{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:HZQL7ZXPWUEIP6JPHLELQIDEJ2","short_pith_number":"pith:HZQL7ZXP","canonical_record":{"source":{"id":"2108.10262","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-08-23T15:59:14Z","cross_cats_sorted":[],"title_canon_sha256":"dfb4d3e1a3960d807e77b3268741e8823657d510e6ca606c1c68974f30abcaf7","abstract_canon_sha256":"ae2473ef97e2dfe640c9671ac1fbba874a37582ff8a16c9a1069c77325e52369"},"schema_version":"1.0"},"canonical_sha256":"3e60bfe6efb50887f92f3ac8b820644ea2b6bfd9e95890137b24e5b336d2cb0b","source":{"kind":"arxiv","id":"2108.10262","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.10262","created_at":"2026-07-05T03:08:03Z"},{"alias_kind":"arxiv_version","alias_value":"2108.10262v1","created_at":"2026-07-05T03:08:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.10262","created_at":"2026-07-05T03:08:03Z"},{"alias_kind":"pith_short_12","alias_value":"HZQL7ZXPWUEI","created_at":"2026-07-05T03:08:03Z"},{"alias_kind":"pith_short_16","alias_value":"HZQL7ZXPWUEIP6JP","created_at":"2026-07-05T03:08:03Z"},{"alias_kind":"pith_short_8","alias_value":"HZQL7ZXP","created_at":"2026-07-05T03:08:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:HZQL7ZXPWUEIP6JPHLELQIDEJ2","target":"record","payload":{"canonical_record":{"source":{"id":"2108.10262","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-08-23T15:59:14Z","cross_cats_sorted":[],"title_canon_sha256":"dfb4d3e1a3960d807e77b3268741e8823657d510e6ca606c1c68974f30abcaf7","abstract_canon_sha256":"ae2473ef97e2dfe640c9671ac1fbba874a37582ff8a16c9a1069c77325e52369"},"schema_version":"1.0"},"canonical_sha256":"3e60bfe6efb50887f92f3ac8b820644ea2b6bfd9e95890137b24e5b336d2cb0b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:08:03.921426Z","signature_b64":"p3mWRnIfVYQT8fljB3u0q+wGOqY8VgApYuRGUzyvkdDhtJY0hieTELoqOdLtj45bSD8CdhF4egeq90JwJPV/DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e60bfe6efb50887f92f3ac8b820644ea2b6bfd9e95890137b24e5b336d2cb0b","last_reissued_at":"2026-07-05T03:08:03.920918Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:08:03.920918Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2108.10262","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":"2026-07-05T03:08:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vbrLbW3Hh0DPrL2hYZJlo+MuGXFu9sVuGM86TBIEXEwk2YwaYd+WLwmWTl51zadSNWyBGAzfFNEM83vBmsPHDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:21:43.338793Z"},"content_sha256":"9eae6115fb467b247decd0ab22df4a3ea18f98f500abcae53c2eaa70952fe44b","schema_version":"1.0","event_id":"sha256:9eae6115fb467b247decd0ab22df4a3ea18f98f500abcae53c2eaa70952fe44b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:HZQL7ZXPWUEIP6JPHLELQIDEJ2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Cube Sampled K-Prototype Clustering for Featured Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aditya A. Shastri, Kapil Ahuja, Navneet Pratap Singh, Seemandhar Jain, Yann Busnel","submitted_at":"2021-08-23T15:59:14Z","abstract_excerpt":"Clustering large amount of data is becoming increasingly important in the current times. Due to the large sizes of data, clustering algorithm often take too much time. Sampling this data before clustering is commonly used to reduce this time. In this work, we propose a probabilistic sampling technique called cube sampling along with K-Prototype clustering. Cube sampling is used because of its accurate sample selection. K-Prototype is most frequently used clustering algorithm when the data is numerical as well as categorical (very common in today's time). The novelty of this work is in obtainin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.10262","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/2108.10262/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":"2026-07-05T03:08:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2Q89uC2dsEUIS0stg/aqt1kR5UDdlafqxoW63EgKRNKPV3s93TlwbkaFGIkBq/7Byp1CCwlJZueTJEUYRD3yBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:21:43.339161Z"},"content_sha256":"73171a5e65d5bd949cb8f38ce55ccd5415d785258835abfe5a1a2e6ed11924ee","schema_version":"1.0","event_id":"sha256:73171a5e65d5bd949cb8f38ce55ccd5415d785258835abfe5a1a2e6ed11924ee"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HZQL7ZXPWUEIP6JPHLELQIDEJ2/bundle.json","state_url":"https://pith.science/pith/HZQL7ZXPWUEIP6JPHLELQIDEJ2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HZQL7ZXPWUEIP6JPHLELQIDEJ2/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":"2026-07-06T23:21:43Z","links":{"resolver":"https://pith.science/pith/HZQL7ZXPWUEIP6JPHLELQIDEJ2","bundle":"https://pith.science/pith/HZQL7ZXPWUEIP6JPHLELQIDEJ2/bundle.json","state":"https://pith.science/pith/HZQL7ZXPWUEIP6JPHLELQIDEJ2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HZQL7ZXPWUEIP6JPHLELQIDEJ2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:HZQL7ZXPWUEIP6JPHLELQIDEJ2","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":"ae2473ef97e2dfe640c9671ac1fbba874a37582ff8a16c9a1069c77325e52369","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-08-23T15:59:14Z","title_canon_sha256":"dfb4d3e1a3960d807e77b3268741e8823657d510e6ca606c1c68974f30abcaf7"},"schema_version":"1.0","source":{"id":"2108.10262","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.10262","created_at":"2026-07-05T03:08:03Z"},{"alias_kind":"arxiv_version","alias_value":"2108.10262v1","created_at":"2026-07-05T03:08:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.10262","created_at":"2026-07-05T03:08:03Z"},{"alias_kind":"pith_short_12","alias_value":"HZQL7ZXPWUEI","created_at":"2026-07-05T03:08:03Z"},{"alias_kind":"pith_short_16","alias_value":"HZQL7ZXPWUEIP6JP","created_at":"2026-07-05T03:08:03Z"},{"alias_kind":"pith_short_8","alias_value":"HZQL7ZXP","created_at":"2026-07-05T03:08:03Z"}],"graph_snapshots":[{"event_id":"sha256:73171a5e65d5bd949cb8f38ce55ccd5415d785258835abfe5a1a2e6ed11924ee","target":"graph","created_at":"2026-07-05T03:08:03Z","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/2108.10262/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Clustering large amount of data is becoming increasingly important in the current times. Due to the large sizes of data, clustering algorithm often take too much time. Sampling this data before clustering is commonly used to reduce this time. In this work, we propose a probabilistic sampling technique called cube sampling along with K-Prototype clustering. Cube sampling is used because of its accurate sample selection. K-Prototype is most frequently used clustering algorithm when the data is numerical as well as categorical (very common in today's time). The novelty of this work is in obtainin","authors_text":"Aditya A. Shastri, Kapil Ahuja, Navneet Pratap Singh, Seemandhar Jain, Yann Busnel","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-08-23T15:59:14Z","title":"Cube Sampled K-Prototype Clustering for Featured Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.10262","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":"sha256:9eae6115fb467b247decd0ab22df4a3ea18f98f500abcae53c2eaa70952fe44b","target":"record","created_at":"2026-07-05T03:08:03Z","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":"ae2473ef97e2dfe640c9671ac1fbba874a37582ff8a16c9a1069c77325e52369","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-08-23T15:59:14Z","title_canon_sha256":"dfb4d3e1a3960d807e77b3268741e8823657d510e6ca606c1c68974f30abcaf7"},"schema_version":"1.0","source":{"id":"2108.10262","kind":"arxiv","version":1}},"canonical_sha256":"3e60bfe6efb50887f92f3ac8b820644ea2b6bfd9e95890137b24e5b336d2cb0b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3e60bfe6efb50887f92f3ac8b820644ea2b6bfd9e95890137b24e5b336d2cb0b","first_computed_at":"2026-07-05T03:08:03.920918Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:08:03.920918Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"p3mWRnIfVYQT8fljB3u0q+wGOqY8VgApYuRGUzyvkdDhtJY0hieTELoqOdLtj45bSD8CdhF4egeq90JwJPV/DA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:08:03.921426Z","signed_message":"canonical_sha256_bytes"},"source_id":"2108.10262","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9eae6115fb467b247decd0ab22df4a3ea18f98f500abcae53c2eaa70952fe44b","sha256:73171a5e65d5bd949cb8f38ce55ccd5415d785258835abfe5a1a2e6ed11924ee"],"state_sha256":"90b5265ff855c31442e2a35f7f3e004ae6d22928244078e1ccd404ab6c0f14e9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W4V/Y/bgIfiNxCYKWA0in9JhlriquNvYO4SIBEcJ/CDJ4nsL17yqPtzkYk87yf5M0QBO6hy8cURgnqTtwP70BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T23:21:43.341144Z","bundle_sha256":"ea81a83ac4ec7714888ee4aef8392080367baf3348e2cf1c40457a60d84ad027"}}