{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:4SMBDPOJ7J6MVYQJPGKIBIEAW3","short_pith_number":"pith:4SMBDPOJ","canonical_record":{"source":{"id":"1501.05590","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-01-22T18:16:30Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f8242846fbe8b571fb03215ca111cc6e88a0132ca44c86afd28f0d0bafb55ccd","abstract_canon_sha256":"8378d3555b293e3b4ce89ed548a95f72e4041ef5e6e237ee9e5ccc4b249bee29"},"schema_version":"1.0"},"canonical_sha256":"e49811bdc9fa7ccae209799480a080b6c94f7613dfb0a575fa5b75ab28e4e8dc","source":{"kind":"arxiv","id":"1501.05590","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1501.05590","created_at":"2026-05-18T00:58:36Z"},{"alias_kind":"arxiv_version","alias_value":"1501.05590v1","created_at":"2026-05-18T00:58:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1501.05590","created_at":"2026-05-18T00:58:36Z"},{"alias_kind":"pith_short_12","alias_value":"4SMBDPOJ7J6M","created_at":"2026-05-18T12:29:05Z"},{"alias_kind":"pith_short_16","alias_value":"4SMBDPOJ7J6MVYQJ","created_at":"2026-05-18T12:29:05Z"},{"alias_kind":"pith_short_8","alias_value":"4SMBDPOJ","created_at":"2026-05-18T12:29:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:4SMBDPOJ7J6MVYQJPGKIBIEAW3","target":"record","payload":{"canonical_record":{"source":{"id":"1501.05590","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-01-22T18:16:30Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f8242846fbe8b571fb03215ca111cc6e88a0132ca44c86afd28f0d0bafb55ccd","abstract_canon_sha256":"8378d3555b293e3b4ce89ed548a95f72e4041ef5e6e237ee9e5ccc4b249bee29"},"schema_version":"1.0"},"canonical_sha256":"e49811bdc9fa7ccae209799480a080b6c94f7613dfb0a575fa5b75ab28e4e8dc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:58:36.266721Z","signature_b64":"YWz6Dp5tkIb5O8UubS+SUAUyczin5kxQM0EttCPdWQjYJdldWoBffebpIvVVz5j+O30RrY7yWSDhBwC7aWTDBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e49811bdc9fa7ccae209799480a080b6c94f7613dfb0a575fa5b75ab28e4e8dc","last_reissued_at":"2026-05-18T00:58:36.266026Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:58:36.266026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1501.05590","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":"2026-05-18T00:58:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ztjtY1ev6wdJyefVfsLdRQy6t7neMue0Zj3MBP1MX+hSBf9wbmHnC8WcP7urRtEGMrJ9bmuqL/SHF2RDfRkRDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T19:13:52.773805Z"},"content_sha256":"0d1c073fef5153b37bb1a0c8c834f5a434aadb8cbf16eda6d96ee7585004ac76","schema_version":"1.0","event_id":"sha256:0d1c073fef5153b37bb1a0c8c834f5a434aadb8cbf16eda6d96ee7585004ac76"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:4SMBDPOJ7J6MVYQJPGKIBIEAW3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sketch and Validate for Big Data Clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Georgios B. Giannakis, Konstantinos Slavakis, Panagiotis A. Traganitis","submitted_at":"2015-01-22T18:16:30Z","abstract_excerpt":"In response to the need for learning tools tuned to big data analytics, the present paper introduces a framework for efficient clustering of huge sets of (possibly high-dimensional) data. Building on random sampling and consensus (RANSAC) ideas pursued earlier in a different (computer vision) context for robust regression, a suite of novel dimensionality and set-reduction algorithms is developed. The advocated sketch-and-validate (SkeVa) family includes two algorithms that rely on K-means clustering per iteration on reduced number of dimensions and/or feature vectors: The first operates in a b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1501.05590","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":"2026-05-18T00:58:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wW0c7vO1uOOuUkNuXhzo6jzqIuua0pw3EzvlMyzw0XOhJckYsA/1/V4PRP50r4hWanaO9MO0EwrWa9RFyAzDDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T19:13:52.774532Z"},"content_sha256":"750bbd89ef5ea74b74e6055f5ba991c80954231ba276013cd3e4bebb4c73319b","schema_version":"1.0","event_id":"sha256:750bbd89ef5ea74b74e6055f5ba991c80954231ba276013cd3e4bebb4c73319b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4SMBDPOJ7J6MVYQJPGKIBIEAW3/bundle.json","state_url":"https://pith.science/pith/4SMBDPOJ7J6MVYQJPGKIBIEAW3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4SMBDPOJ7J6MVYQJPGKIBIEAW3/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":"2026-06-08T19:13:52Z","links":{"resolver":"https://pith.science/pith/4SMBDPOJ7J6MVYQJPGKIBIEAW3","bundle":"https://pith.science/pith/4SMBDPOJ7J6MVYQJPGKIBIEAW3/bundle.json","state":"https://pith.science/pith/4SMBDPOJ7J6MVYQJPGKIBIEAW3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4SMBDPOJ7J6MVYQJPGKIBIEAW3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:4SMBDPOJ7J6MVYQJPGKIBIEAW3","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":"8378d3555b293e3b4ce89ed548a95f72e4041ef5e6e237ee9e5ccc4b249bee29","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-01-22T18:16:30Z","title_canon_sha256":"f8242846fbe8b571fb03215ca111cc6e88a0132ca44c86afd28f0d0bafb55ccd"},"schema_version":"1.0","source":{"id":"1501.05590","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1501.05590","created_at":"2026-05-18T00:58:36Z"},{"alias_kind":"arxiv_version","alias_value":"1501.05590v1","created_at":"2026-05-18T00:58:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1501.05590","created_at":"2026-05-18T00:58:36Z"},{"alias_kind":"pith_short_12","alias_value":"4SMBDPOJ7J6M","created_at":"2026-05-18T12:29:05Z"},{"alias_kind":"pith_short_16","alias_value":"4SMBDPOJ7J6MVYQJ","created_at":"2026-05-18T12:29:05Z"},{"alias_kind":"pith_short_8","alias_value":"4SMBDPOJ","created_at":"2026-05-18T12:29:05Z"}],"graph_snapshots":[{"event_id":"sha256:750bbd89ef5ea74b74e6055f5ba991c80954231ba276013cd3e4bebb4c73319b","target":"graph","created_at":"2026-05-18T00:58:36Z","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 response to the need for learning tools tuned to big data analytics, the present paper introduces a framework for efficient clustering of huge sets of (possibly high-dimensional) data. Building on random sampling and consensus (RANSAC) ideas pursued earlier in a different (computer vision) context for robust regression, a suite of novel dimensionality and set-reduction algorithms is developed. The advocated sketch-and-validate (SkeVa) family includes two algorithms that rely on K-means clustering per iteration on reduced number of dimensions and/or feature vectors: The first operates in a b","authors_text":"Georgios B. Giannakis, Konstantinos Slavakis, Panagiotis A. Traganitis","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-01-22T18:16:30Z","title":"Sketch and Validate for Big Data Clustering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1501.05590","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":"sha256:0d1c073fef5153b37bb1a0c8c834f5a434aadb8cbf16eda6d96ee7585004ac76","target":"record","created_at":"2026-05-18T00:58:36Z","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":"8378d3555b293e3b4ce89ed548a95f72e4041ef5e6e237ee9e5ccc4b249bee29","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2015-01-22T18:16:30Z","title_canon_sha256":"f8242846fbe8b571fb03215ca111cc6e88a0132ca44c86afd28f0d0bafb55ccd"},"schema_version":"1.0","source":{"id":"1501.05590","kind":"arxiv","version":1}},"canonical_sha256":"e49811bdc9fa7ccae209799480a080b6c94f7613dfb0a575fa5b75ab28e4e8dc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e49811bdc9fa7ccae209799480a080b6c94f7613dfb0a575fa5b75ab28e4e8dc","first_computed_at":"2026-05-18T00:58:36.266026Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:58:36.266026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YWz6Dp5tkIb5O8UubS+SUAUyczin5kxQM0EttCPdWQjYJdldWoBffebpIvVVz5j+O30RrY7yWSDhBwC7aWTDBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:58:36.266721Z","signed_message":"canonical_sha256_bytes"},"source_id":"1501.05590","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0d1c073fef5153b37bb1a0c8c834f5a434aadb8cbf16eda6d96ee7585004ac76","sha256:750bbd89ef5ea74b74e6055f5ba991c80954231ba276013cd3e4bebb4c73319b"],"state_sha256":"61c4bb85cf677d0d38d4ccfedbd499223736d363d777753ec2894825adcd502b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qpUu3OHji9krP26S6BDKD+EL1H1D6CrTVfd59CZLBvxR4f57ydAYOmpI38Nllf6Nz3O3ayMc321L1+Fo1aZkAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T19:13:52.778539Z","bundle_sha256":"aab0eb3279deafe6d4efe034f72cf0b9a1b71e67cc76f50e218511e9c7219335"}}