{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:47NY4PMOLFIJSTU2UNC7QSLMQY","short_pith_number":"pith:47NY4PMO","schema_version":"1.0","canonical_sha256":"e7db8e3d8e5950994e9aa345f8496c86221568b18ccbd42190db6be723bb599d","source":{"kind":"arxiv","id":"1903.05228","version":1},"attestation_state":"computed","paper":{"title":"Distributed Dependency Discovery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Hemant Saxena, Ihab F. Ilyas, Lukasz Golab","submitted_at":"2019-03-12T21:29:08Z","abstract_excerpt":"We analyze the problem of discovering dependencies from distributed big data. Existing (non-distributed) algorithms focus on minimizing computation by pruning the search space of possible dependencies. However, distributed algorithms must also optimize communication costs, especially in shared-nothing settings, leading to a more complex optimization space. To understand this space, we introduce six primitives shared by existing dependency discovery algorithms, corresponding to data processing steps separated by communication barriers. Through case studies, we show how the primitives allow us t"},"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":"1903.05228","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2019-03-12T21:29:08Z","cross_cats_sorted":[],"title_canon_sha256":"1e1b4e86096ed0cddb51d958f322ed3bf629e9d5a501a086f2a6a7ad6b006f80","abstract_canon_sha256":"71908a0f592fff521f9685beee7836fd2a9812c5fd7a5b4fe8eccb2e62c6ae1c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:25.029520Z","signature_b64":"LIyoRvXpqFNmoqRcWVtZSrJ0ukzkAd3ywfZmZKRrs06a970tlGBY67CJfIthqy5i8hOrXgKtB/OeRVWyai5uBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7db8e3d8e5950994e9aa345f8496c86221568b18ccbd42190db6be723bb599d","last_reissued_at":"2026-05-17T23:51:25.028812Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:25.028812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distributed Dependency Discovery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Hemant Saxena, Ihab F. Ilyas, Lukasz Golab","submitted_at":"2019-03-12T21:29:08Z","abstract_excerpt":"We analyze the problem of discovering dependencies from distributed big data. Existing (non-distributed) algorithms focus on minimizing computation by pruning the search space of possible dependencies. However, distributed algorithms must also optimize communication costs, especially in shared-nothing settings, leading to a more complex optimization space. To understand this space, we introduce six primitives shared by existing dependency discovery algorithms, corresponding to data processing steps separated by communication barriers. Through case studies, we show how the primitives allow us t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.05228","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":"1903.05228","created_at":"2026-05-17T23:51:25.028912+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.05228v1","created_at":"2026-05-17T23:51:25.028912+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.05228","created_at":"2026-05-17T23:51:25.028912+00:00"},{"alias_kind":"pith_short_12","alias_value":"47NY4PMOLFIJ","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_16","alias_value":"47NY4PMOLFIJSTU2","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_8","alias_value":"47NY4PMO","created_at":"2026-05-18T12:33:10.108867+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/47NY4PMOLFIJSTU2UNC7QSLMQY","json":"https://pith.science/pith/47NY4PMOLFIJSTU2UNC7QSLMQY.json","graph_json":"https://pith.science/api/pith-number/47NY4PMOLFIJSTU2UNC7QSLMQY/graph.json","events_json":"https://pith.science/api/pith-number/47NY4PMOLFIJSTU2UNC7QSLMQY/events.json","paper":"https://pith.science/paper/47NY4PMO"},"agent_actions":{"view_html":"https://pith.science/pith/47NY4PMOLFIJSTU2UNC7QSLMQY","download_json":"https://pith.science/pith/47NY4PMOLFIJSTU2UNC7QSLMQY.json","view_paper":"https://pith.science/paper/47NY4PMO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.05228&json=true","fetch_graph":"https://pith.science/api/pith-number/47NY4PMOLFIJSTU2UNC7QSLMQY/graph.json","fetch_events":"https://pith.science/api/pith-number/47NY4PMOLFIJSTU2UNC7QSLMQY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/47NY4PMOLFIJSTU2UNC7QSLMQY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/47NY4PMOLFIJSTU2UNC7QSLMQY/action/storage_attestation","attest_author":"https://pith.science/pith/47NY4PMOLFIJSTU2UNC7QSLMQY/action/author_attestation","sign_citation":"https://pith.science/pith/47NY4PMOLFIJSTU2UNC7QSLMQY/action/citation_signature","submit_replication":"https://pith.science/pith/47NY4PMOLFIJSTU2UNC7QSLMQY/action/replication_record"}},"created_at":"2026-05-17T23:51:25.028912+00:00","updated_at":"2026-05-17T23:51:25.028912+00:00"}