{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IIOZJHRS4VPN4YKVENOFDBYNAL","short_pith_number":"pith:IIOZJHRS","schema_version":"1.0","canonical_sha256":"421d949e32e55ede6155235c51870d02c985a59d5bad816756c5fd876beeb898","source":{"kind":"arxiv","id":"2505.24675","version":1},"attestation_state":"computed","paper":{"title":"Trustworthy Provenance for Big Data Science: a Modular Architecture Leveraging Blockchain in Federated Settings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.NI","authors_text":"Ian Foster, Nicola Giuseppe Marchioro, Sandro Luigi Fiore, Valentine Anantharaj, Yannis Velegrakis","submitted_at":"2025-05-30T15:04:09Z","abstract_excerpt":"Ensuring the trustworthiness and long-term verifiability of scientific data is a foundational challenge in the era of data-intensive, collaborative research. Provenance metadata plays a key role in this context, capturing the origin, transformation, and usage of research artifacts. However, existing solutions often fall short when applied to distributed, multi-institutional settings. This paper introduces a modular, domain-agnostic architecture for provenance tracking in federated environments, leveraging permissioned blockchain infrastructure to guarantee integrity, immutability, and auditabi"},"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":"2505.24675","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NI","submitted_at":"2025-05-30T15:04:09Z","cross_cats_sorted":[],"title_canon_sha256":"534eb5f328ebb8f34f73f43e7c1c218259aa5b5a20c79377bd25ea817cec9a47","abstract_canon_sha256":"06c615fde58db3694ab2c5b54873c4c7639984a9aba70441f09b00ba8c2fe65b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:54.410168Z","signature_b64":"zzP/ZSmqltUGV3zpHTHGN6kuUL/mh6qqJ6SEqKyedhrJvKrW6UcZFYJeeYX6nt2nuPI9o2pzkOKCfZPRSXUwDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"421d949e32e55ede6155235c51870d02c985a59d5bad816756c5fd876beeb898","last_reissued_at":"2026-07-05T11:12:54.409687Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:54.409687Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Trustworthy Provenance for Big Data Science: a Modular Architecture Leveraging Blockchain in Federated Settings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.NI","authors_text":"Ian Foster, Nicola Giuseppe Marchioro, Sandro Luigi Fiore, Valentine Anantharaj, Yannis Velegrakis","submitted_at":"2025-05-30T15:04:09Z","abstract_excerpt":"Ensuring the trustworthiness and long-term verifiability of scientific data is a foundational challenge in the era of data-intensive, collaborative research. Provenance metadata plays a key role in this context, capturing the origin, transformation, and usage of research artifacts. However, existing solutions often fall short when applied to distributed, multi-institutional settings. This paper introduces a modular, domain-agnostic architecture for provenance tracking in federated environments, leveraging permissioned blockchain infrastructure to guarantee integrity, immutability, and auditabi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24675","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/2505.24675/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":"2505.24675","created_at":"2026-07-05T11:12:54.409750+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.24675v1","created_at":"2026-07-05T11:12:54.409750+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24675","created_at":"2026-07-05T11:12:54.409750+00:00"},{"alias_kind":"pith_short_12","alias_value":"IIOZJHRS4VPN","created_at":"2026-07-05T11:12:54.409750+00:00"},{"alias_kind":"pith_short_16","alias_value":"IIOZJHRS4VPN4YKV","created_at":"2026-07-05T11:12:54.409750+00:00"},{"alias_kind":"pith_short_8","alias_value":"IIOZJHRS","created_at":"2026-07-05T11:12:54.409750+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.01075","citing_title":"Provenance Tracking in Large-Scale Machine Learning Systems","ref_index":39,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IIOZJHRS4VPN4YKVENOFDBYNAL","json":"https://pith.science/pith/IIOZJHRS4VPN4YKVENOFDBYNAL.json","graph_json":"https://pith.science/api/pith-number/IIOZJHRS4VPN4YKVENOFDBYNAL/graph.json","events_json":"https://pith.science/api/pith-number/IIOZJHRS4VPN4YKVENOFDBYNAL/events.json","paper":"https://pith.science/paper/IIOZJHRS"},"agent_actions":{"view_html":"https://pith.science/pith/IIOZJHRS4VPN4YKVENOFDBYNAL","download_json":"https://pith.science/pith/IIOZJHRS4VPN4YKVENOFDBYNAL.json","view_paper":"https://pith.science/paper/IIOZJHRS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.24675&json=true","fetch_graph":"https://pith.science/api/pith-number/IIOZJHRS4VPN4YKVENOFDBYNAL/graph.json","fetch_events":"https://pith.science/api/pith-number/IIOZJHRS4VPN4YKVENOFDBYNAL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IIOZJHRS4VPN4YKVENOFDBYNAL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IIOZJHRS4VPN4YKVENOFDBYNAL/action/storage_attestation","attest_author":"https://pith.science/pith/IIOZJHRS4VPN4YKVENOFDBYNAL/action/author_attestation","sign_citation":"https://pith.science/pith/IIOZJHRS4VPN4YKVENOFDBYNAL/action/citation_signature","submit_replication":"https://pith.science/pith/IIOZJHRS4VPN4YKVENOFDBYNAL/action/replication_record"}},"created_at":"2026-07-05T11:12:54.409750+00:00","updated_at":"2026-07-05T11:12:54.409750+00:00"}