{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:B7JYQOCTBRBXUJXAJBA7NIGVH6","short_pith_number":"pith:B7JYQOCT","schema_version":"1.0","canonical_sha256":"0fd38838530c437a26e04841f6a0d53fbe2ea5af2da8c43efad740684cb19fb5","source":{"kind":"arxiv","id":"1912.02892","version":2},"attestation_state":"computed","paper":{"title":"Enabling Machine Learning-Ready HPC Ensembles with Merlin","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","physics.comp-ph","physics.plasm-ph"],"primary_cat":"cs.DC","authors_text":"Ben Bay, Bhavya Kailkhura, Bogdan Kustowski, Brian Spears, Brian Van Essen, David Fox, Francesco Di Natale, Jae-Seung Yeom, Jayaraman Thiagarajan, Jeremy White, Jessica Semler, Jim A. Gaffney, J. Luc Peterson, Joe Koning, Kevin Athey, Peer-Timo Bremer, Peter Robinson, Rushil Anirudh, Sam A. Jacobs, Steven Langer","submitted_at":"2019-12-05T21:40:07Z","abstract_excerpt":"With the growing complexity of computational and experimental facilities, many scientific researchers are turning to machine learning (ML) techniques to analyze large scale ensemble data. With complexities such as multi-component workflows, heterogeneous machine architectures, parallel file systems, and batch scheduling, care must be taken to facilitate this analysis in a high performance computing (HPC) environment. In this paper, we present Merlin, a workflow framework to enable large ML-friendly ensembles of scientific HPC simulations. By augmenting traditional HPC with distributed compute "},"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":"1912.02892","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2019-12-05T21:40:07Z","cross_cats_sorted":["cs.LG","physics.comp-ph","physics.plasm-ph"],"title_canon_sha256":"a1c69f9ac93e7abaae90560daa2a00cc998bd04ef33f3dbe82c15f688f5362df","abstract_canon_sha256":"d3f539cf0e1a6318d4665e4302d5451a27a85962a1070e300a1884e5df064f6a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:54:27.885043Z","signature_b64":"uOQaIbVPUmYrVDrlpS903ued3qpWd0qhkuCR6R/aOuaH/U0a2w5pWRhgZfmlbkaqbCiMaL7EHr9v6Gh3F+aBDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0fd38838530c437a26e04841f6a0d53fbe2ea5af2da8c43efad740684cb19fb5","last_reissued_at":"2026-07-05T02:54:27.884540Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:54:27.884540Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enabling Machine Learning-Ready HPC Ensembles with Merlin","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","physics.comp-ph","physics.plasm-ph"],"primary_cat":"cs.DC","authors_text":"Ben Bay, Bhavya Kailkhura, Bogdan Kustowski, Brian Spears, Brian Van Essen, David Fox, Francesco Di Natale, Jae-Seung Yeom, Jayaraman Thiagarajan, Jeremy White, Jessica Semler, Jim A. Gaffney, J. Luc Peterson, Joe Koning, Kevin Athey, Peer-Timo Bremer, Peter Robinson, Rushil Anirudh, Sam A. Jacobs, Steven Langer","submitted_at":"2019-12-05T21:40:07Z","abstract_excerpt":"With the growing complexity of computational and experimental facilities, many scientific researchers are turning to machine learning (ML) techniques to analyze large scale ensemble data. With complexities such as multi-component workflows, heterogeneous machine architectures, parallel file systems, and batch scheduling, care must be taken to facilitate this analysis in a high performance computing (HPC) environment. In this paper, we present Merlin, a workflow framework to enable large ML-friendly ensembles of scientific HPC simulations. By augmenting traditional HPC with distributed compute "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.02892","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/1912.02892/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":"1912.02892","created_at":"2026-07-05T02:54:27.884600+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.02892v2","created_at":"2026-07-05T02:54:27.884600+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.02892","created_at":"2026-07-05T02:54:27.884600+00:00"},{"alias_kind":"pith_short_12","alias_value":"B7JYQOCTBRBX","created_at":"2026-07-05T02:54:27.884600+00:00"},{"alias_kind":"pith_short_16","alias_value":"B7JYQOCTBRBXUJXA","created_at":"2026-07-05T02:54:27.884600+00:00"},{"alias_kind":"pith_short_8","alias_value":"B7JYQOCT","created_at":"2026-07-05T02:54:27.884600+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/B7JYQOCTBRBXUJXAJBA7NIGVH6","json":"https://pith.science/pith/B7JYQOCTBRBXUJXAJBA7NIGVH6.json","graph_json":"https://pith.science/api/pith-number/B7JYQOCTBRBXUJXAJBA7NIGVH6/graph.json","events_json":"https://pith.science/api/pith-number/B7JYQOCTBRBXUJXAJBA7NIGVH6/events.json","paper":"https://pith.science/paper/B7JYQOCT"},"agent_actions":{"view_html":"https://pith.science/pith/B7JYQOCTBRBXUJXAJBA7NIGVH6","download_json":"https://pith.science/pith/B7JYQOCTBRBXUJXAJBA7NIGVH6.json","view_paper":"https://pith.science/paper/B7JYQOCT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.02892&json=true","fetch_graph":"https://pith.science/api/pith-number/B7JYQOCTBRBXUJXAJBA7NIGVH6/graph.json","fetch_events":"https://pith.science/api/pith-number/B7JYQOCTBRBXUJXAJBA7NIGVH6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B7JYQOCTBRBXUJXAJBA7NIGVH6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B7JYQOCTBRBXUJXAJBA7NIGVH6/action/storage_attestation","attest_author":"https://pith.science/pith/B7JYQOCTBRBXUJXAJBA7NIGVH6/action/author_attestation","sign_citation":"https://pith.science/pith/B7JYQOCTBRBXUJXAJBA7NIGVH6/action/citation_signature","submit_replication":"https://pith.science/pith/B7JYQOCTBRBXUJXAJBA7NIGVH6/action/replication_record"}},"created_at":"2026-07-05T02:54:27.884600+00:00","updated_at":"2026-07-05T02:54:27.884600+00:00"}