{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:A6UF7K3CFBRFPFUCCKUJMKSJVP","short_pith_number":"pith:A6UF7K3C","schema_version":"1.0","canonical_sha256":"07a85fab62286257968212a8962a49abe468f25912366f2966f3be972e9285eb","source":{"kind":"arxiv","id":"1311.6335","version":1},"attestation_state":"computed","paper":{"title":"SOFA: An Extensible Logical Optimizer for UDF-heavy Dataflows","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Arvid Heise, Astrid Rheinl\\\"ander, Fabian Hueske, Felix Naumann, Ulf Leser","submitted_at":"2013-11-25T15:26:49Z","abstract_excerpt":"Recent years have seen an increased interest in large-scale analytical dataflows on non-relational data. These dataflows are compiled into execution graphs scheduled on large compute clusters. In many novel application areas the predominant building blocks of such dataflows are user-defined predicates or functions (UDFs). However, the heavy use of UDFs is not well taken into account for dataflow optimization in current systems.\n  SOFA is a novel and extensible optimizer for UDF-heavy dataflows. It builds on a concise set of properties for describing the semantics of Map/Reduce-style UDFs and a"},"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":"1311.6335","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2013-11-25T15:26:49Z","cross_cats_sorted":[],"title_canon_sha256":"b526ef1b81d64ddb80968ac1212f00dc10bafb3f139cbc2d4f930e54f9bfa072","abstract_canon_sha256":"375781e1e9d6f98cabffe9e25260f3dd91600fe76751f7febe72a7f00a03c9ac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:06:14.336719Z","signature_b64":"ibKbGcvICXm9vQg3O5zK8ljaixLX3QTwA8jGyGCGj/c4Tlt+AnHjB/+xMJEHHOd8pzII8TPmi70YXVj/2LwuAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07a85fab62286257968212a8962a49abe468f25912366f2966f3be972e9285eb","last_reissued_at":"2026-05-18T03:06:14.336221Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:06:14.336221Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SOFA: An Extensible Logical Optimizer for UDF-heavy Dataflows","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Arvid Heise, Astrid Rheinl\\\"ander, Fabian Hueske, Felix Naumann, Ulf Leser","submitted_at":"2013-11-25T15:26:49Z","abstract_excerpt":"Recent years have seen an increased interest in large-scale analytical dataflows on non-relational data. These dataflows are compiled into execution graphs scheduled on large compute clusters. In many novel application areas the predominant building blocks of such dataflows are user-defined predicates or functions (UDFs). However, the heavy use of UDFs is not well taken into account for dataflow optimization in current systems.\n  SOFA is a novel and extensible optimizer for UDF-heavy dataflows. It builds on a concise set of properties for describing the semantics of Map/Reduce-style UDFs and a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1311.6335","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":"1311.6335","created_at":"2026-05-18T03:06:14.336307+00:00"},{"alias_kind":"arxiv_version","alias_value":"1311.6335v1","created_at":"2026-05-18T03:06:14.336307+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1311.6335","created_at":"2026-05-18T03:06:14.336307+00:00"},{"alias_kind":"pith_short_12","alias_value":"A6UF7K3CFBRF","created_at":"2026-05-18T12:27:38.830355+00:00"},{"alias_kind":"pith_short_16","alias_value":"A6UF7K3CFBRFPFUC","created_at":"2026-05-18T12:27:38.830355+00:00"},{"alias_kind":"pith_short_8","alias_value":"A6UF7K3C","created_at":"2026-05-18T12:27:38.830355+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/A6UF7K3CFBRFPFUCCKUJMKSJVP","json":"https://pith.science/pith/A6UF7K3CFBRFPFUCCKUJMKSJVP.json","graph_json":"https://pith.science/api/pith-number/A6UF7K3CFBRFPFUCCKUJMKSJVP/graph.json","events_json":"https://pith.science/api/pith-number/A6UF7K3CFBRFPFUCCKUJMKSJVP/events.json","paper":"https://pith.science/paper/A6UF7K3C"},"agent_actions":{"view_html":"https://pith.science/pith/A6UF7K3CFBRFPFUCCKUJMKSJVP","download_json":"https://pith.science/pith/A6UF7K3CFBRFPFUCCKUJMKSJVP.json","view_paper":"https://pith.science/paper/A6UF7K3C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1311.6335&json=true","fetch_graph":"https://pith.science/api/pith-number/A6UF7K3CFBRFPFUCCKUJMKSJVP/graph.json","fetch_events":"https://pith.science/api/pith-number/A6UF7K3CFBRFPFUCCKUJMKSJVP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A6UF7K3CFBRFPFUCCKUJMKSJVP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A6UF7K3CFBRFPFUCCKUJMKSJVP/action/storage_attestation","attest_author":"https://pith.science/pith/A6UF7K3CFBRFPFUCCKUJMKSJVP/action/author_attestation","sign_citation":"https://pith.science/pith/A6UF7K3CFBRFPFUCCKUJMKSJVP/action/citation_signature","submit_replication":"https://pith.science/pith/A6UF7K3CFBRFPFUCCKUJMKSJVP/action/replication_record"}},"created_at":"2026-05-18T03:06:14.336307+00:00","updated_at":"2026-05-18T03:06:14.336307+00:00"}