{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XDETKHCTOR22IICZWBNES5D3CH","short_pith_number":"pith:XDETKHCT","schema_version":"1.0","canonical_sha256":"b8c9351c537475a42059b05a49747b11e6c6520891885500e6f432480c2fb8df","source":{"kind":"arxiv","id":"2409.08949","version":1},"attestation_state":"computed","paper":{"title":"Generic and ML Workloads in an HPC Datacenter: Node Energy, Job Failures, and Node-Job Analysis","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AR"],"primary_cat":"cs.DC","authors_text":"Alexandru Iosup, Damian Podareanu, Daniel Hofst\\\"atter, Dmitry Duplyakin, Duncan Kampert, Ivona Brandic, Sacheendra Talluri, Shashikant Ilager, Xiaoyu Chu","submitted_at":"2024-09-13T16:08:08Z","abstract_excerpt":"HPC datacenters offer a backbone to the modern digital society. Increasingly, they run Machine Learning (ML) jobs next to generic, compute-intensive workloads, supporting science, business, and other decision-making processes. However, understanding how ML jobs impact the operation of HPC datacenters, relative to generic jobs, remains desirable but understudied. In this work, we leverage long-term operational data, collected from a national-scale production HPC datacenter, and statistically compare how ML and generic jobs can impact the performance, failures, resource utilization, and energy c"},"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":"2409.08949","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.DC","submitted_at":"2024-09-13T16:08:08Z","cross_cats_sorted":["cs.AR"],"title_canon_sha256":"3f05e0c96601b11a68f28fa9ac9469879b00da43fce560dbc124c8ea3600558a","abstract_canon_sha256":"40fadef4ba849f143fcfd321241ef93bb4e81d3602ffdebf71ed1fbbf50e8b31"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:06:50.111798Z","signature_b64":"vzL35QIUhJyfDWEN1XD4/an2nG2lK4myDe7deHhZ3iYhYWzGQqyLa/flhCyrkwrh/t/gcioFv3aA+rLcHpKQCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8c9351c537475a42059b05a49747b11e6c6520891885500e6f432480c2fb8df","last_reissued_at":"2026-07-05T09:06:50.111371Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:06:50.111371Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generic and ML Workloads in an HPC Datacenter: Node Energy, Job Failures, and Node-Job Analysis","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AR"],"primary_cat":"cs.DC","authors_text":"Alexandru Iosup, Damian Podareanu, Daniel Hofst\\\"atter, Dmitry Duplyakin, Duncan Kampert, Ivona Brandic, Sacheendra Talluri, Shashikant Ilager, Xiaoyu Chu","submitted_at":"2024-09-13T16:08:08Z","abstract_excerpt":"HPC datacenters offer a backbone to the modern digital society. Increasingly, they run Machine Learning (ML) jobs next to generic, compute-intensive workloads, supporting science, business, and other decision-making processes. However, understanding how ML jobs impact the operation of HPC datacenters, relative to generic jobs, remains desirable but understudied. In this work, we leverage long-term operational data, collected from a national-scale production HPC datacenter, and statistically compare how ML and generic jobs can impact the performance, failures, resource utilization, and energy c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.08949","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/2409.08949/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":"2409.08949","created_at":"2026-07-05T09:06:50.111435+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.08949v1","created_at":"2026-07-05T09:06:50.111435+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.08949","created_at":"2026-07-05T09:06:50.111435+00:00"},{"alias_kind":"pith_short_12","alias_value":"XDETKHCTOR22","created_at":"2026-07-05T09:06:50.111435+00:00"},{"alias_kind":"pith_short_16","alias_value":"XDETKHCTOR22IICZ","created_at":"2026-07-05T09:06:50.111435+00:00"},{"alias_kind":"pith_short_8","alias_value":"XDETKHCT","created_at":"2026-07-05T09:06:50.111435+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.12469","citing_title":"An Empirical Characterization of Outages and Incidents in Public Services for Large Language Models","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XDETKHCTOR22IICZWBNES5D3CH","json":"https://pith.science/pith/XDETKHCTOR22IICZWBNES5D3CH.json","graph_json":"https://pith.science/api/pith-number/XDETKHCTOR22IICZWBNES5D3CH/graph.json","events_json":"https://pith.science/api/pith-number/XDETKHCTOR22IICZWBNES5D3CH/events.json","paper":"https://pith.science/paper/XDETKHCT"},"agent_actions":{"view_html":"https://pith.science/pith/XDETKHCTOR22IICZWBNES5D3CH","download_json":"https://pith.science/pith/XDETKHCTOR22IICZWBNES5D3CH.json","view_paper":"https://pith.science/paper/XDETKHCT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.08949&json=true","fetch_graph":"https://pith.science/api/pith-number/XDETKHCTOR22IICZWBNES5D3CH/graph.json","fetch_events":"https://pith.science/api/pith-number/XDETKHCTOR22IICZWBNES5D3CH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XDETKHCTOR22IICZWBNES5D3CH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XDETKHCTOR22IICZWBNES5D3CH/action/storage_attestation","attest_author":"https://pith.science/pith/XDETKHCTOR22IICZWBNES5D3CH/action/author_attestation","sign_citation":"https://pith.science/pith/XDETKHCTOR22IICZWBNES5D3CH/action/citation_signature","submit_replication":"https://pith.science/pith/XDETKHCTOR22IICZWBNES5D3CH/action/replication_record"}},"created_at":"2026-07-05T09:06:50.111435+00:00","updated_at":"2026-07-05T09:06:50.111435+00:00"}