{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:RJTXVEPIOEN5XF7WK4J77WOMNZ","short_pith_number":"pith:RJTXVEPI","canonical_record":{"source":{"id":"2107.04074","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-08T19:24:09Z","cross_cats_sorted":[],"title_canon_sha256":"bba1ae7e65a1d1458e4545148016b300cca3b4ac7cd0d1b152e658a02b486465","abstract_canon_sha256":"cfe9ad7d927dbd99e8c394441bda746e0288b3d2012b51cc46d04aaf5b55e2db"},"schema_version":"1.0"},"canonical_sha256":"8a677a91e8711bdb97f65713ffd9cc6e563d611975c05733e74e7d3f8249d13d","source":{"kind":"arxiv","id":"2107.04074","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.04074","created_at":"2026-07-05T03:27:33Z"},{"alias_kind":"arxiv_version","alias_value":"2107.04074v1","created_at":"2026-07-05T03:27:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.04074","created_at":"2026-07-05T03:27:33Z"},{"alias_kind":"pith_short_12","alias_value":"RJTXVEPIOEN5","created_at":"2026-07-05T03:27:33Z"},{"alias_kind":"pith_short_16","alias_value":"RJTXVEPIOEN5XF7W","created_at":"2026-07-05T03:27:33Z"},{"alias_kind":"pith_short_8","alias_value":"RJTXVEPI","created_at":"2026-07-05T03:27:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:RJTXVEPIOEN5XF7WK4J77WOMNZ","target":"record","payload":{"canonical_record":{"source":{"id":"2107.04074","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-08T19:24:09Z","cross_cats_sorted":[],"title_canon_sha256":"bba1ae7e65a1d1458e4545148016b300cca3b4ac7cd0d1b152e658a02b486465","abstract_canon_sha256":"cfe9ad7d927dbd99e8c394441bda746e0288b3d2012b51cc46d04aaf5b55e2db"},"schema_version":"1.0"},"canonical_sha256":"8a677a91e8711bdb97f65713ffd9cc6e563d611975c05733e74e7d3f8249d13d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:27:33.604866Z","signature_b64":"BBkLnZ9a0RsNh9ozQbKnuNc5UKjlRfz5UOsw1+OS3dZZ/h4oPLOEUh+1LLwkBioYY9sWqVuOE/CDzajs10rTAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a677a91e8711bdb97f65713ffd9cc6e563d611975c05733e74e7d3f8249d13d","last_reissued_at":"2026-07-05T03:27:33.604329Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:27:33.604329Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2107.04074","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":"2026-07-05T03:27:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8uV7u85Tw3dmzLH+0fAuBrQTTBd0tsm7TRfu5kONUt9GUpKyW9knsiSZP/WM0nLJLpvhqxCcdHxdQLlvvdtNCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:45:59.470832Z"},"content_sha256":"a8ce700c5cfd9b90282b89d26a8202400a3918d637541dd0b0c0197497dbccf2","schema_version":"1.0","event_id":"sha256:a8ce700c5cfd9b90282b89d26a8202400a3918d637541dd0b0c0197497dbccf2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:RJTXVEPIOEN5XF7WK4J77WOMNZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Accelerating Spherical k-Means","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Andreas Lang, Erich Schubert, Gloria Feher","submitted_at":"2021-07-08T19:24:09Z","abstract_excerpt":"Spherical k-means is a widely used clustering algorithm for sparse and high-dimensional data such as document vectors. While several improvements and accelerations have been introduced for the original k-means algorithm, not all easily translate to the spherical variant: Many acceleration techniques, such as the algorithms of Elkan and Hamerly, rely on the triangle inequality of Euclidean distances. However, spherical k-means uses Cosine similarities instead of distances for computational efficiency. In this paper, we incorporate the Elkan and Hamerly accelerations to the spherical k-means alg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.04074","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2107.04074/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T03:27:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"niKWh0kJs0Gua4YcTyWh62MzlfJLW6ni+bh+xP17JQSU4WpmFExFq4tFRGenbQFlYIgzhwMBU6t9YpBgbMH4AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:45:59.471420Z"},"content_sha256":"a48b9cc21788d5b7fa5495b3e94474a3e9b3d3873bd95d039f5756f2f8a4d575","schema_version":"1.0","event_id":"sha256:a48b9cc21788d5b7fa5495b3e94474a3e9b3d3873bd95d039f5756f2f8a4d575"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RJTXVEPIOEN5XF7WK4J77WOMNZ/bundle.json","state_url":"https://pith.science/pith/RJTXVEPIOEN5XF7WK4J77WOMNZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RJTXVEPIOEN5XF7WK4J77WOMNZ/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":"2026-08-03T19:45:59Z","links":{"resolver":"https://pith.science/pith/RJTXVEPIOEN5XF7WK4J77WOMNZ","bundle":"https://pith.science/pith/RJTXVEPIOEN5XF7WK4J77WOMNZ/bundle.json","state":"https://pith.science/pith/RJTXVEPIOEN5XF7WK4J77WOMNZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RJTXVEPIOEN5XF7WK4J77WOMNZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:RJTXVEPIOEN5XF7WK4J77WOMNZ","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":"cfe9ad7d927dbd99e8c394441bda746e0288b3d2012b51cc46d04aaf5b55e2db","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-08T19:24:09Z","title_canon_sha256":"bba1ae7e65a1d1458e4545148016b300cca3b4ac7cd0d1b152e658a02b486465"},"schema_version":"1.0","source":{"id":"2107.04074","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.04074","created_at":"2026-07-05T03:27:33Z"},{"alias_kind":"arxiv_version","alias_value":"2107.04074v1","created_at":"2026-07-05T03:27:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.04074","created_at":"2026-07-05T03:27:33Z"},{"alias_kind":"pith_short_12","alias_value":"RJTXVEPIOEN5","created_at":"2026-07-05T03:27:33Z"},{"alias_kind":"pith_short_16","alias_value":"RJTXVEPIOEN5XF7W","created_at":"2026-07-05T03:27:33Z"},{"alias_kind":"pith_short_8","alias_value":"RJTXVEPI","created_at":"2026-07-05T03:27:33Z"}],"graph_snapshots":[{"event_id":"sha256:a48b9cc21788d5b7fa5495b3e94474a3e9b3d3873bd95d039f5756f2f8a4d575","target":"graph","created_at":"2026-07-05T03:27:33Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2107.04074/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Spherical k-means is a widely used clustering algorithm for sparse and high-dimensional data such as document vectors. While several improvements and accelerations have been introduced for the original k-means algorithm, not all easily translate to the spherical variant: Many acceleration techniques, such as the algorithms of Elkan and Hamerly, rely on the triangle inequality of Euclidean distances. However, spherical k-means uses Cosine similarities instead of distances for computational efficiency. In this paper, we incorporate the Elkan and Hamerly accelerations to the spherical k-means alg","authors_text":"Andreas Lang, Erich Schubert, Gloria Feher","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-08T19:24:09Z","title":"Accelerating Spherical k-Means"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.04074","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:a8ce700c5cfd9b90282b89d26a8202400a3918d637541dd0b0c0197497dbccf2","target":"record","created_at":"2026-07-05T03:27:33Z","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":"cfe9ad7d927dbd99e8c394441bda746e0288b3d2012b51cc46d04aaf5b55e2db","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-08T19:24:09Z","title_canon_sha256":"bba1ae7e65a1d1458e4545148016b300cca3b4ac7cd0d1b152e658a02b486465"},"schema_version":"1.0","source":{"id":"2107.04074","kind":"arxiv","version":1}},"canonical_sha256":"8a677a91e8711bdb97f65713ffd9cc6e563d611975c05733e74e7d3f8249d13d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8a677a91e8711bdb97f65713ffd9cc6e563d611975c05733e74e7d3f8249d13d","first_computed_at":"2026-07-05T03:27:33.604329Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:27:33.604329Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BBkLnZ9a0RsNh9ozQbKnuNc5UKjlRfz5UOsw1+OS3dZZ/h4oPLOEUh+1LLwkBioYY9sWqVuOE/CDzajs10rTAA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:27:33.604866Z","signed_message":"canonical_sha256_bytes"},"source_id":"2107.04074","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a8ce700c5cfd9b90282b89d26a8202400a3918d637541dd0b0c0197497dbccf2","sha256:a48b9cc21788d5b7fa5495b3e94474a3e9b3d3873bd95d039f5756f2f8a4d575"],"state_sha256":"08b3ebe4836d07fb9f269eaddc26efe1dcc20e2ccac196b35d5f5e1058c6f6c7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bqJXHvI7wiRwPdoHMJ5ywqWLGJvJkmuxCHVlVxDEs4oeWtloztJHggJeWbORLkt0XD62h+lr4Jb9kFanQe6ADg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T19:45:59.474910Z","bundle_sha256":"ed103e789bf5e045fb2fd2a40d9825f50b4d716d1a8b64f4ca63fdd75b5c2ae3"}}