{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KKS7ZIWUUJTNLWF7STR6F76WYD","short_pith_number":"pith:KKS7ZIWU","schema_version":"1.0","canonical_sha256":"52a5fca2d4a266d5d8bf94e3e2ffd6c0dc726688cb6ffba64e625707909d614d","source":{"kind":"arxiv","id":"2307.03683","version":2},"attestation_state":"computed","paper":{"title":"Differentiable Turbulence: Closure as a partial differential equation constrained optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"physics.flu-dyn","authors_text":"Dibyajyoti Chakraborty, Romit Maulik, Varun Shankar, Venkatasubramanian Viswanathan","submitted_at":"2023-07-07T15:51:55Z","abstract_excerpt":"Deep learning is increasingly becoming a promising pathway to improving the accuracy of sub-grid scale (SGS) turbulence closure models for large eddy simulations (LES). We leverage the concept of differentiable turbulence, whereby an end-to-end differentiable solver is used in combination with physics-inspired choices of deep learning architectures to learn highly effective and versatile SGS models for two-dimensional turbulent flow. We perform an in-depth analysis of the inductive biases in the chosen architectures, finding that the inclusion of small-scale non-local features is most critical"},"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":"2307.03683","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.flu-dyn","submitted_at":"2023-07-07T15:51:55Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"117eb071ff7a003345708dd6bbdd816091ded18560abaf25ae2b2b26d9b353a2","abstract_canon_sha256":"c502d71fe1a3564e4f1894a4eed7552c62547783a819e177faea03460466fd45"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:01:31.337361Z","signature_b64":"+TIPDTcReuWcBGNXyalr8JeE6UQFLdUzAURp7rNF5xgp8ZFu7yIW3q76kro2cHpKncIgEv1RAUO+224n4rDyAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52a5fca2d4a266d5d8bf94e3e2ffd6c0dc726688cb6ffba64e625707909d614d","last_reissued_at":"2026-07-05T08:01:31.336868Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:01:31.336868Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Differentiable Turbulence: Closure as a partial differential equation constrained optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"physics.flu-dyn","authors_text":"Dibyajyoti Chakraborty, Romit Maulik, Varun Shankar, Venkatasubramanian Viswanathan","submitted_at":"2023-07-07T15:51:55Z","abstract_excerpt":"Deep learning is increasingly becoming a promising pathway to improving the accuracy of sub-grid scale (SGS) turbulence closure models for large eddy simulations (LES). We leverage the concept of differentiable turbulence, whereby an end-to-end differentiable solver is used in combination with physics-inspired choices of deep learning architectures to learn highly effective and versatile SGS models for two-dimensional turbulent flow. We perform an in-depth analysis of the inductive biases in the chosen architectures, finding that the inclusion of small-scale non-local features is most critical"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.03683","kind":"arxiv","version":2},"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/2307.03683/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":"2307.03683","created_at":"2026-07-05T08:01:31.336924+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.03683v2","created_at":"2026-07-05T08:01:31.336924+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.03683","created_at":"2026-07-05T08:01:31.336924+00:00"},{"alias_kind":"pith_short_12","alias_value":"KKS7ZIWUUJTN","created_at":"2026-07-05T08:01:31.336924+00:00"},{"alias_kind":"pith_short_16","alias_value":"KKS7ZIWUUJTNLWF7","created_at":"2026-07-05T08:01:31.336924+00:00"},{"alias_kind":"pith_short_8","alias_value":"KKS7ZIWU","created_at":"2026-07-05T08:01:31.336924+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.26358","citing_title":"Deep Learning-based Algebraic Reynolds Stress Closures for RANS Simulations of Turbulent Flows","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KKS7ZIWUUJTNLWF7STR6F76WYD","json":"https://pith.science/pith/KKS7ZIWUUJTNLWF7STR6F76WYD.json","graph_json":"https://pith.science/api/pith-number/KKS7ZIWUUJTNLWF7STR6F76WYD/graph.json","events_json":"https://pith.science/api/pith-number/KKS7ZIWUUJTNLWF7STR6F76WYD/events.json","paper":"https://pith.science/paper/KKS7ZIWU"},"agent_actions":{"view_html":"https://pith.science/pith/KKS7ZIWUUJTNLWF7STR6F76WYD","download_json":"https://pith.science/pith/KKS7ZIWUUJTNLWF7STR6F76WYD.json","view_paper":"https://pith.science/paper/KKS7ZIWU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.03683&json=true","fetch_graph":"https://pith.science/api/pith-number/KKS7ZIWUUJTNLWF7STR6F76WYD/graph.json","fetch_events":"https://pith.science/api/pith-number/KKS7ZIWUUJTNLWF7STR6F76WYD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KKS7ZIWUUJTNLWF7STR6F76WYD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KKS7ZIWUUJTNLWF7STR6F76WYD/action/storage_attestation","attest_author":"https://pith.science/pith/KKS7ZIWUUJTNLWF7STR6F76WYD/action/author_attestation","sign_citation":"https://pith.science/pith/KKS7ZIWUUJTNLWF7STR6F76WYD/action/citation_signature","submit_replication":"https://pith.science/pith/KKS7ZIWUUJTNLWF7STR6F76WYD/action/replication_record"}},"created_at":"2026-07-05T08:01:31.336924+00:00","updated_at":"2026-07-05T08:01:31.336924+00:00"}