{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:GYX3FFROZ2FCKP4MQKBNN4WZRE","short_pith_number":"pith:GYX3FFRO","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"},"canonical_sha256":"362fb2962ece8a253f8c8282d6f2d98908e9dc3b5d1349b2d3f9f9fe49c91d11","source":{"kind":"arxiv","id":"2403.15721","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.15721","created_at":"2026-07-05T08:05:12Z"},{"alias_kind":"arxiv_version","alias_value":"2403.15721v3","created_at":"2026-07-05T08:05:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.15721","created_at":"2026-07-05T08:05:12Z"},{"alias_kind":"pith_short_12","alias_value":"GYX3FFROZ2FC","created_at":"2026-07-05T08:05:12Z"},{"alias_kind":"pith_short_16","alias_value":"GYX3FFROZ2FCKP4M","created_at":"2026-07-05T08:05:12Z"},{"alias_kind":"pith_short_8","alias_value":"GYX3FFRO","created_at":"2026-07-05T08:05:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:GYX3FFROZ2FCKP4MQKBNN4WZRE","target":"record","payload":{"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"},"canonical_sha256":"362fb2962ece8a253f8c8282d6f2d98908e9dc3b5d1349b2d3f9f9fe49c91d11","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"},"source_kind":"arxiv","source_id":"2403.15721","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:05:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wSidJfHjpLWi06o5YL1nJ8Czhy90x+9X81sihE+BapOT0ZAV4peqJbXaQm3SKfWO2Ld66A9lVDzZIK2rDJDBBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T15:34:26.544899Z"},"content_sha256":"5cc992a2fdc12e70a85656116b7659bc7ec0ad7f228d20c093974aef87d4e48c","schema_version":"1.0","event_id":"sha256:5cc992a2fdc12e70a85656116b7659bc7ec0ad7f228d20c093974aef87d4e48c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:GYX3FFROZ2FCKP4MQKBNN4WZRE","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:05:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6gPFZ57Qp6K76Nie5L0eMHGyFwlfKeCEPv1zKNmzknXgC2EARMzs+1PnLZXFNRIo/nEtPfo+xXYyxspKcp5tBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T15:34:26.545213Z"},"content_sha256":"c65ce3bb80b10ed7dd0bc29fd52f4b405d0a82a8a3ec4eb81a9e96bbce81d519","schema_version":"1.0","event_id":"sha256:c65ce3bb80b10ed7dd0bc29fd52f4b405d0a82a8a3ec4eb81a9e96bbce81d519"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GYX3FFROZ2FCKP4MQKBNN4WZRE/bundle.json","state_url":"https://pith.science/pith/GYX3FFROZ2FCKP4MQKBNN4WZRE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GYX3FFROZ2FCKP4MQKBNN4WZRE/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-02T15:34:26Z","links":{"resolver":"https://pith.science/pith/GYX3FFROZ2FCKP4MQKBNN4WZRE","bundle":"https://pith.science/pith/GYX3FFROZ2FCKP4MQKBNN4WZRE/bundle.json","state":"https://pith.science/pith/GYX3FFROZ2FCKP4MQKBNN4WZRE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GYX3FFROZ2FCKP4MQKBNN4WZRE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GYX3FFROZ2FCKP4MQKBNN4WZRE","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"9bd0e352a2693f8a471145eaff28f3e3e11b31c5979b6dbd1e82109ce0a38f01","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2024-03-23T05:01:26Z","title_canon_sha256":"d048c4606fc412a89c3e5e3d768029c0f4531cd55a38a03d8aadb0b9e189fa7b"},"schema_version":"1.0","source":{"id":"2403.15721","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.15721","created_at":"2026-07-05T08:05:12Z"},{"alias_kind":"arxiv_version","alias_value":"2403.15721v3","created_at":"2026-07-05T08:05:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.15721","created_at":"2026-07-05T08:05:12Z"},{"alias_kind":"pith_short_12","alias_value":"GYX3FFROZ2FC","created_at":"2026-07-05T08:05:12Z"},{"alias_kind":"pith_short_16","alias_value":"GYX3FFROZ2FCKP4M","created_at":"2026-07-05T08:05:12Z"},{"alias_kind":"pith_short_8","alias_value":"GYX3FFRO","created_at":"2026-07-05T08:05:12Z"}],"graph_snapshots":[{"event_id":"sha256:c65ce3bb80b10ed7dd0bc29fd52f4b405d0a82a8a3ec4eb81a9e96bbce81d519","target":"graph","created_at":"2026-07-05T08:05:12Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2403.15721/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","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","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2024-03-23T05:01:26Z","title":"Design and Implementation of an Analysis Pipeline for Heterogeneous Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.15721","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5cc992a2fdc12e70a85656116b7659bc7ec0ad7f228d20c093974aef87d4e48c","target":"record","created_at":"2026-07-05T08:05:12Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"9bd0e352a2693f8a471145eaff28f3e3e11b31c5979b6dbd1e82109ce0a38f01","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2024-03-23T05:01:26Z","title_canon_sha256":"d048c4606fc412a89c3e5e3d768029c0f4531cd55a38a03d8aadb0b9e189fa7b"},"schema_version":"1.0","source":{"id":"2403.15721","kind":"arxiv","version":3}},"canonical_sha256":"362fb2962ece8a253f8c8282d6f2d98908e9dc3b5d1349b2d3f9f9fe49c91d11","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"362fb2962ece8a253f8c8282d6f2d98908e9dc3b5d1349b2d3f9f9fe49c91d11","first_computed_at":"2026-07-05T08:05:12.496015Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:05:12.496015Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zc9J3ecewbP57QZa1dlRzAep0qpDBxvd/00EBynSW7C8jYxYICMScMRo6rGKzqKH54OKrp3S5ZZ7jHT2EA2MAw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:05:12.496499Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.15721","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5cc992a2fdc12e70a85656116b7659bc7ec0ad7f228d20c093974aef87d4e48c","sha256:c65ce3bb80b10ed7dd0bc29fd52f4b405d0a82a8a3ec4eb81a9e96bbce81d519"],"state_sha256":"4a79c96d742a680ad821b890a90d713c50336acf36ce11467a10871f030ff13c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kF+4qzxALcT7Yatsns1fONV7okrPmY3l8Ri1RFBAj9WLEKSj98qGT2pvjnF2Uum7t7xwu9SirVr4h34RDQdWAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-02T15:34:26.547565Z","bundle_sha256":"8facc4afac88f5623680acf4d1c08c74fa32fab3c94decc1ad19d845c5525990"}}