{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WHBGM47ZYOO2IDFNWCFWPFKRJM","short_pith_number":"pith:WHBGM47Z","schema_version":"1.0","canonical_sha256":"b1c26673f9c39da40cadb08b6795514b2195fe61b23b29261ade0db966de5175","source":{"kind":"arxiv","id":"2407.16353","version":2},"attestation_state":"computed","paper":{"title":"Sizey: Memory-Efficient Execution of Scientific Workflow Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Dominik Scheinert, Fabian Lehmann, Fabian Skalski, Jonathan Bader, Jonathan Will, Lauritz Thamsen, Odej Kao","submitted_at":"2024-07-23T09:54:07Z","abstract_excerpt":"As the amount of available data continues to grow in fields as diverse as bioinformatics, physics, and remote sensing, the importance of scientific workflows in the design and implementation of reproducible data analysis pipelines increases. When developing workflows, resource requirements must be defined for each type of task in the workflow. Typically, task types vary widely in their computational demands because they are simply wrappers for arbitrary black-box analysis tools. Furthermore, the resource consumption for the same task type can vary considerably as well due to different inputs. "},"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":"2407.16353","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2024-07-23T09:54:07Z","cross_cats_sorted":[],"title_canon_sha256":"bd3e162607bbe732942a234e61c41b08bb24124451474826446c7a4fb36d608d","abstract_canon_sha256":"0f6d497b4db6d8ea69de56aafbb13e650423de548c9f8b870f508e6daa78ebd8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:11:59.876909Z","signature_b64":"1JWR5sMTifBddRheQLBXFGBkAzw6vDFd7TB1GSb35VY4fPPiCHx1ZKDb53g/BKMDcGvAfBLuzwN3rUFkonaZCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1c26673f9c39da40cadb08b6795514b2195fe61b23b29261ade0db966de5175","last_reissued_at":"2026-07-05T10:11:59.876342Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:11:59.876342Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sizey: Memory-Efficient Execution of Scientific Workflow Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Dominik Scheinert, Fabian Lehmann, Fabian Skalski, Jonathan Bader, Jonathan Will, Lauritz Thamsen, Odej Kao","submitted_at":"2024-07-23T09:54:07Z","abstract_excerpt":"As the amount of available data continues to grow in fields as diverse as bioinformatics, physics, and remote sensing, the importance of scientific workflows in the design and implementation of reproducible data analysis pipelines increases. When developing workflows, resource requirements must be defined for each type of task in the workflow. Typically, task types vary widely in their computational demands because they are simply wrappers for arbitrary black-box analysis tools. Furthermore, the resource consumption for the same task type can vary considerably as well due to different inputs. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.16353","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/2407.16353/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":"2407.16353","created_at":"2026-07-05T10:11:59.876405+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.16353v2","created_at":"2026-07-05T10:11:59.876405+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.16353","created_at":"2026-07-05T10:11:59.876405+00:00"},{"alias_kind":"pith_short_12","alias_value":"WHBGM47ZYOO2","created_at":"2026-07-05T10:11:59.876405+00:00"},{"alias_kind":"pith_short_16","alias_value":"WHBGM47ZYOO2IDFN","created_at":"2026-07-05T10:11:59.876405+00:00"},{"alias_kind":"pith_short_8","alias_value":"WHBGM47Z","created_at":"2026-07-05T10:11:59.876405+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/WHBGM47ZYOO2IDFNWCFWPFKRJM","json":"https://pith.science/pith/WHBGM47ZYOO2IDFNWCFWPFKRJM.json","graph_json":"https://pith.science/api/pith-number/WHBGM47ZYOO2IDFNWCFWPFKRJM/graph.json","events_json":"https://pith.science/api/pith-number/WHBGM47ZYOO2IDFNWCFWPFKRJM/events.json","paper":"https://pith.science/paper/WHBGM47Z"},"agent_actions":{"view_html":"https://pith.science/pith/WHBGM47ZYOO2IDFNWCFWPFKRJM","download_json":"https://pith.science/pith/WHBGM47ZYOO2IDFNWCFWPFKRJM.json","view_paper":"https://pith.science/paper/WHBGM47Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.16353&json=true","fetch_graph":"https://pith.science/api/pith-number/WHBGM47ZYOO2IDFNWCFWPFKRJM/graph.json","fetch_events":"https://pith.science/api/pith-number/WHBGM47ZYOO2IDFNWCFWPFKRJM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WHBGM47ZYOO2IDFNWCFWPFKRJM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WHBGM47ZYOO2IDFNWCFWPFKRJM/action/storage_attestation","attest_author":"https://pith.science/pith/WHBGM47ZYOO2IDFNWCFWPFKRJM/action/author_attestation","sign_citation":"https://pith.science/pith/WHBGM47ZYOO2IDFNWCFWPFKRJM/action/citation_signature","submit_replication":"https://pith.science/pith/WHBGM47ZYOO2IDFNWCFWPFKRJM/action/replication_record"}},"created_at":"2026-07-05T10:11:59.876405+00:00","updated_at":"2026-07-05T10:11:59.876405+00:00"}