{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GYX3FFROZ2FCKP4MQKBNN4WZRE","short_pith_number":"pith:GYX3FFRO","schema_version":"1.0","canonical_sha256":"362fb2962ece8a253f8c8282d6f2d98908e9dc3b5d1349b2d3f9f9fe49c91d11","source":{"kind":"arxiv","id":"2403.15721","version":3},"attestation_state":"computed","paper":{"title":"Design and Implementation of an Analysis Pipeline for Heterogeneous Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Andre Merzky, Arup Kumar Sarker, Aymen Alsaadi, Geoffrey Fox, Gregor von Laszewski, Matteo Turilli, Mikhail Titov, Mills Staylor, Niranda Perera, Ozgur Ozan Kilic, Shantenu Jha","submitted_at":"2024-03-23T05:01:26Z","abstract_excerpt":"Managing and preparing complex data for deep learning, a prevalent approach in large-scale data science can be challenging. Data transfer for model training also presents difficulties, impacting scientific fields like genomics, climate modeling, and astronomy. A large-scale solution like Google Pathways with a distributed execution environment for deep learning models exists but is proprietary. Integrating existing open-source, scalable runtime tools and data frameworks on high-performance computing (HPC) platforms is crucial to address these challenges. Our objective is to establish a smooth "},"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":"2403.15721","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2024-03-23T05:01:26Z","cross_cats_sorted":[],"title_canon_sha256":"d048c4606fc412a89c3e5e3d768029c0f4531cd55a38a03d8aadb0b9e189fa7b","abstract_canon_sha256":"9bd0e352a2693f8a471145eaff28f3e3e11b31c5979b6dbd1e82109ce0a38f01"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:05:12.496499Z","signature_b64":"zc9J3ecewbP57QZa1dlRzAep0qpDBxvd/00EBynSW7C8jYxYICMScMRo6rGKzqKH54OKrp3S5ZZ7jHT2EA2MAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"362fb2962ece8a253f8c8282d6f2d98908e9dc3b5d1349b2d3f9f9fe49c91d11","last_reissued_at":"2026-07-05T08:05:12.496015Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:05:12.496015Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Design and Implementation of an Analysis Pipeline for Heterogeneous Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Andre Merzky, Arup Kumar Sarker, Aymen Alsaadi, Geoffrey Fox, Gregor von Laszewski, Matteo Turilli, Mikhail Titov, Mills Staylor, Niranda Perera, Ozgur Ozan Kilic, Shantenu Jha","submitted_at":"2024-03-23T05:01:26Z","abstract_excerpt":"Managing and preparing complex data for deep learning, a prevalent approach in large-scale data science can be challenging. Data transfer for model training also presents difficulties, impacting scientific fields like genomics, climate modeling, and astronomy. A large-scale solution like Google Pathways with a distributed execution environment for deep learning models exists but is proprietary. Integrating existing open-source, scalable runtime tools and data frameworks on high-performance computing (HPC) platforms is crucial to address these challenges. Our objective is to establish a smooth "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.15721","kind":"arxiv","version":3},"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/2403.15721/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":"2403.15721","created_at":"2026-07-05T08:05:12.496076+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.15721v3","created_at":"2026-07-05T08:05:12.496076+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.15721","created_at":"2026-07-05T08:05:12.496076+00:00"},{"alias_kind":"pith_short_12","alias_value":"GYX3FFROZ2FC","created_at":"2026-07-05T08:05:12.496076+00:00"},{"alias_kind":"pith_short_16","alias_value":"GYX3FFROZ2FCKP4M","created_at":"2026-07-05T08:05:12.496076+00:00"},{"alias_kind":"pith_short_8","alias_value":"GYX3FFRO","created_at":"2026-07-05T08:05:12.496076+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/GYX3FFROZ2FCKP4MQKBNN4WZRE","json":"https://pith.science/pith/GYX3FFROZ2FCKP4MQKBNN4WZRE.json","graph_json":"https://pith.science/api/pith-number/GYX3FFROZ2FCKP4MQKBNN4WZRE/graph.json","events_json":"https://pith.science/api/pith-number/GYX3FFROZ2FCKP4MQKBNN4WZRE/events.json","paper":"https://pith.science/paper/GYX3FFRO"},"agent_actions":{"view_html":"https://pith.science/pith/GYX3FFROZ2FCKP4MQKBNN4WZRE","download_json":"https://pith.science/pith/GYX3FFROZ2FCKP4MQKBNN4WZRE.json","view_paper":"https://pith.science/paper/GYX3FFRO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.15721&json=true","fetch_graph":"https://pith.science/api/pith-number/GYX3FFROZ2FCKP4MQKBNN4WZRE/graph.json","fetch_events":"https://pith.science/api/pith-number/GYX3FFROZ2FCKP4MQKBNN4WZRE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GYX3FFROZ2FCKP4MQKBNN4WZRE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GYX3FFROZ2FCKP4MQKBNN4WZRE/action/storage_attestation","attest_author":"https://pith.science/pith/GYX3FFROZ2FCKP4MQKBNN4WZRE/action/author_attestation","sign_citation":"https://pith.science/pith/GYX3FFROZ2FCKP4MQKBNN4WZRE/action/citation_signature","submit_replication":"https://pith.science/pith/GYX3FFROZ2FCKP4MQKBNN4WZRE/action/replication_record"}},"created_at":"2026-07-05T08:05:12.496076+00:00","updated_at":"2026-07-05T08:05:12.496076+00:00"}