{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:VJM65JCM4DRIMLHMJD5TD47ISN","short_pith_number":"pith:VJM65JCM","canonical_record":{"source":{"id":"1703.00830","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2017-03-02T15:27:14Z","cross_cats_sorted":["cs.DC","cs.LG"],"title_canon_sha256":"946b951d65655187d6797419cfb1729701562ca5d62619149b345b9f00e4444f","abstract_canon_sha256":"7336a660ac0a6d68fa9e26b42e6e1dfdd010ec9671dd379a132ea10d66a55a7d"},"schema_version":"1.0"},"canonical_sha256":"aa59eea44ce0e2862cec48fb31f3e8936de5e4b857d5e5cfa9b31583e5951f36","source":{"kind":"arxiv","id":"1703.00830","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.00830","created_at":"2026-05-17T23:51:54Z"},{"alias_kind":"arxiv_version","alias_value":"1703.00830v3","created_at":"2026-05-17T23:51:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.00830","created_at":"2026-05-17T23:51:54Z"},{"alias_kind":"pith_short_12","alias_value":"VJM65JCM4DRI","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_16","alias_value":"VJM65JCM4DRIMLHM","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_8","alias_value":"VJM65JCM","created_at":"2026-05-18T12:31:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:VJM65JCM4DRIMLHMJD5TD47ISN","target":"record","payload":{"canonical_record":{"source":{"id":"1703.00830","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2017-03-02T15:27:14Z","cross_cats_sorted":["cs.DC","cs.LG"],"title_canon_sha256":"946b951d65655187d6797419cfb1729701562ca5d62619149b345b9f00e4444f","abstract_canon_sha256":"7336a660ac0a6d68fa9e26b42e6e1dfdd010ec9671dd379a132ea10d66a55a7d"},"schema_version":"1.0"},"canonical_sha256":"aa59eea44ce0e2862cec48fb31f3e8936de5e4b857d5e5cfa9b31583e5951f36","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:54.904668Z","signature_b64":"j6SwbbuXVxLubj7GrPGOMnMie2t8hCZfx5TjRPZixkvjXdc3pALFTzMtoG+Vjfy3XYjOooPpw8nl0L7eKq4RDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa59eea44ce0e2862cec48fb31f3e8936de5e4b857d5e5cfa9b31583e5951f36","last_reissued_at":"2026-05-17T23:51:54.904209Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:54.904209Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1703.00830","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:51:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H9RhZFtBjjiVj/Llgh9rAaiMgLcZIJoCMp/NpIywLtrcjxZAcBAADHvAVYB2vY1zsaVS0u+Hc3ExHhTLy5ghDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T13:47:49.977120Z"},"content_sha256":"36bdae5bd5a8395d68bac76deb416409843f61011314dd3b5ce7b5035b758b6a","schema_version":"1.0","event_id":"sha256:36bdae5bd5a8395d68bac76deb416409843f61011314dd3b5ce7b5035b758b6a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:VJM65JCM4DRIMLHMJD5TD47ISN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Robust Communication-Optimal Distributed Clustering Algorithms","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","cs.LG"],"primary_cat":"cs.DS","authors_text":"Ainesh Bakshi, Colin White, David Woodruff, Maria-Florina Balcan, Pranjal Awasthi","submitted_at":"2017-03-02T15:27:14Z","abstract_excerpt":"In this work, we study the $k$-median and $k$-means clustering problems when the data is distributed across many servers and can contain outliers. While there has been a lot of work on these problems for worst-case instances, we focus on gaining a finer understanding through the lens of beyond worst-case analysis. Our main motivation is the following: for many applications such as clustering proteins by function or clustering communities in a social network, there is some unknown target clustering, and the hope is that running a $k$-median or $k$-means algorithm will produce clusterings which "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.00830","kind":"arxiv","version":3},"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":"2026-05-17T23:51:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2HDOY/So7QLUkzjfNdZ7giNYHUguyW/oz7vtNcb+jZK8jT1ho/6ZS3oj0xqn3UUchoY5PkW1sY82YdSJqeNnAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T13:47:49.977484Z"},"content_sha256":"c77ea714acc8627a3226319693d5df098dea4b9aae73c77955a5a542cfd42022","schema_version":"1.0","event_id":"sha256:c77ea714acc8627a3226319693d5df098dea4b9aae73c77955a5a542cfd42022"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VJM65JCM4DRIMLHMJD5TD47ISN/bundle.json","state_url":"https://pith.science/pith/VJM65JCM4DRIMLHMJD5TD47ISN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VJM65JCM4DRIMLHMJD5TD47ISN/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":"2026-06-04T13:47:49Z","links":{"resolver":"https://pith.science/pith/VJM65JCM4DRIMLHMJD5TD47ISN","bundle":"https://pith.science/pith/VJM65JCM4DRIMLHMJD5TD47ISN/bundle.json","state":"https://pith.science/pith/VJM65JCM4DRIMLHMJD5TD47ISN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VJM65JCM4DRIMLHMJD5TD47ISN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:VJM65JCM4DRIMLHMJD5TD47ISN","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":"7336a660ac0a6d68fa9e26b42e6e1dfdd010ec9671dd379a132ea10d66a55a7d","cross_cats_sorted":["cs.DC","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2017-03-02T15:27:14Z","title_canon_sha256":"946b951d65655187d6797419cfb1729701562ca5d62619149b345b9f00e4444f"},"schema_version":"1.0","source":{"id":"1703.00830","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.00830","created_at":"2026-05-17T23:51:54Z"},{"alias_kind":"arxiv_version","alias_value":"1703.00830v3","created_at":"2026-05-17T23:51:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.00830","created_at":"2026-05-17T23:51:54Z"},{"alias_kind":"pith_short_12","alias_value":"VJM65JCM4DRI","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_16","alias_value":"VJM65JCM4DRIMLHM","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_8","alias_value":"VJM65JCM","created_at":"2026-05-18T12:31:49Z"}],"graph_snapshots":[{"event_id":"sha256:c77ea714acc8627a3226319693d5df098dea4b9aae73c77955a5a542cfd42022","target":"graph","created_at":"2026-05-17T23:51:54Z","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":"In this work, we study the $k$-median and $k$-means clustering problems when the data is distributed across many servers and can contain outliers. While there has been a lot of work on these problems for worst-case instances, we focus on gaining a finer understanding through the lens of beyond worst-case analysis. Our main motivation is the following: for many applications such as clustering proteins by function or clustering communities in a social network, there is some unknown target clustering, and the hope is that running a $k$-median or $k$-means algorithm will produce clusterings which ","authors_text":"Ainesh Bakshi, Colin White, David Woodruff, Maria-Florina Balcan, Pranjal Awasthi","cross_cats":["cs.DC","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2017-03-02T15:27:14Z","title":"Robust Communication-Optimal Distributed Clustering Algorithms"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.00830","kind":"arxiv","version":3},"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":"sha256:36bdae5bd5a8395d68bac76deb416409843f61011314dd3b5ce7b5035b758b6a","target":"record","created_at":"2026-05-17T23:51:54Z","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":"7336a660ac0a6d68fa9e26b42e6e1dfdd010ec9671dd379a132ea10d66a55a7d","cross_cats_sorted":["cs.DC","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2017-03-02T15:27:14Z","title_canon_sha256":"946b951d65655187d6797419cfb1729701562ca5d62619149b345b9f00e4444f"},"schema_version":"1.0","source":{"id":"1703.00830","kind":"arxiv","version":3}},"canonical_sha256":"aa59eea44ce0e2862cec48fb31f3e8936de5e4b857d5e5cfa9b31583e5951f36","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aa59eea44ce0e2862cec48fb31f3e8936de5e4b857d5e5cfa9b31583e5951f36","first_computed_at":"2026-05-17T23:51:54.904209Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:51:54.904209Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"j6SwbbuXVxLubj7GrPGOMnMie2t8hCZfx5TjRPZixkvjXdc3pALFTzMtoG+Vjfy3XYjOooPpw8nl0L7eKq4RDQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:51:54.904668Z","signed_message":"canonical_sha256_bytes"},"source_id":"1703.00830","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:36bdae5bd5a8395d68bac76deb416409843f61011314dd3b5ce7b5035b758b6a","sha256:c77ea714acc8627a3226319693d5df098dea4b9aae73c77955a5a542cfd42022"],"state_sha256":"fec4e227b7cd4dbdc134dbe8652bd27ad9eba8fa0583c561921e56610ffec277"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0e/NS8OIOqoDjcwMjlOIA9l8z3eratsz+BEUhjz56uxQiHpb0p60a4T2YQ5JYIOQfaQ1UhkCLrynkAfGiz8DDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T13:47:49.979492Z","bundle_sha256":"a1bd45438a21961a9e20c006fcf5f6cd2dc973d09d209bae51d2cf86c76e0d99"}}