{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2012:4EPIOFB6QWWXXJD6QN36PECCJ2","short_pith_number":"pith:4EPIOFB6","canonical_record":{"source":{"id":"1203.6402","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2012-03-29T00:06:07Z","cross_cats_sorted":[],"title_canon_sha256":"6a08cf86de757952ccec9892cbc2e74c0d96ffa6d2e9cc10019616581921df05","abstract_canon_sha256":"b1f1b45c4c738c7407f3f9f1af88f4c1e16e4be2bd369b97e7aa8de3496dfdbb"},"schema_version":"1.0"},"canonical_sha256":"e11e87143e85ad7ba47e8377e790424eb3ca254ae26415fdcb6c6fd047f4b14b","source":{"kind":"arxiv","id":"1203.6402","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1203.6402","created_at":"2026-05-18T03:59:02Z"},{"alias_kind":"arxiv_version","alias_value":"1203.6402v1","created_at":"2026-05-18T03:59:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1203.6402","created_at":"2026-05-18T03:59:02Z"},{"alias_kind":"pith_short_12","alias_value":"4EPIOFB6QWWX","created_at":"2026-05-18T12:26:53Z"},{"alias_kind":"pith_short_16","alias_value":"4EPIOFB6QWWXXJD6","created_at":"2026-05-18T12:26:53Z"},{"alias_kind":"pith_short_8","alias_value":"4EPIOFB6","created_at":"2026-05-18T12:26:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2012:4EPIOFB6QWWXXJD6QN36PECCJ2","target":"record","payload":{"canonical_record":{"source":{"id":"1203.6402","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2012-03-29T00:06:07Z","cross_cats_sorted":[],"title_canon_sha256":"6a08cf86de757952ccec9892cbc2e74c0d96ffa6d2e9cc10019616581921df05","abstract_canon_sha256":"b1f1b45c4c738c7407f3f9f1af88f4c1e16e4be2bd369b97e7aa8de3496dfdbb"},"schema_version":"1.0"},"canonical_sha256":"e11e87143e85ad7ba47e8377e790424eb3ca254ae26415fdcb6c6fd047f4b14b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:59:02.624858Z","signature_b64":"i34x10uoyU6LgXln0byVgeOraJuHj1j+W8S6XEhxQ9YNVDOoymAMMVWfYqR59e3V9uxR+fdW/YTN276++ursDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e11e87143e85ad7ba47e8377e790424eb3ca254ae26415fdcb6c6fd047f4b14b","last_reissued_at":"2026-05-18T03:59:02.624181Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:59:02.624181Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1203.6402","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":"2026-05-18T03:59:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DuISjvATTyHzBPy+6tLLU8yUZt/qRiX3iNs3M0MtsBQLocSYe5UpsUm5KzvEXLn+nrbcr38fxb0JF/KLBLlwAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T03:45:49.140737Z"},"content_sha256":"b5fe8e3242f060b988e89ec86866641111cf313960f8e60ff709537aa1f4efc9","schema_version":"1.0","event_id":"sha256:b5fe8e3242f060b988e89ec86866641111cf313960f8e60ff709537aa1f4efc9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2012:4EPIOFB6QWWXXJD6QN36PECCJ2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scalable K-Means++","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Andrea Vattani, Bahman Bahmani, Benjamin Moseley, Ravi Kumar, Sergei Vassilvitskii","submitted_at":"2012-03-29T00:06:07Z","abstract_excerpt":"Over half a century old and showing no signs of aging, k-means remains one of the most popular data processing algorithms. As is well-known, a proper initialization of k-means is crucial for obtaining a good final solution. The recently proposed k-means++ initialization algorithm achieves this, obtaining an initial set of centers that is provably close to the optimum solution. A major downside of the k-means++ is its inherent sequential nature, which limits its applicability to massive data: one must make k passes over the data to find a good initial set of centers. In this work we show how to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1203.6402","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":"2026-05-18T03:59:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TFmnhk73cw815ILnXAzK0/vQtmIfj93L5/xzA2iCDItf6ijwZwqfM8MxEiaT8ECKe4nZtsYLeLP6+zqLXu//Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T03:45:49.141081Z"},"content_sha256":"60d9d30fee7d0deea3f5871b7b7de234037b9ade77d06b245b3a4d042d98e610","schema_version":"1.0","event_id":"sha256:60d9d30fee7d0deea3f5871b7b7de234037b9ade77d06b245b3a4d042d98e610"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4EPIOFB6QWWXXJD6QN36PECCJ2/bundle.json","state_url":"https://pith.science/pith/4EPIOFB6QWWXXJD6QN36PECCJ2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4EPIOFB6QWWXXJD6QN36PECCJ2/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":"2026-06-01T03:45:49Z","links":{"resolver":"https://pith.science/pith/4EPIOFB6QWWXXJD6QN36PECCJ2","bundle":"https://pith.science/pith/4EPIOFB6QWWXXJD6QN36PECCJ2/bundle.json","state":"https://pith.science/pith/4EPIOFB6QWWXXJD6QN36PECCJ2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4EPIOFB6QWWXXJD6QN36PECCJ2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:4EPIOFB6QWWXXJD6QN36PECCJ2","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":"b1f1b45c4c738c7407f3f9f1af88f4c1e16e4be2bd369b97e7aa8de3496dfdbb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2012-03-29T00:06:07Z","title_canon_sha256":"6a08cf86de757952ccec9892cbc2e74c0d96ffa6d2e9cc10019616581921df05"},"schema_version":"1.0","source":{"id":"1203.6402","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1203.6402","created_at":"2026-05-18T03:59:02Z"},{"alias_kind":"arxiv_version","alias_value":"1203.6402v1","created_at":"2026-05-18T03:59:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1203.6402","created_at":"2026-05-18T03:59:02Z"},{"alias_kind":"pith_short_12","alias_value":"4EPIOFB6QWWX","created_at":"2026-05-18T12:26:53Z"},{"alias_kind":"pith_short_16","alias_value":"4EPIOFB6QWWXXJD6","created_at":"2026-05-18T12:26:53Z"},{"alias_kind":"pith_short_8","alias_value":"4EPIOFB6","created_at":"2026-05-18T12:26:53Z"}],"graph_snapshots":[{"event_id":"sha256:60d9d30fee7d0deea3f5871b7b7de234037b9ade77d06b245b3a4d042d98e610","target":"graph","created_at":"2026-05-18T03:59:02Z","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":"Over half a century old and showing no signs of aging, k-means remains one of the most popular data processing algorithms. As is well-known, a proper initialization of k-means is crucial for obtaining a good final solution. The recently proposed k-means++ initialization algorithm achieves this, obtaining an initial set of centers that is provably close to the optimum solution. A major downside of the k-means++ is its inherent sequential nature, which limits its applicability to massive data: one must make k passes over the data to find a good initial set of centers. In this work we show how to","authors_text":"Andrea Vattani, Bahman Bahmani, Benjamin Moseley, Ravi Kumar, Sergei Vassilvitskii","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2012-03-29T00:06:07Z","title":"Scalable K-Means++"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1203.6402","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:b5fe8e3242f060b988e89ec86866641111cf313960f8e60ff709537aa1f4efc9","target":"record","created_at":"2026-05-18T03:59:02Z","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":"b1f1b45c4c738c7407f3f9f1af88f4c1e16e4be2bd369b97e7aa8de3496dfdbb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2012-03-29T00:06:07Z","title_canon_sha256":"6a08cf86de757952ccec9892cbc2e74c0d96ffa6d2e9cc10019616581921df05"},"schema_version":"1.0","source":{"id":"1203.6402","kind":"arxiv","version":1}},"canonical_sha256":"e11e87143e85ad7ba47e8377e790424eb3ca254ae26415fdcb6c6fd047f4b14b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e11e87143e85ad7ba47e8377e790424eb3ca254ae26415fdcb6c6fd047f4b14b","first_computed_at":"2026-05-18T03:59:02.624181Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:59:02.624181Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"i34x10uoyU6LgXln0byVgeOraJuHj1j+W8S6XEhxQ9YNVDOoymAMMVWfYqR59e3V9uxR+fdW/YTN276++ursDw==","signature_status":"signed_v1","signed_at":"2026-05-18T03:59:02.624858Z","signed_message":"canonical_sha256_bytes"},"source_id":"1203.6402","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b5fe8e3242f060b988e89ec86866641111cf313960f8e60ff709537aa1f4efc9","sha256:60d9d30fee7d0deea3f5871b7b7de234037b9ade77d06b245b3a4d042d98e610"],"state_sha256":"80e47bf7d1785f8f692fed2aac188c616c9360487f98fc9fdb8c54208293d457"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nwDPJDq2bA0d7HP02uN7ZVj77uNMFSXOS0LVExJLV2iDiLkIH6HGIrSSNJnAa7/meW2WeR2HE2Dhiwysw9+DBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T03:45:49.143129Z","bundle_sha256":"32f274e2c968d19520c8d524186ecff743596fe38a216b3c220be923c43cc518"}}