{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:BVN5IRZVFKBJENI7CPF7626W7Y","short_pith_number":"pith:BVN5IRZV","canonical_record":{"source":{"id":"2604.23874","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.flu-dyn","submitted_at":"2026-04-26T20:36:12Z","cross_cats_sorted":["cs.LG","math.DS","physics.comp-ph","physics.geo-ph"],"title_canon_sha256":"c35c5c5d646255bb231d8df664d3ca782cd9db568a25ccb4991719f9e5b6d299","abstract_canon_sha256":"c1fe21d9096617c775c2b74a40b13e936bc80d4071e4535e21e4ae3a14ce96ff"},"schema_version":"1.0"},"canonical_sha256":"0d5bd447352a8292351f13cbff6bd6fe304bfa255af59da0c96649828cefb87b","source":{"kind":"arxiv","id":"2604.23874","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.23874","created_at":"2026-06-11T01:09:36Z"},{"alias_kind":"arxiv_version","alias_value":"2604.23874v3","created_at":"2026-06-11T01:09:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.23874","created_at":"2026-06-11T01:09:36Z"},{"alias_kind":"pith_short_12","alias_value":"BVN5IRZVFKBJ","created_at":"2026-06-11T01:09:36Z"},{"alias_kind":"pith_short_16","alias_value":"BVN5IRZVFKBJENI7","created_at":"2026-06-11T01:09:36Z"},{"alias_kind":"pith_short_8","alias_value":"BVN5IRZV","created_at":"2026-06-11T01:09:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:BVN5IRZVFKBJENI7CPF7626W7Y","target":"record","payload":{"canonical_record":{"source":{"id":"2604.23874","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.flu-dyn","submitted_at":"2026-04-26T20:36:12Z","cross_cats_sorted":["cs.LG","math.DS","physics.comp-ph","physics.geo-ph"],"title_canon_sha256":"c35c5c5d646255bb231d8df664d3ca782cd9db568a25ccb4991719f9e5b6d299","abstract_canon_sha256":"c1fe21d9096617c775c2b74a40b13e936bc80d4071e4535e21e4ae3a14ce96ff"},"schema_version":"1.0"},"canonical_sha256":"0d5bd447352a8292351f13cbff6bd6fe304bfa255af59da0c96649828cefb87b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:09:36.367661Z","signature_b64":"Egk5in+fgkrG8vkTn6MJK06AfUXTzq5j9ng5C2O3I3pN3oDJy10WfrgvhlTMo9/EPuHwnBDKZewKpBY2nqd3AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0d5bd447352a8292351f13cbff6bd6fe304bfa255af59da0c96649828cefb87b","last_reissued_at":"2026-06-11T01:09:36.366594Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:09:36.366594Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2604.23874","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-11T01:09:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CeOyvuWDvo5HTLdSyc5UmcWj1RyzdmFKlEC4hCv547HcRaSkjCTvmIjsOQo0Xi7MGjpchkG1gAZ3eAMQ6QC/AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T20:14:33.836853Z"},"content_sha256":"6b710e860ec9aa686de6e8ada38b8742264c4f043b281a368e978203419ca36d","schema_version":"1.0","event_id":"sha256:6b710e860ec9aa686de6e8ada38b8742264c4f043b281a368e978203419ca36d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:BVN5IRZVFKBJENI7CPF7626W7Y","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Learning of Solver-Aware Turbulence Closures from Nudged LES Dynamics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Nudging sparse DNS observations into LES lets neural networks learn stable turbulence closures without backpropagating through the solver.","cross_cats":["cs.LG","math.DS","physics.comp-ph","physics.geo-ph"],"primary_cat":"physics.flu-dyn","authors_text":"Ashwin Suriyanarayanan, Dibyajyoti Chakraborty, Romit Maulik","submitted_at":"2026-04-26T20:36:12Z","abstract_excerpt":"The differentiable physics paradigm may be leveraged as an a-posteriori approach for discovering turbulence closure models by embedding a neural network parameterization directly inside the solver and optimizing it given potentially sparse target data. This addresses a key limitation of a-priori learning where direct numerical simulation (DNS) data is used to approximate the subgrid stress with the assumption of a low-pass filter. Closures trained in this a-priori manner frequently lead to unstable deployments due to the mismatch between the assumed filter and the effect of numerical discretiz"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Our approach enables the deep learning model to successfully learn the required forcing to capture the ground-truth statistics while maintaining long term stability without needing adjoints or backpropagation through the solver. We train and evaluate the model's ability to adapt to different numerical and temporal schemes.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that nudging DNS data as sparse observations can effectively train closures that overcome the filter mismatch and numerical discretization issues without introducing new instabilities or requiring solver-specific adjustments.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Nudging enables a-priori training of stable neural network turbulence closures for LES that adapt to various numerical schemes without solver modifications or adjoints.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Nudging sparse DNS observations into LES lets neural networks learn stable turbulence closures without backpropagating through the solver.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"8bb1698d56281eda91086029e5af984b52732da0c6fc69032b497b5746b66996"},"source":{"id":"2604.23874","kind":"arxiv","version":3},"verdict":{"id":"870ed3e1-cdc3-492b-ba8b-d0091a884915","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-08T05:14:08.649297Z","strongest_claim":"Our approach enables the deep learning model to successfully learn the required forcing to capture the ground-truth statistics while maintaining long term stability without needing adjoints or backpropagation through the solver. We train and evaluate the model's ability to adapt to different numerical and temporal schemes.","one_line_summary":"Nudging enables a-priori training of stable neural network turbulence closures for LES that adapt to various numerical schemes without solver modifications or adjoints.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that nudging DNS data as sparse observations can effectively train closures that overcome the filter mismatch and numerical discretization issues without introducing new instabilities or requiring solver-specific adjustments.","pith_extraction_headline":"Nudging sparse DNS observations into LES lets neural networks learn stable turbulence closures without backpropagating through the solver."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.23874/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-21T07:43:03.518206Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T22:42:31.135914Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"b3f25169017ab1cb55a0ea8b817a5acf85d72d3340a40206d1d543b78a143ea1"},"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"},"verdict_id":"870ed3e1-cdc3-492b-ba8b-d0091a884915"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-11T01:09:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6GlJlEAornaVS53nuRFYO240vah3eh5uduYPCdxGpazrq08/nnVlasszIG4ZN7UVukR/Bwzu1AcVq+acGmfgAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T20:14:33.837621Z"},"content_sha256":"5632f86ba798bbd94ecaec50cd68d2311efa26b99ae1f489a936ec7ec825e495","schema_version":"1.0","event_id":"sha256:5632f86ba798bbd94ecaec50cd68d2311efa26b99ae1f489a936ec7ec825e495"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BVN5IRZVFKBJENI7CPF7626W7Y/bundle.json","state_url":"https://pith.science/pith/BVN5IRZVFKBJENI7CPF7626W7Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BVN5IRZVFKBJENI7CPF7626W7Y/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-05T20:14:33Z","links":{"resolver":"https://pith.science/pith/BVN5IRZVFKBJENI7CPF7626W7Y","bundle":"https://pith.science/pith/BVN5IRZVFKBJENI7CPF7626W7Y/bundle.json","state":"https://pith.science/pith/BVN5IRZVFKBJENI7CPF7626W7Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BVN5IRZVFKBJENI7CPF7626W7Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:BVN5IRZVFKBJENI7CPF7626W7Y","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":"c1fe21d9096617c775c2b74a40b13e936bc80d4071e4535e21e4ae3a14ce96ff","cross_cats_sorted":["cs.LG","math.DS","physics.comp-ph","physics.geo-ph"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.flu-dyn","submitted_at":"2026-04-26T20:36:12Z","title_canon_sha256":"c35c5c5d646255bb231d8df664d3ca782cd9db568a25ccb4991719f9e5b6d299"},"schema_version":"1.0","source":{"id":"2604.23874","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.23874","created_at":"2026-06-11T01:09:36Z"},{"alias_kind":"arxiv_version","alias_value":"2604.23874v3","created_at":"2026-06-11T01:09:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.23874","created_at":"2026-06-11T01:09:36Z"},{"alias_kind":"pith_short_12","alias_value":"BVN5IRZVFKBJ","created_at":"2026-06-11T01:09:36Z"},{"alias_kind":"pith_short_16","alias_value":"BVN5IRZVFKBJENI7","created_at":"2026-06-11T01:09:36Z"},{"alias_kind":"pith_short_8","alias_value":"BVN5IRZV","created_at":"2026-06-11T01:09:36Z"}],"graph_snapshots":[{"event_id":"sha256:5632f86ba798bbd94ecaec50cd68d2311efa26b99ae1f489a936ec7ec825e495","target":"graph","created_at":"2026-06-11T01:09:36Z","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":"Our approach enables the deep learning model to successfully learn the required forcing to capture the ground-truth statistics while maintaining long term stability without needing adjoints or backpropagation through the solver. We train and evaluate the model's ability to adapt to different numerical and temporal schemes."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The assumption that nudging DNS data as sparse observations can effectively train closures that overcome the filter mismatch and numerical discretization issues without introducing new instabilities or requiring solver-specific adjustments."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Nudging enables a-priori training of stable neural network turbulence closures for LES that adapt to various numerical schemes without solver modifications or adjoints."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Nudging sparse DNS observations into LES lets neural networks learn stable turbulence closures without backpropagating through the solver."}],"snapshot_sha256":"8bb1698d56281eda91086029e5af984b52732da0c6fc69032b497b5746b66996"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-21T07:43:03.518206Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T22:42:31.135914Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2604.23874/integrity.json","findings":[],"snapshot_sha256":"b3f25169017ab1cb55a0ea8b817a5acf85d72d3340a40206d1d543b78a143ea1","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The differentiable physics paradigm may be leveraged as an a-posteriori approach for discovering turbulence closure models by embedding a neural network parameterization directly inside the solver and optimizing it given potentially sparse target data. This addresses a key limitation of a-priori learning where direct numerical simulation (DNS) data is used to approximate the subgrid stress with the assumption of a low-pass filter. Closures trained in this a-priori manner frequently lead to unstable deployments due to the mismatch between the assumed filter and the effect of numerical discretiz","authors_text":"Ashwin Suriyanarayanan, Dibyajyoti Chakraborty, Romit Maulik","cross_cats":["cs.LG","math.DS","physics.comp-ph","physics.geo-ph"],"headline":"Nudging sparse DNS observations into LES lets neural networks learn stable turbulence closures without backpropagating through the solver.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.flu-dyn","submitted_at":"2026-04-26T20:36:12Z","title":"Deep Learning of Solver-Aware Turbulence Closures from Nudged LES Dynamics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.23874","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-08T05:14:08.649297Z","id":"870ed3e1-cdc3-492b-ba8b-d0091a884915","model_set":{"reader":"grok-4.3"},"one_line_summary":"Nudging enables a-priori training of stable neural network turbulence closures for LES that adapt to various numerical schemes without solver modifications or adjoints.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Nudging sparse DNS observations into LES lets neural networks learn stable turbulence closures without backpropagating through the solver.","strongest_claim":"Our approach enables the deep learning model to successfully learn the required forcing to capture the ground-truth statistics while maintaining long term stability without needing adjoints or backpropagation through the solver. We train and evaluate the model's ability to adapt to different numerical and temporal schemes.","weakest_assumption":"The assumption that nudging DNS data as sparse observations can effectively train closures that overcome the filter mismatch and numerical discretization issues without introducing new instabilities or requiring solver-specific adjustments."}},"verdict_id":"870ed3e1-cdc3-492b-ba8b-d0091a884915"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6b710e860ec9aa686de6e8ada38b8742264c4f043b281a368e978203419ca36d","target":"record","created_at":"2026-06-11T01:09:36Z","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":"c1fe21d9096617c775c2b74a40b13e936bc80d4071e4535e21e4ae3a14ce96ff","cross_cats_sorted":["cs.LG","math.DS","physics.comp-ph","physics.geo-ph"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.flu-dyn","submitted_at":"2026-04-26T20:36:12Z","title_canon_sha256":"c35c5c5d646255bb231d8df664d3ca782cd9db568a25ccb4991719f9e5b6d299"},"schema_version":"1.0","source":{"id":"2604.23874","kind":"arxiv","version":3}},"canonical_sha256":"0d5bd447352a8292351f13cbff6bd6fe304bfa255af59da0c96649828cefb87b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0d5bd447352a8292351f13cbff6bd6fe304bfa255af59da0c96649828cefb87b","first_computed_at":"2026-06-11T01:09:36.366594Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-11T01:09:36.366594Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Egk5in+fgkrG8vkTn6MJK06AfUXTzq5j9ng5C2O3I3pN3oDJy10WfrgvhlTMo9/EPuHwnBDKZewKpBY2nqd3AQ==","signature_status":"signed_v1","signed_at":"2026-06-11T01:09:36.367661Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.23874","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6b710e860ec9aa686de6e8ada38b8742264c4f043b281a368e978203419ca36d","sha256:5632f86ba798bbd94ecaec50cd68d2311efa26b99ae1f489a936ec7ec825e495"],"state_sha256":"5176d070414dd23b163c96865651546b17616f498122ebff57698d3d515b1d06"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BbBiAyRLMrYAZeKvkGl/Vo3nGn95bCpp561xu3AijdcJHxb3rcL55ki+EP79pgqNQSdVXDwHb5klb0TLHGgBBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T20:14:33.840412Z","bundle_sha256":"ac1afbfab455a4d98cc48304277cfafe52c84d8908a4a26549f7690a875b3928"}}