{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:JMDDW5Z4BZCJUWNSSO4KKESC5E","short_pith_number":"pith:JMDDW5Z4","schema_version":"1.0","canonical_sha256":"4b063b773c0e449a59b293b8a51242e918e841a664958a61a9371fdd9cbbe4b2","source":{"kind":"arxiv","id":"2107.11536","version":1},"attestation_state":"computed","paper":{"title":"SODA: A Semantics-Aware Optimization Framework for Data-Intensive Applications Using Hybrid Program Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Bingbing Rao, Hong Zhang, Liqiang Wang, Siyang Lu, Zixia Liu","submitted_at":"2021-07-24T05:33:05Z","abstract_excerpt":"In the era of data explosion, a growing number of data-intensive computing frameworks, such as Apache Hadoop and Spark, have been proposed to handle the massive volume of unstructured data in parallel. Since programming models provided by these frameworks allow users to specify complex and diversified user-defined functions (UDFs) with predefined operations, the grand challenge of tuning up entire system performance arises if programmers do not fully understand the semantics of code, data, and runtime systems. In this paper, we design a holistic semantics-aware optimization for data-intensive "},"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":"2107.11536","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2021-07-24T05:33:05Z","cross_cats_sorted":[],"title_canon_sha256":"e0a1387f128e68b2455edabf36bfa428f08db23b689de30d10c9aa20f788db1c","abstract_canon_sha256":"e830115ede9b4572bd20d125da164cdfe61d07e1271d53ca98b8edff855c1d5e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:00:20.404135Z","signature_b64":"3XRiQ5GmgQRGqKvSZhSqgsw7jqt2EuOJWNHveKLUICLhEoH7a3ro2yQnTe6yOb9AiZPsgR9eMmvsSNTbEhCOAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b063b773c0e449a59b293b8a51242e918e841a664958a61a9371fdd9cbbe4b2","last_reissued_at":"2026-07-05T03:00:20.403731Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:00:20.403731Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SODA: A Semantics-Aware Optimization Framework for Data-Intensive Applications Using Hybrid Program Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Bingbing Rao, Hong Zhang, Liqiang Wang, Siyang Lu, Zixia Liu","submitted_at":"2021-07-24T05:33:05Z","abstract_excerpt":"In the era of data explosion, a growing number of data-intensive computing frameworks, such as Apache Hadoop and Spark, have been proposed to handle the massive volume of unstructured data in parallel. Since programming models provided by these frameworks allow users to specify complex and diversified user-defined functions (UDFs) with predefined operations, the grand challenge of tuning up entire system performance arises if programmers do not fully understand the semantics of code, data, and runtime systems. In this paper, we design a holistic semantics-aware optimization for data-intensive "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.11536","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/2107.11536/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":"2107.11536","created_at":"2026-07-05T03:00:20.403793+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.11536v1","created_at":"2026-07-05T03:00:20.403793+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.11536","created_at":"2026-07-05T03:00:20.403793+00:00"},{"alias_kind":"pith_short_12","alias_value":"JMDDW5Z4BZCJ","created_at":"2026-07-05T03:00:20.403793+00:00"},{"alias_kind":"pith_short_16","alias_value":"JMDDW5Z4BZCJUWNS","created_at":"2026-07-05T03:00:20.403793+00:00"},{"alias_kind":"pith_short_8","alias_value":"JMDDW5Z4","created_at":"2026-07-05T03:00:20.403793+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/JMDDW5Z4BZCJUWNSSO4KKESC5E","json":"https://pith.science/pith/JMDDW5Z4BZCJUWNSSO4KKESC5E.json","graph_json":"https://pith.science/api/pith-number/JMDDW5Z4BZCJUWNSSO4KKESC5E/graph.json","events_json":"https://pith.science/api/pith-number/JMDDW5Z4BZCJUWNSSO4KKESC5E/events.json","paper":"https://pith.science/paper/JMDDW5Z4"},"agent_actions":{"view_html":"https://pith.science/pith/JMDDW5Z4BZCJUWNSSO4KKESC5E","download_json":"https://pith.science/pith/JMDDW5Z4BZCJUWNSSO4KKESC5E.json","view_paper":"https://pith.science/paper/JMDDW5Z4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.11536&json=true","fetch_graph":"https://pith.science/api/pith-number/JMDDW5Z4BZCJUWNSSO4KKESC5E/graph.json","fetch_events":"https://pith.science/api/pith-number/JMDDW5Z4BZCJUWNSSO4KKESC5E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JMDDW5Z4BZCJUWNSSO4KKESC5E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JMDDW5Z4BZCJUWNSSO4KKESC5E/action/storage_attestation","attest_author":"https://pith.science/pith/JMDDW5Z4BZCJUWNSSO4KKESC5E/action/author_attestation","sign_citation":"https://pith.science/pith/JMDDW5Z4BZCJUWNSSO4KKESC5E/action/citation_signature","submit_replication":"https://pith.science/pith/JMDDW5Z4BZCJUWNSSO4KKESC5E/action/replication_record"}},"created_at":"2026-07-05T03:00:20.403793+00:00","updated_at":"2026-07-05T03:00:20.403793+00:00"}