{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:7RH4QSP7UW2FR3NPILVNQUKO3C","short_pith_number":"pith:7RH4QSP7","schema_version":"1.0","canonical_sha256":"fc4fc849ffa5b458edaf42ead8514ed8888a93512b433e97e6347ecd1a660950","source":{"kind":"arxiv","id":"2205.04611","version":1},"attestation_state":"computed","paper":{"title":"Optimizing a DIscrete Loss (ODIL) to solve forward and inverse problems for partial differential equations using machine learning tools","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.NA","physics.comp-ph"],"primary_cat":"math.NA","authors_text":"Petr Karnakov, Petros Koumoutsakos, Sergey Litvinov","submitted_at":"2022-05-10T01:08:17Z","abstract_excerpt":"We introduce the Optimizing a Discrete Loss (ODIL) framework for the numerical solution of Partial Differential Equations (PDE) using machine learning tools. The framework formulates numerical methods as a minimization of discrete residuals that are solved using gradient descent and Newton's methods. We demonstrate the value of this approach on equations that may have missing parameters or where no sufficient data is available to form a well-posed initial-value problem. The framework is presented for mesh based discretizations of PDEs and inherits their accuracy, convergence, and conservation "},"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":"2205.04611","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"math.NA","submitted_at":"2022-05-10T01:08:17Z","cross_cats_sorted":["cs.NA","physics.comp-ph"],"title_canon_sha256":"0b6ddf88720589ed47e6b3bf4c9c3810a36ca9b41dca5574b2b9a7810d4f8976","abstract_canon_sha256":"3c4b0f436ea39c3eee6a4501da8beba124181467aa2c2d450926628fa1b026c1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:35:34.303816Z","signature_b64":"Iuo1xjUQ04JiNgxVj/aUp4/WYI4YIY8v9ugMD4Os8EwRYaeEfAj3TVHWvpe7bW1sGcmYkdzIHy6uL6P9jFI9Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc4fc849ffa5b458edaf42ead8514ed8888a93512b433e97e6347ecd1a660950","last_reissued_at":"2026-07-05T07:35:34.303406Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:35:34.303406Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimizing a DIscrete Loss (ODIL) to solve forward and inverse problems for partial differential equations using machine learning tools","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.NA","physics.comp-ph"],"primary_cat":"math.NA","authors_text":"Petr Karnakov, Petros Koumoutsakos, Sergey Litvinov","submitted_at":"2022-05-10T01:08:17Z","abstract_excerpt":"We introduce the Optimizing a Discrete Loss (ODIL) framework for the numerical solution of Partial Differential Equations (PDE) using machine learning tools. The framework formulates numerical methods as a minimization of discrete residuals that are solved using gradient descent and Newton's methods. We demonstrate the value of this approach on equations that may have missing parameters or where no sufficient data is available to form a well-posed initial-value problem. The framework is presented for mesh based discretizations of PDEs and inherits their accuracy, convergence, and conservation "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.04611","kind":"arxiv","version":1},"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/2205.04611/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":"2205.04611","created_at":"2026-07-05T07:35:34.303468+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.04611v1","created_at":"2026-07-05T07:35:34.303468+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.04611","created_at":"2026-07-05T07:35:34.303468+00:00"},{"alias_kind":"pith_short_12","alias_value":"7RH4QSP7UW2F","created_at":"2026-07-05T07:35:34.303468+00:00"},{"alias_kind":"pith_short_16","alias_value":"7RH4QSP7UW2FR3NP","created_at":"2026-07-05T07:35:34.303468+00:00"},{"alias_kind":"pith_short_8","alias_value":"7RH4QSP7","created_at":"2026-07-05T07:35:34.303468+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7RH4QSP7UW2FR3NPILVNQUKO3C","json":"https://pith.science/pith/7RH4QSP7UW2FR3NPILVNQUKO3C.json","graph_json":"https://pith.science/api/pith-number/7RH4QSP7UW2FR3NPILVNQUKO3C/graph.json","events_json":"https://pith.science/api/pith-number/7RH4QSP7UW2FR3NPILVNQUKO3C/events.json","paper":"https://pith.science/paper/7RH4QSP7"},"agent_actions":{"view_html":"https://pith.science/pith/7RH4QSP7UW2FR3NPILVNQUKO3C","download_json":"https://pith.science/pith/7RH4QSP7UW2FR3NPILVNQUKO3C.json","view_paper":"https://pith.science/paper/7RH4QSP7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.04611&json=true","fetch_graph":"https://pith.science/api/pith-number/7RH4QSP7UW2FR3NPILVNQUKO3C/graph.json","fetch_events":"https://pith.science/api/pith-number/7RH4QSP7UW2FR3NPILVNQUKO3C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7RH4QSP7UW2FR3NPILVNQUKO3C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7RH4QSP7UW2FR3NPILVNQUKO3C/action/storage_attestation","attest_author":"https://pith.science/pith/7RH4QSP7UW2FR3NPILVNQUKO3C/action/author_attestation","sign_citation":"https://pith.science/pith/7RH4QSP7UW2FR3NPILVNQUKO3C/action/citation_signature","submit_replication":"https://pith.science/pith/7RH4QSP7UW2FR3NPILVNQUKO3C/action/replication_record"}},"created_at":"2026-07-05T07:35:34.303468+00:00","updated_at":"2026-07-05T07:35:34.303468+00:00"}