{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CH7ZNEM7ATASMFIJBQN7X3IG3M","short_pith_number":"pith:CH7ZNEM7","schema_version":"1.0","canonical_sha256":"11ff96919f04c12615090c1bfbed06db1bac318c18cbd779238930e853d64ea4","source":{"kind":"arxiv","id":"2601.11428","version":7},"attestation_state":"computed","paper":{"title":"Diagnosing Failure Modes of Neural Operators Across Diverse PDE Families","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Strong in-distribution accuracy does not reliably predict robustness in neural PDE solvers across architectures and equation families.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Lennon Shikhman","submitted_at":"2026-01-16T16:47:44Z","abstract_excerpt":"Neural PDE solvers are increasingly used as learned surrogates for families of partial differential equations, where the key machine learning challenge is not only interpolation on a fixed benchmark distribution but generalization under structured shifts in coefficients, boundary conditions, discretization, and rollout horizon. Yet evaluation is still often dominated by in-distribution test error, making robustness difficult to assess. We introduce a standardized stress-testing framework for neural PDE solvers under deployment-relevant shift. We instantiate it on three representative architect"},"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":"2601.11428","kind":"arxiv","version":7},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-01-16T16:47:44Z","cross_cats_sorted":[],"title_canon_sha256":"67c39cac47e5ab0157918302a8403d1c6748be8e982662a4c9c3cbafa3d16c81","abstract_canon_sha256":"755fe80eca0eb1bce0a74a920e378c724f0d81f45736f2c1915e3b43be420adb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:02:30.869532Z","signature_b64":"PZp0OM0cbW83vw2U29zZgbZPMpCQGc8s7qcMvP97meMcwFr19aAbHPcFQt2olhSu0wbZY8hoGWhSbGi9nWtzAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"11ff96919f04c12615090c1bfbed06db1bac318c18cbd779238930e853d64ea4","last_reissued_at":"2026-05-26T01:02:30.868568Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:02:30.868568Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diagnosing Failure Modes of Neural Operators Across Diverse PDE Families","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Strong in-distribution accuracy does not reliably predict robustness in neural PDE solvers across architectures and equation families.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Lennon Shikhman","submitted_at":"2026-01-16T16:47:44Z","abstract_excerpt":"Neural PDE solvers are increasingly used as learned surrogates for families of partial differential equations, where the key machine learning challenge is not only interpolation on a fixed benchmark distribution but generalization under structured shifts in coefficients, boundary conditions, discretization, and rollout horizon. Yet evaluation is still often dominated by in-distribution test error, making robustness difficult to assess. We introduce a standardized stress-testing framework for neural PDE solvers under deployment-relevant shift. We instantiate it on three representative architect"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"strong in-distribution accuracy does not reliably predict robustness, and that failure patterns depend jointly on architecture and PDE family.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The chosen shifts in coefficients, boundary conditions, discretization, and rollout horizon, together with the five selected PDE families, are representative of deployment-relevant distribution shifts.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A new stress-testing framework reveals that in-distribution accuracy does not reliably predict robustness of neural operators across diverse PDE families and architectures.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Strong in-distribution accuracy does not reliably predict robustness in neural PDE solvers across architectures and equation families.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"220cc0c2c815c2d96d592fb4fae4f9f0db320b2ef6f7027a38ab099c60c6fda4"},"source":{"id":"2601.11428","kind":"arxiv","version":7},"verdict":{"id":"0b08e979-5530-48f0-9d97-d5ef6a929211","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T13:24:56.456710Z","strongest_claim":"strong in-distribution accuracy does not reliably predict robustness, and that failure patterns depend jointly on architecture and PDE family.","one_line_summary":"A new stress-testing framework reveals that in-distribution accuracy does not reliably predict robustness of neural operators across diverse PDE families and architectures.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The chosen shifts in coefficients, boundary conditions, discretization, and rollout horizon, together with the five selected PDE families, are representative of deployment-relevant distribution shifts.","pith_extraction_headline":"Strong in-distribution accuracy does not reliably predict robustness in neural PDE solvers across architectures and equation families."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2601.11428/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":"2601.11428","created_at":"2026-05-26T01:02:30.868696+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.11428v7","created_at":"2026-05-26T01:02:30.868696+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.11428","created_at":"2026-05-26T01:02:30.868696+00:00"},{"alias_kind":"pith_short_12","alias_value":"CH7ZNEM7ATAS","created_at":"2026-05-26T01:02:30.868696+00:00"},{"alias_kind":"pith_short_16","alias_value":"CH7ZNEM7ATASMFIJ","created_at":"2026-05-26T01:02:30.868696+00:00"},{"alias_kind":"pith_short_8","alias_value":"CH7ZNEM7","created_at":"2026-05-26T01:02:30.868696+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/CH7ZNEM7ATASMFIJBQN7X3IG3M","json":"https://pith.science/pith/CH7ZNEM7ATASMFIJBQN7X3IG3M.json","graph_json":"https://pith.science/api/pith-number/CH7ZNEM7ATASMFIJBQN7X3IG3M/graph.json","events_json":"https://pith.science/api/pith-number/CH7ZNEM7ATASMFIJBQN7X3IG3M/events.json","paper":"https://pith.science/paper/CH7ZNEM7"},"agent_actions":{"view_html":"https://pith.science/pith/CH7ZNEM7ATASMFIJBQN7X3IG3M","download_json":"https://pith.science/pith/CH7ZNEM7ATASMFIJBQN7X3IG3M.json","view_paper":"https://pith.science/paper/CH7ZNEM7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.11428&json=true","fetch_graph":"https://pith.science/api/pith-number/CH7ZNEM7ATASMFIJBQN7X3IG3M/graph.json","fetch_events":"https://pith.science/api/pith-number/CH7ZNEM7ATASMFIJBQN7X3IG3M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CH7ZNEM7ATASMFIJBQN7X3IG3M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CH7ZNEM7ATASMFIJBQN7X3IG3M/action/storage_attestation","attest_author":"https://pith.science/pith/CH7ZNEM7ATASMFIJBQN7X3IG3M/action/author_attestation","sign_citation":"https://pith.science/pith/CH7ZNEM7ATASMFIJBQN7X3IG3M/action/citation_signature","submit_replication":"https://pith.science/pith/CH7ZNEM7ATASMFIJBQN7X3IG3M/action/replication_record"}},"created_at":"2026-05-26T01:02:30.868696+00:00","updated_at":"2026-05-26T01:02:30.868696+00:00"}