{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:ZB2BH6HPO53J2B76WGO3NIQSO4","short_pith_number":"pith:ZB2BH6HP","schema_version":"1.0","canonical_sha256":"c87413f8ef77769d07feb19db6a212770c3425fdb910b86fa215d2df7924de58","source":{"kind":"arxiv","id":"1808.08424","version":2},"attestation_state":"computed","paper":{"title":"Efficiently Processing Workflow Provenance Queries on SPARK","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Himanshu Gupta, Mauricio Hernandez, Pranay Lohia, Rajmohan C, Sameep Mehta, Siddhartha Brahma","submitted_at":"2018-08-25T13:38:22Z","abstract_excerpt":"In this paper, we investigate how we can leverage Spark platform for efficiently processing provenance queries on large volumes of workflow provenance data. We focus on processing provenance queries at attribute-value level which is the finest granularity available. We propose a novel weakly connected component based framework which is carefully engineered to quickly determine a minimal volume of data containing the entire lineage of the queried attribute-value. This minimal volume of data is then processed to figure out the provenance of the queried attribute-value. The proposed framework com"},"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":"1808.08424","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2018-08-25T13:38:22Z","cross_cats_sorted":[],"title_canon_sha256":"a0e4c83621d58ec1ac7674b7dc05c0ac53016daf71265aabfaa664a7ef953c8c","abstract_canon_sha256":"ba1e920884d704962e677664d8fbdf6af863c7d6b6c919e67989cdb39b9290e8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:02:19.255930Z","signature_b64":"abqSRBRO7AFOnbjwAXV3QquOP7cACjklKcJyvAg9fDNjIFG6G1f88+9yXZ/ApOOcA8QdhtkJ3gqlks8c01+gAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c87413f8ef77769d07feb19db6a212770c3425fdb910b86fa215d2df7924de58","last_reissued_at":"2026-05-18T00:02:19.255550Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:02:19.255550Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficiently Processing Workflow Provenance Queries on SPARK","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Himanshu Gupta, Mauricio Hernandez, Pranay Lohia, Rajmohan C, Sameep Mehta, Siddhartha Brahma","submitted_at":"2018-08-25T13:38:22Z","abstract_excerpt":"In this paper, we investigate how we can leverage Spark platform for efficiently processing provenance queries on large volumes of workflow provenance data. We focus on processing provenance queries at attribute-value level which is the finest granularity available. We propose a novel weakly connected component based framework which is carefully engineered to quickly determine a minimal volume of data containing the entire lineage of the queried attribute-value. This minimal volume of data is then processed to figure out the provenance of the queried attribute-value. The proposed framework com"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.08424","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":""},"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":"1808.08424","created_at":"2026-05-18T00:02:19.255606+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.08424v2","created_at":"2026-05-18T00:02:19.255606+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.08424","created_at":"2026-05-18T00:02:19.255606+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZB2BH6HPO53J","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZB2BH6HPO53J2B76","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZB2BH6HP","created_at":"2026-05-18T12:33:04.347982+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/ZB2BH6HPO53J2B76WGO3NIQSO4","json":"https://pith.science/pith/ZB2BH6HPO53J2B76WGO3NIQSO4.json","graph_json":"https://pith.science/api/pith-number/ZB2BH6HPO53J2B76WGO3NIQSO4/graph.json","events_json":"https://pith.science/api/pith-number/ZB2BH6HPO53J2B76WGO3NIQSO4/events.json","paper":"https://pith.science/paper/ZB2BH6HP"},"agent_actions":{"view_html":"https://pith.science/pith/ZB2BH6HPO53J2B76WGO3NIQSO4","download_json":"https://pith.science/pith/ZB2BH6HPO53J2B76WGO3NIQSO4.json","view_paper":"https://pith.science/paper/ZB2BH6HP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.08424&json=true","fetch_graph":"https://pith.science/api/pith-number/ZB2BH6HPO53J2B76WGO3NIQSO4/graph.json","fetch_events":"https://pith.science/api/pith-number/ZB2BH6HPO53J2B76WGO3NIQSO4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZB2BH6HPO53J2B76WGO3NIQSO4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZB2BH6HPO53J2B76WGO3NIQSO4/action/storage_attestation","attest_author":"https://pith.science/pith/ZB2BH6HPO53J2B76WGO3NIQSO4/action/author_attestation","sign_citation":"https://pith.science/pith/ZB2BH6HPO53J2B76WGO3NIQSO4/action/citation_signature","submit_replication":"https://pith.science/pith/ZB2BH6HPO53J2B76WGO3NIQSO4/action/replication_record"}},"created_at":"2026-05-18T00:02:19.255606+00:00","updated_at":"2026-05-18T00:02:19.255606+00:00"}