{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:WTPMCB5ZKBEO2CFPLZCGNGPUNV","short_pith_number":"pith:WTPMCB5Z","canonical_record":{"source":{"id":"1612.08499","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-12-27T05:03:09Z","cross_cats_sorted":[],"title_canon_sha256":"458d2192c772cdb1d6c332ad816ad352420070747b0b76b90aedee69f671e077","abstract_canon_sha256":"e12c2f72c1f86f8f81c1b15d9d062794972342a60db3167cfb1f0fbcaa3df57d"},"schema_version":"1.0"},"canonical_sha256":"b4dec107b95048ed08af5e446699f46d50949199d02291438f4ba090379d9af1","source":{"kind":"arxiv","id":"1612.08499","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.08499","created_at":"2026-05-18T00:53:52Z"},{"alias_kind":"arxiv_version","alias_value":"1612.08499v1","created_at":"2026-05-18T00:53:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.08499","created_at":"2026-05-18T00:53:52Z"},{"alias_kind":"pith_short_12","alias_value":"WTPMCB5ZKBEO","created_at":"2026-05-18T12:30:51Z"},{"alias_kind":"pith_short_16","alias_value":"WTPMCB5ZKBEO2CFP","created_at":"2026-05-18T12:30:51Z"},{"alias_kind":"pith_short_8","alias_value":"WTPMCB5Z","created_at":"2026-05-18T12:30:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:WTPMCB5ZKBEO2CFPLZCGNGPUNV","target":"record","payload":{"canonical_record":{"source":{"id":"1612.08499","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-12-27T05:03:09Z","cross_cats_sorted":[],"title_canon_sha256":"458d2192c772cdb1d6c332ad816ad352420070747b0b76b90aedee69f671e077","abstract_canon_sha256":"e12c2f72c1f86f8f81c1b15d9d062794972342a60db3167cfb1f0fbcaa3df57d"},"schema_version":"1.0"},"canonical_sha256":"b4dec107b95048ed08af5e446699f46d50949199d02291438f4ba090379d9af1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:53:52.835113Z","signature_b64":"wWdqsD4eJ34Dnd0KNuN3+L2w7znZCyzNfqXfgcaT46D7SeJi1xPOpPH2dHSwpfKxS0CORvWxOHQBXUmdbvpcBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4dec107b95048ed08af5e446699f46d50949199d02291438f4ba090379d9af1","last_reissued_at":"2026-05-18T00:53:52.834496Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:53:52.834496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1612.08499","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":"2026-05-18T00:53:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tW0JpIvxoyRsf3xu1ekwQcxFE0AZ2UKrAWOc/8AMjnAEQneOwdIzDus3AtiuMn96LBDfJ3hHMsDXaPUiCvkDCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T19:47:48.946510Z"},"content_sha256":"b0e1f8cd7acadd9b1cb1943552001e004e2eef7d1fe0c08afaf468cf5e6185d6","schema_version":"1.0","event_id":"sha256:b0e1f8cd7acadd9b1cb1943552001e004e2eef7d1fe0c08afaf468cf5e6185d6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:WTPMCB5ZKBEO2CFPLZCGNGPUNV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"End-to-End Data Visualization by Metric Learning and Coordinate Transformation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Atilla Baskurt, Christophe Garcia, Khalid Idrissi, Lilei Zheng, Stefan Duffner, Ying Zhang","submitted_at":"2016-12-27T05:03:09Z","abstract_excerpt":"This paper presents a deep nonlinear metric learning framework for data visualization on an image dataset. We propose the Triangular Similarity and prove its equivalence to the Cosine Similarity in measuring a data pair. Based on this novel similarity, a geometrically motivated loss function - the triangular loss - is then developed for optimizing a metric learning system comprising two identical CNNs. It is shown that this deep nonlinear system can be efficiently trained by a hybrid algorithm based on the conventional backpropagation algorithm. More interestingly, benefiting from classical ma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.08499","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":"2026-05-18T00:53:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7BGxdJHfGXt3eN89S2lIrvWf/eSEMMIETOnpvJkjy907HfGYzFSApaA8ujMrDHqbKOVzwwRM3nM3mCgAB0DkDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T19:47:48.946902Z"},"content_sha256":"26951559f87ea1c53884e08ad7325394e23c8b33d57da2bb5221ae3310f10b11","schema_version":"1.0","event_id":"sha256:26951559f87ea1c53884e08ad7325394e23c8b33d57da2bb5221ae3310f10b11"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WTPMCB5ZKBEO2CFPLZCGNGPUNV/bundle.json","state_url":"https://pith.science/pith/WTPMCB5ZKBEO2CFPLZCGNGPUNV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WTPMCB5ZKBEO2CFPLZCGNGPUNV/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":"2026-06-01T19:47:48Z","links":{"resolver":"https://pith.science/pith/WTPMCB5ZKBEO2CFPLZCGNGPUNV","bundle":"https://pith.science/pith/WTPMCB5ZKBEO2CFPLZCGNGPUNV/bundle.json","state":"https://pith.science/pith/WTPMCB5ZKBEO2CFPLZCGNGPUNV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WTPMCB5ZKBEO2CFPLZCGNGPUNV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:WTPMCB5ZKBEO2CFPLZCGNGPUNV","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":"e12c2f72c1f86f8f81c1b15d9d062794972342a60db3167cfb1f0fbcaa3df57d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-12-27T05:03:09Z","title_canon_sha256":"458d2192c772cdb1d6c332ad816ad352420070747b0b76b90aedee69f671e077"},"schema_version":"1.0","source":{"id":"1612.08499","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.08499","created_at":"2026-05-18T00:53:52Z"},{"alias_kind":"arxiv_version","alias_value":"1612.08499v1","created_at":"2026-05-18T00:53:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.08499","created_at":"2026-05-18T00:53:52Z"},{"alias_kind":"pith_short_12","alias_value":"WTPMCB5ZKBEO","created_at":"2026-05-18T12:30:51Z"},{"alias_kind":"pith_short_16","alias_value":"WTPMCB5ZKBEO2CFP","created_at":"2026-05-18T12:30:51Z"},{"alias_kind":"pith_short_8","alias_value":"WTPMCB5Z","created_at":"2026-05-18T12:30:51Z"}],"graph_snapshots":[{"event_id":"sha256:26951559f87ea1c53884e08ad7325394e23c8b33d57da2bb5221ae3310f10b11","target":"graph","created_at":"2026-05-18T00:53:52Z","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":"This paper presents a deep nonlinear metric learning framework for data visualization on an image dataset. We propose the Triangular Similarity and prove its equivalence to the Cosine Similarity in measuring a data pair. Based on this novel similarity, a geometrically motivated loss function - the triangular loss - is then developed for optimizing a metric learning system comprising two identical CNNs. It is shown that this deep nonlinear system can be efficiently trained by a hybrid algorithm based on the conventional backpropagation algorithm. More interestingly, benefiting from classical ma","authors_text":"Atilla Baskurt, Christophe Garcia, Khalid Idrissi, Lilei Zheng, Stefan Duffner, Ying Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-12-27T05:03:09Z","title":"End-to-End Data Visualization by Metric Learning and Coordinate Transformation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.08499","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:b0e1f8cd7acadd9b1cb1943552001e004e2eef7d1fe0c08afaf468cf5e6185d6","target":"record","created_at":"2026-05-18T00:53:52Z","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":"e12c2f72c1f86f8f81c1b15d9d062794972342a60db3167cfb1f0fbcaa3df57d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-12-27T05:03:09Z","title_canon_sha256":"458d2192c772cdb1d6c332ad816ad352420070747b0b76b90aedee69f671e077"},"schema_version":"1.0","source":{"id":"1612.08499","kind":"arxiv","version":1}},"canonical_sha256":"b4dec107b95048ed08af5e446699f46d50949199d02291438f4ba090379d9af1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b4dec107b95048ed08af5e446699f46d50949199d02291438f4ba090379d9af1","first_computed_at":"2026-05-18T00:53:52.834496Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:53:52.834496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wWdqsD4eJ34Dnd0KNuN3+L2w7znZCyzNfqXfgcaT46D7SeJi1xPOpPH2dHSwpfKxS0CORvWxOHQBXUmdbvpcBg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:53:52.835113Z","signed_message":"canonical_sha256_bytes"},"source_id":"1612.08499","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b0e1f8cd7acadd9b1cb1943552001e004e2eef7d1fe0c08afaf468cf5e6185d6","sha256:26951559f87ea1c53884e08ad7325394e23c8b33d57da2bb5221ae3310f10b11"],"state_sha256":"bdfd15e9b3c067d5421b5c96233841f82158706e6dc14e5df818b96fea2e4900"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fMAKawyjXKHty+edFXQBEugGjVlNudBefcdzGlYRV0TwqqjlBKEpH69Wo34xO8TIufy+9r3qXUjMTCMgjpsRCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T19:47:48.948830Z","bundle_sha256":"3f80bbaafbdf4cef1adf7b06f3ba4048446d53a8b381e55786e2693e6ffaf391"}}