{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:T26OZ7HADEZLYWDY2EHXMRXJZA","short_pith_number":"pith:T26OZ7HA","schema_version":"1.0","canonical_sha256":"9ebcecfce01932bc5878d10f7646e9c80b28dbb405a22d95354f396423712bef","source":{"kind":"arxiv","id":"1802.04023","version":1},"attestation_state":"computed","paper":{"title":"Fair and Diverse DPP-based Data Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY","cs.IR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Amit Deshpande, Damian Straszak, L. Elisa Celis, Nisheeth K. Vishnoi, Tarun Kathuria, Vijay Keswani","submitted_at":"2018-02-12T13:12:43Z","abstract_excerpt":"Sampling methods that choose a subset of the data proportional to its diversity in the feature space are popular for data summarization. However, recent studies have noted the occurrence of bias (under- or over-representation of a certain gender or race) in such data summarization methods. In this paper we initiate a study of the problem of outputting a diverse and fair summary of a given dataset. We work with a well-studied determinantal measure of diversity and corresponding distributions (DPPs) and present a framework that allows us to incorporate a general class of fairness constraints int"},"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":"1802.04023","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-12T13:12:43Z","cross_cats_sorted":["cs.CY","cs.IR","stat.ML"],"title_canon_sha256":"9e98d3eeea45cd44c3d2c0adca9cdabe2b25579b0988c8a1de810985591155f3","abstract_canon_sha256":"eb1c99987fb2c5d6c1e0a85ab63a5a26e34d19609de9011725a1471f088731de"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:23:49.713060Z","signature_b64":"/yhMLeNHFfuIlwWMF3+OuKI4Yg1YYt5O6awvxG6jYuNGsAZwHP6JiZJMJS4z8OH+2WUmL88hm8zU9pYj8S98CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ebcecfce01932bc5878d10f7646e9c80b28dbb405a22d95354f396423712bef","last_reissued_at":"2026-05-18T00:23:49.712356Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:23:49.712356Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fair and Diverse DPP-based Data Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CY","cs.IR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Amit Deshpande, Damian Straszak, L. Elisa Celis, Nisheeth K. Vishnoi, Tarun Kathuria, Vijay Keswani","submitted_at":"2018-02-12T13:12:43Z","abstract_excerpt":"Sampling methods that choose a subset of the data proportional to its diversity in the feature space are popular for data summarization. However, recent studies have noted the occurrence of bias (under- or over-representation of a certain gender or race) in such data summarization methods. In this paper we initiate a study of the problem of outputting a diverse and fair summary of a given dataset. We work with a well-studied determinantal measure of diversity and corresponding distributions (DPPs) and present a framework that allows us to incorporate a general class of fairness constraints int"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.04023","kind":"arxiv","version":1},"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":"1802.04023","created_at":"2026-05-18T00:23:49.712482+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.04023v1","created_at":"2026-05-18T00:23:49.712482+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.04023","created_at":"2026-05-18T00:23:49.712482+00:00"},{"alias_kind":"pith_short_12","alias_value":"T26OZ7HADEZL","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_16","alias_value":"T26OZ7HADEZLYWDY","created_at":"2026-05-18T12:32:53.628368+00:00"},{"alias_kind":"pith_short_8","alias_value":"T26OZ7HA","created_at":"2026-05-18T12:32:53.628368+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/T26OZ7HADEZLYWDY2EHXMRXJZA","json":"https://pith.science/pith/T26OZ7HADEZLYWDY2EHXMRXJZA.json","graph_json":"https://pith.science/api/pith-number/T26OZ7HADEZLYWDY2EHXMRXJZA/graph.json","events_json":"https://pith.science/api/pith-number/T26OZ7HADEZLYWDY2EHXMRXJZA/events.json","paper":"https://pith.science/paper/T26OZ7HA"},"agent_actions":{"view_html":"https://pith.science/pith/T26OZ7HADEZLYWDY2EHXMRXJZA","download_json":"https://pith.science/pith/T26OZ7HADEZLYWDY2EHXMRXJZA.json","view_paper":"https://pith.science/paper/T26OZ7HA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.04023&json=true","fetch_graph":"https://pith.science/api/pith-number/T26OZ7HADEZLYWDY2EHXMRXJZA/graph.json","fetch_events":"https://pith.science/api/pith-number/T26OZ7HADEZLYWDY2EHXMRXJZA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T26OZ7HADEZLYWDY2EHXMRXJZA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T26OZ7HADEZLYWDY2EHXMRXJZA/action/storage_attestation","attest_author":"https://pith.science/pith/T26OZ7HADEZLYWDY2EHXMRXJZA/action/author_attestation","sign_citation":"https://pith.science/pith/T26OZ7HADEZLYWDY2EHXMRXJZA/action/citation_signature","submit_replication":"https://pith.science/pith/T26OZ7HADEZLYWDY2EHXMRXJZA/action/replication_record"}},"created_at":"2026-05-18T00:23:49.712482+00:00","updated_at":"2026-05-18T00:23:49.712482+00:00"}