{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:EQWEU7JEJ3MWKBN5IOG3SPMKVU","short_pith_number":"pith:EQWEU7JE","canonical_record":{"source":{"id":"1810.00511","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2018-10-01T02:58:34Z","cross_cats_sorted":[],"title_canon_sha256":"d112e3427af9de0fba3e3c0824cfb102d1a0b8836d43cf8c2367d4d403831870","abstract_canon_sha256":"ed3b93340dc2fb372ce674ef340ff856297c830aba753e8540a87c044c431a0e"},"schema_version":"1.0"},"canonical_sha256":"242c4a7d244ed96505bd438db93d8aad38c1939bda4449981408b4b25aaae65c","source":{"kind":"arxiv","id":"1810.00511","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.00511","created_at":"2026-05-17T23:59:38Z"},{"alias_kind":"arxiv_version","alias_value":"1810.00511v2","created_at":"2026-05-17T23:59:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.00511","created_at":"2026-05-17T23:59:38Z"},{"alias_kind":"pith_short_12","alias_value":"EQWEU7JEJ3MW","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"EQWEU7JEJ3MWKBN5","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"EQWEU7JE","created_at":"2026-05-18T12:32:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:EQWEU7JEJ3MWKBN5IOG3SPMKVU","target":"record","payload":{"canonical_record":{"source":{"id":"1810.00511","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2018-10-01T02:58:34Z","cross_cats_sorted":[],"title_canon_sha256":"d112e3427af9de0fba3e3c0824cfb102d1a0b8836d43cf8c2367d4d403831870","abstract_canon_sha256":"ed3b93340dc2fb372ce674ef340ff856297c830aba753e8540a87c044c431a0e"},"schema_version":"1.0"},"canonical_sha256":"242c4a7d244ed96505bd438db93d8aad38c1939bda4449981408b4b25aaae65c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:38.227756Z","signature_b64":"j3xJ1idJlbU0XKbD9d6ygQkA+3uA5ZQ5Qqfr2BccWmoEgU+8nbA64kyNQCYBya0agdBRcuxqKhWq1qxvUQvKCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"242c4a7d244ed96505bd438db93d8aad38c1939bda4449981408b4b25aaae65c","last_reissued_at":"2026-05-17T23:59:38.227023Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:38.227023Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.00511","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:59:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CC1zXTxR0edY/D02X6QOszNqUzDmeByZkAtxzxiHGjZO+TKzMzvcmiXQPJkIGehGDTTVpys/bC6quNa0eWIrAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T04:21:49.486962Z"},"content_sha256":"633722cc1c2a24ccd40a5c204fb2bd1c98f58adb472696a90c0554ff3e7be532","schema_version":"1.0","event_id":"sha256:633722cc1c2a24ccd40a5c204fb2bd1c98f58adb472696a90c0554ff3e7be532"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:EQWEU7JEJ3MWKBN5IOG3SPMKVU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Chasing Similarity: Distribution-aware Aggregation Scheduling (Extended Version)","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Anastasios Sidiropoulos, Ario Salmasi, Feilong Liu, Spyros Blanas","submitted_at":"2018-10-01T02:58:34Z","abstract_excerpt":"Parallel aggregation is a ubiquitous operation in data analytics that is expressed as GROUP BY in SQL, reduce in Hadoop, or segment in TensorFlow. Parallel aggregation starts with an optional local pre-aggregation step and then repartitions the intermediate result across the network. While local pre-aggregation works well for low-cardinality aggregations, the network communication cost remains significant for high-cardinality aggregations even after local pre-aggregation. The problem is that the repartition-based algorithm for high-cardinality aggregation does not fully utilize the network.\n  "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.00511","kind":"arxiv","version":2},"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":"2026-05-17T23:59:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kH6hOnUEAwmQFtXEL3FCQxg5fLOO5wqkuDFKySVIrpr0i1uGAQmAaHOyI2Py7WldHrDB/yA9pHz66xiF9OLvCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T04:21:49.487308Z"},"content_sha256":"5118b8a4cf83da2fa71ee8e1542dd899bb56ba589b02f50b68b89f1a6a794016","schema_version":"1.0","event_id":"sha256:5118b8a4cf83da2fa71ee8e1542dd899bb56ba589b02f50b68b89f1a6a794016"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EQWEU7JEJ3MWKBN5IOG3SPMKVU/bundle.json","state_url":"https://pith.science/pith/EQWEU7JEJ3MWKBN5IOG3SPMKVU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EQWEU7JEJ3MWKBN5IOG3SPMKVU/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":"2026-06-02T04:21:49Z","links":{"resolver":"https://pith.science/pith/EQWEU7JEJ3MWKBN5IOG3SPMKVU","bundle":"https://pith.science/pith/EQWEU7JEJ3MWKBN5IOG3SPMKVU/bundle.json","state":"https://pith.science/pith/EQWEU7JEJ3MWKBN5IOG3SPMKVU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EQWEU7JEJ3MWKBN5IOG3SPMKVU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:EQWEU7JEJ3MWKBN5IOG3SPMKVU","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":"ed3b93340dc2fb372ce674ef340ff856297c830aba753e8540a87c044c431a0e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2018-10-01T02:58:34Z","title_canon_sha256":"d112e3427af9de0fba3e3c0824cfb102d1a0b8836d43cf8c2367d4d403831870"},"schema_version":"1.0","source":{"id":"1810.00511","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.00511","created_at":"2026-05-17T23:59:38Z"},{"alias_kind":"arxiv_version","alias_value":"1810.00511v2","created_at":"2026-05-17T23:59:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.00511","created_at":"2026-05-17T23:59:38Z"},{"alias_kind":"pith_short_12","alias_value":"EQWEU7JEJ3MW","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_16","alias_value":"EQWEU7JEJ3MWKBN5","created_at":"2026-05-18T12:32:22Z"},{"alias_kind":"pith_short_8","alias_value":"EQWEU7JE","created_at":"2026-05-18T12:32:22Z"}],"graph_snapshots":[{"event_id":"sha256:5118b8a4cf83da2fa71ee8e1542dd899bb56ba589b02f50b68b89f1a6a794016","target":"graph","created_at":"2026-05-17T23:59:38Z","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":"Parallel aggregation is a ubiquitous operation in data analytics that is expressed as GROUP BY in SQL, reduce in Hadoop, or segment in TensorFlow. Parallel aggregation starts with an optional local pre-aggregation step and then repartitions the intermediate result across the network. While local pre-aggregation works well for low-cardinality aggregations, the network communication cost remains significant for high-cardinality aggregations even after local pre-aggregation. The problem is that the repartition-based algorithm for high-cardinality aggregation does not fully utilize the network.\n  ","authors_text":"Anastasios Sidiropoulos, Ario Salmasi, Feilong Liu, Spyros Blanas","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2018-10-01T02:58:34Z","title":"Chasing Similarity: Distribution-aware Aggregation Scheduling (Extended Version)"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.00511","kind":"arxiv","version":2},"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":"sha256:633722cc1c2a24ccd40a5c204fb2bd1c98f58adb472696a90c0554ff3e7be532","target":"record","created_at":"2026-05-17T23:59:38Z","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":"ed3b93340dc2fb372ce674ef340ff856297c830aba753e8540a87c044c431a0e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2018-10-01T02:58:34Z","title_canon_sha256":"d112e3427af9de0fba3e3c0824cfb102d1a0b8836d43cf8c2367d4d403831870"},"schema_version":"1.0","source":{"id":"1810.00511","kind":"arxiv","version":2}},"canonical_sha256":"242c4a7d244ed96505bd438db93d8aad38c1939bda4449981408b4b25aaae65c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"242c4a7d244ed96505bd438db93d8aad38c1939bda4449981408b4b25aaae65c","first_computed_at":"2026-05-17T23:59:38.227023Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:59:38.227023Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"j3xJ1idJlbU0XKbD9d6ygQkA+3uA5ZQ5Qqfr2BccWmoEgU+8nbA64kyNQCYBya0agdBRcuxqKhWq1qxvUQvKCg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:59:38.227756Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.00511","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:633722cc1c2a24ccd40a5c204fb2bd1c98f58adb472696a90c0554ff3e7be532","sha256:5118b8a4cf83da2fa71ee8e1542dd899bb56ba589b02f50b68b89f1a6a794016"],"state_sha256":"b37fa4d27369ad2873ca95868fda602070ea4379fc46bdd738efb0a86913e180"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mtW5Kr6pyC9wyPIn7ld1kKLn0gQcJVIcZJXnJ6Wzo0U1+c7dYUFczfHIob29PN55Mdx6+Gw74Lqs5owdJNMTCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T04:21:49.489338Z","bundle_sha256":"3eb4062351358c372b1e5b1a9b1bd6ad6a65dd302cac2c657ec8f7a1eb08bf38"}}