{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:LIU4LKNVYFU4ZZV6PAC2XKAHRM","short_pith_number":"pith:LIU4LKNV","canonical_record":{"source":{"id":"2101.09899","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-01-25T05:18:51Z","cross_cats_sorted":[],"title_canon_sha256":"cf7863b1b407611197420635fe98ff9752b5f95b467fa04ae5d77c8f35fc5bea","abstract_canon_sha256":"cd4164590b8cc9f0635cc16f66bc5904bcae25efc23a99c7abf96ec28e900d98"},"schema_version":"1.0"},"canonical_sha256":"5a29c5a9b5c169cce6be7805aba8078b2bc983b180cc26480552456a19dd3b41","source":{"kind":"arxiv","id":"2101.09899","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.09899","created_at":"2026-07-05T02:52:14Z"},{"alias_kind":"arxiv_version","alias_value":"2101.09899v3","created_at":"2026-07-05T02:52:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.09899","created_at":"2026-07-05T02:52:14Z"},{"alias_kind":"pith_short_12","alias_value":"LIU4LKNVYFU4","created_at":"2026-07-05T02:52:14Z"},{"alias_kind":"pith_short_16","alias_value":"LIU4LKNVYFU4ZZV6","created_at":"2026-07-05T02:52:14Z"},{"alias_kind":"pith_short_8","alias_value":"LIU4LKNV","created_at":"2026-07-05T02:52:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:LIU4LKNVYFU4ZZV6PAC2XKAHRM","target":"record","payload":{"canonical_record":{"source":{"id":"2101.09899","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-01-25T05:18:51Z","cross_cats_sorted":[],"title_canon_sha256":"cf7863b1b407611197420635fe98ff9752b5f95b467fa04ae5d77c8f35fc5bea","abstract_canon_sha256":"cd4164590b8cc9f0635cc16f66bc5904bcae25efc23a99c7abf96ec28e900d98"},"schema_version":"1.0"},"canonical_sha256":"5a29c5a9b5c169cce6be7805aba8078b2bc983b180cc26480552456a19dd3b41","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:52:14.794508Z","signature_b64":"XfHfhiPJ3dqWoGgJRljdxX6vMLiRKSX1l5vQwF4Gm03uuAqh7+t+Dt3fHbVGCDOePehMxOWm/A4Bhu22EsBeBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a29c5a9b5c169cce6be7805aba8078b2bc983b180cc26480552456a19dd3b41","last_reissued_at":"2026-07-05T02:52:14.794113Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:52:14.794113Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2101.09899","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:52:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Vup2joS3a/pxRXQU81b3ZdCDbRJcOjLV8H3JKEXBqF16ZSBRcx9xlQEXnjiNCppJtFpkN5EYlVe/IBCR6s7oDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T04:07:41.309689Z"},"content_sha256":"c69494393e4908d29ca518040fa11731fdb328876dd847eb0bd9043385f1b0c1","schema_version":"1.0","event_id":"sha256:c69494393e4908d29ca518040fa11731fdb328876dd847eb0bd9043385f1b0c1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:LIU4LKNVYFU4ZZV6PAC2XKAHRM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MultiFace: A Generic Training Mechanism for Boosting Face Recognition Performance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jing Xu, Kun Bai, Tszhang Guo, Yong Xu, Zenglin Xu","submitted_at":"2021-01-25T05:18:51Z","abstract_excerpt":"Deep Convolutional Neural Networks (DCNNs) and their variants have been widely used in large scale face recognition(FR) recently. Existing methods have achieved good performance on many FR benchmarks. However, most of them suffer from two major problems. First, these methods converge quite slowly since they optimize the loss functions in a high-dimensional and sparse Gaussian Sphere. Second, the high dimensionality of features, despite the powerful descriptive ability, brings difficulty to the optimization, which may lead to a sub-optimal local optimum. To address these problems, we propose a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.09899","kind":"arxiv","version":3},"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/2101.09899/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:52:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lnXWGjysuysGAwFOxEYQoSkhqyuEcML0ZkkVLS4ew6amQiKiTzlpnnE1IkJABkykjbyF6KUmtehfF2xKaZRQBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T04:07:41.310180Z"},"content_sha256":"fd531d1c3e5859b52ead23efddfeb56d9d6edf4e53eac3ba8f54cdb40349b1da","schema_version":"1.0","event_id":"sha256:fd531d1c3e5859b52ead23efddfeb56d9d6edf4e53eac3ba8f54cdb40349b1da"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LIU4LKNVYFU4ZZV6PAC2XKAHRM/bundle.json","state_url":"https://pith.science/pith/LIU4LKNVYFU4ZZV6PAC2XKAHRM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LIU4LKNVYFU4ZZV6PAC2XKAHRM/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T04:07:41Z","links":{"resolver":"https://pith.science/pith/LIU4LKNVYFU4ZZV6PAC2XKAHRM","bundle":"https://pith.science/pith/LIU4LKNVYFU4ZZV6PAC2XKAHRM/bundle.json","state":"https://pith.science/pith/LIU4LKNVYFU4ZZV6PAC2XKAHRM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LIU4LKNVYFU4ZZV6PAC2XKAHRM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:LIU4LKNVYFU4ZZV6PAC2XKAHRM","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"cd4164590b8cc9f0635cc16f66bc5904bcae25efc23a99c7abf96ec28e900d98","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-01-25T05:18:51Z","title_canon_sha256":"cf7863b1b407611197420635fe98ff9752b5f95b467fa04ae5d77c8f35fc5bea"},"schema_version":"1.0","source":{"id":"2101.09899","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.09899","created_at":"2026-07-05T02:52:14Z"},{"alias_kind":"arxiv_version","alias_value":"2101.09899v3","created_at":"2026-07-05T02:52:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.09899","created_at":"2026-07-05T02:52:14Z"},{"alias_kind":"pith_short_12","alias_value":"LIU4LKNVYFU4","created_at":"2026-07-05T02:52:14Z"},{"alias_kind":"pith_short_16","alias_value":"LIU4LKNVYFU4ZZV6","created_at":"2026-07-05T02:52:14Z"},{"alias_kind":"pith_short_8","alias_value":"LIU4LKNV","created_at":"2026-07-05T02:52:14Z"}],"graph_snapshots":[{"event_id":"sha256:fd531d1c3e5859b52ead23efddfeb56d9d6edf4e53eac3ba8f54cdb40349b1da","target":"graph","created_at":"2026-07-05T02:52:14Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2101.09899/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep Convolutional Neural Networks (DCNNs) and their variants have been widely used in large scale face recognition(FR) recently. Existing methods have achieved good performance on many FR benchmarks. However, most of them suffer from two major problems. First, these methods converge quite slowly since they optimize the loss functions in a high-dimensional and sparse Gaussian Sphere. Second, the high dimensionality of features, despite the powerful descriptive ability, brings difficulty to the optimization, which may lead to a sub-optimal local optimum. To address these problems, we propose a ","authors_text":"Jing Xu, Kun Bai, Tszhang Guo, Yong Xu, Zenglin Xu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-01-25T05:18:51Z","title":"MultiFace: A Generic Training Mechanism for Boosting Face Recognition Performance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.09899","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c69494393e4908d29ca518040fa11731fdb328876dd847eb0bd9043385f1b0c1","target":"record","created_at":"2026-07-05T02:52:14Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"cd4164590b8cc9f0635cc16f66bc5904bcae25efc23a99c7abf96ec28e900d98","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-01-25T05:18:51Z","title_canon_sha256":"cf7863b1b407611197420635fe98ff9752b5f95b467fa04ae5d77c8f35fc5bea"},"schema_version":"1.0","source":{"id":"2101.09899","kind":"arxiv","version":3}},"canonical_sha256":"5a29c5a9b5c169cce6be7805aba8078b2bc983b180cc26480552456a19dd3b41","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5a29c5a9b5c169cce6be7805aba8078b2bc983b180cc26480552456a19dd3b41","first_computed_at":"2026-07-05T02:52:14.794113Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:52:14.794113Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XfHfhiPJ3dqWoGgJRljdxX6vMLiRKSX1l5vQwF4Gm03uuAqh7+t+Dt3fHbVGCDOePehMxOWm/A4Bhu22EsBeBg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:52:14.794508Z","signed_message":"canonical_sha256_bytes"},"source_id":"2101.09899","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c69494393e4908d29ca518040fa11731fdb328876dd847eb0bd9043385f1b0c1","sha256:fd531d1c3e5859b52ead23efddfeb56d9d6edf4e53eac3ba8f54cdb40349b1da"],"state_sha256":"02d89bd4483daeaf032dfc193fc5477ddeeb68c926bafa8fdd31fd8812c6427c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NNiNzB0RypzLZKGq57Ol8hEIpGvWKkS0J9eXp79PevivZK40QCoh3pbW73WcXVPxzeny5bHk87S0oVLv+19gBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T04:07:41.313952Z","bundle_sha256":"5aead9d55425906892d25a7e164953436d874922b8c9ef96e9c5ef5365faecdf"}}