{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:ZMIBXYUAMKXT44IZNLXVUJSUNL","short_pith_number":"pith:ZMIBXYUA","canonical_record":{"source":{"id":"1702.00196","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2017-02-01T10:30:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"de63968f76476269dc1ed690f65c1c572f699b770a37ace7c1a4c3eae85ca62b","abstract_canon_sha256":"8085e867d8d656ad795ce7b4f3d5a131e87ea73d0732c13276641befbea6539b"},"schema_version":"1.0"},"canonical_sha256":"cb101be28062af3e71196aef5a26546ad480b7c204ead1a7d612fa6d517e2ac1","source":{"kind":"arxiv","id":"1702.00196","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.00196","created_at":"2026-05-18T00:51:34Z"},{"alias_kind":"arxiv_version","alias_value":"1702.00196v1","created_at":"2026-05-18T00:51:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.00196","created_at":"2026-05-18T00:51:34Z"},{"alias_kind":"pith_short_12","alias_value":"ZMIBXYUAMKXT","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_16","alias_value":"ZMIBXYUAMKXT44IZ","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_8","alias_value":"ZMIBXYUA","created_at":"2026-05-18T12:31:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:ZMIBXYUAMKXT44IZNLXVUJSUNL","target":"record","payload":{"canonical_record":{"source":{"id":"1702.00196","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2017-02-01T10:30:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"de63968f76476269dc1ed690f65c1c572f699b770a37ace7c1a4c3eae85ca62b","abstract_canon_sha256":"8085e867d8d656ad795ce7b4f3d5a131e87ea73d0732c13276641befbea6539b"},"schema_version":"1.0"},"canonical_sha256":"cb101be28062af3e71196aef5a26546ad480b7c204ead1a7d612fa6d517e2ac1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:51:34.987021Z","signature_b64":"dzdCFCzPCR2ZlcxaBibbyXI2g15h6aW7+5nt7xZ3myWqL6d6LaKKJ4A/YcBlOKgYSVDLOa82a13d4fPw4w08Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cb101be28062af3e71196aef5a26546ad480b7c204ead1a7d612fa6d517e2ac1","last_reissued_at":"2026-05-18T00:51:34.986413Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:51:34.986413Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1702.00196","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":"2026-05-18T00:51:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xj5KZdQN5d16sdMrHKQHcOr6SoGaOXhjN/FlNKOzLHvyeuUGLSsRTEJb3Q1d6zxSDVXB0rvCjTk0IZAxzY3uCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T01:43:45.108983Z"},"content_sha256":"d5531b8d1ce8e2e02bcb9b6240b9b75130ffdf5b9a90a26cd0615647a9aaf736","schema_version":"1.0","event_id":"sha256:d5531b8d1ce8e2e02bcb9b6240b9b75130ffdf5b9a90a26cd0615647a9aaf736"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:ZMIBXYUAMKXT44IZNLXVUJSUNL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Communication-Optimal Distributed Clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DS","authors_text":"David P. Woodruff, He Sun, Jiecao Chen, Qin Zhang","submitted_at":"2017-02-01T10:30:32Z","abstract_excerpt":"Clustering large datasets is a fundamental problem with a number of applications in machine learning. Data is often collected on different sites and clustering needs to be performed in a distributed manner with low communication. We would like the quality of the clustering in the distributed setting to match that in the centralized setting for which all the data resides on a single site. In this work, we study both graph and geometric clustering problems in two distributed models: (1) a point-to-point model, and (2) a model with a broadcast channel. We give protocols in both models which we sh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.00196","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":"2026-05-18T00:51:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HtXKSl4GBqmbxTdrbnqSQ7AbMFDLyIyZxi9UKu5XX+R59TteUkJO6/KwLDCQ1aZJDepxazuOtWVq6c+l592bAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T01:43:45.109879Z"},"content_sha256":"f6dcae7006fc007311b15a70d6fb0a514a980e46c557c2bfd46f609787b37358","schema_version":"1.0","event_id":"sha256:f6dcae7006fc007311b15a70d6fb0a514a980e46c557c2bfd46f609787b37358"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZMIBXYUAMKXT44IZNLXVUJSUNL/bundle.json","state_url":"https://pith.science/pith/ZMIBXYUAMKXT44IZNLXVUJSUNL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZMIBXYUAMKXT44IZNLXVUJSUNL/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":"2026-06-11T01:43:45Z","links":{"resolver":"https://pith.science/pith/ZMIBXYUAMKXT44IZNLXVUJSUNL","bundle":"https://pith.science/pith/ZMIBXYUAMKXT44IZNLXVUJSUNL/bundle.json","state":"https://pith.science/pith/ZMIBXYUAMKXT44IZNLXVUJSUNL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZMIBXYUAMKXT44IZNLXVUJSUNL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:ZMIBXYUAMKXT44IZNLXVUJSUNL","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":"8085e867d8d656ad795ce7b4f3d5a131e87ea73d0732c13276641befbea6539b","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2017-02-01T10:30:32Z","title_canon_sha256":"de63968f76476269dc1ed690f65c1c572f699b770a37ace7c1a4c3eae85ca62b"},"schema_version":"1.0","source":{"id":"1702.00196","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.00196","created_at":"2026-05-18T00:51:34Z"},{"alias_kind":"arxiv_version","alias_value":"1702.00196v1","created_at":"2026-05-18T00:51:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.00196","created_at":"2026-05-18T00:51:34Z"},{"alias_kind":"pith_short_12","alias_value":"ZMIBXYUAMKXT","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_16","alias_value":"ZMIBXYUAMKXT44IZ","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_8","alias_value":"ZMIBXYUA","created_at":"2026-05-18T12:31:59Z"}],"graph_snapshots":[{"event_id":"sha256:f6dcae7006fc007311b15a70d6fb0a514a980e46c557c2bfd46f609787b37358","target":"graph","created_at":"2026-05-18T00:51:34Z","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":"Clustering large datasets is a fundamental problem with a number of applications in machine learning. Data is often collected on different sites and clustering needs to be performed in a distributed manner with low communication. We would like the quality of the clustering in the distributed setting to match that in the centralized setting for which all the data resides on a single site. In this work, we study both graph and geometric clustering problems in two distributed models: (1) a point-to-point model, and (2) a model with a broadcast channel. We give protocols in both models which we sh","authors_text":"David P. Woodruff, He Sun, Jiecao Chen, Qin Zhang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2017-02-01T10:30:32Z","title":"Communication-Optimal Distributed Clustering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.00196","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:d5531b8d1ce8e2e02bcb9b6240b9b75130ffdf5b9a90a26cd0615647a9aaf736","target":"record","created_at":"2026-05-18T00:51:34Z","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":"8085e867d8d656ad795ce7b4f3d5a131e87ea73d0732c13276641befbea6539b","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2017-02-01T10:30:32Z","title_canon_sha256":"de63968f76476269dc1ed690f65c1c572f699b770a37ace7c1a4c3eae85ca62b"},"schema_version":"1.0","source":{"id":"1702.00196","kind":"arxiv","version":1}},"canonical_sha256":"cb101be28062af3e71196aef5a26546ad480b7c204ead1a7d612fa6d517e2ac1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cb101be28062af3e71196aef5a26546ad480b7c204ead1a7d612fa6d517e2ac1","first_computed_at":"2026-05-18T00:51:34.986413Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:51:34.986413Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dzdCFCzPCR2ZlcxaBibbyXI2g15h6aW7+5nt7xZ3myWqL6d6LaKKJ4A/YcBlOKgYSVDLOa82a13d4fPw4w08Cw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:51:34.987021Z","signed_message":"canonical_sha256_bytes"},"source_id":"1702.00196","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d5531b8d1ce8e2e02bcb9b6240b9b75130ffdf5b9a90a26cd0615647a9aaf736","sha256:f6dcae7006fc007311b15a70d6fb0a514a980e46c557c2bfd46f609787b37358"],"state_sha256":"c756b6e23f0474aa968ddd1f3a489cef0d87dee131349e2b8ec769f0b4335557"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m9GSWlNYRnMmEoeISNdVfdWVDjM3CPkxyghVWbwh8ckNH+AozRmbNOtCouZH57uEBl4BwwoUZ3mWD/rvbUfEBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T01:43:45.114449Z","bundle_sha256":"71b82a8f44cc6afe65a1f79b42d3e3cb4f75cb9071763d796010b2d12c4a17e2"}}