{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:IPFEOKWGVBV4SAV7NJM63OXV5Q","short_pith_number":"pith:IPFEOKWG","canonical_record":{"source":{"id":"1903.03238","kind":"arxiv","version":8},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-08T01:28:17Z","cross_cats_sorted":[],"title_canon_sha256":"cc7c15889e2d768490637c07b58270d548da9918c1d02d9d39590b1c15920250","abstract_canon_sha256":"d7ead3477542f79ad3f455fd26d73a22a1eeb64eb5bbac6fa821eac81b177e30"},"schema_version":"1.0"},"canonical_sha256":"43ca472ac6a86bc902bf6a59edbaf5ec12274cbcff39854df7024260144d8176","source":{"kind":"arxiv","id":"1903.03238","version":8},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.03238","created_at":"2026-07-05T02:24:27Z"},{"alias_kind":"arxiv_version","alias_value":"1903.03238v8","created_at":"2026-07-05T02:24:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.03238","created_at":"2026-07-05T02:24:27Z"},{"alias_kind":"pith_short_12","alias_value":"IPFEOKWGVBV4","created_at":"2026-07-05T02:24:27Z"},{"alias_kind":"pith_short_16","alias_value":"IPFEOKWGVBV4SAV7","created_at":"2026-07-05T02:24:27Z"},{"alias_kind":"pith_short_8","alias_value":"IPFEOKWG","created_at":"2026-07-05T02:24:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:IPFEOKWGVBV4SAV7NJM63OXV5Q","target":"record","payload":{"canonical_record":{"source":{"id":"1903.03238","kind":"arxiv","version":8},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-08T01:28:17Z","cross_cats_sorted":[],"title_canon_sha256":"cc7c15889e2d768490637c07b58270d548da9918c1d02d9d39590b1c15920250","abstract_canon_sha256":"d7ead3477542f79ad3f455fd26d73a22a1eeb64eb5bbac6fa821eac81b177e30"},"schema_version":"1.0"},"canonical_sha256":"43ca472ac6a86bc902bf6a59edbaf5ec12274cbcff39854df7024260144d8176","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:24:27.327850Z","signature_b64":"h8n8vr0AsNURo6/GqcU83MHEwKvIrMdNaVfXEIhLOArStF3Gihk4UkkwrQoTho8RGwY3FPX1LrdoXktw+YZLDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"43ca472ac6a86bc902bf6a59edbaf5ec12274cbcff39854df7024260144d8176","last_reissued_at":"2026-07-05T02:24:27.327328Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:24:27.327328Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1903.03238","source_version":8,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:24:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"04i88UgA6mTJ7+5iai+aUTuqzqGWuWRvV3pK8VSkMOk29ly/xY25qUoi3PzZ1AvQHF2j71Uzl/DiGX+pH5scAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T15:42:12.693272Z"},"content_sha256":"96390e63181d62ec09d3dce16d364986414864407d11dc8cac611e7bab3cdb05","schema_version":"1.0","event_id":"sha256:96390e63181d62ec09d3dce16d364986414864407d11dc8cac611e7bab3cdb05"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:IPFEOKWGVBV4SAV7NJM63OXV5Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Ranked List Loss for Deep Metric Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Elyor Kodirov, Neil M. Robertson, Xinshao Wang, Yang Hua","submitted_at":"2019-03-08T01:28:17Z","abstract_excerpt":"The objective of deep metric learning (DML) is to learn embeddings that can capture semantic similarity and dissimilarity information among data points. Existing pairwise or tripletwise loss functions used in DML are known to suffer from slow convergence due to a large proportion of trivial pairs or triplets as the model improves. To improve this, ranking-motivated structured losses are proposed recently to incorporate multiple examples and exploit the structured information among them. They converge faster and achieve state-of-the-art performance. In this work, we unveil two limitations of ex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.03238","kind":"arxiv","version":8},"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/1903.03238/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":"2026-07-05T02:24:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XB+wQHuUpd187+U07qhj/OwmKZs3u88QT0XB/m3LBbK69IXn2T2scruMYTAw2MQjaiu96fhEsv5HuCHVpU8/Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T15:42:12.693682Z"},"content_sha256":"077f635e27327e34c9827539ef9a8c1b1b18a738a71f0ac8a6f637c5feb86243","schema_version":"1.0","event_id":"sha256:077f635e27327e34c9827539ef9a8c1b1b18a738a71f0ac8a6f637c5feb86243"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IPFEOKWGVBV4SAV7NJM63OXV5Q/bundle.json","state_url":"https://pith.science/pith/IPFEOKWGVBV4SAV7NJM63OXV5Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IPFEOKWGVBV4SAV7NJM63OXV5Q/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":"2026-07-05T15:42:12Z","links":{"resolver":"https://pith.science/pith/IPFEOKWGVBV4SAV7NJM63OXV5Q","bundle":"https://pith.science/pith/IPFEOKWGVBV4SAV7NJM63OXV5Q/bundle.json","state":"https://pith.science/pith/IPFEOKWGVBV4SAV7NJM63OXV5Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IPFEOKWGVBV4SAV7NJM63OXV5Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:IPFEOKWGVBV4SAV7NJM63OXV5Q","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":"d7ead3477542f79ad3f455fd26d73a22a1eeb64eb5bbac6fa821eac81b177e30","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-08T01:28:17Z","title_canon_sha256":"cc7c15889e2d768490637c07b58270d548da9918c1d02d9d39590b1c15920250"},"schema_version":"1.0","source":{"id":"1903.03238","kind":"arxiv","version":8}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.03238","created_at":"2026-07-05T02:24:27Z"},{"alias_kind":"arxiv_version","alias_value":"1903.03238v8","created_at":"2026-07-05T02:24:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.03238","created_at":"2026-07-05T02:24:27Z"},{"alias_kind":"pith_short_12","alias_value":"IPFEOKWGVBV4","created_at":"2026-07-05T02:24:27Z"},{"alias_kind":"pith_short_16","alias_value":"IPFEOKWGVBV4SAV7","created_at":"2026-07-05T02:24:27Z"},{"alias_kind":"pith_short_8","alias_value":"IPFEOKWG","created_at":"2026-07-05T02:24:27Z"}],"graph_snapshots":[{"event_id":"sha256:077f635e27327e34c9827539ef9a8c1b1b18a738a71f0ac8a6f637c5feb86243","target":"graph","created_at":"2026-07-05T02:24:27Z","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/1903.03238/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The objective of deep metric learning (DML) is to learn embeddings that can capture semantic similarity and dissimilarity information among data points. Existing pairwise or tripletwise loss functions used in DML are known to suffer from slow convergence due to a large proportion of trivial pairs or triplets as the model improves. To improve this, ranking-motivated structured losses are proposed recently to incorporate multiple examples and exploit the structured information among them. They converge faster and achieve state-of-the-art performance. In this work, we unveil two limitations of ex","authors_text":"Elyor Kodirov, Neil M. Robertson, Xinshao Wang, Yang Hua","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-08T01:28:17Z","title":"Ranked List Loss for Deep Metric Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.03238","kind":"arxiv","version":8},"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":"sha256:96390e63181d62ec09d3dce16d364986414864407d11dc8cac611e7bab3cdb05","target":"record","created_at":"2026-07-05T02:24:27Z","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":"d7ead3477542f79ad3f455fd26d73a22a1eeb64eb5bbac6fa821eac81b177e30","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-03-08T01:28:17Z","title_canon_sha256":"cc7c15889e2d768490637c07b58270d548da9918c1d02d9d39590b1c15920250"},"schema_version":"1.0","source":{"id":"1903.03238","kind":"arxiv","version":8}},"canonical_sha256":"43ca472ac6a86bc902bf6a59edbaf5ec12274cbcff39854df7024260144d8176","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"43ca472ac6a86bc902bf6a59edbaf5ec12274cbcff39854df7024260144d8176","first_computed_at":"2026-07-05T02:24:27.327328Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:24:27.327328Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"h8n8vr0AsNURo6/GqcU83MHEwKvIrMdNaVfXEIhLOArStF3Gihk4UkkwrQoTho8RGwY3FPX1LrdoXktw+YZLDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:24:27.327850Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.03238","source_kind":"arxiv","source_version":8}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:96390e63181d62ec09d3dce16d364986414864407d11dc8cac611e7bab3cdb05","sha256:077f635e27327e34c9827539ef9a8c1b1b18a738a71f0ac8a6f637c5feb86243"],"state_sha256":"6a7142c58863b79c394dd51d32fd6f2eef6f555a144ac2cae3ba44042d3fe0c1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FXXxkHyTv7XfiWTT3tUzthGis+S7xxx3UlBFLNY73sVuGsrvCiHRsFgxa7Mz4oZAIbe+KjchXs6OBGmehTypCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T15:42:12.696470Z","bundle_sha256":"3a895ecf50990a90e91350b50694ee6dfa222620834b69e787009bd226d39b42"}}