{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:47NY4PMOLFIJSTU2UNC7QSLMQY","short_pith_number":"pith:47NY4PMO","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"},"canonical_sha256":"e7db8e3d8e5950994e9aa345f8496c86221568b18ccbd42190db6be723bb599d","source":{"kind":"arxiv","id":"1903.05228","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.05228","created_at":"2026-05-17T23:51:25Z"},{"alias_kind":"arxiv_version","alias_value":"1903.05228v1","created_at":"2026-05-17T23:51:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.05228","created_at":"2026-05-17T23:51:25Z"},{"alias_kind":"pith_short_12","alias_value":"47NY4PMOLFIJ","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"47NY4PMOLFIJSTU2","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"47NY4PMO","created_at":"2026-05-18T12:33:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:47NY4PMOLFIJSTU2UNC7QSLMQY","target":"record","payload":{"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"},"canonical_sha256":"e7db8e3d8e5950994e9aa345f8496c86221568b18ccbd42190db6be723bb599d","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"},"source_kind":"arxiv","source_id":"1903.05228","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:51:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FdnLMQm7AJ1e64+jX4zvdOLxhUfQmuXi8Sp+IvjYQC68PGeYuZe/7o4YDnX/oewnf0z3HvfLl1Z/DngIzD17Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T12:11:54.858772Z"},"content_sha256":"791fe31fba863e2061676832e5e8cbd8b687d29f8f713c3f8be9cc70322835d7","schema_version":"1.0","event_id":"sha256:791fe31fba863e2061676832e5e8cbd8b687d29f8f713c3f8be9cc70322835d7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:47NY4PMOLFIJSTU2UNC7QSLMQY","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:51:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Hol1EdU51TQFtzK0MKmb1vJDyj8Vb1VGN9nSt9kWRur2XNtGrN/NvUfQT3jRuGbfd1axVNpSil5j5dN8ymzPAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T12:11:54.859105Z"},"content_sha256":"58d82ea221749b51b1bea92ff1484ce2e77d0524588da000f048fe2dd8fd5b04","schema_version":"1.0","event_id":"sha256:58d82ea221749b51b1bea92ff1484ce2e77d0524588da000f048fe2dd8fd5b04"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/47NY4PMOLFIJSTU2UNC7QSLMQY/bundle.json","state_url":"https://pith.science/pith/47NY4PMOLFIJSTU2UNC7QSLMQY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/47NY4PMOLFIJSTU2UNC7QSLMQY/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":"2026-06-27T12:11:54Z","links":{"resolver":"https://pith.science/pith/47NY4PMOLFIJSTU2UNC7QSLMQY","bundle":"https://pith.science/pith/47NY4PMOLFIJSTU2UNC7QSLMQY/bundle.json","state":"https://pith.science/pith/47NY4PMOLFIJSTU2UNC7QSLMQY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/47NY4PMOLFIJSTU2UNC7QSLMQY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:47NY4PMOLFIJSTU2UNC7QSLMQY","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":"71908a0f592fff521f9685beee7836fd2a9812c5fd7a5b4fe8eccb2e62c6ae1c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2019-03-12T21:29:08Z","title_canon_sha256":"1e1b4e86096ed0cddb51d958f322ed3bf629e9d5a501a086f2a6a7ad6b006f80"},"schema_version":"1.0","source":{"id":"1903.05228","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.05228","created_at":"2026-05-17T23:51:25Z"},{"alias_kind":"arxiv_version","alias_value":"1903.05228v1","created_at":"2026-05-17T23:51:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.05228","created_at":"2026-05-17T23:51:25Z"},{"alias_kind":"pith_short_12","alias_value":"47NY4PMOLFIJ","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_16","alias_value":"47NY4PMOLFIJSTU2","created_at":"2026-05-18T12:33:10Z"},{"alias_kind":"pith_short_8","alias_value":"47NY4PMO","created_at":"2026-05-18T12:33:10Z"}],"graph_snapshots":[{"event_id":"sha256:58d82ea221749b51b1bea92ff1484ce2e77d0524588da000f048fe2dd8fd5b04","target":"graph","created_at":"2026-05-17T23:51:25Z","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":"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","authors_text":"Hemant Saxena, Ihab F. Ilyas, Lukasz Golab","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2019-03-12T21:29:08Z","title":"Distributed Dependency Discovery"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.05228","kind":"arxiv","version":1},"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":"sha256:791fe31fba863e2061676832e5e8cbd8b687d29f8f713c3f8be9cc70322835d7","target":"record","created_at":"2026-05-17T23:51:25Z","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":"71908a0f592fff521f9685beee7836fd2a9812c5fd7a5b4fe8eccb2e62c6ae1c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2019-03-12T21:29:08Z","title_canon_sha256":"1e1b4e86096ed0cddb51d958f322ed3bf629e9d5a501a086f2a6a7ad6b006f80"},"schema_version":"1.0","source":{"id":"1903.05228","kind":"arxiv","version":1}},"canonical_sha256":"e7db8e3d8e5950994e9aa345f8496c86221568b18ccbd42190db6be723bb599d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e7db8e3d8e5950994e9aa345f8496c86221568b18ccbd42190db6be723bb599d","first_computed_at":"2026-05-17T23:51:25.028812Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:51:25.028812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LIyoRvXpqFNmoqRcWVtZSrJ0ukzkAd3ywfZmZKRrs06a970tlGBY67CJfIthqy5i8hOrXgKtB/OeRVWyai5uBQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:51:25.029520Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.05228","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:791fe31fba863e2061676832e5e8cbd8b687d29f8f713c3f8be9cc70322835d7","sha256:58d82ea221749b51b1bea92ff1484ce2e77d0524588da000f048fe2dd8fd5b04"],"state_sha256":"cc0844478f01f4ffaf68dbf4c101d89f29719ad251001b06d2158e1e8c8cc853"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gQFi0p5ZKrjxa/YQwjjYL189ufx7wI3yG5SRn0VjoRk/WF0Hy8IRFlSt+U4sdUHz67D8y/VSPIyOrm+eMz5KBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-27T12:11:54.861775Z","bundle_sha256":"7ef83069c5a942f91ef83aa081529fc441f67685b642457bf2d8283b563efce0"}}