{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:ZB2BH6HPO53J2B76WGO3NIQSO4","short_pith_number":"pith:ZB2BH6HP","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"},"canonical_sha256":"c87413f8ef77769d07feb19db6a212770c3425fdb910b86fa215d2df7924de58","source":{"kind":"arxiv","id":"1808.08424","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.08424","created_at":"2026-05-18T00:02:19Z"},{"alias_kind":"arxiv_version","alias_value":"1808.08424v2","created_at":"2026-05-18T00:02:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.08424","created_at":"2026-05-18T00:02:19Z"},{"alias_kind":"pith_short_12","alias_value":"ZB2BH6HPO53J","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"ZB2BH6HPO53J2B76","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"ZB2BH6HP","created_at":"2026-05-18T12:33:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:ZB2BH6HPO53J2B76WGO3NIQSO4","target":"record","payload":{"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"},"canonical_sha256":"c87413f8ef77769d07feb19db6a212770c3425fdb910b86fa215d2df7924de58","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"},"source_kind":"arxiv","source_id":"1808.08424","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:02:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g96nzJ1/l8dx+LJPDKVeBl/+EqZV8TZAi3p9qGxdPgKLN3Qzp6i/4ceOpJS9TTaUUSdtewXMQf7aPq4PdDwCBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T14:37:39.198836Z"},"content_sha256":"b7c920ac1cebbf18a90b42e7addebb85eeb8bb66a3d796e78ff0acd5cf682622","schema_version":"1.0","event_id":"sha256:b7c920ac1cebbf18a90b42e7addebb85eeb8bb66a3d796e78ff0acd5cf682622"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:ZB2BH6HPO53J2B76WGO3NIQSO4","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:02:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GZdgfSdkJQpgs5UGQfvfZXAjwffCWtUrbL656vJ7SGeYm1XizTmT9tZ5WyhWwG7QPUTMT+ak3vs+F+6qqZpiDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T14:37:39.199182Z"},"content_sha256":"9821b0d030f7211d256980700d21b32a10761a7d2712a5d6e0eb71d79741ec9f","schema_version":"1.0","event_id":"sha256:9821b0d030f7211d256980700d21b32a10761a7d2712a5d6e0eb71d79741ec9f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZB2BH6HPO53J2B76WGO3NIQSO4/bundle.json","state_url":"https://pith.science/pith/ZB2BH6HPO53J2B76WGO3NIQSO4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZB2BH6HPO53J2B76WGO3NIQSO4/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":"2026-06-07T14:37:39Z","links":{"resolver":"https://pith.science/pith/ZB2BH6HPO53J2B76WGO3NIQSO4","bundle":"https://pith.science/pith/ZB2BH6HPO53J2B76WGO3NIQSO4/bundle.json","state":"https://pith.science/pith/ZB2BH6HPO53J2B76WGO3NIQSO4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZB2BH6HPO53J2B76WGO3NIQSO4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:ZB2BH6HPO53J2B76WGO3NIQSO4","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":"ba1e920884d704962e677664d8fbdf6af863c7d6b6c919e67989cdb39b9290e8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2018-08-25T13:38:22Z","title_canon_sha256":"a0e4c83621d58ec1ac7674b7dc05c0ac53016daf71265aabfaa664a7ef953c8c"},"schema_version":"1.0","source":{"id":"1808.08424","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.08424","created_at":"2026-05-18T00:02:19Z"},{"alias_kind":"arxiv_version","alias_value":"1808.08424v2","created_at":"2026-05-18T00:02:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.08424","created_at":"2026-05-18T00:02:19Z"},{"alias_kind":"pith_short_12","alias_value":"ZB2BH6HPO53J","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"ZB2BH6HPO53J2B76","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"ZB2BH6HP","created_at":"2026-05-18T12:33:04Z"}],"graph_snapshots":[{"event_id":"sha256:9821b0d030f7211d256980700d21b32a10761a7d2712a5d6e0eb71d79741ec9f","target":"graph","created_at":"2026-05-18T00:02:19Z","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"},"paper":{"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","authors_text":"Himanshu Gupta, Mauricio Hernandez, Pranay Lohia, Rajmohan C, Sameep Mehta, Siddhartha Brahma","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2018-08-25T13:38:22Z","title":"Efficiently Processing Workflow Provenance Queries on SPARK"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.08424","kind":"arxiv","version":2},"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:b7c920ac1cebbf18a90b42e7addebb85eeb8bb66a3d796e78ff0acd5cf682622","target":"record","created_at":"2026-05-18T00:02:19Z","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":"ba1e920884d704962e677664d8fbdf6af863c7d6b6c919e67989cdb39b9290e8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2018-08-25T13:38:22Z","title_canon_sha256":"a0e4c83621d58ec1ac7674b7dc05c0ac53016daf71265aabfaa664a7ef953c8c"},"schema_version":"1.0","source":{"id":"1808.08424","kind":"arxiv","version":2}},"canonical_sha256":"c87413f8ef77769d07feb19db6a212770c3425fdb910b86fa215d2df7924de58","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c87413f8ef77769d07feb19db6a212770c3425fdb910b86fa215d2df7924de58","first_computed_at":"2026-05-18T00:02:19.255550Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:02:19.255550Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"abqSRBRO7AFOnbjwAXV3QquOP7cACjklKcJyvAg9fDNjIFG6G1f88+9yXZ/ApOOcA8QdhtkJ3gqlks8c01+gAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:02:19.255930Z","signed_message":"canonical_sha256_bytes"},"source_id":"1808.08424","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b7c920ac1cebbf18a90b42e7addebb85eeb8bb66a3d796e78ff0acd5cf682622","sha256:9821b0d030f7211d256980700d21b32a10761a7d2712a5d6e0eb71d79741ec9f"],"state_sha256":"849f2d57ac463e2099e393407300178ab34a598371d6284fa09b77de24efe2c7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1aypIXXhdZWNGXP9uL5JtdQi0EON8w4vrRceiBc5jAN25KOgzZRWWRcC3LjQFI2l/ltfloSn2JymQygq9BK9Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T14:37:39.202235Z","bundle_sha256":"6f4f992a88dcd0a91f2897752fbcf85615ee3e3509cb7909f60a8a32202ade2b"}}