{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SDMMNWGYSIEDQACFK4YOBYUJVN","short_pith_number":"pith:SDMMNWGY","schema_version":"1.0","canonical_sha256":"90d8c6d8d892083800455730e0e289ab4df5c71946fc812df0d7f09182a0c26d","source":{"kind":"arxiv","id":"2508.00645","version":1},"attestation_state":"computed","paper":{"title":"SmartFlow: A CFD-solver-agnostic deep reinforcement learning framework for computational fluid dynamics on HPC platforms","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["physics.comp-ph"],"primary_cat":"physics.flu-dyn","authors_text":"Andrea Beck, Bernat Font, Di Zhou, Felix Rodach, Francisco Alc\\'antara-\\'Avila, Jean Rabault, Jiawei Chen, Johan Larsson, Junle Liu, Maochao Xiao, Marius Kurz, Oriol Lehmkuhl, Pol Su\\'arez, Ricard Montal\\`a, Ricardo Vinuesa, Sergio Pirozzoli, Ting Zhu, Yuning Wang","submitted_at":"2025-08-01T14:03:41Z","abstract_excerpt":"Deep reinforcement learning (DRL) is emerging as a powerful tool for fluid-dynamics research, encompassing active flow control, autonomous navigation, turbulence modeling and discovery of novel numerical schemes. We introduce SmartFlow, a CFD-solver-agnostic framework for both single- and multi-agent DRL algorithms that can easily integrate with MPI-parallel CPU and GPU-accelerated solvers. Built on Relexi and SmartSOD2D, SmartFlow uses the SmartSim infrastructure library and our newly developed SmartRedis-MPI library to enable asynchronous, low-latency, in-memory communication between CFD sol"},"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":"2508.00645","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"physics.flu-dyn","submitted_at":"2025-08-01T14:03:41Z","cross_cats_sorted":["physics.comp-ph"],"title_canon_sha256":"19ffe2241d39913f1df263291a125fd3cdc560f61de9dc53e63b6241e70b6914","abstract_canon_sha256":"e4128c206d292f7429069c01fce814614f1d2bf21f478f1e066323496a56a493"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:46:59.609246Z","signature_b64":"H3LkIPuddLQwRrhLrkjRK3jjJUyEyNmWPhLWuovIdVTULhgvA6tIMMO9/ruanXpY3iMRnBtj+ekqTQXGzMAnDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90d8c6d8d892083800455730e0e289ab4df5c71946fc812df0d7f09182a0c26d","last_reissued_at":"2026-07-05T11:46:59.608733Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:46:59.608733Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SmartFlow: A CFD-solver-agnostic deep reinforcement learning framework for computational fluid dynamics on HPC platforms","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["physics.comp-ph"],"primary_cat":"physics.flu-dyn","authors_text":"Andrea Beck, Bernat Font, Di Zhou, Felix Rodach, Francisco Alc\\'antara-\\'Avila, Jean Rabault, Jiawei Chen, Johan Larsson, Junle Liu, Maochao Xiao, Marius Kurz, Oriol Lehmkuhl, Pol Su\\'arez, Ricard Montal\\`a, Ricardo Vinuesa, Sergio Pirozzoli, Ting Zhu, Yuning Wang","submitted_at":"2025-08-01T14:03:41Z","abstract_excerpt":"Deep reinforcement learning (DRL) is emerging as a powerful tool for fluid-dynamics research, encompassing active flow control, autonomous navigation, turbulence modeling and discovery of novel numerical schemes. We introduce SmartFlow, a CFD-solver-agnostic framework for both single- and multi-agent DRL algorithms that can easily integrate with MPI-parallel CPU and GPU-accelerated solvers. Built on Relexi and SmartSOD2D, SmartFlow uses the SmartSim infrastructure library and our newly developed SmartRedis-MPI library to enable asynchronous, low-latency, in-memory communication between CFD sol"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.00645","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/2508.00645/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":"2508.00645","created_at":"2026-07-05T11:46:59.608799+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.00645v1","created_at":"2026-07-05T11:46:59.608799+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.00645","created_at":"2026-07-05T11:46:59.608799+00:00"},{"alias_kind":"pith_short_12","alias_value":"SDMMNWGYSIED","created_at":"2026-07-05T11:46:59.608799+00:00"},{"alias_kind":"pith_short_16","alias_value":"SDMMNWGYSIEDQACF","created_at":"2026-07-05T11:46:59.608799+00:00"},{"alias_kind":"pith_short_8","alias_value":"SDMMNWGY","created_at":"2026-07-05T11:46:59.608799+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/SDMMNWGYSIEDQACFK4YOBYUJVN","json":"https://pith.science/pith/SDMMNWGYSIEDQACFK4YOBYUJVN.json","graph_json":"https://pith.science/api/pith-number/SDMMNWGYSIEDQACFK4YOBYUJVN/graph.json","events_json":"https://pith.science/api/pith-number/SDMMNWGYSIEDQACFK4YOBYUJVN/events.json","paper":"https://pith.science/paper/SDMMNWGY"},"agent_actions":{"view_html":"https://pith.science/pith/SDMMNWGYSIEDQACFK4YOBYUJVN","download_json":"https://pith.science/pith/SDMMNWGYSIEDQACFK4YOBYUJVN.json","view_paper":"https://pith.science/paper/SDMMNWGY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.00645&json=true","fetch_graph":"https://pith.science/api/pith-number/SDMMNWGYSIEDQACFK4YOBYUJVN/graph.json","fetch_events":"https://pith.science/api/pith-number/SDMMNWGYSIEDQACFK4YOBYUJVN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SDMMNWGYSIEDQACFK4YOBYUJVN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SDMMNWGYSIEDQACFK4YOBYUJVN/action/storage_attestation","attest_author":"https://pith.science/pith/SDMMNWGYSIEDQACFK4YOBYUJVN/action/author_attestation","sign_citation":"https://pith.science/pith/SDMMNWGYSIEDQACFK4YOBYUJVN/action/citation_signature","submit_replication":"https://pith.science/pith/SDMMNWGYSIEDQACFK4YOBYUJVN/action/replication_record"}},"created_at":"2026-07-05T11:46:59.608799+00:00","updated_at":"2026-07-05T11:46:59.608799+00:00"}