{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:KOV57TBK5O6FHEJYHCYHPXVUDG","short_pith_number":"pith:KOV57TBK","canonical_record":{"source":{"id":"1907.02907","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-07-05T16:10:57Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1a6fe4abbc00768d57252ca96b9cef41cb8e965cbd7946e474e712cb937da97d","abstract_canon_sha256":"75d383f0089a5fc46fe7c9e8c90dfb65e4687e0e0382cfea11d1cb1f4d213b60"},"schema_version":"1.0"},"canonical_sha256":"53abdfcc2aebbc53913838b077deb419afa117bde579bc60231834fb753cad9e","source":{"kind":"arxiv","id":"1907.02907","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.02907","created_at":"2026-05-17T23:41:22Z"},{"alias_kind":"arxiv_version","alias_value":"1907.02907v1","created_at":"2026-05-17T23:41:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.02907","created_at":"2026-05-17T23:41:22Z"},{"alias_kind":"pith_short_12","alias_value":"KOV57TBK5O6F","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"KOV57TBK5O6FHEJY","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"KOV57TBK","created_at":"2026-05-18T12:33:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:KOV57TBK5O6FHEJYHCYHPXVUDG","target":"record","payload":{"canonical_record":{"source":{"id":"1907.02907","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-07-05T16:10:57Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1a6fe4abbc00768d57252ca96b9cef41cb8e965cbd7946e474e712cb937da97d","abstract_canon_sha256":"75d383f0089a5fc46fe7c9e8c90dfb65e4687e0e0382cfea11d1cb1f4d213b60"},"schema_version":"1.0"},"canonical_sha256":"53abdfcc2aebbc53913838b077deb419afa117bde579bc60231834fb753cad9e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:41:22.649242Z","signature_b64":"1Gwi6NSrYku9hgYjX5V1AYLfV+VVN6F1MP/FRfMbwavW59wC/gVIgsRVp0VGRxOXO3TKGRG+DXus2L1qiorvDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53abdfcc2aebbc53913838b077deb419afa117bde579bc60231834fb753cad9e","last_reissued_at":"2026-05-17T23:41:22.648679Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:41:22.648679Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1907.02907","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":"2026-05-17T23:41:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xeD3l52mhGTWYaxfhrNV3mcFInuTtUps6/Zh7uqz53esBTIBndaJnm87/HCRtH0AO0xgKOhl5YndLkGIqLWVDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T19:23:22.626957Z"},"content_sha256":"0a1a6833d107e46069922c523e80a00bdea4747cd521fbb869825c786299058a","schema_version":"1.0","event_id":"sha256:0a1a6833d107e46069922c523e80a00bdea4747cd521fbb869825c786299058a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:KOV57TBK5O6FHEJYHCYHPXVUDG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hybridized Threshold Clustering for Massive Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Aruna Sai Kannamareddy, ChandraVyas Annakula, Jasjeet S. Sekhon, Jianmei Luo, Michael Higgins, William Henry Hsu","submitted_at":"2019-07-05T16:10:57Z","abstract_excerpt":"As the size $n$ of datasets become massive, many commonly-used clustering algorithms (for example, $k$-means or hierarchical agglomerative clustering (HAC) require prohibitive computational cost and memory. In this paper, we propose a solution to these clustering problems by extending threshold clustering (TC) to problems of instance selection. TC is a recently developed clustering algorithm designed to partition data into many small clusters in linearithmic time (on average). Our proposed clustering method is as follows. First, TC is performed and clusters are reduced into single \"prototype\" "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.02907","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":"2026-05-17T23:41:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rgvQSWYHdtg9U7JVkfeC0HVSahzwABjuJL394gtfdsnwykYFcwe1o9IJpFfQmiJnsuAF0Jj1vO0vIaGQY20MBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T19:23:22.627295Z"},"content_sha256":"79b838a29bf3dde627070c41675cf33d5c8c881b43d2f2f043e42607b1d7fdea","schema_version":"1.0","event_id":"sha256:79b838a29bf3dde627070c41675cf33d5c8c881b43d2f2f043e42607b1d7fdea"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KOV57TBK5O6FHEJYHCYHPXVUDG/bundle.json","state_url":"https://pith.science/pith/KOV57TBK5O6FHEJYHCYHPXVUDG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KOV57TBK5O6FHEJYHCYHPXVUDG/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":"2026-05-30T19:23:22Z","links":{"resolver":"https://pith.science/pith/KOV57TBK5O6FHEJYHCYHPXVUDG","bundle":"https://pith.science/pith/KOV57TBK5O6FHEJYHCYHPXVUDG/bundle.json","state":"https://pith.science/pith/KOV57TBK5O6FHEJYHCYHPXVUDG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KOV57TBK5O6FHEJYHCYHPXVUDG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:KOV57TBK5O6FHEJYHCYHPXVUDG","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":"75d383f0089a5fc46fe7c9e8c90dfb65e4687e0e0382cfea11d1cb1f4d213b60","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-07-05T16:10:57Z","title_canon_sha256":"1a6fe4abbc00768d57252ca96b9cef41cb8e965cbd7946e474e712cb937da97d"},"schema_version":"1.0","source":{"id":"1907.02907","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.02907","created_at":"2026-05-17T23:41:22Z"},{"alias_kind":"arxiv_version","alias_value":"1907.02907v1","created_at":"2026-05-17T23:41:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.02907","created_at":"2026-05-17T23:41:22Z"},{"alias_kind":"pith_short_12","alias_value":"KOV57TBK5O6F","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"KOV57TBK5O6FHEJY","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"KOV57TBK","created_at":"2026-05-18T12:33:21Z"}],"graph_snapshots":[{"event_id":"sha256:79b838a29bf3dde627070c41675cf33d5c8c881b43d2f2f043e42607b1d7fdea","target":"graph","created_at":"2026-05-17T23:41:22Z","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":"As the size $n$ of datasets become massive, many commonly-used clustering algorithms (for example, $k$-means or hierarchical agglomerative clustering (HAC) require prohibitive computational cost and memory. In this paper, we propose a solution to these clustering problems by extending threshold clustering (TC) to problems of instance selection. TC is a recently developed clustering algorithm designed to partition data into many small clusters in linearithmic time (on average). Our proposed clustering method is as follows. First, TC is performed and clusters are reduced into single \"prototype\" ","authors_text":"Aruna Sai Kannamareddy, ChandraVyas Annakula, Jasjeet S. Sekhon, Jianmei Luo, Michael Higgins, William Henry Hsu","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-07-05T16:10:57Z","title":"Hybridized Threshold Clustering for Massive Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.02907","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":"sha256:0a1a6833d107e46069922c523e80a00bdea4747cd521fbb869825c786299058a","target":"record","created_at":"2026-05-17T23:41:22Z","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":"75d383f0089a5fc46fe7c9e8c90dfb65e4687e0e0382cfea11d1cb1f4d213b60","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-07-05T16:10:57Z","title_canon_sha256":"1a6fe4abbc00768d57252ca96b9cef41cb8e965cbd7946e474e712cb937da97d"},"schema_version":"1.0","source":{"id":"1907.02907","kind":"arxiv","version":1}},"canonical_sha256":"53abdfcc2aebbc53913838b077deb419afa117bde579bc60231834fb753cad9e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"53abdfcc2aebbc53913838b077deb419afa117bde579bc60231834fb753cad9e","first_computed_at":"2026-05-17T23:41:22.648679Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:41:22.648679Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1Gwi6NSrYku9hgYjX5V1AYLfV+VVN6F1MP/FRfMbwavW59wC/gVIgsRVp0VGRxOXO3TKGRG+DXus2L1qiorvDw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:41:22.649242Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.02907","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0a1a6833d107e46069922c523e80a00bdea4747cd521fbb869825c786299058a","sha256:79b838a29bf3dde627070c41675cf33d5c8c881b43d2f2f043e42607b1d7fdea"],"state_sha256":"cf2852fb878f95500a13e8b17cbbd00729e2fb76b3444619dfd75c2ef690ee66"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NK0E5Wym00pcd3T/G89rjEzoSsWAtqXUJXpCnIpH7ubkSK3jNoeDE8tsK9DkRFFp9nNsb9Tg40r+m/hgPRexDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T19:23:22.629186Z","bundle_sha256":"37da779309f81c6fa6a37d533157318ab72fad5a4222c213a1e0dc9cb5a405a5"}}