{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2011:6SKX3ELXYZKMIK7SXIV3FEPCXR","short_pith_number":"pith:6SKX3ELX","canonical_record":{"source":{"id":"1109.5664","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2011-09-26T18:44:00Z","cross_cats_sorted":["cs.DS"],"title_canon_sha256":"2053e3845733ca0df55c6ad4562ea2135309c87db4ac88fedbf39f7786e396bb","abstract_canon_sha256":"da3676aec94b972f9ce3a76fffd7da183053aa7ce46db9f9646454c2355cd908"},"schema_version":"1.0"},"canonical_sha256":"f4957d9177c654c42bf2ba2bb291e2bc668599bb17ec74996c21493f505e63a6","source":{"kind":"arxiv","id":"1109.5664","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1109.5664","created_at":"2026-05-18T00:58:43Z"},{"alias_kind":"arxiv_version","alias_value":"1109.5664v4","created_at":"2026-05-18T00:58:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1109.5664","created_at":"2026-05-18T00:58:43Z"},{"alias_kind":"pith_short_12","alias_value":"6SKX3ELXYZKM","created_at":"2026-05-18T12:26:22Z"},{"alias_kind":"pith_short_16","alias_value":"6SKX3ELXYZKMIK7S","created_at":"2026-05-18T12:26:22Z"},{"alias_kind":"pith_short_8","alias_value":"6SKX3ELX","created_at":"2026-05-18T12:26:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2011:6SKX3ELXYZKMIK7SXIV3FEPCXR","target":"record","payload":{"canonical_record":{"source":{"id":"1109.5664","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2011-09-26T18:44:00Z","cross_cats_sorted":["cs.DS"],"title_canon_sha256":"2053e3845733ca0df55c6ad4562ea2135309c87db4ac88fedbf39f7786e396bb","abstract_canon_sha256":"da3676aec94b972f9ce3a76fffd7da183053aa7ce46db9f9646454c2355cd908"},"schema_version":"1.0"},"canonical_sha256":"f4957d9177c654c42bf2ba2bb291e2bc668599bb17ec74996c21493f505e63a6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:58:43.327082Z","signature_b64":"/r7bZqnW4JqkEr59OEzonRP3vZgWgdQhvxVhF9MybaRD56lC70XnRfalhyT6lUumQMmY7IOa+mM+vOYkJsXJBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f4957d9177c654c42bf2ba2bb291e2bc668599bb17ec74996c21493f505e63a6","last_reissued_at":"2026-05-18T00:58:43.326599Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:58:43.326599Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1109.5664","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:58:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8Zv4PBir0qEYDh/Pl6q487mSjJx5IzNJDBDrZCvwm5AOr2sTp/x9X88ypnaK1xTYijVNSkmVx7cS2DPpIzSNBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T18:19:43.310774Z"},"content_sha256":"0288496db9f578bb53d1bb1d7d1475f742ee82d71101fdf9722cbd6761531dec","schema_version":"1.0","event_id":"sha256:0288496db9f578bb53d1bb1d7d1475f742ee82d71101fdf9722cbd6761531dec"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2011:6SKX3ELXYZKMIK7SXIV3FEPCXR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deterministic Feature Selection for $k$-means Clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS"],"primary_cat":"cs.LG","authors_text":"Christos Boutsidis, Malik Magdon-Ismail","submitted_at":"2011-09-26T18:44:00Z","abstract_excerpt":"We study feature selection for $k$-means clustering. Although the literature contains many methods with good empirical performance, algorithms with provable theoretical behavior have only recently been developed. Unfortunately, these algorithms are randomized and fail with, say, a constant probability. We address this issue by presenting a deterministic feature selection algorithm for k-means with theoretical guarantees. At the heart of our algorithm lies a deterministic method for decompositions of the identity."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1109.5664","kind":"arxiv","version":4},"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":"2026-05-18T00:58:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qsu0LwwJQnbWeFxkdDw3oEx053N+fDHAZp7yoCNnBwrcOS0VZsg5jxetd6NPxMdA/BXhKoIsngZQC5+o9q4bCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T18:19:43.311484Z"},"content_sha256":"98825d67f8acb4abd182a2f02f95ab1e8cf0d569cd48651d32b692bb6e6d171f","schema_version":"1.0","event_id":"sha256:98825d67f8acb4abd182a2f02f95ab1e8cf0d569cd48651d32b692bb6e6d171f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6SKX3ELXYZKMIK7SXIV3FEPCXR/bundle.json","state_url":"https://pith.science/pith/6SKX3ELXYZKMIK7SXIV3FEPCXR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6SKX3ELXYZKMIK7SXIV3FEPCXR/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":"2026-05-25T18:19:43Z","links":{"resolver":"https://pith.science/pith/6SKX3ELXYZKMIK7SXIV3FEPCXR","bundle":"https://pith.science/pith/6SKX3ELXYZKMIK7SXIV3FEPCXR/bundle.json","state":"https://pith.science/pith/6SKX3ELXYZKMIK7SXIV3FEPCXR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6SKX3ELXYZKMIK7SXIV3FEPCXR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2011:6SKX3ELXYZKMIK7SXIV3FEPCXR","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":"da3676aec94b972f9ce3a76fffd7da183053aa7ce46db9f9646454c2355cd908","cross_cats_sorted":["cs.DS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2011-09-26T18:44:00Z","title_canon_sha256":"2053e3845733ca0df55c6ad4562ea2135309c87db4ac88fedbf39f7786e396bb"},"schema_version":"1.0","source":{"id":"1109.5664","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1109.5664","created_at":"2026-05-18T00:58:43Z"},{"alias_kind":"arxiv_version","alias_value":"1109.5664v4","created_at":"2026-05-18T00:58:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1109.5664","created_at":"2026-05-18T00:58:43Z"},{"alias_kind":"pith_short_12","alias_value":"6SKX3ELXYZKM","created_at":"2026-05-18T12:26:22Z"},{"alias_kind":"pith_short_16","alias_value":"6SKX3ELXYZKMIK7S","created_at":"2026-05-18T12:26:22Z"},{"alias_kind":"pith_short_8","alias_value":"6SKX3ELX","created_at":"2026-05-18T12:26:22Z"}],"graph_snapshots":[{"event_id":"sha256:98825d67f8acb4abd182a2f02f95ab1e8cf0d569cd48651d32b692bb6e6d171f","target":"graph","created_at":"2026-05-18T00:58:43Z","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":"We study feature selection for $k$-means clustering. Although the literature contains many methods with good empirical performance, algorithms with provable theoretical behavior have only recently been developed. Unfortunately, these algorithms are randomized and fail with, say, a constant probability. We address this issue by presenting a deterministic feature selection algorithm for k-means with theoretical guarantees. At the heart of our algorithm lies a deterministic method for decompositions of the identity.","authors_text":"Christos Boutsidis, Malik Magdon-Ismail","cross_cats":["cs.DS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2011-09-26T18:44:00Z","title":"Deterministic Feature Selection for $k$-means Clustering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1109.5664","kind":"arxiv","version":4},"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":"sha256:0288496db9f578bb53d1bb1d7d1475f742ee82d71101fdf9722cbd6761531dec","target":"record","created_at":"2026-05-18T00:58:43Z","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":"da3676aec94b972f9ce3a76fffd7da183053aa7ce46db9f9646454c2355cd908","cross_cats_sorted":["cs.DS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2011-09-26T18:44:00Z","title_canon_sha256":"2053e3845733ca0df55c6ad4562ea2135309c87db4ac88fedbf39f7786e396bb"},"schema_version":"1.0","source":{"id":"1109.5664","kind":"arxiv","version":4}},"canonical_sha256":"f4957d9177c654c42bf2ba2bb291e2bc668599bb17ec74996c21493f505e63a6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f4957d9177c654c42bf2ba2bb291e2bc668599bb17ec74996c21493f505e63a6","first_computed_at":"2026-05-18T00:58:43.326599Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:58:43.326599Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/r7bZqnW4JqkEr59OEzonRP3vZgWgdQhvxVhF9MybaRD56lC70XnRfalhyT6lUumQMmY7IOa+mM+vOYkJsXJBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:58:43.327082Z","signed_message":"canonical_sha256_bytes"},"source_id":"1109.5664","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0288496db9f578bb53d1bb1d7d1475f742ee82d71101fdf9722cbd6761531dec","sha256:98825d67f8acb4abd182a2f02f95ab1e8cf0d569cd48651d32b692bb6e6d171f"],"state_sha256":"5fe795c783db8dd29fa944f8c510409b10c34bd980c1988dc9fde501974a6f85"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/D2oHy5OuaXP5Q0mlIRWRrR6YZJd4MGEmdu1lO2W9ckCONeJAEHYzx/2rfiURKunWGXyrDhTB3ek5KUUXcuWAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T18:19:43.318101Z","bundle_sha256":"97ed7a83d82ed21dc0f5e918297d21a95f1a2b0c7793fe8fe70ef753538be0c2"}}