{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MENK2YFCBJKLRHOFV3RPOQLUCY","short_pith_number":"pith:MENK2YFC","schema_version":"1.0","canonical_sha256":"611aad60a20a54b89dc5aee2f74174163013b56dad511bf2a61140195ca67a58","source":{"kind":"arxiv","id":"2507.21269","version":1},"attestation_state":"computed","paper":{"title":"Numerical PDE solvers outperform neural PDE solvers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.NA"],"primary_cat":"math.NA","authors_text":"Adam Oberman, Guillaume Rabusseau, Michael Rizvi-Martel, Patrick Chatain","submitted_at":"2025-07-28T18:50:37Z","abstract_excerpt":"We present DeepFDM, a differentiable finite-difference framework for learning spatially varying coefficients in time-dependent partial differential equations (PDEs). By embedding a classical forward-Euler discretization into a convolutional architecture, DeepFDM enforces stability and first-order convergence via CFL-compliant coefficient parameterizations. Model weights correspond directly to PDE coefficients, yielding an interpretable inverse-problem formulation. We evaluate DeepFDM on a benchmark suite of scalar PDEs: advection, diffusion, advection-diffusion, reaction-diffusion and inhomoge"},"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":"2507.21269","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.NA","submitted_at":"2025-07-28T18:50:37Z","cross_cats_sorted":["cs.LG","cs.NA"],"title_canon_sha256":"5b015a131bbaceb6c14f988f5943be87155674c6f45d6f8922ce4eb2f9eec52b","abstract_canon_sha256":"f72d3e996a318bd1098312e07ad865deaf33aa36f11208dd5d4d820661176a29"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:44:55.950554Z","signature_b64":"kvad+N4e0FPudpoHYM5xsVg03gORovKPPkJ40xb+dozfSD+C1V8mlqPejFXKAgnSQUIs49uhscbFUmIaEA4VAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"611aad60a20a54b89dc5aee2f74174163013b56dad511bf2a61140195ca67a58","last_reissued_at":"2026-07-05T11:44:55.950101Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:44:55.950101Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Numerical PDE solvers outperform neural PDE solvers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.NA"],"primary_cat":"math.NA","authors_text":"Adam Oberman, Guillaume Rabusseau, Michael Rizvi-Martel, Patrick Chatain","submitted_at":"2025-07-28T18:50:37Z","abstract_excerpt":"We present DeepFDM, a differentiable finite-difference framework for learning spatially varying coefficients in time-dependent partial differential equations (PDEs). By embedding a classical forward-Euler discretization into a convolutional architecture, DeepFDM enforces stability and first-order convergence via CFL-compliant coefficient parameterizations. Model weights correspond directly to PDE coefficients, yielding an interpretable inverse-problem formulation. We evaluate DeepFDM on a benchmark suite of scalar PDEs: advection, diffusion, advection-diffusion, reaction-diffusion and inhomoge"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.21269","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/2507.21269/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":"2507.21269","created_at":"2026-07-05T11:44:55.950156+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.21269v1","created_at":"2026-07-05T11:44:55.950156+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.21269","created_at":"2026-07-05T11:44:55.950156+00:00"},{"alias_kind":"pith_short_12","alias_value":"MENK2YFCBJKL","created_at":"2026-07-05T11:44:55.950156+00:00"},{"alias_kind":"pith_short_16","alias_value":"MENK2YFCBJKLRHOF","created_at":"2026-07-05T11:44:55.950156+00:00"},{"alias_kind":"pith_short_8","alias_value":"MENK2YFC","created_at":"2026-07-05T11:44:55.950156+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01749","citing_title":"Identifiability Limits of Physics-Informed Inference for Spatial Stochastic Dynamics from Static Snapshots","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MENK2YFCBJKLRHOFV3RPOQLUCY","json":"https://pith.science/pith/MENK2YFCBJKLRHOFV3RPOQLUCY.json","graph_json":"https://pith.science/api/pith-number/MENK2YFCBJKLRHOFV3RPOQLUCY/graph.json","events_json":"https://pith.science/api/pith-number/MENK2YFCBJKLRHOFV3RPOQLUCY/events.json","paper":"https://pith.science/paper/MENK2YFC"},"agent_actions":{"view_html":"https://pith.science/pith/MENK2YFCBJKLRHOFV3RPOQLUCY","download_json":"https://pith.science/pith/MENK2YFCBJKLRHOFV3RPOQLUCY.json","view_paper":"https://pith.science/paper/MENK2YFC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.21269&json=true","fetch_graph":"https://pith.science/api/pith-number/MENK2YFCBJKLRHOFV3RPOQLUCY/graph.json","fetch_events":"https://pith.science/api/pith-number/MENK2YFCBJKLRHOFV3RPOQLUCY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MENK2YFCBJKLRHOFV3RPOQLUCY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MENK2YFCBJKLRHOFV3RPOQLUCY/action/storage_attestation","attest_author":"https://pith.science/pith/MENK2YFCBJKLRHOFV3RPOQLUCY/action/author_attestation","sign_citation":"https://pith.science/pith/MENK2YFCBJKLRHOFV3RPOQLUCY/action/citation_signature","submit_replication":"https://pith.science/pith/MENK2YFCBJKLRHOFV3RPOQLUCY/action/replication_record"}},"created_at":"2026-07-05T11:44:55.950156+00:00","updated_at":"2026-07-05T11:44:55.950156+00:00"}