{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:DBCY7TBLETNF2SZCID6HTX5PIT","short_pith_number":"pith:DBCY7TBL","canonical_record":{"source":{"id":"1602.00360","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-02-01T01:49:23Z","cross_cats_sorted":[],"title_canon_sha256":"784414b519fd640f4311006a9aff97f7427392a411c2947dcc19dbe736ab34c6","abstract_canon_sha256":"2d2f0c8f29c9268d5dce3fbf7a1e3a59b6248f7d0d27a6d52354311d6db7dd9f"},"schema_version":"1.0"},"canonical_sha256":"18458fcc2b24da5d4b2240fc79dfaf44f683d1a5c31d034da55378d4fc2ac062","source":{"kind":"arxiv","id":"1602.00360","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1602.00360","created_at":"2026-05-18T01:21:35Z"},{"alias_kind":"arxiv_version","alias_value":"1602.00360v1","created_at":"2026-05-18T01:21:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.00360","created_at":"2026-05-18T01:21:35Z"},{"alias_kind":"pith_short_12","alias_value":"DBCY7TBLETNF","created_at":"2026-05-18T12:30:09Z"},{"alias_kind":"pith_short_16","alias_value":"DBCY7TBLETNF2SZC","created_at":"2026-05-18T12:30:09Z"},{"alias_kind":"pith_short_8","alias_value":"DBCY7TBL","created_at":"2026-05-18T12:30:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:DBCY7TBLETNF2SZCID6HTX5PIT","target":"record","payload":{"canonical_record":{"source":{"id":"1602.00360","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-02-01T01:49:23Z","cross_cats_sorted":[],"title_canon_sha256":"784414b519fd640f4311006a9aff97f7427392a411c2947dcc19dbe736ab34c6","abstract_canon_sha256":"2d2f0c8f29c9268d5dce3fbf7a1e3a59b6248f7d0d27a6d52354311d6db7dd9f"},"schema_version":"1.0"},"canonical_sha256":"18458fcc2b24da5d4b2240fc79dfaf44f683d1a5c31d034da55378d4fc2ac062","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:21:35.571399Z","signature_b64":"SQLk9sOL8NKLUi5Arj8R4UhL4HChU1nW38rJ1T4hMCsKhLEdbuZoKRnEl5rD91LF1NrIBY+fClaY1oQVk+syCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18458fcc2b24da5d4b2240fc79dfaf44f683d1a5c31d034da55378d4fc2ac062","last_reissued_at":"2026-05-18T01:21:35.570640Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:21:35.570640Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1602.00360","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":"2026-05-18T01:21:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NFhHQU9vvsTAxa4/WIJX36jAQPJwyzbvj9A08pRTQXv1GpcCEo0yn+WfLOiOtC1zSp1e7QO15XWsLozq/gdEDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T02:26:52.430750Z"},"content_sha256":"225d7b092f21617964c655b873037611cff001f90412c1ee53fa66a3aaa76d1d","schema_version":"1.0","event_id":"sha256:225d7b092f21617964c655b873037611cff001f90412c1ee53fa66a3aaa76d1d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:DBCY7TBLETNF2SZCID6HTX5PIT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Semi-supervised K-means++","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ML","authors_text":"Carey E. Priebe, Jordan Yoder","submitted_at":"2016-02-01T01:49:23Z","abstract_excerpt":"Traditionally, practitioners initialize the {\\tt k-means} algorithm with centers chosen uniformly at random. Randomized initialization with uneven weights ({\\tt k-means++}) has recently been used to improve the performance over this strategy in cost and run-time. We consider the k-means problem with semi-supervised information, where some of the data are pre-labeled, and we seek to label the rest according to the minimum cost solution. By extending the {\\tt k-means++} algorithm and analysis to account for the labels, we derive an improved theoretical bound on expected cost and observe improved"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.00360","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":"2026-05-18T01:21:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ItaAMflZ1mJ7ia7CSLqzJGLvORX0Y0WavEzdgvt0/Np93ueLj0q2c/QyV/ugxvyKheOfCVY3KzlZNqV/vVkODw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T02:26:52.431094Z"},"content_sha256":"dffaf2e53792cb612c309329896e5ce88bf7cb495960888be77bcceef43aed52","schema_version":"1.0","event_id":"sha256:dffaf2e53792cb612c309329896e5ce88bf7cb495960888be77bcceef43aed52"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DBCY7TBLETNF2SZCID6HTX5PIT/bundle.json","state_url":"https://pith.science/pith/DBCY7TBLETNF2SZCID6HTX5PIT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DBCY7TBLETNF2SZCID6HTX5PIT/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":"2026-06-04T02:26:52Z","links":{"resolver":"https://pith.science/pith/DBCY7TBLETNF2SZCID6HTX5PIT","bundle":"https://pith.science/pith/DBCY7TBLETNF2SZCID6HTX5PIT/bundle.json","state":"https://pith.science/pith/DBCY7TBLETNF2SZCID6HTX5PIT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DBCY7TBLETNF2SZCID6HTX5PIT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:DBCY7TBLETNF2SZCID6HTX5PIT","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":"2d2f0c8f29c9268d5dce3fbf7a1e3a59b6248f7d0d27a6d52354311d6db7dd9f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-02-01T01:49:23Z","title_canon_sha256":"784414b519fd640f4311006a9aff97f7427392a411c2947dcc19dbe736ab34c6"},"schema_version":"1.0","source":{"id":"1602.00360","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1602.00360","created_at":"2026-05-18T01:21:35Z"},{"alias_kind":"arxiv_version","alias_value":"1602.00360v1","created_at":"2026-05-18T01:21:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.00360","created_at":"2026-05-18T01:21:35Z"},{"alias_kind":"pith_short_12","alias_value":"DBCY7TBLETNF","created_at":"2026-05-18T12:30:09Z"},{"alias_kind":"pith_short_16","alias_value":"DBCY7TBLETNF2SZC","created_at":"2026-05-18T12:30:09Z"},{"alias_kind":"pith_short_8","alias_value":"DBCY7TBL","created_at":"2026-05-18T12:30:09Z"}],"graph_snapshots":[{"event_id":"sha256:dffaf2e53792cb612c309329896e5ce88bf7cb495960888be77bcceef43aed52","target":"graph","created_at":"2026-05-18T01:21:35Z","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":"Traditionally, practitioners initialize the {\\tt k-means} algorithm with centers chosen uniformly at random. Randomized initialization with uneven weights ({\\tt k-means++}) has recently been used to improve the performance over this strategy in cost and run-time. We consider the k-means problem with semi-supervised information, where some of the data are pre-labeled, and we seek to label the rest according to the minimum cost solution. By extending the {\\tt k-means++} algorithm and analysis to account for the labels, we derive an improved theoretical bound on expected cost and observe improved","authors_text":"Carey E. Priebe, Jordan Yoder","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-02-01T01:49:23Z","title":"Semi-supervised K-means++"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.00360","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":"sha256:225d7b092f21617964c655b873037611cff001f90412c1ee53fa66a3aaa76d1d","target":"record","created_at":"2026-05-18T01:21:35Z","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":"2d2f0c8f29c9268d5dce3fbf7a1e3a59b6248f7d0d27a6d52354311d6db7dd9f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-02-01T01:49:23Z","title_canon_sha256":"784414b519fd640f4311006a9aff97f7427392a411c2947dcc19dbe736ab34c6"},"schema_version":"1.0","source":{"id":"1602.00360","kind":"arxiv","version":1}},"canonical_sha256":"18458fcc2b24da5d4b2240fc79dfaf44f683d1a5c31d034da55378d4fc2ac062","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"18458fcc2b24da5d4b2240fc79dfaf44f683d1a5c31d034da55378d4fc2ac062","first_computed_at":"2026-05-18T01:21:35.570640Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:21:35.570640Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SQLk9sOL8NKLUi5Arj8R4UhL4HChU1nW38rJ1T4hMCsKhLEdbuZoKRnEl5rD91LF1NrIBY+fClaY1oQVk+syCg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:21:35.571399Z","signed_message":"canonical_sha256_bytes"},"source_id":"1602.00360","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:225d7b092f21617964c655b873037611cff001f90412c1ee53fa66a3aaa76d1d","sha256:dffaf2e53792cb612c309329896e5ce88bf7cb495960888be77bcceef43aed52"],"state_sha256":"91fc9fc1260a97743bfd9ffe9bda5bcf31202e5525dd438779e465e5199409f2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VTmjZLhBmIYiCjj+gbsk0Jtf+7j7MqLKg9HvnFe4+YZASwLF3xtiQugWqnNZHU0FMVukjIAVCgB+5rX3kpHvCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T02:26:52.433510Z","bundle_sha256":"b815f2a00137c5776f88a4a9204f7abca60cda8306cb7f7174c48753ca67b9f2"}}