{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:SVY4EFAXDRRW62Y66H7JHZKO7S","short_pith_number":"pith:SVY4EFAX","canonical_record":{"source":{"id":"1904.08720","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-18T12:14:50Z","cross_cats_sorted":[],"title_canon_sha256":"75d646a1cdb972affaf099c5aef36062393fd4751db0897dcaafb20edbae9ae4","abstract_canon_sha256":"47fc4389b27074c49a63b0288d30d69259238fd4f116cc39e2399da79d1f7085"},"schema_version":"1.0"},"canonical_sha256":"9571c214171c636f6b1ef1fe93e54efca5656f5289c49c15cae8bdd2fc8c967e","source":{"kind":"arxiv","id":"1904.08720","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.08720","created_at":"2026-05-17T23:48:13Z"},{"alias_kind":"arxiv_version","alias_value":"1904.08720v1","created_at":"2026-05-17T23:48:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.08720","created_at":"2026-05-17T23:48:13Z"},{"alias_kind":"pith_short_12","alias_value":"SVY4EFAXDRRW","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"SVY4EFAXDRRW62Y6","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"SVY4EFAX","created_at":"2026-05-18T12:33:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:SVY4EFAXDRRW62Y66H7JHZKO7S","target":"record","payload":{"canonical_record":{"source":{"id":"1904.08720","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-18T12:14:50Z","cross_cats_sorted":[],"title_canon_sha256":"75d646a1cdb972affaf099c5aef36062393fd4751db0897dcaafb20edbae9ae4","abstract_canon_sha256":"47fc4389b27074c49a63b0288d30d69259238fd4f116cc39e2399da79d1f7085"},"schema_version":"1.0"},"canonical_sha256":"9571c214171c636f6b1ef1fe93e54efca5656f5289c49c15cae8bdd2fc8c967e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:13.238677Z","signature_b64":"Bz7GDHY+PG9HSUetK2PB4g21vXAQxgSEWGaGPSKmBc0tBaOOl3Ib4Rv6Khb3bEeOFBxBme1W1+4J2NouCpcmCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9571c214171c636f6b1ef1fe93e54efca5656f5289c49c15cae8bdd2fc8c967e","last_reissued_at":"2026-05-17T23:48:13.237911Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:13.237911Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1904.08720","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:48:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OVdiCNghYpwqrNOwVF9pMH49hmFog75MjcDTi8B7IxR6UTcDzRNN2cB8W2BHmXhRHmZzYtB4Jd402/vuSXZhCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T18:37:02.862919Z"},"content_sha256":"d2ad9d25b9661f4d9ba722ae920d36ab0132eb408042068f9983b5daa8bc9744","schema_version":"1.0","event_id":"sha256:d2ad9d25b9661f4d9ba722ae920d36ab0132eb408042068f9983b5daa8bc9744"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:SVY4EFAXDRRW62Y66H7JHZKO7S","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Theoretically Sound Upper Bound on the Triplet Loss for Improving the Efficiency of Deep Distance Metric Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gustavo Carneiro, Ian Reid, Thanh-Toan Do, Toan Tran, Tuan Hoang, Vijay Kumar","submitted_at":"2019-04-18T12:14:50Z","abstract_excerpt":"We propose a method that substantially improves the efficiency of deep distance metric learning based on the optimization of the triplet loss function. One epoch of such training process based on a naive optimization of the triplet loss function has a run-time complexity O(N^3), where N is the number of training samples. Such optimization scales poorly, and the most common approach proposed to address this high complexity issue is based on sub-sampling the set of triplets needed for the training process. Another approach explored in the field relies on an ad-hoc linearization (in terms of N) o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.08720","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:48:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hXM+wmVbX8fUn/AGgouhxpjqKdz0hj1Eo0uZA8nY1Au3fN4N50d8yEYVWHuqwmRRqDjTG32Cyj/lnqEXGGhqCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T18:37:02.863351Z"},"content_sha256":"4fc2b1957d459db2d6b58fd0c99754b00a56312497f352e5f6976f604af04e84","schema_version":"1.0","event_id":"sha256:4fc2b1957d459db2d6b58fd0c99754b00a56312497f352e5f6976f604af04e84"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SVY4EFAXDRRW62Y66H7JHZKO7S/bundle.json","state_url":"https://pith.science/pith/SVY4EFAXDRRW62Y66H7JHZKO7S/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SVY4EFAXDRRW62Y66H7JHZKO7S/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":"2026-05-29T18:37:02Z","links":{"resolver":"https://pith.science/pith/SVY4EFAXDRRW62Y66H7JHZKO7S","bundle":"https://pith.science/pith/SVY4EFAXDRRW62Y66H7JHZKO7S/bundle.json","state":"https://pith.science/pith/SVY4EFAXDRRW62Y66H7JHZKO7S/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SVY4EFAXDRRW62Y66H7JHZKO7S/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:SVY4EFAXDRRW62Y66H7JHZKO7S","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":"47fc4389b27074c49a63b0288d30d69259238fd4f116cc39e2399da79d1f7085","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-18T12:14:50Z","title_canon_sha256":"75d646a1cdb972affaf099c5aef36062393fd4751db0897dcaafb20edbae9ae4"},"schema_version":"1.0","source":{"id":"1904.08720","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.08720","created_at":"2026-05-17T23:48:13Z"},{"alias_kind":"arxiv_version","alias_value":"1904.08720v1","created_at":"2026-05-17T23:48:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.08720","created_at":"2026-05-17T23:48:13Z"},{"alias_kind":"pith_short_12","alias_value":"SVY4EFAXDRRW","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"SVY4EFAXDRRW62Y6","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"SVY4EFAX","created_at":"2026-05-18T12:33:27Z"}],"graph_snapshots":[{"event_id":"sha256:4fc2b1957d459db2d6b58fd0c99754b00a56312497f352e5f6976f604af04e84","target":"graph","created_at":"2026-05-17T23:48:13Z","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":"We propose a method that substantially improves the efficiency of deep distance metric learning based on the optimization of the triplet loss function. One epoch of such training process based on a naive optimization of the triplet loss function has a run-time complexity O(N^3), where N is the number of training samples. Such optimization scales poorly, and the most common approach proposed to address this high complexity issue is based on sub-sampling the set of triplets needed for the training process. Another approach explored in the field relies on an ad-hoc linearization (in terms of N) o","authors_text":"Gustavo Carneiro, Ian Reid, Thanh-Toan Do, Toan Tran, Tuan Hoang, Vijay Kumar","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-18T12:14:50Z","title":"A Theoretically Sound Upper Bound on the Triplet Loss for Improving the Efficiency of Deep Distance Metric Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.08720","kind":"arxiv","version":1},"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:d2ad9d25b9661f4d9ba722ae920d36ab0132eb408042068f9983b5daa8bc9744","target":"record","created_at":"2026-05-17T23:48:13Z","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":"47fc4389b27074c49a63b0288d30d69259238fd4f116cc39e2399da79d1f7085","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-18T12:14:50Z","title_canon_sha256":"75d646a1cdb972affaf099c5aef36062393fd4751db0897dcaafb20edbae9ae4"},"schema_version":"1.0","source":{"id":"1904.08720","kind":"arxiv","version":1}},"canonical_sha256":"9571c214171c636f6b1ef1fe93e54efca5656f5289c49c15cae8bdd2fc8c967e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9571c214171c636f6b1ef1fe93e54efca5656f5289c49c15cae8bdd2fc8c967e","first_computed_at":"2026-05-17T23:48:13.237911Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:48:13.237911Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Bz7GDHY+PG9HSUetK2PB4g21vXAQxgSEWGaGPSKmBc0tBaOOl3Ib4Rv6Khb3bEeOFBxBme1W1+4J2NouCpcmCw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:48:13.238677Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.08720","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d2ad9d25b9661f4d9ba722ae920d36ab0132eb408042068f9983b5daa8bc9744","sha256:4fc2b1957d459db2d6b58fd0c99754b00a56312497f352e5f6976f604af04e84"],"state_sha256":"682958e000c36ff0f518807262efec9ace6f1debb2ac1982f3757eaf4366df42"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R8oYQlBneXdzqGWLRbqsgKLl5B9+6ItK0IPx0QAR9b9mlTdJehJnsOw3wAfamx6QF4KfOdntXdy6r0fHddEtDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-29T18:37:02.867338Z","bundle_sha256":"cdbba65795a2d8bd950453dad2d09c566fbc23eaf74cfe6b6fe0e1d0aecde345"}}