{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:S3WH2F6KJ3UGFT3GGLZOHI6JIG","short_pith_number":"pith:S3WH2F6K","schema_version":"1.0","canonical_sha256":"96ec7d17ca4ee862cf6632f2e3a3c941ab59597d6f7b55716cbd4fbe95c321f4","source":{"kind":"arxiv","id":"1703.07464","version":3},"attestation_state":"computed","paper":{"title":"No Fuss Distance Metric Learning using Proxies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexander Toshev, Saurabh Singh, Sergey Ioffe, Thomas K. Leung, Yair Movshovitz-Attias","submitted_at":"2017-03-21T23:11:56Z","abstract_excerpt":"We address the problem of distance metric learning (DML), defined as learning a distance consistent with a notion of semantic similarity. Traditionally, for this problem supervision is expressed in the form of sets of points that follow an ordinal relationship -- an anchor point $x$ is similar to a set of positive points $Y$, and dissimilar to a set of negative points $Z$, and a loss defined over these distances is minimized. While the specifics of the optimization differ, in this work we collectively call this type of supervision Triplets and all methods that follow this pattern Triplet-Based"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1703.07464","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-21T23:11:56Z","cross_cats_sorted":[],"title_canon_sha256":"2734e90f278eade8af5d24c91367ea1e961189905b3d1587923c86454306d3c6","abstract_canon_sha256":"fe7051d48ea26a0da5a2df6790a34908697984010f7f5735515042618dcb1348"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:38:46.120516Z","signature_b64":"I2+nGpE7paxPq/BmvoadF448W7jEizBW0/nRlHzyuFo4mlfMagTK6wY50rLu/Q47lQEtzw/9WuUlLsDZOHGaDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"96ec7d17ca4ee862cf6632f2e3a3c941ab59597d6f7b55716cbd4fbe95c321f4","last_reissued_at":"2026-05-18T00:38:46.119902Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:38:46.119902Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"No Fuss Distance Metric Learning using Proxies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexander Toshev, Saurabh Singh, Sergey Ioffe, Thomas K. Leung, Yair Movshovitz-Attias","submitted_at":"2017-03-21T23:11:56Z","abstract_excerpt":"We address the problem of distance metric learning (DML), defined as learning a distance consistent with a notion of semantic similarity. Traditionally, for this problem supervision is expressed in the form of sets of points that follow an ordinal relationship -- an anchor point $x$ is similar to a set of positive points $Y$, and dissimilar to a set of negative points $Z$, and a loss defined over these distances is minimized. While the specifics of the optimization differ, in this work we collectively call this type of supervision Triplets and all methods that follow this pattern Triplet-Based"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.07464","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":""},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1703.07464","created_at":"2026-05-18T00:38:46.119968+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.07464v3","created_at":"2026-05-18T00:38:46.119968+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.07464","created_at":"2026-05-18T00:38:46.119968+00:00"},{"alias_kind":"pith_short_12","alias_value":"S3WH2F6KJ3UG","created_at":"2026-05-18T12:31:43.269735+00:00"},{"alias_kind":"pith_short_16","alias_value":"S3WH2F6KJ3UGFT3G","created_at":"2026-05-18T12:31:43.269735+00:00"},{"alias_kind":"pith_short_8","alias_value":"S3WH2F6K","created_at":"2026-05-18T12:31:43.269735+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.09245","citing_title":"Quadruplet Selection Methods for Deep Embedding Learning","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S3WH2F6KJ3UGFT3GGLZOHI6JIG","json":"https://pith.science/pith/S3WH2F6KJ3UGFT3GGLZOHI6JIG.json","graph_json":"https://pith.science/api/pith-number/S3WH2F6KJ3UGFT3GGLZOHI6JIG/graph.json","events_json":"https://pith.science/api/pith-number/S3WH2F6KJ3UGFT3GGLZOHI6JIG/events.json","paper":"https://pith.science/paper/S3WH2F6K"},"agent_actions":{"view_html":"https://pith.science/pith/S3WH2F6KJ3UGFT3GGLZOHI6JIG","download_json":"https://pith.science/pith/S3WH2F6KJ3UGFT3GGLZOHI6JIG.json","view_paper":"https://pith.science/paper/S3WH2F6K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.07464&json=true","fetch_graph":"https://pith.science/api/pith-number/S3WH2F6KJ3UGFT3GGLZOHI6JIG/graph.json","fetch_events":"https://pith.science/api/pith-number/S3WH2F6KJ3UGFT3GGLZOHI6JIG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S3WH2F6KJ3UGFT3GGLZOHI6JIG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S3WH2F6KJ3UGFT3GGLZOHI6JIG/action/storage_attestation","attest_author":"https://pith.science/pith/S3WH2F6KJ3UGFT3GGLZOHI6JIG/action/author_attestation","sign_citation":"https://pith.science/pith/S3WH2F6KJ3UGFT3GGLZOHI6JIG/action/citation_signature","submit_replication":"https://pith.science/pith/S3WH2F6KJ3UGFT3GGLZOHI6JIG/action/replication_record"}},"created_at":"2026-05-18T00:38:46.119968+00:00","updated_at":"2026-05-18T00:38:46.119968+00:00"}