{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:PS6JQ57CDR3TUUNNQBOZ5V7G2Y","short_pith_number":"pith:PS6JQ57C","canonical_record":{"source":{"id":"1511.05933","kind":"arxiv","version":8},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-18T20:26:42Z","cross_cats_sorted":[],"title_canon_sha256":"35858d9d8429a42e3cc69b94263b9eb7beb139c80da3480aad912065fc1371b8","abstract_canon_sha256":"32ca5931adb985cf388e13b7a04d7384b30d2cfa658b7e35a4db8d3d56cafaff"},"schema_version":"1.0"},"canonical_sha256":"7cbc9877e21c773a51ad805d9ed7e6d602dcc141028838c34a29e2c8297a779f","source":{"kind":"arxiv","id":"1511.05933","version":8},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1511.05933","created_at":"2026-05-18T01:00:53Z"},{"alias_kind":"arxiv_version","alias_value":"1511.05933v8","created_at":"2026-05-18T01:00:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.05933","created_at":"2026-05-18T01:00:53Z"},{"alias_kind":"pith_short_12","alias_value":"PS6JQ57CDR3T","created_at":"2026-05-18T12:29:37Z"},{"alias_kind":"pith_short_16","alias_value":"PS6JQ57CDR3TUUNN","created_at":"2026-05-18T12:29:37Z"},{"alias_kind":"pith_short_8","alias_value":"PS6JQ57C","created_at":"2026-05-18T12:29:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:PS6JQ57CDR3TUUNNQBOZ5V7G2Y","target":"record","payload":{"canonical_record":{"source":{"id":"1511.05933","kind":"arxiv","version":8},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-18T20:26:42Z","cross_cats_sorted":[],"title_canon_sha256":"35858d9d8429a42e3cc69b94263b9eb7beb139c80da3480aad912065fc1371b8","abstract_canon_sha256":"32ca5931adb985cf388e13b7a04d7384b30d2cfa658b7e35a4db8d3d56cafaff"},"schema_version":"1.0"},"canonical_sha256":"7cbc9877e21c773a51ad805d9ed7e6d602dcc141028838c34a29e2c8297a779f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:00:53.585626Z","signature_b64":"VjY0BupFA5wYjlO4tl/w3FldcKzvb25lcSTLvj0vsqQepBpeXZOjKDhert6WvY/uRn7ni5RqSlJ0A+Q9GY/6Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7cbc9877e21c773a51ad805d9ed7e6d602dcc141028838c34a29e2c8297a779f","last_reissued_at":"2026-05-18T01:00:53.585141Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:00:53.585141Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1511.05933","source_version":8,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:00:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eqHTpeLCMb/R0Z8Gakv2HPLJeE/8iBbxtcgDhYfLcJ6p8fN98K83AlYD0L+6YF/E7FGXD+btOp8XLFsn29wRBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T16:58:06.265141Z"},"content_sha256":"c33db49614c7edd6a22f83442df07b99a0419a2bddf4805779280913ffc487b7","schema_version":"1.0","event_id":"sha256:c33db49614c7edd6a22f83442df07b99a0419a2bddf4805779280913ffc487b7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:PS6JQ57CDR3TUUNNQBOZ5V7G2Y","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Seeding K-Means using Method of Moments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Sayantan Dasgupta","submitted_at":"2015-11-18T20:26:42Z","abstract_excerpt":"K-means is one of the most widely used algorithms for clustering in Data Mining applications, which attempts to minimize the sum of the square of the Euclidean distance of the points in the clusters from the respective means of the clusters. However, K-means suffers from local minima problem and is not guaranteed to converge to the optimal cost. K-means++ tries to address the problem by seeding the means using a distance-based sampling scheme. However, seeding the means in K-means++ needs $O\\left(K\\right)$ sequential passes through the entire dataset, and this can be very costly for large data"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.05933","kind":"arxiv","version":8},"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":"2026-05-18T01:00:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WHo1XdOSiW4KhRWUvsiwr0q3o5ibNEmQw2toWbLnSb7eb0pRiEE7/FQNzc+KuGBRTPLVX74OcBhZrd2NOUu3Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T16:58:06.265876Z"},"content_sha256":"3a289db31e47460bfe66129da4d5546f98a76e7d8142085b02816a3d10aa2b4c","schema_version":"1.0","event_id":"sha256:3a289db31e47460bfe66129da4d5546f98a76e7d8142085b02816a3d10aa2b4c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PS6JQ57CDR3TUUNNQBOZ5V7G2Y/bundle.json","state_url":"https://pith.science/pith/PS6JQ57CDR3TUUNNQBOZ5V7G2Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PS6JQ57CDR3TUUNNQBOZ5V7G2Y/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":"2026-06-10T16:58:06Z","links":{"resolver":"https://pith.science/pith/PS6JQ57CDR3TUUNNQBOZ5V7G2Y","bundle":"https://pith.science/pith/PS6JQ57CDR3TUUNNQBOZ5V7G2Y/bundle.json","state":"https://pith.science/pith/PS6JQ57CDR3TUUNNQBOZ5V7G2Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PS6JQ57CDR3TUUNNQBOZ5V7G2Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:PS6JQ57CDR3TUUNNQBOZ5V7G2Y","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":"32ca5931adb985cf388e13b7a04d7384b30d2cfa658b7e35a4db8d3d56cafaff","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-18T20:26:42Z","title_canon_sha256":"35858d9d8429a42e3cc69b94263b9eb7beb139c80da3480aad912065fc1371b8"},"schema_version":"1.0","source":{"id":"1511.05933","kind":"arxiv","version":8}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1511.05933","created_at":"2026-05-18T01:00:53Z"},{"alias_kind":"arxiv_version","alias_value":"1511.05933v8","created_at":"2026-05-18T01:00:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.05933","created_at":"2026-05-18T01:00:53Z"},{"alias_kind":"pith_short_12","alias_value":"PS6JQ57CDR3T","created_at":"2026-05-18T12:29:37Z"},{"alias_kind":"pith_short_16","alias_value":"PS6JQ57CDR3TUUNN","created_at":"2026-05-18T12:29:37Z"},{"alias_kind":"pith_short_8","alias_value":"PS6JQ57C","created_at":"2026-05-18T12:29:37Z"}],"graph_snapshots":[{"event_id":"sha256:3a289db31e47460bfe66129da4d5546f98a76e7d8142085b02816a3d10aa2b4c","target":"graph","created_at":"2026-05-18T01:00:53Z","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":"K-means is one of the most widely used algorithms for clustering in Data Mining applications, which attempts to minimize the sum of the square of the Euclidean distance of the points in the clusters from the respective means of the clusters. However, K-means suffers from local minima problem and is not guaranteed to converge to the optimal cost. K-means++ tries to address the problem by seeding the means using a distance-based sampling scheme. However, seeding the means in K-means++ needs $O\\left(K\\right)$ sequential passes through the entire dataset, and this can be very costly for large data","authors_text":"Sayantan Dasgupta","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-18T20:26:42Z","title":"Seeding K-Means using Method of Moments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.05933","kind":"arxiv","version":8},"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:c33db49614c7edd6a22f83442df07b99a0419a2bddf4805779280913ffc487b7","target":"record","created_at":"2026-05-18T01:00:53Z","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":"32ca5931adb985cf388e13b7a04d7384b30d2cfa658b7e35a4db8d3d56cafaff","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-18T20:26:42Z","title_canon_sha256":"35858d9d8429a42e3cc69b94263b9eb7beb139c80da3480aad912065fc1371b8"},"schema_version":"1.0","source":{"id":"1511.05933","kind":"arxiv","version":8}},"canonical_sha256":"7cbc9877e21c773a51ad805d9ed7e6d602dcc141028838c34a29e2c8297a779f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7cbc9877e21c773a51ad805d9ed7e6d602dcc141028838c34a29e2c8297a779f","first_computed_at":"2026-05-18T01:00:53.585141Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:00:53.585141Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VjY0BupFA5wYjlO4tl/w3FldcKzvb25lcSTLvj0vsqQepBpeXZOjKDhert6WvY/uRn7ni5RqSlJ0A+Q9GY/6Bw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:00:53.585626Z","signed_message":"canonical_sha256_bytes"},"source_id":"1511.05933","source_kind":"arxiv","source_version":8}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c33db49614c7edd6a22f83442df07b99a0419a2bddf4805779280913ffc487b7","sha256:3a289db31e47460bfe66129da4d5546f98a76e7d8142085b02816a3d10aa2b4c"],"state_sha256":"080d785ae2a9ba08d3b6af73128a94ad877da5ae2c8e94cedb453eedc47619de"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+vs8K0JOjbkyIJBDAqOu031zwoy3O3AAdqJcL90nsr9lw0MOWjUxwujUZiPP+l9TscYLt5Vaoo6LSL2vw1coBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T16:58:06.270358Z","bundle_sha256":"d02238f5b976e473f24221b84082defa868c439867c58a911f70ed68d0d23207"}}