{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SD725TGKKB53MKFSPIQEKAXUYF","short_pith_number":"pith:SD725TGK","schema_version":"1.0","canonical_sha256":"90ffaeccca507bb628b27a204502f4c1747f69696a039884bf643b5c759a9f28","source":{"kind":"arxiv","id":"2411.11421","version":3},"attestation_state":"computed","paper":{"title":"Enabling DBSCAN for Very Large-Scale High-Dimensional Spaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Yongyu Wang","submitted_at":"2024-11-18T09:46:45Z","abstract_excerpt":"DBSCAN is one of the most important non-parametric unsupervised data analysis tools. By applying DBSCAN to a dataset, two key analytical results can be obtained: (1) clustering data points based on density distribution and (2) identifying outliers in the dataset. However, the time complexity of the DBSCAN algorithm is $O(n^2 \\beta)$, where $n$ is the number of data points and $\\beta = O(D)$, with $D$ representing the dimensionality of the data space. As a result, DBSCAN becomes computationally infeasible when both $n$ and $D$ are large. In this paper, we propose a DBSCAN method based on spectr"},"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":"2411.11421","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-18T09:46:45Z","cross_cats_sorted":[],"title_canon_sha256":"0a1d5169124e62601bd857c746445953b0c4abf53f9c7ee4e6a3cb1104cfd5ba","abstract_canon_sha256":"2f77851da9449e8e91cdd978dc15893334e3e5743f9c079303bb7450264fd6bb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:43:37.038846Z","signature_b64":"LoAjhScLz5B0FccE2LUXWI/718NqI1kUtOGF1iBSYY+m8wYvcx1SHI9FEkw+sLs578amp8g9FyYdNlx2xoUGCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90ffaeccca507bb628b27a204502f4c1747f69696a039884bf643b5c759a9f28","last_reissued_at":"2026-07-05T09:43:37.038364Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:43:37.038364Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enabling DBSCAN for Very Large-Scale High-Dimensional Spaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Yongyu Wang","submitted_at":"2024-11-18T09:46:45Z","abstract_excerpt":"DBSCAN is one of the most important non-parametric unsupervised data analysis tools. By applying DBSCAN to a dataset, two key analytical results can be obtained: (1) clustering data points based on density distribution and (2) identifying outliers in the dataset. However, the time complexity of the DBSCAN algorithm is $O(n^2 \\beta)$, where $n$ is the number of data points and $\\beta = O(D)$, with $D$ representing the dimensionality of the data space. As a result, DBSCAN becomes computationally infeasible when both $n$ and $D$ are large. In this paper, we propose a DBSCAN method based on spectr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.11421","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2411.11421/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2411.11421","created_at":"2026-07-05T09:43:37.038417+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.11421v3","created_at":"2026-07-05T09:43:37.038417+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.11421","created_at":"2026-07-05T09:43:37.038417+00:00"},{"alias_kind":"pith_short_12","alias_value":"SD725TGKKB53","created_at":"2026-07-05T09:43:37.038417+00:00"},{"alias_kind":"pith_short_16","alias_value":"SD725TGKKB53MKFS","created_at":"2026-07-05T09:43:37.038417+00:00"},{"alias_kind":"pith_short_8","alias_value":"SD725TGK","created_at":"2026-07-05T09:43:37.038417+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.03848","citing_title":"Advanced Clustering Framework for Semiconductor Image Analytics Integrating Deep TDA with Self-Supervised and Transfer Learning Techniques","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SD725TGKKB53MKFSPIQEKAXUYF","json":"https://pith.science/pith/SD725TGKKB53MKFSPIQEKAXUYF.json","graph_json":"https://pith.science/api/pith-number/SD725TGKKB53MKFSPIQEKAXUYF/graph.json","events_json":"https://pith.science/api/pith-number/SD725TGKKB53MKFSPIQEKAXUYF/events.json","paper":"https://pith.science/paper/SD725TGK"},"agent_actions":{"view_html":"https://pith.science/pith/SD725TGKKB53MKFSPIQEKAXUYF","download_json":"https://pith.science/pith/SD725TGKKB53MKFSPIQEKAXUYF.json","view_paper":"https://pith.science/paper/SD725TGK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.11421&json=true","fetch_graph":"https://pith.science/api/pith-number/SD725TGKKB53MKFSPIQEKAXUYF/graph.json","fetch_events":"https://pith.science/api/pith-number/SD725TGKKB53MKFSPIQEKAXUYF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SD725TGKKB53MKFSPIQEKAXUYF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SD725TGKKB53MKFSPIQEKAXUYF/action/storage_attestation","attest_author":"https://pith.science/pith/SD725TGKKB53MKFSPIQEKAXUYF/action/author_attestation","sign_citation":"https://pith.science/pith/SD725TGKKB53MKFSPIQEKAXUYF/action/citation_signature","submit_replication":"https://pith.science/pith/SD725TGKKB53MKFSPIQEKAXUYF/action/replication_record"}},"created_at":"2026-07-05T09:43:37.038417+00:00","updated_at":"2026-07-05T09:43:37.038417+00:00"}