{"as_of":"2026-08-12T04:15:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:6e15a89e3e8e0300a645a01a401dea0626ef86fe3c949552a6b8c5b58bc8c883","coverage":[{"denominator":42,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":42,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T16:51:00.536240Z","state":"measured"},{"denominator":43,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":43,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-11T06:34:44.6726+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-08T19:06:22.016193Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-07-08T19:15:30.439186Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2412.09752","last_updated":"2024-12-12T22:57:28Z","snapshot_observed_at":"2026-08-12T03:09:30.255276Z","submitted_at":"2024-12-12T22:57:28Z","title":"A Quasilinear Algorithm for Computing Higher-Order Derivatives of Deep Feed-Forward Neural Networks","version":1},"cited_work":{"arxiv_id":"2412.09752","doi":null,"metadata_source":"pith","pith_arxiv_id":"2412.09752","snapshot_observed_at":"2026-07-08T19:15:30.439186Z","title":"A Quasilinear Algorithm for Computing Higher-Order Derivatives of Deep Feed-Forward Neural Networks","venue":"cs.LG","work_id":"06dc088e-6c38-4b92-9ab1-130aedf6221d","year":2024},"citing_paper":{"arxiv_id":"2607.06026","last_updated":"2026-07-07T09:05:35Z","snapshot_observed_at":"2026-08-05T02:19:20.849414Z","submitted_at":"2026-07-07T09:05:35Z","title":"SplineNet: An Isogeometric Deep Learning Method for Complex Shells","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-07-08T19:06:22.016193Z"},"links":{"cited_paper":"/paper/2412.09752","citing_paper":"/paper/2607.06026"},"observation_digest":"sha256:6f9c601e44f7ff4ac9e3f3403de1838341c19ca897e65e7e9347afc487e307f2","observation_id":"85f7a439-c97f-4b7f-ab61-873713f3c71c","resolution":{"observed_at":"2026-07-08T19:15:30.440419Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2412.09752/citation-record","integrity":"/paper/2412.09752/integrity","json":"/paper/2412.09752/citation-record.json","paper":"/paper/2412.09752"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T16:51:01.385734Z","title":"A NTONION , X","venue":null,"work_id":"1153525f-fd26-4458-b5f4-a2eb4363daf1","year":2024},"citing_paper":{"arxiv_id":"2412.09752","last_updated":"2024-12-12T22:57:28Z","snapshot_observed_at":"2026-08-12T03:09:30.255276Z","submitted_at":"2024-12-12T22:57:28Z","title":"A Quasilinear Algorithm for Computing Higher-Order Derivatives of Deep Feed-Forward Neural Networks","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-11T16:51:00.339571Z"},"links":{"citing_paper":"/paper/2412.09752"},"observation_digest":"sha256:975022affb20c8b230f4fdf440b5e0ed162af7e8cfb4d1c1a322352ee1b5f71b","observation_id":"c9af28d5-d075-49d3-b170-1177ab00f48f","resolution":{"observed_at":"2026-08-11T16:51:01.390395Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T16:51:01.370504Z","title":"B ARENBLATT AND Y","venue":null,"work_id":"1fd9760c-a442-4824-a21f-a1faaee8e459","year":1972},"citing_paper":{"arxiv_id":"2412.09752","last_updated":"2024-12-12T22:57:28Z","snapshot_observed_at":"2026-08-12T03:09:30.255276Z","submitted_at":"2024-12-12T22:57:28Z","title":"A Quasilinear Algorithm for Computing Higher-Order Derivatives of Deep Feed-Forward Neural Networks","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-11T16:51:00.345240Z"},"links":{"citing_paper":"/paper/2412.09752"},"observation_digest":"sha256:2569e6e02cfc9c3a3a08bd9b519f1d5fb24a0e2d0ae036fe6229264fab0600f9","observation_id":"70f59e82-ec56-45d2-8eed-21e56c14ed48","resolution":{"observed_at":"2026-08-11T16:51:01.375162Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T16:51:01.355467Z","title":null,"venue":null,"work_id":"b4e2f854-2291-41ee-9940-63493d96d070","year":2018},"citing_paper":{"arxiv_id":"2412.09752","last_updated":"2024-12-12T22:57:28Z","snapshot_observed_at":"2026-08-12T03:09:30.255276Z","submitted_at":"2024-12-12T22:57:28Z","title":"A Quasilinear Algorithm for Computing Higher-Order Derivatives of Deep Feed-Forward Neural Networks","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-11T16:51:00.350214Z"},"links":{"citing_paper":"/paper/2412.09752"},"observation_digest":"sha256:85b3eb5db694e8f62e1d43cb3976f2d705b40c4df1ed3bfef7adadd0d11bd807","observation_id":"54f959ce-de22-4389-b278-6b75cde85c77","resolution":{"observed_at":"2026-08-11T16:51:01.360269Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T16:51:01.340356Z","title":"B IASI , Self-similar solutions to the compressible euler equations and their instabilities, Communications in Nonlinear Science and Numerical Simulation, 103 (2021), p","venue":null,"work_id":"0fba8378-3185-4a5a-8f57-36ca8960e72f","year":2021},"citing_paper":{"arxiv_id":"2412.09752","last_updated":"2024-12-12T22:57:28Z","snapshot_observed_at":"2026-08-12T03:09:30.255276Z","submitted_at":"2024-12-12T22:57:28Z","title":"A Quasilinear Algorithm for Computing Higher-Order Derivatives of Deep Feed-Forward Neural Networks","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-11T16:51:00.355112Z"},"links":{"citing_paper":"/paper/2412.09752"},"observation_digest":"sha256:8b5d4bf96f4e946e803a06795ae75c748588a1a6ec6c60b4e6604f6d9524867b","observation_id":"641d4fde-41f6-44f0-9952-4eb046aaec31","resolution":{"observed_at":"2026-08-11T16:51:01.345531Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T16:51:00.360252Z","title":"B ISCHOF AND M","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.09752","last_updated":"2024-12-12T22:57:28Z","snapshot_observed_at":"2026-08-12T03:09:30.255276Z","submitted_at":"2024-12-12T22:57:28Z","title":"A Quasilinear Algorithm for Computing Higher-Order Derivatives of Deep Feed-Forward Neural Networks","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-11T16:51:00.360252Z"},"links":{"citing_paper":"/paper/2412.09752"},"observation_digest":"sha256:246005e2fa823e85ba9f473f2e1e442045d9c0f16471fcd36c6780e98fbb7285","observation_id":"03172e1b-5fee-4c89-817d-6c3ab381fe95","resolution":{"observed_at":"2026-08-11T16:51:00.360252Z","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":"2026-08-11T16:51:01.324600Z","title":null,"venue":null,"work_id":"c4772c34-619a-4d36-8240-592999c47c12","year":2010},"citing_paper":{"arxiv_id":"2412.09752","last_updated":"2024-12-12T22:57:28Z","snapshot_observed_at":"2026-08-12T03:09:30.255276Z","submitted_at":"2024-12-12T22:57:28Z","title":"A Quasilinear Algorithm for Computing Higher-Order Derivatives of Deep Feed-Forward Neural Networks","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-11T16:51:00.365260Z"},"links":{"citing_paper":"/paper/2412.09752"},"observation_digest":"sha256:b637da8785aad7e2ed7522a99b7ec0d38341062f1de41aa7ff632053347a6752","observation_id":"984e0d4c-d085-48e0-bae3-8a1f8366b569","resolution":{"observed_at":"2026-08-11T16:51:01.329224Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T16:51:01.308062Z","title":null,"venue":null,"work_id":"a61c602f-d5a4-42bb-8efd-1c2e91436365","year":2023},"citing_paper":{"arxiv_id":"2412.09752","last_updated":"2024-12-12T22:57:28Z","snapshot_observed_at":"2026-08-12T03:09:30.255276Z","submitted_at":"2024-12-12T22:57:28Z","title":"A Quasilinear Algorithm for Computing Higher-Order Derivatives of Deep Feed-Forward Neural Networks","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-11T16:51:00.370543Z"},"links":{"citing_paper":"/paper/2412.09752"},"observation_digest":"sha256:d49a238c7d9a7845530c72be8ab85a3ea58fbdfcf2749e34ca7d7f5ba5acbb67","observation_id":"f1c14406-c98d-46dc-ac38-fdefd461f9cd","resolution":{"observed_at":"2026-08-11T16:51:01.313402Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T16:51:01.291814Z","title":"C HIU , J","venue":null,"work_id":"27a43b3e-14a1-4d6a-9f5a-0d8e9845d63a","year":2022},"citing_paper":{"arxiv_id":"2412.09752","last_updated":"2024-12-12T22:57:28Z","snapshot_observed_at":"2026-08-12T03:09:30.255276Z","submitted_at":"2024-12-12T22:57:28Z","title":"A Quasilinear Algorithm for Computing Higher-Order Derivatives of Deep Feed-Forward Neural Networks","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-11T16:51:00.375185Z"},"links":{"citing_paper":"/paper/2412.09752"},"observation_digest":"sha256:1b594d63171660bf18598b98837c59c913748379764534a17f2c5fb07e4f940a","observation_id":"940344c3-3da4-4617-a5ea-8c407a127d72","resolution":{"observed_at":"2026-08-11T16:51:01.297195Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T16:51:01.275209Z","title":"C YBENKO , Approximation by superpositions of a sigmoidal function, Mathematics of control, signals and systems, 2 (1989), pp","venue":null,"work_id":"f007065c-4189-4a28-8fd4-0f346e3bb75a","year":1989},"citing_paper":{"arxiv_id":"2412.09752","last_updated":"2024-12-12T22:57:28Z","snapshot_observed_at":"2026-08-12T03:09:30.255276Z","submitted_at":"2024-12-12T22:57:28Z","title":"A Quasilinear Algorithm for Computing Higher-Order Derivatives of Deep Feed-Forward Neural Networks","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-11T16:51:00.379653Z"},"links":{"citing_paper":"/paper/2412.09752"},"observation_digest":"sha256:84cc8c14c1a809605f16f6b226bdc195caab0e8a6d929ea37bd6edfd0b2c0112","observation_id":"033bb0d2-b291-4ddb-b326-0d20e4fddb20","resolution":{"observed_at":"2026-08-11T16:51:01.280507Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T16:51:01.254641Z","title":null,"venue":null,"work_id":"cb7740e9-7078-4c0f-bd89-608d3c9ad4ca","year":2017},"citing_paper":{"arxiv_id":"2412.09752","last_updated":"2024-12-12T22:57:28Z","snapshot_observed_at":"2026-08-12T03:09:30.255276Z","submitted_at":"2024-12-12T22:57:28Z","title":"A Quasilinear Algorithm for Computing Higher-Order Derivatives of Deep Feed-Forward Neural Networks","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-11T16:51:00.384208Z"},"links":{"citing_paper":"/paper/2412.09752"},"observation_digest":"sha256:f03e448c8a9c78e86954ae73d48777ad36ce13072e6f4b18acaa70327c699d74","observation_id":"e000fef0-a1d7-49eb-82fc-fb8024584679","resolution":{"observed_at":"2026-08-11T16:51:01.262544Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.05801","last_updated":"2024-05-03T10:59:26Z","snapshot_observed_at":"2026-07-06T16:29:51.896529Z","submitted_at":"2023-10-09T15:37:06Z","title":"An operator preconditioning perspective on training in physics-informed machine learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.05801","snapshot_observed_at":"2026-08-11T16:51:00.388892Z","title":"D E RYCK , F","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.09752","last_updated":"2024-12-12T22:57:28Z","snapshot_observed_at":"2026-08-12T03:09:30.255276Z","submitted_at":"2024-12-12T22:57:28Z","title":"A Quasilinear Algorithm for Computing Higher-Order Derivatives of Deep Feed-Forward Neural Networks","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-11T16:51:00.388892Z"},"links":{"cited_paper":"/paper/2310.05801","citing_paper":"/paper/2412.09752"},"observation_digest":"sha256:4051561aea81ee2502731a2717fe5b488495e1f47bf0dfaa1e9561fb38695963","observation_id":"1bcaacb6-b2c3-4a70-bd76-d99558e030d1","resolution":{"observed_at":"2026-08-11T16:51:00.388892Z","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":"2026-08-11T16:51:01.238791Z","title":"E GGERS AND M","venue":null,"work_id":"364a73ee-d0e7-4473-9ac1-46050293b433","year":2015},"citing_paper":{"arxiv_id":"2412.09752","last_updated":"2024-12-12T22:57:28Z","snapshot_observed_at":"2026-08-12T03:09:30.255276Z","submitted_at":"2024-12-12T22:57:28Z","title":"A Quasilinear Algorithm for Computing Higher-Order Derivatives of Deep Feed-Forward Neural Networks","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-11T16:51:00.394320Z"},"links":{"citing_paper":"/paper/2412.09752"},"observation_digest":"sha256:caf456315eea8252dc182ba31a28ff874443e020979ee126d85b592bb2fa380c","observation_id":"d11ab607-c243-42ac-b1c1-1a7701bc5ac9","resolution":{"observed_at":"2026-08-11T16:51:01.243433Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T16:51:01.223400Z","title":null,"venue":null,"work_id":"5169d81a-0410-437b-ae1b-8101e77802b1","year":2022},"citing_paper":{"arxiv_id":"2412.09752","last_updated":"2024-12-12T22:57:28Z","snapshot_observed_at":"2026-08-12T03:09:30.255276Z","submitted_at":"2024-12-12T22:57:28Z","title":"A Quasilinear Algorithm for Computing Higher-Order Derivatives of Deep Feed-Forward Neural Networks","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-11T16:51:00.399388Z"},"links":{"citing_paper":"/paper/2412.09752"},"observation_digest":"sha256:a8119c218f823d28977d10c579dd158f64b9b7a679bbbe28bee22c64bab49651","observation_id":"c353f79d-8927-41a8-ae06-26f8ba6b47f5","resolution":{"observed_at":"2026-08-11T16:51:01.227989Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T16:51:01.208004Z","title":"F AREA , O","venue":null,"work_id":"2cfba6ba-3500-4321-a4a5-e26670988ff7","year":2024},"citing_paper":{"arxiv_id":"2412.09752","last_updated":"2024-12-12T22:57:28Z","snapshot_observed_at":"2026-08-12T03:09:30.255276Z","submitted_at":"2024-12-12T22:57:28Z","title":"A Quasilinear Algorithm for Computing Higher-Order Derivatives of Deep Feed-Forward Neural Networks","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-11T16:51:00.404321Z"},"links":{"citing_paper":"/paper/2412.09752"},"observation_digest":"sha256:35f3ce7ebd127c41efcb6ce4a20f83cd01cba23689e8c45d1076631231f302d9","observation_id":"fe98b127-3a21-492f-9ee9-57a4946c66f5","resolution":{"observed_at":"2026-08-11T16:51:01.213142Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T16:51:01.190941Z","title":"H ABERMAN , Elementary applied partial differential equations: with Fourier series and boundary value problems , Prentice-Hall Englewood Cliffs, NJ, 1987","venue":null,"work_id":"ea5d483b-d0ec-4a21-8626-9ed0263b963b","year":1987},"citing_paper":{"arxiv_id":"2412.09752","last_updated":"2024-12-12T22:57:28Z","snapshot_observed_at":"2026-08-12T03:09:30.255276Z","submitted_at":"2024-12-12T22:57:28Z","title":"A Quasilinear Algorithm for Computing Higher-Order Derivatives of Deep Feed-Forward Neural Networks","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-11T16:51:00.410554Z"},"links":{"citing_paper":"/paper/2412.09752"},"observation_digest":"sha256:7f22fdb0390b2d59699247721ebb424dc8fbef84bd855b87ebe9b4e72eb86e8d","observation_id":"19d7d06b-3afc-43cf-9680-9a9b468eddff","resolution":{"observed_at":"2026-08-11T16:51:01.196395Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T16:51:01.175019Z","title":null,"venue":null,"work_id":"1faf83c2-722a-4f39-8308-1a1e47810863","year":1917},"citing_paper":{"arxiv_id":"2412.09752","last_updated":"2024-12-12T22:57:28Z","snapshot_observed_at":"2026-08-12T03:09:30.255276Z","submitted_at":"2024-12-12T22:57:28Z","title":"A Quasilinear Algorithm for Computing Higher-Order Derivatives of Deep Feed-Forward Neural Networks","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-11T16:51:00.415488Z"},"links":{"citing_paper":"/paper/2412.09752"},"observation_digest":"sha256:02b256dde73ce76a7989f33ac17c96c30d85f2159d3bf945e56b9c1902bfa58d","observation_id":"831a0274-c738-47b0-891c-a655a5fb04de","resolution":{"observed_at":"2026-08-11T16:51:01.179588Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T16:51:01.158654Z","title":"H ORNIK , Approximation capabilities of multilayer feedforward net- works, Neural networks, 4 (1991), pp","venue":null,"work_id":"f8e0eeb1-f1f2-4082-b236-e4fc2ee26d44","year":1991},"citing_paper":{"arxiv_id":"2412.09752","last_updated":"2024-12-12T22:57:28Z","snapshot_observed_at":"2026-08-12T03:09:30.255276Z","submitted_at":"2024-12-12T22:57:28Z","title":"A Quasilinear Algorithm for Computing Higher-Order Derivatives of Deep Feed-Forward Neural Networks","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-11T16:51:00.420206Z"},"links":{"citing_paper":"/paper/2412.09752"},"observation_digest":"sha256:25ab2f1d252b0b597ec4b7941d59f5042dd9547f15e97d3284131b4ea2781275","observation_id":"8a7ea37e-9cd8-4fb5-ab32-9eb68945fe94","resolution":{"observed_at":"2026-08-11T16:51:01.163940Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T16:51:01.142920Z","title":"J AHANI -NASAB AND M","venue":null,"work_id":"6ceeb5a1-3452-45f9-bad0-eddd48653945","year":2024},"citing_paper":{"arxiv_id":"2412.09752","last_updated":"2024-12-12T22:57:28Z","snapshot_observed_at":"2026-08-12T03:09:30.255276Z","submitted_at":"2024-12-12T22:57:28Z","title":"A Quasilinear Algorithm for Computing Higher-Order Derivatives of Deep Feed-Forward Neural Networks","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-11T16:51:00.425129Z"},"links":{"citing_paper":"/paper/2412.09752"},"observation_digest":"sha256:84b8e0f525504f12abd998f32208bde3142606e4020c82beaf168b65ab7660a6","observation_id":"564ad5a6-0f65-4df7-9331-5cc55f7743ec","resolution":{"observed_at":"2026-08-11T16:51:01.148132Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T16:51:01.127733Z","title":"K RISHNAPRIYAN , A","venue":null,"work_id":"26b26d41-ad49-4d79-bef2-963068b09761","year":2021},"citing_paper":{"arxiv_id":"2412.09752","last_updated":"2024-12-12T22:57:28Z","snapshot_observed_at":"2026-08-12T03:09:30.255276Z","submitted_at":"2024-12-12T22:57:28Z","title":"A Quasilinear Algorithm for Computing Higher-Order Derivatives of Deep Feed-Forward Neural Networks","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-11T16:51:00.429679Z"},"links":{"citing_paper":"/paper/2412.09752"},"observation_digest":"sha256:7aef4dd40a23968043105d05f5e042b6e4afe1fa100e52be5eb39bf4da6faf0e","observation_id":"7e713e6f-c50e-4925-84c9-60ec816093ba","resolution":{"observed_at":"2026-08-11T16:51:01.132459Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T16:51:01.111731Z","title":"M ADDU , D","venue":null,"work_id":"5153e911-6413-4b4a-9e79-dbdc96d649d8","year":2022},"citing_paper":{"arxiv_id":"2412.09752","last_updated":"2024-12-12T22:57:28Z","snapshot_observed_at":"2026-08-12T03:09:30.255276Z","submitted_at":"2024-12-12T22:57:28Z","title":"A Quasilinear Algorithm for Computing Higher-Order Derivatives of Deep Feed-Forward Neural Networks","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-11T16:51:00.434924Z"},"links":{"citing_paper":"/paper/2412.09752"},"observation_digest":"sha256:d780fef363028a34e2d2c2e43d31e83105d3fa9ba4294c1ffe7205a03007e472","observation_id":"9439ac1b-d23d-46fd-ac78-2709357f575f","resolution":{"observed_at":"2026-08-11T16:51:01.116707Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T16:51:01.096266Z","title":"M ARKIDIS , The old and the new: Can physics-informed deep- learning replace traditional linear solvers? , Frontiers in big Data, 4 (2021), p","venue":null,"work_id":"f6608f66-0d76-4146-b3b5-a74862e71587","year":2021},"citing_paper":{"arxiv_id":"2412.09752","last_updated":"2024-12-12T22:57:28Z","snapshot_observed_at":"2026-08-12T03:09:30.255276Z","submitted_at":"2024-12-12T22:57:28Z","title":"A Quasilinear Algorithm for Computing Higher-Order Derivatives of Deep Feed-Forward Neural Networks","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-11T16:51:00.439728Z"},"links":{"citing_paper":"/paper/2412.09752"},"observation_digest":"sha256:6e2e1da110e8376f28de7ca43829c95033a7e9f50f3306ccff10e9d7530086fd","observation_id":"c5b6f9d4-cc92-4603-9fd3-559aacae10a0","resolution":{"observed_at":"2026-08-11T16:51:01.101424Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T16:51:01.081488Z","title":"M CGREIVY AND A","venue":null,"work_id":"b044bde8-a6a5-460d-8b71-09dabdd9e00c","year":2024},"citing_paper":{"arxiv_id":"2412.09752","last_updated":"2024-12-12T22:57:28Z","snapshot_observed_at":"2026-08-12T03:09:30.255276Z","submitted_at":"2024-12-12T22:57:28Z","title":"A Quasilinear Algorithm for Computing Higher-Order Derivatives of Deep Feed-Forward Neural Networks","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-11T16:51:00.444156Z"},"links":{"citing_paper":"/paper/2412.09752"},"observation_digest":"sha256:db9a35ed9095a801830d2d557325922e939c14d4a7460b3439e0c3529e516a8c","observation_id":"e39d9b5c-a2d6-4a1d-bd24-15a22d584917","resolution":{"observed_at":"2026-08-11T16:51:01.086247Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T16:51:01.066844Z","title":null,"venue":null,"work_id":"ac20384f-8e3e-4fe0-b3f6-35d8dfdee132","year":2021},"citing_paper":{"arxiv_id":"2412.09752","last_updated":"2024-12-12T22:57:28Z","snapshot_observed_at":"2026-08-12T03:09:30.255276Z","submitted_at":"2024-12-12T22:57:28Z","title":"A Quasilinear Algorithm for Computing Higher-Order Derivatives of Deep Feed-Forward Neural Networks","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-11T16:51:00.448700Z"},"links":{"citing_paper":"/paper/2412.09752"},"observation_digest":"sha256:a4b8fc80aa2de3959eb1d68387984da7d67bd57cf276f9cea8c04a0ad3ba1287","observation_id":"7aeeff4b-5259-4dfd-ba84-1a75c55db6e1","resolution":{"observed_at":"2026-08-11T16:51:01.071366Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T16:51:01.052606Z","title":"N OCEDAL AND S","venue":null,"work_id":"06728d69-9bd7-42a7-81ad-87eaac16474c","year":1999},"citing_paper":{"arxiv_id":"2412.09752","last_updated":"2024-12-12T22:57:28Z","snapshot_observed_at":"2026-08-12T03:09:30.255276Z","submitted_at":"2024-12-12T22:57:28Z","title":"A Quasilinear Algorithm for Computing Higher-Order Derivatives of Deep Feed-Forward Neural Networks","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-11T16:51:00.452918Z"},"links":{"citing_paper":"/paper/2412.09752"},"observation_digest":"sha256:74e93da0748739ece15a2525e495124cde2432173374835080c8d723cb5d6540","observation_id":"43d26ea9-b602-4cad-ab5a-3c7c81cdff4c","resolution":{"observed_at":"2026-08-11T16:51:01.057167Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T16:51:01.037759Z","title":"O H AND F","venue":null,"work_id":"072c1c7c-4756-4982-bf8e-c9d8acd8b62c","year":2024},"citing_paper":{"arxiv_id":"2412.09752","last_updated":"2024-12-12T22:57:28Z","snapshot_observed_at":"2026-08-12T03:09:30.255276Z","submitted_at":"2024-12-12T22:57:28Z","title":"A Quasilinear Algorithm for Computing Higher-Order Derivatives of Deep Feed-Forward Neural Networks","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-11T16:51:00.457268Z"},"links":{"citing_paper":"/paper/2412.09752"},"observation_digest":"sha256:f331cd53ba8f2fc16b7e79fa95616e2717e67ac1727096e2cc6989fa7c9c57c5","observation_id":"06c10354-e75d-4eaf-995c-fc628a13048d","resolution":{"observed_at":"2026-08-11T16:51:01.042777Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T16:51:01.021973Z","title":"P ASZKE , S","venue":null,"work_id":"3317348e-931c-412c-954c-48a437119b1b","year":2019},"citing_paper":{"arxiv_id":"2412.09752","last_updated":"2024-12-12T22:57:28Z","snapshot_observed_at":"2026-08-12T03:09:30.255276Z","submitted_at":"2024-12-12T22:57:28Z","title":"A Quasilinear Algorithm for Computing Higher-Order Derivatives of Deep Feed-Forward Neural Networks","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-11T16:51:00.461700Z"},"links":{"citing_paper":"/paper/2412.09752"},"observation_digest":"sha256:7417fba825a3c4e571a013012a8a0941da525907d534e9917426035c06d252e0","observation_id":"a7a89d43-226c-4b3f-832c-0c8fbee2663c","resolution":{"observed_at":"2026-08-11T16:51:01.026767Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T16:51:01.006202Z","title":"P ENWARDEN , A","venue":null,"work_id":"61bd72f7-63e0-44ce-b996-3ccd146a1110","year":2023},"citing_paper":{"arxiv_id":"2412.09752","last_updated":"2024-12-12T22:57:28Z","snapshot_observed_at":"2026-08-12T03:09:30.255276Z","submitted_at":"2024-12-12T22:57:28Z","title":"A Quasilinear Algorithm for Computing Higher-Order Derivatives of Deep Feed-Forward Neural Networks","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-11T16:51:00.466244Z"},"links":{"citing_paper":"/paper/2412.09752"},"observation_digest":"sha256:55dd2e4591963eeeaafe32a185cf41897997b3c6b5800c86970760d19d7839dc","observation_id":"3671ed4f-665b-4514-b8bc-06d0fa8d8cac","resolution":{"observed_at":"2026-08-11T16:51:01.011214Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T16:51:00.990666Z","title":"R AHAMAN , A","venue":null,"work_id":"85f25a7e-ce9c-482c-937e-566a8767b4a9","year":2019},"citing_paper":{"arxiv_id":"2412.09752","last_updated":"2024-12-12T22:57:28Z","snapshot_observed_at":"2026-08-12T03:09:30.255276Z","submitted_at":"2024-12-12T22:57:28Z","title":"A Quasilinear Algorithm for Computing Higher-Order Derivatives of Deep Feed-Forward Neural Networks","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-11T16:51:00.470809Z"},"links":{"citing_paper":"/paper/2412.09752"},"observation_digest":"sha256:93578ff02c24bf1f330445c292c9193df134460af7da2c5eb2437e8eae7aa714","observation_id":"3ec86ec7-b7ed-4a6d-958d-be8c12ca1bca","resolution":{"observed_at":"2026-08-11T16:51:00.995255Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T16:51:00.975569Z","title":"R AISSI , P","venue":null,"work_id":"3375bd4b-7364-4335-9efd-dce588089b00","year":2019},"citing_paper":{"arxiv_id":"2412.09752","last_updated":"2024-12-12T22:57:28Z","snapshot_observed_at":"2026-08-12T03:09:30.255276Z","submitted_at":"2024-12-12T22:57:28Z","title":"A Quasilinear Algorithm for Computing Higher-Order Derivatives of Deep Feed-Forward Neural Networks","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-11T16:51:00.475579Z"},"links":{"citing_paper":"/paper/2412.09752"},"observation_digest":"sha256:08896a25cdce446764f3eb91dacbfa1924f4f48c6a882ded440559c9fe6bdde5","observation_id":"206f2395-3486-43ce-9811-b1fa6650880d","resolution":{"observed_at":"2026-08-11T16:51:00.980208Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.01868","last_updated":"2024-06-03T23:35:42Z","snapshot_observed_at":"2026-08-10T11:52:09.961227Z","submitted_at":"2024-02-02T19:46:43Z","title":"Challenges in Training PINNs: A Loss Landscape Perspective","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.01868","snapshot_observed_at":"2026-08-11T16:51:00.480088Z","title":"R ATHORE , W","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.09752","last_updated":"2024-12-12T22:57:28Z","snapshot_observed_at":"2026-08-12T03:09:30.255276Z","submitted_at":"2024-12-12T22:57:28Z","title":"A Quasilinear Algorithm for Computing Higher-Order Derivatives of Deep Feed-Forward Neural Networks","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-11T16:51:00.480088Z"},"links":{"cited_paper":"/paper/2402.01868","citing_paper":"/paper/2412.09752"},"observation_digest":"sha256:8130bbf8d731c0972d8b92fffbb60d06e430a13f19767ce0e1d6bdd0ebc3df6a","observation_id":"72355189-f33e-45b7-a36b-2752d0ffdc04","resolution":{"observed_at":"2026-08-11T16:51:00.480088Z","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":"2026-08-11T16:51:00.959078Z","title":"R OMAN , The formula of faa di bruno , The American Mathematical Monthly, 87 (1980), pp","venue":null,"work_id":"5ca95f23-2e8a-42d8-a532-714cb033e2cb","year":1980},"citing_paper":{"arxiv_id":"2412.09752","last_updated":"2024-12-12T22:57:28Z","snapshot_observed_at":"2026-08-12T03:09:30.255276Z","submitted_at":"2024-12-12T22:57:28Z","title":"A Quasilinear Algorithm for Computing Higher-Order Derivatives of Deep Feed-Forward Neural Networks","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-11T16:51:00.485093Z"},"links":{"citing_paper":"/paper/2412.09752"},"observation_digest":"sha256:f88f9703e9f053e4b8e4efa74f50bab70e248dce4100c0e1cee54c7d82aa6368","observation_id":"2a128bd0-acb0-4a2a-9131-80226b9cd0e5","resolution":{"observed_at":"2026-08-11T16:51:00.964524Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T16:51:00.942579Z","title":"S HARMA AND V","venue":null,"work_id":"57cb6333-6b9d-47da-954c-5bf72545c24a","year":2022},"citing_paper":{"arxiv_id":"2412.09752","last_updated":"2024-12-12T22:57:28Z","snapshot_observed_at":"2026-08-12T03:09:30.255276Z","submitted_at":"2024-12-12T22:57:28Z","title":"A Quasilinear Algorithm for Computing Higher-Order Derivatives of Deep Feed-Forward Neural Networks","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-11T16:51:00.489807Z"},"links":{"citing_paper":"/paper/2412.09752"},"observation_digest":"sha256:86b26511d65f8b296b4816c2a2263c596ac92120a1ce2697fbe53a4cbbf1753f","observation_id":"2fe378d7-4432-4019-88d5-1fa47e9d2389","resolution":{"observed_at":"2026-08-11T16:51:00.947373Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T16:51:00.926402Z","title":null,"venue":null,"work_id":"9c092889-67e7-4207-b045-fe2b5e95da7d","year":2020},"citing_paper":{"arxiv_id":"2412.09752","last_updated":"2024-12-12T22:57:28Z","snapshot_observed_at":"2026-08-12T03:09:30.255276Z","submitted_at":"2024-12-12T22:57:28Z","title":"A Quasilinear Algorithm for Computing Higher-Order Derivatives of Deep Feed-Forward Neural Networks","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-11T16:51:00.494156Z"},"links":{"citing_paper":"/paper/2412.09752"},"observation_digest":"sha256:797f4a07a6c86f17c31e25726ae80f95cdc3c64d0e88fe17da91cc85312eb16c","observation_id":"cd0cf97d-1916-45a2-bd0e-79762014a544","resolution":{"observed_at":"2026-08-11T16:51:00.931255Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T16:51:00.909590Z","title":"S IMARD , B","venue":null,"work_id":"c5af9a5d-180a-46eb-a1fd-b48f6ea67b72","year":1991},"citing_paper":{"arxiv_id":"2412.09752","last_updated":"2024-12-12T22:57:28Z","snapshot_observed_at":"2026-08-12T03:09:30.255276Z","submitted_at":"2024-12-12T22:57:28Z","title":"A Quasilinear Algorithm for Computing Higher-Order Derivatives of Deep Feed-Forward Neural Networks","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-11T16:51:00.498599Z"},"links":{"citing_paper":"/paper/2412.09752"},"observation_digest":"sha256:458f6db05a1089aed7188e6f833317213cf85b5dc79b7983ca60ae39aba5806a","observation_id":"486cf8e9-bf1c-445d-a2a5-7b411d3c87ae","resolution":{"observed_at":"2026-08-11T16:51:00.915157Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2101.08932","last_updated":"2021-12-08T08:30:55Z","snapshot_observed_at":"2026-08-10T16:55:17.303276Z","submitted_at":"2021-01-22T03:35:42Z","title":"Sobolev Training for Physics Informed Neural Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2101.08932","snapshot_observed_at":"2026-08-11T16:51:00.502906Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.09752","last_updated":"2024-12-12T22:57:28Z","snapshot_observed_at":"2026-08-12T03:09:30.255276Z","submitted_at":"2024-12-12T22:57:28Z","title":"A Quasilinear Algorithm for Computing Higher-Order Derivatives of Deep Feed-Forward Neural Networks","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-11T16:51:00.502906Z"},"links":{"cited_paper":"/paper/2101.08932","citing_paper":"/paper/2412.09752"},"observation_digest":"sha256:b7596f2ce3dc623fb8e38fc10ef8436af21ab95f85f751da07eec4dc8a097042","observation_id":"bdd8f5b3-14ed-4ed7-b985-82827a8b77ea","resolution":{"observed_at":"2026-08-11T16:51:00.502906Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.12171","last_updated":"2024-08-22T07:33:11Z","snapshot_observed_at":"2026-08-11T16:42:26.301337Z","submitted_at":"2024-08-22T07:33:11Z","title":"Recent Advances on Machine Learning for Computational Fluid Dynamics: A Survey","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.12171","snapshot_observed_at":"2026-08-11T16:51:00.507623Z","title":"W ANG , Y","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.09752","last_updated":"2024-12-12T22:57:28Z","snapshot_observed_at":"2026-08-12T03:09:30.255276Z","submitted_at":"2024-12-12T22:57:28Z","title":"A Quasilinear Algorithm for Computing Higher-Order Derivatives of Deep Feed-Forward Neural Networks","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-11T16:51:00.507623Z"},"links":{"cited_paper":"/paper/2408.12171","citing_paper":"/paper/2412.09752"},"observation_digest":"sha256:0eb2b43ff385f2350fbb5fdcfcb94db7e111ba35f9ea9b59d733036c3707837b","observation_id":"70fe2c39-e161-41a8-a94f-19907921dd55","resolution":{"observed_at":"2026-08-11T16:51:00.507623Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.08468","last_updated":"2023-08-16T16:19:25Z","snapshot_observed_at":"2026-08-11T03:11:19.241010Z","submitted_at":"2023-08-16T16:19:25Z","title":"An Expert's Guide to Training Physics-informed Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.08468","snapshot_observed_at":"2026-08-11T16:51:00.512622Z","title":"W ANG , S","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.09752","last_updated":"2024-12-12T22:57:28Z","snapshot_observed_at":"2026-08-12T03:09:30.255276Z","submitted_at":"2024-12-12T22:57:28Z","title":"A Quasilinear Algorithm for Computing Higher-Order Derivatives of Deep Feed-Forward Neural Networks","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-11T16:51:00.512622Z"},"links":{"cited_paper":"/paper/2308.08468","citing_paper":"/paper/2412.09752"},"observation_digest":"sha256:1d2c2e8b6a0fcc87991da661dcb512e5a1a3aab9a7ca1423e2932ebc3a2be85c","observation_id":"64c964ba-7a24-4ca0-a70c-ae86eb656765","resolution":{"observed_at":"2026-08-11T16:51:00.512622Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2001.04536","last_updated":"2020-01-13T21:23:49Z","snapshot_observed_at":"2026-08-08T04:03:26.228439Z","submitted_at":"2020-01-13T21:23:49Z","title":"Understanding and mitigating gradient pathologies in physics-informed neural networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2001.04536","snapshot_observed_at":"2026-08-11T16:51:00.517590Z","title":"W ANG , Y","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.09752","last_updated":"2024-12-12T22:57:28Z","snapshot_observed_at":"2026-08-12T03:09:30.255276Z","submitted_at":"2024-12-12T22:57:28Z","title":"A Quasilinear Algorithm for Computing Higher-Order Derivatives of Deep Feed-Forward Neural Networks","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-11T16:51:00.517590Z"},"links":{"cited_paper":"/paper/2001.04536","citing_paper":"/paper/2412.09752"},"observation_digest":"sha256:4ce64e2442e076e5abb42b4fda347699325fe0ebb2adae07b662014166ac880f","observation_id":"06bcdd48-e19e-4890-bd27-2f7d2cf17a23","resolution":{"observed_at":"2026-08-11T16:51:00.517590Z","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":"2026-08-11T16:51:00.884607Z","title":"W ANG , X","venue":null,"work_id":"1c9c59c8-2ca0-4ebb-9445-d8a58ee79901","year":2022},"citing_paper":{"arxiv_id":"2412.09752","last_updated":"2024-12-12T22:57:28Z","snapshot_observed_at":"2026-08-12T03:09:30.255276Z","submitted_at":"2024-12-12T22:57:28Z","title":"A Quasilinear Algorithm for Computing Higher-Order Derivatives of Deep Feed-Forward Neural Networks","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-11T16:51:00.522544Z"},"links":{"citing_paper":"/paper/2412.09752"},"observation_digest":"sha256:3c373e2c4786a9a68cdcedac5c8550dc66ff93b7b86e42b17f8b090c9d09473d","observation_id":"36a1c248-3703-4d7b-a665-5bc1bbeda857","resolution":{"observed_at":"2026-08-11T16:51:00.890273Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T16:51:00.859487Z","title":"W ANG , C.-Y","venue":null,"work_id":"d6587201-347c-4a00-9291-96b875c37906","year":2023},"citing_paper":{"arxiv_id":"2412.09752","last_updated":"2024-12-12T22:57:28Z","snapshot_observed_at":"2026-08-12T03:09:30.255276Z","submitted_at":"2024-12-12T22:57:28Z","title":"A Quasilinear Algorithm for Computing Higher-Order Derivatives of Deep Feed-Forward Neural Networks","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-11T16:51:00.526869Z"},"links":{"citing_paper":"/paper/2412.09752"},"observation_digest":"sha256:54780240373b4499713484d81306d2ca3c0cbb3499a496aed01d559206e3b338","observation_id":"952b95f1-31f2-4fa4-9191-d481067e8388","resolution":{"observed_at":"2026-08-11T16:51:00.867285Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1901.06523","last_updated":"2024-05-17T02:22:47Z","snapshot_observed_at":"2026-08-08T08:28:28.807955Z","submitted_at":"2019-01-19T13:37:39Z","title":"Frequency Principle: Fourier Analysis Sheds Light on Deep Neural Networks","version":7},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1901.06523","snapshot_observed_at":"2026-08-11T16:51:00.531290Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.09752","last_updated":"2024-12-12T22:57:28Z","snapshot_observed_at":"2026-08-12T03:09:30.255276Z","submitted_at":"2024-12-12T22:57:28Z","title":"A Quasilinear Algorithm for Computing Higher-Order Derivatives of Deep Feed-Forward Neural Networks","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-11T16:51:00.531290Z"},"links":{"cited_paper":"/paper/1901.06523","citing_paper":"/paper/2412.09752"},"observation_digest":"sha256:caf64ad527626b7a71e7c8e798378e8d4007b90778a86738c3fcbf5a7dc7b272","observation_id":"6b1c0949-18d7-478c-bf49-970bfdb84bbe","resolution":{"observed_at":"2026-08-11T16:51:00.531290Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.00152","last_updated":"2026-07-24T20:12:43Z","snapshot_observed_at":"2026-07-30T23:51:47.712715Z","submitted_at":"2024-01-31T20:10:10Z","title":"Deeper or Wider: A Perspective from Optimal Generalization Error with Sobolev Loss","version":6},"cited_work":{"arxiv_id":"2402.00152","doi":null,"metadata_source":"pith","pith_arxiv_id":"2402.00152","snapshot_observed_at":"2026-08-11T16:51:00.575204Z","title":"Deeper or Wider: A Perspective from Optimal Generalization Error with Sobolev Loss","venue":"cs.LG","work_id":"9f93d2c0-a907-4e84-9392-4561ca58d132","year":2024},"citing_paper":{"arxiv_id":"2412.09752","last_updated":"2024-12-12T22:57:28Z","snapshot_observed_at":"2026-08-12T03:09:30.255276Z","submitted_at":"2024-12-12T22:57:28Z","title":"A Quasilinear Algorithm for Computing Higher-Order Derivatives of Deep Feed-Forward Neural Networks","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-11T16:51:00.536240Z"},"links":{"cited_paper":"/paper/2402.00152","citing_paper":"/paper/2412.09752"},"observation_digest":"sha256:8619cdcef55040a0bad403cacae2bc4bd1b507ddff0a55dbdbeefe8a1b6c7a7a","observation_id":"a411e0b5-0553-449e-86a7-fcbc5cfde9cd","resolution":{"observed_at":"2026-08-11T16:51:00.582720Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-11T06:34:44.6726+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2412.09752","last_updated":"2024-12-12T22:57:28Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-12T03:09:30.255276Z","submitted_at":"2024-12-12T22:57:28Z","title":"A Quasilinear Algorithm for Computing Higher-Order Derivatives of Deep Feed-Forward Neural Networks"},"reference_resolution":{"displayed":42,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":16,"verified_exact":1,"verified_fuzzy":25},"total_outbound_references":42},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-11T06:34:44.6726+00:00","source":"crossref"},{"observed_at":"2026-08-11T06:34:36.301508+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 42 of 42 outbound references and 1 inbound Pith citation observation for arXiv:2412.09752."}