{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2012:WGQFKHBEXLNJC4RG3NZGZX2SLZ","short_pith_number":"pith:WGQFKHBE","schema_version":"1.0","canonical_sha256":"b1a0551c24bada917226db726cdf525e600763a8188bd013d81cedfa771ea058","source":{"kind":"arxiv","id":"1208.0082","version":1},"attestation_state":"computed","paper":{"title":"Stubby: A Transformation-based Optimizer for MapReduce Workflows","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Harold Lim, Herodotos Herodotou, Shivnath Babu","submitted_at":"2012-08-01T03:49:32Z","abstract_excerpt":"There is a growing trend of performing analysis on large datasets using workflows composed of MapReduce jobs connected through producer-consumer relationships based on data. This trend has spurred the development of a number of interfaces--ranging from program-based to query-based interfaces--for generating MapReduce workflows. Studies have shown that the gap in performance can be quite large between optimized and unoptimized workflows. However, automatic cost-based optimization of MapReduce workflows remains a challenge due to the multitude of interfaces, large size of the execution plan spac"},"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":"1208.0082","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2012-08-01T03:49:32Z","cross_cats_sorted":[],"title_canon_sha256":"16f19bd0ead81746aa9b6042a9e4fcc97be3d1757da21b58d3aa02c455b18e21","abstract_canon_sha256":"7e281a8b98e9cf5311730d2be7fe972c7305f396c911352af79e7658bd61479e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:49:45.026626Z","signature_b64":"LgF/iazDwCBij1zPv6yHsB9ZoljFpehoETGfINvu3pNByduRLLZGCCoowl6mVton64/f9/1yMbW+L1Ot1whxAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1a0551c24bada917226db726cdf525e600763a8188bd013d81cedfa771ea058","last_reissued_at":"2026-05-18T03:49:45.025564Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:49:45.025564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stubby: A Transformation-based Optimizer for MapReduce Workflows","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Harold Lim, Herodotos Herodotou, Shivnath Babu","submitted_at":"2012-08-01T03:49:32Z","abstract_excerpt":"There is a growing trend of performing analysis on large datasets using workflows composed of MapReduce jobs connected through producer-consumer relationships based on data. This trend has spurred the development of a number of interfaces--ranging from program-based to query-based interfaces--for generating MapReduce workflows. Studies have shown that the gap in performance can be quite large between optimized and unoptimized workflows. However, automatic cost-based optimization of MapReduce workflows remains a challenge due to the multitude of interfaces, large size of the execution plan spac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1208.0082","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":""},"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":"1208.0082","created_at":"2026-05-18T03:49:45.025709+00:00"},{"alias_kind":"arxiv_version","alias_value":"1208.0082v1","created_at":"2026-05-18T03:49:45.025709+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1208.0082","created_at":"2026-05-18T03:49:45.025709+00:00"},{"alias_kind":"pith_short_12","alias_value":"WGQFKHBEXLNJ","created_at":"2026-05-18T12:27:25.539911+00:00"},{"alias_kind":"pith_short_16","alias_value":"WGQFKHBEXLNJC4RG","created_at":"2026-05-18T12:27:25.539911+00:00"},{"alias_kind":"pith_short_8","alias_value":"WGQFKHBE","created_at":"2026-05-18T12:27:25.539911+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/WGQFKHBEXLNJC4RG3NZGZX2SLZ","json":"https://pith.science/pith/WGQFKHBEXLNJC4RG3NZGZX2SLZ.json","graph_json":"https://pith.science/api/pith-number/WGQFKHBEXLNJC4RG3NZGZX2SLZ/graph.json","events_json":"https://pith.science/api/pith-number/WGQFKHBEXLNJC4RG3NZGZX2SLZ/events.json","paper":"https://pith.science/paper/WGQFKHBE"},"agent_actions":{"view_html":"https://pith.science/pith/WGQFKHBEXLNJC4RG3NZGZX2SLZ","download_json":"https://pith.science/pith/WGQFKHBEXLNJC4RG3NZGZX2SLZ.json","view_paper":"https://pith.science/paper/WGQFKHBE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1208.0082&json=true","fetch_graph":"https://pith.science/api/pith-number/WGQFKHBEXLNJC4RG3NZGZX2SLZ/graph.json","fetch_events":"https://pith.science/api/pith-number/WGQFKHBEXLNJC4RG3NZGZX2SLZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WGQFKHBEXLNJC4RG3NZGZX2SLZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WGQFKHBEXLNJC4RG3NZGZX2SLZ/action/storage_attestation","attest_author":"https://pith.science/pith/WGQFKHBEXLNJC4RG3NZGZX2SLZ/action/author_attestation","sign_citation":"https://pith.science/pith/WGQFKHBEXLNJC4RG3NZGZX2SLZ/action/citation_signature","submit_replication":"https://pith.science/pith/WGQFKHBEXLNJC4RG3NZGZX2SLZ/action/replication_record"}},"created_at":"2026-05-18T03:49:45.025709+00:00","updated_at":"2026-05-18T03:49:45.025709+00:00"}