{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:BEVG6XXAVEY3J2KCLGWFEIFTCO","short_pith_number":"pith:BEVG6XXA","schema_version":"1.0","canonical_sha256":"092a6f5ee0a931b4e94259ac5220b31394e7aef2fc342c051e9e344d7089c688","source":{"kind":"arxiv","id":"2008.06021","version":1},"attestation_state":"computed","paper":{"title":"BioMetricNet: deep unconstrained face verification through learning of metrics regularized onto Gaussian distributions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Arslan Ali, Enrico Magli, Matteo Testa, Tiziano Bianchi","submitted_at":"2020-08-13T17:22:46Z","abstract_excerpt":"We present BioMetricNet: a novel framework for deep unconstrained face verification which learns a regularized metric to compare facial features. Differently from popular methods such as FaceNet, the proposed approach does not impose any specific metric on facial features; instead, it shapes the decision space by learning a latent representation in which matching and non-matching pairs are mapped onto clearly separated and well-behaved target distributions. In particular, the network jointly learns the best feature representation, and the best metric that follows the target distributions, to b"},"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":"2008.06021","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-08-13T17:22:46Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"352aa54017f8a167e96276e5c32bdc5aa90b5bc3fb09f9c43dd1a34b9f8c4064","abstract_canon_sha256":"722ab2a1c0efbf679451d099353f8a4e78697c45d7bc651bb8250190ea2d7b20"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:26:59.470153Z","signature_b64":"6y6xU7yDaWAtZRlGEIUsc6RMrAai6m+HqMl/nzuUU+pz7AiguYl7kgtiF74aWGQKEjbvfbZt1g/Oh2avuW7nBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"092a6f5ee0a931b4e94259ac5220b31394e7aef2fc342c051e9e344d7089c688","last_reissued_at":"2026-07-05T01:26:59.469704Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:26:59.469704Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BioMetricNet: deep unconstrained face verification through learning of metrics regularized onto Gaussian distributions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Arslan Ali, Enrico Magli, Matteo Testa, Tiziano Bianchi","submitted_at":"2020-08-13T17:22:46Z","abstract_excerpt":"We present BioMetricNet: a novel framework for deep unconstrained face verification which learns a regularized metric to compare facial features. Differently from popular methods such as FaceNet, the proposed approach does not impose any specific metric on facial features; instead, it shapes the decision space by learning a latent representation in which matching and non-matching pairs are mapped onto clearly separated and well-behaved target distributions. In particular, the network jointly learns the best feature representation, and the best metric that follows the target distributions, to b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.06021","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2008.06021/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":"2008.06021","created_at":"2026-07-05T01:26:59.469767+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.06021v1","created_at":"2026-07-05T01:26:59.469767+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.06021","created_at":"2026-07-05T01:26:59.469767+00:00"},{"alias_kind":"pith_short_12","alias_value":"BEVG6XXAVEY3","created_at":"2026-07-05T01:26:59.469767+00:00"},{"alias_kind":"pith_short_16","alias_value":"BEVG6XXAVEY3J2KC","created_at":"2026-07-05T01:26:59.469767+00:00"},{"alias_kind":"pith_short_8","alias_value":"BEVG6XXA","created_at":"2026-07-05T01:26:59.469767+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/BEVG6XXAVEY3J2KCLGWFEIFTCO","json":"https://pith.science/pith/BEVG6XXAVEY3J2KCLGWFEIFTCO.json","graph_json":"https://pith.science/api/pith-number/BEVG6XXAVEY3J2KCLGWFEIFTCO/graph.json","events_json":"https://pith.science/api/pith-number/BEVG6XXAVEY3J2KCLGWFEIFTCO/events.json","paper":"https://pith.science/paper/BEVG6XXA"},"agent_actions":{"view_html":"https://pith.science/pith/BEVG6XXAVEY3J2KCLGWFEIFTCO","download_json":"https://pith.science/pith/BEVG6XXAVEY3J2KCLGWFEIFTCO.json","view_paper":"https://pith.science/paper/BEVG6XXA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.06021&json=true","fetch_graph":"https://pith.science/api/pith-number/BEVG6XXAVEY3J2KCLGWFEIFTCO/graph.json","fetch_events":"https://pith.science/api/pith-number/BEVG6XXAVEY3J2KCLGWFEIFTCO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BEVG6XXAVEY3J2KCLGWFEIFTCO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BEVG6XXAVEY3J2KCLGWFEIFTCO/action/storage_attestation","attest_author":"https://pith.science/pith/BEVG6XXAVEY3J2KCLGWFEIFTCO/action/author_attestation","sign_citation":"https://pith.science/pith/BEVG6XXAVEY3J2KCLGWFEIFTCO/action/citation_signature","submit_replication":"https://pith.science/pith/BEVG6XXAVEY3J2KCLGWFEIFTCO/action/replication_record"}},"created_at":"2026-07-05T01:26:59.469767+00:00","updated_at":"2026-07-05T01:26:59.469767+00:00"}