{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:TNYUTNIKYY4OOLKLZDZTJRWHBR","short_pith_number":"pith:TNYUTNIK","schema_version":"1.0","canonical_sha256":"9b7149b50ac638e72d4bc8f334c6c70c72c983c79e7258165f7ca46751be04cb","source":{"kind":"arxiv","id":"1704.03421","version":2},"attestation_state":"computed","paper":{"title":"Efficient Large Scale Clustering based on Data Partitioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DB","authors_text":"Malika Bendechache, M-Tahar Kechadi, Nhien-An Le-Khac","submitted_at":"2017-04-11T17:05:01Z","abstract_excerpt":"Clustering techniques are very attractive for extracting and identifying patterns in datasets. However, their application to very large spatial datasets presents numerous challenges such as high-dimensionality data, heterogeneity, and high complexity of some algorithms. For instance, some algorithms may have linear complexity but they require the domain knowledge in order to determine their input parameters. Distributed clustering techniques constitute a very good alternative to the big data challenges (e.g.,Volume, Variety, Veracity, and Velocity). Usually these techniques consist of two phas"},"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":"1704.03421","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2017-04-11T17:05:01Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3f348e9adf484e5f71109ce3dddb40882046c45ae4678ab8b2715198506fd5c2","abstract_canon_sha256":"64ac417f6d2de5bb124625712fcc585238d0fc048fcac13030226c9ebc36657b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:39.959196Z","signature_b64":"3yCV8zCxKyqmNvnCc2iw5ZwpDmYV0jRGvFgb/0jv048i0IgmqgAP41GCgY2Jf8knvxvn6JrEQT6UfNDxO7gUAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b7149b50ac638e72d4bc8f334c6c70c72c983c79e7258165f7ca46751be04cb","last_reissued_at":"2026-05-18T00:22:39.958732Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:39.958732Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Large Scale Clustering based on Data Partitioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DB","authors_text":"Malika Bendechache, M-Tahar Kechadi, Nhien-An Le-Khac","submitted_at":"2017-04-11T17:05:01Z","abstract_excerpt":"Clustering techniques are very attractive for extracting and identifying patterns in datasets. However, their application to very large spatial datasets presents numerous challenges such as high-dimensionality data, heterogeneity, and high complexity of some algorithms. For instance, some algorithms may have linear complexity but they require the domain knowledge in order to determine their input parameters. Distributed clustering techniques constitute a very good alternative to the big data challenges (e.g.,Volume, Variety, Veracity, and Velocity). Usually these techniques consist of two phas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.03421","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1704.03421","created_at":"2026-05-18T00:22:39.958796+00:00"},{"alias_kind":"arxiv_version","alias_value":"1704.03421v2","created_at":"2026-05-18T00:22:39.958796+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.03421","created_at":"2026-05-18T00:22:39.958796+00:00"},{"alias_kind":"pith_short_12","alias_value":"TNYUTNIKYY4O","created_at":"2026-05-18T12:31:46.661854+00:00"},{"alias_kind":"pith_short_16","alias_value":"TNYUTNIKYY4OOLKL","created_at":"2026-05-18T12:31:46.661854+00:00"},{"alias_kind":"pith_short_8","alias_value":"TNYUTNIK","created_at":"2026-05-18T12:31:46.661854+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/TNYUTNIKYY4OOLKLZDZTJRWHBR","json":"https://pith.science/pith/TNYUTNIKYY4OOLKLZDZTJRWHBR.json","graph_json":"https://pith.science/api/pith-number/TNYUTNIKYY4OOLKLZDZTJRWHBR/graph.json","events_json":"https://pith.science/api/pith-number/TNYUTNIKYY4OOLKLZDZTJRWHBR/events.json","paper":"https://pith.science/paper/TNYUTNIK"},"agent_actions":{"view_html":"https://pith.science/pith/TNYUTNIKYY4OOLKLZDZTJRWHBR","download_json":"https://pith.science/pith/TNYUTNIKYY4OOLKLZDZTJRWHBR.json","view_paper":"https://pith.science/paper/TNYUTNIK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1704.03421&json=true","fetch_graph":"https://pith.science/api/pith-number/TNYUTNIKYY4OOLKLZDZTJRWHBR/graph.json","fetch_events":"https://pith.science/api/pith-number/TNYUTNIKYY4OOLKLZDZTJRWHBR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TNYUTNIKYY4OOLKLZDZTJRWHBR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TNYUTNIKYY4OOLKLZDZTJRWHBR/action/storage_attestation","attest_author":"https://pith.science/pith/TNYUTNIKYY4OOLKLZDZTJRWHBR/action/author_attestation","sign_citation":"https://pith.science/pith/TNYUTNIKYY4OOLKLZDZTJRWHBR/action/citation_signature","submit_replication":"https://pith.science/pith/TNYUTNIKYY4OOLKLZDZTJRWHBR/action/replication_record"}},"created_at":"2026-05-18T00:22:39.958796+00:00","updated_at":"2026-05-18T00:22:39.958796+00:00"}