{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:IMSGUSZGCKRFNALSKMSNRED7QO","short_pith_number":"pith:IMSGUSZG","canonical_record":{"source":{"id":"1511.08990","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2015-11-29T10:06:11Z","cross_cats_sorted":[],"title_canon_sha256":"5c8a88b87c77e7d41122241096b721d40129eded80513d96db0161f0b2649cce","abstract_canon_sha256":"ad2521e7bbf804397cea315a34225cee3af87c1a033d8f82ced92002bbb31ffc"},"schema_version":"1.0"},"canonical_sha256":"43246a4b2612a25681725324d8907f839af8d0ec2c7a608750e27b03a767c955","source":{"kind":"arxiv","id":"1511.08990","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1511.08990","created_at":"2026-05-18T01:21:11Z"},{"alias_kind":"arxiv_version","alias_value":"1511.08990v2","created_at":"2026-05-18T01:21:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.08990","created_at":"2026-05-18T01:21:11Z"},{"alias_kind":"pith_short_12","alias_value":"IMSGUSZGCKRF","created_at":"2026-05-18T12:29:25Z"},{"alias_kind":"pith_short_16","alias_value":"IMSGUSZGCKRFNALS","created_at":"2026-05-18T12:29:25Z"},{"alias_kind":"pith_short_8","alias_value":"IMSGUSZG","created_at":"2026-05-18T12:29:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:IMSGUSZGCKRFNALSKMSNRED7QO","target":"record","payload":{"canonical_record":{"source":{"id":"1511.08990","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2015-11-29T10:06:11Z","cross_cats_sorted":[],"title_canon_sha256":"5c8a88b87c77e7d41122241096b721d40129eded80513d96db0161f0b2649cce","abstract_canon_sha256":"ad2521e7bbf804397cea315a34225cee3af87c1a033d8f82ced92002bbb31ffc"},"schema_version":"1.0"},"canonical_sha256":"43246a4b2612a25681725324d8907f839af8d0ec2c7a608750e27b03a767c955","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:21:11.124535Z","signature_b64":"D/u7q+tZ78j/BIq0ejjbjMmTRpwWPVOHFG2U9KbU3TQR53i4zhtrkGp5Fj6fYASZ7kRLc1P6HZWZTsRG9zOuBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"43246a4b2612a25681725324d8907f839af8d0ec2c7a608750e27b03a767c955","last_reissued_at":"2026-05-18T01:21:11.123925Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:21:11.123925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1511.08990","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:21:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XWJ/S2WER2m5Tpg+2O4f4mMojGqOa0RgxJM7R0yDH6nvKqyFiCSfIobThJTusXxmun76z1K6khM/u4E8PePWBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T04:43:33.871543Z"},"content_sha256":"498e0a7eeff6d3d73ba97f9f327c2b2b59d7a878ae7dff6243fb8693e4a250b7","schema_version":"1.0","event_id":"sha256:498e0a7eeff6d3d73ba97f9f327c2b2b59d7a878ae7dff6243fb8693e4a250b7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:IMSGUSZGCKRFNALSKMSNRED7QO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"k-Means for Streaming and Distributed Big Sparse Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DS","authors_text":"Artem Barger, Dan Feldman","submitted_at":"2015-11-29T10:06:11Z","abstract_excerpt":"We provide the first streaming algorithm for computing a provable approximation to the $k$-means of sparse Big data. Here, sparse Big Data is a set of $n$ vectors in $\\mathbb{R}^d$, where each vector has $O(1)$ non-zeroes entries, and $d\\geq n$. E.g., adjacency matrix of a graph, web-links, social network, document-terms, or image-features matrices.\n  Our streaming algorithm stores at most $\\log n\\cdot k^{O(1)}$ input points in memory. If the stream is distributed among $M$ machines, the running time reduces by a factor of $M$, while communicating a total of $M\\cdot k^{O(1)}$ (sparse) input po"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.08990","kind":"arxiv","version":2},"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":"2026-05-18T01:21:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3dB3sin1lu+jVGPh44xA9UTo8Y6zIkV7gFnh8YEqtSIqNf4PcK3I98piw9v17P39boEvg1hxBaWpN4lHNmbJCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T04:43:33.872236Z"},"content_sha256":"2be0166ff00ecffc9a6f6f2a12693412b24e4c2ecb76efe88b7d3f6993665903","schema_version":"1.0","event_id":"sha256:2be0166ff00ecffc9a6f6f2a12693412b24e4c2ecb76efe88b7d3f6993665903"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IMSGUSZGCKRFNALSKMSNRED7QO/bundle.json","state_url":"https://pith.science/pith/IMSGUSZGCKRFNALSKMSNRED7QO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IMSGUSZGCKRFNALSKMSNRED7QO/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":"2026-05-20T04:43:33Z","links":{"resolver":"https://pith.science/pith/IMSGUSZGCKRFNALSKMSNRED7QO","bundle":"https://pith.science/pith/IMSGUSZGCKRFNALSKMSNRED7QO/bundle.json","state":"https://pith.science/pith/IMSGUSZGCKRFNALSKMSNRED7QO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IMSGUSZGCKRFNALSKMSNRED7QO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:IMSGUSZGCKRFNALSKMSNRED7QO","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":"ad2521e7bbf804397cea315a34225cee3af87c1a033d8f82ced92002bbb31ffc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2015-11-29T10:06:11Z","title_canon_sha256":"5c8a88b87c77e7d41122241096b721d40129eded80513d96db0161f0b2649cce"},"schema_version":"1.0","source":{"id":"1511.08990","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1511.08990","created_at":"2026-05-18T01:21:11Z"},{"alias_kind":"arxiv_version","alias_value":"1511.08990v2","created_at":"2026-05-18T01:21:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.08990","created_at":"2026-05-18T01:21:11Z"},{"alias_kind":"pith_short_12","alias_value":"IMSGUSZGCKRF","created_at":"2026-05-18T12:29:25Z"},{"alias_kind":"pith_short_16","alias_value":"IMSGUSZGCKRFNALS","created_at":"2026-05-18T12:29:25Z"},{"alias_kind":"pith_short_8","alias_value":"IMSGUSZG","created_at":"2026-05-18T12:29:25Z"}],"graph_snapshots":[{"event_id":"sha256:2be0166ff00ecffc9a6f6f2a12693412b24e4c2ecb76efe88b7d3f6993665903","target":"graph","created_at":"2026-05-18T01:21:11Z","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":"We provide the first streaming algorithm for computing a provable approximation to the $k$-means of sparse Big data. Here, sparse Big Data is a set of $n$ vectors in $\\mathbb{R}^d$, where each vector has $O(1)$ non-zeroes entries, and $d\\geq n$. E.g., adjacency matrix of a graph, web-links, social network, document-terms, or image-features matrices.\n  Our streaming algorithm stores at most $\\log n\\cdot k^{O(1)}$ input points in memory. If the stream is distributed among $M$ machines, the running time reduces by a factor of $M$, while communicating a total of $M\\cdot k^{O(1)}$ (sparse) input po","authors_text":"Artem Barger, Dan Feldman","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2015-11-29T10:06:11Z","title":"k-Means for Streaming and Distributed Big Sparse Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.08990","kind":"arxiv","version":2},"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":"sha256:498e0a7eeff6d3d73ba97f9f327c2b2b59d7a878ae7dff6243fb8693e4a250b7","target":"record","created_at":"2026-05-18T01:21:11Z","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":"ad2521e7bbf804397cea315a34225cee3af87c1a033d8f82ced92002bbb31ffc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DS","submitted_at":"2015-11-29T10:06:11Z","title_canon_sha256":"5c8a88b87c77e7d41122241096b721d40129eded80513d96db0161f0b2649cce"},"schema_version":"1.0","source":{"id":"1511.08990","kind":"arxiv","version":2}},"canonical_sha256":"43246a4b2612a25681725324d8907f839af8d0ec2c7a608750e27b03a767c955","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"43246a4b2612a25681725324d8907f839af8d0ec2c7a608750e27b03a767c955","first_computed_at":"2026-05-18T01:21:11.123925Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:21:11.123925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"D/u7q+tZ78j/BIq0ejjbjMmTRpwWPVOHFG2U9KbU3TQR53i4zhtrkGp5Fj6fYASZ7kRLc1P6HZWZTsRG9zOuBw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:21:11.124535Z","signed_message":"canonical_sha256_bytes"},"source_id":"1511.08990","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:498e0a7eeff6d3d73ba97f9f327c2b2b59d7a878ae7dff6243fb8693e4a250b7","sha256:2be0166ff00ecffc9a6f6f2a12693412b24e4c2ecb76efe88b7d3f6993665903"],"state_sha256":"cbedb8aca045a5c98ac7d82f630e0360d97aec42f2d5eb82bb929fc99abac1af"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6859bcFNsulKsOEHScN8fIzEml6jqrzy7LfuZsZD7JKt96lH8/eEPILLZqN2kM0rdvtTqcE2a6qjmr3HvHOIAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-20T04:43:33.876217Z","bundle_sha256":"73d79a43ebe86097a9b054ef2c0a3ff28a68dec6854d3975e6c02e88e0f96986"}}