{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:V6EGGOAH6YXH4Z7S5WFR6BQAT4","short_pith_number":"pith:V6EGGOAH","schema_version":"1.0","canonical_sha256":"af88633807f62e7e67f2ed8b1f06009f09257396da44002bb9bdae7c4b6fdf5e","source":{"kind":"arxiv","id":"1905.04457","version":2},"attestation_state":"computed","paper":{"title":"Triplet Distillation for Deep Face Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Daniel T. Yi, Huan Wang, Roland Hu, Yushu Feng","submitted_at":"2019-05-11T06:23:51Z","abstract_excerpt":"Convolutional neural networks (CNNs) have achieved a great success in face recognition, which unfortunately comes at the cost of massive computation and storage consumption. Many compact face recognition networks are thus proposed to resolve this problem. Triplet loss is effective to further improve the performance of those compact models. However, it normally employs a fixed margin to all the samples, which neglects the informative similarity structures between different identities. In this paper, we propose an enhanced version of triplet loss, named triplet distillation, which exploits the c"},"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":"1905.04457","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-11T06:23:51Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1ac9bac199890c4a60cd7d01e7e16778a0b3b2321e1e513e3131aabe01819e8e","abstract_canon_sha256":"53861221d54a283c9be6995795fa8d483b414d26e6ed721f7d029d2eef4a7ee6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:51.537510Z","signature_b64":"eJ5eTy4KwJjJll1CBWHusoeztnyYqvbBoD3jNHoKKgpOqDEJ1OnwhcPcvDtlD5IofsA5UNBdWyuZi463n/I5Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af88633807f62e7e67f2ed8b1f06009f09257396da44002bb9bdae7c4b6fdf5e","last_reissued_at":"2026-05-17T23:45:51.537028Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:51.537028Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Triplet Distillation for Deep Face Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Daniel T. Yi, Huan Wang, Roland Hu, Yushu Feng","submitted_at":"2019-05-11T06:23:51Z","abstract_excerpt":"Convolutional neural networks (CNNs) have achieved a great success in face recognition, which unfortunately comes at the cost of massive computation and storage consumption. Many compact face recognition networks are thus proposed to resolve this problem. Triplet loss is effective to further improve the performance of those compact models. However, it normally employs a fixed margin to all the samples, which neglects the informative similarity structures between different identities. In this paper, we propose an enhanced version of triplet loss, named triplet distillation, which exploits the c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.04457","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":"1905.04457","created_at":"2026-05-17T23:45:51.537109+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.04457v2","created_at":"2026-05-17T23:45:51.537109+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.04457","created_at":"2026-05-17T23:45:51.537109+00:00"},{"alias_kind":"pith_short_12","alias_value":"V6EGGOAH6YXH","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"V6EGGOAH6YXH4Z7S","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"V6EGGOAH","created_at":"2026-05-18T12:33:30.264802+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/V6EGGOAH6YXH4Z7S5WFR6BQAT4","json":"https://pith.science/pith/V6EGGOAH6YXH4Z7S5WFR6BQAT4.json","graph_json":"https://pith.science/api/pith-number/V6EGGOAH6YXH4Z7S5WFR6BQAT4/graph.json","events_json":"https://pith.science/api/pith-number/V6EGGOAH6YXH4Z7S5WFR6BQAT4/events.json","paper":"https://pith.science/paper/V6EGGOAH"},"agent_actions":{"view_html":"https://pith.science/pith/V6EGGOAH6YXH4Z7S5WFR6BQAT4","download_json":"https://pith.science/pith/V6EGGOAH6YXH4Z7S5WFR6BQAT4.json","view_paper":"https://pith.science/paper/V6EGGOAH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.04457&json=true","fetch_graph":"https://pith.science/api/pith-number/V6EGGOAH6YXH4Z7S5WFR6BQAT4/graph.json","fetch_events":"https://pith.science/api/pith-number/V6EGGOAH6YXH4Z7S5WFR6BQAT4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V6EGGOAH6YXH4Z7S5WFR6BQAT4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V6EGGOAH6YXH4Z7S5WFR6BQAT4/action/storage_attestation","attest_author":"https://pith.science/pith/V6EGGOAH6YXH4Z7S5WFR6BQAT4/action/author_attestation","sign_citation":"https://pith.science/pith/V6EGGOAH6YXH4Z7S5WFR6BQAT4/action/citation_signature","submit_replication":"https://pith.science/pith/V6EGGOAH6YXH4Z7S5WFR6BQAT4/action/replication_record"}},"created_at":"2026-05-17T23:45:51.537109+00:00","updated_at":"2026-05-17T23:45:51.537109+00:00"}