{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:I7YSQZO25RWNN5BVQCIBGBALBS","short_pith_number":"pith:I7YSQZO2","schema_version":"1.0","canonical_sha256":"47f12865daec6cd6f435809013040b0c853a5e06ca2397165baa1cad3a594a83","source":{"kind":"arxiv","id":"1709.10330","version":2},"attestation_state":"computed","paper":{"title":"Clustering of imbalanced high-dimensional media data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ME","authors_text":"Christian Breiteneder, Maia Zaharieva, Peter Filzmoser, Sarka Brodinova, Thomas Ortner","submitted_at":"2017-09-29T11:15:38Z","abstract_excerpt":"Media content in large repositories usually exhibits multiple groups of strongly varying sizes. Media of potential interest often form notably smaller groups. Such media groups differ so much from the remaining data that it may be worthy to look at them in more detail. In contrast, media with popular content appear in larger groups. Identifying groups of varying sizes is addressed by clustering of imbalanced data. Clustering highly imbalanced media groups is additionally challenged by the high dimensionality of the underlying features. In this paper, we present the Imbalanced Clustering (IClus"},"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":"1709.10330","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2017-09-29T11:15:38Z","cross_cats_sorted":[],"title_canon_sha256":"877374c3e4634ff5768085518603e095df4450bc7f14bdb0d15b30399353bc00","abstract_canon_sha256":"d02eebb948d9a87a360e30adcd6684c53b0951d62751fdb05e023df914d52d14"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:33:38.732630Z","signature_b64":"JtmtFR1i5X2o7Sx0s3q2zEiNo0xZ/YroWG4XKgUv9JkKbpJBSJ0aV8R3UPei7h5ycnxhY/KWmZYh37vLrSCABQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47f12865daec6cd6f435809013040b0c853a5e06ca2397165baa1cad3a594a83","last_reissued_at":"2026-05-18T00:33:38.732179Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:33:38.732179Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Clustering of imbalanced high-dimensional media data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ME","authors_text":"Christian Breiteneder, Maia Zaharieva, Peter Filzmoser, Sarka Brodinova, Thomas Ortner","submitted_at":"2017-09-29T11:15:38Z","abstract_excerpt":"Media content in large repositories usually exhibits multiple groups of strongly varying sizes. Media of potential interest often form notably smaller groups. Such media groups differ so much from the remaining data that it may be worthy to look at them in more detail. In contrast, media with popular content appear in larger groups. Identifying groups of varying sizes is addressed by clustering of imbalanced data. Clustering highly imbalanced media groups is additionally challenged by the high dimensionality of the underlying features. In this paper, we present the Imbalanced Clustering (IClus"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.10330","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":"1709.10330","created_at":"2026-05-18T00:33:38.732257+00:00"},{"alias_kind":"arxiv_version","alias_value":"1709.10330v2","created_at":"2026-05-18T00:33:38.732257+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.10330","created_at":"2026-05-18T00:33:38.732257+00:00"},{"alias_kind":"pith_short_12","alias_value":"I7YSQZO25RWN","created_at":"2026-05-18T12:31:21.493067+00:00"},{"alias_kind":"pith_short_16","alias_value":"I7YSQZO25RWNN5BV","created_at":"2026-05-18T12:31:21.493067+00:00"},{"alias_kind":"pith_short_8","alias_value":"I7YSQZO2","created_at":"2026-05-18T12:31:21.493067+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/I7YSQZO25RWNN5BVQCIBGBALBS","json":"https://pith.science/pith/I7YSQZO25RWNN5BVQCIBGBALBS.json","graph_json":"https://pith.science/api/pith-number/I7YSQZO25RWNN5BVQCIBGBALBS/graph.json","events_json":"https://pith.science/api/pith-number/I7YSQZO25RWNN5BVQCIBGBALBS/events.json","paper":"https://pith.science/paper/I7YSQZO2"},"agent_actions":{"view_html":"https://pith.science/pith/I7YSQZO25RWNN5BVQCIBGBALBS","download_json":"https://pith.science/pith/I7YSQZO25RWNN5BVQCIBGBALBS.json","view_paper":"https://pith.science/paper/I7YSQZO2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1709.10330&json=true","fetch_graph":"https://pith.science/api/pith-number/I7YSQZO25RWNN5BVQCIBGBALBS/graph.json","fetch_events":"https://pith.science/api/pith-number/I7YSQZO25RWNN5BVQCIBGBALBS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I7YSQZO25RWNN5BVQCIBGBALBS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I7YSQZO25RWNN5BVQCIBGBALBS/action/storage_attestation","attest_author":"https://pith.science/pith/I7YSQZO25RWNN5BVQCIBGBALBS/action/author_attestation","sign_citation":"https://pith.science/pith/I7YSQZO25RWNN5BVQCIBGBALBS/action/citation_signature","submit_replication":"https://pith.science/pith/I7YSQZO25RWNN5BVQCIBGBALBS/action/replication_record"}},"created_at":"2026-05-18T00:33:38.732257+00:00","updated_at":"2026-05-18T00:33:38.732257+00:00"}