{"as_of":"2026-08-07T16:40:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:135c63880d5357bf6906d18fb9d5ec813fffc95d18fd43796c3e3b998f1408a3","coverage":[{"denominator":25,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":25,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-12T04:33:35.163697Z","state":"measured"},{"denominator":25,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":25,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+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/2607.03148/citation-record","integrity":"/paper/2607.03148/integrity","json":"/paper/2607.03148/citation-record.json","paper":"/paper/2607.03148"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"1412.6830","last_updated":"2015-04-21T08:05:02Z","snapshot_observed_at":"2026-07-06T04:04:22.105016Z","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":"2026-07-12T04:33:35.163697Z","title":"Learning Activation Functions to Improve Deep Neural Networks","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.03148","last_updated":"2026-07-03T09:38:16Z","snapshot_observed_at":"2026-08-06T04:49:23.967161Z","submitted_at":"2026-07-03T09:38:16Z","title":"Rethinking Neural Nonlinearity as Gating","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-07-12T04:33:35.163697Z"},"links":{"cited_paper":"/paper/1412.6830","citing_paper":"/paper/2607.03148"},"observation_digest":"sha256:634eeb1d7122db093bffc3266d7397c85b791fcc91451cf936632a8694cf875f","observation_id":"5b5436f0-8d91-4eb7-b691-8803cce259d2","resolution":{"observed_at":"2026-07-12T04:33:35.163697Z","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":"2026-07-12T04:33:35.163697Z","title":"Training Stochastic Model Recognition Algorithms as Networks can Lead to Maximum Mutual Information Estimation of Parameters","venue":null,"work_id":null,"year":1989},"citing_paper":{"arxiv_id":"2607.03148","last_updated":"2026-07-03T09:38:16Z","snapshot_observed_at":"2026-08-06T04:49:23.967161Z","submitted_at":"2026-07-03T09:38:16Z","title":"Rethinking Neural Nonlinearity as Gating","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-07-12T04:33:35.163697Z"},"links":{"citing_paper":"/paper/2607.03148"},"observation_digest":"sha256:4e59449a8eeebae9f2c91256395b4c10ac69c9621b564730e11ee8d8961db705","observation_id":"781d29f4-3b1d-475d-80c9-47ee7df91e61","resolution":{"observed_at":"2026-07-12T04:33:35.163697Z","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":"10.1109/isca.2016.13","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"PRIME: A Novel Processing-in-Memory Architecture for Neural Network Computation in ReRAM-Based Main Memory","venue":null,"work_id":"d72ac7fd-eb07-4b5c-a6ae-16da6dcfb991","year":2016},"citing_paper":{"arxiv_id":"2607.03148","last_updated":"2026-07-03T09:38:16Z","snapshot_observed_at":"2026-08-06T04:49:23.967161Z","submitted_at":"2026-07-03T09:38:16Z","title":"Rethinking Neural Nonlinearity as Gating","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-07-12T04:33:35.163697Z"},"links":{"citing_paper":"/paper/2607.03148"},"observation_digest":"sha256:65ce57833c5b12a181b4c6cb23d4bf74ba694724368b8552c0372e86961a7b7b","observation_id":"04da861e-8ff4-477a-ba3a-19d7be97c880","resolution":{"observed_at":"2026-07-12T04:38:28.800622Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-07-13T20:50:18.431876+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-13T20:50:18.431876+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-07-12T04:33:35.163697Z","title":"Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.03148","last_updated":"2026-07-03T09:38:16Z","snapshot_observed_at":"2026-08-06T04:49:23.967161Z","submitted_at":"2026-07-03T09:38:16Z","title":"Rethinking Neural Nonlinearity as Gating","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-07-12T04:33:35.163697Z"},"links":{"cited_paper":"/paper/1511.07289","citing_paper":"/paper/2607.03148"},"observation_digest":"sha256:959fa3881843f1ea0da957355bea014299db822aa7a506670e1e3cbf19430d65","observation_id":"57122c4a-4ccf-4948-92c0-7ffda737ac00","resolution":{"observed_at":"2026-07-12T04:33:35.163697Z","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":"2026-07-12T04:33:35.163697Z","title":"Maxout Networks","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2607.03148","last_updated":"2026-07-03T09:38:16Z","snapshot_observed_at":"2026-08-06T04:49:23.967161Z","submitted_at":"2026-07-03T09:38:16Z","title":"Rethinking Neural Nonlinearity as Gating","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-07-12T04:33:35.163697Z"},"links":{"citing_paper":"/paper/2607.03148"},"observation_digest":"sha256:814ad19aebc82839c4849282e230c26628bf0afddcbb432fe1d581ee807062b9","observation_id":"20d8910d-b851-43f5-b1ad-6ded3fd0b200","resolution":{"observed_at":"2026-07-12T04:33:35.163697Z","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":"2026-07-12T04:33:35.163697Z","title":"On the Impact of the Activation func- tion on Deep Neural Networks Training","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.03148","last_updated":"2026-07-03T09:38:16Z","snapshot_observed_at":"2026-08-06T04:49:23.967161Z","submitted_at":"2026-07-03T09:38:16Z","title":"Rethinking Neural Nonlinearity as Gating","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-07-12T04:33:35.163697Z"},"links":{"citing_paper":"/paper/2607.03148"},"observation_digest":"sha256:56eca0073a0e6cde141db713d189417b385e41f29458d5d2ddd6df41aededf4d","observation_id":"2e3963c0-e020-422b-a9ca-6b0ccc2742ff","resolution":{"observed_at":"2026-07-12T04:33:35.163697Z","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":"2026-07-12T04:33:35.163697Z","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.03148","last_updated":"2026-07-03T09:38:16Z","snapshot_observed_at":"2026-08-06T04:49:23.967161Z","submitted_at":"2026-07-03T09:38:16Z","title":"Rethinking Neural Nonlinearity as Gating","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-07-12T04:33:35.163697Z"},"links":{"citing_paper":"/paper/2607.03148"},"observation_digest":"sha256:69a1c18db338cf3c34259d8b32cab034e3a0614b29602bde29381c885c1193cf","observation_id":"4d03bc0f-44e0-41fb-8d64-e7644109af5d","resolution":{"observed_at":"2026-07-12T04:33:35.163697Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1606.08415","last_updated":"2023-06-06T01:53:32Z","snapshot_observed_at":"2026-07-06T05:01:27.910364Z","submitted_at":"2016-06-27T19:20:40Z","title":"Gaussian Error Linear Units (GELUs)","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1606.08415","snapshot_observed_at":"2026-07-12T04:33:35.163697Z","title":"Gaussian Error Linear Units (GELUs)","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.03148","last_updated":"2026-07-03T09:38:16Z","snapshot_observed_at":"2026-08-06T04:49:23.967161Z","submitted_at":"2026-07-03T09:38:16Z","title":"Rethinking Neural Nonlinearity as Gating","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-07-12T04:33:35.163697Z"},"links":{"cited_paper":"/paper/1606.08415","citing_paper":"/paper/2607.03148"},"observation_digest":"sha256:dc6e2c4817001ccbdcebdc9dd5b49aa4cf2d0fe034a1fbabbd978e5657757644","observation_id":"972e1884-2f19-4e46-aa20-08b9045aeb10","resolution":{"observed_at":"2026-07-12T04:33:35.163697Z","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":"2026-07-12T04:33:35.163697Z","title":"Curvature Tuning: Provable Training- free Model Steering From a Single Parameter","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.03148","last_updated":"2026-07-03T09:38:16Z","snapshot_observed_at":"2026-08-06T04:49:23.967161Z","submitted_at":"2026-07-03T09:38:16Z","title":"Rethinking Neural Nonlinearity as Gating","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-07-12T04:33:35.163697Z"},"links":{"citing_paper":"/paper/2607.03148"},"observation_digest":"sha256:71e1ce6868a896f98c2922f92f57fc034004a4de5352fad5cc9dfffaf5f37600","observation_id":"da280fd5-a8c6-4acb-a55a-950b1edce5a8","resolution":{"observed_at":"2026-07-12T04:33:35.163697Z","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":"2026-07-12T04:33:35.163697Z","title":"In-Memory Computing with Resistive Switching Devices","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.03148","last_updated":"2026-07-03T09:38:16Z","snapshot_observed_at":"2026-08-06T04:49:23.967161Z","submitted_at":"2026-07-03T09:38:16Z","title":"Rethinking Neural Nonlinearity as Gating","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-07-12T04:33:35.163697Z"},"links":{"citing_paper":"/paper/2607.03148"},"observation_digest":"sha256:2976c25e93fbc9b2788f0f399b62d9096bf81d5b10f3a62eab2887fc29bce221","observation_id":"6a3bcf62-47d3-4677-a52c-b519eff7ec65","resolution":{"observed_at":"2026-07-12T04:33:35.163697Z","resolver_source":null,"status":"malformed_identifier"},"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":"2026-07-12T04:33:35.163697Z","title":null,"venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2607.03148","last_updated":"2026-07-03T09:38:16Z","snapshot_observed_at":"2026-08-06T04:49:23.967161Z","submitted_at":"2026-07-03T09:38:16Z","title":"Rethinking Neural Nonlinearity as Gating","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-07-12T04:33:35.163697Z"},"links":{"citing_paper":"/paper/2607.03148"},"observation_digest":"sha256:ae2395c8e420381749d01b4bf786787dcb2ca5f9bd38df766239d986863e4079","observation_id":"1246c2e0-cc30-4ad5-ac37-4de875c9962a","resolution":{"observed_at":"2026-07-12T04:33:35.163697Z","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":"2026-07-12T04:33:35.163697Z","title":"Analog In-Memory Computing Attention Mechanism for Fast and Energy-Efficient Large Language Models","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.03148","last_updated":"2026-07-03T09:38:16Z","snapshot_observed_at":"2026-08-06T04:49:23.967161Z","submitted_at":"2026-07-03T09:38:16Z","title":"Rethinking Neural Nonlinearity as Gating","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-07-12T04:33:35.163697Z"},"links":{"citing_paper":"/paper/2607.03148"},"observation_digest":"sha256:1614588ddde24661523bbaea2a959b2d8c9575a2344fd2f28e8f0e67c82bdbe1","observation_id":"bf2f3223-a83d-4d95-a426-1de956a38019","resolution":{"observed_at":"2026-07-12T04:33:35.163697Z","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":"2026-07-12T04:33:35.163697Z","title":"KAN: Kolmogorov-Arnold Networks","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.03148","last_updated":"2026-07-03T09:38:16Z","snapshot_observed_at":"2026-08-06T04:49:23.967161Z","submitted_at":"2026-07-03T09:38:16Z","title":"Rethinking Neural Nonlinearity as Gating","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-07-12T04:33:35.163697Z"},"links":{"citing_paper":"/paper/2607.03148"},"observation_digest":"sha256:6a2377a440b104b28f46c7fd1f41b466f9200af3fa71595ff5a57ed2b16c6b2a","observation_id":"f3411697-8fe9-474c-92b7-72ece09ce67d","resolution":{"observed_at":"2026-07-12T04:33:35.163697Z","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":"2026-07-12T04:33:35.163697Z","title":"Rectifier Nonlinearities Improve Neural Network Acoustic Models","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2607.03148","last_updated":"2026-07-03T09:38:16Z","snapshot_observed_at":"2026-08-06T04:49:23.967161Z","submitted_at":"2026-07-03T09:38:16Z","title":"Rethinking Neural Nonlinearity as Gating","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-07-12T04:33:35.163697Z"},"links":{"citing_paper":"/paper/2607.03148"},"observation_digest":"sha256:9a3bef47399b910eea9c0c2699fbaafe749618e10474e3af8f526bfdd045c588","observation_id":"9b529d5b-6147-4381-b6b0-492a4eee5144","resolution":{"observed_at":"2026-07-12T04:33:35.163697Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"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":"2026-07-12T04:33:35.163697Z","title":"Mish: A Self Regularized Non-Monotonic Activation Function","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.03148","last_updated":"2026-07-03T09:38:16Z","snapshot_observed_at":"2026-08-06T04:49:23.967161Z","submitted_at":"2026-07-03T09:38:16Z","title":"Rethinking Neural Nonlinearity as Gating","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-07-12T04:33:35.163697Z"},"links":{"cited_paper":"/paper/1908.08681","citing_paper":"/paper/2607.03148"},"observation_digest":"sha256:c3c8e73d96024c4eb869c80db32873be8f720ea7f7d0ec7d841997eba9a09a12","observation_id":"c52b5bbe-8036-4dd4-b1b0-3117424f4b0e","resolution":{"observed_at":"2026-07-12T04:33:35.163697Z","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":"2026-07-12T04:33:35.163697Z","title":"Padé Activation Units: End- to-end Learning of Flexible Activation Functions in Deep Networks","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.03148","last_updated":"2026-07-03T09:38:16Z","snapshot_observed_at":"2026-08-06T04:49:23.967161Z","submitted_at":"2026-07-03T09:38:16Z","title":"Rethinking Neural Nonlinearity as Gating","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-07-12T04:33:35.163697Z"},"links":{"citing_paper":"/paper/2607.03148"},"observation_digest":"sha256:f584c5c5e35262d7973af9cadf0ed55a489ddc650db94b1e6a1f264920e62854","observation_id":"45791a63-a9b6-45bb-a29e-1301714dfc7d","resolution":{"observed_at":"2026-07-12T04:33:35.163697Z","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":"2026-07-12T04:33:35.163697Z","title":"Rectified Linear Units Improve Restricted Boltzmann Machines","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2607.03148","last_updated":"2026-07-03T09:38:16Z","snapshot_observed_at":"2026-08-06T04:49:23.967161Z","submitted_at":"2026-07-03T09:38:16Z","title":"Rethinking Neural Nonlinearity as Gating","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-07-12T04:33:35.163697Z"},"links":{"citing_paper":"/paper/2607.03148"},"observation_digest":"sha256:836c3931fea5ce2ed48837b12a6d2187854c69bb64946439429626297b75d761","observation_id":"f216dc78-e164-4437-8fe5-c63bb8c8f616","resolution":{"observed_at":"2026-07-12T04:33:35.163697Z","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":"2026-07-12T04:33:35.163697Z","title":"Training and Operation of an Integrated Neuromorphic Network Based on Metal-Oxide Memristors","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.03148","last_updated":"2026-07-03T09:38:16Z","snapshot_observed_at":"2026-08-06T04:49:23.967161Z","submitted_at":"2026-07-03T09:38:16Z","title":"Rethinking Neural Nonlinearity as Gating","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-07-12T04:33:35.163697Z"},"links":{"citing_paper":"/paper/2607.03148"},"observation_digest":"sha256:fa8c0eaa603b01f0ab895090e50dcbeff46945b30f5cc5cd7ba883ab013e2536","observation_id":"b868710e-78c6-4397-921e-5785eb20a59c","resolution":{"observed_at":"2026-07-12T04:33:35.163697Z","resolver_source":null,"status":"malformed_identifier"},"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":"2026-07-12T04:33:35.163697Z","title":"Searching for Activation Functions","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.03148","last_updated":"2026-07-03T09:38:16Z","snapshot_observed_at":"2026-08-06T04:49:23.967161Z","submitted_at":"2026-07-03T09:38:16Z","title":"Rethinking Neural Nonlinearity as Gating","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-07-12T04:33:35.163697Z"},"links":{"citing_paper":"/paper/2607.03148"},"observation_digest":"sha256:3d6b39250f207c797b4c584b90e4e87dd944e58d59f2435733e28f5751470313","observation_id":"c8996269-1715-46e2-a363-fc684b96d751","resolution":{"observed_at":"2026-07-12T04:33:35.163697Z","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":"2026-07-12T04:33:35.163697Z","title":"ImageNet Large Scale Visual Recognition Challenge","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.03148","last_updated":"2026-07-03T09:38:16Z","snapshot_observed_at":"2026-08-06T04:49:23.967161Z","submitted_at":"2026-07-03T09:38:16Z","title":"Rethinking Neural Nonlinearity as Gating","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-07-12T04:33:35.163697Z"},"links":{"citing_paper":"/paper/2607.03148"},"observation_digest":"sha256:2c86edb47c516948aefbaca4c03783770ff29f1f6833efcfeeea4ece247bf409","observation_id":"40a1d3ad-2002-4a24-98a0-9cfbea1fd29a","resolution":{"observed_at":"2026-07-12T04:33:35.163697Z","resolver_source":null,"status":"malformed_identifier"},"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":"2026-07-12T04:33:35.163697Z","title":"Memory Devices and Applications for In-Memory Computing","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.03148","last_updated":"2026-07-03T09:38:16Z","snapshot_observed_at":"2026-08-06T04:49:23.967161Z","submitted_at":"2026-07-03T09:38:16Z","title":"Rethinking Neural Nonlinearity as Gating","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-07-12T04:33:35.163697Z"},"links":{"citing_paper":"/paper/2607.03148"},"observation_digest":"sha256:07f5c081c5a186bb1efb0fa8dacee53bc152f45b31e8af73c995bc6b557f2845","observation_id":"3de00180-1532-4e79-8434-35482e2c269f","resolution":{"observed_at":"2026-07-12T04:33:35.163697Z","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":"2026-07-12T04:33:35.163697Z","title":"ISAAC: A Convolutional Neural Network Accelerator with In-Situ Ana- log Arithmetic in Crossbars","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.03148","last_updated":"2026-07-03T09:38:16Z","snapshot_observed_at":"2026-08-06T04:49:23.967161Z","submitted_at":"2026-07-03T09:38:16Z","title":"Rethinking Neural Nonlinearity as Gating","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-07-12T04:33:35.163697Z"},"links":{"citing_paper":"/paper/2607.03148"},"observation_digest":"sha256:a246802c01645cd55a96c32400c13fba7bc2c8b64b7b75f6cd314b2f1afac9b3","observation_id":"397c1aef-cd72-451e-b718-371f5b176886","resolution":{"observed_at":"2026-07-12T04:33:35.163697Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2002.05202","last_updated":"2020-02-12T19:57:13Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2020-02-12T19:57:13Z","title":"GLU Variants Improve Transformer","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.05202","snapshot_observed_at":"2026-07-12T04:33:35.163697Z","title":"GLU Variants Improve Transformer","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.03148","last_updated":"2026-07-03T09:38:16Z","snapshot_observed_at":"2026-08-06T04:49:23.967161Z","submitted_at":"2026-07-03T09:38:16Z","title":"Rethinking Neural Nonlinearity as Gating","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-07-12T04:33:35.163697Z"},"links":{"cited_paper":"/paper/2002.05202","citing_paper":"/paper/2607.03148"},"observation_digest":"sha256:073a3efdc250626b46a55f958161b93fc94bff6677289864ac7f32e63e0debcd","observation_id":"22c1e60f-0a01-475b-934d-6345d37c5bbb","resolution":{"observed_at":"2026-07-12T04:33:35.163697Z","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":"2026-07-12T04:33:35.163697Z","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture- of-Experts Layer","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.03148","last_updated":"2026-07-03T09:38:16Z","snapshot_observed_at":"2026-08-06T04:49:23.967161Z","submitted_at":"2026-07-03T09:38:16Z","title":"Rethinking Neural Nonlinearity as Gating","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-07-12T04:33:35.163697Z"},"links":{"citing_paper":"/paper/2607.03148"},"observation_digest":"sha256:67be8f4056ce3a32c9f510398822e33276b2d475e6a54cc8cdba3d28f67f0385","observation_id":"90f272d1-b3be-424f-91fe-722c74c2988c","resolution":{"observed_at":"2026-07-12T04:33:35.163697Z","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":"2026-07-12T04:33:35.163697Z","title":"Training Very Deep Net- works","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.03148","last_updated":"2026-07-03T09:38:16Z","snapshot_observed_at":"2026-08-06T04:49:23.967161Z","submitted_at":"2026-07-03T09:38:16Z","title":"Rethinking Neural Nonlinearity as Gating","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-07-12T04:33:35.163697Z"},"links":{"citing_paper":"/paper/2607.03148"},"observation_digest":"sha256:8aa8e4e2a90105a95d2ce683ceb9bebd98ae3be41d3ad4b75a1a484e28d61462","observation_id":"5d43d356-2425-4eec-ac55-fc56c7ec4d1f","resolution":{"observed_at":"2026-07-12T04:33:35.163697Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.03148","last_updated":"2026-07-03T09:38:16Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-06T04:49:23.967161Z","submitted_at":"2026-07-03T09:38:16Z","title":"Rethinking Neural Nonlinearity as Gating"},"reference_resolution":{"displayed":25,"state_counts":{"malformed_identifier":5,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":19,"verified_exact":1,"verified_fuzzy":0},"total_outbound_references":25},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 25 of 25 outbound references and 0 inbound Pith citation observations for arXiv:2607.03148."}