{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:SUBQNZDNMMXXVWXFDSOLMLWEOL","short_pith_number":"pith:SUBQNZDN","schema_version":"1.0","canonical_sha256":"950306e46d632f7adae51c9cb62ec472ee9665ded022a703721e348b9f89e8a8","source":{"kind":"arxiv","id":"1703.02375","version":5},"attestation_state":"computed","paper":{"title":"Graph sketching-based Space-efficient Data Clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS"],"primary_cat":"cs.LG","authors_text":"Anne Morvan, C\\'edric Gouy-Pailler, Jamal Atif, Krzysztof Choromanski","submitted_at":"2017-03-07T13:43:45Z","abstract_excerpt":"In this paper, we address the problem of recovering arbitrary-shaped data clusters from datasets while facing \\emph{high space constraints}, as this is for instance the case in many real-world applications when analysis algorithms are directly deployed on resources-limited mobile devices collecting the data. We present DBMSTClu a new space-efficient density-based \\emph{non-parametric} method working on a Minimum Spanning Tree (MST) recovered from a limited number of linear measurements i.e. a \\emph{sketched} version of the dissimilarity graph $\\mathcal{G}$ between the $N$ objects to cluster. U"},"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":"1703.02375","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-07T13:43:45Z","cross_cats_sorted":["cs.DS"],"title_canon_sha256":"5b3f4bdcd5be3aa4ed09f815b94064271a7d8fbb10fe14bd734613af16435ab9","abstract_canon_sha256":"e8fcd5d062ab7ed1651c0c4e72eb9bf20b17ac3b2637e63d1cc83e4e40c572d5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:57.161222Z","signature_b64":"KpkgN1ffwBw7wWLfxaQi4a6ZyHmjXWM1qceAYVt+BCxjRczo9DdCq2eAL7Ves9ugWgUtPWA3oVrVPVl5AQ//Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"950306e46d632f7adae51c9cb62ec472ee9665ded022a703721e348b9f89e8a8","last_reissued_at":"2026-05-18T00:14:57.160509Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:57.160509Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Graph sketching-based Space-efficient Data Clustering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS"],"primary_cat":"cs.LG","authors_text":"Anne Morvan, C\\'edric Gouy-Pailler, Jamal Atif, Krzysztof Choromanski","submitted_at":"2017-03-07T13:43:45Z","abstract_excerpt":"In this paper, we address the problem of recovering arbitrary-shaped data clusters from datasets while facing \\emph{high space constraints}, as this is for instance the case in many real-world applications when analysis algorithms are directly deployed on resources-limited mobile devices collecting the data. We present DBMSTClu a new space-efficient density-based \\emph{non-parametric} method working on a Minimum Spanning Tree (MST) recovered from a limited number of linear measurements i.e. a \\emph{sketched} version of the dissimilarity graph $\\mathcal{G}$ between the $N$ objects to cluster. U"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.02375","kind":"arxiv","version":5},"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":"1703.02375","created_at":"2026-05-18T00:14:57.160626+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.02375v5","created_at":"2026-05-18T00:14:57.160626+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.02375","created_at":"2026-05-18T00:14:57.160626+00:00"},{"alias_kind":"pith_short_12","alias_value":"SUBQNZDNMMXX","created_at":"2026-05-18T12:31:43.269735+00:00"},{"alias_kind":"pith_short_16","alias_value":"SUBQNZDNMMXXVWXF","created_at":"2026-05-18T12:31:43.269735+00:00"},{"alias_kind":"pith_short_8","alias_value":"SUBQNZDN","created_at":"2026-05-18T12:31:43.269735+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/SUBQNZDNMMXXVWXFDSOLMLWEOL","json":"https://pith.science/pith/SUBQNZDNMMXXVWXFDSOLMLWEOL.json","graph_json":"https://pith.science/api/pith-number/SUBQNZDNMMXXVWXFDSOLMLWEOL/graph.json","events_json":"https://pith.science/api/pith-number/SUBQNZDNMMXXVWXFDSOLMLWEOL/events.json","paper":"https://pith.science/paper/SUBQNZDN"},"agent_actions":{"view_html":"https://pith.science/pith/SUBQNZDNMMXXVWXFDSOLMLWEOL","download_json":"https://pith.science/pith/SUBQNZDNMMXXVWXFDSOLMLWEOL.json","view_paper":"https://pith.science/paper/SUBQNZDN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.02375&json=true","fetch_graph":"https://pith.science/api/pith-number/SUBQNZDNMMXXVWXFDSOLMLWEOL/graph.json","fetch_events":"https://pith.science/api/pith-number/SUBQNZDNMMXXVWXFDSOLMLWEOL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SUBQNZDNMMXXVWXFDSOLMLWEOL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SUBQNZDNMMXXVWXFDSOLMLWEOL/action/storage_attestation","attest_author":"https://pith.science/pith/SUBQNZDNMMXXVWXFDSOLMLWEOL/action/author_attestation","sign_citation":"https://pith.science/pith/SUBQNZDNMMXXVWXFDSOLMLWEOL/action/citation_signature","submit_replication":"https://pith.science/pith/SUBQNZDNMMXXVWXFDSOLMLWEOL/action/replication_record"}},"created_at":"2026-05-18T00:14:57.160626+00:00","updated_at":"2026-05-18T00:14:57.160626+00:00"}