{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:2C7AL3N5EGKBVYSHRTV7AGTFHN","short_pith_number":"pith:2C7AL3N5","canonical_record":{"source":{"id":"2105.11653","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-05-25T04:14:21Z","cross_cats_sorted":[],"title_canon_sha256":"edb5de5cf1b6d5e5c586347b7eb62bf319efe4fefdf96057b099beafca0b366e","abstract_canon_sha256":"0c9b70bbfadc44dae09ff5423710f13fdb030bc7299f3f70e8efd1da1d478126"},"schema_version":"1.0"},"canonical_sha256":"d0be05edbd21941ae2478cebf01a653b7dd3a16cc0c62249a63d32e8bff4b2bc","source":{"kind":"arxiv","id":"2105.11653","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.11653","created_at":"2026-07-05T02:42:54Z"},{"alias_kind":"arxiv_version","alias_value":"2105.11653v1","created_at":"2026-07-05T02:42:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.11653","created_at":"2026-07-05T02:42:54Z"},{"alias_kind":"pith_short_12","alias_value":"2C7AL3N5EGKB","created_at":"2026-07-05T02:42:54Z"},{"alias_kind":"pith_short_16","alias_value":"2C7AL3N5EGKBVYSH","created_at":"2026-07-05T02:42:54Z"},{"alias_kind":"pith_short_8","alias_value":"2C7AL3N5","created_at":"2026-07-05T02:42:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:2C7AL3N5EGKBVYSHRTV7AGTFHN","target":"record","payload":{"canonical_record":{"source":{"id":"2105.11653","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-05-25T04:14:21Z","cross_cats_sorted":[],"title_canon_sha256":"edb5de5cf1b6d5e5c586347b7eb62bf319efe4fefdf96057b099beafca0b366e","abstract_canon_sha256":"0c9b70bbfadc44dae09ff5423710f13fdb030bc7299f3f70e8efd1da1d478126"},"schema_version":"1.0"},"canonical_sha256":"d0be05edbd21941ae2478cebf01a653b7dd3a16cc0c62249a63d32e8bff4b2bc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:42:54.991259Z","signature_b64":"egldqoQcBX9bqpENmWwz2VmgvoaVo8tSxEyD/OpGGt83XevK8nMxwAF7NwtSJk7TCuOnPnhuCKt+ZZ/+plsHCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0be05edbd21941ae2478cebf01a653b7dd3a16cc0c62249a63d32e8bff4b2bc","last_reissued_at":"2026-07-05T02:42:54.990774Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:42:54.990774Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2105.11653","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":"2026-07-05T02:42:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CxMBi1CBR/15NaB+OdIuUsghbIqPWzQKBnwcXqTQmo2QMIVBCsy9CrDNadqLfUDM8mzwFI3kSbp86ekx6I9gDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:43:27.807894Z"},"content_sha256":"556fba12c6f899f525b8b3cc555a4b3655ecb522d0d1d426a66195544ebd4bd6","schema_version":"1.0","event_id":"sha256:556fba12c6f899f525b8b3cc555a4b3655ecb522d0d1d426a66195544ebd4bd6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:2C7AL3N5EGKBVYSHRTV7AGTFHN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scaling Hierarchical Agglomerative Clustering to Billion-sized Datasets","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"(2) 0x Labs), Anand Rajagopalan (1), Baris Sumengen (1), David Simcha (1), Gui Citovsky (1), Mason Liang (2), Olivier Bachem (1), Pradipta Mitra (1), Sam Blasiak (1), Sanjiv Kumar (1) ((1) Google Research","submitted_at":"2021-05-25T04:14:21Z","abstract_excerpt":"Hierarchical Agglomerative Clustering (HAC) is one of the oldest but still most widely used clustering methods. However, HAC is notoriously hard to scale to large data sets as the underlying complexity is at least quadratic in the number of data points and many algorithms to solve HAC are inherently sequential. In this paper, we propose {Reciprocal Agglomerative Clustering (RAC)}, a distributed algorithm for HAC, that uses a novel strategy to efficiently merge clusters in parallel. We prove theoretically that RAC recovers the exact solution of HAC. Furthermore, under clusterability and balance"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.11653","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/2105.11653/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":"2026-07-05T02:42:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BI928X2jEC04sw22IJBrDJvyX6X4DXpljmq0QcaM9Mj6tAacZhMG00u3wRkPC809lILcm8bkvEvDQZBwq+WEAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:43:27.808406Z"},"content_sha256":"0434914776f1e121ad3ebee8e754f4da877d4f9a826cdf43fb02e072a5466380","schema_version":"1.0","event_id":"sha256:0434914776f1e121ad3ebee8e754f4da877d4f9a826cdf43fb02e072a5466380"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2C7AL3N5EGKBVYSHRTV7AGTFHN/bundle.json","state_url":"https://pith.science/pith/2C7AL3N5EGKBVYSHRTV7AGTFHN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2C7AL3N5EGKBVYSHRTV7AGTFHN/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":"2026-08-08T19:43:27Z","links":{"resolver":"https://pith.science/pith/2C7AL3N5EGKBVYSHRTV7AGTFHN","bundle":"https://pith.science/pith/2C7AL3N5EGKBVYSHRTV7AGTFHN/bundle.json","state":"https://pith.science/pith/2C7AL3N5EGKBVYSHRTV7AGTFHN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2C7AL3N5EGKBVYSHRTV7AGTFHN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:2C7AL3N5EGKBVYSHRTV7AGTFHN","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":"0c9b70bbfadc44dae09ff5423710f13fdb030bc7299f3f70e8efd1da1d478126","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-05-25T04:14:21Z","title_canon_sha256":"edb5de5cf1b6d5e5c586347b7eb62bf319efe4fefdf96057b099beafca0b366e"},"schema_version":"1.0","source":{"id":"2105.11653","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.11653","created_at":"2026-07-05T02:42:54Z"},{"alias_kind":"arxiv_version","alias_value":"2105.11653v1","created_at":"2026-07-05T02:42:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.11653","created_at":"2026-07-05T02:42:54Z"},{"alias_kind":"pith_short_12","alias_value":"2C7AL3N5EGKB","created_at":"2026-07-05T02:42:54Z"},{"alias_kind":"pith_short_16","alias_value":"2C7AL3N5EGKBVYSH","created_at":"2026-07-05T02:42:54Z"},{"alias_kind":"pith_short_8","alias_value":"2C7AL3N5","created_at":"2026-07-05T02:42:54Z"}],"graph_snapshots":[{"event_id":"sha256:0434914776f1e121ad3ebee8e754f4da877d4f9a826cdf43fb02e072a5466380","target":"graph","created_at":"2026-07-05T02:42:54Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2105.11653/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Hierarchical Agglomerative Clustering (HAC) is one of the oldest but still most widely used clustering methods. However, HAC is notoriously hard to scale to large data sets as the underlying complexity is at least quadratic in the number of data points and many algorithms to solve HAC are inherently sequential. In this paper, we propose {Reciprocal Agglomerative Clustering (RAC)}, a distributed algorithm for HAC, that uses a novel strategy to efficiently merge clusters in parallel. We prove theoretically that RAC recovers the exact solution of HAC. Furthermore, under clusterability and balance","authors_text":"(2) 0x Labs), Anand Rajagopalan (1), Baris Sumengen (1), David Simcha (1), Gui Citovsky (1), Mason Liang (2), Olivier Bachem (1), Pradipta Mitra (1), Sam Blasiak (1), Sanjiv Kumar (1) ((1) Google Research","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-05-25T04:14:21Z","title":"Scaling Hierarchical Agglomerative Clustering to Billion-sized Datasets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.11653","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":"sha256:556fba12c6f899f525b8b3cc555a4b3655ecb522d0d1d426a66195544ebd4bd6","target":"record","created_at":"2026-07-05T02:42:54Z","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":"0c9b70bbfadc44dae09ff5423710f13fdb030bc7299f3f70e8efd1da1d478126","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-05-25T04:14:21Z","title_canon_sha256":"edb5de5cf1b6d5e5c586347b7eb62bf319efe4fefdf96057b099beafca0b366e"},"schema_version":"1.0","source":{"id":"2105.11653","kind":"arxiv","version":1}},"canonical_sha256":"d0be05edbd21941ae2478cebf01a653b7dd3a16cc0c62249a63d32e8bff4b2bc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d0be05edbd21941ae2478cebf01a653b7dd3a16cc0c62249a63d32e8bff4b2bc","first_computed_at":"2026-07-05T02:42:54.990774Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:42:54.990774Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"egldqoQcBX9bqpENmWwz2VmgvoaVo8tSxEyD/OpGGt83XevK8nMxwAF7NwtSJk7TCuOnPnhuCKt+ZZ/+plsHCg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:42:54.991259Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.11653","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:556fba12c6f899f525b8b3cc555a4b3655ecb522d0d1d426a66195544ebd4bd6","sha256:0434914776f1e121ad3ebee8e754f4da877d4f9a826cdf43fb02e072a5466380"],"state_sha256":"de90f17fcee1f231fb20dd8d243577e998145ac3228dbc7ba63dc4a4327c4844"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gjxkaTW22Q8OLIJCCtPZLuTRO3IcpHcrfnrVdiPO5hqDcf/NEvjR1mp7l64LN9fH1mhzXLZBs54EMOw1O8FrCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T19:43:27.812776Z","bundle_sha256":"9b19e11b4f11b89d0899a5c9eb4c750982593b6e1c604297dabd9f1c9e1d5573"}}