{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XOEPLDEHTGTHIAISFVJGILUJQK","short_pith_number":"pith:XOEPLDEH","schema_version":"1.0","canonical_sha256":"bb88f58c8799a67401122d52642e8982bf5860245f5eda48f7bca461592a7fc2","source":{"kind":"arxiv","id":"2407.19000","version":2},"attestation_state":"computed","paper":{"title":"Reinforcement learning for anisotropic p-adaptation and error estimation in high-order solvers","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG","physics.comp-ph"],"primary_cat":"physics.flu-dyn","authors_text":"David Huergo, Eduardo Jan\\'e, Esteban Ferrer, Gonzalo Rubio, Mart\\'in de Frutos, Oscar A. Marino","submitted_at":"2024-07-26T17:55:23Z","abstract_excerpt":"We present a novel approach to automate and optimize anisotropic p-adaptation in high-order h/p solvers using Reinforcement Learning (RL). The dynamic RL adaptation uses the evolving solution to adjust the high-order polynomials. We develop an offline training approach, decoupled from the main solver, which shows minimal overcost when performing simulations. In addition, we derive an inexpensive RL-based error estimation approach that enables the quantification of local discretization errors. The proposed methodology is agnostic to both the computational mesh and the partial differential equat"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2407.19000","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"physics.flu-dyn","submitted_at":"2024-07-26T17:55:23Z","cross_cats_sorted":["cs.LG","physics.comp-ph"],"title_canon_sha256":"04a478f3290c0b5227d5981863fd62df0edc042d2d8b60a6ff11fe4d07f1d7ca","abstract_canon_sha256":"9bafd6c5661dc395eda1e727e1e6265fb44db53576a9a9a3cbfe2296b8ca3176"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:15:35.351241Z","signature_b64":"OPwc/U1LkOEurW4L7myHRqXC9SYNkWFJtvN1mq0EwF/0eZd0OxOWzdGYkL8fVvy3I4p73gsG+z3ew3GZ/gldBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb88f58c8799a67401122d52642e8982bf5860245f5eda48f7bca461592a7fc2","last_reissued_at":"2026-07-05T09:15:35.350739Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:15:35.350739Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement learning for anisotropic p-adaptation and error estimation in high-order solvers","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG","physics.comp-ph"],"primary_cat":"physics.flu-dyn","authors_text":"David Huergo, Eduardo Jan\\'e, Esteban Ferrer, Gonzalo Rubio, Mart\\'in de Frutos, Oscar A. Marino","submitted_at":"2024-07-26T17:55:23Z","abstract_excerpt":"We present a novel approach to automate and optimize anisotropic p-adaptation in high-order h/p solvers using Reinforcement Learning (RL). The dynamic RL adaptation uses the evolving solution to adjust the high-order polynomials. We develop an offline training approach, decoupled from the main solver, which shows minimal overcost when performing simulations. In addition, we derive an inexpensive RL-based error estimation approach that enables the quantification of local discretization errors. The proposed methodology is agnostic to both the computational mesh and the partial differential equat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.19000","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2407.19000/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2407.19000","created_at":"2026-07-05T09:15:35.350799+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.19000v2","created_at":"2026-07-05T09:15:35.350799+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.19000","created_at":"2026-07-05T09:15:35.350799+00:00"},{"alias_kind":"pith_short_12","alias_value":"XOEPLDEHTGTH","created_at":"2026-07-05T09:15:35.350799+00:00"},{"alias_kind":"pith_short_16","alias_value":"XOEPLDEHTGTHIAIS","created_at":"2026-07-05T09:15:35.350799+00:00"},{"alias_kind":"pith_short_8","alias_value":"XOEPLDEH","created_at":"2026-07-05T09:15:35.350799+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.02634","citing_title":"Transfer learning-enhanced deep reinforcement learning for aerodynamic airfoil optimisation subject to structural constraints","ref_index":40,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XOEPLDEHTGTHIAISFVJGILUJQK","json":"https://pith.science/pith/XOEPLDEHTGTHIAISFVJGILUJQK.json","graph_json":"https://pith.science/api/pith-number/XOEPLDEHTGTHIAISFVJGILUJQK/graph.json","events_json":"https://pith.science/api/pith-number/XOEPLDEHTGTHIAISFVJGILUJQK/events.json","paper":"https://pith.science/paper/XOEPLDEH"},"agent_actions":{"view_html":"https://pith.science/pith/XOEPLDEHTGTHIAISFVJGILUJQK","download_json":"https://pith.science/pith/XOEPLDEHTGTHIAISFVJGILUJQK.json","view_paper":"https://pith.science/paper/XOEPLDEH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.19000&json=true","fetch_graph":"https://pith.science/api/pith-number/XOEPLDEHTGTHIAISFVJGILUJQK/graph.json","fetch_events":"https://pith.science/api/pith-number/XOEPLDEHTGTHIAISFVJGILUJQK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XOEPLDEHTGTHIAISFVJGILUJQK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XOEPLDEHTGTHIAISFVJGILUJQK/action/storage_attestation","attest_author":"https://pith.science/pith/XOEPLDEHTGTHIAISFVJGILUJQK/action/author_attestation","sign_citation":"https://pith.science/pith/XOEPLDEHTGTHIAISFVJGILUJQK/action/citation_signature","submit_replication":"https://pith.science/pith/XOEPLDEHTGTHIAISFVJGILUJQK/action/replication_record"}},"created_at":"2026-07-05T09:15:35.350799+00:00","updated_at":"2026-07-05T09:15:35.350799+00:00"}