{"as_of":"2026-08-18T13:21:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:731537b67ccea75f56da72511603f33fa97a76ebe70fbc0c72583582fb62fe9c","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":9,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":9,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+00:00","state":"measured"},{"denominator":9,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":9,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T21:56:04.483696Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":1,"source":"arxiv_reference","source_observed_at":"2026-08-05T02:28:24.338817Z","state":"measured"}],"external_citation_measurements":[{"count":17,"observed_at":"2026-08-05T02:28:24.338817Z","source":"arxiv_reference"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2109.14545","last_updated":"2022-06-28T04:13:53Z","snapshot_observed_at":"2026-08-18T05:50:54.233206Z","submitted_at":"2021-09-29T16:41:19Z","title":"Activation Functions in Deep Learning: A Comprehensive Survey and Benchmark","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.14545","snapshot_observed_at":"2026-08-12T19:56:02.420302Z","title":"A comprehensive survey and performance anal- ysis of activation functions in deep learning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.10507","last_updated":"2024-11-15T14:36:07Z","snapshot_observed_at":"2026-08-17T03:59:13.560674Z","submitted_at":"2024-11-15T14:36:07Z","title":"RedTest: Towards Measuring Redundancy in Deep Neural Networks Effectively","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-12T19:56:02.420302Z"},"links":{"cited_paper":"/paper/2109.14545","citing_paper":"/paper/2411.10507"},"observation_digest":"sha256:071fd1e5bb22e9f8d007e64bac259cce5e0188075faa6526395b8f231717c3b2","observation_id":"d413411f-fa13-4dc6-9d46-d52626a67c13","resolution":{"observed_at":"2026-08-12T19:56:02.420302Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.14545","last_updated":"2022-06-28T04:13:53Z","snapshot_observed_at":"2026-08-18T05:50:54.233206Z","submitted_at":"2021-09-29T16:41:19Z","title":"Activation Functions in Deep Learning: A Comprehensive Survey and Benchmark","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.14545","snapshot_observed_at":"2026-08-10T20:40:11.494329Z","title":"R.; Singh, S","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2501.07755","last_updated":"2025-01-13T23:56:24Z","snapshot_observed_at":"2026-08-13T06:02:04.619695Z","submitted_at":"2025-01-13T23:56:24Z","title":"Performance Optimization of Ratings-Based Reinforcement Learning","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-10T20:40:11.494329Z"},"links":{"cited_paper":"/paper/2109.14545","citing_paper":"/paper/2501.07755"},"observation_digest":"sha256:1edeebb0e90f955d89fb1d4452e241c2559c08a471c36fb40c45fb2a53dafaf9","observation_id":"48c8d32f-7867-4ca9-9e95-242ec330554d","resolution":{"observed_at":"2026-08-10T20:40:11.494329Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.14545","last_updated":"2022-06-28T04:13:53Z","snapshot_observed_at":"2026-08-18T05:50:54.233206Z","submitted_at":"2021-09-29T16:41:19Z","title":"Activation Functions in Deep Learning: A Comprehensive Survey and Benchmark","version":3},"cited_work":{"arxiv_id":"2109.14545","doi":"10.48550/arxiv.2109.14545","metadata_source":"arxiv_reference","pith_arxiv_id":"2109.14545","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":null,"venue":"arXiv (Cornell University)","work_id":"aea15b3a-e667-49a2-8398-e8fe9420638c","year":2022},"citing_paper":{"arxiv_id":"2503.17461","last_updated":"2026-07-15T08:47:01Z","snapshot_observed_at":"2026-08-16T12:47:51.272948Z","submitted_at":"2025-03-21T18:17:17Z","title":"Electroweak diboson production in association with a high-mass dijet system in semileptonic final states from $pp$ collisions at $\\sqrt{s} = 13$ TeV with the ATLAS detector","version":1},"reference_index":103,"source":"pdf_text","source_observed_at":"2026-05-22T22:28:05.029646Z"},"links":{"cited_paper":"/paper/2109.14545","citing_paper":"/paper/2503.17461"},"observation_digest":"sha256:bfb4493fc76036404d5d6a038e0f4b118b76de4bf84d839f9d7998df1d09f21a","observation_id":"394cc07f-b509-4f1e-b9c9-1a9ccd3710bf","resolution":{"observed_at":"2026-05-22T22:32:12.737916Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-05-22T17:52:38.750604+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-22T17:52:38.750604+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2109.14545","last_updated":"2022-06-28T04:13:53Z","snapshot_observed_at":"2026-08-18T05:50:54.233206Z","submitted_at":"2021-09-29T16:41:19Z","title":"Activation Functions in Deep Learning: A Comprehensive Survey and Benchmark","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.14545","snapshot_observed_at":"2026-08-15T21:56:04.483696Z","title":"Activation functions in deep learning: A comprehensive survey and benchmark,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.08566","last_updated":"2025-05-13T13:41:04Z","snapshot_observed_at":"2026-08-15T21:49:18.466370Z","submitted_at":"2025-05-13T13:41:04Z","title":"Extract the Best, Discard the Rest: CSI Feedback with Offline Large AI Models","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-15T21:56:04.483696Z"},"links":{"cited_paper":"/paper/2109.14545","citing_paper":"/paper/2505.08566"},"observation_digest":"sha256:27f127d042a261daa1193b04c37129dc92253346e86323e93b25b1cf4522f590","observation_id":"318f28b2-1569-49f9-a08a-05cf6e56c972","resolution":{"observed_at":"2026-08-15T21:56:04.483696Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.14545","last_updated":"2022-06-28T04:13:53Z","snapshot_observed_at":"2026-08-18T05:50:54.233206Z","submitted_at":"2021-09-29T16:41:19Z","title":"Activation Functions in Deep Learning: A Comprehensive Survey and Benchmark","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.14545","snapshot_observed_at":"2026-08-06T06:01:11.669453Z","title":"Activa- tion functions in deep learning: A comprehensive survey and benchmark,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.01001","last_updated":"2025-08-01T18:10:49Z","snapshot_observed_at":"2026-08-09T20:22:50.977080Z","submitted_at":"2025-08-01T18:10:49Z","title":"Criticality analysis of nuclear binding energy neural networks","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-06T06:01:11.669453Z"},"links":{"cited_paper":"/paper/2109.14545","citing_paper":"/paper/2508.01001"},"observation_digest":"sha256:55741daf6dd872b19af77d4fc10583441eba27cb6579579087e3764ed244b115","observation_id":"02ae8122-ae7d-4c83-928e-aecd1ce210dc","resolution":{"observed_at":"2026-08-06T06:01:11.669453Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.14545","last_updated":"2022-06-28T04:13:53Z","snapshot_observed_at":"2026-08-18T05:50:54.233206Z","submitted_at":"2021-09-29T16:41:19Z","title":"Activation Functions in Deep Learning: A Comprehensive Survey and Benchmark","version":3},"cited_work":{"arxiv_id":"2109.14545","doi":"10.48550/arxiv.2109.14545","metadata_source":"arxiv_reference","pith_arxiv_id":"2109.14545","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":null,"venue":"arXiv (Cornell University)","work_id":"aea15b3a-e667-49a2-8398-e8fe9420638c","year":2022},"citing_paper":{"arxiv_id":"2511.05186","last_updated":"2026-05-06T13:25:17Z","snapshot_observed_at":"2026-07-06T22:35:07.844255Z","submitted_at":"2025-11-07T12:07:32Z","title":"Physics-informed neural network (PINN) modeling of charged particle multiplicity using the two-component framework in heavy-ion collisions: A comparison with data-driven neural networks","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-05-18T00:13:45.357960Z"},"links":{"cited_paper":"/paper/2109.14545","citing_paper":"/paper/2511.05186"},"observation_digest":"sha256:a74c4c4c62981e33a8344327075448dd836a259a8d593173703069f9cc6e18ef","observation_id":"11598f0e-73d5-489f-8651-6ec573ea5d77","resolution":{"observed_at":"2026-05-18T00:15:31.702810Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-05-22T17:52:38.750604+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-22T17:52:38.750604+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2109.14545","last_updated":"2022-06-28T04:13:53Z","snapshot_observed_at":"2026-08-18T05:50:54.233206Z","submitted_at":"2021-09-29T16:41:19Z","title":"Activation Functions in Deep Learning: A Comprehensive Survey and Benchmark","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.14545","snapshot_observed_at":"2026-08-03T22:43:26.947162Z","title":"A compre- hensive survey and performance analysis of activation functions in deep learning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2511.11703","last_updated":"2026-05-27T22:45:09Z","snapshot_observed_at":"2026-08-17T00:08:04.104300Z","submitted_at":"2025-11-12T14:28:46Z","title":"Enhancing Reinforcement Learning in 3D Environments through Semantic Segmentation: A Case Study in ViZDoom","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-03T22:43:26.947162Z"},"links":{"cited_paper":"/paper/2109.14545","citing_paper":"/paper/2511.11703"},"observation_digest":"sha256:7071f91b5a0c8da1e39c0de612f1011ca57f7dcf9e2b65b0522610926898c26f","observation_id":"0c71c84e-2469-4248-9e84-b1dc36c0dcc3","resolution":{"observed_at":"2026-08-03T22:43:26.947162Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.14545","last_updated":"2022-06-28T04:13:53Z","snapshot_observed_at":"2026-08-18T05:50:54.233206Z","submitted_at":"2021-09-29T16:41:19Z","title":"Activation Functions in Deep Learning: A Comprehensive Survey and Benchmark","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.14545","snapshot_observed_at":"2026-08-03T11:27:30.163142Z","title":"Xavier Glorot and Yoshua Bengio","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2601.06441","last_updated":"2026-07-07T04:53:43Z","snapshot_observed_at":"2026-08-17T10:15:45.025160Z","submitted_at":"2026-01-10T05:51:25Z","title":"FlexAct: Why Learn when you can Pick?","version":2},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-03T11:27:30.163142Z"},"links":{"cited_paper":"/paper/2109.14545","citing_paper":"/paper/2601.06441"},"observation_digest":"sha256:e600878445895bcc9a0dd5a42bf432a0449e45135840686e382de1fa894085a7","observation_id":"40cf83a4-dcc1-4add-af58-ce5831ba0ba9","resolution":{"observed_at":"2026-08-03T11:27:30.163142Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.14545","last_updated":"2022-06-28T04:13:53Z","snapshot_observed_at":"2026-08-18T05:50:54.233206Z","submitted_at":"2021-09-29T16:41:19Z","title":"Activation Functions in Deep Learning: A Comprehensive Survey and Benchmark","version":3},"cited_work":{"arxiv_id":"2109.14545","doi":"10.48550/arxiv.2109.14545","metadata_source":"arxiv_reference","pith_arxiv_id":"2109.14545","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":null,"venue":"arXiv (Cornell University)","work_id":"aea15b3a-e667-49a2-8398-e8fe9420638c","year":2022},"citing_paper":{"arxiv_id":"2605.21830","last_updated":"2026-05-20T23:51:51Z","snapshot_observed_at":"2026-08-12T13:06:04.583614Z","submitted_at":"2026-05-20T23:51:51Z","title":"Solving forward and inverse wave scattering via boundary integral equations and deep learning. Applications to cloaking design","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-05-22T07:15:46.315943Z"},"links":{"cited_paper":"/paper/2109.14545","citing_paper":"/paper/2605.21830"},"observation_digest":"sha256:340b1cc0b6a50e24c37bbf4dc5c311f22fdad81dc78ddb1dfc92c5707ff5eecf","observation_id":"23a21835-bb86-4b42-99e2-744b6f5e946f","resolution":{"observed_at":"2026-05-22T07:16:12.662778Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-05-22T17:52:38.750604+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-22T17:52:38.750604+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2109.14545/citation-record","integrity":"/paper/2109.14545/integrity","json":"/paper/2109.14545/citation-record.json","paper":"/paper/2109.14545"},"outbound":[],"paper":{"arxiv_id":"2109.14545","last_updated":"2022-06-28T04:13:53Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-18T05:50:54.233206Z","submitted_at":"2021-09-29T16:41:19Z","title":"Activation Functions in Deep Learning: A Comprehensive Survey and Benchmark"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 9 inbound Pith citation observations for arXiv:2109.14545."}