{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:UONHQXDTCB6LRSCDGRDMA7MZRB","short_pith_number":"pith:UONHQXDT","canonical_record":{"source":{"id":"1906.00938","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-03T17:30:24Z","cross_cats_sorted":["cs.CV","math.OC","stat.ML"],"title_canon_sha256":"55156ba82bd0e3cd9e2bd7753c7e746413ad10779495f895c86eb555b9937788","abstract_canon_sha256":"580b167a69ed3ee0805b93918e0513e5c497c87f5c19ab43bb66147a2d2d2c92"},"schema_version":"1.0"},"canonical_sha256":"a39a785c73107cb8c8433446c07d99885c46420f28bdc4929cd2bdedc03579ef","source":{"kind":"arxiv","id":"1906.00938","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.00938","created_at":"2026-05-17T23:44:23Z"},{"alias_kind":"arxiv_version","alias_value":"1906.00938v1","created_at":"2026-05-17T23:44:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.00938","created_at":"2026-05-17T23:44:23Z"},{"alias_kind":"pith_short_12","alias_value":"UONHQXDTCB6L","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"UONHQXDTCB6LRSCD","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"UONHQXDT","created_at":"2026-05-18T12:33:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:UONHQXDTCB6LRSCDGRDMA7MZRB","target":"record","payload":{"canonical_record":{"source":{"id":"1906.00938","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-03T17:30:24Z","cross_cats_sorted":["cs.CV","math.OC","stat.ML"],"title_canon_sha256":"55156ba82bd0e3cd9e2bd7753c7e746413ad10779495f895c86eb555b9937788","abstract_canon_sha256":"580b167a69ed3ee0805b93918e0513e5c497c87f5c19ab43bb66147a2d2d2c92"},"schema_version":"1.0"},"canonical_sha256":"a39a785c73107cb8c8433446c07d99885c46420f28bdc4929cd2bdedc03579ef","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:23.447982Z","signature_b64":"6HtvHU+yP3mCiys2AhQf1OgptltpwhTUOME2xEBI2M62bw9Zm61vo0IXzKV7FZWqvbMVRKEl5VixGDGb69/KBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a39a785c73107cb8c8433446c07d99885c46420f28bdc4929cd2bdedc03579ef","last_reissued_at":"2026-05-17T23:44:23.447474Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:23.447474Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.00938","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":"2026-05-17T23:44:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k/vhjI2mKPUhLGSLMMuIy4CgagUMVQ0E0ZHsh5ce+Ed81EoAhnXEN3+6VzwJpuUO899GgBlSrGiCYfGh/QJGBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T05:02:11.311251Z"},"content_sha256":"f6da098fb0f49a6ab5f448618f3074f1ff35b48f3fe5f9cb76b909da3c85fdbe","schema_version":"1.0","event_id":"sha256:f6da098fb0f49a6ab5f448618f3074f1ff35b48f3fe5f9cb76b909da3c85fdbe"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:UONHQXDTCB6LRSCDGRDMA7MZRB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Big-Data Clustering: K-Means or K-Indicators?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Feiyu Chen, Liwei Xu, Taiping Zhang, Yin Zhang, Yuchen Yang","submitted_at":"2019-06-03T17:30:24Z","abstract_excerpt":"The K-means algorithm is arguably the most popular data clustering method, commonly applied to processed datasets in some \"feature spaces\", as is in spectral clustering. Highly sensitive to initializations, however, K-means encounters a scalability bottleneck with respect to the number of clusters K as this number grows in big data applications. In this work, we promote a closely related model called K-indicators model and construct an efficient, semi-convex-relaxation algorithm that requires no randomized initializations. We present extensive empirical results to show advantages of the new al"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.00938","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":"2026-05-17T23:44:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5RXg03Df98b5lDT2eZ9+dtVFH/6U6ZSH2DCh1ktxpIzU0igtS/5uTsir01g3+uqkP9TciX4t+Rs6Qio1P97nDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T05:02:11.311907Z"},"content_sha256":"8dfc9ca3ee3eaaf00164725064548eda03b4cd87b3a4537a3390b269d7fbf9da","schema_version":"1.0","event_id":"sha256:8dfc9ca3ee3eaaf00164725064548eda03b4cd87b3a4537a3390b269d7fbf9da"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UONHQXDTCB6LRSCDGRDMA7MZRB/bundle.json","state_url":"https://pith.science/pith/UONHQXDTCB6LRSCDGRDMA7MZRB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UONHQXDTCB6LRSCDGRDMA7MZRB/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":"2026-05-30T05:02:11Z","links":{"resolver":"https://pith.science/pith/UONHQXDTCB6LRSCDGRDMA7MZRB","bundle":"https://pith.science/pith/UONHQXDTCB6LRSCDGRDMA7MZRB/bundle.json","state":"https://pith.science/pith/UONHQXDTCB6LRSCDGRDMA7MZRB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UONHQXDTCB6LRSCDGRDMA7MZRB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:UONHQXDTCB6LRSCDGRDMA7MZRB","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":"580b167a69ed3ee0805b93918e0513e5c497c87f5c19ab43bb66147a2d2d2c92","cross_cats_sorted":["cs.CV","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-03T17:30:24Z","title_canon_sha256":"55156ba82bd0e3cd9e2bd7753c7e746413ad10779495f895c86eb555b9937788"},"schema_version":"1.0","source":{"id":"1906.00938","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.00938","created_at":"2026-05-17T23:44:23Z"},{"alias_kind":"arxiv_version","alias_value":"1906.00938v1","created_at":"2026-05-17T23:44:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.00938","created_at":"2026-05-17T23:44:23Z"},{"alias_kind":"pith_short_12","alias_value":"UONHQXDTCB6L","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"UONHQXDTCB6LRSCD","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"UONHQXDT","created_at":"2026-05-18T12:33:30Z"}],"graph_snapshots":[{"event_id":"sha256:8dfc9ca3ee3eaaf00164725064548eda03b4cd87b3a4537a3390b269d7fbf9da","target":"graph","created_at":"2026-05-17T23:44:23Z","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 K-means algorithm is arguably the most popular data clustering method, commonly applied to processed datasets in some \"feature spaces\", as is in spectral clustering. Highly sensitive to initializations, however, K-means encounters a scalability bottleneck with respect to the number of clusters K as this number grows in big data applications. In this work, we promote a closely related model called K-indicators model and construct an efficient, semi-convex-relaxation algorithm that requires no randomized initializations. We present extensive empirical results to show advantages of the new al","authors_text":"Feiyu Chen, Liwei Xu, Taiping Zhang, Yin Zhang, Yuchen Yang","cross_cats":["cs.CV","math.OC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-03T17:30:24Z","title":"Big-Data Clustering: K-Means or K-Indicators?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.00938","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:f6da098fb0f49a6ab5f448618f3074f1ff35b48f3fe5f9cb76b909da3c85fdbe","target":"record","created_at":"2026-05-17T23:44:23Z","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":"580b167a69ed3ee0805b93918e0513e5c497c87f5c19ab43bb66147a2d2d2c92","cross_cats_sorted":["cs.CV","math.OC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-03T17:30:24Z","title_canon_sha256":"55156ba82bd0e3cd9e2bd7753c7e746413ad10779495f895c86eb555b9937788"},"schema_version":"1.0","source":{"id":"1906.00938","kind":"arxiv","version":1}},"canonical_sha256":"a39a785c73107cb8c8433446c07d99885c46420f28bdc4929cd2bdedc03579ef","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a39a785c73107cb8c8433446c07d99885c46420f28bdc4929cd2bdedc03579ef","first_computed_at":"2026-05-17T23:44:23.447474Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:44:23.447474Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6HtvHU+yP3mCiys2AhQf1OgptltpwhTUOME2xEBI2M62bw9Zm61vo0IXzKV7FZWqvbMVRKEl5VixGDGb69/KBA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:44:23.447982Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.00938","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f6da098fb0f49a6ab5f448618f3074f1ff35b48f3fe5f9cb76b909da3c85fdbe","sha256:8dfc9ca3ee3eaaf00164725064548eda03b4cd87b3a4537a3390b269d7fbf9da"],"state_sha256":"60168360cecdfe40233950c0bde167f69f969ded5f5e04285f78ad08a0d62a01"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WPNSro/tAFkbfiaAEUFh6grOlo5zFX1t5ZsuYL1YQ1AY/0VFK9ONoqmilAsmYdulzU8MSJaxsd1aHwUXEGRYBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T05:02:11.314915Z","bundle_sha256":"09c15f7ee0e1ed9064bae9b3c07f02dd20de1de200302f9e947123955790e60d"}}