{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:7H4RYNA37ZZ6RV4ISLQL2IIXTC","short_pith_number":"pith:7H4RYNA3","schema_version":"1.0","canonical_sha256":"f9f91c341bfe73e8d78892e0bd211798949bcb57d248d92ca5480c4eaa21c998","source":{"kind":"arxiv","id":"1411.7923","version":1},"attestation_state":"computed","paper":{"title":"Learning Face Representation from Scratch","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dong Yi, Shengcai Liao, Stan Z. Li, Zhen Lei","submitted_at":"2014-11-28T16:05:18Z","abstract_excerpt":"Pushing by big data and deep convolutional neural network (CNN), the performance of face recognition is becoming comparable to human. Using private large scale training datasets, several groups achieve very high performance on LFW, i.e., 97% to 99%. While there are many open source implementations of CNN, none of large scale face dataset is publicly available. The current situation in the field of face recognition is that data is more important than algorithm. To solve this problem, this paper proposes a semi-automatical way to collect face images from Internet and builds a large scale dataset"},"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":"1411.7923","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-11-28T16:05:18Z","cross_cats_sorted":[],"title_canon_sha256":"8b5d05183cfea4393541f4276e720fec7225f71478f346e64fb474eb066f8904","abstract_canon_sha256":"c35f88959ddc6c2d92ca9046e2b261f15c6b721a0c87f163c14d00478d193ae3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:32:36.994350Z","signature_b64":"SeLwzfe/8bKBioy+uysF8X5DdKbr2ImyFx6L5Tdfm7IhbcFrVRjclZgiOdTizX+qqzcBEEA+QttwzrnncFeUCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9f91c341bfe73e8d78892e0bd211798949bcb57d248d92ca5480c4eaa21c998","last_reissued_at":"2026-05-18T02:32:36.993994Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:32:36.993994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Face Representation from Scratch","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dong Yi, Shengcai Liao, Stan Z. Li, Zhen Lei","submitted_at":"2014-11-28T16:05:18Z","abstract_excerpt":"Pushing by big data and deep convolutional neural network (CNN), the performance of face recognition is becoming comparable to human. Using private large scale training datasets, several groups achieve very high performance on LFW, i.e., 97% to 99%. While there are many open source implementations of CNN, none of large scale face dataset is publicly available. The current situation in the field of face recognition is that data is more important than algorithm. To solve this problem, this paper proposes a semi-automatical way to collect face images from Internet and builds a large scale dataset"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1411.7923","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":"1411.7923","created_at":"2026-05-18T02:32:36.994046+00:00"},{"alias_kind":"arxiv_version","alias_value":"1411.7923v1","created_at":"2026-05-18T02:32:36.994046+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1411.7923","created_at":"2026-05-18T02:32:36.994046+00:00"},{"alias_kind":"pith_short_12","alias_value":"7H4RYNA37ZZ6","created_at":"2026-05-18T12:28:16.859392+00:00"},{"alias_kind":"pith_short_16","alias_value":"7H4RYNA37ZZ6RV4I","created_at":"2026-05-18T12:28:16.859392+00:00"},{"alias_kind":"pith_short_8","alias_value":"7H4RYNA3","created_at":"2026-05-18T12:28:16.859392+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":15,"internal_anchor_count":9,"sample":[{"citing_arxiv_id":"1906.08507","citing_title":"Multiple-Identity Image Attacks Against Face-based Identity Verification","ref_index":47,"is_internal_anchor":true},{"citing_arxiv_id":"1906.10546","citing_title":"Knowledge Amalgamation from Heterogeneous Networks by Common Feature Learning","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"1907.02642","citing_title":"Primate Face Identification in the Wild","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"1907.02157","citing_title":"Slim-CNN: A Light-Weight CNN for Face Attribute Prediction","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"1907.10104","citing_title":"Exploring Factors for Improving Low Resolution Face Recognition","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18238","citing_title":"Non-Colliding Biometric Identities for Digital Entities: Geometry, Capacity, and Million-Scale Virtual Identity Provisioning","ref_index":40,"is_internal_anchor":true},{"citing_arxiv_id":"2512.03199","citing_title":"Does Head Pose Correction Improve Biometric Facial Recognition?","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13396","citing_title":"PreFIQs: Face Image Quality Is What Survives Pruning","ref_index":52,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12792","citing_title":"SoK: A Comprehensive Analysis of the Current Status of Neural Tangent Generalization Attacks with Research Directions","ref_index":103,"is_internal_anchor":true},{"citing_arxiv_id":"2604.21689","citing_title":"StyleID: A Perception-Aware Dataset and Metric for Stylization-Agnostic Facial Identity Recognition","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04769","citing_title":"Lightweight Cross-Spectral Face Recognition via Contrastive Alignment and Distillation","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20585","citing_title":"On the Impact of Face Segmentation-Based Background Removal on Recognition and Morphing Attack Detection","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12686","citing_title":"BID-LoRA: A Parameter-Efficient Framework for Continual Learning and Unlearning","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07884","citing_title":"Reinforcement-Guided Synthetic Data Generation for Privacy-Sensitive Identity Recognition","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07282","citing_title":"Are Face Embeddings Compatible Across Deep Neural Network Models?","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7H4RYNA37ZZ6RV4ISLQL2IIXTC","json":"https://pith.science/pith/7H4RYNA37ZZ6RV4ISLQL2IIXTC.json","graph_json":"https://pith.science/api/pith-number/7H4RYNA37ZZ6RV4ISLQL2IIXTC/graph.json","events_json":"https://pith.science/api/pith-number/7H4RYNA37ZZ6RV4ISLQL2IIXTC/events.json","paper":"https://pith.science/paper/7H4RYNA3"},"agent_actions":{"view_html":"https://pith.science/pith/7H4RYNA37ZZ6RV4ISLQL2IIXTC","download_json":"https://pith.science/pith/7H4RYNA37ZZ6RV4ISLQL2IIXTC.json","view_paper":"https://pith.science/paper/7H4RYNA3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1411.7923&json=true","fetch_graph":"https://pith.science/api/pith-number/7H4RYNA37ZZ6RV4ISLQL2IIXTC/graph.json","fetch_events":"https://pith.science/api/pith-number/7H4RYNA37ZZ6RV4ISLQL2IIXTC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7H4RYNA37ZZ6RV4ISLQL2IIXTC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7H4RYNA37ZZ6RV4ISLQL2IIXTC/action/storage_attestation","attest_author":"https://pith.science/pith/7H4RYNA37ZZ6RV4ISLQL2IIXTC/action/author_attestation","sign_citation":"https://pith.science/pith/7H4RYNA37ZZ6RV4ISLQL2IIXTC/action/citation_signature","submit_replication":"https://pith.science/pith/7H4RYNA37ZZ6RV4ISLQL2IIXTC/action/replication_record"}},"created_at":"2026-05-18T02:32:36.994046+00:00","updated_at":"2026-05-18T02:32:36.994046+00:00"}