{"as_of":"2026-08-17T00:02:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:cc5055568fe83933da4950031f23e373189f59f29c4fece3205ab7608c5d1d83","coverage":[{"denominator":91,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":91,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T16:18:52.852949Z","state":"measured"},{"denominator":91,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":91,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-16T06:30:59.297886+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/2608.03600/citation-record","integrity":"/paper/2608.03600/integrity","json":"/paper/2608.03600/citation-record.json","paper":"/paper/2608.03600"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T16:18:44.080674Z","title":"Evans.Partial Differential Equations, volume 19 ofGraduate Studies in Mathe- matics","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:44.080674Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:5d791a7303a7d9eba937fe54786fbc9891ea59c46395fab496d8af760a6dd3cf","observation_id":"34a98559-151c-4dfa-8f66-13ccb354ab7f","resolution":{"observed_at":"2026-08-05T16:18:44.080674Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T16:18:44.142369Z","title":null,"venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:44.142369Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:2cd2b42c7423712fddd29df8c9e284a265f4207ade167daebfabb58b327f5480","observation_id":"da36b192-5b2a-430c-acc7-208ece00472a","resolution":{"observed_at":"2026-08-05T16:18:44.142369Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T16:18:44.226996Z","title":"Oberkampf and Timothy G","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:44.226996Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:4229a6b91a3cf09a12bf2fdb9985b8ea310bad27e40a5b4457b0c9a370a18169","observation_id":"d4b8fba1-23ac-40d0-b005-26015b0828c9","resolution":{"observed_at":"2026-08-05T16:18:44.226996Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T16:18:44.332723Z","title":"Prentice Hall, Upper Saddle River, NJ, 2 edition, 1999","venue":null,"work_id":null,"year":1999},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:44.332723Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:a612e464e4dff01aef8d21918e0cdc24211cd208cd90eca930daafe1217cd6ab","observation_id":"ca0ce083-75cd-465d-85df-d51f761efb6a","resolution":{"observed_at":"2026-08-05T16:18:44.332723Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T16:18:44.461131Z","title":"LeVeque.Finite Difference Methods for Ordinary and Partial Differential Equations: Steady-State and Time-Dependent Problems","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:44.461131Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:8207e94215254aa35171ea069f44b5b44c9399fb7e700b1e3fdd24dcd8bade6e","observation_id":"e809e583-7bb2-4a2f-896a-029e527fa3f7","resolution":{"observed_at":"2026-08-05T16:18:44.461131Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T16:18:44.532390Z","title":null,"venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:44.532390Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:c0002eeb711aaeb42ed586cf36657e566a4dbe8798ed3b37038f287539b15241","observation_id":"834c796f-f8da-4860-a8ef-3da92ab4c0f4","resolution":{"observed_at":"2026-08-05T16:18:44.532390Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T16:18:44.617867Z","title":"Brenner and L","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:44.617867Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:b8209e1ba9ce3cff610ca8d72b0f190e8f20277113b77f28b3bfc40b96e97146","observation_id":"671728f8-7ad9-4916-89f9-0ba80d85b12e","resolution":{"observed_at":"2026-08-05T16:18:44.617867Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T16:18:44.718210Z","title":"Trefethen.Spectral Methods in MATLAB","venue":null,"work_id":null,"year":2000},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:44.718210Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:6c08c26e843271d9484e7b65c93612d50da4c718377c85b7a828ec141cc5bc2f","observation_id":"742e39ea-51be-479e-9bc8-6e4871cca775","resolution":{"observed_at":"2026-08-05T16:18:44.718210Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T16:18:44.778448Z","title":"Review of discontinuous galerkin finite element methods for partial differential equations on complicated domains","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:44.778448Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:33583d3e0b44973ef1729c645432480eacc62d8aa7ae706f71bd2993bc40914a","observation_id":"32e1e83c-e8b0-456c-941f-03703802e7be","resolution":{"observed_at":"2026-08-05T16:18:44.778448Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T16:18:44.855748Z","title":"A review of mesh adaptation technology applied to computational fluid dynamics.Fluids, 10(5):129, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:44.855748Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:2894146adeab586f05e4ad89064842e9d05d23fe630be0f6f2e5a8be224f7293","observation_id":"fa4abf32-a90f-41cd-b45d-3eb704bc37de","resolution":{"observed_at":"2026-08-05T16:18:44.855748Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T16:18:44.976610Z","title":"Springer, Berlin, Heidelberg, 1971","venue":null,"work_id":null,"year":1971},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:44.976610Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:e113277df9fe15ebf05485b6274ff16bfd6d5fb5c03432511523bbcf621d83c4","observation_id":"09346225-dfea-4b2c-a292-6afb35bd6268","resolution":{"observed_at":"2026-08-05T16:18:44.976610Z","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":"2026-08-05T16:19:06.126154Z","title":"Springer, Dor- drecht, 2009","venue":null,"work_id":"95b48cb1-7b25-4b1f-a775-c4cfc00c0cca","year":2009},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:45.107034Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:82dc5531525893c7a94a3c9adc4f98f05aaed522606f80b3f8bb880636795547","observation_id":"83ce9f33-270a-4ba3-8b11-30f10f964e76","resolution":{"observed_at":"2026-08-05T16:19:06.192318Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T16:19:05.883147Z","title":"Gunzburger.Perspectives in Flow Control and Optimization","venue":null,"work_id":"a0980846-ba0d-44f5-b78f-0d5aca8915b3","year":2002},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:45.226793Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:964301fa1831568e5b7e3b40c8b9c2a5c9144d459f483a54dae8be23fef97062","observation_id":"7989a46f-6778-4773-962a-0856228739a7","resolution":{"observed_at":"2026-08-05T16:19:05.984497Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T16:19:05.713422Z","title":"Bendsøe and Ole Sigmund.Topology Optimization: Theory, Methods, and Applica- tions","venue":null,"work_id":"52782e3b-3c31-49c3-9374-4c33b8bd8cb7","year":2004},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:45.318804Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:07f74d513031b6deafff9d2b1d1283c1301704d2a315fa4ebdb5098b2b494358","observation_id":"d5e1172a-f6f5-4ddc-8355-6bd9a8d75ebf","resolution":{"observed_at":"2026-08-05T16:19:05.786848Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T16:18:45.462230Z","title":"Brunton, Joshua L","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:45.462230Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:d96e223b7de6ba28fdc82d5e8ea55d62b7698e0fa58a529aa9f5645d021204da","observation_id":"f93466f6-5816-4ec0-a0a4-7c6beb0c5380","resolution":{"observed_at":"2026-08-05T16:18:45.462230Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T16:18:45.590133Z","title":"Rudy, Steven L","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:45.590133Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:300084be4c80eb5e301a72962252d1584b9c795feef3bd097cdfba4b457ddd17","observation_id":"06e7c1a8-9326-4867-8e19-0dfd58e94171","resolution":{"observed_at":"2026-08-05T16:18:45.590133Z","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":"2026-08-05T16:19:05.499187Z","title":"Data-driven equation discovery of ocean mesoscale closures","venue":null,"work_id":"814b56f4-0e1f-42ec-bc4c-8674107d1995","year":2020},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:45.731443Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:5b631f3b570c12964e02a35e178de03222338c40c2717d448a67f4f57820af55","observation_id":"705900b0-b8d9-4ca3-9da9-02a1df26dc09","resolution":{"observed_at":"2026-08-05T16:19:05.603649Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T16:19:05.262760Z","title":"Formulating turbulence closures using sparse regression with embedded form invariance.Physical Review Fluids, 5(8):084611, 2020","venue":null,"work_id":"7f57b1f5-b33f-4561-9c20-bcec8c6b0b77","year":2020},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:45.845010Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:9ec561f8542393074c0bdafe89e121b4754be1468c1472568c193ff21163d1a6","observation_id":"a140e736-fafe-4954-9018-0a7e2f3e00b6","resolution":{"observed_at":"2026-08-05T16:19:05.387241Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T16:19:05.066684Z","title":"Data-driven discovery of coarse-grained equations","venue":null,"work_id":"9b70176a-e2a9-4269-9c2a-cfac0b6257bf","year":2021},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:45.989309Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:172fa62f2dd4af0fbaec7798d9f0272f7f8050d03a0e4192eaa779493e79d9f9","observation_id":"343f0245-c043-402a-bd6a-84a838c4afb0","resolution":{"observed_at":"2026-08-05T16:19:05.158617Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T16:18:46.157043Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:46.157043Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:9828b6a68f58dd1e3bf0b4ba5b2246e076dcf0298016dbffb2049b8e40d6bc72","observation_id":"a6de3e7e-c341-4761-8193-affbbb38e549","resolution":{"observed_at":"2026-08-05T16:18:46.157043Z","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":"2026-08-05T16:19:04.808485Z","title":null,"venue":null,"work_id":"c8fb5e34-6a99-4aa1-9788-309fcec2fc95","year":2019},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:46.313488Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:d41bcee077268cbc63409730970fe209abf6cea6bd9e8331fdcb798da885900e","observation_id":"b04bf933-a70b-4774-81b9-fbce346b5242","resolution":{"observed_at":"2026-08-05T16:19:04.934620Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T16:19:04.609984Z","title":"Smith, Ayya Alieva, Qing Wang, Michael P","venue":null,"work_id":"ef27cf60-0c0b-4317-99cb-cba7e3fde20c","year":2021},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:46.431680Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:cbcd2cba21517a78f743a90d4fc7d0a37fbd4b9d93233fb5a9da46cf2c6c96c1","observation_id":"5d631dab-8dab-42a3-a68b-e7ddf57c1d6b","resolution":{"observed_at":"2026-08-05T16:19:04.713134Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T16:18:46.540551Z","title":"Learning nonlinear operators via DeepONet based on the universal approximation theorem of operators","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:46.540551Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:e1f4c5478942ff2abd881433354415cdfaed513195679e509163a5e7dfc8df80","observation_id":"c6d342bd-e9d8-4d92-ad2a-b8256d8d8efe","resolution":{"observed_at":"2026-08-05T16:18:46.540551Z","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":"2026-08-05T16:19:04.496128Z","title":"Fourier neural operator for parametric partial differential equations","venue":null,"work_id":"28c1e43e-a985-45e5-a7dd-081340e964b6","year":2021},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:46.656647Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:d86393c51499eaf15f4abbc3492a1838c9c97db0b67932ab1448ee18059e9dee","observation_id":"a3b5042f-c961-4a86-b0e0-4fe440939b41","resolution":{"observed_at":"2026-08-05T16:19:04.546189Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T16:18:46.708343Z","title":"Factorized Fourier neural operators","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:46.708343Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:2a42fe594ccf2ba13ff1d4d16747e7da4701d9120b1395ad512a612e0504beb5","observation_id":"edb3df40-3dcb-4de5-a1e2-c0a3a313be58","resolution":{"observed_at":"2026-08-05T16:18:46.708343Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T16:18:46.741318Z","title":"Physics-informed neural networks with hard constraints for inverse design.SIAM Journal on Scientific Computing, 43(6):B1105–B1132, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:46.741318Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:34a03a60bad12b0c0bd61090e4cd8db42ecd18ad2f45c6ed158d63e67bd823fe","observation_id":"f933571a-056d-4c31-9fda-3b61c0ed073b","resolution":{"observed_at":"2026-08-05T16:18:46.741318Z","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":"2026-08-05T16:19:04.279383Z","title":"Gradient-enhanced physics- informed neural networks for forward and inverse pde problems.Computer Methods in Applied Mechanics and Engineering, 393:114823, 2022","venue":null,"work_id":"63ab0608-cde2-4809-a6d3-623b62ad4f25","year":2022},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:46.858792Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:865c40d897e5f2e49ee648940749c35189e7f7ebb675f110565774d9dfd2f8f7","observation_id":"d042fb22-248d-4f37-8f80-4a2351466b3b","resolution":{"observed_at":"2026-08-05T16:19:04.383908Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T16:19:04.080925Z","title":"Encoding physics to learn reaction–diffusion processes.Nature Machine Intelligence, 5(7):765–779, 2023","venue":null,"work_id":"0bfc2e94-527a-4612-8cd0-046f4416b56c","year":2023},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:46.952603Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:71e28f1b6fe92e92d395b67b40c81c56c484946d5a814a561c8b86538a8eb692","observation_id":"16144691-e3de-40f3-8640-99c0f8dfdf55","resolution":{"observed_at":"2026-08-05T16:19:04.168736Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T16:19:03.817406Z","title":"Pesanet: Physics-encoded spec- tral attention network for simulating pde-governed complex systems","venue":null,"work_id":"b9ec36e4-0aaf-4020-b44d-c1120c0d3569","year":2025},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:47.062895Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:5d1ca1381e933a70f61da30e51c7fa6c9e61288db1b50a5954c5c435994333ae","observation_id":"c2302bc5-5e3d-4e3f-a44f-9b60d2896a59","resolution":{"observed_at":"2026-08-05T16:19:03.915199Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T16:19:03.592280Z","title":"Artificial neural networks trained through deep reinforcement learning discover control strategies for active flow control.Journal of Fluid Mechanics, 865:281–302, 2019","venue":null,"work_id":"c2c33ea2-546b-4fcb-8cac-52a74ada1263","year":2019},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:47.165696Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:6b275ccb94f93a8227b3560ac27149e221ade132e10d0490c4349f3fac6a14ba","observation_id":"ec3874a6-5be9-48f7-9b3b-0e97307c03a2","resolution":{"observed_at":"2026-08-05T16:19:03.710999Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T16:19:03.364364Z","title":"Learning to control pdes with differentiable physics, 2020","venue":null,"work_id":"a3ef5d81-3751-4cc3-a57e-59a440505919","year":2020},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:47.274024Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:df76f8fc6e8b4ac840c677aa5479d8b6216a07b0e3394e3c80c224f0616b7998","observation_id":"0cefd96f-fdc8-41f8-b60c-51f6e97b8fd0","resolution":{"observed_at":"2026-08-05T16:19:03.502339Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T16:19:03.194947Z","title":"Direct shape optimization through deep reinforcement learning.Journal of Computational Physics, 428:110080, 2021","venue":null,"work_id":"392f1b34-ea68-4c9f-893b-5179878c20d8","year":2021},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:47.365511Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:695694b04bd1884c24ed853e0905886e6348cd0800798ae0826943fb461111a5","observation_id":"ee71c12d-7dd6-44be-80bd-bc56edac9bab","resolution":{"observed_at":"2026-08-05T16:19:03.270362Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T16:19:03.032255Z","title":"Stachenfeld, Alvaro Sanchez-Gonzalez, Pe- ter Battaglia, Jessica B","venue":null,"work_id":"53d67a7b-5d97-47a0-855e-af9f3d81f39c","year":2022},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:47.478520Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:d6f57fd9ca52183f6920e4168f2398b6fdccf92e07a8b72683e6122f6426cd65","observation_id":"5802d220-0d14-4582-8960-515c591af541","resolution":{"observed_at":"2026-08-05T16:19:03.108373Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T16:18:47.649677Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:47.649677Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:41d5099c2869d470e52228099e612160e4248a6380c454a2a78e5f1df350d29b","observation_id":"a2ff970f-266b-496a-956c-a35ecb0d67d4","resolution":{"observed_at":"2026-08-05T16:18:47.649677Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T16:18:47.745295Z","title":"Chi, Quoc V","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:47.745295Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:ecffbea19e824be58184ea2c4f837a2d48ab774ae2ab84d37f8eb1cb1184f72b","observation_id":"94cb1065-c665-4d57-97fc-2cb837a19c3a","resolution":{"observed_at":"2026-08-05T16:18:47.745295Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2205.00445","last_updated":"2022-05-01T11:01:28Z","snapshot_observed_at":"2026-08-12T06:42:48.798440Z","submitted_at":"2022-05-01T11:01:28Z","title":"MRKL Systems: A modular, neuro-symbolic architecture that combines large language models, external knowledge sources and discrete reasoning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.00445","snapshot_observed_at":"2026-08-05T16:18:47.805897Z","title":"Mielke, Yonatan Belinkov, Barak Lenz, Omer Lieber, et al","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:47.805897Z"},"links":{"cited_paper":"/paper/2205.00445","citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:32923ca4b605087f6f4a839f8ee6be77ef1ea09886378a01bf2d9b0781f8cd4e","observation_id":"01643b77-3029-4f91-acf1-e739d3af753b","resolution":{"observed_at":"2026-08-05T16:18:47.805897Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.07761","last_updated":"2024-07-22T07:13:18Z","snapshot_observed_at":"2026-08-16T13:53:10.354190Z","submitted_at":"2024-05-13T14:03:49Z","title":"LLM4ED: Large Language Models for Automatic Equation Discovery","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.07761","snapshot_observed_at":"2026-08-05T16:18:47.984276Z","title":"Llm4ed: Large language models for automatic equation discovery.arXiv preprint arXiv:2405.07761, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:47.984276Z"},"links":{"cited_paper":"/paper/2405.07761","citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:5a6e68a066c2d022ff8857a4765db578a32a2ba007155558d87393ab317f2d29","observation_id":"688a5ed4-f226-4236-9d76-045dcf29d938","resolution":{"observed_at":"2026-08-05T16:18:47.984276Z","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":"2026-08-05T16:19:02.799166Z","title":"Physpde: Rethinking pde discovery and a physical hypothesis selection benchmark","venue":null,"work_id":"b0b7867e-4284-41a3-a5d1-036bb1788129","year":2025},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:48.088447Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:1d713b9e3a682f3deadb2c318cde0482ec6cc2156a23ea2bf0da85d98cfb21ca","observation_id":"63ebc101-381a-42f4-86ba-4acb061ec525","resolution":{"observed_at":"2026-08-05T16:19:02.891730Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T16:19:02.577230Z","title":"Codepde: An inference framework for llm-driven pde solver generation","venue":null,"work_id":"4f770251-ed00-4081-b9a8-6076d2fadcc2","year":2026},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:48.189783Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:3b208585d524f63340477430fd25fb8c2db75e0a2a7645cf2a227ef8506b1288","observation_id":"a7858813-6387-49d6-b686-8dec5806e8f1","resolution":{"observed_at":"2026-08-05T16:19:02.677029Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T16:19:02.404446Z","title":"Foam-agent: Towards automated intelligent cfd workflows","venue":null,"work_id":"dbfaf99a-c7b1-4b3f-9f9e-f10376e31dd9","year":2025},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:48.243279Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:5d2de8941101b9204e364b8daabcb95df2d11d368730e98d7e3897ef336b0633","observation_id":"1b62f2ad-3648-45fb-9175-0c0f67af63d8","resolution":{"observed_at":"2026-08-05T16:19:02.486055Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T16:18:48.328982Z","title":"Pde-sharp: Pde solver hybrids through analysis and refinement passes.arXiv preprint arXiv:2511.00183, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:48.328982Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:96b239213820f1d5fd1fea36b7db75a7ce50aa953f6d7c202f1f5bdb46d3883c","observation_id":"e706ab58-f934-4d50-9c4e-2db7181f7615","resolution":{"observed_at":"2026-08-05T16:18:48.328982Z","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":"2026-08-05T16:19:02.287335Z","title":"Pde-controller: Llms for autoformalization and reasoning of pdes","venue":null,"work_id":"aacb1a7c-95bc-4180-b0eb-16558a310f14","year":2025},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:48.391492Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:7af18dc85eec750cb4a7cf5bdd812c8353c512d1a85eca1110bf856c0610408e","observation_id":"2921c93a-d007-4e4f-93e0-f3270f651e7b","resolution":{"observed_at":"2026-08-05T16:19:02.346579Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T16:19:02.088227Z","title":"Using large language models for parametric shape op- timization.Physics of Fluids, 37(8):083601, 2025","venue":null,"work_id":"7094bd65-645a-47e9-b813-d1fe77f7c771","year":2025},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:48.437046Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:1ea2126498d7a032cf728e155cdccf0a3a057b54abea8f2455575d881d15116d","observation_id":"f6c51466-8128-464f-8736-fd0ab89b7c3a","resolution":{"observed_at":"2026-08-05T16:19:02.195485Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T16:19:01.910554Z","title":"Accelerating scientific discovery with co-scientist.Nature, 655:487–496, 2026","venue":null,"work_id":"6c8e3d22-6df5-4964-838d-8cf2273cebe0","year":2026},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:48.552823Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:6dd397711fa919aa23ca2763c89849246781c89be0463b4ee6fd0ba43e039982","observation_id":"ffb367f9-d793-4aa4-842e-8bac8fce8f6c","resolution":{"observed_at":"2026-08-05T16:19:01.994569Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T16:19:01.769599Z","title":"Ghareeb, Benjamin Chang, Ludovico Mitchener, Angela Yiu, Caralyn J","venue":null,"work_id":"78e47abf-569e-4586-9c57-c9618a9a777f","year":2026},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:48.652683Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:833eefd86446f40804c9af27b0dbfa6c7573aa74a7b8312d1716ef98650543c4","observation_id":"7968a697-c3a8-4b73-a20f-9b668e78deb1","resolution":{"observed_at":"2026-08-05T16:19:01.845941Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T16:19:01.549337Z","title":"Evaluating llms’ divergent thinking capabilities for scientific idea generation with minimal context.Nature Communications, 17(1):3625, 2026","venue":null,"work_id":"c47e273c-9302-4c5c-90cd-27b99a1e4333","year":2026},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:48.757430Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:47285e00e5912366cbc4cb3780dfbc9a41fc07f709712dd0a48567ffc51565c3","observation_id":"baeedead-a9f3-4c8e-aab2-9f0d80a420f3","resolution":{"observed_at":"2026-08-05T16:19:01.664646Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T16:19:01.377207Z","title":"Llm assisted mathematical modeling: Homogeneous laplace equation in cylinder with the complete electrode model","venue":null,"work_id":"6ca16081-b71a-46fc-8391-e3ca217373c1","year":2025},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:48.807285Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:b7990ab71f5e1291f5b9e1097f400095881b6f8de319dd4e69d3bd1329033858","observation_id":"5c22b411-ffe8-462e-ba35-3fc2d110ef59","resolution":{"observed_at":"2026-08-05T16:19:01.459853Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T16:19:01.181987Z","title":"Agentic symbolic search: Characterizing pdes beyond hand-crafted expressions, meshes, and neural networks, 2026","venue":null,"work_id":"bf29d0eb-e60c-49dd-8303-f685addb6368","year":2026},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:48.928058Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:34b1759db738c3a71c540c457ffe4f3d6b40be2af75dae619375cb71648110c4","observation_id":"f93f45a1-85d3-4251-939c-f817a516c307","resolution":{"observed_at":"2026-08-05T16:19:01.268100Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T16:19:00.998293Z","title":"The impact of large language models on scientific discovery: a preliminary study using gpt-4","venue":null,"work_id":"7cf83c96-d8ee-46a2-9233-caa233b62669","year":2023},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:49.055822Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:5c2f70e5c070f41fd3730196921843091466bdb49d2448c510d5014612aaf701","observation_id":"2a2c1f0f-5198-4c17-982f-66129aea1fee","resolution":{"observed_at":"2026-08-05T16:19:01.083668Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.04282","last_updated":"2025-06-04T04:52:34Z","snapshot_observed_at":"2026-08-16T06:47:28.767521Z","submitted_at":"2025-06-04T04:52:34Z","title":"DrSR: LLM based Scientific Equation Discovery with Dual Reasoning from Data and Experience","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.04282","snapshot_observed_at":"2026-08-05T16:18:49.131757Z","title":"Drsr: Llm based scientific equation discovery with dual reasoning from data and experience.arXiv preprint arXiv:2506.04282, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:49.131757Z"},"links":{"cited_paper":"/paper/2506.04282","citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:cbf65be4314c6a546f8ffd731de13f2fd0f00e565b58f54a914329a552e18660","observation_id":"87620b2a-cf1a-47af-b059-edb00896f0c1","resolution":{"observed_at":"2026-08-05T16:18:49.131757Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.18400","last_updated":"2025-03-20T16:37:17Z","snapshot_observed_at":"2026-08-16T13:57:06.966339Z","submitted_at":"2024-04-29T03:30:06Z","title":"LLM-SR: Scientific Equation Discovery via Programming with Large Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.18400","snapshot_observed_at":"2026-08-05T16:18:49.194922Z","title":"Llm-sr: Scientific equation discovery via programming with large language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:49.194922Z"},"links":{"cited_paper":"/paper/2404.18400","citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:4b7f419cfde444085f5b6d2ea2590e0f3f53ee39cd3e72a37a27e44edeace645","observation_id":"e4012e50-6705-4548-b592-a4fad9b928bb","resolution":{"observed_at":"2026-08-05T16:18:49.194922Z","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":"2503.09986","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T16:18:53.238655Z","title":"From equations to insights: Unraveling symbolic structures in pdes with llms.arXiv preprint arXiv:2503.09986, 2025","venue":null,"work_id":"aec598c2-240f-40e3-aca5-f7ee2aa8b4b5","year":2025},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:49.309539Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:7c0dff53e0b8fe1bac4dfe754e8717a1b4bffd2bf13feebf1b573d4f4f51c4c0","observation_id":"f9ff3fa7-ee2f-429c-be39-52ded5a6a942","resolution":{"observed_at":"2026-08-05T16:18:53.311247Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.09783","last_updated":"2024-05-16T03:04:10Z","snapshot_observed_at":"2026-08-16T13:52:18.863672Z","submitted_at":"2024-05-16T03:04:10Z","title":"LLM and Simulation as Bilevel Optimizers: A New Paradigm to Advance Physical Scientific Discovery","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.09783","snapshot_observed_at":"2026-08-05T16:18:49.350413Z","title":"Llm and simulation as bilevel optimizers: A new paradigm to advance physical scientific discovery.arXiv preprint arXiv:2405.09783, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:49.350413Z"},"links":{"cited_paper":"/paper/2405.09783","citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:244bb474fde67fd69256c10d33350a8f77d4ebaa71ebe7db475cb2d6d0d67874","observation_id":"8a067c7b-22d9-4e8b-ba7a-298d8bfeabd0","resolution":{"observed_at":"2026-08-05T16:18:49.350413Z","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":"2026-08-05T16:19:00.803286Z","title":null,"venue":null,"work_id":"ab500a2d-5713-4026-b146-1022d7451102","year":2025},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:49.428273Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:fe42d5bb578851eafaeddbdc1356e485ba2436deac01567999108958c79201e8","observation_id":"e5313d3e-2170-455f-91d5-7c3ecfc94ce5","resolution":{"observed_at":"2026-08-05T16:19:00.893189Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T16:19:00.592398Z","title":"Pdeagent-bench: A multi-metric, multi-library benchmark for pde solver generation, 2026","venue":null,"work_id":"38a8da9c-1dbd-4625-b739-8bac77d9547d","year":2026},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:49.514429Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:2c49c6f6125b4fc774a196b92b96d8d354a3980fbff07f6f4b9d9f161cb72bd7","observation_id":"9ca5f8e2-ed19-4342-89c5-67027f22a110","resolution":{"observed_at":"2026-08-05T16:19:00.694053Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T16:19:00.399060Z","title":"Deepseek vs","venue":null,"work_id":"985f4df5-bfd2-4c70-afa1-059adb9a7d14","year":2025},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:49.615381Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:54a6b3083a21e384b2c3a1db71fee1ec7265b9c6f792f7b801b100e602aad879","observation_id":"fd0e4df3-e0d3-49e6-b851-6b07374b4f8f","resolution":{"observed_at":"2026-08-05T16:19:00.467164Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T16:19:00.169599Z","title":"All-fem: Agentic large language models fine-tuned for 24 finite element methods.Computer Methods in Applied Mechanics and Engineering, 457:118985, 2026","venue":null,"work_id":"ad5a5f4e-0d1f-4792-9fe4-b9d61e935d8c","year":2026},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:49.735240Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:fbfd884da25bd0956705af801765f3f8b88743fd2ecf672b7f7a7ca8844e45e3","observation_id":"e91a6190-4104-4b26-90f7-b33ca2c6cf0c","resolution":{"observed_at":"2026-08-05T16:19:00.344218Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T16:18:59.976735Z","title":"Automated code development for pde solvers using large language models","venue":null,"work_id":"ca8bbe6b-5340-4d8a-954d-260ecf0db0b2","year":2025},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:49.826034Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:2b2952239ea03b70be47bb428817f523ba34c6df2c483c60bd293eb18653bbde","observation_id":"eeabfe76-604d-4e18-ba05-171304c0bfb1","resolution":{"observed_at":"2026-08-05T16:19:00.069748Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T16:18:59.789707Z","title":"Autonumerics: An autonomous, pde-agnostic multi-agent pipeline for scientific computing, 2026","venue":null,"work_id":"c18eb960-58db-4783-95e9-e49648ba9794","year":2026},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:49.904416Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:0267ffcd8173d3c45d42069ca0807662b97c7a37e7ad988d63541c27f270b179","observation_id":"94e64bfa-fc25-4367-a9d1-cb975e87a4a9","resolution":{"observed_at":"2026-08-05T16:18:59.896749Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T16:18:59.583732Z","title":"Evaluations of large language models in computa- tional fluid dynamics: Leveraging, learning and creating knowledge.Theoretical and Applied Mechanics Letters, 15(3):100597, 2025","venue":null,"work_id":"20ab01f0-6916-4cc9-ad91-bb4b675c4520","year":2025},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:50.032651Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:172822c645dcb143407d388510677fdcfdb98705895ee5fcf0088682f6bb6eb4","observation_id":"fa04a730-0e79-4b78-9e5a-3346f4f2ecdd","resolution":{"observed_at":"2026-08-05T16:18:59.670106Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T16:18:59.367664Z","title":"Cfdllmbench: A benchmark suite for evaluating large language models in computational fluid dynamics","venue":null,"work_id":"390f99d4-f4a0-4033-8395-d8c49e38cec7","year":2025},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:50.083928Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:cb0454d6f16e15ab07657dc4aa80c60800c46715cdb3603db999bb6f7ada9bab","observation_id":"03e57cfc-9a0f-4b7b-babd-96a292c242c6","resolution":{"observed_at":"2026-08-05T16:18:59.444667Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T16:18:50.138829Z","title":"Openfoamgpt: A retrieval-augmented large language model (llm) agent for openfoam-based computational fluid dynamics.Physics of Fluids, 37(3), 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:50.138829Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:8bdea932d98a5e5dbe5699d6e3e87de0b722934cdc5abb79e74778e13c13340b","observation_id":"903dd180-fd50-452f-86e8-ae674cd66747","resolution":{"observed_at":"2026-08-05T16:18:50.138829Z","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":"2026-08-05T16:18:59.125825Z","title":"Ai cfd scientist: Toward open-ended computational fluid dynamics discovery with physics-aware ai agents, 2026","venue":null,"work_id":"f6c902de-b3ab-4167-9486-5fee1e93e3df","year":2026},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:50.267832Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:7518e3e47a525e354445c2dbd7e72a8f2e1e386a16ebbcbcaba9881cc9cc37b5","observation_id":"69fe66e0-0f21-45c7-b2cf-b391c7fa3dc4","resolution":{"observed_at":"2026-08-05T16:18:59.269734Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T16:18:58.937486Z","title":"Openfoamgpt 2.0: End-to-end, trustworthy automation for computational fluid dynamics.International Journal of Heat and Fluid Flow, 120:110399, 2026","venue":null,"work_id":"470cf8c8-2341-41c3-937b-d9b81e48b396","year":2026},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:50.352574Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:9f48f2121c97722ce3aa3666e8e8a8bfb9455fda7fa49d51a6a50c05519de926","observation_id":"1cf628ea-6f62-482a-9cdd-decf5c627b93","resolution":{"observed_at":"2026-08-05T16:18:59.040847Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T16:18:58.674589Z","title":"Metaopenfoam: an llm-based multi-agent framework for cfd","venue":null,"work_id":"c6915907-dafa-4425-9e6e-710fe77a776c","year":2024},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:50.418371Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:8b639b1b83ea67a8a6c98eaa64d7d669bae6f294a21190d20d2698f67b919864","observation_id":"13569cd7-bf2a-4330-9f04-38dcb19e6936","resolution":{"observed_at":"2026-08-05T16:18:58.836302Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T16:18:58.390422Z","title":"Metaopenfoam 2.0: Large language model driven chain of thought for automating cfd simulation and post-processing.Journal Name, 2025","venue":null,"work_id":"b49ff850-f239-42d5-a61c-5770f31fe7b0","year":2025},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:50.512003Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:8e998756f463ad8edde5c895a9297c15ddaa639702650f907517b1002728891e","observation_id":"0bc953ed-07cc-427a-a39b-5e7ef071b777","resolution":{"observed_at":"2026-08-05T16:18:58.515670Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T16:18:58.073121Z","title":"Chatcfd: An llm-driven agent for end-to-end cfd automation with domain-specific structured reasoning","venue":null,"work_id":"aa41d43d-bf9c-4bd7-92f3-b4294a82991b","year":2025},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:50.674667Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:ceca52f35bc3042a113be0f844008baeadb39f5c7a7dc13b4fcad564cebfbcd6","observation_id":"547f7227-6cdf-433c-b8d5-ac50d72d7b32","resolution":{"observed_at":"2026-08-05T16:18:58.189970Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T16:18:57.739343Z","title":"Fine-tuning a large language model for automating com- putational fluid dynamics simulations.Theoretical and Applied Mechanics Letters, 15:100594, 2025","venue":null,"work_id":"fdca2660-761d-43fd-9a31-23f553bad798","year":2025},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:50.765431Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:634124c75f6ce6c7993dc439d6a5d7339b7262e7f4c14d453cf66d630b9f97f6","observation_id":"0f910363-9428-4298-95ed-8357aeaac612","resolution":{"observed_at":"2026-08-05T16:18:57.932209Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T16:18:57.407426Z","title":"Physics simulation capabilities of llms.Physica Scripta, 99(11):116003, oct 2024","venue":null,"work_id":"7f1520e3-6160-4aa9-b228-9b750776b9f2","year":2024},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:50.820759Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:6c45ac5df08671a2981b84bbeceba09f23b2bbae49d8dace9536b524ed39cfe3","observation_id":"49e9db7a-ed9f-476c-9319-cfab14e856ae","resolution":{"observed_at":"2026-08-05T16:18:57.539936Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T16:18:57.247078Z","title":"Mycrunchgpt: Achatgptassistedframeworkforscientificmachinelearning.Journal of Machine Learning for Modeling and Computing, 4(4):41–72, January 2023","venue":null,"work_id":"86f98412-1898-4ed1-beb4-4ab8e3514477","year":2023},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:50.976305Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:3ef5e5e7acc644f436ef7121a160bf5896573f59559e58c3357b75961b54e3c8","observation_id":"236a9a0e-1f1a-4c77-a067-3bdd33a5e057","resolution":{"observed_at":"2026-08-05T16:18:57.323653Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2501.12053","last_updated":"2025-01-21T11:26:02Z","snapshot_observed_at":"2026-08-15T13:32:24.759837Z","submitted_at":"2025-01-21T11:26:02Z","title":"PINNsAgent: Automated PDE Surrogation with Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.12053","snapshot_observed_at":"2026-08-05T16:18:51.098372Z","title":"Pinnsagent: Automated pde surrogation with large language models.arXiv preprint arXiv:2501.12053, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:51.098372Z"},"links":{"cited_paper":"/paper/2501.12053","citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:d7d713ee46f444a7d9dcfa183951e5e8d21b53a0037ad4ed8bc1b8ccf4b7bf5c","observation_id":"455538be-7430-4df8-86fa-fbf6ac4152c0","resolution":{"observed_at":"2026-08-05T16:18:51.098372Z","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":"2026-08-05T16:18:57.061379Z","title":"Lang-pinn: From language to physics-informed neural networks via a multi-agent framework","venue":null,"work_id":"24d09abb-ca79-4597-bb1a-c1d901c5af0f","year":2025},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:51.172354Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:7a48b1a9248d36700bf175a56c6353326ee2f12a7e71ef5823ae4e2645d71493","observation_id":"5747acb2-9304-4dc4-9e47-d1722877ccce","resolution":{"observed_at":"2026-08-05T16:18:57.163703Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T16:18:51.249520Z","title":"Text-trained llms can zero-shot extrapolate pde dynamics.arXiv preprint arXiv:2509.06322, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:51.249520Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:d98c36bbe5353c0100042c5f939c72801e99097a0b05c39cbf299d16dcf27c9a","observation_id":"0086d22d-09aa-4000-8715-371b83c016f6","resolution":{"observed_at":"2026-08-05T16:18:51.249520Z","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":"2026-08-05T16:18:56.794931Z","title":"Unisolver: Pde- conditional transformers towards universal neural pde solvers","venue":null,"work_id":"f6dd2685-8b4a-45a2-8e80-abf174bcdad7","year":2025},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:51.364379Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:0a66ce59bb1b72d6b6cf92517b149072290f2ab5c526f3d92b9683fc4421b436","observation_id":"d4aba927-5b7f-480c-8cca-e298aeca1816","resolution":{"observed_at":"2026-08-05T16:18:56.929600Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T16:18:56.549189Z","title":"UPS: Efficiently building foundation models for PDE solving via cross-modal adaptation.Transactions on Machine Learning Re- search, 2024","venue":null,"work_id":"4a1339f5-70a8-40ee-8648-817d36fd674b","year":2024},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:51.436838Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:0cc79c98bf86378248d26e2c2b0f988b163858725ad469208fb5699355234b6a","observation_id":"a639cd34-ae5e-4074-9efd-a8ab7ee35ed6","resolution":{"observed_at":"2026-08-05T16:18:56.693449Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T16:18:56.402582Z","title":"Fluid-llm: Learning computational fluid dynamics with spatiotemporal-aware large language models","venue":null,"work_id":"dbf7fa0e-35b0-42bf-bac0-d339e6a5aa1e","year":2024},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:51.520737Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:9326d74b234f824cd6e7199040394f4c5b2dababed6ccbeafe5ab354f932f489","observation_id":"c81484b8-6a00-4359-a6ca-242f2e052f02","resolution":{"observed_at":"2026-08-05T16:18:56.479753Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T16:18:56.159737Z","title":"Buchanan, and Amir Barati Farimani","venue":null,"work_id":"f8ec7895-1d3a-461b-b9c1-08187536ad2a","year":2025},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:51.601218Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:7aacb6425f1061deb0d4b705414fb69f569e4b22cf1fcd518f552627f74c8c7e","observation_id":"7e0e2556-fe6e-418a-992f-066d32979b30","resolution":{"observed_at":"2026-08-05T16:18:56.255200Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T16:18:55.942922Z","title":"Yang, Zulfikhar A","venue":null,"work_id":"5ea0de59-3e4f-4a58-8edc-a8f0f0c6506b","year":2023},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:51.678928Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:2d77511aad889b6c826d66b6913164e5e176a878dfea7a58402d92e270c973de","observation_id":"9cafb488-3202-4ee5-8e7d-fe8052741509","resolution":{"observed_at":"2026-08-05T16:18:56.058706Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T16:18:55.712278Z","title":"Aeroagent: A vision- physics-decision framework for aerodynamic vehicle design","venue":null,"work_id":"9c1836bf-fc69-40d3-9194-315949d4e496","year":2026},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:51.774246Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:ab7aaae774ac30b765dd545416b0bb17f4eb0ad0091ba284e2555c3eef19997d","observation_id":"dd340a43-ab67-46ea-9b66-d8d1103462d6","resolution":{"observed_at":"2026-08-05T16:18:55.815362Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T16:18:55.485038Z","title":"Shapebench: A scalable benchmark and diagnostic suite for standardized evaluation in aerodynamic shape optimization, 2026","venue":null,"work_id":"f821a878-5bf6-4f89-b638-a9df8a57f42d","year":2026},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:51.831800Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:cd3296fda55fe9e767917d5b0d94eddb30e50478356fbad4fbd9f554d7b43117","observation_id":"6f59649c-4161-4ae6-b0d0-82fcf923e5dc","resolution":{"observed_at":"2026-08-05T16:18:55.579112Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T16:18:55.259555Z","title":"Optmetaopenfoam: Large language model driven chain of thought for sensitivity analysis and parameter optimization based on cfd.Journal Name, 2025","venue":null,"work_id":"0eefafc9-2380-4078-b821-6c2845c77642","year":2025},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:51.902578Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:013c9a39bfc8e25da594ef1cd150b63fc0e320734805a3d1a68093d2175eda14","observation_id":"9ff55fb5-62cf-423c-a553-a8a956e838f2","resolution":{"observed_at":"2026-08-05T16:18:55.315190Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T16:18:55.145616Z","title":"Self-evolving scientific agent discovers generalizable physically-reasoned fluid control, 2026","venue":null,"work_id":"bbc00171-0b04-45c7-8d65-0cef66bd154c","year":2026},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:52.131193Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:ea6f463e0a7a69d17c2db0c6b87cd8a35b4e1fc911b149929a70aee364b77587","observation_id":"ad476b8b-0045-4dba-9ff8-dfe54c64fd24","resolution":{"observed_at":"2026-08-05T16:18:55.183166Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T16:18:54.956972Z","title":null,"venue":null,"work_id":"99e4d2ad-f958-4f56-b5d5-26910922cd01","year":2025},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:52.236515Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:a88986a25bdb7576d05a8c5fb65fd0826f42f427d03e0c29045dc1999c3aeb85","observation_id":"53dc8168-9a24-494b-b282-6d35dcfb4d36","resolution":{"observed_at":"2026-08-05T16:18:55.023199Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T16:18:54.782242Z","title":"Toward knowledge-guided ai for inverse design in manufacturing: A perspective on domain, physics, and human–ai synergy","venue":null,"work_id":"1d284600-0576-48c7-b4c4-7407a52d63f8","year":2025},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:52.313152Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:803fe45dfcfb4c37ad2bc9020cc323495f327e912800d2ef95581f6f294fb9ef","observation_id":"6931d88c-f34c-4ad8-8abb-a9a4cbf7a99d","resolution":{"observed_at":"2026-08-05T16:18:54.878610Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T16:18:54.602920Z","title":"Toward autonomous engineering design: A knowledge-guided multi-agent framework, 2025","venue":null,"work_id":"4d31dacd-5e05-4f5a-8612-9209b203b46c","year":2025},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:52.367994Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:d228ae2d982622c0ef17d009490d0e9234861637ed66a0b4be1c5335838ae7be","observation_id":"50de0bdf-5b50-4afd-b613-33320c091578","resolution":{"observed_at":"2026-08-05T16:18:54.694853Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T16:18:54.440271Z","title":"Think like a scientist: Physics-guided llm agent for equation discovery, 2026","venue":null,"work_id":"185b0c57-9ac8-4b28-9744-0c048de55cc3","year":2026},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:52.459872Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:5761223ec566eed5f74946d83ccfa0d3ed42687bc93e4a31cf1a2808389251c4","observation_id":"ed6c9d42-ed0b-4fee-9742-5f671e080e9f","resolution":{"observed_at":"2026-08-05T16:18:54.511583Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T16:18:54.250290Z","title":"Callaghan, and Dongxiao Zhang","venue":null,"work_id":"ef92f4b2-14d1-4570-9634-5b4730b840e7","year":2025},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:52.542554Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:fccd6fa9e1a29a5a55067226e0d93dd9fc87abd352c9870390712596ca351b4b","observation_id":"77a8e1e8-4d1b-4e5a-90f3-66c1c95183dc","resolution":{"observed_at":"2026-08-05T16:18:54.322809Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T16:18:54.051217Z","title":"Osher, and Hayden Schaeffer","venue":null,"work_id":"4acf2410-9364-436e-8a27-8d487fef901f","year":2025},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:52.615274Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:875cf6fc6d25948e425cf01cbff50db0124b66b99056807b1c78158a66ae07b7","observation_id":"f8f932cc-cda0-4ea0-b559-c23d2d5ff6f9","resolution":{"observed_at":"2026-08-05T16:18:54.154310Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T16:18:53.907833Z","title":"Jasak, A","venue":null,"work_id":"0162df9b-e2be-44f9-a473-58f83327e2bc","year":2007},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:52.676379Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:830c4e3235da314f36ee02b36399e5c76f43c6a5778f8017d9d31a1a68717c7b","observation_id":"0f5d9b7b-91b0-4132-aa19-3e672cb763aa","resolution":{"observed_at":"2026-08-05T16:18:53.974237Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T16:18:53.747609Z","title":"PDEBench: AnExtensiveBenchmarkforScientificMachine Learning","venue":null,"work_id":"0fc20f38-eee0-4468-a6de-2d9ee0d67276","year":2022},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:52.737499Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:0b9c464b1061939c1aafc8805907528a05c7764f7d10a598344acea209ad6ea1","observation_id":"a00397e1-51b4-4ce8-a7a3-dd5d6610f228","resolution":{"observed_at":"2026-08-05T16:18:53.804186Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-05T16:18:53.602607Z","title":"Pinnacle: a comprehensive benchmark of physics-informed neural networks for solving pdes","venue":null,"work_id":"8b6af2e6-400b-4396-a1c4-572c9477b201","year":2024},"citing_paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows","version":1},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-08-05T16:18:52.852949Z"},"links":{"citing_paper":"/paper/2608.03600"},"observation_digest":"sha256:d5fecb110f7c3a5b71d5aa1ab4fec8514046dbad7e5854b559bc4f285b3401a0","observation_id":"f07c5078-2ba8-492e-84db-3a5ba6626006","resolution":{"observed_at":"2026-08-05T16:18:53.674753Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2608.03600","last_updated":"2026-08-04T12:51:32Z","latest_version":1,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-15T13:33:09.366084Z","submitted_at":"2026-08-04T12:51:32Z","title":"Large language models for partial differential equation workflows"},"reference_resolution":{"displayed":91,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":31,"verified_exact":1,"verified_fuzzy":59},"total_outbound_references":91},"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":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 91 of 91 outbound references and 0 inbound Pith citation observations for arXiv:2608.03600."}