{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:EUIG2CWLFRROYFJPQPAR2EZSWJ","short_pith_number":"pith:EUIG2CWL","canonical_record":{"source":{"id":"1704.01858","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-04-06T14:29:10Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"bbfe48c69ddca984ce89253320f1e54f05712296afb909be3d2e9a1502b0703e","abstract_canon_sha256":"f3586362335e8c73e4adf319260ff2a6d0545b0a646e513e0f6ed4ada5cdb469"},"schema_version":"1.0"},"canonical_sha256":"25106d0acb2c62ec152f83c11d1332b25dc7f4bfe7d1c3a60f8a292048426639","source":{"kind":"arxiv","id":"1704.01858","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.01858","created_at":"2026-05-18T00:46:54Z"},{"alias_kind":"arxiv_version","alias_value":"1704.01858v1","created_at":"2026-05-18T00:46:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.01858","created_at":"2026-05-18T00:46:54Z"},{"alias_kind":"pith_short_12","alias_value":"EUIG2CWLFRRO","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_16","alias_value":"EUIG2CWLFRROYFJP","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_8","alias_value":"EUIG2CWL","created_at":"2026-05-18T12:31:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:EUIG2CWLFRROYFJPQPAR2EZSWJ","target":"record","payload":{"canonical_record":{"source":{"id":"1704.01858","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-04-06T14:29:10Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"bbfe48c69ddca984ce89253320f1e54f05712296afb909be3d2e9a1502b0703e","abstract_canon_sha256":"f3586362335e8c73e4adf319260ff2a6d0545b0a646e513e0f6ed4ada5cdb469"},"schema_version":"1.0"},"canonical_sha256":"25106d0acb2c62ec152f83c11d1332b25dc7f4bfe7d1c3a60f8a292048426639","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:46:54.153723Z","signature_b64":"cOAxoFF2RZUEtO3lZkj/nFZlBak5lFutlI7nV24vyeS6aflAoz7DO7+BTWXcSCUro2EXWD0nhNtHseQH5TNPCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"25106d0acb2c62ec152f83c11d1332b25dc7f4bfe7d1c3a60f8a292048426639","last_reissued_at":"2026-05-18T00:46:54.153284Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:46:54.153284Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1704.01858","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":"2026-05-18T00:46:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HNekdPYOfW4LfMqgZvnFBU+WItPRQEHvVKLSUreIepotEXIYigG4QFKq+udzuRDN3BLU11lTSGuADMdvawLMCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T15:45:15.175825Z"},"content_sha256":"4710cfa3d3b2887993f44a8c8895ce910fec43452ed4bcf0a12a769ed93b5e85","schema_version":"1.0","event_id":"sha256:4710cfa3d3b2887993f44a8c8895ce910fec43452ed4bcf0a12a769ed93b5e85"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:EUIG2CWLFRROYFJPQPAR2EZSWJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Online Hierarchical Algorithm for Extreme Clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Akshay Krishnamurthy, Andrew McCallum, Ari Kobren, Nicholas Monath","submitted_at":"2017-04-06T14:29:10Z","abstract_excerpt":"Many modern clustering methods scale well to a large number of data items, N, but not to a large number of clusters, K. This paper introduces PERCH, a new non-greedy algorithm for online hierarchical clustering that scales to both massive N and K--a problem setting we term extreme clustering. Our algorithm efficiently routes new data points to the leaves of an incrementally-built tree. Motivated by the desire for both accuracy and speed, our approach performs tree rotations for the sake of enhancing subtree purity and encouraging balancedness. We prove that, under a natural separability assump"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.01858","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":"2026-05-18T00:46:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"34qcSEoHKHSMi2CWPjds9Ijx0I4SV0aKaD/a2Hm4dQBiJavW25ea2pfqM095834TdjyZDHWhZ5qzoek94DOTBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T15:45:15.176592Z"},"content_sha256":"3c5cbe2c0b72685ae9e13181cdb5b250c6dcd1664c4f7a901c02dc71a33616cd","schema_version":"1.0","event_id":"sha256:3c5cbe2c0b72685ae9e13181cdb5b250c6dcd1664c4f7a901c02dc71a33616cd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EUIG2CWLFRROYFJPQPAR2EZSWJ/bundle.json","state_url":"https://pith.science/pith/EUIG2CWLFRROYFJPQPAR2EZSWJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EUIG2CWLFRROYFJPQPAR2EZSWJ/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":"2026-05-27T15:45:15Z","links":{"resolver":"https://pith.science/pith/EUIG2CWLFRROYFJPQPAR2EZSWJ","bundle":"https://pith.science/pith/EUIG2CWLFRROYFJPQPAR2EZSWJ/bundle.json","state":"https://pith.science/pith/EUIG2CWLFRROYFJPQPAR2EZSWJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EUIG2CWLFRROYFJPQPAR2EZSWJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:EUIG2CWLFRROYFJPQPAR2EZSWJ","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":"f3586362335e8c73e4adf319260ff2a6d0545b0a646e513e0f6ed4ada5cdb469","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-04-06T14:29:10Z","title_canon_sha256":"bbfe48c69ddca984ce89253320f1e54f05712296afb909be3d2e9a1502b0703e"},"schema_version":"1.0","source":{"id":"1704.01858","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.01858","created_at":"2026-05-18T00:46:54Z"},{"alias_kind":"arxiv_version","alias_value":"1704.01858v1","created_at":"2026-05-18T00:46:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.01858","created_at":"2026-05-18T00:46:54Z"},{"alias_kind":"pith_short_12","alias_value":"EUIG2CWLFRRO","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_16","alias_value":"EUIG2CWLFRROYFJP","created_at":"2026-05-18T12:31:12Z"},{"alias_kind":"pith_short_8","alias_value":"EUIG2CWL","created_at":"2026-05-18T12:31:12Z"}],"graph_snapshots":[{"event_id":"sha256:3c5cbe2c0b72685ae9e13181cdb5b250c6dcd1664c4f7a901c02dc71a33616cd","target":"graph","created_at":"2026-05-18T00:46:54Z","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":"Many modern clustering methods scale well to a large number of data items, N, but not to a large number of clusters, K. This paper introduces PERCH, a new non-greedy algorithm for online hierarchical clustering that scales to both massive N and K--a problem setting we term extreme clustering. Our algorithm efficiently routes new data points to the leaves of an incrementally-built tree. Motivated by the desire for both accuracy and speed, our approach performs tree rotations for the sake of enhancing subtree purity and encouraging balancedness. We prove that, under a natural separability assump","authors_text":"Akshay Krishnamurthy, Andrew McCallum, Ari Kobren, Nicholas Monath","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-04-06T14:29:10Z","title":"An Online Hierarchical Algorithm for Extreme Clustering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.01858","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":"sha256:4710cfa3d3b2887993f44a8c8895ce910fec43452ed4bcf0a12a769ed93b5e85","target":"record","created_at":"2026-05-18T00:46:54Z","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":"f3586362335e8c73e4adf319260ff2a6d0545b0a646e513e0f6ed4ada5cdb469","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-04-06T14:29:10Z","title_canon_sha256":"bbfe48c69ddca984ce89253320f1e54f05712296afb909be3d2e9a1502b0703e"},"schema_version":"1.0","source":{"id":"1704.01858","kind":"arxiv","version":1}},"canonical_sha256":"25106d0acb2c62ec152f83c11d1332b25dc7f4bfe7d1c3a60f8a292048426639","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"25106d0acb2c62ec152f83c11d1332b25dc7f4bfe7d1c3a60f8a292048426639","first_computed_at":"2026-05-18T00:46:54.153284Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:46:54.153284Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cOAxoFF2RZUEtO3lZkj/nFZlBak5lFutlI7nV24vyeS6aflAoz7DO7+BTWXcSCUro2EXWD0nhNtHseQH5TNPCA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:46:54.153723Z","signed_message":"canonical_sha256_bytes"},"source_id":"1704.01858","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4710cfa3d3b2887993f44a8c8895ce910fec43452ed4bcf0a12a769ed93b5e85","sha256:3c5cbe2c0b72685ae9e13181cdb5b250c6dcd1664c4f7a901c02dc71a33616cd"],"state_sha256":"3440908edb0e8744d70d374f5b8dcaa85490b70849922a82e22d2eb451aff22e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IpS47BptxiSZuWKEwWmAz/jmYfi2DdiXzhecD1FoZsMlpvY+/liZxwB5ZHuuoATeTl2saNOp6EntdQpjD4H4Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T15:45:15.180527Z","bundle_sha256":"0afd2b451b6d80db2c7dd1625a99cff6bb611594c1cbfbdd776cef3add17ab6b"}}