{"as_of":"2026-08-16T10:03:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:0cddc8f065d066ad3edf70d0c6b36da7062a75f6ef043a92ae0069aafc6bad93","coverage":[{"denominator":41,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":41,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T21:06:23.143073Z","state":"measured"},{"denominator":41,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":41,"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/2505.10930/citation-record","integrity":"/paper/2505.10930/integrity","json":"/paper/2505.10930/citation-record.json","paper":"/paper/2505.10930"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"4340.04920","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T21:06:23.226959Z","title":null,"venue":null,"work_id":"8356ee40-ca28-4914-a9fa-6d62894416a1","year":1997},"citing_paper":{"arxiv_id":"2505.10930","last_updated":"2025-05-31T03:05:23Z","snapshot_observed_at":"2026-08-15T20:58:40.579359Z","submitted_at":"2025-05-16T07:08:47Z","title":"Physics-informed Temporal Alignment for Auto-regressive PDE Foundation Models","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T21:06:23.128918Z"},"links":{"citing_paper":"/paper/2505.10930"},"observation_digest":"sha256:8e5e742a76684db6562a65322b0551b3be05d881fa5fda0747f323c4e592c0b6","observation_id":"1c72eccf-3e13-4e8a-9fff-e9093e27cede","resolution":{"observed_at":"2026-08-15T21:06:23.232996Z","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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T21:06:23.783059Z","title":"The total length of the testing dataset consists of 20 steps","venue":null,"work_id":"5c3b027e-45f0-4432-ad67-5ecd126e85f1","year":2024},"citing_paper":{"arxiv_id":"2505.10930","last_updated":"2025-05-31T03:05:23Z","snapshot_observed_at":"2026-08-15T20:58:40.579359Z","submitted_at":"2025-05-16T07:08:47Z","title":"Physics-informed Temporal Alignment for Auto-regressive PDE Foundation Models","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T21:06:23.125073Z"},"links":{"citing_paper":"/paper/2505.10930"},"observation_digest":"sha256:623e19ff566744637fa1e18fdc3420b1fd85276d1aa70138573b43f5c1368e0f","observation_id":"2b19e219-9256-4f71-a0c5-5d703cf5ae25","resolution":{"observed_at":"2026-08-15T21:06:23.787091Z","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":"2306.08827","last_updated":"2023-10-05T06:33:52Z","snapshot_observed_at":"2026-08-14T23:19:42.878527Z","submitted_at":"2023-06-15T02:49:05Z","title":"PINNacle: A Comprehensive Benchmark of Physics-Informed Neural Networks for Solving PDEs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.08827","snapshot_observed_at":"2026-08-15T21:06:23.028187Z","title":"Gnot: A general neu- ral operator transformer for operator learning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.10930","last_updated":"2025-05-31T03:05:23Z","snapshot_observed_at":"2026-08-15T20:58:40.579359Z","submitted_at":"2025-05-16T07:08:47Z","title":"Physics-informed Temporal Alignment for Auto-regressive PDE Foundation Models","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T21:06:23.028187Z"},"links":{"cited_paper":"/paper/2306.08827","citing_paper":"/paper/2505.10930"},"observation_digest":"sha256:3839aaa22dffe96a669c487621d77e7af6cd1c0cd01537ec6b397edab2af1629","observation_id":"f00cb017-8b77-4f6b-8370-effd812905cc","resolution":{"observed_at":"2026-08-15T21:06:23.028187Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.16228","last_updated":"2024-07-11T23:03:09Z","snapshot_observed_at":"2026-08-13T05:41:07.997609Z","submitted_at":"2023-10-24T22:54:05Z","title":"On the Foundations of Shortcut Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.16228","snapshot_observed_at":"2026-08-15T21:06:23.031864Z","title":"L., Mobahi, H., Fel, T., and Mozer, M","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.10930","last_updated":"2025-05-31T03:05:23Z","snapshot_observed_at":"2026-08-15T20:58:40.579359Z","submitted_at":"2025-05-16T07:08:47Z","title":"Physics-informed Temporal Alignment for Auto-regressive PDE Foundation Models","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T21:06:23.031864Z"},"links":{"cited_paper":"/paper/2310.16228","citing_paper":"/paper/2505.10930"},"observation_digest":"sha256:414d4b1c2e6dc5d98cba5cf868b6dccc16cf96805fe6a064903db58839847268","observation_id":"25d5aab3-2c2a-43da-ac61-fd72d0cc5688","resolution":{"observed_at":"2026-08-15T21:06:23.031864Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2004.07802","last_updated":"2021-03-18T17:47:28Z","snapshot_observed_at":"2026-07-06T09:12:55.577444Z","submitted_at":"2020-04-16T17:46:39Z","title":"Geometry-Aware Gradient Algorithms for Neural Architecture Search","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2004.07802","snapshot_observed_at":"2026-08-15T21:06:23.038808Z","title":"C., Kumar, A., and Pathak, D","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.10930","last_updated":"2025-05-31T03:05:23Z","snapshot_observed_at":"2026-08-15T20:58:40.579359Z","submitted_at":"2025-05-16T07:08:47Z","title":"Physics-informed Temporal Alignment for Auto-regressive PDE Foundation Models","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T21:06:23.038808Z"},"links":{"cited_paper":"/paper/2004.07802","citing_paper":"/paper/2505.10930"},"observation_digest":"sha256:b595fa9db83fa0ca4b9314859e1eb53ac744ddfdcc66f58fc388acb9ffc4bfd9","observation_id":"fb9766a4-8e3f-4b77-802e-51ee2b238b36","resolution":{"observed_at":"2026-08-15T21:06:23.038808Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1805.06334","last_updated":"2018-05-17T16:12:16Z","snapshot_observed_at":"2026-08-14T19:14:39.502319Z","submitted_at":"2018-05-16T13:59:20Z","title":"Auxiliary Tasks in Multi-task Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1805.06334","snapshot_observed_at":"2026-08-15T21:06:23.045906Z","title":"Scalable trans- former for pde surrogate modeling.Advances in Neural Information Processing Systems, 36, 2024b","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.10930","last_updated":"2025-05-31T03:05:23Z","snapshot_observed_at":"2026-08-15T20:58:40.579359Z","submitted_at":"2025-05-16T07:08:47Z","title":"Physics-informed Temporal Alignment for Auto-regressive PDE Foundation Models","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T21:06:23.045906Z"},"links":{"cited_paper":"/paper/1805.06334","citing_paper":"/paper/2505.10930"},"observation_digest":"sha256:50dea102a5a331e4f5847c4821d12cfdd6b8678e58a3a55cb2f11913255550c1","observation_id":"f5f680ad-fa50-487f-8f53-5b3bfdfe236f","resolution":{"observed_at":"2026-08-15T21:06:23.045906Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.03163","last_updated":"2024-12-25T02:59:32Z","snapshot_observed_at":"2026-08-12T23:49:42.710301Z","submitted_at":"2024-06-05T11:53:28Z","title":"Foundation Models for Geophysics: Review and Perspective","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.03163","snapshot_observed_at":"2026-08-15T21:06:23.049072Z","title":"Model sparsity can simplify machine unlearning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.10930","last_updated":"2025-05-31T03:05:23Z","snapshot_observed_at":"2026-08-15T20:58:40.579359Z","submitted_at":"2025-05-16T07:08:47Z","title":"Physics-informed Temporal Alignment for Auto-regressive PDE Foundation Models","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T21:06:23.049072Z"},"links":{"cited_paper":"/paper/2406.03163","citing_paper":"/paper/2505.10930"},"observation_digest":"sha256:d1a58fab288fe59f12a73793bfefaf11cea66dc39a5387e59660180c252a6134","observation_id":"b2433f20-95b9-443b-89df-88a2a14a28fe","resolution":{"observed_at":"2026-08-15T21:06:23.049072Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.09811","last_updated":"2024-09-15T18:20:15Z","snapshot_observed_at":"2026-08-15T22:14:06.466470Z","submitted_at":"2024-09-15T18:20:15Z","title":"PROSE-FD: A Multimodal PDE Foundation Model for Learning Multiple Operators for Forecasting Fluid Dynamics","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.09811","snapshot_observed_at":"2026-08-15T21:06:23.052279Z","title":"Prose-fd: A multimodal PDE foundation model for learning multiple operators for forecasting fluid dynamics","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.10930","last_updated":"2025-05-31T03:05:23Z","snapshot_observed_at":"2026-08-15T20:58:40.579359Z","submitted_at":"2025-05-16T07:08:47Z","title":"Physics-informed Temporal Alignment for Auto-regressive PDE Foundation Models","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T21:06:23.052279Z"},"links":{"cited_paper":"/paper/2409.09811","citing_paper":"/paper/2505.10930"},"observation_digest":"sha256:7d697b5b44aa9ee894004ef03f0117ac4dee5eeb97e0d9f96f3381c882ff6956","observation_id":"06f10b83-d83b-4e6b-a51f-39568dc3784f","resolution":{"observed_at":"2026-08-15T21:06:23.052279Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1910.03193","last_updated":"2020-04-15T00:51:54Z","snapshot_observed_at":"2026-08-15T10:02:22.851586Z","submitted_at":"2019-10-08T03:21:14Z","title":"DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operators","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.03193","snapshot_observed_at":"2026-08-15T21:06:23.055531Z","title":null,"venue":null,"work_id":null,"year":1910},"citing_paper":{"arxiv_id":"2505.10930","last_updated":"2025-05-31T03:05:23Z","snapshot_observed_at":"2026-08-15T20:58:40.579359Z","submitted_at":"2025-05-16T07:08:47Z","title":"Physics-informed Temporal Alignment for Auto-regressive PDE Foundation Models","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T21:06:23.055531Z"},"links":{"cited_paper":"/paper/1910.03193","citing_paper":"/paper/2505.10930"},"observation_digest":"sha256:182a867d8d71d38e667348cac8142f2d1908ef324466afb9c4913e73ab129351","observation_id":"7136dc6e-5fd3-424e-8b63-3421f261d61e","resolution":{"observed_at":"2026-08-15T21:06:23.055531Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.05963","last_updated":"2024-02-23T16:39:40Z","snapshot_observed_at":"2026-08-14T04:54:54.118946Z","submitted_at":"2023-09-13T06:30:08Z","title":"CFDBench: A Large-Scale Benchmark for Machine Learning Methods in Fluid Dynamics","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.05963","snapshot_observed_at":"2026-08-15T21:06:23.058900Z","title":"Cfdbench: A comprehen- sive benchmark for machine learning methods in fluid dynamics.arXiv preprint arXiv:2310.05963,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.10930","last_updated":"2025-05-31T03:05:23Z","snapshot_observed_at":"2026-08-15T20:58:40.579359Z","submitted_at":"2025-05-16T07:08:47Z","title":"Physics-informed Temporal Alignment for Auto-regressive PDE Foundation Models","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T21:06:23.058900Z"},"links":{"cited_paper":"/paper/2310.05963","citing_paper":"/paper/2505.10930"},"observation_digest":"sha256:9e88ac85455bdfc440520477410184c4bc980ad98fa6e69947efc878e19237a4","observation_id":"410a084e-cc7c-45de-b6c1-f12b52702d6a","resolution":{"observed_at":"2026-08-15T21:06:23.058900Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.02994","last_updated":"2024-12-10T16:25:53Z","snapshot_observed_at":"2026-08-13T05:57:24.197845Z","submitted_at":"2023-10-04T17:29:19Z","title":"Multiple Physics Pretraining for Physical Surrogate Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.02994","snapshot_observed_at":"2026-08-15T21:06:23.062221Z","title":"R.-S., Parker, L","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.10930","last_updated":"2025-05-31T03:05:23Z","snapshot_observed_at":"2026-08-15T20:58:40.579359Z","submitted_at":"2025-05-16T07:08:47Z","title":"Physics-informed Temporal Alignment for Auto-regressive PDE Foundation Models","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T21:06:23.062221Z"},"links":{"cited_paper":"/paper/2310.02994","citing_paper":"/paper/2505.10930"},"observation_digest":"sha256:8683114a17f6d934cff7e52df7c09dabfb8c9f58d985521d5a81cc6fcaedd35e","observation_id":"14bdc1aa-92be-4074-9a4f-fbbcdaf077c9","resolution":{"observed_at":"2026-08-15T21:06:23.062221Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1206.6471","last_updated":"2012-06-27T19:59:59Z","snapshot_observed_at":"2026-08-15T00:55:08.924193Z","submitted_at":"2012-06-27T19:59:59Z","title":"On Causal and Anticausal Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1206.6471","snapshot_observed_at":"2026-08-15T21:06:23.065504Z","title":"On causal and anticausal learning.arXiv preprint arXiv:1206.6471,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.10930","last_updated":"2025-05-31T03:05:23Z","snapshot_observed_at":"2026-08-15T20:58:40.579359Z","submitted_at":"2025-05-16T07:08:47Z","title":"Physics-informed Temporal Alignment for Auto-regressive PDE Foundation Models","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T21:06:23.065504Z"},"links":{"cited_paper":"/paper/1206.6471","citing_paper":"/paper/2505.10930"},"observation_digest":"sha256:da4dacddeed9ddc5ca32f512d44e97b78c02dd023aefdc732483202007d7dfad","observation_id":"64855994-d82b-4f19-bb11-1200a163350b","resolution":{"observed_at":"2026-08-15T21:06:23.065504Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.16176","last_updated":"2025-04-02T18:36:37Z","snapshot_observed_at":"2026-08-13T05:18:57.794801Z","submitted_at":"2023-11-23T15:47:33Z","title":"Mitigating Shortcut Learning with Diffusion Counterfactuals and Diverse Ensembles","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.16176","snapshot_observed_at":"2026-08-15T21:06:23.068869Z","title":"J., Nicoli- cioiu, A","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.10930","last_updated":"2025-05-31T03:05:23Z","snapshot_observed_at":"2026-08-15T20:58:40.579359Z","submitted_at":"2025-05-16T07:08:47Z","title":"Physics-informed Temporal Alignment for Auto-regressive PDE Foundation Models","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T21:06:23.068869Z"},"links":{"cited_paper":"/paper/2311.16176","citing_paper":"/paper/2505.10930"},"observation_digest":"sha256:362f40203425590dc29459c2bef80c27d933b34f2976bd83cecb2c5743622088","observation_id":"341673be-85f7-46b8-b24d-dd988dd43170","resolution":{"observed_at":"2026-08-15T21:06:23.068869Z","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":"2026-08-15T21:06:23.793603Z","title":"Ups: Efficiently building foundation models for PDE solving via cross- modal adaptation","venue":null,"work_id":"8aeff084-9f57-4618-ac5b-7168f36ec895","year":2024},"citing_paper":{"arxiv_id":"2505.10930","last_updated":"2025-05-31T03:05:23Z","snapshot_observed_at":"2026-08-15T20:58:40.579359Z","submitted_at":"2025-05-16T07:08:47Z","title":"Physics-informed Temporal Alignment for Auto-regressive PDE Foundation Models","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T21:06:23.072274Z"},"links":{"citing_paper":"/paper/2505.10930"},"observation_digest":"sha256:3a71b1e39ff93957b61db2fe82dcc2c90ab58597549de2a06ba8e86ffc41cc94","observation_id":"e3a67178-4578-42ce-96cc-ee81fd483ce9","resolution":{"observed_at":"2026-08-15T21:06:23.796807Z","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":"2411.02018","last_updated":"2024-11-28T11:00:19Z","snapshot_observed_at":"2026-08-14T14:08:48.413586Z","submitted_at":"2024-11-04T12:13:04Z","title":"Shortcut Learning in In-Context Learning: A Survey","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.02018","snapshot_observed_at":"2026-08-15T21:06:23.075574Z","title":"Shortcut learning in in-context learning: A survey.arXiv preprint arXiv:2411.02018, 2024a","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.10930","last_updated":"2025-05-31T03:05:23Z","snapshot_observed_at":"2026-08-15T20:58:40.579359Z","submitted_at":"2025-05-16T07:08:47Z","title":"Physics-informed Temporal Alignment for Auto-regressive PDE Foundation Models","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T21:06:23.075574Z"},"links":{"cited_paper":"/paper/2411.02018","citing_paper":"/paper/2505.10930"},"observation_digest":"sha256:91eb6a5b14c42f28e7cec1952ccdf44ad5805c2d11679479f337ec386265c3cb","observation_id":"5cec65c6-2a06-4fb7-b433-a731a5fe567b","resolution":{"observed_at":"2026-08-15T21:06:23.075574Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.12355","last_updated":"2025-01-31T20:40:12Z","snapshot_observed_at":"2026-08-13T00:27:13.048028Z","submitted_at":"2024-04-18T17:34:20Z","title":"Towards a Foundation Model for Partial Differential Equations: Multi-Operator Learning and Extrapolation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.12355","snapshot_observed_at":"2026-08-15T21:06:23.078991Z","title":"Towards a foundation model for partial differential equation: Multi- operator learning and extrapolation.arXiv preprint arXiv:2404.12355,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.10930","last_updated":"2025-05-31T03:05:23Z","snapshot_observed_at":"2026-08-15T20:58:40.579359Z","submitted_at":"2025-05-16T07:08:47Z","title":"Physics-informed Temporal Alignment for Auto-regressive PDE Foundation Models","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T21:06:23.078991Z"},"links":{"cited_paper":"/paper/2404.12355","citing_paper":"/paper/2505.10930"},"observation_digest":"sha256:6b1bbe0bdc2d405bf2fb5b8076fa534a6df7b4f391778d311c03e3934f63a6d5","observation_id":"ce1fd0c0-217e-4037-9be0-fbb0b760ebaf","resolution":{"observed_at":"2026-08-15T21:06:23.078991Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.17256","last_updated":"2023-09-09T18:32:00Z","snapshot_observed_at":"2026-08-15T15:29:54.820196Z","submitted_at":"2023-05-26T20:56:30Z","title":"Large Language Models Can be Lazy Learners: Analyze Shortcuts in In-Context Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.17256","snapshot_observed_at":"2026-08-15T21:06:23.082243Z","title":"Large language models can be lazy learners: Analyze shortcuts in in- context learning.arXiv preprint arXiv:2305.17256,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.10930","last_updated":"2025-05-31T03:05:23Z","snapshot_observed_at":"2026-08-15T20:58:40.579359Z","submitted_at":"2025-05-16T07:08:47Z","title":"Physics-informed Temporal Alignment for Auto-regressive PDE Foundation Models","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T21:06:23.082243Z"},"links":{"cited_paper":"/paper/2305.17256","citing_paper":"/paper/2505.10930"},"observation_digest":"sha256:0c17d4d3c2c67a219b6f4849cd809aebc82a0e92f46a2ce8bbeff41917bdd5e6","observation_id":"54607c21-3c31-4b99-9313-db71fee65e16","resolution":{"observed_at":"2026-08-15T21:06:23.082243Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.04463","last_updated":"2020-04-06T12:17:35Z","snapshot_observed_at":"2026-08-14T19:16:21.509579Z","submitted_at":"2019-08-13T02:26:14Z","title":"DL-PDE: Deep-learning based data-driven discovery of partial differential equations from discrete and noisy data","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.04463","snapshot_observed_at":"2026-08-15T21:06:23.092739Z","title":"Dl-PDE: Deep-learning based data-driven discovery of partial differential equa- tions from discrete and noisy data.arXiv preprint arXiv:1908.04463,","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2505.10930","last_updated":"2025-05-31T03:05:23Z","snapshot_observed_at":"2026-08-15T20:58:40.579359Z","submitted_at":"2025-05-16T07:08:47Z","title":"Physics-informed Temporal Alignment for Auto-regressive PDE Foundation Models","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T21:06:23.092739Z"},"links":{"cited_paper":"/paper/1908.04463","citing_paper":"/paper/2505.10930"},"observation_digest":"sha256:4daba46dd41444497242121c2032f02bbd8e2998a350af7438fde80a7cb8c03c","observation_id":"91ee18ef-06eb-4866-9f8e-a6e3d7e1d12c","resolution":{"observed_at":"2026-08-15T21:06:23.092739Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.12652","last_updated":"2025-01-27T10:11:21Z","snapshot_observed_at":"2026-08-13T04:14:53.981817Z","submitted_at":"2024-02-20T02:02:29Z","title":"PDEformer: Towards a Foundation Model for One-Dimensional Partial Differential Equations","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.12652","snapshot_observed_at":"2026-08-15T21:06:23.096077Z","title":"PDEformer: Towards a foundation model for one- dimensional partial differential equations.arXiv preprint arXiv:2402.12652, 2024a","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.10930","last_updated":"2025-05-31T03:05:23Z","snapshot_observed_at":"2026-08-15T20:58:40.579359Z","submitted_at":"2025-05-16T07:08:47Z","title":"Physics-informed Temporal Alignment for Auto-regressive PDE Foundation Models","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-15T21:06:23.096077Z"},"links":{"cited_paper":"/paper/2402.12652","citing_paper":"/paper/2505.10930"},"observation_digest":"sha256:5c4e2c2654ecf933e376089ca1407e964b74e8de5413d4a5701a5dd834a70f35","observation_id":"d74492ac-d6dc-48bd-ab09-74c79c7ead3d","resolution":{"observed_at":"2026-08-15T21:06:23.096077Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.13343","last_updated":"2024-10-17T08:52:52Z","snapshot_observed_at":"2026-08-12T22:21:10.172647Z","submitted_at":"2024-10-17T08:52:52Z","title":"Do LLMs Overcome Shortcut Learning? An Evaluation of Shortcut Challenges in Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.13343","snapshot_observed_at":"2026-08-15T21:06:23.099446Z","title":"Do llms overcome shortcut learning? an evaluation of short- cut challenges in large language models.arXiv preprint arXiv:2410.13343,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.10930","last_updated":"2025-05-31T03:05:23Z","snapshot_observed_at":"2026-08-15T20:58:40.579359Z","submitted_at":"2025-05-16T07:08:47Z","title":"Physics-informed Temporal Alignment for Auto-regressive PDE Foundation Models","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T21:06:23.099446Z"},"links":{"cited_paper":"/paper/2410.13343","citing_paper":"/paper/2505.10930"},"observation_digest":"sha256:84afcbef268655124bcfe13839e65ba8fb3d0e63668a096acfc3d95e800ba575","observation_id":"efbe8f45-eff9-429e-aa30-2e4097fe2e87","resolution":{"observed_at":"2026-08-15T21:06:23.099446Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.07955","last_updated":"2024-07-19T04:31:38Z","snapshot_observed_at":"2026-08-13T00:57:00.524770Z","submitted_at":"2024-03-12T07:24:17Z","title":"Towards Faithful Explanations: Boosting Rationalization with Shortcuts Discovery","version":2},"cited_work":{"arxiv_id":"2403.07955","doi":null,"metadata_source":"pith","pith_arxiv_id":"2403.07955","snapshot_observed_at":"2026-08-15T21:06:23.291028Z","title":"Towards Faithful Explanations: Boosting Rationalization with Shortcuts Discovery","venue":"cs.LG","work_id":"36e5d48c-a57f-48b5-8393-0f682c6e5ba7","year":2024},"citing_paper":{"arxiv_id":"2505.10930","last_updated":"2025-05-31T03:05:23Z","snapshot_observed_at":"2026-08-15T20:58:40.579359Z","submitted_at":"2025-05-16T07:08:47Z","title":"Physics-informed Temporal Alignment for Auto-regressive PDE Foundation Models","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-15T21:06:23.102845Z"},"links":{"cited_paper":"/paper/2403.07955","citing_paper":"/paper/2505.10930"},"observation_digest":"sha256:f683531fbc7669ced5d5353556a846f7081c77b1e755569909da40c203631502","observation_id":"070901b0-40a0-4c4f-b060-714471f847aa","resolution":{"observed_at":"2026-08-15T21:06:23.295620Z","resolver_source":"local_arxiv","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":"2307.11833","last_updated":"2024-05-07T14:04:16Z","snapshot_observed_at":"2026-08-13T10:50:14.227809Z","submitted_at":"2023-07-21T18:06:27Z","title":"PINNsFormer: A Transformer-Based Framework For Physics-Informed Neural Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.11833","snapshot_observed_at":"2026-08-15T21:06:23.109346Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.10930","last_updated":"2025-05-31T03:05:23Z","snapshot_observed_at":"2026-08-15T20:58:40.579359Z","submitted_at":"2025-05-16T07:08:47Z","title":"Physics-informed Temporal Alignment for Auto-regressive PDE Foundation Models","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-15T21:06:23.109346Z"},"links":{"cited_paper":"/paper/2307.11833","citing_paper":"/paper/2505.10930"},"observation_digest":"sha256:ec4c15e5e103c38744665fb0175d2d19511875b465a8098c7026a9945fa3d93e","observation_id":"08697b56-cb25-4fc1-993e-c3860022bbc9","resolution":{"observed_at":"2026-08-15T21:06:23.109346Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.17728","last_updated":"2024-12-05T18:55:44Z","snapshot_observed_at":"2026-08-13T00:44:41.074191Z","submitted_at":"2024-03-26T14:17:01Z","title":"Masked Autoencoders are PDE Learners","version":3},"cited_work":{"arxiv_id":"2403.17728","doi":null,"metadata_source":"pith","pith_arxiv_id":"2403.17728","snapshot_observed_at":"2026-08-15T21:06:23.259404Z","title":"Masked Autoencoders are PDE Learners","venue":"cs.LG","work_id":"59b9ff91-c074-4cd7-9e31-7c0f3f5c961d","year":2024},"citing_paper":{"arxiv_id":"2505.10930","last_updated":"2025-05-31T03:05:23Z","snapshot_observed_at":"2026-08-15T20:58:40.579359Z","submitted_at":"2025-05-16T07:08:47Z","title":"Physics-informed Temporal Alignment for Auto-regressive PDE Foundation Models","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-15T21:06:23.112878Z"},"links":{"cited_paper":"/paper/2403.17728","citing_paper":"/paper/2505.10930"},"observation_digest":"sha256:da27ba8c726cdf973e5967a8a4b85cef0a65c69ae386442d96f5e5edd449c8ae","observation_id":"be8682ee-e9f2-4f7c-bcef-efe3862804d1","resolution":{"observed_at":"2026-08-15T21:06:23.263126Z","resolver_source":"local_arxiv","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":"2406.08473","last_updated":"2024-10-02T16:37:16Z","snapshot_observed_at":"2026-08-12T23:44:17.008304Z","submitted_at":"2024-06-12T17:56:46Z","title":"Strategies for Pretraining Neural Operators","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.08473","snapshot_observed_at":"2026-08-15T21:06:23.117362Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.10930","last_updated":"2025-05-31T03:05:23Z","snapshot_observed_at":"2026-08-15T20:58:40.579359Z","submitted_at":"2025-05-16T07:08:47Z","title":"Physics-informed Temporal Alignment for Auto-regressive PDE Foundation Models","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-15T21:06:23.117362Z"},"links":{"cited_paper":"/paper/2406.08473","citing_paper":"/paper/2505.10930"},"observation_digest":"sha256:e14f990942958fddf648f16dd51e1581b7af9226dea4f4de5fb98b2bf279585f","observation_id":"d34ad860-a1f7-4500-90fa-68390cd36310","resolution":{"observed_at":"2026-08-15T21:06:23.117362Z","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":"2026-08-15T21:06:23.772390Z","title":"The sequentially thresholded least squares (STLS) method (Budi ˇsi´c et al.,","venue":null,"work_id":"17b58e1f-faef-4e50-871a-6c092ae69bb8","year":2014},"citing_paper":{"arxiv_id":"2505.10930","last_updated":"2025-05-31T03:05:23Z","snapshot_observed_at":"2026-08-15T20:58:40.579359Z","submitted_at":"2025-05-16T07:08:47Z","title":"Physics-informed Temporal Alignment for Auto-regressive PDE Foundation Models","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-15T21:06:23.132383Z"},"links":{"citing_paper":"/paper/2505.10930"},"observation_digest":"sha256:8de4be6fd027127d4025698b26c854cb225a4082d639ada4e6dabddc25dbab0c","observation_id":"b4ed660a-b1bb-4575-9a7f-0db238f375f4","resolution":{"observed_at":"2026-08-15T21:06:23.776147Z","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":"2026-08-15T21:06:23.762637Z","title":"STRidge time","venue":null,"work_id":"6fc3fed5-ecd6-41b4-ab6e-41e1e68cbdd6","year":2012},"citing_paper":{"arxiv_id":"2505.10930","last_updated":"2025-05-31T03:05:23Z","snapshot_observed_at":"2026-08-15T20:58:40.579359Z","submitted_at":"2025-05-16T07:08:47Z","title":"Physics-informed Temporal Alignment for Auto-regressive PDE Foundation Models","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-15T21:06:23.135831Z"},"links":{"citing_paper":"/paper/2505.10930"},"observation_digest":"sha256:2c5138bf0ec0e59125f96c259ef26621f9ad0a2cd32d2b678438901caddc3007","observation_id":"440d6c55-7183-451d-b30c-24a49243ce93","resolution":{"observed_at":"2026-08-15T21:06:23.766015Z","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":"2026-08-15T21:06:23.751976Z","title":null,"venue":null,"work_id":"b0001b6f-5623-4e3f-a11a-3920686021dd","year":2012},"citing_paper":{"arxiv_id":"2505.10930","last_updated":"2025-05-31T03:05:23Z","snapshot_observed_at":"2026-08-15T20:58:40.579359Z","submitted_at":"2025-05-16T07:08:47Z","title":"Physics-informed Temporal Alignment for Auto-regressive PDE Foundation Models","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-15T21:06:23.139589Z"},"links":{"citing_paper":"/paper/2505.10930"},"observation_digest":"sha256:e4bc2c130d0830d9c3741e6853138e08813b515ba867ba42cfe5f6ca56b23b6f","observation_id":"2bc71c72-7c62-4157-a760-2e0d3758af2c","resolution":{"observed_at":"2026-08-15T21:06:23.755980Z","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":"2026-08-15T21:06:23.741340Z","title":null,"venue":null,"work_id":"03da7718-ec62-4a8f-9e47-88417a9726ac","year":null},"citing_paper":{"arxiv_id":"2505.10930","last_updated":"2025-05-31T03:05:23Z","snapshot_observed_at":"2026-08-15T20:58:40.579359Z","submitted_at":"2025-05-16T07:08:47Z","title":"Physics-informed Temporal Alignment for Auto-regressive PDE Foundation Models","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-15T21:06:23.143073Z"},"links":{"citing_paper":"/paper/2505.10930"},"observation_digest":"sha256:df15a72136873b9efa6660fae7ec6419c33fedd27603a479c29e03fbdbf87c26","observation_id":"d7baf9a8-a397-4de6-a4a5-6690069855d9","resolution":{"observed_at":"2026-08-15T21:06:23.745020Z","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":{"arxiv_id":"2111.13587","last_updated":"2022-03-27T04:24:27Z","snapshot_observed_at":"2026-08-15T11:56:35.554400Z","submitted_at":"2021-11-24T05:44:31Z","title":"Adaptive Fourier Neural Operators: Efficient Token Mixers for Transformers","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2111.13587","snapshot_observed_at":"2026-08-15T21:06:23.021256Z","title":"Adaptive fourier neural operators: Efficient token mixers for transformers.arXiv preprint arXiv:2111.13587,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.10930","last_updated":"2025-05-31T03:05:23Z","snapshot_observed_at":"2026-08-15T20:58:40.579359Z","submitted_at":"2025-05-16T07:08:47Z","title":"Physics-informed Temporal Alignment for Auto-regressive PDE Foundation Models","version":2},"reference_index":1973,"source":"pdf_text","source_observed_at":"2026-08-15T21:06:23.021256Z"},"links":{"cited_paper":"/paper/2111.13587","citing_paper":"/paper/2505.10930"},"observation_digest":"sha256:8ad02a17ac1ed33d4b3f59da5498b1dc52ea3a7ba49c8768520ff8ce0f3fc79d","observation_id":"6b1d26eb-0be7-40e9-94a4-1c414b97e62c","resolution":{"observed_at":"2026-08-15T21:06:23.021256Z","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":"2503.10253","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T21:06:23.395357Z","title":"and Efros, A","venue":null,"work_id":"1a0184e0-ca94-4999-a3e5-5d229100f416","year":null},"citing_paper":{"arxiv_id":"2505.10930","last_updated":"2025-05-31T03:05:23Z","snapshot_observed_at":"2026-08-15T20:58:40.579359Z","submitted_at":"2025-05-16T07:08:47Z","title":"Physics-informed Temporal Alignment for Auto-regressive PDE Foundation Models","version":2},"reference_index":1997,"source":"pdf_text","source_observed_at":"2026-08-15T21:06:23.085601Z"},"links":{"citing_paper":"/paper/2505.10930"},"observation_digest":"sha256:5175452f3fe8b47a470ad69dca03fdc52339b0f15c03316d950cc7dee9940fdc","observation_id":"2c7aac9b-7350-4d16-9060-aab7140e8b23","resolution":{"observed_at":"2026-08-15T21:06:23.400650Z","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":"2103.06922","last_updated":"2021-04-13T22:38:11Z","snapshot_observed_at":"2026-08-13T19:59:39.692329Z","submitted_at":"2021-03-11T19:39:56Z","title":"Towards Interpreting and Mitigating Shortcut Learning Behavior of NLU Models","version":3},"cited_work":{"arxiv_id":"2103.06922","doi":null,"metadata_source":"pith","pith_arxiv_id":"2103.06922","snapshot_observed_at":"2026-08-15T21:06:23.699218Z","title":"Towards Interpreting and Mitigating Shortcut Learning Behavior of NLU Models","venue":"cs.CL","work_id":"ac07be8f-4f4b-45a6-b7d5-61b8271962af","year":2021},"citing_paper":{"arxiv_id":"2505.10930","last_updated":"2025-05-31T03:05:23Z","snapshot_observed_at":"2026-08-15T20:58:40.579359Z","submitted_at":"2025-05-16T07:08:47Z","title":"Physics-informed Temporal Alignment for Auto-regressive PDE Foundation Models","version":2},"reference_index":2006,"source":"pdf_text","source_observed_at":"2026-08-15T21:06:23.013954Z"},"links":{"cited_paper":"/paper/2103.06922","citing_paper":"/paper/2505.10930"},"observation_digest":"sha256:5932e4b8bec04aed11c510b8f8ab2b0fed6a6ee4acc3a6e35a3b44903a8bc86f","observation_id":"b6a6121a-0081-41b3-962c-151ad3e70e80","resolution":{"observed_at":"2026-08-15T21:06:23.703156Z","resolver_source":"local_arxiv","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":"2410.03132","last_updated":"2025-03-25T19:16:05Z","snapshot_observed_at":"2026-08-12T22:31:04.694544Z","submitted_at":"2024-10-04T04:07:15Z","title":"Autoregressive Action Sequence Learning for Robotic Manipulation","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.03132","snapshot_observed_at":"2026-08-15T21:06:23.105923Z","title":"Autoregressive action sequence learning for robotic manipulation.arXiv preprint arXiv:2410.03132, 2024a","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.10930","last_updated":"2025-05-31T03:05:23Z","snapshot_observed_at":"2026-08-15T20:58:40.579359Z","submitted_at":"2025-05-16T07:08:47Z","title":"Physics-informed Temporal Alignment for Auto-regressive PDE Foundation Models","version":2},"reference_index":2008,"source":"pdf_text","source_observed_at":"2026-08-15T21:06:23.105923Z"},"links":{"cited_paper":"/paper/2410.03132","citing_paper":"/paper/2505.10930"},"observation_digest":"sha256:886cf160cf7144379ce932e657301328adb3b343d1a190e5ffabccc298bfeace","observation_id":"5eee344d-792a-4775-a81a-50f48879c35a","resolution":{"observed_at":"2026-08-15T21:06:23.105923Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.02322","last_updated":"2025-02-11T00:53:58Z","snapshot_observed_at":"2026-08-12T22:51:56.316854Z","submitted_at":"2024-09-03T22:31:57Z","title":"TimeDiT: General-purpose Diffusion Transformers for Time Series Foundation Model","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.02322","snapshot_observed_at":"2026-08-15T21:06:23.002031Z","title":"Timedit: General- purpose diffusion transformers for time series foundation model.arXiv preprint arXiv:2409.02322,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.10930","last_updated":"2025-05-31T03:05:23Z","snapshot_observed_at":"2026-08-15T20:58:40.579359Z","submitted_at":"2025-05-16T07:08:47Z","title":"Physics-informed Temporal Alignment for Auto-regressive PDE Foundation Models","version":2},"reference_index":2012,"source":"pdf_text","source_observed_at":"2026-08-15T21:06:23.002031Z"},"links":{"cited_paper":"/paper/2409.02322","citing_paper":"/paper/2505.10930"},"observation_digest":"sha256:c672a640636c4e5886aaa7ef659e85973ae95420b7939043131ccf07886bf927","observation_id":"b503160a-2782-405b-b0dc-8bc6590fff2c","resolution":{"observed_at":"2026-08-15T21:06:23.002031Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1811.12231","last_updated":"2022-11-09T23:15:15Z","snapshot_observed_at":"2026-08-15T04:09:02.437506Z","submitted_at":"2018-11-29T15:04:05Z","title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1811.12231","snapshot_observed_at":"2026-08-15T21:06:23.017655Z","title":"A., and Brendel, W","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.10930","last_updated":"2025-05-31T03:05:23Z","snapshot_observed_at":"2026-08-15T20:58:40.579359Z","submitted_at":"2025-05-16T07:08:47Z","title":"Physics-informed Temporal Alignment for Auto-regressive PDE Foundation Models","version":2},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-15T21:06:23.017655Z"},"links":{"cited_paper":"/paper/1811.12231","citing_paper":"/paper/2505.10930"},"observation_digest":"sha256:0803dc2c7c4318e6703276464eabc0f819683c1b13cd1e0bc2309041ada4761e","observation_id":"5fda1873-3b75-44cb-b377-f1578de5df9b","resolution":{"observed_at":"2026-08-15T21:06:23.017655Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.08895","last_updated":"2021-05-17T03:12:33Z","snapshot_observed_at":"2026-08-14T20:53:04.124337Z","submitted_at":"2020-10-18T00:34:21Z","title":"Fourier Neural Operator for Parametric Partial Differential Equations","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.08895","snapshot_observed_at":"2026-08-15T21:06:23.042432Z","title":"Fourier neural operator for parametric partial differential equa- tions.arXiv preprint arXiv:2010.08895, 2020b","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2505.10930","last_updated":"2025-05-31T03:05:23Z","snapshot_observed_at":"2026-08-15T20:58:40.579359Z","submitted_at":"2025-05-16T07:08:47Z","title":"Physics-informed Temporal Alignment for Auto-regressive PDE Foundation Models","version":2},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-15T21:06:23.042432Z"},"links":{"cited_paper":"/paper/2010.08895","citing_paper":"/paper/2505.10930"},"observation_digest":"sha256:212505a27451f451fc8043aa3264fb5b19d632ab80dc803e6cfb87e3f251185b","observation_id":"711f8783-c170-4710-856d-4d51c04ce4bc","resolution":{"observed_at":"2026-08-15T21:06:23.042432Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.09110","last_updated":"2025-08-22T20:31:51Z","snapshot_observed_at":"2026-08-15T05:10:26.759523Z","submitted_at":"2024-03-14T05:17:39Z","title":"SINDy-RL: Interpretable and Efficient Model-Based Reinforcement Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.09110","snapshot_observed_at":"2026-08-15T21:06:23.120983Z","title":"N., and Brunton, S","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.10930","last_updated":"2025-05-31T03:05:23Z","snapshot_observed_at":"2026-08-15T20:58:40.579359Z","submitted_at":"2025-05-16T07:08:47Z","title":"Physics-informed Temporal Alignment for Auto-regressive PDE Foundation Models","version":2},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-15T21:06:23.120983Z"},"links":{"cited_paper":"/paper/2403.09110","citing_paper":"/paper/2505.10930"},"observation_digest":"sha256:68938df3efdda2bbf890d22db11ccee7c6304c19636d0c2b46ba16d214e82cef","observation_id":"b6aeb57e-822f-4496-bfcb-a7f06e89d8ad","resolution":{"observed_at":"2026-08-15T21:06:23.120983Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2209.15616","last_updated":"2022-11-15T23:07:10Z","snapshot_observed_at":"2026-08-13T23:59:33.714743Z","submitted_at":"2022-09-30T17:40:05Z","title":"Towards Multi-spatiotemporal-scale Generalized PDE Modeling","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2209.15616","snapshot_observed_at":"2026-08-15T21:06:23.024969Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.10930","last_updated":"2025-05-31T03:05:23Z","snapshot_observed_at":"2026-08-15T20:58:40.579359Z","submitted_at":"2025-05-16T07:08:47Z","title":"Physics-informed Temporal Alignment for Auto-regressive PDE Foundation Models","version":2},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-15T21:06:23.024969Z"},"links":{"cited_paper":"/paper/2209.15616","citing_paper":"/paper/2505.10930"},"observation_digest":"sha256:4f23f0aea746b95db6675eaea6da1605e8cad4848f91eea44aa4e939d95755e0","observation_id":"7ee89f25-e3fd-4196-a4f2-e8f1630bcf7a","resolution":{"observed_at":"2026-08-15T21:06:23.024969Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.05987","last_updated":"2024-12-25T10:13:28Z","snapshot_observed_at":"2026-08-14T17:11:59.532006Z","submitted_at":"2024-05-08T14:15:51Z","title":"Physics-Enhanced Machine Learning: a position paper for dynamical systems investigations","version":3},"cited_work":{"arxiv_id":"2405.05987","doi":null,"metadata_source":"pith","pith_arxiv_id":"2405.05987","snapshot_observed_at":"2026-08-15T21:06:23.712316Z","title":"Physics-Enhanced Machine Learning: a position paper for dynamical systems investigations","venue":"cs.LG","work_id":"35daf85a-9e14-4092-9c50-5769ce5fbd1f","year":2024},"citing_paper":{"arxiv_id":"2505.10930","last_updated":"2025-05-31T03:05:23Z","snapshot_observed_at":"2026-08-15T20:58:40.579359Z","submitted_at":"2025-05-16T07:08:47Z","title":"Physics-informed Temporal Alignment for Auto-regressive PDE Foundation Models","version":2},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-15T21:06:23.010276Z"},"links":{"cited_paper":"/paper/2405.05987","citing_paper":"/paper/2505.10930"},"observation_digest":"sha256:4edccaccb44d974851c2d10415ed30e558211aa028e9e203db9b1bafd58cba13","observation_id":"1687997c-5a08-44d6-9ee9-75305ba31ed7","resolution":{"observed_at":"2026-08-15T21:06:23.716108Z","resolver_source":"local_arxiv","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":"1801.06146","last_updated":"2018-05-23T09:23:47Z","snapshot_observed_at":"2026-08-14T19:54:00.470999Z","submitted_at":"2018-01-18T17:54:52Z","title":"Universal Language Model Fine-tuning for Text Classification","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1801.06146","snapshot_observed_at":"2026-08-15T21:06:23.035440Z","title":"and Ruder, S","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.10930","last_updated":"2025-05-31T03:05:23Z","snapshot_observed_at":"2026-08-15T20:58:40.579359Z","submitted_at":"2025-05-16T07:08:47Z","title":"Physics-informed Temporal Alignment for Auto-regressive PDE Foundation Models","version":2},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-15T21:06:23.035440Z"},"links":{"cited_paper":"/paper/1801.06146","citing_paper":"/paper/2505.10930"},"observation_digest":"sha256:047eaea01db1b3b049e9cb133e96af201d238656541d236055c715d130b986a0","observation_id":"edd9db8d-912c-4326-9651-c8759008ad22","resolution":{"observed_at":"2026-08-15T21:06:23.035440Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.16014","last_updated":"2025-05-29T06:25:04Z","snapshot_observed_at":"2026-08-13T04:10:42.581564Z","submitted_at":"2024-02-25T07:19:01Z","title":"OmniArch: Building Foundation Model For Scientific Computing","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.16014","snapshot_observed_at":"2026-08-15T21:06:23.006477Z","title":"Omniarch: Building the foun- dation model for scientific computing.arXiv preprint arXiv:2402.16014,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.10930","last_updated":"2025-05-31T03:05:23Z","snapshot_observed_at":"2026-08-15T20:58:40.579359Z","submitted_at":"2025-05-16T07:08:47Z","title":"Physics-informed Temporal Alignment for Auto-regressive PDE Foundation Models","version":2},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-15T21:06:23.006477Z"},"links":{"cited_paper":"/paper/2402.16014","citing_paper":"/paper/2505.10930"},"observation_digest":"sha256:f9b542621b00caabc1be29507cc9b7eec2d3c54c221ed7a726e9ef8e6e868416","observation_id":"83f83ba2-5017-4047-b385-e62d9f32e0c0","resolution":{"observed_at":"2026-08-15T21:06:23.006477Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.11752","last_updated":"2025-05-15T14:08:49Z","snapshot_observed_at":"2026-08-16T02:42:56.383367Z","submitted_at":"2024-05-20T03:26:58Z","title":"Towards Foundation Model for Chemical Reactor Modeling: Meta-Learning with Physics-Informed Adaptation","version":3},"cited_work":{"arxiv_id":"2405.11752","doi":null,"metadata_source":"pith","pith_arxiv_id":"2405.11752","snapshot_observed_at":"2026-08-15T21:06:23.330413Z","title":"Towards Foundation Model for Chemical Reactor Modeling: Meta-Learning with Physics-Informed Adaptation","venue":"cs.CE","work_id":"6613e540-822c-4795-8644-081bb78deb7f","year":2024},"citing_paper":{"arxiv_id":"2505.10930","last_updated":"2025-05-31T03:05:23Z","snapshot_observed_at":"2026-08-15T20:58:40.579359Z","submitted_at":"2025-05-16T07:08:47Z","title":"Physics-informed Temporal Alignment for Auto-regressive PDE Foundation Models","version":2},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-15T21:06:23.089284Z"},"links":{"cited_paper":"/paper/2405.11752","citing_paper":"/paper/2505.10930"},"observation_digest":"sha256:46bc993877df910c66f0002ed7350695890bd2b84d20b971172dab547f6e97d9","observation_id":"e520395a-d750-4480-bb80-cee43496ced6","resolution":{"observed_at":"2026-08-15T21:06:23.334309Z","resolver_source":"local_arxiv","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"}}],"paper":{"arxiv_id":"2505.10930","last_updated":"2025-05-31T03:05:23Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-15T20:58:40.579359Z","submitted_at":"2025-05-16T07:08:47Z","title":"Physics-informed Temporal Alignment for Auto-regressive PDE Foundation Models"},"reference_resolution":{"displayed":41,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":30,"verified_exact":7,"verified_fuzzy":4},"total_outbound_references":41},"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 16 August 2026, this Paper Citation Record lists 41 of 41 outbound references and 0 inbound Pith citation observations for arXiv:2505.10930."}