{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:GELFD3FQPXZUQL6CPEL2POHJTF","short_pith_number":"pith:GELFD3FQ","canonical_record":{"source":{"id":"1801.02949","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-01-09T14:32:06Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fbffe01c0f0cd610233421dff8b8290cce1a9cac0219b7d03119f36fc5b2a410","abstract_canon_sha256":"5762181e3abae366db0b224c67369ccab2a3b2e2a10cbe93162ba00f491d3c4a"},"schema_version":"1.0"},"canonical_sha256":"311651ecb07df3482fc27917a7b8e9994a9288af50094328dd9fb45bab895939","source":{"kind":"arxiv","id":"1801.02949","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.02949","created_at":"2026-05-18T00:26:21Z"},{"alias_kind":"arxiv_version","alias_value":"1801.02949v1","created_at":"2026-05-18T00:26:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.02949","created_at":"2026-05-18T00:26:21Z"},{"alias_kind":"pith_short_12","alias_value":"GELFD3FQPXZU","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"GELFD3FQPXZUQL6C","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"GELFD3FQ","created_at":"2026-05-18T12:32:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:GELFD3FQPXZUQL6CPEL2POHJTF","target":"record","payload":{"canonical_record":{"source":{"id":"1801.02949","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-01-09T14:32:06Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fbffe01c0f0cd610233421dff8b8290cce1a9cac0219b7d03119f36fc5b2a410","abstract_canon_sha256":"5762181e3abae366db0b224c67369ccab2a3b2e2a10cbe93162ba00f491d3c4a"},"schema_version":"1.0"},"canonical_sha256":"311651ecb07df3482fc27917a7b8e9994a9288af50094328dd9fb45bab895939","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:26:21.947878Z","signature_b64":"hSEuEYbJc0Ph2PhaKfXQYZ7PgTiV91052sjfmir4vXi9wQvsXGCQMER1aQpmedP6HPUa4IXqwZyHJlpPYx82Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"311651ecb07df3482fc27917a7b8e9994a9288af50094328dd9fb45bab895939","last_reissued_at":"2026-05-18T00:26:21.947215Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:26:21.947215Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1801.02949","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":"2026-05-18T00:26:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+SChiIOwMEct75Zqi5Aamuv/y1c/ScZuAnZ2yY1yezEVUFHqdvawlf6isybXFphZQFgfl1NZIBFO5Ys6/9LkBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T06:02:14.487990Z"},"content_sha256":"26108bbcfc5109c1a5d0244616047db6ecc714752c3aa30850c23927a3104d2f","schema_version":"1.0","event_id":"sha256:26108bbcfc5109c1a5d0244616047db6ecc714752c3aa30850c23927a3104d2f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:GELFD3FQPXZUQL6CPEL2POHJTF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An efficient K -means clustering algorithm for massive data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Aritz P\\'erez, Jose A. Lozano, Marco Cap\\'o","submitted_at":"2018-01-09T14:32:06Z","abstract_excerpt":"The analysis of continously larger datasets is a task of major importance in a wide variety of scientific fields. In this sense, cluster analysis algorithms are a key element of exploratory data analysis, due to their easiness in the implementation and relatively low computational cost. Among these algorithms, the K -means algorithm stands out as the most popular approach, besides its high dependency on the initial conditions, as well as to the fact that it might not scale well on massive datasets. In this article, we propose a recursive and parallel approximation to the K -means algorithm tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.02949","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":"2026-05-18T00:26:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7UPcNcUEGi6Ui5hQPCYDJBTakbQM9UZiAK/fhmOkzC9OWWEl3MMfk3qxHeO5EYhQ0YfBaJNlhWifBQ6lXMRwDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T06:02:14.488652Z"},"content_sha256":"91f57da742f8e2952a39de4adea9bb5e8eb599c8ff55dd6f7f89486ccc8419a1","schema_version":"1.0","event_id":"sha256:91f57da742f8e2952a39de4adea9bb5e8eb599c8ff55dd6f7f89486ccc8419a1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GELFD3FQPXZUQL6CPEL2POHJTF/bundle.json","state_url":"https://pith.science/pith/GELFD3FQPXZUQL6CPEL2POHJTF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GELFD3FQPXZUQL6CPEL2POHJTF/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":"2026-06-11T06:02:14Z","links":{"resolver":"https://pith.science/pith/GELFD3FQPXZUQL6CPEL2POHJTF","bundle":"https://pith.science/pith/GELFD3FQPXZUQL6CPEL2POHJTF/bundle.json","state":"https://pith.science/pith/GELFD3FQPXZUQL6CPEL2POHJTF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GELFD3FQPXZUQL6CPEL2POHJTF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:GELFD3FQPXZUQL6CPEL2POHJTF","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":"5762181e3abae366db0b224c67369ccab2a3b2e2a10cbe93162ba00f491d3c4a","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-01-09T14:32:06Z","title_canon_sha256":"fbffe01c0f0cd610233421dff8b8290cce1a9cac0219b7d03119f36fc5b2a410"},"schema_version":"1.0","source":{"id":"1801.02949","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1801.02949","created_at":"2026-05-18T00:26:21Z"},{"alias_kind":"arxiv_version","alias_value":"1801.02949v1","created_at":"2026-05-18T00:26:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1801.02949","created_at":"2026-05-18T00:26:21Z"},{"alias_kind":"pith_short_12","alias_value":"GELFD3FQPXZU","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_16","alias_value":"GELFD3FQPXZUQL6C","created_at":"2026-05-18T12:32:25Z"},{"alias_kind":"pith_short_8","alias_value":"GELFD3FQ","created_at":"2026-05-18T12:32:25Z"}],"graph_snapshots":[{"event_id":"sha256:91f57da742f8e2952a39de4adea9bb5e8eb599c8ff55dd6f7f89486ccc8419a1","target":"graph","created_at":"2026-05-18T00:26:21Z","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 analysis of continously larger datasets is a task of major importance in a wide variety of scientific fields. In this sense, cluster analysis algorithms are a key element of exploratory data analysis, due to their easiness in the implementation and relatively low computational cost. Among these algorithms, the K -means algorithm stands out as the most popular approach, besides its high dependency on the initial conditions, as well as to the fact that it might not scale well on massive datasets. In this article, we propose a recursive and parallel approximation to the K -means algorithm tha","authors_text":"Aritz P\\'erez, Jose A. Lozano, Marco Cap\\'o","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-01-09T14:32:06Z","title":"An efficient K -means clustering algorithm for massive data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1801.02949","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":"sha256:26108bbcfc5109c1a5d0244616047db6ecc714752c3aa30850c23927a3104d2f","target":"record","created_at":"2026-05-18T00:26:21Z","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":"5762181e3abae366db0b224c67369ccab2a3b2e2a10cbe93162ba00f491d3c4a","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-01-09T14:32:06Z","title_canon_sha256":"fbffe01c0f0cd610233421dff8b8290cce1a9cac0219b7d03119f36fc5b2a410"},"schema_version":"1.0","source":{"id":"1801.02949","kind":"arxiv","version":1}},"canonical_sha256":"311651ecb07df3482fc27917a7b8e9994a9288af50094328dd9fb45bab895939","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"311651ecb07df3482fc27917a7b8e9994a9288af50094328dd9fb45bab895939","first_computed_at":"2026-05-18T00:26:21.947215Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:26:21.947215Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hSEuEYbJc0Ph2PhaKfXQYZ7PgTiV91052sjfmir4vXi9wQvsXGCQMER1aQpmedP6HPUa4IXqwZyHJlpPYx82Aw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:26:21.947878Z","signed_message":"canonical_sha256_bytes"},"source_id":"1801.02949","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:26108bbcfc5109c1a5d0244616047db6ecc714752c3aa30850c23927a3104d2f","sha256:91f57da742f8e2952a39de4adea9bb5e8eb599c8ff55dd6f7f89486ccc8419a1"],"state_sha256":"94e28f5cf48b64c8c811a6e439f462d129f24658451f81307c06bd4dbf79a55b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nu/Tp4mbB6KjWvCOEuExPNakpuMt6MvbbzOnMDjD+IzwwTCn1CmEI8H9QiKXMEg5G9UOdcfR2o05nueEGY63DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T06:02:14.492602Z","bundle_sha256":"28035ca7e74529e5e5f5a4b693fa6ecd145cd386d4745cc370418ab0917327ec"}}