{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:CH7ZNEM7ATASMFIJBQN7X3IG3M","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"755fe80eca0eb1bce0a74a920e378c724f0d81f45736f2c1915e3b43be420adb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-01-16T16:47:44Z","title_canon_sha256":"67c39cac47e5ab0157918302a8403d1c6748be8e982662a4c9c3cbafa3d16c81"},"schema_version":"1.0","source":{"id":"2601.11428","kind":"arxiv","version":7}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.11428","created_at":"2026-05-26T01:02:30Z"},{"alias_kind":"arxiv_version","alias_value":"2601.11428v7","created_at":"2026-05-26T01:02:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.11428","created_at":"2026-05-26T01:02:30Z"},{"alias_kind":"pith_short_12","alias_value":"CH7ZNEM7ATAS","created_at":"2026-05-26T01:02:30Z"},{"alias_kind":"pith_short_16","alias_value":"CH7ZNEM7ATASMFIJ","created_at":"2026-05-26T01:02:30Z"},{"alias_kind":"pith_short_8","alias_value":"CH7ZNEM7","created_at":"2026-05-26T01:02:30Z"}],"graph_snapshots":[{"event_id":"sha256:bbbb85a6133bca08032aedfd2a8d790f74aebdac66067e5936546c7a73291b92","target":"graph","created_at":"2026-05-26T01:02:30Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"strong in-distribution accuracy does not reliably predict robustness, and that failure patterns depend jointly on architecture and PDE family."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Strong in-distribution accuracy does not reliably predict robustness in neural PDE solvers across architectures and equation families."}],"snapshot_sha256":"220cc0c2c815c2d96d592fb4fae4f9f0db320b2ef6f7027a38ab099c60c6fda4"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2601.11428/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Lennon Shikhman","cross_cats":[],"headline":"Strong in-distribution accuracy does not reliably predict robustness in neural PDE solvers across architectures and equation families.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-01-16T16:47:44Z","title":"Diagnosing Failure Modes of Neural Operators Across Diverse PDE Families"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.11428","kind":"arxiv","version":7},"verdict":{"created_at":"2026-05-16T13:24:56.456710Z","id":"0b08e979-5530-48f0-9d97-d5ef6a929211","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"Strong in-distribution accuracy does not reliably predict robustness in neural PDE solvers across architectures and equation families.","strongest_claim":"strong in-distribution accuracy does not reliably predict robustness, and that failure patterns depend jointly on architecture and PDE family.","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."}},"verdict_id":"0b08e979-5530-48f0-9d97-d5ef6a929211"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:3b14dce30eea7a19e5864f6906152ad99f00552298a357017e74c8400e39175b","target":"record","created_at":"2026-05-26T01:02:30Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"755fe80eca0eb1bce0a74a920e378c724f0d81f45736f2c1915e3b43be420adb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-01-16T16:47:44Z","title_canon_sha256":"67c39cac47e5ab0157918302a8403d1c6748be8e982662a4c9c3cbafa3d16c81"},"schema_version":"1.0","source":{"id":"2601.11428","kind":"arxiv","version":7}},"canonical_sha256":"11ff96919f04c12615090c1bfbed06db1bac318c18cbd779238930e853d64ea4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"11ff96919f04c12615090c1bfbed06db1bac318c18cbd779238930e853d64ea4","first_computed_at":"2026-05-26T01:02:30.868568Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T01:02:30.868568Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PZp0OM0cbW83vw2U29zZgbZPMpCQGc8s7qcMvP97meMcwFr19aAbHPcFQt2olhSu0wbZY8hoGWhSbGi9nWtzAA==","signature_status":"signed_v1","signed_at":"2026-05-26T01:02:30.869532Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.11428","source_kind":"arxiv","source_version":7}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3b14dce30eea7a19e5864f6906152ad99f00552298a357017e74c8400e39175b","sha256:bbbb85a6133bca08032aedfd2a8d790f74aebdac66067e5936546c7a73291b92"],"state_sha256":"c5dfb126e7c38755fea88688c5e9e48f2305544f054ae4a83af14ac638c2dec4"}