{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:S5J7HYSRWNRJVTTOIUVRQTXG74","short_pith_number":"pith:S5J7HYSR","canonical_record":{"source":{"id":"1502.04265","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2015-02-15T01:03:47Z","cross_cats_sorted":[],"title_canon_sha256":"253728244a0b6daa70fae1e50ecb5a541aa86edbc9e617b0a8b1f2ff5ead6490","abstract_canon_sha256":"f724fa29b112c396e0d130b5786eb73f2e0c32ef6bc879126e886228e0c99a42"},"schema_version":"1.0"},"canonical_sha256":"9753f3e251b3629ace6e452b184ee6ff31635583dffde8c11b8f38494472b970","source":{"kind":"arxiv","id":"1502.04265","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1502.04265","created_at":"2026-05-18T02:00:02Z"},{"alias_kind":"arxiv_version","alias_value":"1502.04265v3","created_at":"2026-05-18T02:00:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1502.04265","created_at":"2026-05-18T02:00:02Z"},{"alias_kind":"pith_short_12","alias_value":"S5J7HYSRWNRJ","created_at":"2026-05-18T12:29:39Z"},{"alias_kind":"pith_short_16","alias_value":"S5J7HYSRWNRJVTTO","created_at":"2026-05-18T12:29:39Z"},{"alias_kind":"pith_short_8","alias_value":"S5J7HYSR","created_at":"2026-05-18T12:29:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:S5J7HYSRWNRJVTTOIUVRQTXG74","target":"record","payload":{"canonical_record":{"source":{"id":"1502.04265","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2015-02-15T01:03:47Z","cross_cats_sorted":[],"title_canon_sha256":"253728244a0b6daa70fae1e50ecb5a541aa86edbc9e617b0a8b1f2ff5ead6490","abstract_canon_sha256":"f724fa29b112c396e0d130b5786eb73f2e0c32ef6bc879126e886228e0c99a42"},"schema_version":"1.0"},"canonical_sha256":"9753f3e251b3629ace6e452b184ee6ff31635583dffde8c11b8f38494472b970","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:00:02.244377Z","signature_b64":"WEI5y6BaO/23l6ns4drzTH7Pc1ONzrDdnIUWMYntVw6JdZ66DI6wfH3s12LmOeiJzEcu2ZNG0Ook4crX2WNrAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9753f3e251b3629ace6e452b184ee6ff31635583dffde8c11b8f38494472b970","last_reissued_at":"2026-05-18T02:00:02.243883Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:00:02.243883Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1502.04265","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:00:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AMJ10afhYjGaW/O0gt+dFZPsJrbcj01Qpj/ImhH7Y1rZX0yWsvRE2AgCWY8c0eu+Z+X1Y66kQjXOuikPmAudDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T01:33:04.177264Z"},"content_sha256":"c1bdde35ad0a96cb0a118b34504b8464be97c0173638d4956523d89335db6138","schema_version":"1.0","event_id":"sha256:c1bdde35ad0a96cb0a118b34504b8464be97c0173638d4956523d89335db6138"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:S5J7HYSRWNRJVTTOIUVRQTXG74","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Solving $k$-means on High-dimensional Big Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DS","authors_text":"Daniel R. Schmidt, Jan-Philipp W. Kappmeier, Melanie Schmidt","submitted_at":"2015-02-15T01:03:47Z","abstract_excerpt":"In recent years, there have been major efforts to develop data stream algorithms that process inputs in one pass over the data with little memory requirement. For the $k$-means problem, this has led to the development of several $(1+\\varepsilon)$-approximations (under the assumption that $k$ is a constant), but also to the design of algorithms that are extremely fast in practice and compute solutions of high accuracy. However, when not only the length of the stream is high but also the dimensionality of the input points, then current methods reach their limits.\n  We propose two algorithms, pie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1502.04265","kind":"arxiv","version":3},"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":"2026-05-18T02:00:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WR1QBige0KtFdSnBLPoSx1fVbODFbv+H53Gl35shW8LNXWuAtCJauhGyyckAqWutKl8KFlAWJhlOLUpvZOH4Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T01:33:04.177748Z"},"content_sha256":"07758db78f53a126d87f31f3b5b6a6e17cec28a6c54b77f1b58106facabdd3ca","schema_version":"1.0","event_id":"sha256:07758db78f53a126d87f31f3b5b6a6e17cec28a6c54b77f1b58106facabdd3ca"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/S5J7HYSRWNRJVTTOIUVRQTXG74/bundle.json","state_url":"https://pith.science/pith/S5J7HYSRWNRJVTTOIUVRQTXG74/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/S5J7HYSRWNRJVTTOIUVRQTXG74/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":"2026-05-31T01:33:04Z","links":{"resolver":"https://pith.science/pith/S5J7HYSRWNRJVTTOIUVRQTXG74","bundle":"https://pith.science/pith/S5J7HYSRWNRJVTTOIUVRQTXG74/bundle.json","state":"https://pith.science/pith/S5J7HYSRWNRJVTTOIUVRQTXG74/state.json","well_known_bundle":"https://pith.science/.well-known/pith/S5J7HYSRWNRJVTTOIUVRQTXG74/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:S5J7HYSRWNRJVTTOIUVRQTXG74","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":"f724fa29b112c396e0d130b5786eb73f2e0c32ef6bc879126e886228e0c99a42","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2015-02-15T01:03:47Z","title_canon_sha256":"253728244a0b6daa70fae1e50ecb5a541aa86edbc9e617b0a8b1f2ff5ead6490"},"schema_version":"1.0","source":{"id":"1502.04265","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1502.04265","created_at":"2026-05-18T02:00:02Z"},{"alias_kind":"arxiv_version","alias_value":"1502.04265v3","created_at":"2026-05-18T02:00:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1502.04265","created_at":"2026-05-18T02:00:02Z"},{"alias_kind":"pith_short_12","alias_value":"S5J7HYSRWNRJ","created_at":"2026-05-18T12:29:39Z"},{"alias_kind":"pith_short_16","alias_value":"S5J7HYSRWNRJVTTO","created_at":"2026-05-18T12:29:39Z"},{"alias_kind":"pith_short_8","alias_value":"S5J7HYSR","created_at":"2026-05-18T12:29:39Z"}],"graph_snapshots":[{"event_id":"sha256:07758db78f53a126d87f31f3b5b6a6e17cec28a6c54b77f1b58106facabdd3ca","target":"graph","created_at":"2026-05-18T02:00:02Z","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":"In recent years, there have been major efforts to develop data stream algorithms that process inputs in one pass over the data with little memory requirement. For the $k$-means problem, this has led to the development of several $(1+\\varepsilon)$-approximations (under the assumption that $k$ is a constant), but also to the design of algorithms that are extremely fast in practice and compute solutions of high accuracy. However, when not only the length of the stream is high but also the dimensionality of the input points, then current methods reach their limits.\n  We propose two algorithms, pie","authors_text":"Daniel R. Schmidt, Jan-Philipp W. Kappmeier, Melanie Schmidt","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2015-02-15T01:03:47Z","title":"Solving $k$-means on High-dimensional Big Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1502.04265","kind":"arxiv","version":3},"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:c1bdde35ad0a96cb0a118b34504b8464be97c0173638d4956523d89335db6138","target":"record","created_at":"2026-05-18T02:00:02Z","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":"f724fa29b112c396e0d130b5786eb73f2e0c32ef6bc879126e886228e0c99a42","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2015-02-15T01:03:47Z","title_canon_sha256":"253728244a0b6daa70fae1e50ecb5a541aa86edbc9e617b0a8b1f2ff5ead6490"},"schema_version":"1.0","source":{"id":"1502.04265","kind":"arxiv","version":3}},"canonical_sha256":"9753f3e251b3629ace6e452b184ee6ff31635583dffde8c11b8f38494472b970","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9753f3e251b3629ace6e452b184ee6ff31635583dffde8c11b8f38494472b970","first_computed_at":"2026-05-18T02:00:02.243883Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:00:02.243883Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WEI5y6BaO/23l6ns4drzTH7Pc1ONzrDdnIUWMYntVw6JdZ66DI6wfH3s12LmOeiJzEcu2ZNG0Ook4crX2WNrAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T02:00:02.244377Z","signed_message":"canonical_sha256_bytes"},"source_id":"1502.04265","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c1bdde35ad0a96cb0a118b34504b8464be97c0173638d4956523d89335db6138","sha256:07758db78f53a126d87f31f3b5b6a6e17cec28a6c54b77f1b58106facabdd3ca"],"state_sha256":"ac36c2d71d93f215c517ad7418b8325adb342eb87ecdf661567ead961f8813e1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OgBym9DFAlCad+xSrZFTbl2wypT8C3nWCMqjhoZC4onhyryCP1YPB4EFZE0Os0rM8QQQ2GyN/ySikyqWpaLICQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T01:33:04.180958Z","bundle_sha256":"4120036c7ab3f16a83867a5909f3d16ce6a4f835bc81c11e3eafe46ec5d966cb"}}