T14:37:24Z","title":"On Hardening DNNs against Noisy Computations","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-10T15:07:02.395204Z"},"links":{"citing_paper":"/paper/2501.14531"},"observation_digest":"sha256:c9a34837be8587d2e03b420a9bf1c198bdf45ff3ea3d8999b5faeb0f99f309f0","observation_id":"a803637a-78e8-4bbe-9e89-a1f72340bdf1","resolution":{"observed_at":"2026-08-10T15:07:03.131157Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T15:07:03.116026Z","title":"Relative robustness of quantized neural networks against adversarial attacks","venue":null,"work_id":"e8519263-5400-450c-ad87-304ac56e41f2","year":2020},"citing_paper":{"arxiv_id":"2501.14531","last_updated":"2025-01-24T14:37:24Z","snapshot_observed_at":"2026-08-10T15:01:42.874211Z","submitted_at":"2025-01-24T14:37:24Z","title":"On Hardening DNNs against Noisy Computations","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-10T15:07:02.399599Z"},"links":{"citing_paper":"/paper/2501.14531"},"observation_digest":"sha256:b377aedbbe27a481e8997aea9d686836680981055febc7ded3f9d996b6afb68e","observation_id":"d8f36dab-1fa1-45be-bdc9-5cd9a677e8ac","resolution":{"observed_at":"2026-08-10T15:07:03.119862Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.05820","last_updated":"2024-01-11T10:36:45Z","snapshot_observed_at":"2026-08-11T21:13:22.371444Z","submitted_at":"2024-01-11T10:36:45Z","title":"Implications of Noise in Resistive Memory on Deep Neural Networks for Image Classification","version":1},"cited_work":{"arxiv_id":"2401.05820","doi":"10.48550/arxiv.2401.05820","metadata_source":"pith","pith_arxiv_id":"2401.05820","snapshot_observed_at":"2026-08-10T18:16:17.926450Z","title":"Implications of Noise in Resistive Memory on Deep Neural Networks for Image Classification","venue":"cs.LG","work_id":"40ef82b1-6fad-4ed5-b38d-413023deb741","year":2024},"citing_paper":{"arxiv_id":"2501.14531","last_updated":"2025-01-24T14:37:24Z","snapshot_observed_at":"2026-08-10T15:01:42.874211Z","submitted_at":"2025-01-24T14:37:24Z","title":"On Hardening DNNs against Noisy Computations","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-10T15:07:02.403424Z"},"links":{"cited_paper":"/paper/2401.05820","citing_paper":"/paper/2501.14531"},"observation_digest":"sha256:63649382f41fab8cadda5f427675d99aa12c3a007210161c23e9cd741f21a936","observation_id":"77015ba3-4950-426e-8d30-716cc39b1c60","resolution":{"observed_at":"2026-08-10T15:07:02.593956Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T15:07:03.103233Z","title":"A survey of quantization methods for efficient neural network inference","venue":null,"work_id":"72c21ce4-d7db-4b93-a6fc-5969cf4fa9e1","year":2022},"citing_paper":{"arxiv_id":"2501.14531","last_updated":"2025-01-24T14:37:24Z","snapshot_observed_at":"2026-08-10T15:01:42.874211Z","submitted_at":"2025-01-24T14:37:24Z","title":"On Hardening DNNs against Noisy Computations","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-10T15:07:02.407494Z"},"links":{"citing_paper":"/paper/2501.14531"},"observation_digest":"sha256:c00ced198efba99052c673ebc53400fb2966f2c2543f300ab5c818ec77cbdcca","observation_id":"eb670dcc-0ad7-4ea0-bb0e-e4c48f61e1bb","resolution":{"observed_at":"2026-08-10T15:07:03.107283Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T15:07:02.411460Z","title":"How many bits does it take to quantize your neural network?","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2501.14531","last_updated":"2025-01-24T14:37:24Z","snapshot_observed_at":"2026-08-10T15:01:42.874211Z","submitted_at":"2025-01-24T14:37:24Z","title":"On Hardening DNNs against Noisy Computations","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-10T15:07:02.411460Z"},"links":{"citing_paper":"/paper/2501.14531"},"observation_digest":"sha256:a25a30df6fa1d9d9183df1eaae32c3040bebd1199ab178ebbf739a1dee0d921e","observation_id":"ec097a0f-21bf-49b5-95b8-fe0e9f0f7ead","resolution":{"observed_at":"2026-08-10T15:07:02.411460Z","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":"2026-08-10T15:07:03.091016Z","title":"On the adversarial robustness of quantized neural net- works","venue":null,"work_id":"45f95a1e-5bc0-4a2c-a63e-3af669d6b132","year":2021},"citing_paper":{"arxiv_id":"2501.14531","last_updated":"2025-01-24T14:37:24Z","snapshot_observed_at":"2026-08-10T15:01:42.874211Z","submitted_at":"2025-01-24T14:37:24Z","title":"On Hardening DNNs against Noisy Computations","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-10T15:07:02.415417Z"},"links":{"citing_paper":"/paper/2501.14531"},"observation_digest":"sha256:07a1dca3dac98d4933326249d3c450ed89b8287b5d0f09e4522dce76c3bf2823","observation_id":"7ccaadd4-1bcb-4674-a741-abb5e7c3c7d4","resolution":{"observed_at":"2026-08-10T15:07:03.095231Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T15:07:03.079570Z","title":"Deep residual learning for image recognition","venue":null,"work_id":"74e38277-baa6-4077-a59b-a380b89748ad","year":2016},"citing_paper":{"arxiv_id":"2501.14531","last_updated":"2025-01-24T14:37:24Z","snapshot_observed_at":"2026-08-10T15:01:42.874211Z","submitted_at":"2025-01-24T14:37:24Z","title":"On Hardening DNNs against Noisy Computations","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-10T15:07:02.419255Z"},"links":{"citing_paper":"/paper/2501.14531"},"observation_digest":"sha256:22c3dccf3c7b3802597fc33c8f4838b13d93e228a81fa50f4b25a1cf69e323fe","observation_id":"ff986b70-7b7b-423d-9449-e428267b3719","resolution":{"observed_at":"2026-08-10T15:07:03.083663Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T15:07:03.066883Z","title":"Neural network compression for noisy storage devices","venue":null,"work_id":"63186360-3e92-4f71-80cc-811db20062a9","year":2023},"citing_paper":{"arxiv_id":"2501.14531","last_updated":"2025-01-24T14:37:24Z","snapshot_observed_at":"2026-08-10T15:01:42.874211Z","submitted_at":"2025-01-24T14:37:24Z","title":"On Hardening DNNs against Noisy Computations","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-10T15:07:02.422959Z"},"links":{"citing_paper":"/paper/2501.14531"},"observation_digest":"sha256:c254cb6b3d1de72741dcfad34cb4a6c9dcf73e9afa2d3458777779434c6e47e1","observation_id":"dc8e1d92-b2b4-4413-9bc9-e784cfd8bd0b","resolution":{"observed_at":"2026-08-10T15:07:03.071755Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T15:07:03.055643Z","title":"Accurate deep neural network infer- ence using computational phase-change memory","venue":null,"work_id":"ab114583-c1f7-4d04-9aee-7b4bc2ac676e","year":2020},"citing_paper":{"arxiv_id":"2501.14531","last_updated":"2025-01-24T14:37:24Z","snapshot_observed_at":"2026-08-10T15:01:42.874211Z","submitted_at":"2025-01-24T14:37:24Z","title":"On Hardening DNNs against Noisy Computations","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-10T15:07:02.426729Z"},"links":{"citing_paper":"/paper/2501.14531"},"observation_digest":"sha256:e2ee8509b37e799d30f216d2407c3fbb3ce7a8f0042125ae1db168b8991030c2","observation_id":"731ee32b-a2e9-4b36-a650-5e7432f62c01","resolution":{"observed_at":"2026-08-10T15:07:03.059614Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T15:07:03.044416Z","title":"Adam: A Method for Stochastic Optimization","venue":null,"work_id":"0af3a3c1-55df-46ef-96c4-7bea8346c627","year":2014},"citing_paper":{"arxiv_id":"2501.14531","last_updated":"2025-01-24T14:37:24Z","snapshot_observed_at":"2026-08-10T15:01:42.874211Z","submitted_at":"2025-01-24T14:37:24Z","title":"On Hardening DNNs against Noisy Computations","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-10T15:07:02.430901Z"},"links":{"citing_paper":"/paper/2501.14531"},"observation_digest":"sha256:8f9224e2caddb855f064510acd5afbaeae4bdb5a3b9cc5417fb9546becfaf7d7","observation_id":"004e58b7-a735-4d9b-82d0-3ae401694b1f","resolution":{"observed_at":"2026-08-10T15:07:03.048103Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1007/978-3-030-93736-2","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T15:07:02.565881Z","title":"Towards Addressing Noise and Static Variations of Analog Computations Using Effi- cient Retraining","venue":null,"work_id":"2d35f6a2-fbd5-4183-8ec9-29a91b59034a","year":2021},"citing_paper":{"arxiv_id":"2501.14531","last_updated":"2025-01-24T14:37:24Z","snapshot_observed_at":"2026-08-10T15:01:42.874211Z","submitted_at":"2025-01-24T14:37:24Z","title":"On Hardening DNNs against Noisy Computations","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-10T15:07:02.434354Z"},"links":{"citing_paper":"/paper/2501.14531"},"observation_digest":"sha256:20957981409e25821f3c60ecbf4eb7af03b86cb113d650a8c10754b19c6035c6","observation_id":"01c2b031-eefd-4e2f-8a48-fb3b15496bdb","resolution":{"observed_at":"2026-08-10T15:07:02.571048Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1806.08342","last_updated":"2018-06-21T17:32:46Z","snapshot_observed_at":"2026-07-06T06:46:08.396066Z","submitted_at":"2018-06-21T17:32:46Z","title":"Quantizing deep convolutional networks for efficient inference: A whitepaper","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1806.08342","snapshot_observed_at":"2026-08-10T15:07:02.437798Z","title":"Quantizing deep convo- lutional networks for efficient inference: A whitepaper","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2501.14531","last_updated":"2025-01-24T14:37:24Z","snapshot_observed_at":"2026-08-10T15:01:42.874211Z","submitted_at":"2025-01-24T14:37:24Z","title":"On Hardening DNNs against Noisy Computations","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-10T15:07:02.437798Z"},"links":{"cited_paper":"/paper/1806.08342","citing_paper":"/paper/2501.14531"},"observation_digest":"sha256:0b0b887a672868b378ee2d7627b65195ce4f0666a4893bbb5d47f46da425db04","observation_id":"e9d7c422-a846-45f0-b7e7-29a72050585f","resolution":{"observed_at":"2026-08-10T15:07:02.437798Z","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":"2026-08-10T15:07:03.033074Z","title":null,"venue":null,"work_id":"e32e4bd2-48ab-4357-ae0f-1f3c6da647b8","year":2009},"citing_paper":{"arxiv_id":"2501.14531","last_updated":"2025-01-24T14:37:24Z","snapshot_observed_at":"2026-08-10T15:01:42.874211Z","submitted_at":"2025-01-24T14:37:24Z","title":"On Hardening DNNs against Noisy Computations","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-10T15:07:02.441484Z"},"links":{"citing_paper":"/paper/2501.14531"},"observation_digest":"sha256:0aeaf490122cfd25e1b2f9ba9b106a07eb64311ecd29faa3b7479bd40a3c87f9","observation_id":"eaed201b-688b-4c7c-8d38-b2eb72f87d1f","resolution":{"observed_at":"2026-08-10T15:07:03.037114Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.14292","last_updated":"2023-09-25T17:04:09Z","snapshot_observed_at":"2026-07-06T16:23:26.584450Z","submitted_at":"2023-09-25T17:04:09Z","title":"On the Non-Associativity of Analog Computations","version":1},"cited_work":{"arxiv_id":"2309.14292","doi":"10.48550/arxiv.2309.14292","metadata_source":"pith","pith_arxiv_id":"2309.14292","snapshot_observed_at":"2026-08-10T18:16:17.926450Z","title":"On the Non-Associativity of Analog Computations","venue":"cs.AR","work_id":"32f77d54-d6e5-4b03-8b46-c96bf4706202","year":2023},"citing_paper":{"arxiv_id":"2501.14531","last_updated":"2025-01-24T14:37:24Z","snapshot_observed_at":"2026-08-10T15:01:42.874211Z","submitted_at":"2025-01-24T14:37:24Z","title":"On Hardening DNNs against Noisy Computations","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-10T15:07:02.451341Z"},"links":{"cited_paper":"/paper/2309.14292","citing_paper":"/paper/2501.14531"},"observation_digest":"sha256:8f2e1cbce8769a25f02e9b3ff800f007b411e9055f719aed92e6893452a3e0e6","observation_id":"d3b6d4f4-db37-42f1-a97a-34b315cb9ce5","resolution":{"observed_at":"2026-08-10T15:07:02.557023Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T15:07:03.021003Z","title":"Gradient-based learning applied to document recognition","venue":null,"work_id":"d1b2a544-f530-4451-a3f9-85d18e52a009","year":1998},"citing_paper":{"arxiv_id":"2501.14531","last_updated":"2025-01-24T14:37:24Z","snapshot_observed_at":"2026-08-10T15:01:42.874211Z","submitted_at":"2025-01-24T14:37:24Z","title":"On Hardening DNNs against Noisy Computations","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-10T15:07:02.455156Z"},"links":{"citing_paper":"/paper/2501.14531"},"observation_digest":"sha256:d11d13450434725ce37fc8201f85998cc65c1decf2bce7ff2b400a303d163941","observation_id":"1a1b626a-6c9d-4c55-90f1-7378a77a5a2d","resolution":{"observed_at":"2026-08-10T15:07:03.024820Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T15:07:03.009520Z","title":"Defensive Quan- tization: When Efficiency Meets Robustness","venue":null,"work_id":"46e1d6d3-c627-4d6a-a528-58a77403d5d0","year":2019},"citing_paper":{"arxiv_id":"2501.14531","last_updated":"2025-01-24T14:37:24Z","snapshot_observed_at":"2026-08-10T15:01:42.874211Z","submitted_at":"2025-01-24T14:37:24Z","title":"On Hardening DNNs against Noisy Computations","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-10T15:07:02.459115Z"},"links":{"citing_paper":"/paper/2501.14531"},"observation_digest":"sha256:0020bc1d3bdaff77341414639870183966d467ee450ad1303c4109328a581c32","observation_id":"69a4052c-4ff4-4575-9fac-bfb8ac64c49a","resolution":{"observed_at":"2026-08-10T15:07:03.013672Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T15:07:02.998268Z","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","venue":null,"work_id":"3c37256d-cf4d-4232-9063-ce48de9941a8","year":2017},"citing_paper":{"arxiv_id":"2501.14531","last_updated":"2025-01-24T14:37:24Z","snapshot_observed_at":"2026-08-10T15:01:42.874211Z","submitted_at":"2025-01-24T14:37:24Z","title":"On Hardening DNNs against Noisy Computations","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-10T15:07:02.462555Z"},"links":{"citing_paper":"/paper/2501.14531"},"observation_digest":"sha256:918c0b65290eaa9a2d726dcdfa60d4cdb0bcb7921d0af6cab9358dd94f3aaea7","observation_id":"14cdb53a-b953-43a2-addf-63ca0b99c34a","resolution":{"observed_at":"2026-08-10T15:07:03.001981Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T15:07:02.986707Z","title":"Mixed-signal computing for deep neural network inference","venue":null,"work_id":"8e64fd17-6869-47f6-9e51-41f8b57f907a","year":2020},"citing_paper":{"arxiv_id":"2501.14531","last_updated":"2025-01-24T14:37:24Z","snapshot_observed_at":"2026-08-10T15:01:42.874211Z","submitted_at":"2025-01-24T14:37:24Z","title":"On Hardening DNNs against Noisy Computations","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-10T15:07:02.465554Z"},"links":{"citing_paper":"/paper/2501.14531"},"observation_digest":"sha256:abab84f35a319ea164a34b7d0a0e56d26f8660e0d857717d30c56aab8a43bf61","observation_id":"8aa576a3-1cd0-4591-aee7-772a95c8f367","resolution":{"observed_at":"2026-08-10T15:07:02.989854Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2106.08295","last_updated":"2021-06-15T17:12:42Z","snapshot_observed_at":"2026-08-02T11:19:40.664702Z","submitted_at":"2021-06-15T17:12:42Z","title":"A White Paper on Neural Network Quantization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.08295","snapshot_observed_at":"2026-08-10T15:07:02.468859Z","title":"A White Paper on Neural Network Quantization","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.14531","last_updated":"2025-01-24T14:37:24Z","snapshot_observed_at":"2026-08-10T15:01:42.874211Z","submitted_at":"2025-01-24T14:37:24Z","title":"On Hardening DNNs against Noisy Computations","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-10T15:07:02.468859Z"},"links":{"cited_paper":"/paper/2106.08295","citing_paper":"/paper/2501.14531"},"observation_digest":"sha256:44ef3d25e8dcffdd11f0588e975ef6657d43cac7399254feff6be6809d54fb3d","observation_id":"902c6d47-41e0-4a68-837e-5239f08e4271","resolution":{"observed_at":"2026-08-10T15:07:02.468859Z","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":"2026-08-10T15:07:02.472129Z","title":"XILINX/brevitas","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2501.14531","last_updated":"2025-01-24T14:37:24Z","snapshot_observed_at":"2026-08-10T15:01:42.874211Z","submitted_at":"2025-01-24T14:37:24Z","title":"On Hardening DNNs against Noisy Computations","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-10T15:07:02.472129Z"},"links":{"citing_paper":"/paper/2501.14531"},"observation_digest":"sha256:cd45cbaaaf06b84a8030bf6e1fba05ba46a8ab71fa6574a8feab3b31323f8573","observation_id":"f5387166-15c3-4418-991f-f71ac7d70efe","resolution":{"observed_at":"2026-08-10T15:07:02.472129Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1802.05668","last_updated":"2018-02-15T17:18:49Z","snapshot_observed_at":"2026-07-06T06:23:42.900306Z","submitted_at":"2018-02-15T17:18:49Z","title":"Model compression via distillation and quantization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1802.05668","snapshot_observed_at":"2026-08-10T15:07:02.475224Z","title":"Model compression via distillation and quantization","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2501.14531","last_updated":"2025-01-24T14:37:24Z","snapshot_observed_at":"2026-08-10T15:01:42.874211Z","submitted_at":"2025-01-24T14:37:24Z","title":"On Hardening DNNs against Noisy Computations","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-10T15:07:02.475224Z"},"links":{"cited_paper":"/paper/1802.05668","citing_paper":"/paper/2501.14531"},"observation_digest":"sha256:d781c7421c8ba6f2e195651ab78090963aafbd8f03bcec756f2579cb282e75e6","observation_id":"932bc61b-b53a-4f77-ab4b-15df4755ea93","resolution":{"observed_at":"2026-08-10T15:07:02.475224Z","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":"2026-08-10T15:07:02.975523Z","title":"Analog/mixed-signal hardware error modeling for deep learning inference","venue":null,"work_id":"2ee0307a-678b-455b-98d5-83fcb5ade85d","year":2019},"citing_paper":{"arxiv_id":"2501.14531","last_updated":"2025-01-24T14:37:24Z","snapshot_observed_at":"2026-08-10T15:01:42.874211Z","submitted_at":"2025-01-24T14:37:24Z","title":"On Hardening DNNs against Noisy Computations","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-10T15:07:02.478750Z"},"links":{"citing_paper":"/paper/2501.14531"},"observation_digest":"sha256:67d232bd00acc8daa2a506246c7e2a0fc8c9c9ac592d05d2a7cfae09a0ef352f","observation_id":"103c5167-09d7-46c7-a696-a53b9aeecbc0","resolution":{"observed_at":"2026-08-10T15:07:02.979416Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T15:07:02.964153Z","title":"Resource-Efficient Neural Net- works for Embedded Systems","venue":null,"work_id":"dbd5ad9c-e853-45eb-aa45-ff93fad03855","year":2024},"citing_paper":{"arxiv_id":"2501.14531","last_updated":"2025-01-24T14:37:24Z","snapshot_observed_at":"2026-08-10T15:01:42.874211Z","submitted_at":"2025-01-24T14:37:24Z","title":"On Hardening DNNs against Noisy Computations","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-10T15:07:02.481894Z"},"links":{"citing_paper":"/paper/2501.14531"},"observation_digest":"sha256:eb841f65862175ae1975e8029eedebac487761e67543f8ae20352a94cdc70762","observation_id":"77289342-5ed6-4640-809d-00cb86bb2e1b","resolution":{"observed_at":"2026-08-10T15:07:02.968155Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T15:07:02.951685Z","title":"Denoising noisy neural networks: A bayesian approach with compensation","venue":null,"work_id":"dd1ca57e-f1a3-429f-8afd-a712eac28659","year":2023},"citing_paper":{"arxiv_id":"2501.14531","last_updated":"2025-01-24T14:37:24Z","snapshot_observed_at":"2026-08-10T15:01:42.874211Z","submitted_at":"2025-01-24T14:37:24Z","title":"On Hardening DNNs against Noisy Computations","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-10T15:07:02.485710Z"},"links":{"citing_paper":"/paper/2501.14531"},"observation_digest":"sha256:743795a8a6c621bdc544e05ebe6e230f6643c683b7bfad03e67a56ff9f0cabf7","observation_id":"41d92f9e-7484-4a2f-b33c-1e4a9e26aa84","resolution":{"observed_at":"2026-08-10T15:07:02.956078Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T15:07:02.938993Z","title":"Deep learning with coherent nanophotonic circuits","venue":null,"work_id":"2ec0ce62-e93c-4a8a-aeb8-632113e94776","year":2017},"citing_paper":{"arxiv_id":"2501.14531","last_updated":"2025-01-24T14:37:24Z","snapshot_observed_at":"2026-08-10T15:01:42.874211Z","submitted_at":"2025-01-24T14:37:24Z","title":"On Hardening DNNs against Noisy Computations","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-10T15:07:02.489363Z"},"links":{"citing_paper":"/paper/2501.14531"},"observation_digest":"sha256:f172a8c6afdff6343cf2407c53a8d68265800b060f2c072ba79e8d1c95d52fe5","observation_id":"2fb8b824-7079-420b-a77a-31f40a00027a","resolution":{"observed_at":"2026-08-10T15:07:02.943357Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+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":"2026-08-10T15:07:02.926406Z","title":"Very deep convolutional networks for large-scale image recogni- tion","venue":null,"work_id":"330b2857-3f0f-4d5b-832d-dd64b8932e09","year":2014},"citing_paper":{"arxiv_id":"2501.14531","last_updated":"2025-01-24T14:37:24Z","snapshot_observed_at":"2026-08-10T15:01:42.874211Z","submitted_at":"2025-01-24T14:37:24Z","title":"On Hardening DNNs against Noisy Computations","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-10T15:07:02.493130Z"},"links":{"citing_paper":"/paper/2501.14531"},"observation_digest":"sha256:6a06dd4e8156e504876d59b1ed0061e80728eb346ddc423e42c3bbf8f8b8c918","observation_id":"63025512-0c23-4a9b-a16d-f57e2eb1efa3","resolution":{"observed_at":"2026-08-10T15:07:02.930763Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1511.06488","last_updated":"2016-01-07T13:50:22Z","snapshot_observed_at":"2026-07-06T04:37:10.505278Z","submitted_at":"2015-11-20T04:55:46Z","title":"Resiliency of Deep Neural Networks under Quantization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1511.06488","snapshot_observed_at":"2026-08-10T15:07:02.497062Z","title":"Resiliency of deep neural networks under quantiza- tion","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2501.14531","last_updated":"2025-01-24T14:37:24Z","snapshot_observed_at":"2026-08-10T15:01:42.874211Z","submitted_at":"2025-01-24T14:37:24Z","title":"On Hardening DNNs against Noisy Computations","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-10T15:07:02.497062Z"},"links":{"cited_paper":"/paper/1511.06488","citing_paper":"/paper/2501.14531"},"observation_digest":"sha256:5a65fae899c4abff366907468f26deec9ca17f3b1854ebd18fbd405c6e6d0fe7","observation_id":"3d6b475b-66da-4e39-9a15-f58a7d067144","resolution":{"observed_at":"2026-08-10T15:07:02.497062Z","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":"2026-08-10T15:07:02.914160Z","title":"Improving the robustness of analog deep neural networks through a Bayes-optimized noise injection approach","venue":null,"work_id":"23be7cf0-cd99-4c2c-80ff-7145502f66a6","year":2023},"citing_paper":{"arxiv_id":"2501.14531","last_updated":"2025-01-24T14:37:24Z","snapshot_observed_at":"2026-08-10T15:01:42.874211Z","submitted_at":"2025-01-24T14:37:24Z","title":"On Hardening DNNs against Noisy Computations","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-10T15:07:02.501237Z"},"links":{"citing_paper":"/paper/2501.14531"},"observation_digest":"sha256:afe20e48a90b712fd66704c34aa3fba4522d29e728cb4cc5d2914f5eb22ac1d5","observation_id":"72daa8a1-1ad0-4885-b2d5-8083054c0830","resolution":{"observed_at":"2026-08-10T15:07:02.918314Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2001.04974","last_updated":"2020-01-14T18:59:48Z","snapshot_observed_at":"2026-07-06T08:50:28.781109Z","submitted_at":"2020-01-14T18:59:48Z","title":"Noisy Machines: Understanding Noisy Neural Networks and Enhancing Robustness to Analog Hardware Errors Using Distillation","version":1},"cited_work":{"arxiv_id":"2001.04974","doi":null,"metadata_source":"pith","pith_arxiv_id":"2001.04974","snapshot_observed_at":"2026-08-10T15:07:02.626668Z","title":"Noisy Machines: Understanding Noisy Neural Networks and Enhancing Robustness to Analog Hardware Errors Using Distillation","venue":"cs.LG","work_id":"1c32c537-3596-4e51-b6e0-488fe6b66996","year":2020},"citing_paper":{"arxiv_id":"2501.14531","last_updated":"2025-01-24T14:37:24Z","snapshot_observed_at":"2026-08-10T15:01:42.874211Z","submitted_at":"2025-01-24T14:37:24Z","title":"On Hardening DNNs against Noisy Computations","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-10T15:07:02.505099Z"},"links":{"cited_paper":"/paper/2001.04974","citing_paper":"/paper/2501.14531"},"observation_digest":"sha256:fbbe5f49b89f298c7fabdca9b10437be215ca41406fbbc244d7ece79e377f8fd","observation_id":"ddefcb4d-621b-4f9f-b401-108d5f0492d6","resolution":{"observed_at":"2026-08-10T15:07:02.631470Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2501.14531","last_updated":"2025-01-24T14:37:24Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-10T15:01:42.874211Z","submitted_at":"2025-01-24T14:37:24Z","title":"On Hardening DNNs against Noisy Computations"},"reference_resolution":{"displayed":34,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":9,"verified_exact":6,"verified_fuzzy":19},"total_outbound_references":34},"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":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 34 of 34 outbound references and 0 inbound Pith citation observations for arXiv:2501.14531."}