{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:L5VBO4PQ2JDYG55GD2F2YM6ZLO","short_pith_number":"pith:L5VBO4PQ","schema_version":"1.0","canonical_sha256":"5f6a1771f0d2478377a61e8bac33d95bb7aa701b172ec076fa0295bd3e0ebadc","source":{"kind":"arxiv","id":"2301.10327","version":3},"attestation_state":"computed","paper":{"title":"Generating Multidimensional Clusters With Support Lines","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CV","cs.PL"],"primary_cat":"cs.LG","authors_text":"Diogo de Andrade, Nuno Fachada","submitted_at":"2023-01-24T22:08:24Z","abstract_excerpt":"Synthetic data is essential for assessing clustering techniques, complementing and extending real data, and allowing for more complete coverage of a given problem's space. In turn, synthetic data generators have the potential of creating vast amounts of data -- a crucial activity when real-world data is at premium -- while providing a well-understood generation procedure and an interpretable instrument for methodically investigating cluster analysis algorithms. Here, we present Clugen, a modular procedure for synthetic data generation, capable of creating multidimensional clusters supported by"},"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":"2301.10327","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-24T22:08:24Z","cross_cats_sorted":["cs.CV","cs.PL"],"title_canon_sha256":"43c41153bda5cdd59c70149216ca474776a6e6c1e8be70eb9c35406e3a7b5e38","abstract_canon_sha256":"7eb32facea1e418fd89b2e1c63492b87705966d065bd3ca42d5c6eddfaf71614"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:52:08.330250Z","signature_b64":"uh5dOEry4f42ESDFDPJb7VY3fJdT+9QOM3H73P5Xn4Kp6XZMKXU4DoHi6OUA0WldZzmg6iqLkubv93Sbe+I1DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f6a1771f0d2478377a61e8bac33d95bb7aa701b172ec076fa0295bd3e0ebadc","last_reissued_at":"2026-07-05T07:52:08.329722Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:52:08.329722Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generating Multidimensional Clusters With Support Lines","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CV","cs.PL"],"primary_cat":"cs.LG","authors_text":"Diogo de Andrade, Nuno Fachada","submitted_at":"2023-01-24T22:08:24Z","abstract_excerpt":"Synthetic data is essential for assessing clustering techniques, complementing and extending real data, and allowing for more complete coverage of a given problem's space. In turn, synthetic data generators have the potential of creating vast amounts of data -- a crucial activity when real-world data is at premium -- while providing a well-understood generation procedure and an interpretable instrument for methodically investigating cluster analysis algorithms. Here, we present Clugen, a modular procedure for synthetic data generation, capable of creating multidimensional clusters supported by"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.10327","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/2301.10327/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":"2301.10327","created_at":"2026-07-05T07:52:08.329790+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.10327v3","created_at":"2026-07-05T07:52:08.329790+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.10327","created_at":"2026-07-05T07:52:08.329790+00:00"},{"alias_kind":"pith_short_12","alias_value":"L5VBO4PQ2JDY","created_at":"2026-07-05T07:52:08.329790+00:00"},{"alias_kind":"pith_short_16","alias_value":"L5VBO4PQ2JDYG55G","created_at":"2026-07-05T07:52:08.329790+00:00"},{"alias_kind":"pith_short_8","alias_value":"L5VBO4PQ","created_at":"2026-07-05T07:52:08.329790+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.14163","citing_title":"DSMentor: Enhancing Data Science Agents with Curriculum Learning and Online Knowledge Accumulation","ref_index":2009,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L5VBO4PQ2JDYG55GD2F2YM6ZLO","json":"https://pith.science/pith/L5VBO4PQ2JDYG55GD2F2YM6ZLO.json","graph_json":"https://pith.science/api/pith-number/L5VBO4PQ2JDYG55GD2F2YM6ZLO/graph.json","events_json":"https://pith.science/api/pith-number/L5VBO4PQ2JDYG55GD2F2YM6ZLO/events.json","paper":"https://pith.science/paper/L5VBO4PQ"},"agent_actions":{"view_html":"https://pith.science/pith/L5VBO4PQ2JDYG55GD2F2YM6ZLO","download_json":"https://pith.science/pith/L5VBO4PQ2JDYG55GD2F2YM6ZLO.json","view_paper":"https://pith.science/paper/L5VBO4PQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.10327&json=true","fetch_graph":"https://pith.science/api/pith-number/L5VBO4PQ2JDYG55GD2F2YM6ZLO/graph.json","fetch_events":"https://pith.science/api/pith-number/L5VBO4PQ2JDYG55GD2F2YM6ZLO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L5VBO4PQ2JDYG55GD2F2YM6ZLO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L5VBO4PQ2JDYG55GD2F2YM6ZLO/action/storage_attestation","attest_author":"https://pith.science/pith/L5VBO4PQ2JDYG55GD2F2YM6ZLO/action/author_attestation","sign_citation":"https://pith.science/pith/L5VBO4PQ2JDYG55GD2F2YM6ZLO/action/citation_signature","submit_replication":"https://pith.science/pith/L5VBO4PQ2JDYG55GD2F2YM6ZLO/action/replication_record"}},"created_at":"2026-07-05T07:52:08.329790+00:00","updated_at":"2026-07-05T07:52:08.329790+00:00"}