{"as_of":"2026-08-17T13:36:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:b52025a5f4f0d6ad2705496a746f13bfa9adad60ea4691322155a5d1fdbfb6c3","coverage":[{"denominator":43,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":43,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T20:56:01.586850Z","state":"measured"},{"denominator":45,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":45,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-17T06:30:58.91139+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":"2026-06-30T22:37:13.002522Z","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":"2026-07-01T13:55:45.491954Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2505.11589","last_updated":"2025-05-16T18:00:02Z","snapshot_observed_at":"2026-08-15T20:49:21.280173Z","submitted_at":"2025-05-16T18:00:02Z","title":"A Training Framework for Optimal and Stable Training of Polynomial Neural Networks","version":1},"cited_work":{"arxiv_id":"2505.11589","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.11589","snapshot_observed_at":"2026-07-01T13:55:45.491954Z","title":null,"venue":null,"work_id":"8ff7d49e-2eab-425d-80b4-2aebf471e331","year":2025},"citing_paper":{"arxiv_id":"2605.09609","last_updated":"2026-06-17T23:10:51Z","snapshot_observed_at":"2026-08-15T16:19:29.932542Z","submitted_at":"2026-05-10T15:46:00Z","title":"Minimal Filling Architectures of Polynomial Neural Networks: Counterexamples, Frontier Search, and Defects","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-05-12T02:23:10.600301Z"},"links":{"cited_paper":"/paper/2505.11589","citing_paper":"/paper/2605.09609"},"observation_digest":"sha256:f720e141cd680ec69f7bb863357b53b7e0fe58d68c292101e8fa462b4c5133f3","observation_id":"98e168f1-a45d-418f-b5fa-6d4ac9fea195","resolution":{"observed_at":"2026-05-12T07:41:31.829274Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.11589","last_updated":"2025-05-16T18:00:02Z","snapshot_observed_at":"2026-08-15T20:49:21.280173Z","submitted_at":"2025-05-16T18:00:02Z","title":"A Training Framework for Optimal and Stable Training of Polynomial Neural Networks","version":1},"cited_work":{"arxiv_id":"2505.11589","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.11589","snapshot_observed_at":"2026-07-01T13:55:45.491954Z","title":null,"venue":null,"work_id":"8ff7d49e-2eab-425d-80b4-2aebf471e331","year":2025},"citing_paper":{"arxiv_id":"2605.09609","last_updated":"2026-06-17T23:10:51Z","snapshot_observed_at":"2026-08-15T16:19:29.932542Z","submitted_at":"2026-05-10T15:46:00Z","title":"Minimal Filling Architectures of Polynomial Neural Networks: Counterexamples, Frontier Search, and Defects","version":2},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-06-30T22:37:13.002522Z"},"links":{"cited_paper":"/paper/2505.11589","citing_paper":"/paper/2605.09609"},"observation_digest":"sha256:8494a98dabdb28500efd8d6c87deff075e5bbc842b62628d4b969d0fcd7e2255","observation_id":"c0a246ae-8607-4986-988b-b36017419078","resolution":{"observed_at":"2026-07-01T13:55:45.493334Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2505.11589/citation-record","integrity":"/paper/2505.11589/integrity","json":"/paper/2505.11589/citation-record.json","paper":"/paper/2505.11589"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:56:02.395247Z","title":"https://www.hhs.gov/hipaa/, 1996","venue":null,"work_id":"04068ddc-f19d-4f7f-a34b-ba1c1f78d0a9","year":1996},"citing_paper":{"arxiv_id":"2505.11589","last_updated":"2025-05-16T18:00:02Z","snapshot_observed_at":"2026-08-15T20:49:21.280173Z","submitted_at":"2025-05-16T18:00:02Z","title":"A Training Framework for Optimal and Stable Training of Polynomial Neural Networks","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-15T20:56:01.403827Z"},"links":{"citing_paper":"/paper/2505.11589"},"observation_digest":"sha256:7186fdf1084b25c78c9b14602d891776200cd8eb1c34a7612fb6986f3d5d409e","observation_id":"6269d8ed-3079-47fb-b2a8-2c6e418d81f5","resolution":{"observed_at":"2026-08-15T20:56:02.399063Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:56:02.382415Z","title":"http://data.europa.eu/eli/reg/2016/679/oj, 2016","venue":null,"work_id":"51856144-f5d2-4bab-b0a6-97d0a1b64d6c","year":2016},"citing_paper":{"arxiv_id":"2505.11589","last_updated":"2025-05-16T18:00:02Z","snapshot_observed_at":"2026-08-15T20:49:21.280173Z","submitted_at":"2025-05-16T18:00:02Z","title":"A Training Framework for Optimal and Stable Training of Polynomial Neural Networks","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-15T20:56:01.409772Z"},"links":{"citing_paper":"/paper/2505.11589"},"observation_digest":"sha256:2030ea937a6ed3aba20bbe320085678d2c3e924e2cbc446fe800c56d6e07d6c1","observation_id":"bbc023e2-6063-4462-b5de-c3c9ca54d8b2","resolution":{"observed_at":"2026-08-15T20:56:02.386379Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1902.01870","last_updated":"2019-02-05T19:07:07Z","snapshot_observed_at":"2026-08-14T17:20:36.024764Z","submitted_at":"2019-02-05T19:07:07Z","title":"Stabilizing Inputs to Approximated Nonlinear Functions for Inference with Homomorphic Encryption in Deep Neural Networks","version":1},"cited_work":{"arxiv_id":"1902.01870","doi":null,"metadata_source":"pith","pith_arxiv_id":"1902.01870","snapshot_observed_at":"2026-08-15T20:56:02.078662Z","title":"Stabilizing Inputs to Approximated Nonlinear Functions for Inference with Homomorphic Encryption in Deep Neural Networks","venue":"cs.LG","work_id":"7ee4a22a-d76b-4709-9ecc-37e721dbc1d8","year":2019},"citing_paper":{"arxiv_id":"2505.11589","last_updated":"2025-05-16T18:00:02Z","snapshot_observed_at":"2026-08-15T20:49:21.280173Z","submitted_at":"2025-05-16T18:00:02Z","title":"A Training Framework for Optimal and Stable Training of Polynomial Neural Networks","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-15T20:56:01.414308Z"},"links":{"cited_paper":"/paper/1902.01870","citing_paper":"/paper/2505.11589"},"observation_digest":"sha256:0762897b6fbc803921b77e23d26386a6a84901937fc58d4fb97fbdcd7deda4a8","observation_id":"45becb5b-ef18-4a06-80a9-9422e6440a16","resolution":{"observed_at":"2026-08-15T20:56:02.083376Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2011.05530","last_updated":"2024-02-06T08:29:25Z","snapshot_observed_at":"2026-08-16T19:06:42.019966Z","submitted_at":"2020-11-11T03:32:22Z","title":"On Polynomial Approximations for Privacy-Preserving and Verifiable ReLU Networks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2011.05530","snapshot_observed_at":"2026-08-15T20:56:01.420217Z","title":"Ali, Jinhyun So, and Amir Salman Avestimehr","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2505.11589","last_updated":"2025-05-16T18:00:02Z","snapshot_observed_at":"2026-08-15T20:49:21.280173Z","submitted_at":"2025-05-16T18:00:02Z","title":"A Training Framework for Optimal and Stable Training of Polynomial Neural Networks","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-15T20:56:01.420217Z"},"links":{"cited_paper":"/paper/2011.05530","citing_paper":"/paper/2505.11589"},"observation_digest":"sha256:a9dd7cc19bddc71ab5aee668dd4d28829d40cedd40151e2630fad0d82ae90945","observation_id":"6d70c6ef-0e97-4b08-bd7c-dfb0fa1c215f","resolution":{"observed_at":"2026-08-15T20:56:01.420217Z","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":"2026-08-15T20:56:02.369079Z","title":"OpenFHE : Open-source fully homomorphic encryption library","venue":null,"work_id":"38b9687c-424e-4f93-8696-f300188ad079","year":2022},"citing_paper":{"arxiv_id":"2505.11589","last_updated":"2025-05-16T18:00:02Z","snapshot_observed_at":"2026-08-15T20:49:21.280173Z","submitted_at":"2025-05-16T18:00:02Z","title":"A Training Framework for Optimal and Stable Training of Polynomial Neural Networks","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-15T20:56:01.425115Z"},"links":{"citing_paper":"/paper/2505.11589"},"observation_digest":"sha256:fb14b7a8943726331a3ac4dc582811ad76ececc091daaf709bc87b83c6e308e5","observation_id":"1933d993-922f-4f87-9ffd-222e273cecd9","resolution":{"observed_at":"2026-08-15T20:56:02.373484Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:56:02.355948Z","title":"A methodology for training homomorphic encryption friendly neural networks","venue":null,"work_id":"037a41a2-3791-4860-b547-7fd4db447ee5","year":2021},"citing_paper":{"arxiv_id":"2505.11589","last_updated":"2025-05-16T18:00:02Z","snapshot_observed_at":"2026-08-15T20:49:21.280173Z","submitted_at":"2025-05-16T18:00:02Z","title":"A Training Framework for Optimal and Stable Training of Polynomial Neural Networks","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-15T20:56:01.429587Z"},"links":{"citing_paper":"/paper/2505.11589"},"observation_digest":"sha256:15d63dbf66eae5b50b8987f6da78cda9bb4a02410a7793ed3ac5347523cc9515","observation_id":"e82395b3-af08-4beb-b608-a579d44141c8","resolution":{"observed_at":"2026-08-15T20:56:02.360046Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2304.14836","last_updated":"2023-06-11T10:07:52Z","snapshot_observed_at":"2026-08-16T15:37:25.601486Z","submitted_at":"2023-04-26T20:41:37Z","title":"Training Large Scale Polynomial CNNs for E2E Inference over Homomorphic Encryption","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.14836","snapshot_observed_at":"2026-08-15T20:56:01.434090Z","title":"Sensitive tuning of large scale cnns for e2e secure prediction using homomorphic encryption","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.11589","last_updated":"2025-05-16T18:00:02Z","snapshot_observed_at":"2026-08-15T20:49:21.280173Z","submitted_at":"2025-05-16T18:00:02Z","title":"A Training Framework for Optimal and Stable Training of Polynomial Neural Networks","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-15T20:56:01.434090Z"},"links":{"cited_paper":"/paper/2304.14836","citing_paper":"/paper/2505.11589"},"observation_digest":"sha256:f7dc587717cdef09276657847f17a30ea199d2dcce4efb8184d2cf9a955860b1","observation_id":"ca3b1825-4386-4f80-a6b4-9e7d9ecdc46d","resolution":{"observed_at":"2026-08-15T20:56:01.434090Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.04172","last_updated":"2019-08-29T19:16:10Z","snapshot_observed_at":"2026-08-16T11:45:50.652032Z","submitted_at":"2019-08-12T14:30:13Z","title":"nGraph-HE2: A High-Throughput Framework for Neural Network Inference on Encrypted Data","version":2},"cited_work":{"arxiv_id":"1908.04172","doi":null,"metadata_source":"pith","pith_arxiv_id":"1908.04172","snapshot_observed_at":"2026-08-15T20:56:02.034235Z","title":"nGraph-HE2: A High-Throughput Framework for Neural Network Inference on Encrypted Data","venue":"cs.CR","work_id":"66ea03fb-b726-4ac2-9149-d06f0cc6c897","year":2019},"citing_paper":{"arxiv_id":"2505.11589","last_updated":"2025-05-16T18:00:02Z","snapshot_observed_at":"2026-08-15T20:49:21.280173Z","submitted_at":"2025-05-16T18:00:02Z","title":"A Training Framework for Optimal and Stable Training of Polynomial Neural Networks","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-15T20:56:01.439774Z"},"links":{"cited_paper":"/paper/1908.04172","citing_paper":"/paper/2505.11589"},"observation_digest":"sha256:a8d196adb7b9ab5c72363bcd585839378aff997d8d7215d83ebe77f7d16c88f2","observation_id":"22cea893-1478-4bf7-979c-ffc69a0afcb9","resolution":{"observed_at":"2026-08-15T20:56:02.039047Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:56:02.343209Z","title":"Low latency privacy preserving inference","venue":null,"work_id":"57c9188d-1974-40cd-aa0a-0ae08de55384","year":2018},"citing_paper":{"arxiv_id":"2505.11589","last_updated":"2025-05-16T18:00:02Z","snapshot_observed_at":"2026-08-15T20:49:21.280173Z","submitted_at":"2025-05-16T18:00:02Z","title":"A Training Framework for Optimal and Stable Training of Polynomial Neural Networks","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-15T20:56:01.443829Z"},"links":{"citing_paper":"/paper/2505.11589"},"observation_digest":"sha256:23e885e15cb80e963ab878121410e7ec27b6fc1470df54c175b2ca31fd2cee52","observation_id":"9a62f445-ecfe-4f6d-88c6-f6a963c21af8","resolution":{"observed_at":"2026-08-15T20:56:02.347400Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:56:02.330203Z","title":"Capture-24: A large dataset of wrist-worn activity tracker data collected in the wild for human activity recognition","venue":null,"work_id":"dd8e64e9-0a13-45a8-bdd3-febb8fce56c6","year":2024},"citing_paper":{"arxiv_id":"2505.11589","last_updated":"2025-05-16T18:00:02Z","snapshot_observed_at":"2026-08-15T20:49:21.280173Z","submitted_at":"2025-05-16T18:00:02Z","title":"A Training Framework for Optimal and Stable Training of Polynomial Neural Networks","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-15T20:56:01.448161Z"},"links":{"citing_paper":"/paper/2505.11589"},"observation_digest":"sha256:7b0e8d89e648e785993b21e413a797bce0aba96fcb9064b2da898133051d9b7e","observation_id":"85f94d51-e455-4c01-9579-f5c5422cd696","resolution":{"observed_at":"2026-08-15T20:56:02.335001Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:56:02.317691Z","title":"Homomorphic encryption for arithmetic of approximate numbers","venue":null,"work_id":"9b23a6b6-4a63-4caf-9865-c3fafc156073","year":2017},"citing_paper":{"arxiv_id":"2505.11589","last_updated":"2025-05-16T18:00:02Z","snapshot_observed_at":"2026-08-15T20:49:21.280173Z","submitted_at":"2025-05-16T18:00:02Z","title":"A Training Framework for Optimal and Stable Training of Polynomial Neural Networks","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-15T20:56:01.452276Z"},"links":{"citing_paper":"/paper/2505.11589"},"observation_digest":"sha256:9a7924771e2021ca7bf5e924b3fc7d4f658bbbb82eae61a31f81e13887cbf8fb","observation_id":"6ed75fd9-519e-4d44-9f72-8e1b00b3fe4a","resolution":{"observed_at":"2026-08-15T20:56:02.321794Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:56:02.305243Z","title":"Chrysos, Stylianos Moschoglou, Giorgos Bouritsas, Yannis Panagakis, Jiankang Deng, and Stefanos Zafeiriou","venue":null,"work_id":"24fff8b3-fe4e-45fe-bf50-80d681d4aed2","year":2020},"citing_paper":{"arxiv_id":"2505.11589","last_updated":"2025-05-16T18:00:02Z","snapshot_observed_at":"2026-08-15T20:49:21.280173Z","submitted_at":"2025-05-16T18:00:02Z","title":"A Training Framework for Optimal and Stable Training of Polynomial Neural Networks","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-15T20:56:01.456848Z"},"links":{"citing_paper":"/paper/2505.11589"},"observation_digest":"sha256:ced62ce23f0b7428655f265329d5f39ed08b69fb3163599409faf2713f264844","observation_id":"1b53140e-0f4c-4d09-bb17-cfc1ea9bfcec","resolution":{"observed_at":"2026-08-15T20:56:02.309291Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:56:01.460583Z","title":"The mnist database of handwritten digit images for machine learning research","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2505.11589","last_updated":"2025-05-16T18:00:02Z","snapshot_observed_at":"2026-08-15T20:49:21.280173Z","submitted_at":"2025-05-16T18:00:02Z","title":"A Training Framework for Optimal and Stable Training of Polynomial Neural Networks","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-15T20:56:01.460583Z"},"links":{"citing_paper":"/paper/2505.11589"},"observation_digest":"sha256:9a3d1126faf40790e738bc8962d9d16e2b2cbec7238c9a58fbfd0fe0f83b5c6e","observation_id":"10e910a1-c9c3-48cb-92c5-332219328e4f","resolution":{"observed_at":"2026-08-15T20:56:01.460583Z","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":"2026-08-15T20:56:02.281440Z","title":"Cryptonets: applying neural networks to encrypted data with high throughput and accuracy","venue":null,"work_id":"84415925-dd1f-418a-b16b-ca64d185e57b","year":null},"citing_paper":{"arxiv_id":"2505.11589","last_updated":"2025-05-16T18:00:02Z","snapshot_observed_at":"2026-08-15T20:49:21.280173Z","submitted_at":"2025-05-16T18:00:02Z","title":"A Training Framework for Optimal and Stable Training of Polynomial Neural Networks","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-15T20:56:01.464746Z"},"links":{"citing_paper":"/paper/2505.11589"},"observation_digest":"sha256:4f7c7e553e9a4b88e812d7f8ee60ed18764e0865e5cc4935d053c35620ba6a45","observation_id":"f01026af-98ca-4500-bb08-220f82579667","resolution":{"observed_at":"2026-08-15T20:56:02.286420Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2205.14108","last_updated":"2022-10-18T18:48:56Z","snapshot_observed_at":"2026-08-16T16:57:07.666756Z","submitted_at":"2022-05-27T17:19:05Z","title":"Scalable Interpretability via Polynomials","version":4},"cited_work":{"arxiv_id":"2205.14108","doi":"10.48550/arxiv.2205.14108","metadata_source":"pith","pith_arxiv_id":"2205.14108","snapshot_observed_at":"2026-08-16T12:16:17.039197Z","title":"Scalable Interpretability via Polynomials","venue":"cs.LG","work_id":"f4f43319-7948-41f3-a200-99c9f3e69d21","year":2022},"citing_paper":{"arxiv_id":"2505.11589","last_updated":"2025-05-16T18:00:02Z","snapshot_observed_at":"2026-08-15T20:49:21.280173Z","submitted_at":"2025-05-16T18:00:02Z","title":"A Training Framework for Optimal and Stable Training of Polynomial Neural Networks","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-15T20:56:01.469054Z"},"links":{"cited_paper":"/paper/2205.14108","citing_paper":"/paper/2505.11589"},"observation_digest":"sha256:17e99fba869d69fac303fe12217af92bcc3f28843c882dfb496cac48995986b6","observation_id":"1220f43c-6dfe-4a1d-8a4f-2244adeac1e0","resolution":{"observed_at":"2026-08-15T20:56:01.671588Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:56:02.266783Z","title":"A new remez-type algorithm for best polynomial approximation","venue":null,"work_id":"f186b304-2f40-4de6-ad3b-0f59069686b9","year":2020},"citing_paper":{"arxiv_id":"2505.11589","last_updated":"2025-05-16T18:00:02Z","snapshot_observed_at":"2026-08-15T20:49:21.280173Z","submitted_at":"2025-05-16T18:00:02Z","title":"A Training Framework for Optimal and Stable Training of Polynomial Neural Networks","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-15T20:56:01.473265Z"},"links":{"citing_paper":"/paper/2505.11589"},"observation_digest":"sha256:f76a2390208e5a3e9e3f8f1608431c2094f70e42631fccab803daa5a29cfac40","observation_id":"b4d8d4d6-7fa3-45cf-b232-91ac52aea5f1","resolution":{"observed_at":"2026-08-15T20:56:02.270758Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:56:02.252999Z","title":"Interpretable polynomial neural ordinary differential equations","venue":null,"work_id":"30829e4c-c0c2-4a46-9dc8-1e06372fbe79","year":2022},"citing_paper":{"arxiv_id":"2505.11589","last_updated":"2025-05-16T18:00:02Z","snapshot_observed_at":"2026-08-15T20:49:21.280173Z","submitted_at":"2025-05-16T18:00:02Z","title":"A Training Framework for Optimal and Stable Training of Polynomial Neural Networks","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-15T20:56:01.477688Z"},"links":{"citing_paper":"/paper/2505.11589"},"observation_digest":"sha256:78835d224bfa6609528c509afd79126d85a2e1070910966531d16323c7b37a81","observation_id":"345f5721-91fc-4b75-ab88-2cf69efa5bff","resolution":{"observed_at":"2026-08-15T20:56:02.257432Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:56:02.241455Z","title":"Polynomial activation functions","venue":null,"work_id":"07d7bcb1-625e-4ff0-819d-2ac41fdf70ec","year":2020},"citing_paper":{"arxiv_id":"2505.11589","last_updated":"2025-05-16T18:00:02Z","snapshot_observed_at":"2026-08-15T20:49:21.280173Z","submitted_at":"2025-05-16T18:00:02Z","title":"A Training Framework for Optimal and Stable Training of Polynomial Neural Networks","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-15T20:56:01.482809Z"},"links":{"citing_paper":"/paper/2505.11589"},"observation_digest":"sha256:56d68d42dc7259e857e6ba6e22be10b3db82a978a960befe73cb4b20961a42f4","observation_id":"6ec59626-46dc-4d54-8a2d-ad235dabd788","resolution":{"observed_at":"2026-08-15T20:56:02.245413Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:56:01.487179Z","title":"Improved polynomial neural networks with normalised activations","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.11589","last_updated":"2025-05-16T18:00:02Z","snapshot_observed_at":"2026-08-15T20:49:21.280173Z","submitted_at":"2025-05-16T18:00:02Z","title":"A Training Framework for Optimal and Stable Training of Polynomial Neural Networks","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-15T20:56:01.487179Z"},"links":{"citing_paper":"/paper/2505.11589"},"observation_digest":"sha256:eb41b2b885539c9a9a227514138d03579a83caa4c4be88a9fd0333865b8017bb","observation_id":"0a986940-2b8d-400e-bc2f-06d11a822ec4","resolution":{"observed_at":"2026-08-15T20:56:01.487179Z","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":"2026-08-15T20:56:02.229955Z","title":"Zhang, Shaoqing Ren, and Jian Sun","venue":null,"work_id":"445eefc9-2741-4974-a025-cdafac6ce976","year":2015},"citing_paper":{"arxiv_id":"2505.11589","last_updated":"2025-05-16T18:00:02Z","snapshot_observed_at":"2026-08-15T20:49:21.280173Z","submitted_at":"2025-05-16T18:00:02Z","title":"A Training Framework for Optimal and Stable Training of Polynomial Neural Networks","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-15T20:56:01.491759Z"},"links":{"citing_paper":"/paper/2505.11589"},"observation_digest":"sha256:16fdec4b77f6c640fb9f5bc364a1af992e42a423b6c40bfc263382668005b577","observation_id":"df023d95-682f-4520-8ab6-cf6cf7ac29a9","resolution":{"observed_at":"2026-08-15T20:56:02.233995Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1711.05189","last_updated":"2017-11-14T16:53:39Z","snapshot_observed_at":"2026-08-16T18:40:57.312906Z","submitted_at":"2017-11-14T16:53:39Z","title":"CryptoDL: Deep Neural Networks over Encrypted Data","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.05189","snapshot_observed_at":"2026-08-15T20:56:01.496232Z","title":"Cryptodl: Deep neural networks over encrypted data","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.11589","last_updated":"2025-05-16T18:00:02Z","snapshot_observed_at":"2026-08-15T20:49:21.280173Z","submitted_at":"2025-05-16T18:00:02Z","title":"A Training Framework for Optimal and Stable Training of Polynomial Neural Networks","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-15T20:56:01.496232Z"},"links":{"cited_paper":"/paper/1711.05189","citing_paper":"/paper/2505.11589"},"observation_digest":"sha256:ec74a1ac458cf5928c054ebf99427f5310e33b21f9fccbe485f4b1683c7a84ad","observation_id":"9fcb701d-abca-4e7f-b29a-a2d1290effac","resolution":{"observed_at":"2026-08-15T20:56:01.496232Z","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":"2026-08-15T20:56:01.501340Z","title":"Stinchcombe, and Halbert L","venue":null,"work_id":null,"year":1989},"citing_paper":{"arxiv_id":"2505.11589","last_updated":"2025-05-16T18:00:02Z","snapshot_observed_at":"2026-08-15T20:49:21.280173Z","submitted_at":"2025-05-16T18:00:02Z","title":"A Training Framework for Optimal and Stable Training of Polynomial Neural Networks","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-15T20:56:01.501340Z"},"links":{"citing_paper":"/paper/2505.11589"},"observation_digest":"sha256:37b7c53a60fc8efab6794efc3dd1817c13aa3e7459a493a49489bc942104ed6e","observation_id":"92c0ea08-3000-448e-8145-558f1533941c","resolution":{"observed_at":"2026-08-15T20:56:01.501340Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1502.03167","last_updated":"2015-03-02T20:44:12Z","snapshot_observed_at":"2026-08-12T21:01:12.961874Z","submitted_at":"2015-02-11T01:44:18Z","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1502.03167","snapshot_observed_at":"2026-08-15T20:56:01.505131Z","title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2505.11589","last_updated":"2025-05-16T18:00:02Z","snapshot_observed_at":"2026-08-15T20:49:21.280173Z","submitted_at":"2025-05-16T18:00:02Z","title":"A Training Framework for Optimal and Stable Training of Polynomial Neural Networks","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-15T20:56:01.505131Z"},"links":{"cited_paper":"/paper/1502.03167","citing_paper":"/paper/2505.11589"},"observation_digest":"sha256:915ff1f8c659ab6d8c37c57c04b12268f978dfd5be7efbfc13d34b7c12e24999","observation_id":"43198825-9346-49bd-9e99-ab9d085bcf54","resolution":{"observed_at":"2026-08-15T20:56:01.505131Z","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":"2026-08-15T20:56:02.209322Z","title":"Highly accurate cnn inference using approximate activation functions over homomorphic encryption","venue":null,"work_id":"dd41e8ff-4aeb-43ce-8123-c041fc3bdaab","year":2020},"citing_paper":{"arxiv_id":"2505.11589","last_updated":"2025-05-16T18:00:02Z","snapshot_observed_at":"2026-08-15T20:49:21.280173Z","submitted_at":"2025-05-16T18:00:02Z","title":"A Training Framework for Optimal and Stable Training of Polynomial Neural Networks","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-15T20:56:01.509110Z"},"links":{"citing_paper":"/paper/2505.11589"},"observation_digest":"sha256:7e3cef5c22ae84f4a61d913f16623842c55d8c65c1447b57b6271c80f0091e01","observation_id":"ce8660ca-23f4-47d7-bc74-6fd7ec1b8d9f","resolution":{"observed_at":"2026-08-15T20:56:02.213419Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:56:02.197098Z","title":"GAZELLE : A low latency framework for secure neural network inference","venue":null,"work_id":"638ae578-99c4-44a9-a536-00ea1c389a15","year":2018},"citing_paper":{"arxiv_id":"2505.11589","last_updated":"2025-05-16T18:00:02Z","snapshot_observed_at":"2026-08-15T20:49:21.280173Z","submitted_at":"2025-05-16T18:00:02Z","title":"A Training Framework for Optimal and Stable Training of Polynomial Neural Networks","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-15T20:56:01.512825Z"},"links":{"citing_paper":"/paper/2505.11589"},"observation_digest":"sha256:387cfbdcca7a7428751319bd5ee94602ef803fcd792ffe81b097f56c784b3feb","observation_id":"b6e45fd2-e068-4512-b0fa-a7e039dd9ded","resolution":{"observed_at":"2026-08-15T20:56:02.201135Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:56:01.516594Z","title":"Universal Approximation with Deep Narrow Networks","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.11589","last_updated":"2025-05-16T18:00:02Z","snapshot_observed_at":"2026-08-15T20:49:21.280173Z","submitted_at":"2025-05-16T18:00:02Z","title":"A Training Framework for Optimal and Stable Training of Polynomial Neural Networks","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-15T20:56:01.516594Z"},"links":{"citing_paper":"/paper/2505.11589"},"observation_digest":"sha256:9667c3116efda5eadd7b823b7e2be795c9645801cd627ef821905bca606907dc","observation_id":"2d3cfee1-3304-4cf7-8910-0a90666052c1","resolution":{"observed_at":"2026-08-15T20:56:01.516594Z","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":"2026-08-15T20:56:02.177844Z","title":"On the expressive power of deep polynomial neural networks","venue":null,"work_id":"0cafd128-565f-4a32-a00e-990c3466a8e7","year":2019},"citing_paper":{"arxiv_id":"2505.11589","last_updated":"2025-05-16T18:00:02Z","snapshot_observed_at":"2026-08-15T20:49:21.280173Z","submitted_at":"2025-05-16T18:00:02Z","title":"A Training Framework for Optimal and Stable Training of Polynomial Neural Networks","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-15T20:56:01.521241Z"},"links":{"citing_paper":"/paper/2505.11589"},"observation_digest":"sha256:38b25e4a8390542f6ab49f3cd83a1c28b56d0c500c417c71d45a2bfc7d9e1d32","observation_id":"5ef0a224-1688-4933-8160-9287a9387f06","resolution":{"observed_at":"2026-08-15T20:56:02.181922Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:56:01.525314Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2505.11589","last_updated":"2025-05-16T18:00:02Z","snapshot_observed_at":"2026-08-15T20:49:21.280173Z","submitted_at":"2025-05-16T18:00:02Z","title":"A Training Framework for Optimal and Stable Training of Polynomial Neural Networks","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-15T20:56:01.525314Z"},"links":{"citing_paper":"/paper/2505.11589"},"observation_digest":"sha256:f3fe52fd67a062a1e3b6942aa69dd05029cdc95c4403bd82099e047bf8f72f17","observation_id":"8acb6cfc-d6cf-4f32-b524-35991fb715c7","resolution":{"observed_at":"2026-08-15T20:56:01.525314Z","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":"2026-08-15T20:56:01.530380Z","title":"Cifar-100 (canadian institute for advanced research)","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.11589","last_updated":"2025-05-16T18:00:02Z","snapshot_observed_at":"2026-08-15T20:49:21.280173Z","submitted_at":"2025-05-16T18:00:02Z","title":"A Training Framework for Optimal and Stable Training of Polynomial Neural Networks","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-15T20:56:01.530380Z"},"links":{"citing_paper":"/paper/2505.11589"},"observation_digest":"sha256:8fb6ca6dfbc389c1f0a61cd9a1021bcc68c3e62e8fa877701efab4262bb2ae15","observation_id":"90ee0873-8d47-44ac-9e61-3634ff5757b9","resolution":{"observed_at":"2026-08-15T20:56:01.530380Z","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":"2026-08-15T20:56:02.148176Z","title":"Precise approximation of convolutional neural networks for homomorphically encrypted data","venue":null,"work_id":"95f8a9c4-507d-48a4-803b-16082d523833","year":2021},"citing_paper":{"arxiv_id":"2505.11589","last_updated":"2025-05-16T18:00:02Z","snapshot_observed_at":"2026-08-15T20:49:21.280173Z","submitted_at":"2025-05-16T18:00:02Z","title":"A Training Framework for Optimal and Stable Training of Polynomial Neural Networks","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-15T20:56:01.534547Z"},"links":{"citing_paper":"/paper/2505.11589"},"observation_digest":"sha256:765a37163cf568e72364ac1efc7e0bfe3976c28a30ddbdba3ffe12fc2f477272","observation_id":"e659526e-56e2-4568-a644-aa55d79313bd","resolution":{"observed_at":"2026-08-15T20:56:02.152908Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:56:01.538726Z","title":"Optimized layerwise approximation for efficient private inference on fully homomorphic encryption, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.11589","last_updated":"2025-05-16T18:00:02Z","snapshot_observed_at":"2026-08-15T20:49:21.280173Z","submitted_at":"2025-05-16T18:00:02Z","title":"A Training Framework for Optimal and Stable Training of Polynomial Neural Networks","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-15T20:56:01.538726Z"},"links":{"citing_paper":"/paper/2505.11589"},"observation_digest":"sha256:568536f71ab015d90614421633621c52b2cc6b9e6e2a4f33c28a90f795145d93","observation_id":"72fb29c9-c677-4f07-b6d8-dc6114069799","resolution":{"observed_at":"2026-08-15T20:56:01.538726Z","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":"2026-08-15T20:56:02.136161Z","title":"Decoupled weight decay regularization","venue":null,"work_id":"9df8d426-7cd6-498f-8463-dc6deb7afd65","year":2017},"citing_paper":{"arxiv_id":"2505.11589","last_updated":"2025-05-16T18:00:02Z","snapshot_observed_at":"2026-08-15T20:49:21.280173Z","submitted_at":"2025-05-16T18:00:02Z","title":"A Training Framework for Optimal and Stable Training of Polynomial Neural Networks","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-15T20:56:01.542438Z"},"links":{"citing_paper":"/paper/2505.11589"},"observation_digest":"sha256:496c42f7b1eb9f4cc70adaedcdeb43c7253c74ec6221072106e86cef11d0584f","observation_id":"01ba7b84-619e-491e-b9fc-05d80238c51a","resolution":{"observed_at":"2026-08-15T20:56:02.140037Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.24033/bsmf.989","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:56:01.648968Z","title":null,"venue":null,"work_id":"2c761d0b-68e6-4879-9fe9-7c16aaa2808b","year":1918},"citing_paper":{"arxiv_id":"2505.11589","last_updated":"2025-05-16T18:00:02Z","snapshot_observed_at":"2026-08-15T20:49:21.280173Z","submitted_at":"2025-05-16T18:00:02Z","title":"A Training Framework for Optimal and Stable Training of Polynomial Neural Networks","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-15T20:56:01.545979Z"},"links":{"citing_paper":"/paper/2505.11589"},"observation_digest":"sha256:ba0eebc24cb6f0bf2fdd9790e0bc5defe09a9d8dfa2a24fe812626975bc1b03c","observation_id":"1965d21a-4a76-47aa-8de3-e829b9d02901","resolution":{"observed_at":"2026-08-15T20:56:01.652973Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:56:02.124222Z","title":"Trefethen","venue":null,"work_id":"262e2e19-a2e2-4d3c-bc4d-92974ff75b56","year":2009},"citing_paper":{"arxiv_id":"2505.11589","last_updated":"2025-05-16T18:00:02Z","snapshot_observed_at":"2026-08-15T20:49:21.280173Z","submitted_at":"2025-05-16T18:00:02Z","title":"A Training Framework for Optimal and Stable Training of Polynomial Neural Networks","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-15T20:56:01.550034Z"},"links":{"citing_paper":"/paper/2505.11589"},"observation_digest":"sha256:a923ffdea29c8838c52d6577af578490cc5041b3cfe085a272dfd96522eeee64","observation_id":"a173cf94-5214-4a20-afeb-da4f50ba2bb5","resolution":{"observed_at":"2026-08-15T20:56:02.127993Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2201.06699","last_updated":"2022-02-18T05:10:15Z","snapshot_observed_at":"2026-08-16T17:27:45.105538Z","submitted_at":"2022-01-18T02:02:02Z","title":"AESPA: Accuracy Preserving Low-degree Polynomial Activation for Fast Private Inference","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.06699","snapshot_observed_at":"2026-08-15T20:56:01.555163Z","title":"AESPA: accuracy preserving low-degree polynomial activation for fast private inference","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.11589","last_updated":"2025-05-16T18:00:02Z","snapshot_observed_at":"2026-08-15T20:49:21.280173Z","submitted_at":"2025-05-16T18:00:02Z","title":"A Training Framework for Optimal and Stable Training of Polynomial Neural Networks","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-15T20:56:01.555163Z"},"links":{"cited_paper":"/paper/2201.06699","citing_paper":"/paper/2505.11589"},"observation_digest":"sha256:a87e6c915b60a17c22a69ebac27ce759befea59f398ef9ade50384e284ba2e97","observation_id":"058db889-b768-4322-9bf4-6baf69b74958","resolution":{"observed_at":"2026-08-15T20:56:01.555163Z","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":"10.1371/journal.pone.0306420","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T20:56:01.633703Z","title":"Self-learning activation functions to increase accuracy of privacy-preserving convolutional neural networks with homomorphic encryption","venue":null,"work_id":"64067b97-7711-4b50-9039-9e515483e4bf","year":2024},"citing_paper":{"arxiv_id":"2505.11589","last_updated":"2025-05-16T18:00:02Z","snapshot_observed_at":"2026-08-15T20:49:21.280173Z","submitted_at":"2025-05-16T18:00:02Z","title":"A Training Framework for Optimal and Stable Training of Polynomial Neural Networks","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-15T20:56:01.559703Z"},"links":{"citing_paper":"/paper/2505.11589"},"observation_digest":"sha256:c3496d19a4647d0afa74336c89094fc3fd4423a6d4195b932bd0131988b0b5c2","observation_id":"11a1a3bd-27e0-46fc-ac32-e24d189e7635","resolution":{"observed_at":"2026-08-15T20:56:01.640324Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:56:01.563473Z","title":"Human Activity Recognition Using Smartphones","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2505.11589","last_updated":"2025-05-16T18:00:02Z","snapshot_observed_at":"2026-08-15T20:49:21.280173Z","submitted_at":"2025-05-16T18:00:02Z","title":"A Training Framework for Optimal and Stable Training of Polynomial Neural Networks","version":1},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-15T20:56:01.563473Z"},"links":{"citing_paper":"/paper/2505.11589"},"observation_digest":"sha256:ee0fb3e5ea66539631bb1154bb136d357f3aba27387b05ad7181c628492c591f","observation_id":"fde89be1-e3d2-4b01-a1cc-1d57ef8dc496","resolution":{"observed_at":"2026-08-15T20:56:01.563473Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1804.03209","last_updated":"2018-04-09T19:58:17Z","snapshot_observed_at":"2026-08-15T16:28:51.252929Z","submitted_at":"2018-04-09T19:58:17Z","title":"Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1804.03209","snapshot_observed_at":"2026-08-15T20:56:01.567406Z","title":"Speech commands: A dataset for limited-vocabulary speech recognition, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.11589","last_updated":"2025-05-16T18:00:02Z","snapshot_observed_at":"2026-08-15T20:49:21.280173Z","submitted_at":"2025-05-16T18:00:02Z","title":"A Training Framework for Optimal and Stable Training of Polynomial Neural Networks","version":1},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-15T20:56:01.567406Z"},"links":{"cited_paper":"/paper/1804.03209","citing_paper":"/paper/2505.11589"},"observation_digest":"sha256:a64e2e2cf13623809cd61614cf8d5c2d865c666b630096e3becf5df3dab0a601","observation_id":"7e8bcd8b-218e-4b4c-bb0d-dccd6668fbc1","resolution":{"observed_at":"2026-08-15T20:56:01.567406Z","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":"2026-08-15T20:56:01.571267Z","title":"Ppolynets: Achieving high prediction accuracy and efficiency with parametric polynomial activations","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.11589","last_updated":"2025-05-16T18:00:02Z","snapshot_observed_at":"2026-08-15T20:49:21.280173Z","submitted_at":"2025-05-16T18:00:02Z","title":"A Training Framework for Optimal and Stable Training of Polynomial Neural Networks","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-15T20:56:01.571267Z"},"links":{"citing_paper":"/paper/2505.11589"},"observation_digest":"sha256:f50a1a9ff4895cc254c7182ea631cb55dc11fee4f314f3031834fc680dd36aa9","observation_id":"0580d3f4-ea2f-4a55-8e8a-e5f6042864c4","resolution":{"observed_at":"2026-08-15T20:56:01.571267Z","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":"2026-08-15T20:56:02.111397Z","title":"Extrapolation of polynomial nets and their generalization guarantees, 2022","venue":null,"work_id":"9b5c0ce2-d695-4c6b-9a80-397a4894c65c","year":2022},"citing_paper":{"arxiv_id":"2505.11589","last_updated":"2025-05-16T18:00:02Z","snapshot_observed_at":"2026-08-15T20:49:21.280173Z","submitted_at":"2025-05-16T18:00:02Z","title":"A Training Framework for Optimal and Stable Training of Polynomial Neural Networks","version":1},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-15T20:56:01.575452Z"},"links":{"citing_paper":"/paper/2505.11589"},"observation_digest":"sha256:bf00eb205946a0d840cc123aabf6b0d6f409fa41f897cf9b966654208807b05d","observation_id":"251aeaad-5bda-4e85-841e-83a8330b2242","resolution":{"observed_at":"2026-08-15T20:56:02.115641Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-15T20:56:01.579335Z","title":"Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.11589","last_updated":"2025-05-16T18:00:02Z","snapshot_observed_at":"2026-08-15T20:49:21.280173Z","submitted_at":"2025-05-16T18:00:02Z","title":"A Training Framework for Optimal and Stable Training of Polynomial Neural Networks","version":1},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-15T20:56:01.579335Z"},"links":{"citing_paper":"/paper/2505.11589"},"observation_digest":"sha256:9b49aba3dfd63fa373ccebcadc1fb8b4aced31b6900df49c336b6a403d8020bc","observation_id":"e5525528-f5d7-487b-9dc4-6903c5c3e269","resolution":{"observed_at":"2026-08-15T20:56:01.579335Z","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":"2026-08-15T20:56:01.583044Z","title":"Polynomial activation neural networks: Modeling, stability analysis and coverage bp-training","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.11589","last_updated":"2025-05-16T18:00:02Z","snapshot_observed_at":"2026-08-15T20:49:21.280173Z","submitted_at":"2025-05-16T18:00:02Z","title":"A Training Framework for Optimal and Stable Training of Polynomial Neural Networks","version":1},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-15T20:56:01.583044Z"},"links":{"citing_paper":"/paper/2505.11589"},"observation_digest":"sha256:3121885eb66e8ef66255bd476b967457737eed98e090527148383746e2fd3acb","observation_id":"74eb3189-1c9d-404d-8d73-7fc855f1b184","resolution":{"observed_at":"2026-08-15T20:56:01.583044Z","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":"2026-08-15T20:56:02.092287Z","title":"Converting transformers to polynomial form for secure inference over homomorphic encryption, 2023","venue":null,"work_id":"a7ee83bd-38d3-4f7f-9d4e-42ebda147b17","year":2023},"citing_paper":{"arxiv_id":"2505.11589","last_updated":"2025-05-16T18:00:02Z","snapshot_observed_at":"2026-08-15T20:49:21.280173Z","submitted_at":"2025-05-16T18:00:02Z","title":"A Training Framework for Optimal and Stable Training of Polynomial Neural Networks","version":1},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-15T20:56:01.586850Z"},"links":{"citing_paper":"/paper/2505.11589"},"observation_digest":"sha256:a6b47eae8060bf902a81bc6c1c3f11b56a0d1c91492646b2b312d76992c20c6e","observation_id":"4d107f10-fa5e-41a5-a054-c0500f1da844","resolution":{"observed_at":"2026-08-15T20:56:02.097091Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2505.11589","last_updated":"2025-05-16T18:00:02Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-15T20:49:21.280173Z","submitted_at":"2025-05-16T18:00:02Z","title":"A Training Framework for Optimal and Stable Training of Polynomial Neural Networks"},"reference_resolution":{"displayed":43,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":17,"verified_exact":5,"verified_fuzzy":21},"total_outbound_references":43},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 43 of 43 outbound references and 2 inbound Pith citation observations for arXiv:2505.11589."}