{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:CZFYRN67O5ZDYONWXCRUFRNTMP","short_pith_number":"pith:CZFYRN67","schema_version":"1.0","canonical_sha256":"164b88b7df77723c39b6b8a342c5b363ccb89413c5583bd024dfa46872f04835","source":{"kind":"arxiv","id":"1603.00560","version":2},"attestation_state":"computed","paper":{"title":"Learnt quasi-transitive similarity for retrieval from large collections of faces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ognjen Arandjelovic","submitted_at":"2016-03-02T03:04:37Z","abstract_excerpt":"We are interested in identity-based retrieval of face sets from large unlabelled collections acquired in uncontrolled environments. Given a baseline algorithm for measuring the similarity of two face sets, the meta-algorithm introduced in this paper seeks to leverage the structure of the data corpus to make the best use of the available baseline. In particular, we show how partial transitivity of inter-personal similarity can be exploited to improve the retrieval of particularly challenging sets which poorly match the query under the baseline measure. We: (i) describe the use of proxy sets as "},"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":"1603.00560","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-03-02T03:04:37Z","cross_cats_sorted":[],"title_canon_sha256":"e2cabd0d760e89718322d2448f8a21179e7810ba34e9c869be8b2540970e04fe","abstract_canon_sha256":"84439768ff05311b676527660530181802a4d5d37b0d2e6ffbf206c0d8bc859e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:17:07.388261Z","signature_b64":"9L6tgpCA9Un1WtGI4ZopPOv6DIG1faEqWyua0ki43w1dp4VXMxvZb9OTGuiTjvUhsHDnKiGetufPx4KKzXyTDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"164b88b7df77723c39b6b8a342c5b363ccb89413c5583bd024dfa46872f04835","last_reissued_at":"2026-05-18T01:17:07.387445Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:17:07.387445Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learnt quasi-transitive similarity for retrieval from large collections of faces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ognjen Arandjelovic","submitted_at":"2016-03-02T03:04:37Z","abstract_excerpt":"We are interested in identity-based retrieval of face sets from large unlabelled collections acquired in uncontrolled environments. Given a baseline algorithm for measuring the similarity of two face sets, the meta-algorithm introduced in this paper seeks to leverage the structure of the data corpus to make the best use of the available baseline. In particular, we show how partial transitivity of inter-personal similarity can be exploited to improve the retrieval of particularly challenging sets which poorly match the query under the baseline measure. We: (i) describe the use of proxy sets as "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1603.00560","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":"1603.00560","created_at":"2026-05-18T01:17:07.387585+00:00"},{"alias_kind":"arxiv_version","alias_value":"1603.00560v2","created_at":"2026-05-18T01:17:07.387585+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1603.00560","created_at":"2026-05-18T01:17:07.387585+00:00"},{"alias_kind":"pith_short_12","alias_value":"CZFYRN67O5ZD","created_at":"2026-05-18T12:30:09.641336+00:00"},{"alias_kind":"pith_short_16","alias_value":"CZFYRN67O5ZDYONW","created_at":"2026-05-18T12:30:09.641336+00:00"},{"alias_kind":"pith_short_8","alias_value":"CZFYRN67","created_at":"2026-05-18T12:30:09.641336+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/CZFYRN67O5ZDYONWXCRUFRNTMP","json":"https://pith.science/pith/CZFYRN67O5ZDYONWXCRUFRNTMP.json","graph_json":"https://pith.science/api/pith-number/CZFYRN67O5ZDYONWXCRUFRNTMP/graph.json","events_json":"https://pith.science/api/pith-number/CZFYRN67O5ZDYONWXCRUFRNTMP/events.json","paper":"https://pith.science/paper/CZFYRN67"},"agent_actions":{"view_html":"https://pith.science/pith/CZFYRN67O5ZDYONWXCRUFRNTMP","download_json":"https://pith.science/pith/CZFYRN67O5ZDYONWXCRUFRNTMP.json","view_paper":"https://pith.science/paper/CZFYRN67","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1603.00560&json=true","fetch_graph":"https://pith.science/api/pith-number/CZFYRN67O5ZDYONWXCRUFRNTMP/graph.json","fetch_events":"https://pith.science/api/pith-number/CZFYRN67O5ZDYONWXCRUFRNTMP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CZFYRN67O5ZDYONWXCRUFRNTMP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CZFYRN67O5ZDYONWXCRUFRNTMP/action/storage_attestation","attest_author":"https://pith.science/pith/CZFYRN67O5ZDYONWXCRUFRNTMP/action/author_attestation","sign_citation":"https://pith.science/pith/CZFYRN67O5ZDYONWXCRUFRNTMP/action/citation_signature","submit_replication":"https://pith.science/pith/CZFYRN67O5ZDYONWXCRUFRNTMP/action/replication_record"}},"created_at":"2026-05-18T01:17:07.387585+00:00","updated_at":"2026-05-18T01:17:07.387585+00:00"}