{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:YFJDNWRNPNMO7STKD3NZG42YJO","short_pith_number":"pith:YFJDNWRN","canonical_record":{"source":{"id":"1805.05874","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2018-05-15T16:07:53Z","cross_cats_sorted":["cs.DB"],"title_canon_sha256":"2ba6617cc83d6ab12fad31ec39b91f4a2238cb59dc6472fb7dfa1ef774350cb1","abstract_canon_sha256":"dbbc74561ac8dcc3409d701a2650d5728368281fa7e65cad3adbcd0c226afa0f"},"schema_version":"1.0"},"canonical_sha256":"c15236da2d7b58efca6a1edb9373584bbe57fe0ec9d596fc1466d677992e92bf","source":{"kind":"arxiv","id":"1805.05874","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.05874","created_at":"2026-05-18T00:15:53Z"},{"alias_kind":"arxiv_version","alias_value":"1805.05874v1","created_at":"2026-05-18T00:15:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.05874","created_at":"2026-05-18T00:15:53Z"},{"alias_kind":"pith_short_12","alias_value":"YFJDNWRNPNMO","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"YFJDNWRNPNMO7STK","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"YFJDNWRN","created_at":"2026-05-18T12:33:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:YFJDNWRNPNMO7STKD3NZG42YJO","target":"record","payload":{"canonical_record":{"source":{"id":"1805.05874","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2018-05-15T16:07:53Z","cross_cats_sorted":["cs.DB"],"title_canon_sha256":"2ba6617cc83d6ab12fad31ec39b91f4a2238cb59dc6472fb7dfa1ef774350cb1","abstract_canon_sha256":"dbbc74561ac8dcc3409d701a2650d5728368281fa7e65cad3adbcd0c226afa0f"},"schema_version":"1.0"},"canonical_sha256":"c15236da2d7b58efca6a1edb9373584bbe57fe0ec9d596fc1466d677992e92bf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:53.415382Z","signature_b64":"ZR5o4Z/YKMqo9hA6U2R7bWlJJdb+104M4W8iDIkhTDGLzd+WD7tmKNT7hb7jvWCSNXVGH5jqSJ2oqfwonhE8AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c15236da2d7b58efca6a1edb9373584bbe57fe0ec9d596fc1466d677992e92bf","last_reissued_at":"2026-05-18T00:15:53.414621Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:53.414621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.05874","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":"2026-05-18T00:15:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m2NGo1lrfAlSs9mIj2RxEuw1RCNjWRzKm3/lSBpShHjUEMtIyGztj6DQV10PCeLThssg9HAUclW73ALlNhKPAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T05:03:24.864885Z"},"content_sha256":"d8b057414b4ea9e84782c201715756412c1c642f0526abafa23b7023ee2e1e81","schema_version":"1.0","event_id":"sha256:d8b057414b4ea9e84782c201715756412c1c642f0526abafa23b7023ee2e1e81"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:YFJDNWRNPNMO7STKD3NZG42YJO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Approximate Distributed Joins in Apache Spark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.DC","authors_text":"Christof Fetzer, Do Le Quoc, Istemi Ekin Akkus, Pramod Bhatotia, Ruichuan Chen, Spyros Blanas, Thorsten Strufe","submitted_at":"2018-05-15T16:07:53Z","abstract_excerpt":"The join operation is a fundamental building block of parallel data processing. Unfortunately, it is very resource-intensive to compute an equi-join across massive datasets. The approximate computing paradigm allows users to trade accuracy and latency for expensive data processing operations. The equi-join operator is thus a natural candidate for optimization using approximation techniques. Although sampling-based approaches are widely used for approximation, sampling over joins is a compelling but challenging task regarding the output quality. Naive approaches, which perform joins over datase"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.05874","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":"2026-05-18T00:15:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"28gdngXeCTWnJu/jJaQoOApimMksPsQ/P6EADxXAgYTUepQcs2ibz8PZlJfoxae9O3hlvz2MJOdq0ju6RALuAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T05:03:24.865570Z"},"content_sha256":"05b084b57011e7e10831c455a1774074c2c749589d871c636b8e6fb68f5339ae","schema_version":"1.0","event_id":"sha256:05b084b57011e7e10831c455a1774074c2c749589d871c636b8e6fb68f5339ae"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YFJDNWRNPNMO7STKD3NZG42YJO/bundle.json","state_url":"https://pith.science/pith/YFJDNWRNPNMO7STKD3NZG42YJO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YFJDNWRNPNMO7STKD3NZG42YJO/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":"2026-06-07T05:03:24Z","links":{"resolver":"https://pith.science/pith/YFJDNWRNPNMO7STKD3NZG42YJO","bundle":"https://pith.science/pith/YFJDNWRNPNMO7STKD3NZG42YJO/bundle.json","state":"https://pith.science/pith/YFJDNWRNPNMO7STKD3NZG42YJO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YFJDNWRNPNMO7STKD3NZG42YJO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:YFJDNWRNPNMO7STKD3NZG42YJO","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":"dbbc74561ac8dcc3409d701a2650d5728368281fa7e65cad3adbcd0c226afa0f","cross_cats_sorted":["cs.DB"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2018-05-15T16:07:53Z","title_canon_sha256":"2ba6617cc83d6ab12fad31ec39b91f4a2238cb59dc6472fb7dfa1ef774350cb1"},"schema_version":"1.0","source":{"id":"1805.05874","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.05874","created_at":"2026-05-18T00:15:53Z"},{"alias_kind":"arxiv_version","alias_value":"1805.05874v1","created_at":"2026-05-18T00:15:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.05874","created_at":"2026-05-18T00:15:53Z"},{"alias_kind":"pith_short_12","alias_value":"YFJDNWRNPNMO","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"YFJDNWRNPNMO7STK","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"YFJDNWRN","created_at":"2026-05-18T12:33:04Z"}],"graph_snapshots":[{"event_id":"sha256:05b084b57011e7e10831c455a1774074c2c749589d871c636b8e6fb68f5339ae","target":"graph","created_at":"2026-05-18T00:15:53Z","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":"The join operation is a fundamental building block of parallel data processing. Unfortunately, it is very resource-intensive to compute an equi-join across massive datasets. The approximate computing paradigm allows users to trade accuracy and latency for expensive data processing operations. The equi-join operator is thus a natural candidate for optimization using approximation techniques. Although sampling-based approaches are widely used for approximation, sampling over joins is a compelling but challenging task regarding the output quality. Naive approaches, which perform joins over datase","authors_text":"Christof Fetzer, Do Le Quoc, Istemi Ekin Akkus, Pramod Bhatotia, Ruichuan Chen, Spyros Blanas, Thorsten Strufe","cross_cats":["cs.DB"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2018-05-15T16:07:53Z","title":"Approximate Distributed Joins in Apache Spark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.05874","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:d8b057414b4ea9e84782c201715756412c1c642f0526abafa23b7023ee2e1e81","target":"record","created_at":"2026-05-18T00:15:53Z","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":"dbbc74561ac8dcc3409d701a2650d5728368281fa7e65cad3adbcd0c226afa0f","cross_cats_sorted":["cs.DB"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2018-05-15T16:07:53Z","title_canon_sha256":"2ba6617cc83d6ab12fad31ec39b91f4a2238cb59dc6472fb7dfa1ef774350cb1"},"schema_version":"1.0","source":{"id":"1805.05874","kind":"arxiv","version":1}},"canonical_sha256":"c15236da2d7b58efca6a1edb9373584bbe57fe0ec9d596fc1466d677992e92bf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c15236da2d7b58efca6a1edb9373584bbe57fe0ec9d596fc1466d677992e92bf","first_computed_at":"2026-05-18T00:15:53.414621Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:15:53.414621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZR5o4Z/YKMqo9hA6U2R7bWlJJdb+104M4W8iDIkhTDGLzd+WD7tmKNT7hb7jvWCSNXVGH5jqSJ2oqfwonhE8AA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:15:53.415382Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.05874","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d8b057414b4ea9e84782c201715756412c1c642f0526abafa23b7023ee2e1e81","sha256:05b084b57011e7e10831c455a1774074c2c749589d871c636b8e6fb68f5339ae"],"state_sha256":"74603eb29968b359bcf8b4de04f8df02fa2c5e96224230d126e319186246e1e1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iTwaL3EiWN22ROGoWrV8S3QTIf5GfXpwvee+jnx0G6wJgPUBl/3jSSrAtxwrgmwOYDMqnllEeWeWwbRcV2aWCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T05:03:24.869107Z","bundle_sha256":"21123a2c65a04a9fdef8f6c7547064f3ee7104bee8f73d4bf564fb89189da916"}}