{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:SIDCZNHDNJ6HXC4E4K2N7LX3BA","short_pith_number":"pith:SIDCZNHD","schema_version":"1.0","canonical_sha256":"92062cb4e36a7c7b8b84e2b4dfaefb081925dc262bfeca117e19b808b0c630fc","source":{"kind":"arxiv","id":"2002.11841","version":1},"attestation_state":"computed","paper":{"title":"Towards Universal Representation Learning for Deep Face Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anil K. Jain, Kihyuk Sohn, Manmohan Chandraker, Xiang Yu, Yichun Shi","submitted_at":"2020-02-26T23:29:57Z","abstract_excerpt":"Recognizing wild faces is extremely hard as they appear with all kinds of variations. Traditional methods either train with specifically annotated variation data from target domains, or by introducing unlabeled target variation data to adapt from the training data. Instead, we propose a universal representation learning framework that can deal with larger variation unseen in the given training data without leveraging target domain knowledge. We firstly synthesize training data alongside some semantically meaningful variations, such as low resolution, occlusion and head pose. However, directly "},"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":"2002.11841","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-02-26T23:29:57Z","cross_cats_sorted":[],"title_canon_sha256":"7078949132bc944907e81334515aaf624716c82e521532772217d5a0d70e19c9","abstract_canon_sha256":"76385a3d99fd8bb0beca784b84dfbf62dd34a3b471e1a1c76b09c2d4cec78a64"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:44:09.590303Z","signature_b64":"4a7DwV8aoFDp6ZtwYZYifQmTGJHphXJdRnzvO6M20+wJoRk+SHLCLu5F14Zt1FlEFy/Jf0JcCDDrvR6j2l4EBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"92062cb4e36a7c7b8b84e2b4dfaefb081925dc262bfeca117e19b808b0c630fc","last_reissued_at":"2026-07-05T00:44:09.589858Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:44:09.589858Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Universal Representation Learning for Deep Face Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anil K. Jain, Kihyuk Sohn, Manmohan Chandraker, Xiang Yu, Yichun Shi","submitted_at":"2020-02-26T23:29:57Z","abstract_excerpt":"Recognizing wild faces is extremely hard as they appear with all kinds of variations. Traditional methods either train with specifically annotated variation data from target domains, or by introducing unlabeled target variation data to adapt from the training data. Instead, we propose a universal representation learning framework that can deal with larger variation unseen in the given training data without leveraging target domain knowledge. We firstly synthesize training data alongside some semantically meaningful variations, such as low resolution, occlusion and head pose. However, directly "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.11841","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/2002.11841/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":"2002.11841","created_at":"2026-07-05T00:44:09.589916+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.11841v1","created_at":"2026-07-05T00:44:09.589916+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.11841","created_at":"2026-07-05T00:44:09.589916+00:00"},{"alias_kind":"pith_short_12","alias_value":"SIDCZNHDNJ6H","created_at":"2026-07-05T00:44:09.589916+00:00"},{"alias_kind":"pith_short_16","alias_value":"SIDCZNHDNJ6HXC4E","created_at":"2026-07-05T00:44:09.589916+00:00"},{"alias_kind":"pith_short_8","alias_value":"SIDCZNHD","created_at":"2026-07-05T00:44:09.589916+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/SIDCZNHDNJ6HXC4E4K2N7LX3BA","json":"https://pith.science/pith/SIDCZNHDNJ6HXC4E4K2N7LX3BA.json","graph_json":"https://pith.science/api/pith-number/SIDCZNHDNJ6HXC4E4K2N7LX3BA/graph.json","events_json":"https://pith.science/api/pith-number/SIDCZNHDNJ6HXC4E4K2N7LX3BA/events.json","paper":"https://pith.science/paper/SIDCZNHD"},"agent_actions":{"view_html":"https://pith.science/pith/SIDCZNHDNJ6HXC4E4K2N7LX3BA","download_json":"https://pith.science/pith/SIDCZNHDNJ6HXC4E4K2N7LX3BA.json","view_paper":"https://pith.science/paper/SIDCZNHD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.11841&json=true","fetch_graph":"https://pith.science/api/pith-number/SIDCZNHDNJ6HXC4E4K2N7LX3BA/graph.json","fetch_events":"https://pith.science/api/pith-number/SIDCZNHDNJ6HXC4E4K2N7LX3BA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SIDCZNHDNJ6HXC4E4K2N7LX3BA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SIDCZNHDNJ6HXC4E4K2N7LX3BA/action/storage_attestation","attest_author":"https://pith.science/pith/SIDCZNHDNJ6HXC4E4K2N7LX3BA/action/author_attestation","sign_citation":"https://pith.science/pith/SIDCZNHDNJ6HXC4E4K2N7LX3BA/action/citation_signature","submit_replication":"https://pith.science/pith/SIDCZNHDNJ6HXC4E4K2N7LX3BA/action/replication_record"}},"created_at":"2026-07-05T00:44:09.589916+00:00","updated_at":"2026-07-05T00:44:09.589916+00:00"}