{"as_of":"2026-08-08T07:03:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:eb7c75850cce42452fb27ae53da1948570aeed008b35b7a1d3adf2c01ecafa49","coverage":[{"denominator":124,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":100,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-02T02:48:56.887214Z","state":"measured"},{"denominator":100,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":100,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2607.14233/citation-record","integrity":"/paper/2607.14233/integrity","json":"/paper/2607.14233/citation-record.json","paper":"/paper/2607.14233"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T02:48:47.817580Z","title":"How to initialize your network? robust initialization for weightnorm & resnets","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:47.817580Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:37c8b6264bf9f50f3ddef47cffd2f6ecbd3c2892e0a8b3d559691f993057ea72","observation_id":"9dd6c96b-e4ed-49a7-a7d0-d12e6ea219ad","resolution":{"observed_at":"2026-08-02T02:48:47.817580Z","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":"2026-08-02T02:48:47.978350Z","title":"Hypernetwork-based meta-learning for low-rank physics-informed neural networks","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:47.978350Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:d8cc2491f59bd988cdea3d497692ed038d366bcae3bc764cf5ca1b8d6b19338a","observation_id":"52a26cf2-26ae-447f-80e7-98e1cb7a2bb6","resolution":{"observed_at":"2026-08-02T02:48:47.978350Z","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":"2026-08-02T02:48:48.067417Z","title":"Scientific machine learning through physics--informed neural networks: Where we are and what’s next","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:48.067417Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:06ec4098d33514819643939415c2d49b373c6c175a812f957a816972048df0b4","observation_id":"2ba84097-5547-4ce9-8a9f-9ae565b70fc1","resolution":{"observed_at":"2026-08-02T02:48:48.067417Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.05624","last_updated":"2022-06-07T07:37:30Z","snapshot_observed_at":"2026-07-06T12:27:29.223870Z","submitted_at":"2022-01-14T19:05:44Z","title":"Scientific Machine Learning through Physics-Informed Neural Networks: Where we are and What's next","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.05624","snapshot_observed_at":"2026-08-02T02:48:48.181668Z","title":"Scientific machine learning through physics-informed neural networks: Where we are and what's next, 2022 b","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:48.181668Z"},"links":{"cited_paper":"/paper/2201.05624","citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:b09d7b72dc90dba62a107297cf2533600c35f1aab3ce97cd6af5e084face29ce","observation_id":"feae99e8-2ffd-4797-a187-84ff59c9eabc","resolution":{"observed_at":"2026-08-02T02:48:48.181668Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2207.02338","last_updated":"2023-06-07T20:19:38Z","snapshot_observed_at":"2026-07-31T01:25:04.092091Z","submitted_at":"2022-07-05T22:09:40Z","title":"Mitigating Propagation Failures in Physics-informed Neural Networks using Retain-Resample-Release (R3) Sampling","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2207.02338","snapshot_observed_at":"2026-08-02T02:48:48.300518Z","title":"Mitigating propagation failures in physics-informed neural networks using retain-resample-release (r3) sampling, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:48.300518Z"},"links":{"cited_paper":"/paper/2207.02338","citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:194ef4525aacb92a2e91fe88a647a311ab3290cbdb6ad4306b499ad3e1c93e80","observation_id":"4c363a8f-068d-404d-b51e-b0db72153ec5","resolution":{"observed_at":"2026-08-02T02:48:48.300518Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1703.03400","last_updated":"2017-07-18T16:45:29Z","snapshot_observed_at":"2026-08-06T12:29:00.148818Z","submitted_at":"2017-03-09T18:58:03Z","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1703.03400","snapshot_observed_at":"2026-08-02T02:48:48.388571Z","title":"Model- Agnostic Meta - Learning for Fast Adaptation of Deep Networks , July 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:48.388571Z"},"links":{"cited_paper":"/paper/1703.03400","citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:19af41a6b97509a27474f556ad4b0f1a2135925c3019ac2fe1d9c21617ec2abd","observation_id":"a758b184-f45d-49ef-850c-1ede7ecedc1b","resolution":{"observed_at":"2026-08-02T02:48:48.388571Z","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":"2026-08-02T02:48:48.477817Z","title":"Deep learning versus kernel learning: an empirical study of loss landscape geometry and the time evolution of the neural tangent kernel","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:48.477817Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:7b281ec38d3330f5e9d45f01f30bc2a301917363169caf4fe8c752ee22725f1f","observation_id":"a3ec071d-fd38-4c7d-92a3-0cfd07a72c37","resolution":{"observed_at":"2026-08-02T02:48:48.477817Z","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":"2026-08-02T02:48:48.559231Z","title":"Flat minima","venue":null,"work_id":null,"year":1997},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:48.559231Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:52e96a757fa5834d18d118d78551b2dd4f08d514cde954625bea2b151f3fca35","observation_id":"e060d9a5-7c8b-47d9-bdce-6798cdfab03f","resolution":{"observed_at":"2026-08-02T02:48:48.559231Z","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":"2026-08-02T02:48:48.670989Z","title":"Dpm: A novel training method for physics-informed neural networks in extrapolation","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:48.670989Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:99e655c70d03043f11ce06adf76013550d30c9db245eaaf39bdb4141751666c6","observation_id":"1d42d971-00a7-4b27-a91f-fc01f18b5559","resolution":{"observed_at":"2026-08-02T02:48:48.670989Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.01050","last_updated":"2021-11-11T18:47:07Z","snapshot_observed_at":"2026-07-06T11:43:47.468200Z","submitted_at":"2021-09-02T16:06:45Z","title":"Characterizing possible failure modes in physics-informed neural networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.01050","snapshot_observed_at":"2026-08-02T02:48:48.786974Z","title":"Krishnapriyan, Amir Gholami, Shandian Zhe, Robert M","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:48.786974Z"},"links":{"cited_paper":"/paper/2109.01050","citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:88e59f23c8d9e4c6e6481487d70bb34ee5749b380e98c1142a33347b98445ea0","observation_id":"912def68-4edf-462d-901c-46bfc13b421e","resolution":{"observed_at":"2026-08-02T02:48:48.786974Z","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":"2026-08-02T02:48:48.965204Z","title":"Physics informed neural networks for fluid flow analysis with repetitive parameter initialization","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:48.965204Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:ef768b1d4305fa5c6b20478e4361d3e633b89f6001fa9d739db6ea8807c57da8","observation_id":"70a14a70-7003-4f60-8ea0-2d018e89bb22","resolution":{"observed_at":"2026-08-02T02:48:48.965204Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2211.01604","last_updated":"2022-11-03T06:17:52Z","snapshot_observed_at":"2026-08-05T18:43:28.763425Z","submitted_at":"2022-11-03T06:17:52Z","title":"Meta-PDE: Learning to Solve PDEs Quickly Without a Mesh","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2211.01604","snapshot_observed_at":"2026-08-02T02:48:49.135005Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:49.135005Z"},"links":{"cited_paper":"/paper/2211.01604","citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:03dd662151bc7308a70128809256f424353d2deecd786a4e9e0218fae9c77c1f","observation_id":"dfdb8771-6634-4ebf-b8af-bda2adacafcb","resolution":{"observed_at":"2026-08-02T02:48:49.135005Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1711.10566","last_updated":"2017-11-28T21:29:35Z","snapshot_observed_at":"2026-07-06T06:11:42.746828Z","submitted_at":"2017-11-28T21:29:35Z","title":"Physics Informed Deep Learning (Part II): Data-driven Discovery of Nonlinear Partial Differential Equations","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.10566","snapshot_observed_at":"2026-08-02T02:48:49.222232Z","title":"Physics informed deep learning (part ii): Data-driven discovery of nonlinear partial differential equations, 2017 a","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:49.222232Z"},"links":{"cited_paper":"/paper/1711.10566","citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:ccd89cf4e8e2760d1dd3cc422166b42a16e41992bf2e41fa9de9749a566e2e76","observation_id":"0eb52880-f5b4-440b-acf4-ef92839e3887","resolution":{"observed_at":"2026-08-02T02:48:49.222232Z","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":"2026-08-02T02:48:49.467616Z","title":"Numerical gaussian processes for time-dependent and nonlinear partial differential equations","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:49.467616Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:2ccfbc63e7232e97015b6655f786db8c00253e179bde55657573200fd21e8c2d","observation_id":"82cc9c50-c82a-426d-843b-ffe75da54c3f","resolution":{"observed_at":"2026-08-02T02:48:49.467616Z","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":"2026-08-02T02:48:49.587464Z","title":"Meta-learning with implicit gradients","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:49.587464Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:109de487ce033b35f878641fe6b9ac25d3b9ca874939e2838c6f2071f46c48c2","observation_id":"f26bbd17-ffde-48e6-828d-227a9040d46d","resolution":{"observed_at":"2026-08-02T02:48:49.587464Z","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":"2026-08-02T02:48:49.888640Z","title":"Dats: Difficulty-aware task sampler for meta-learning physics-informed neural networks","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:49.888640Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:a7d9288b3d7d2ead37afa3a53908db8ceaa304122e135fda5f12b5d99f60ce71","observation_id":"687bba97-f02e-4a16-8723-2c3e8fbf8d48","resolution":{"observed_at":"2026-08-02T02:48:49.888640Z","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":"2026-08-02T02:48:50.008423Z","title":"Zippered polygon meshes from range images","venue":null,"work_id":null,"year":1994},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:50.008423Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:208ef866dc4896939cbf3878572016d194117e0cd77ccb112df310bde6cac0f8","observation_id":"04a492e3-99ed-4956-ae03-24b919a5bf47","resolution":{"observed_at":"2026-08-02T02:48:50.008423Z","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":"2026-08-02T02:48:50.135377Z","title":"Understanding and mitigating gradient flow pathologies in physics-informed neural networks","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:50.135377Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:93ae9271211c17a1b1694a4b6e06074200a3dd66781204072cf17ecaead77876","observation_id":"41fe49cc-e0d0-4260-8325-22c289261313","resolution":{"observed_at":"2026-08-02T02:48:50.135377Z","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":"2026-08-02T02:48:50.248495Z","title":"On the eigenvector bias of fourier feature networks: From regression to solving multi-scale pdes with physics-informed neural networks","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:50.248495Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:4d34d58ba3805250dbe483ecb8a96b2490b93269e30985a85b93723834be9183","observation_id":"99356bda-d23d-4ae1-9238-e47d2019d67a","resolution":{"observed_at":"2026-08-02T02:48:50.248495Z","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":"2026-08-02T02:48:50.424760Z","title":"When and why pinns fail to train: A neural tangent kernel perspective","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:50.424760Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:4f60387f1a8352f1324e032ac8670ea0731551740360c6e3ee0ca77102d5826e","observation_id":"166e61e2-9fe8-4a8c-9c92-0b2244e8c571","resolution":{"observed_at":"2026-08-02T02:48:50.424760Z","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":"2026-08-02T02:48:50.496079Z","title":"Gradient alignment in physics-informed neural networks: A second-order optimization perspective, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:50.496079Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:622758bb7c47e6cd6c144ef0fb663e578314c30586a909aa7a14f2204e9a6dc5","observation_id":"5f802826-db4b-4d38-b0e9-b61dd41d179e","resolution":{"observed_at":"2026-08-02T02:48:50.496079Z","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":"2026-08-02T02:48:50.619182Z","title":"A comprehensive study of non-adaptive and residual-based adaptive sampling for physics-informed neural networks","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:50.619182Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:91ac185a23e71f68828fb38261d75345b3a42d86f268d7d5820525cf6f867a4f","observation_id":"121e186a-4d39-4795-a7f3-17442897976e","resolution":{"observed_at":"2026-08-02T02:48:50.619182Z","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":"2026-08-02T02:48:50.754235Z","title":"Mean field residual networks: On the edge of chaos","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:50.754235Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:83ed3865e0fd28f58aed123526e026cb7e8c0a4e29f4f15daa3b31e833aaefa8","observation_id":"a14b54d0-a1e9-4ce8-a20e-ce27955d882a","resolution":{"observed_at":"2026-08-02T02:48:50.754235Z","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":"2026-08-02T02:48:50.833603Z","title":"Communication, Simulation, and Intelligent Agents: Implications of Personal Intelligent Machines for Medical Education","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:50.833603Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:b90a5126a97e933e65c0ef8f5291485709d94d29cd004600a39c0c0ad4d72190","observation_id":"8ac90603-95fb-403c-983f-32022ee31e5d","resolution":{"observed_at":"2026-08-02T02:48:50.833603Z","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":"2026-08-02T02:48:50.919200Z","title":"Classification Problem Solving","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:50.919200Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:d7a9d0bf2c3ca4804d4cd6f637a9d203041cf7aca2887a3f14d20735a7967161","observation_id":"c354054f-6d0c-46ae-8cc4-339ccba45fdf","resolution":{"observed_at":"2026-08-02T02:48:50.919200Z","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":"2026-08-02T02:48:51.001427Z","title":", title =","venue":null,"work_id":null,"year":1980},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:51.001427Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:1f015286ef2fffd7806d26d119f701057ec3ffe0feeadd0ecffc7c11cb4576e8","observation_id":"f2d70799-6ead-462f-a015-e8fb8f98bfc9","resolution":{"observed_at":"2026-08-02T02:48:51.001427Z","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":"2026-08-02T02:48:51.109878Z","title":"New Ways to Make Microcircuits Smaller---Duplicate Entry","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:51.109878Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:2ab89fe727ddba6d80f90be7f22f312e0e87fa89fc2758453045f755fd1ff67d","observation_id":"e9b818be-fd56-4d2d-bb23-a31a89ef6394","resolution":{"observed_at":"2026-08-02T02:48:51.109878Z","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":"2026-08-02T02:48:51.171126Z","title":"Clancey and Glenn Rennels , abstract =","venue":null,"work_id":null,"year":1984},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:51.171126Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:d2a4bf35b32afc7c93bb2298ce73c15a56b5e277ad9430b898b73bbd962df56e","observation_id":"5d2de18e-77e7-4a5b-ba4b-5c4c507d81b1","resolution":{"observed_at":"2026-08-02T02:48:51.171126Z","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":"2026-08-02T02:48:51.218605Z","title":"and Rennels, Glenn R","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:51.218605Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:03cb6070cd0ea0fade99dbb5909e0a44ae3b3aa4cd2177e6a56ab5ac583320e6","observation_id":"0595e063-04c9-4c39-b144-1e452f175ac0","resolution":{"observed_at":"2026-08-02T02:48:51.218605Z","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":"2026-08-02T02:48:51.306121Z","title":"Poligon: A System for Parallel Problem Solving","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:51.306121Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:048590845e7e9fad0645bf5e0e6ce8347f96c85c69685bd6bf14f44b97e41ab9","observation_id":"0be9d0b1-4954-4232-95c3-ccb635f54c23","resolution":{"observed_at":"2026-08-02T02:48:51.306121Z","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":"2026-08-02T02:48:51.374602Z","title":"Transfer of Rule-Based Expertise through a Tutorial Dialogue","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:51.374602Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:d7ff15789d2477fc0d8f9f55095aa2ab9d33a7f9b68ff06345c81868fd0a0a95","observation_id":"86514036-3c1c-4b9e-9f35-876d94daea0d","resolution":{"observed_at":"2026-08-02T02:48:51.374602Z","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":"2026-08-02T02:48:51.469007Z","title":"The Engineering of Qualitative Models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:51.469007Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:3f4f3f694f6c76a4f783a94a9c0be3c0c03acd3447ccade001c899cae073ac0a","observation_id":"517d59ed-5d22-4a61-ba8a-fb7db71c80cb","resolution":{"observed_at":"2026-08-02T02:48:51.469007Z","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":"2026-08-02T02:48:51.571740Z","title":"2017 , eprint=","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:51.571740Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:ba80ac214ad6bb1e815ec82350be0b2b5c529a68a9a4d9a8d1e113db50b93067","observation_id":"ee7b6a48-720d-42e4-aa04-f91ee07253fd","resolution":{"observed_at":"2026-08-02T02:48:51.571740Z","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":"2026-08-02T02:48:51.641074Z","title":"Pluto: The 'Other' Red Planet","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:51.641074Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:c50461a73fe85af26f22bd0e8d1309672715cb78c38f4368f6ba174a38a1edc1","observation_id":"1928d495-01cc-412f-8fed-f6ff54dc0f86","resolution":{"observed_at":"2026-08-02T02:48:51.641074Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1711.10561","last_updated":"2017-11-28T21:21:59Z","snapshot_observed_at":"2026-07-06T06:11:42.746828Z","submitted_at":"2017-11-28T21:21:59Z","title":"Physics Informed Deep Learning (Part I): Data-driven Solutions of Nonlinear Partial Differential Equations","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.10561","snapshot_observed_at":"2026-08-02T02:48:51.733220Z","title":"arXiv preprint arXiv:1711.10561 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:51.733220Z"},"links":{"cited_paper":"/paper/1711.10561","citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:3fb0c995f287376ad50fdf69a62335cd12b8577b0e6e53397c02212801508efd","observation_id":"76a5c3a9-bc97-4536-b461-b460da467d57","resolution":{"observed_at":"2026-08-02T02:48:51.733220Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.07662","last_updated":"2024-04-11T11:51:46Z","snapshot_observed_at":"2026-07-06T17:58:47.786948Z","submitted_at":"2024-04-11T11:51:46Z","title":"PINNACLE: PINN Adaptive ColLocation and Experimental points selection","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.07662","snapshot_observed_at":"2026-08-02T02:48:51.785111Z","title":"arXiv preprint arXiv:2404.07662 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:51.785111Z"},"links":{"cited_paper":"/paper/2404.07662","citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:8b7036a458b35c93ac24e3529da813e266896c7ad282f423e12fd4c99fdbeedb","observation_id":"f210a63c-a0f0-492f-8ac9-987fd96910b2","resolution":{"observed_at":"2026-08-02T02:48:51.785111Z","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":"2026-08-02T02:48:51.838385Z","title":"Journal of Machine Learning Research , volume=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:51.838385Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:b430127a79b86cb16c9c2711a32ca0db3674b33170db1f8f0b3e2e60cb57cfd1","observation_id":"031cdcf4-0856-4b70-99bc-88b137d56a38","resolution":{"observed_at":"2026-08-02T02:48:51.838385Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.15989","last_updated":"2024-05-01T20:57:12Z","snapshot_observed_at":"2026-07-06T17:49:36.858294Z","submitted_at":"2024-03-24T02:54:46Z","title":"Knowledge-guided Machine Learning: Current Trends and Future Prospects","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.15989","snapshot_observed_at":"2026-08-02T02:48:51.920546Z","title":"arXiv preprint arXiv:2403.15989 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:51.920546Z"},"links":{"cited_paper":"/paper/2403.15989","citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:9978b9533a410c7cf23754f14575b3565f9c7b53be4224815382d4ee7f31e9da","observation_id":"02d6ed21-24b6-487a-9393-ae1e037d5464","resolution":{"observed_at":"2026-08-02T02:48:51.920546Z","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":"2026-08-02T02:48:51.982910Z","title":"and Zwart, Jacob A","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:51.982910Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:610d7be231f802be1d63ab26adc1349be4d10696c0c8531f8df900a48d404f2c","observation_id":"7f235c89-1496-48b4-bbff-59b74e7ee8bd","resolution":{"observed_at":"2026-08-02T02:48:51.982910Z","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":"2026-08-02T02:48:52.052372Z","title":"Knowledge Guided Machine Learning , pages=","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:52.052372Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:84595ad140492ddbd31382e88f33a716967248ffaf73d4ce8dfcc9d9dec72319","observation_id":"95f8ed8e-152b-4aa9-9cb1-f4f1caca404d","resolution":{"observed_at":"2026-08-02T02:48:52.052372Z","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":"2026-08-02T02:48:52.137055Z","title":"and Steinbach, Michael and Banerjee, Arindam and Ganguly, Auroop and Shekhar, Shashi and Samatova, Nagiza and Kumar, Vipin , journal=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:52.137055Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:11ce360076389fb28583a31bb322b6cc215023039eb3c4ede4b84fc8cfca1bc6","observation_id":"f7c11a82-4de2-494c-ade4-3f6db02f3659","resolution":{"observed_at":"2026-08-02T02:48:52.137055Z","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":"2026-08-02T02:48:52.215118Z","title":"2022 , publisher=","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:52.215118Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:c02791a946c09a5fc41e0b469b3299531ef17873e3e1144d3a2734e9b13fb2b2","observation_id":"5ae9eec9-0dd5-40c9-a5f3-f7d5a9bc5fce","resolution":{"observed_at":"2026-08-02T02:48:52.215118Z","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":"2026-08-02T02:48:52.292264Z","title":", volume =","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:52.292264Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:075698d91b2813d2a3c2c0fdf6469897e7887750a55fc4c4d157193c533164ed","observation_id":"8208584d-d976-4572-8e28-17c6d11fc9bd","resolution":{"observed_at":"2026-08-02T02:48:52.292264Z","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":"2026-08-02T02:48:52.373224Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:52.373224Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:95a71ea9ee9d74ed95654ba8675220d2d9b41ce52d521b6aac31bb789d6dc9e7","observation_id":"b94d2328-4471-463c-b66c-ad52ce10f8d5","resolution":{"observed_at":"2026-08-02T02:48:52.373224Z","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":"2026-08-02T02:48:52.448488Z","title":"Publication manual of the American Psychological Association , isbn =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:52.448488Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:3670c3f308e19056e988ab43935bf7e239ad844804235ee1207e26fc965561a4","observation_id":"80b61d39-1813-4fb6-b7b1-a47b6b6a3229","resolution":{"observed_at":"2026-08-02T02:48:52.448488Z","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":"2026-08-02T02:48:52.525863Z","title":"The Manual of Scientific Style , url =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:52.525863Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:572711de6fe7bdb6837f49a8c2daa3976d0b2e66e37e785bfabbd1617bd3d1c7","observation_id":"dc8b4b23-8e3e-493a-b710-6b1378e60cd3","resolution":{"observed_at":"2026-08-02T02:48:52.525863Z","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":"2026-08-02T02:48:52.609323Z","title":"Crisis Management in the Food and Drinks Industry , url =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:52.609323Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:6e54f788735541828e197ddcf353d3ec067614a09171e0bf2c98d6453b4b4ca6","observation_id":"76fb7e11-ec2a-4ca0-bfca-f23f0872765d","resolution":{"observed_at":"2026-08-02T02:48:52.609323Z","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":"2026-08-02T02:48:52.681454Z","title":"Incorporating Prior Domain Knowledge into Deep Neural Networks , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":56,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:52.681454Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:8d9f6a2cfe766bd6faa333119d1ad066d430dd35c09dbca05ac9f7a7c2374cc3","observation_id":"bb96be00-04c9-4e52-aaed-b58ba5057c48","resolution":{"observed_at":"2026-08-02T02:48:52.681454Z","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":"2026-08-02T02:48:52.742512Z","title":"and Gholami, Amir and Zhe, Shandian and Kirby, Robert M","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":57,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:52.742512Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:cc39f2f9f9a218fa63f2bef75e560c0bbb755a0ee1754a85f22a17e640cc32fa","observation_id":"9f1fc3dc-8931-470f-a3e2-4a8e1c3ce487","resolution":{"observed_at":"2026-08-02T02:48:52.742512Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1703.03400","last_updated":"2017-07-18T16:45:29Z","snapshot_observed_at":"2026-08-06T12:29:00.148818Z","submitted_at":"2017-03-09T18:58:03Z","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1703.03400","snapshot_observed_at":"2026-08-02T02:48:52.809437Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":58,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:52.809437Z"},"links":{"cited_paper":"/paper/1703.03400","citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:fadb1fc2cffbba5e71c6123d12ddb2558fee011e60452c59f5b51cc6b3c3842d","observation_id":"9d018cb3-116f-4f79-9c8d-97d2401dd372","resolution":{"observed_at":"2026-08-02T02:48:52.809437Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1611.01232","last_updated":"2017-04-04T19:36:14Z","snapshot_observed_at":"2026-07-06T05:17:20.642708Z","submitted_at":"2016-11-04T00:44:32Z","title":"Deep Information Propagation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1611.01232","snapshot_observed_at":"2026-08-02T02:48:52.886634Z","title":"arXiv preprint arXiv:1611.01232 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":59,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:52.886634Z"},"links":{"cited_paper":"/paper/1611.01232","citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:5bfe89cae6cbae9e95292cd452d92fe932d3f8b2917219341eb1b51cb269cfc5","observation_id":"0842dda1-9592-4d32-9138-4e92b25f50ff","resolution":{"observed_at":"2026-08-02T02:48:52.886634Z","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":"2026-08-02T02:48:52.961852Z","title":"Journal of computational physics , volume=","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":60,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:52.961852Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:f0b27b0138d119efd358a302ceabc3c0dfcb4eb2fd0364585231a835f54377b5","observation_id":"f4671bac-6314-430c-9214-3e1f9212b42c","resolution":{"observed_at":"2026-08-02T02:48:52.961852Z","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":"2026-08-02T02:48:53.036089Z","title":"Journal of Computational Physics , volume=","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":61,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:53.036089Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:d6d5e2b941929df34624e237382db14a0adbd4dcf5cd910bef5ee41f1070efed","observation_id":"803f3840-c735-4928-a5f2-ef9c1dfec7ef","resolution":{"observed_at":"2026-08-02T02:48:53.036089Z","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":"2026-08-02T02:48:53.111752Z","title":"SIAM Journal on Scientific Computing , volume=","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":62,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:53.111752Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:221053fb9fa2d4cd32e639eadd657c82dcbc4b98a2d7c486f7873abeefa3c9de","observation_id":"a316edab-4dfb-4cd6-85ce-74feb67b2d8c","resolution":{"observed_at":"2026-08-02T02:48:53.111752Z","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":"2026-08-02T02:48:53.213560Z","title":"2023 , eprint=","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":63,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:53.213560Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:d5e304ae0be21c8ddc73678ad5636c9bf35fdb6e608aea9f23dc7442125e4be3","observation_id":"0faac986-005a-4ab0-9642-aa5ab9fb0a2f","resolution":{"observed_at":"2026-08-02T02:48:53.213560Z","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":"2026-08-02T02:48:53.404320Z","title":"Meta-learning PINN loss functions , volume=","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":65,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:53.404320Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:c2fe58a5f15b8ab1922e4de217815eb3652f48a87a0582c8eb4170eef03e1432","observation_id":"60597387-8d24-4732-b3f8-4828942a36f9","resolution":{"observed_at":"2026-08-02T02:48:53.404320Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.1007/s00521-022-07294-2","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"A novel meta-learning initialization method for physics-informed neural networks , volume =","venue":"Neural Computing and Applications","work_id":"819b0c70-17b3-40e3-9c92-d0fa46c8dd3a","year":null},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":66,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:53.520470Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:7ddf287f20979f2803a6b36b38fe6252728f10cda11c9c93547fd86956bb837c","observation_id":"f85a1e74-9901-45ee-91d5-ca323e0063e9","resolution":{"observed_at":"2026-08-02T02:53:30.441064Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+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":"2026-08-02T02:48:53.615220Z","title":", urldate =","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":67,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:53.615220Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:36e9bfdb24257297c23117ed72ce891d8576dfaa5ea62b3abed3768cc54fce64","observation_id":"23f81936-1913-41b8-8050-f60cff831f17","resolution":{"observed_at":"2026-08-02T02:48:53.615220Z","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":"2026-08-02T02:48:53.671949Z","title":"On the convergence of physics informed neural networks for linear second-order elliptic and parabolic type","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":68,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:53.671949Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:c936be7133f28af084e4d58581096b9686a533f5c80223e29ed4c6f20a2d6863","observation_id":"468bf253-e948-4e3e-9e23-4015fae67bd4","resolution":{"observed_at":"2026-08-02T02:48:53.671949Z","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":"2026-08-02T02:48:53.757049Z","title":"Gradient-enhanced physics-informed neural networks for forward and inverse","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":69,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:53.757049Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:3c51d6799b08f0520777e420789f8fc771f54bef84cb0a3b03e14b096c8547ba","observation_id":"d6b0923b-6817-42dc-8760-c126457abea5","resolution":{"observed_at":"2026-08-02T02:48:53.757049Z","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":"2026-08-02T02:48:53.843571Z","title":"2017 , eprint=","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":70,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:53.843571Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:e686d27fd85af246631c264b5826587d64e70bd98ca034d9dd81266c6d92911b","observation_id":"f2e5b446-e93b-4e7d-8bc9-85dc743070a5","resolution":{"observed_at":"2026-08-02T02:48:53.843571Z","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":"2026-08-02T02:48:53.939553Z","title":"Advances in Neural Information Processing Systems , volume=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":71,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:53.939553Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:57134948df2a32a7aee5bf9d41c41e8e9275003060006b46d66976d5b743045f","observation_id":"9f12f91d-8a64-421a-b6cf-5f1a07ef8541","resolution":{"observed_at":"2026-08-02T02:48:53.939553Z","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":"2026-08-02T02:48:54.019987Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":72,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:54.019987Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:0fb73e105fb218029125a7bfd7bf804921fc519e49479617d5ebe18a37cb824a","observation_id":"0ec7c6a4-1bc5-4d52-aa7d-c2f575be4715","resolution":{"observed_at":"2026-08-02T02:48:54.019987Z","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":"2026-08-02T02:48:54.188114Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":73,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:54.188114Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:b815a1fe8c66466bfdd38a74da0a3b71334522a7ed3f6c87f42ce6b053192dbc","observation_id":"76a2c832-68f9-440a-bdab-283bdb7740e1","resolution":{"observed_at":"2026-08-02T02:48:54.188114Z","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":"2026-08-02T02:48:54.290457Z","title":"and Toscano, Juan Diego and Stergiopulos, Nikolaos and Karniadakis, George Em , urldate =","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":74,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:54.290457Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:38c68f8ea5f4ed2d289922beda6b6481ba81c2ccb45e005a5c95df4ef57e4a86","observation_id":"290bee44-d681-4b74-8f5e-89e529b1bedd","resolution":{"observed_at":"2026-08-02T02:48:54.290457Z","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":"2026-08-02T02:48:54.397258Z","title":"and Tegmark, Max , urldate =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":75,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:54.397258Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:5f9f29c3b9899dfe7a41bd4faacb17a91f69c54ed4280a5940a6f92a46a1118c","observation_id":"6f16d8f7-7775-4f38-a01b-6fc52d2a8401","resolution":{"observed_at":"2026-08-02T02:48:54.397258Z","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":"2026-08-02T02:48:54.501473Z","title":"2022 , eprint=","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":76,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:54.501473Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:ce54e07d2e1c46571bc4cf205fbf6a1736f004b2298e6963d4cbad7f9bb5ac31","observation_id":"ac0af712-acca-49d5-a48f-50e9de44e914","resolution":{"observed_at":"2026-08-02T02:48:54.501473Z","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":"2026-08-02T02:48:54.572286Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":77,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:54.572286Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:bf759f5f102861b1eb634c6ebfde6c015610c8e076946a60b2080bdf0bc2a394","observation_id":"2dabded1-3901-4821-8e1c-8a88e756b972","resolution":{"observed_at":"2026-08-02T02:48:54.572286Z","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":"2026-08-02T02:48:54.642033Z","title":"Proceedings of the AAAI Conference on Artificial Intelligence , volume=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":78,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:54.642033Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:f51037c999c65791d37283a30fb30bf894dee603fb7b31bc3ce10a5f502514a2","observation_id":"7335beba-5ca9-4ec4-9c23-3f529543a043","resolution":{"observed_at":"2026-08-02T02:48:54.642033Z","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":"2026-08-02T02:48:54.803226Z","title":"2024 , eprint=","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":79,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:54.803226Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:c0581df86012fcff685dcc5cffc474163977c9eeb52602f039f4c8d6cdda3528","observation_id":"97293701-c145-4960-a786-c49e39aa9ad0","resolution":{"observed_at":"2026-08-02T02:48:54.803226Z","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":"2026-08-02T02:48:54.877281Z","title":"Advances in neural information processing systems , volume=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":80,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:54.877281Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:fc8d50190c1a595a5bcb181b43228019c1f475c7ae3cdd025c5e96f94218d3b9","observation_id":"67aa923d-6ce8-4dae-8463-cc40aaf513cb","resolution":{"observed_at":"2026-08-02T02:48:54.877281Z","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":"2026-08-02T02:48:54.944887Z","title":", urldate =","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":81,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:54.944887Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:47892bed01bd9926d263087bf534f1ff1bfa55c524f176aba521c82a6c8abdc3","observation_id":"a5130b11-f480-47b0-bb19-2d1f8979a927","resolution":{"observed_at":"2026-08-02T02:48:54.944887Z","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":"2026-08-02T02:48:55.043884Z","title":"Advances in neural information processing systems , volume=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":82,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:55.043884Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:0fafe07b325af8b293d64e59ba29e19785c8c9ea9c6ef15adca8887622074bfe","observation_id":"746a2c70-bc13-49ee-bec2-ae994534f228","resolution":{"observed_at":"2026-08-02T02:48:55.043884Z","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":"2026-08-02T02:48:55.121593Z","title":"2017 , eprint=","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":83,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:55.121593Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:c1c15f7211ebebf8b9d65f5e941f11f201ae530422f0017fcfd6a0a6a668c688","observation_id":"18e2be49-eb14-49a3-a0da-725fd420368d","resolution":{"observed_at":"2026-08-02T02:48:55.121593Z","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":"2026-08-02T02:48:55.174402Z","title":"Meta-learning of Physics-informed Neural Networks for Efficiently Solving Newly Given","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":84,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:55.174402Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:d816b616d1955f6bdb64aa1dd5cad53936d1f30b4343bea72b405614e13fe547","observation_id":"12db0513-a870-45f6-8d29-749a72aa22f9","resolution":{"observed_at":"2026-08-02T02:48:55.174402Z","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":"2026-08-02T02:48:55.246474Z","title":"2016 , eprint=","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":85,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:55.246474Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:e6b2d8cad0b47aefc6d233e67aed767c1f8172cf062caad59f2fb2c41dc2a931","observation_id":"b779259a-1814-48e7-9598-9a7549a87471","resolution":{"observed_at":"2026-08-02T02:48:55.246474Z","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":"2026-08-02T02:48:55.304613Z","title":"Mean Field Theory and its application to deep learning , abstract =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":86,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:55.304613Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:6cea1dcca99c559f08e83fd5726dfe97164bfd9da256afe2c0592164812103a6","observation_id":"00fc2a1b-12a4-4a9a-96a9-848733a21127","resolution":{"observed_at":"2026-08-02T02:48:55.304613Z","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":"2026-08-02T02:48:55.406480Z","title":"Book III, Lemma V, Case , volume=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":87,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:55.406480Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:9d7d46b2e3c8c95a29eb2d2e186418a0a44ebad9dacfcfce544202c39a4fcdf5","observation_id":"caff7f1b-b711-43a6-9190-473bb3d5dc1a","resolution":{"observed_at":"2026-08-02T02:48:55.406480Z","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":"2026-08-02T02:48:55.477106Z","title":"Reviews of Modern Physics , volume=","venue":null,"work_id":null,"year":1951},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":88,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:55.477106Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:bae43a437005d5f6d9a29ab3e9fd1d1e384d1864dfcff13f182d77e8a991e0d0","observation_id":"351297b3-9b2d-4c36-9815-fc870a918cdd","resolution":{"observed_at":"2026-08-02T02:48:55.477106Z","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":"2026-08-02T02:48:55.587332Z","title":"SIAM Journal on Scientific Computing , volume=","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":89,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:55.587332Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:f22c394c17c1cb82524d1e08281877e08f71d060b0168a97211b9e87532cdad7","observation_id":"7c3cf5c9-e6b7-414e-bbf1-9c2d792f119b","resolution":{"observed_at":"2026-08-02T02:48:55.587332Z","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":"2026-08-02T02:48:55.646956Z","title":"Computer Methods in Applied Mechanics and Engineering , volume=","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":90,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:55.646956Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:d9d748489ce1eb87036159d01f2878c8426cc8f12c7b1fc17e322372b7bc8e0e","observation_id":"98a6f1db-014f-4d99-a28c-8af83624ee0e","resolution":{"observed_at":"2026-08-02T02:48:55.646956Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.07404","last_updated":"2022-03-14T18:08:18Z","snapshot_observed_at":"2026-07-06T12:47:48.418460Z","submitted_at":"2022-03-14T18:08:18Z","title":"Respecting causality is all you need for training physics-informed neural networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.07404","snapshot_observed_at":"2026-08-02T02:48:55.699909Z","title":"arXiv preprint arXiv:2203.07404 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":91,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:55.699909Z"},"links":{"cited_paper":"/paper/2203.07404","citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:4eb47a82a900e87f9f0ba29b9e864fe91120af863f7827c6543f80f49cb569da","observation_id":"c5555979-9dfc-4882-8449-ecb8643674a1","resolution":{"observed_at":"2026-08-02T02:48:55.699909Z","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":"2026-08-02T02:48:55.764537Z","title":"Optics express , volume=","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":92,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:55.764537Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:7ed44a4e87ee6de048ef322b81113814f1344b72e3096d0e15c4295d6f9c6854","observation_id":"0f90a2df-6df3-4cd3-9a69-75cbd86f5777","resolution":{"observed_at":"2026-08-02T02:48:55.764537Z","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":"2026-08-02T02:48:55.841347Z","title":"Journal of Computational Physics , volume=","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":93,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:55.841347Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:cce66b798fcb77495c80ccfc95f761bdb96d3f875eaa071367813e6630c0bee1","observation_id":"f1e882ec-0033-42a8-9cf8-bb7fb15ca38e","resolution":{"observed_at":"2026-08-02T02:48:55.841347Z","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":"2026-08-02T02:48:55.907758Z","title":"Neurocomputing , volume=","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":94,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:55.907758Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:966fd893ca18791ed6723f5299e95ce41f0926bc8a35c8cef3ddd3f225c86402","observation_id":"d4d40e78-1de6-47c8-8d7b-09726a657a62","resolution":{"observed_at":"2026-08-02T02:48:55.907758Z","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":"2026-08-02T02:48:55.976004Z","title":"Computer Methods in Applied Mechanics and Engineering , volume=","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":95,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:55.976004Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:6e9fc04dae22a1ffad3ff5147bfd4a26ac9377a9ab7a6f426ade9a12951bf2ca","observation_id":"ff775d8c-e69b-4514-9ae8-1eba26a84490","resolution":{"observed_at":"2026-08-02T02:48:55.976004Z","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":"2026-08-02T02:48:56.028895Z","title":"Journal of Computational Physics , volume=","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":96,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:56.028895Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:d86f681fe6283b9556915e69721ba74e77f0ae0a72f5e081b44923779f0078e8","observation_id":"730032a4-ba79-4a1f-8762-35cb9a38bea1","resolution":{"observed_at":"2026-08-02T02:48:56.028895Z","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":"2026-08-02T02:48:56.102840Z","title":"Journal of Scientific Computing , volume=","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":97,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:56.102840Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:cf140cf644f7a95f25cb8dc8f0343c42a5d329bcef4e0a5031f47ab6e7c1b0d9","observation_id":"a7127a57-536b-4672-8646-0b161ca63077","resolution":{"observed_at":"2026-08-02T02:48:56.102840Z","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":"2026-08-02T02:48:56.168000Z","title":"Ihlenburg and I","venue":null,"work_id":null,"year":1995},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":98,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:56.168000Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:c4308e2daa7934380ed395bbad8d984ce98a0876f06bb66a1b9374e6c623bec3","observation_id":"6d841d1e-8252-43e5-8054-c334b8be9591","resolution":{"observed_at":"2026-08-02T02:48:56.168000Z","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":"2026-08-02T02:48:56.200983Z","title":"2006 , publisher=","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":99,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:56.200983Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:1e4204ff1f444d5525271dfc41886237ac4f5f6c4ea7838d1843e362f06a4287","observation_id":"22b31231-b9fb-4470-96bb-4548a3e274a8","resolution":{"observed_at":"2026-08-02T02:48:56.200983Z","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":"2026-08-02T02:48:56.268044Z","title":"Advances in neural information processing systems , volume=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":100,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:56.268044Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:59ad5f18a05f3df3f7a629fbd5a0d7b4cc05a3327c835407e4c5383d08889511","observation_id":"b43da72d-9d63-4a27-83bd-43ad80e32c31","resolution":{"observed_at":"2026-08-02T02:48:56.268044Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1710.11622","last_updated":"2018-02-14T19:16:20Z","snapshot_observed_at":"2026-07-06T06:07:05.119814Z","submitted_at":"2017-10-31T17:55:42Z","title":"Meta-Learning and Universality: Deep Representations and Gradient Descent can Approximate any Learning Algorithm","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.11622","snapshot_observed_at":"2026-08-02T02:48:56.333752Z","title":"arXiv preprint arXiv:1710.11622 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":101,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:56.333752Z"},"links":{"cited_paper":"/paper/1710.11622","citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:192caa899f5482642c9988f90173f8aae17412b059b488906e699503064e6d29","observation_id":"87195938-b215-4c35-aaba-f621abe26517","resolution":{"observed_at":"2026-08-02T02:48:56.333752Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1803.02999","last_updated":"2018-10-22T16:11:14Z","snapshot_observed_at":"2026-08-05T12:53:31.632675Z","submitted_at":"2018-03-08T08:29:38Z","title":"On First-Order Meta-Learning Algorithms","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1803.02999","snapshot_observed_at":"2026-08-02T02:48:56.392764Z","title":"arXiv preprint arXiv:1803.02999 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":102,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:56.392764Z"},"links":{"cited_paper":"/paper/1803.02999","citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:4a0ee3411f5b19184ce6a31fcbfdc3bc939808ff9532e6cc403d69eac48fb518","observation_id":"8c74a724-75e5-4195-91e4-2ce3e8a136e4","resolution":{"observed_at":"2026-08-02T02:48:56.392764Z","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":"2026-08-02T02:48:56.459893Z","title":"Proceedings of the thirteenth international conference on artificial intelligence and statistics , pages=","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":103,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:56.459893Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:d5ceecd444397eda9f87ef3b6174ebcd61d1bb5793302c079f16e5c0d92df411","observation_id":"55068356-05df-4b73-b50a-477022e11e58","resolution":{"observed_at":"2026-08-02T02:48:56.459893Z","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":"2026-08-02T02:48:56.530746Z","title":"Advances in neural information processing systems , volume=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":104,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:56.530746Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:70bdd7125f44f374130461766010e7c6cb8da64957429c91a4b1944b61e6fc36","observation_id":"55a5933d-396d-4597-a6c0-112ac72fe4d9","resolution":{"observed_at":"2026-08-02T02:48:56.530746Z","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":"2026-08-02T02:48:56.598683Z","title":"Conference on learning theory , pages=","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":105,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:56.598683Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:f7fe0832e45bfe127d9ed56615c3d83c300e3a3b4528c16a749e7be80a4b2285","observation_id":"4b3e9edf-9818-4d9d-8dfb-717c9f801acc","resolution":{"observed_at":"2026-08-02T02:48:56.598683Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1509.08101","last_updated":"2015-09-29T13:44:37Z","snapshot_observed_at":"2026-08-03T18:23:00.117102Z","submitted_at":"2015-09-27T15:26:58Z","title":"Representation Benefits of Deep Feedforward Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1509.08101","snapshot_observed_at":"2026-08-02T02:48:56.663253Z","title":"arXiv preprint arXiv:1509.08101 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":106,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:56.663253Z"},"links":{"cited_paper":"/paper/1509.08101","citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:b58e693bf603b190aed99a0d42d6386b9902b743f669824ebb7e5fdcabe158d8","observation_id":"9b9a9e38-0e38-4c2c-b320-d3f9da8a1a17","resolution":{"observed_at":"2026-08-02T02:48:56.663253Z","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":"2026-08-02T02:48:56.742465Z","title":"Theoretical and Applied Mechanics Letters , volume=","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":107,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:56.742465Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:588f7461e25f5bf6b85aa32ff7a386f5f103a3c19b733bb2e964b824a9fde7c0","observation_id":"eb3de6bd-c9be-4a6d-9de0-7ce0e67742c0","resolution":{"observed_at":"2026-08-02T02:48:56.742465Z","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":"2026-08-02T02:48:56.799453Z","title":"Computational Mechanics , volume=","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":108,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:56.799453Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:ca65158b934799e864cce15ad3ba6a6fdbbc7643bb19e6bb08754f8ea6f9298b","observation_id":"d6c3c792-e3b2-4589-9e02-a28560becbfb","resolution":{"observed_at":"2026-08-02T02:48:56.799453Z","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":"2026-08-02T02:48:56.887214Z","title":"Frontiers in Physics , volume=","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks","version":1},"reference_index":109,"source":"arxiv_source","source_observed_at":"2026-08-02T02:48:56.887214Z"},"links":{"citing_paper":"/paper/2607.14233"},"observation_digest":"sha256:8e9aeb439dbac1508b3f5f081b2a08a82fb008372ace4e268aa6df8a000a7d8c","observation_id":"a818069f-a910-4290-97b2-4277ee7a88ef","resolution":{"observed_at":"2026-08-02T02:48:56.887214Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.14233","last_updated":"2026-07-15T18:00:44Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-06T20:47:19.460200Z","submitted_at":"2026-07-15T18:00:44Z","title":"LIGO-PINN: Learned Initialization via Gated Optimization to Alleviate Convergence Failures in Physics Informed Neural Networks"},"reference_resolution":{"displayed":100,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":99,"verified_exact":1,"verified_fuzzy":0},"total_outbound_references":124},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 100 of 124 outbound references and 0 inbound Pith citation observations for arXiv:2607.14233."}