{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:UY4GLGBPSJMMZNUHEMDZU5A7Z7","short_pith_number":"pith:UY4GLGBP","schema_version":"1.0","canonical_sha256":"a63865982f9258ccb68723079a741fcfc2c29dc2c0ddcc4940cdde65946e0ebe","source":{"kind":"arxiv","id":"1611.00822","version":1},"attestation_state":"computed","paper":{"title":"Learning Deep Embeddings with Histogram Loss","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Evgeniya Ustinova, Victor Lempitsky","submitted_at":"2016-11-02T21:48:32Z","abstract_excerpt":"We suggest a loss for learning deep embeddings. The new loss does not introduce parameters that need to be tuned and results in very good embeddings across a range of datasets and problems. The loss is computed by estimating two distribution of similarities for positive (matching) and negative (non-matching) sample pairs, and then computing the probability of a positive pair to have a lower similarity score than a negative pair based on the estimated similarity distributions. We show that such operations can be performed in a simple and piecewise-differentiable manner using 1D histograms with "},"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":"1611.00822","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-11-02T21:48:32Z","cross_cats_sorted":[],"title_canon_sha256":"046726817b7b273393f426e39c781f8dbf4b6484c07f95055e8ee587b8ceab53","abstract_canon_sha256":"2bfc15430a7977e21545367bd2c13e805d5f9f8202e69f2545e0fd14eec24f35"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:00:18.616036Z","signature_b64":"PHmrF5bBvzJOvVxbd3VWfSl//+JyU3W6kchju5hZI/gTAA7tn3G6sb9OLd1qgDnBsl3y0cdpK3bxeO/bH7QWBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a63865982f9258ccb68723079a741fcfc2c29dc2c0ddcc4940cdde65946e0ebe","last_reissued_at":"2026-05-18T01:00:18.615302Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:00:18.615302Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Deep Embeddings with Histogram Loss","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Evgeniya Ustinova, Victor Lempitsky","submitted_at":"2016-11-02T21:48:32Z","abstract_excerpt":"We suggest a loss for learning deep embeddings. The new loss does not introduce parameters that need to be tuned and results in very good embeddings across a range of datasets and problems. The loss is computed by estimating two distribution of similarities for positive (matching) and negative (non-matching) sample pairs, and then computing the probability of a positive pair to have a lower similarity score than a negative pair based on the estimated similarity distributions. We show that such operations can be performed in a simple and piecewise-differentiable manner using 1D histograms with "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.00822","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1611.00822","created_at":"2026-05-18T01:00:18.615431+00:00"},{"alias_kind":"arxiv_version","alias_value":"1611.00822v1","created_at":"2026-05-18T01:00:18.615431+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.00822","created_at":"2026-05-18T01:00:18.615431+00:00"},{"alias_kind":"pith_short_12","alias_value":"UY4GLGBPSJMM","created_at":"2026-05-18T12:30:46.583412+00:00"},{"alias_kind":"pith_short_16","alias_value":"UY4GLGBPSJMMZNUH","created_at":"2026-05-18T12:30:46.583412+00:00"},{"alias_kind":"pith_short_8","alias_value":"UY4GLGBP","created_at":"2026-05-18T12:30:46.583412+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UY4GLGBPSJMMZNUHEMDZU5A7Z7","json":"https://pith.science/pith/UY4GLGBPSJMMZNUHEMDZU5A7Z7.json","graph_json":"https://pith.science/api/pith-number/UY4GLGBPSJMMZNUHEMDZU5A7Z7/graph.json","events_json":"https://pith.science/api/pith-number/UY4GLGBPSJMMZNUHEMDZU5A7Z7/events.json","paper":"https://pith.science/paper/UY4GLGBP"},"agent_actions":{"view_html":"https://pith.science/pith/UY4GLGBPSJMMZNUHEMDZU5A7Z7","download_json":"https://pith.science/pith/UY4GLGBPSJMMZNUHEMDZU5A7Z7.json","view_paper":"https://pith.science/paper/UY4GLGBP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1611.00822&json=true","fetch_graph":"https://pith.science/api/pith-number/UY4GLGBPSJMMZNUHEMDZU5A7Z7/graph.json","fetch_events":"https://pith.science/api/pith-number/UY4GLGBPSJMMZNUHEMDZU5A7Z7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UY4GLGBPSJMMZNUHEMDZU5A7Z7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UY4GLGBPSJMMZNUHEMDZU5A7Z7/action/storage_attestation","attest_author":"https://pith.science/pith/UY4GLGBPSJMMZNUHEMDZU5A7Z7/action/author_attestation","sign_citation":"https://pith.science/pith/UY4GLGBPSJMMZNUHEMDZU5A7Z7/action/citation_signature","submit_replication":"https://pith.science/pith/UY4GLGBPSJMMZNUHEMDZU5A7Z7/action/replication_record"}},"created_at":"2026-05-18T01:00:18.615431+00:00","updated_at":"2026-05-18T01:00:18.615431+00:00"}