{"as_of":"2026-08-10T11:00:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:6124359ed575b4ff1c0d0c1a0daf869e453ea8364c55864857c57bddfea6e76b","coverage":[{"denominator":47,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":47,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T12:39:11.694265Z","state":"measured"},{"denominator":47,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":47,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+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/2507.22090/citation-record","integrity":"/paper/2507.22090/integrity","json":"/paper/2507.22090/citation-record.json","paper":"/paper/2507.22090"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"1412.6830","last_updated":"2015-04-21T08:05:02Z","snapshot_observed_at":"2026-08-08T10:22:07.293115Z","submitted_at":"2014-12-21T20:20:21Z","title":"Learning Activation Functions to Improve Deep Neural Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6830","snapshot_observed_at":"2026-08-06T12:39:07.140374Z","title":"& Baldi, P","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2507.22090","last_updated":"2025-07-29T09:21:57Z","snapshot_observed_at":"2026-08-09T00:13:47.609729Z","submitted_at":"2025-07-29T09:21:57Z","title":"Hybrid activation functions for deep neural networks: S3 and S4 -- a novel approach to gradient flow optimization","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T12:39:07.140374Z"},"links":{"cited_paper":"/paper/1412.6830","citing_paper":"/paper/2507.22090"},"observation_digest":"sha256:a75cc77ce233ad91eb3eaea4f6b6ef70c2ad56166821ba6214a12f5b992d7a29","observation_id":"f8012c82-7e0a-4186-b24a-9512c31fda49","resolution":{"observed_at":"2026-08-06T12:39:07.140374Z","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":"2026-08-06T12:39:17.580244Z","title":"& Prevete, R","venue":null,"work_id":"3dd79b3d-fa64-463b-b8a1-62d461fb18df","year":2021},"citing_paper":{"arxiv_id":"2507.22090","last_updated":"2025-07-29T09:21:57Z","snapshot_observed_at":"2026-08-09T00:13:47.609729Z","submitted_at":"2025-07-29T09:21:57Z","title":"Hybrid activation functions for deep neural networks: S3 and S4 -- a novel approach to gradient flow optimization","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T12:39:07.190869Z"},"links":{"citing_paper":"/paper/2507.22090"},"observation_digest":"sha256:9ae0678cabab511368a60d5f256164154dcf8b2587cf2d40faa1f9de048f10be","observation_id":"002e5468-6f4f-4edb-8821-c57bc3685015","resolution":{"observed_at":"2026-08-06T12:39:17.655232Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T12:39:07.285193Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.22090","last_updated":"2025-07-29T09:21:57Z","snapshot_observed_at":"2026-08-09T00:13:47.609729Z","submitted_at":"2025-07-29T09:21:57Z","title":"Hybrid activation functions for deep neural networks: S3 and S4 -- a novel approach to gradient flow optimization","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T12:39:07.285193Z"},"links":{"citing_paper":"/paper/2507.22090"},"observation_digest":"sha256:8b67dd9b752ce0965aa5cdcc37a7f54ccf233c08bac53e7eb845d31c12a7a6fd","observation_id":"d3c642c3-1e8a-4451-b888-eef108e8fd55","resolution":{"observed_at":"2026-08-06T12:39:07.285193Z","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":"2026-08-06T12:39:17.424564Z","title":"Gomez, Łukasz Kaiser, and Illia Polosukhin","venue":null,"work_id":"b1981044-5de2-42a4-ad3e-bcf2de3eb8f3","year":2017},"citing_paper":{"arxiv_id":"2507.22090","last_updated":"2025-07-29T09:21:57Z","snapshot_observed_at":"2026-08-09T00:13:47.609729Z","submitted_at":"2025-07-29T09:21:57Z","title":"Hybrid activation functions for deep neural networks: S3 and S4 -- a novel approach to gradient flow optimization","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T12:39:07.415846Z"},"links":{"citing_paper":"/paper/2507.22090"},"observation_digest":"sha256:7b8b2eb2b31767912ab42412afd5c7afc6d6f8b9e70ecf7143314be7d9f3621d","observation_id":"b1352200-5678-499d-99ba-d8be0f93f2d8","resolution":{"observed_at":"2026-08-06T12:39:17.511608Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T12:39:07.595597Z","title":"Activation functions and their characteristics in deep neural networks,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2507.22090","last_updated":"2025-07-29T09:21:57Z","snapshot_observed_at":"2026-08-09T00:13:47.609729Z","submitted_at":"2025-07-29T09:21:57Z","title":"Hybrid activation functions for deep neural networks: S3 and S4 -- a novel approach to gradient flow optimization","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T12:39:07.595597Z"},"links":{"citing_paper":"/paper/2507.22090"},"observation_digest":"sha256:0f8aa72d70201ef4bd258af9da5c7cf7c89a47ccf59c2c38234c8c518788390f","observation_id":"a9fe7327-e0e7-41c1-a2c6-158277c0645f","resolution":{"observed_at":"2026-08-06T12:39:07.595597Z","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":"2026-08-06T12:39:17.301723Z","title":"& Bengio, Y","venue":null,"work_id":"6d223ba9-ce57-4e18-a996-3bdae68b8d75","year":2012},"citing_paper":{"arxiv_id":"2507.22090","last_updated":"2025-07-29T09:21:57Z","snapshot_observed_at":"2026-08-09T00:13:47.609729Z","submitted_at":"2025-07-29T09:21:57Z","title":"Hybrid activation functions for deep neural networks: S3 and S4 -- a novel approach to gradient flow optimization","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T12:39:07.655399Z"},"links":{"citing_paper":"/paper/2507.22090"},"observation_digest":"sha256:783b6d16d6b2791d2f7aa541a93b0a10d65f3130aa44ec497432d20c3dce29c7","observation_id":"a8abd9c4-27fa-4f64-8c54-2484df16201e","resolution":{"observed_at":"2026-08-06T12:39:17.365672Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T12:39:17.163244Z","title":"& Pandey, A","venue":null,"work_id":"98860bd3-69a7-4f49-8f0c-85846e8a1fde","year":2022},"citing_paper":{"arxiv_id":"2507.22090","last_updated":"2025-07-29T09:21:57Z","snapshot_observed_at":"2026-08-09T00:13:47.609729Z","submitted_at":"2025-07-29T09:21:57Z","title":"Hybrid activation functions for deep neural networks: S3 and S4 -- a novel approach to gradient flow optimization","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T12:39:07.777384Z"},"links":{"citing_paper":"/paper/2507.22090"},"observation_digest":"sha256:62fddd3377dd45c94510981980c7bec36b7c370c52f08c9724b309a15736c571","observation_id":"bebb8c47-3e94-4947-94f2-be23cf8ed030","resolution":{"observed_at":"2026-08-06T12:39:17.219357Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T12:39:17.025589Z","title":"https://www.kaggle.com/c/boston-housing","venue":null,"work_id":"f69739a5-e4cd-4755-b7f3-b1817acf4fe8","year":null},"citing_paper":{"arxiv_id":"2507.22090","last_updated":"2025-07-29T09:21:57Z","snapshot_observed_at":"2026-08-09T00:13:47.609729Z","submitted_at":"2025-07-29T09:21:57Z","title":"Hybrid activation functions for deep neural networks: S3 and S4 -- a novel approach to gradient flow optimization","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T12:39:07.830703Z"},"links":{"citing_paper":"/paper/2507.22090"},"observation_digest":"sha256:5a9f2b8b8ad5513fd118077289b1a9858e525623cf0ae70428ba0e66ebd7e613","observation_id":"8d1f3d72-7477-477e-81d7-fec55466919a","resolution":{"observed_at":"2026-08-06T12:39:17.090686Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1511.07289","last_updated":"2016-02-22T07:02:58Z","snapshot_observed_at":"2026-07-06T04:37:28.029641Z","submitted_at":"2015-11-23T15:58:05Z","title":"Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1511.07289","snapshot_observed_at":"2026-08-06T12:39:07.927596Z","title":"-A., Unterthiner, T","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2507.22090","last_updated":"2025-07-29T09:21:57Z","snapshot_observed_at":"2026-08-09T00:13:47.609729Z","submitted_at":"2025-07-29T09:21:57Z","title":"Hybrid activation functions for deep neural networks: S3 and S4 -- a novel approach to gradient flow optimization","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T12:39:07.927596Z"},"links":{"cited_paper":"/paper/1511.07289","citing_paper":"/paper/2507.22090"},"observation_digest":"sha256:ebb3c681c407658fbbe871da058ddc7347befb4c320c9b513fa1f731d9d94ef3","observation_id":"4258d684-6491-4a1d-990d-d910467a1b98","resolution":{"observed_at":"2026-08-06T12:39:07.927596Z","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":"2026-08-06T12:39:08.020177Z","title":"Approximation by superpositions of a sigmoidal function","venue":null,"work_id":null,"year":1989},"citing_paper":{"arxiv_id":"2507.22090","last_updated":"2025-07-29T09:21:57Z","snapshot_observed_at":"2026-08-09T00:13:47.609729Z","submitted_at":"2025-07-29T09:21:57Z","title":"Hybrid activation functions for deep neural networks: S3 and S4 -- a novel approach to gradient flow optimization","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T12:39:08.020177Z"},"links":{"citing_paper":"/paper/2507.22090"},"observation_digest":"sha256:4f760ef4b642bd0892b03deb20e416ea041bce2e4c23fe2e94760b205ab9316d","observation_id":"0f76a24d-24ad-45b3-bfe0-53f60080f5f1","resolution":{"observed_at":"2026-08-06T12:39:08.020177Z","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":"2337.2021","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T12:39:13.917771Z","title":"The impact of activation functions on training and performance of a deep neural network,","venue":null,"work_id":"f44561b4-54c6-44a1-944b-4a31e861f926","year":2021},"citing_paper":{"arxiv_id":"2507.22090","last_updated":"2025-07-29T09:21:57Z","snapshot_observed_at":"2026-08-09T00:13:47.609729Z","submitted_at":"2025-07-29T09:21:57Z","title":"Hybrid activation functions for deep neural networks: S3 and S4 -- a novel approach to gradient flow optimization","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T12:39:08.152623Z"},"links":{"citing_paper":"/paper/2507.22090"},"observation_digest":"sha256:2a2c880b3bc1520adc690497c4ea3bc60b469866158a5a749c0af664eb9b74cd","observation_id":"6d134107-9f64-4892-9811-f053bc61f45a","resolution":{"observed_at":"2026-08-06T12:39:13.969094Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T12:39:16.735717Z","title":"& Zhou, J","venue":null,"work_id":"aeee1362-5177-46f7-8cf5-67447d68b299","year":2018},"citing_paper":{"arxiv_id":"2507.22090","last_updated":"2025-07-29T09:21:57Z","snapshot_observed_at":"2026-08-09T00:13:47.609729Z","submitted_at":"2025-07-29T09:21:57Z","title":"Hybrid activation functions for deep neural networks: S3 and S4 -- a novel approach to gradient flow optimization","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T12:39:08.256489Z"},"links":{"citing_paper":"/paper/2507.22090"},"observation_digest":"sha256:6ff93c934d342bc56ba89c5e89dbd37909b18d7a17b74f28274a7f4287a00615","observation_id":"8bba6a91-50e7-460c-9d85-a207dcd73b8e","resolution":{"observed_at":"2026-08-06T12:39:16.914744Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T12:39:08.347492Z","title":"R., Singh, S","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.22090","last_updated":"2025-07-29T09:21:57Z","snapshot_observed_at":"2026-08-09T00:13:47.609729Z","submitted_at":"2025-07-29T09:21:57Z","title":"Hybrid activation functions for deep neural networks: S3 and S4 -- a novel approach to gradient flow optimization","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T12:39:08.347492Z"},"links":{"citing_paper":"/paper/2507.22090"},"observation_digest":"sha256:1e09214780e07f585eb92563a76a78b76a04fd771611bb6549d6ab48d9d2eeb4","observation_id":"15fc05f6-d392-4457-abbd-781b573e100e","resolution":{"observed_at":"2026-08-06T12:39:08.347492Z","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":"2026-08-06T12:39:08.435753Z","title":"& Doya, K","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2507.22090","last_updated":"2025-07-29T09:21:57Z","snapshot_observed_at":"2026-08-09T00:13:47.609729Z","submitted_at":"2025-07-29T09:21:57Z","title":"Hybrid activation functions for deep neural networks: S3 and S4 -- a novel approach to gradient flow optimization","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T12:39:08.435753Z"},"links":{"citing_paper":"/paper/2507.22090"},"observation_digest":"sha256:d345bb992eda9f24afd6c532ae623f59deb0eb1958dd42ced428f81f76bc16f1","observation_id":"dd0afa1a-6ccb-4bfe-a54d-9b1238d2d198","resolution":{"observed_at":"2026-08-06T12:39:08.435753Z","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":"10.52589/ajsteuobyfv1b","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T12:39:12.864408Z","title":"O., Ante, J","venue":null,"work_id":"b85975af-dcc6-42b2-8417-bda9b96168fc","year":2025},"citing_paper":{"arxiv_id":"2507.22090","last_updated":"2025-07-29T09:21:57Z","snapshot_observed_at":"2026-08-09T00:13:47.609729Z","submitted_at":"2025-07-29T09:21:57Z","title":"Hybrid activation functions for deep neural networks: S3 and S4 -- a novel approach to gradient flow optimization","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T12:39:08.546188Z"},"links":{"citing_paper":"/paper/2507.22090"},"observation_digest":"sha256:ba6e2fe26e624f5b8f3de419fe4a892adf6c8c87ff49d4580fc293a047e3aaf2","observation_id":"37373d57-6cf2-4ab4-8fcf-32580335255e","resolution":{"observed_at":"2026-08-06T12:39:12.943488Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.5220/0009175102490257","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T05:30:23.456663Z","title":null,"venue":null,"work_id":"0b29da55-3ea2-4519-b39b-ecf722ea0971","year":2020},"citing_paper":{"arxiv_id":"2507.22090","last_updated":"2025-07-29T09:21:57Z","snapshot_observed_at":"2026-08-09T00:13:47.609729Z","submitted_at":"2025-07-29T09:21:57Z","title":"Hybrid activation functions for deep neural networks: S3 and S4 -- a novel approach to gradient flow optimization","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T12:39:08.727741Z"},"links":{"citing_paper":"/paper/2507.22090"},"observation_digest":"sha256:79fda55325973274236e6901c92fe31ae1c46b2e655e9810a93b7f13ed356182","observation_id":"42f20c68-aaa0-49fd-99af-508b518fd411","resolution":{"observed_at":"2026-08-06T12:39:12.773661Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T12:39:16.511042Z","title":"and Bengio, Y","venue":null,"work_id":"e16c9f87-4d90-4d2b-aed2-e73c4de62b6b","year":2010},"citing_paper":{"arxiv_id":"2507.22090","last_updated":"2025-07-29T09:21:57Z","snapshot_observed_at":"2026-08-09T00:13:47.609729Z","submitted_at":"2025-07-29T09:21:57Z","title":"Hybrid activation functions for deep neural networks: S3 and S4 -- a novel approach to gradient flow optimization","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T12:39:08.842003Z"},"links":{"citing_paper":"/paper/2507.22090"},"observation_digest":"sha256:10eec9bd4733fdd18526232cd24bd9d945cbf9edad1e82462d2fd151f036c10a","observation_id":"e1cee271-e645-401f-996a-21f09504f20c","resolution":{"observed_at":"2026-08-06T12:39:16.607421Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T12:39:16.316656Z","title":"and Bengio, Y","venue":null,"work_id":"0cc988de-6d1e-4c3c-983c-eba5b986e173","year":2011},"citing_paper":{"arxiv_id":"2507.22090","last_updated":"2025-07-29T09:21:57Z","snapshot_observed_at":"2026-08-09T00:13:47.609729Z","submitted_at":"2025-07-29T09:21:57Z","title":"Hybrid activation functions for deep neural networks: S3 and S4 -- a novel approach to gradient flow optimization","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T12:39:08.899442Z"},"links":{"citing_paper":"/paper/2507.22090"},"observation_digest":"sha256:de1b835354465be7d897d91d18e21af94ffe2f112d35b15395b5d53c58bb34d2","observation_id":"521ec621-b3cc-4d52-80d1-caedfc4cd93f","resolution":{"observed_at":"2026-08-06T12:39:16.386439Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T12:39:16.161798Z","title":"& Courville, A","venue":null,"work_id":"e925fbd9-4234-4a4b-8abe-7fc62c546682","year":2016},"citing_paper":{"arxiv_id":"2507.22090","last_updated":"2025-07-29T09:21:57Z","snapshot_observed_at":"2026-08-09T00:13:47.609729Z","submitted_at":"2025-07-29T09:21:57Z","title":"Hybrid activation functions for deep neural networks: S3 and S4 -- a novel approach to gradient flow optimization","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T12:39:08.962419Z"},"links":{"citing_paper":"/paper/2507.22090"},"observation_digest":"sha256:3720d49ea9a3227bb7163cff315a223c4ea47ca202661d83e591c65b30fd7fb0","observation_id":"48812abe-3348-4211-ba70-8085f1d3218c","resolution":{"observed_at":"2026-08-06T12:39:16.242116Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T12:39:16.003544Z","title":null,"venue":null,"work_id":"61b5e297-fbe8-4a10-b39e-3129420489ee","year":2001},"citing_paper":{"arxiv_id":"2507.22090","last_updated":"2025-07-29T09:21:57Z","snapshot_observed_at":"2026-08-09T00:13:47.609729Z","submitted_at":"2025-07-29T09:21:57Z","title":"Hybrid activation functions for deep neural networks: S3 and S4 -- a novel approach to gradient flow optimization","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T12:39:09.072551Z"},"links":{"citing_paper":"/paper/2507.22090"},"observation_digest":"sha256:d4b88dfed78dfd8798ae03bd0ab6287444e98c956e6fc2eab51c8f4f372446eb","observation_id":"91276b8c-136a-4964-8d51-ac5285df4d06","resolution":{"observed_at":"2026-08-06T12:39:16.088868Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T12:39:15.839786Z","title":"https://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_iris.html","venue":null,"work_id":"b42ffd9e-6667-4a5d-aeef-cec344ae0d95","year":null},"citing_paper":{"arxiv_id":"2507.22090","last_updated":"2025-07-29T09:21:57Z","snapshot_observed_at":"2026-08-09T00:13:47.609729Z","submitted_at":"2025-07-29T09:21:57Z","title":"Hybrid activation functions for deep neural networks: S3 and S4 -- a novel approach to gradient flow optimization","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T12:39:09.231024Z"},"links":{"citing_paper":"/paper/2507.22090"},"observation_digest":"sha256:f095e851e0d41d4e252ef5ad143ae6fb28420cf860fa7d1ea0694734fd58670a","observation_id":"fae27df8-f25a-4fe0-85eb-c7035bd8d454","resolution":{"observed_at":"2026-08-06T12:39:15.918287Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2209.02681","last_updated":"2022-12-28T16:52:12Z","snapshot_observed_at":"2026-08-07T06:50:38.030058Z","submitted_at":"2022-09-06T17:51:52Z","title":"How important are activation functions in regression and classification? A survey, performance comparison, and future directions","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2209.02681","snapshot_observed_at":"2026-08-06T12:39:09.308337Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.22090","last_updated":"2025-07-29T09:21:57Z","snapshot_observed_at":"2026-08-09T00:13:47.609729Z","submitted_at":"2025-07-29T09:21:57Z","title":"Hybrid activation functions for deep neural networks: S3 and S4 -- a novel approach to gradient flow optimization","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T12:39:09.308337Z"},"links":{"cited_paper":"/paper/2209.02681","citing_paper":"/paper/2507.22090"},"observation_digest":"sha256:772844fdac6371ed01ba9994dbce30de8e3383b8ae49f1bc3087345a6aaccf01","observation_id":"bb50c474-12e0-49d8-a0b5-880a7269d3d6","resolution":{"observed_at":"2026-08-06T12:39:09.308337Z","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":"2026-08-06T12:39:09.415877Z","title":"Delving Deep into Rectifiers: Surpassing Human -Level Performance on ImageNet Classification,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2507.22090","last_updated":"2025-07-29T09:21:57Z","snapshot_observed_at":"2026-08-09T00:13:47.609729Z","submitted_at":"2025-07-29T09:21:57Z","title":"Hybrid activation functions for deep neural networks: S3 and S4 -- a novel approach to gradient flow optimization","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T12:39:09.415877Z"},"links":{"citing_paper":"/paper/2507.22090"},"observation_digest":"sha256:7ad44bf6884bd305096ec7a89f58aade9bad0537d2634d8d969e5c9d9e270135","observation_id":"22aa2863-5397-41a4-9917-fa31e54aef3c","resolution":{"observed_at":"2026-08-06T12:39:09.415877Z","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":"2019.88800","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T12:39:13.604414Z","title":null,"venue":null,"work_id":"3b99c42d-c591-45f1-bc26-2b78bb0c6d27","year":2019},"citing_paper":{"arxiv_id":"2507.22090","last_updated":"2025-07-29T09:21:57Z","snapshot_observed_at":"2026-08-09T00:13:47.609729Z","submitted_at":"2025-07-29T09:21:57Z","title":"Hybrid activation functions for deep neural networks: S3 and S4 -- a novel approach to gradient flow optimization","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T12:39:09.476736Z"},"links":{"citing_paper":"/paper/2507.22090"},"observation_digest":"sha256:dca8b596372e1ba2397ad14f84ea8cb73ba84fdd26ce979c459ead1362741a20","observation_id":"04b96588-0219-4309-8720-51877d41a378","resolution":{"observed_at":"2026-08-06T12:39:13.732792Z","resolver_source":"raw_fallback","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2507.03061","last_updated":"2025-07-03T16:27:12Z","snapshot_observed_at":"2026-08-06T20:19:10.570475Z","submitted_at":"2025-07-03T16:27:12Z","title":"Multiple data-driven missing imputation","version":1},"cited_work":{"arxiv_id":"2507.03061","doi":null,"metadata_source":"pith","pith_arxiv_id":"2507.03061","snapshot_observed_at":"2026-08-06T12:39:13.420212Z","title":"Multiple data-driven missing imputation","venue":"stat.ME","work_id":"c6f11834-040a-49c1-a9a9-45aa15542f0a","year":2025},"citing_paper":{"arxiv_id":"2507.22090","last_updated":"2025-07-29T09:21:57Z","snapshot_observed_at":"2026-08-09T00:13:47.609729Z","submitted_at":"2025-07-29T09:21:57Z","title":"Hybrid activation functions for deep neural networks: S3 and S4 -- a novel approach to gradient flow optimization","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T12:39:09.549449Z"},"links":{"cited_paper":"/paper/2507.03061","citing_paper":"/paper/2507.22090"},"observation_digest":"sha256:cff94ed40b38ad4879b7433baaf867a66de012f094c3ae4de933585f422eb1e9","observation_id":"10c4d71c-440d-409b-bd0c-caf51effe283","resolution":{"observed_at":"2026-08-06T12:39:13.478770Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.09092","last_updated":"2024-02-14T11:13:33Z","snapshot_observed_at":"2026-08-09T03:39:39.100109Z","submitted_at":"2024-02-14T11:13:33Z","title":"Three Decades of Activations: A Comprehensive Survey of 400 Activation Functions for Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.09092","snapshot_observed_at":"2026-08-06T12:39:09.621769Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.22090","last_updated":"2025-07-29T09:21:57Z","snapshot_observed_at":"2026-08-09T00:13:47.609729Z","submitted_at":"2025-07-29T09:21:57Z","title":"Hybrid activation functions for deep neural networks: S3 and S4 -- a novel approach to gradient flow optimization","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T12:39:09.621769Z"},"links":{"cited_paper":"/paper/2402.09092","citing_paper":"/paper/2507.22090"},"observation_digest":"sha256:a1891ad5ead7de6b59f11eb046e2823224407831617fa36372fd68503d9da895","observation_id":"291d13ce-a8c7-45a3-8c66-db1ccc9a91cc","resolution":{"observed_at":"2026-08-06T12:39:09.621769Z","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":"2026-08-06T12:39:15.656191Z","title":"Computational aspects of critical infrastructures security","venue":null,"work_id":"725b3fbd-6b6d-473a-aa34-b69c157dfc57","year":2020},"citing_paper":{"arxiv_id":"2507.22090","last_updated":"2025-07-29T09:21:57Z","snapshot_observed_at":"2026-08-09T00:13:47.609729Z","submitted_at":"2025-07-29T09:21:57Z","title":"Hybrid activation functions for deep neural networks: S3 and S4 -- a novel approach to gradient flow optimization","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T12:39:09.715067Z"},"links":{"citing_paper":"/paper/2507.22090"},"observation_digest":"sha256:bb0623e6d3c9919dc1cf34c094e70d9f48e6371ff2d0b266010bc30af41a3515","observation_id":"59caa939-3ad9-424e-88b6-aebf3b4c69c1","resolution":{"observed_at":"2026-08-06T12:39:15.748949Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T12:39:15.498218Z","title":null,"venue":null,"work_id":"9c75bbd2-893a-4465-a4f0-69152cfe5f85","year":1998},"citing_paper":{"arxiv_id":"2507.22090","last_updated":"2025-07-29T09:21:57Z","snapshot_observed_at":"2026-08-09T00:13:47.609729Z","submitted_at":"2025-07-29T09:21:57Z","title":"Hybrid activation functions for deep neural networks: S3 and S4 -- a novel approach to gradient flow optimization","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T12:39:09.868343Z"},"links":{"citing_paper":"/paper/2507.22090"},"observation_digest":"sha256:9363e9f70983d743e16958ee6d1b84e69ef5f2b7dc5cd645864e1303aa1ac966","observation_id":"8eeb3dca-4813-45f5-9ef9-f47caf9a10bd","resolution":{"observed_at":"2026-08-06T12:39:15.558983Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T12:39:09.981341Z","title":"& Hinton, G","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2507.22090","last_updated":"2025-07-29T09:21:57Z","snapshot_observed_at":"2026-08-09T00:13:47.609729Z","submitted_at":"2025-07-29T09:21:57Z","title":"Hybrid activation functions for deep neural networks: S3 and S4 -- a novel approach to gradient flow optimization","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T12:39:09.981341Z"},"links":{"citing_paper":"/paper/2507.22090"},"observation_digest":"sha256:49938a3a65fd7854f0cf9f51d959023633330cb4353f9b20517b4613ef6e5032","observation_id":"632694e1-5550-4461-a983-637702ebf33f","resolution":{"observed_at":"2026-08-06T12:39:09.981341Z","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":"2026-08-06T12:39:15.372593Z","title":null,"venue":null,"work_id":"08d448ad-06a5-4de6-b082-c0df33f6b189","year":2012},"citing_paper":{"arxiv_id":"2507.22090","last_updated":"2025-07-29T09:21:57Z","snapshot_observed_at":"2026-08-09T00:13:47.609729Z","submitted_at":"2025-07-29T09:21:57Z","title":"Hybrid activation functions for deep neural networks: S3 and S4 -- a novel approach to gradient flow optimization","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T12:39:10.046653Z"},"links":{"citing_paper":"/paper/2507.22090"},"observation_digest":"sha256:278d3f47880a78309d2f2acf483abf5616c29a1a3d0c194a84f1efaef32d053a","observation_id":"3a5f2ade-f77d-42e9-881b-a32de900c5a0","resolution":{"observed_at":"2026-08-06T12:39:15.437168Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T12:39:15.225585Z","title":"& Goldstein, T","venue":null,"work_id":"e6432f43-0e6b-4891-8b9f-c69acd58ecf1","year":2018},"citing_paper":{"arxiv_id":"2507.22090","last_updated":"2025-07-29T09:21:57Z","snapshot_observed_at":"2026-08-09T00:13:47.609729Z","submitted_at":"2025-07-29T09:21:57Z","title":"Hybrid activation functions for deep neural networks: S3 and S4 -- a novel approach to gradient flow optimization","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T12:39:10.242412Z"},"links":{"citing_paper":"/paper/2507.22090"},"observation_digest":"sha256:951f32308a60e1d0cd6cd6ddfa26c1d23a1adb1e97fdd3c4a06d585659c3df6e","observation_id":"8fa44c4d-f895-42ed-b9a8-e070d7a47548","resolution":{"observed_at":"2026-08-06T12:39:15.307280Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T12:39:15.124835Z","title":"and Ng, A.Y","venue":null,"work_id":"7c2b6d4d-4531-4d95-ab96-8610c7e575e3","year":2013},"citing_paper":{"arxiv_id":"2507.22090","last_updated":"2025-07-29T09:21:57Z","snapshot_observed_at":"2026-08-09T00:13:47.609729Z","submitted_at":"2025-07-29T09:21:57Z","title":"Hybrid activation functions for deep neural networks: S3 and S4 -- a novel approach to gradient flow optimization","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T12:39:10.378096Z"},"links":{"citing_paper":"/paper/2507.22090"},"observation_digest":"sha256:ae8db648ba747205916d19a4557713b12719852e002962c96cdec8c77b63c545","observation_id":"78a5e84b-3f29-40fd-ad0c-b17ad0df0af6","resolution":{"observed_at":"2026-08-06T12:39:15.167658Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T12:39:15.003351Z","title":"& Vrahatis, A","venue":null,"work_id":"8f879d37-7906-4023-a8b5-b5cfe1dcc881","year":2018},"citing_paper":{"arxiv_id":"2507.22090","last_updated":"2025-07-29T09:21:57Z","snapshot_observed_at":"2026-08-09T00:13:47.609729Z","submitted_at":"2025-07-29T09:21:57Z","title":"Hybrid activation functions for deep neural networks: S3 and S4 -- a novel approach to gradient flow optimization","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T12:39:10.487828Z"},"links":{"citing_paper":"/paper/2507.22090"},"observation_digest":"sha256:c235289faea49bfb77f095e2a9733c991ea75e186a1b596b746f3e93633f7c5d","observation_id":"61cca31d-20d3-4f10-bc7d-97b012fa3db1","resolution":{"observed_at":"2026-08-06T12:39:15.052260Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"9615.2020","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T12:39:13.273216Z","title":null,"venue":null,"work_id":"71ac0ac3-e9da-4a22-bee8-7a7f42f58132","year":2020},"citing_paper":{"arxiv_id":"2507.22090","last_updated":"2025-07-29T09:21:57Z","snapshot_observed_at":"2026-08-09T00:13:47.609729Z","submitted_at":"2025-07-29T09:21:57Z","title":"Hybrid activation functions for deep neural networks: S3 and S4 -- a novel approach to gradient flow optimization","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T12:39:10.529438Z"},"links":{"citing_paper":"/paper/2507.22090"},"observation_digest":"sha256:1d14864983c4b04dcf16723d9f6a8fa97002ef18d9b52b4baf73d0dc135c5cd0","observation_id":"1531dcea-7460-4fc7-8200-072f619dd095","resolution":{"observed_at":"2026-08-06T12:39:13.334220Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1908.08681","last_updated":"2020-08-13T05:42:12Z","snapshot_observed_at":"2026-07-06T08:16:16.271286Z","submitted_at":"2019-08-23T06:22:06Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.08681","snapshot_observed_at":"2026-08-06T12:39:10.624184Z","title":"Mish: A self-regularized non-monotonic activation function","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.22090","last_updated":"2025-07-29T09:21:57Z","snapshot_observed_at":"2026-08-09T00:13:47.609729Z","submitted_at":"2025-07-29T09:21:57Z","title":"Hybrid activation functions for deep neural networks: S3 and S4 -- a novel approach to gradient flow optimization","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T12:39:10.624184Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2507.22090"},"observation_digest":"sha256:5b59a49f17fc91b9cedb1bff8bd5e7e557ef4f0d2d04b3b47ae595fb69a026b1","observation_id":"1af972da-eb98-4630-9b01-52330caba868","resolution":{"observed_at":"2026-08-06T12:39:10.624184Z","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":"2026-08-06T12:39:14.851660Z","title":"https://www.kaggle.com/datasets/hojjatk/mnist-dataset","venue":null,"work_id":"8391e209-e0c6-4583-9c2f-b0baa9312079","year":null},"citing_paper":{"arxiv_id":"2507.22090","last_updated":"2025-07-29T09:21:57Z","snapshot_observed_at":"2026-08-09T00:13:47.609729Z","submitted_at":"2025-07-29T09:21:57Z","title":"Hybrid activation functions for deep neural networks: S3 and S4 -- a novel approach to gradient flow optimization","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T12:39:10.705783Z"},"links":{"citing_paper":"/paper/2507.22090"},"observation_digest":"sha256:a6357c9c8ee771f728d2867eff8e5d65eafcf8f90f369329b962946394750e71","observation_id":"9eab66df-4753-417c-a776-fbad359746b0","resolution":{"observed_at":"2026-08-06T12:39:14.905277Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T12:39:14.658717Z","title":"& Bengio, Y","venue":null,"work_id":"f23b09bd-ece8-4a39-a7a6-f247dab560b3","year":2013},"citing_paper":{"arxiv_id":"2507.22090","last_updated":"2025-07-29T09:21:57Z","snapshot_observed_at":"2026-08-09T00:13:47.609729Z","submitted_at":"2025-07-29T09:21:57Z","title":"Hybrid activation functions for deep neural networks: S3 and S4 -- a novel approach to gradient flow optimization","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T12:39:10.777069Z"},"links":{"citing_paper":"/paper/2507.22090"},"observation_digest":"sha256:800e91d314d4dbba0c9bc29e3e34287a59928278d70e8d8914fe2b12ae9a7d18","observation_id":"6a95ff7d-f372-4828-b11d-8306559ed1e1","resolution":{"observed_at":"2026-08-06T12:39:14.752679Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T12:39:14.502837Z","title":null,"venue":null,"work_id":"95f24914-c223-45a4-94cc-51254e0a018d","year":2024},"citing_paper":{"arxiv_id":"2507.22090","last_updated":"2025-07-29T09:21:57Z","snapshot_observed_at":"2026-08-09T00:13:47.609729Z","submitted_at":"2025-07-29T09:21:57Z","title":"Hybrid activation functions for deep neural networks: S3 and S4 -- a novel approach to gradient flow optimization","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T12:39:10.845954Z"},"links":{"citing_paper":"/paper/2507.22090"},"observation_digest":"sha256:efff46c91418b8704e154cfe6c283ca480114c4a779932996345f01f283d3b79","observation_id":"3ef7bdde-8e1b-4ae2-9c4d-6ce790441629","resolution":{"observed_at":"2026-08-06T12:39:14.586186Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1710.05941","last_updated":"2017-10-27T17:45:21Z","snapshot_observed_at":"2026-08-08T18:23:31.977872Z","submitted_at":"2017-10-16T18:05:45Z","title":"Searching for Activation Functions","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.05941","snapshot_observed_at":"2026-08-06T12:39:11.059693Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.22090","last_updated":"2025-07-29T09:21:57Z","snapshot_observed_at":"2026-08-09T00:13:47.609729Z","submitted_at":"2025-07-29T09:21:57Z","title":"Hybrid activation functions for deep neural networks: S3 and S4 -- a novel approach to gradient flow optimization","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T12:39:11.059693Z"},"links":{"cited_paper":"/paper/1710.05941","citing_paper":"/paper/2507.22090"},"observation_digest":"sha256:9375e55ecef43f4cdfa53597a146106dddfc1f936c24c80f3f8facf4475b9bff","observation_id":"acf01ff9-a0d8-4e1a-b114-911998e5961c","resolution":{"observed_at":"2026-08-06T12:39:11.059693Z","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":"10.5334/dsj-2024-017","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T05:30:23.456663Z","title":null,"venue":"Data Science Journal","work_id":"a63a47a1-1b59-4ec8-a557-a3ce49be7e38","year":2024},"citing_paper":{"arxiv_id":"2507.22090","last_updated":"2025-07-29T09:21:57Z","snapshot_observed_at":"2026-08-09T00:13:47.609729Z","submitted_at":"2025-07-29T09:21:57Z","title":"Hybrid activation functions for deep neural networks: S3 and S4 -- a novel approach to gradient flow optimization","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-06T12:39:10.916928Z"},"links":{"citing_paper":"/paper/2507.22090"},"observation_digest":"sha256:5a99262f2f4e542ee2f7319c0f15454d8d9d78def79f2f1e1f9bf8798b35d921","observation_id":"aa340219-6b9d-4379-a119-454b6cef424b","resolution":{"observed_at":"2026-08-06T12:39:12.530711Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.5281/zenodo.16459162","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T05:30:23.456663Z","title":null,"venue":"Zenodo (CERN European Organization for Nuclear Research)","work_id":"137d54c2-d571-4596-a31c-b0fb9504b0d3","year":2025},"citing_paper":{"arxiv_id":"2507.22090","last_updated":"2025-07-29T09:21:57Z","snapshot_observed_at":"2026-08-09T00:13:47.609729Z","submitted_at":"2025-07-29T09:21:57Z","title":"Hybrid activation functions for deep neural networks: S3 and S4 -- a novel approach to gradient flow optimization","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-06T12:39:11.283705Z"},"links":{"citing_paper":"/paper/2507.22090"},"observation_digest":"sha256:089ab3d685eafeed5d6678e3c051061e6689f292abb607520423b88e06bcfd16","observation_id":"41043d23-924d-4a31-bb7a-de7446b0d048","resolution":{"observed_at":"2026-08-06T12:39:12.337885Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T12:39:14.265794Z","title":null,"venue":null,"work_id":"de86246a-fec2-45a7-b79d-c1ec3426718b","year":2015},"citing_paper":{"arxiv_id":"2507.22090","last_updated":"2025-07-29T09:21:57Z","snapshot_observed_at":"2026-08-09T00:13:47.609729Z","submitted_at":"2025-07-29T09:21:57Z","title":"Hybrid activation functions for deep neural networks: S3 and S4 -- a novel approach to gradient flow optimization","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-06T12:39:11.190589Z"},"links":{"citing_paper":"/paper/2507.22090"},"observation_digest":"sha256:3eeec438d71986b1a5049561211db3d481b9b51613ca27272a7026d97ce47c8f","observation_id":"7c1957a6-6fe2-4818-91c3-b792a9082c8b","resolution":{"observed_at":"2026-08-06T12:39:14.402039Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.14428/esann/2025.es2025-211","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T05:30:23.456663Z","title":null,"venue":null,"work_id":"e34151ef-1558-4b62-82fc-f7a158a91d22","year":2025},"citing_paper":{"arxiv_id":"2507.22090","last_updated":"2025-07-29T09:21:57Z","snapshot_observed_at":"2026-08-09T00:13:47.609729Z","submitted_at":"2025-07-29T09:21:57Z","title":"Hybrid activation functions for deep neural networks: S3 and S4 -- a novel approach to gradient flow optimization","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-06T12:39:11.454148Z"},"links":{"citing_paper":"/paper/2507.22090"},"observation_digest":"sha256:0e638b794368feb20392fd34435919a207475cec05079ca6ef6bb4c34eb6834b","observation_id":"3149e844-bb4c-49a6-bc57-741cdeb6bfd2","resolution":{"observed_at":"2026-08-06T12:39:12.081398Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T12:39:14.139595Z","title":null,"venue":null,"work_id":"54e64291-8bf4-4704-b0e6-1723405483f6","year":2018},"citing_paper":{"arxiv_id":"2507.22090","last_updated":"2025-07-29T09:21:57Z","snapshot_observed_at":"2026-08-09T00:13:47.609729Z","submitted_at":"2025-07-29T09:21:57Z","title":"Hybrid activation functions for deep neural networks: S3 and S4 -- a novel approach to gradient flow optimization","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-06T12:39:11.358429Z"},"links":{"citing_paper":"/paper/2507.22090"},"observation_digest":"sha256:6a12d62edea998cae12ebbd0c5a9c4efb4abc280c98177faa7bfb6040c9e3ba9","observation_id":"d405a5da-74f3-4e79-8fce-076ad7c6d5c4","resolution":{"observed_at":"2026-08-06T12:39:14.189422Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1038/s41598-021-96723-8","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T05:30:23.456663Z","title":null,"venue":"Scientific Reports","work_id":"4a82940d-14af-4810-9268-8474eefbff9e","year":2021},"citing_paper":{"arxiv_id":"2507.22090","last_updated":"2025-07-29T09:21:57Z","snapshot_observed_at":"2026-08-09T00:13:47.609729Z","submitted_at":"2025-07-29T09:21:57Z","title":"Hybrid activation functions for deep neural networks: S3 and S4 -- a novel approach to gradient flow optimization","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-06T12:39:11.694265Z"},"links":{"citing_paper":"/paper/2507.22090"},"observation_digest":"sha256:0d31fde87c28b851e9e732b9c63d5b5c59b516e89b770759fc1ee4e2ecdeb59b","observation_id":"375931ce-1305-4413-8894-6862fcbbd770","resolution":{"observed_at":"2026-08-06T12:39:11.805686Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1505.00853","last_updated":"2015-11-27T06:58:14Z","snapshot_observed_at":"2026-07-06T04:16:54.272660Z","submitted_at":"2015-05-05T01:16:39Z","title":"Empirical Evaluation of Rectified Activations in Convolutional Network","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1505.00853","snapshot_observed_at":"2026-08-06T12:39:11.550783Z","title":null,"venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2507.22090","last_updated":"2025-07-29T09:21:57Z","snapshot_observed_at":"2026-08-09T00:13:47.609729Z","submitted_at":"2025-07-29T09:21:57Z","title":"Hybrid activation functions for deep neural networks: S3 and S4 -- a novel approach to gradient flow optimization","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-06T12:39:11.550783Z"},"links":{"cited_paper":"/paper/1505.00853","citing_paper":"/paper/2507.22090"},"observation_digest":"sha256:107d24725409f653edc05a366340b63f11c9ea8c74099af260f86e34662485ad","observation_id":"bd2514c5-8e79-4d62-ac71-d078f415b486","resolution":{"observed_at":"2026-08-06T12:39:11.550783Z","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":"2026-08-06T12:39:10.146480Z","title":"https://doi.org/10.1007/978-3-642-35289-8_3","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.22090","last_updated":"2025-07-29T09:21:57Z","snapshot_observed_at":"2026-08-09T00:13:47.609729Z","submitted_at":"2025-07-29T09:21:57Z","title":"Hybrid activation functions for deep neural networks: S3 and S4 -- a novel approach to gradient flow optimization","version":1},"reference_index":7700,"source":"pdf_text","source_observed_at":"2026-08-06T12:39:10.146480Z"},"links":{"citing_paper":"/paper/2507.22090"},"observation_digest":"sha256:8c1a1c7b6df3980cc02b33531cde1c6cf020e59e594ee0264b621ca129c019b3","observation_id":"83d9e9be-3243-4e90-8799-802d852ae993","resolution":{"observed_at":"2026-08-06T12:39:10.146480Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2507.22090","last_updated":"2025-07-29T09:21:57Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-09T00:13:47.609729Z","submitted_at":"2025-07-29T09:21:57Z","title":"Hybrid activation functions for deep neural networks: S3 and S4 -- a novel approach to gradient flow optimization"},"reference_resolution":{"displayed":47,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":21,"verified_exact":9,"verified_fuzzy":16},"total_outbound_references":47},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 47 of 47 outbound references and 0 inbound Pith citation observations for arXiv:2507.22090."}