{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:2DHB6T6H6HZY2COJTFQO7BBHP5","short_pith_number":"pith:2DHB6T6H","canonical_record":{"source":{"id":"1802.09662","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-02-27T00:54:19Z","cross_cats_sorted":[],"title_canon_sha256":"45340a801110c825601d97a4f347c0808155dcda36d76e3d210508b44082b179","abstract_canon_sha256":"91621acc388504ed5d83e368ba78f786a37980068f062c1e124f4b3466946b11"},"schema_version":"1.0"},"canonical_sha256":"d0ce1f4fc7f1f38d09c99960ef84277f55cb86c381c8bc90969ff05bfe1397bf","source":{"kind":"arxiv","id":"1802.09662","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.09662","created_at":"2026-05-18T00:19:56Z"},{"alias_kind":"arxiv_version","alias_value":"1802.09662v2","created_at":"2026-05-18T00:19:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.09662","created_at":"2026-05-18T00:19:56Z"},{"alias_kind":"pith_short_12","alias_value":"2DHB6T6H6HZY","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_16","alias_value":"2DHB6T6H6HZY2COJ","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_8","alias_value":"2DHB6T6H","created_at":"2026-05-18T12:31:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:2DHB6T6H6HZY2COJTFQO7BBHP5","target":"record","payload":{"canonical_record":{"source":{"id":"1802.09662","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-02-27T00:54:19Z","cross_cats_sorted":[],"title_canon_sha256":"45340a801110c825601d97a4f347c0808155dcda36d76e3d210508b44082b179","abstract_canon_sha256":"91621acc388504ed5d83e368ba78f786a37980068f062c1e124f4b3466946b11"},"schema_version":"1.0"},"canonical_sha256":"d0ce1f4fc7f1f38d09c99960ef84277f55cb86c381c8bc90969ff05bfe1397bf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:19:56.330573Z","signature_b64":"dcnxt3Gj0aLewHlPAaEV9hE8+OeSjiCRBfLscEkLNESeGHa6mWb8/AmKvuQClIOO9/UPUwFrGVSD2/wTzoHkAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0ce1f4fc7f1f38d09c99960ef84277f55cb86c381c8bc90969ff05bfe1397bf","last_reissued_at":"2026-05-18T00:19:56.329866Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:19:56.329866Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.09662","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:19:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W32JuwMmuyN8/7KycX7Uiag/4TrdDiVF3XrTT9LvzSsvrr+oKlkOVNSaFQpZToRUy2tXdOEGWeis5VeZJWK/Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T08:42:14.689362Z"},"content_sha256":"5f4508f7536d517698eb7e4a1c27093a7e1d0f49ced3c39db21c819aca64c47f","schema_version":"1.0","event_id":"sha256:5f4508f7536d517698eb7e4a1c27093a7e1d0f49ced3c39db21c819aca64c47f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:2DHB6T6H6HZY2COJTFQO7BBHP5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Directional Statistics-based Deep Metric Learning for Image Classification and Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hong Yan, Shifeng Chen, Xuefei Zhe","submitted_at":"2018-02-27T00:54:19Z","abstract_excerpt":"Deep distance metric learning (DDML), which is proposed to learn image similarity metrics in an end-to-end manner based on the convolution neural network, has achieved encouraging results in many computer vision tasks.$L2$-normalization in the embedding space has been used to improve the performance of several DDML methods. However, the commonly used Euclidean distance is no longer an accurate metric for $L2$-normalized embedding space, i.e., a hyper-sphere. Another challenge of current DDML methods is that their loss functions are usually based on rigid data formats, such as the triplet tuple"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.09662","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:19:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1jqWoipheK8feZm4bJFCGIKW8LesogYZ77V3iIv+JqNwVE6dnra0Ic4Gqdan8d+Hc72ysrVEa0YbKSJZpk2jDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T08:42:14.690005Z"},"content_sha256":"28351b5d6664b6f179d2ad50a56be079b2b1720368a51735804dff6219a0bb41","schema_version":"1.0","event_id":"sha256:28351b5d6664b6f179d2ad50a56be079b2b1720368a51735804dff6219a0bb41"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2DHB6T6H6HZY2COJTFQO7BBHP5/bundle.json","state_url":"https://pith.science/pith/2DHB6T6H6HZY2COJTFQO7BBHP5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2DHB6T6H6HZY2COJTFQO7BBHP5/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":"2026-06-09T08:42:14Z","links":{"resolver":"https://pith.science/pith/2DHB6T6H6HZY2COJTFQO7BBHP5","bundle":"https://pith.science/pith/2DHB6T6H6HZY2COJTFQO7BBHP5/bundle.json","state":"https://pith.science/pith/2DHB6T6H6HZY2COJTFQO7BBHP5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2DHB6T6H6HZY2COJTFQO7BBHP5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:2DHB6T6H6HZY2COJTFQO7BBHP5","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":"91621acc388504ed5d83e368ba78f786a37980068f062c1e124f4b3466946b11","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-02-27T00:54:19Z","title_canon_sha256":"45340a801110c825601d97a4f347c0808155dcda36d76e3d210508b44082b179"},"schema_version":"1.0","source":{"id":"1802.09662","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.09662","created_at":"2026-05-18T00:19:56Z"},{"alias_kind":"arxiv_version","alias_value":"1802.09662v2","created_at":"2026-05-18T00:19:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.09662","created_at":"2026-05-18T00:19:56Z"},{"alias_kind":"pith_short_12","alias_value":"2DHB6T6H6HZY","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_16","alias_value":"2DHB6T6H6HZY2COJ","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_8","alias_value":"2DHB6T6H","created_at":"2026-05-18T12:31:59Z"}],"graph_snapshots":[{"event_id":"sha256:28351b5d6664b6f179d2ad50a56be079b2b1720368a51735804dff6219a0bb41","target":"graph","created_at":"2026-05-18T00:19:56Z","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"},"paper":{"abstract_excerpt":"Deep distance metric learning (DDML), which is proposed to learn image similarity metrics in an end-to-end manner based on the convolution neural network, has achieved encouraging results in many computer vision tasks.$L2$-normalization in the embedding space has been used to improve the performance of several DDML methods. However, the commonly used Euclidean distance is no longer an accurate metric for $L2$-normalized embedding space, i.e., a hyper-sphere. Another challenge of current DDML methods is that their loss functions are usually based on rigid data formats, such as the triplet tuple","authors_text":"Hong Yan, Shifeng Chen, Xuefei Zhe","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-02-27T00:54:19Z","title":"Directional Statistics-based Deep Metric Learning for Image Classification and Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.09662","kind":"arxiv","version":2},"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":"sha256:5f4508f7536d517698eb7e4a1c27093a7e1d0f49ced3c39db21c819aca64c47f","target":"record","created_at":"2026-05-18T00:19:56Z","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":"91621acc388504ed5d83e368ba78f786a37980068f062c1e124f4b3466946b11","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-02-27T00:54:19Z","title_canon_sha256":"45340a801110c825601d97a4f347c0808155dcda36d76e3d210508b44082b179"},"schema_version":"1.0","source":{"id":"1802.09662","kind":"arxiv","version":2}},"canonical_sha256":"d0ce1f4fc7f1f38d09c99960ef84277f55cb86c381c8bc90969ff05bfe1397bf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d0ce1f4fc7f1f38d09c99960ef84277f55cb86c381c8bc90969ff05bfe1397bf","first_computed_at":"2026-05-18T00:19:56.329866Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:19:56.329866Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dcnxt3Gj0aLewHlPAaEV9hE8+OeSjiCRBfLscEkLNESeGHa6mWb8/AmKvuQClIOO9/UPUwFrGVSD2/wTzoHkAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:19:56.330573Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.09662","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5f4508f7536d517698eb7e4a1c27093a7e1d0f49ced3c39db21c819aca64c47f","sha256:28351b5d6664b6f179d2ad50a56be079b2b1720368a51735804dff6219a0bb41"],"state_sha256":"8e65763102675db2cf4f4ab9e49113f74bcde8a9861afc8555b5f29d33d3f5f5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bTLCPJiGSjXtjFPKq70lUb2F7yM6zsq93D89YwG6mIX9NzW03VLc/YNyFQ5UJatb6WxgWV59QYcblpEfvv2oBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T08:42:14.693658Z","bundle_sha256":"80d5da719a5a5352af8656f603d3f4c96986e86a8f80749515ecb4ce9a31b71e"}}