{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:MP47AEGQH32P4QADJBHZ5BI5EF","short_pith_number":"pith:MP47AEGQ","schema_version":"1.0","canonical_sha256":"63f9f010d03ef4fe4003484f9e851d2144ae87982ead9a0794567d7677b56728","source":{"kind":"arxiv","id":"1502.00316","version":1},"attestation_state":"computed","paper":{"title":"Parallel clustering of high-dimensional social media data streams","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB","cs.SI"],"primary_cat":"cs.DC","authors_text":"Emilio Ferrara, Judy Qiu, Xiaoming Gao","submitted_at":"2015-02-01T21:41:13Z","abstract_excerpt":"We introduce Cloud DIKW as an analysis environment supporting scientific discovery through integrated parallel batch and streaming processing, and apply it to one representative domain application: social media data stream clustering. Recent work demonstrated that high-quality clusters can be generated by representing the data points using high-dimensional vectors that reflect textual content and social network information. Due to the high cost of similarity computation, sequential implementations of even single-pass algorithms cannot keep up with the speed of real-world streams. This paper pr"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1502.00316","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2015-02-01T21:41:13Z","cross_cats_sorted":["cs.DB","cs.SI"],"title_canon_sha256":"5c21c0df7fddda606ad7e161ad876f3964ec3053ab64de9a67854b340c60988a","abstract_canon_sha256":"5104ce4233b37eb4c381185d7f108ec325ae05ea8171f88a013b1cebba2fc88c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:49:35.169055Z","signature_b64":"ldwWHwlzsIZEPL+x13BHiNNryEt3JvKJtUtEE6qDEKXieuU/UCeZPqVADAVB2wSA5sD8//avJrtn7K8YQCClBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"63f9f010d03ef4fe4003484f9e851d2144ae87982ead9a0794567d7677b56728","last_reissued_at":"2026-05-18T00:49:35.168307Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:49:35.168307Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Parallel clustering of high-dimensional social media data streams","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB","cs.SI"],"primary_cat":"cs.DC","authors_text":"Emilio Ferrara, Judy Qiu, Xiaoming Gao","submitted_at":"2015-02-01T21:41:13Z","abstract_excerpt":"We introduce Cloud DIKW as an analysis environment supporting scientific discovery through integrated parallel batch and streaming processing, and apply it to one representative domain application: social media data stream clustering. Recent work demonstrated that high-quality clusters can be generated by representing the data points using high-dimensional vectors that reflect textual content and social network information. Due to the high cost of similarity computation, sequential implementations of even single-pass algorithms cannot keep up with the speed of real-world streams. This paper pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1502.00316","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1502.00316","created_at":"2026-05-18T00:49:35.168451+00:00"},{"alias_kind":"arxiv_version","alias_value":"1502.00316v1","created_at":"2026-05-18T00:49:35.168451+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1502.00316","created_at":"2026-05-18T00:49:35.168451+00:00"},{"alias_kind":"pith_short_12","alias_value":"MP47AEGQH32P","created_at":"2026-05-18T12:29:32.376354+00:00"},{"alias_kind":"pith_short_16","alias_value":"MP47AEGQH32P4QAD","created_at":"2026-05-18T12:29:32.376354+00:00"},{"alias_kind":"pith_short_8","alias_value":"MP47AEGQ","created_at":"2026-05-18T12:29:32.376354+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MP47AEGQH32P4QADJBHZ5BI5EF","json":"https://pith.science/pith/MP47AEGQH32P4QADJBHZ5BI5EF.json","graph_json":"https://pith.science/api/pith-number/MP47AEGQH32P4QADJBHZ5BI5EF/graph.json","events_json":"https://pith.science/api/pith-number/MP47AEGQH32P4QADJBHZ5BI5EF/events.json","paper":"https://pith.science/paper/MP47AEGQ"},"agent_actions":{"view_html":"https://pith.science/pith/MP47AEGQH32P4QADJBHZ5BI5EF","download_json":"https://pith.science/pith/MP47AEGQH32P4QADJBHZ5BI5EF.json","view_paper":"https://pith.science/paper/MP47AEGQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1502.00316&json=true","fetch_graph":"https://pith.science/api/pith-number/MP47AEGQH32P4QADJBHZ5BI5EF/graph.json","fetch_events":"https://pith.science/api/pith-number/MP47AEGQH32P4QADJBHZ5BI5EF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MP47AEGQH32P4QADJBHZ5BI5EF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MP47AEGQH32P4QADJBHZ5BI5EF/action/storage_attestation","attest_author":"https://pith.science/pith/MP47AEGQH32P4QADJBHZ5BI5EF/action/author_attestation","sign_citation":"https://pith.science/pith/MP47AEGQH32P4QADJBHZ5BI5EF/action/citation_signature","submit_replication":"https://pith.science/pith/MP47AEGQH32P4QADJBHZ5BI5EF/action/replication_record"}},"created_at":"2026-05-18T00:49:35.168451+00:00","updated_at":"2026-05-18T00:49:35.168451+00:00"}