{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZXMFJSH3EGWUL4GF73SVILW545","short_pith_number":"pith:ZXMFJSH3","schema_version":"1.0","canonical_sha256":"cdd854c8fb21ad45f0c5fee5542edde76b85aaa84f3792c6185ece3a435f45e3","source":{"kind":"arxiv","id":"2306.00630","version":2},"attestation_state":"computed","paper":{"title":"Class Anchor Margin Loss for Content-Based Image Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Alexandru Ghita, Radu Tudor Ionescu","submitted_at":"2023-06-01T12:53:10Z","abstract_excerpt":"The performance of neural networks in content-based image retrieval (CBIR) is highly influenced by the chosen loss (objective) function. The majority of objective functions for neural models can be divided into metric learning and statistical learning. Metric learning approaches require a pair mining strategy that often lacks efficiency, while statistical learning approaches are not generating highly compact features due to their indirect feature optimization. To this end, we propose a novel repeller-attractor loss that falls in the metric learning paradigm, yet directly optimizes for the L2 m"},"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":"2306.00630","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-06-01T12:53:10Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"83d5422f24158d3bbb3d9cedde3ad97b62f0813fc44ae406cb876fa3be8554a9","abstract_canon_sha256":"0ed090905f18c13c1b937f1a5ed23b7f71cab9711878cfbd136e6eb49a698e28"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:17:08.451755Z","signature_b64":"RjVlSc/9bGH/F1LAZM4uraqtC+dXjcOMiyOS3H3z1EXy4xMzJ8tmyQTOCsfRJ35/mnVl3TPW8sph9NFrJSb0AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cdd854c8fb21ad45f0c5fee5542edde76b85aaa84f3792c6185ece3a435f45e3","last_reissued_at":"2026-07-05T06:17:08.451346Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:17:08.451346Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Class Anchor Margin Loss for Content-Based Image Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CV","authors_text":"Alexandru Ghita, Radu Tudor Ionescu","submitted_at":"2023-06-01T12:53:10Z","abstract_excerpt":"The performance of neural networks in content-based image retrieval (CBIR) is highly influenced by the chosen loss (objective) function. The majority of objective functions for neural models can be divided into metric learning and statistical learning. Metric learning approaches require a pair mining strategy that often lacks efficiency, while statistical learning approaches are not generating highly compact features due to their indirect feature optimization. To this end, we propose a novel repeller-attractor loss that falls in the metric learning paradigm, yet directly optimizes for the L2 m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.00630","kind":"arxiv","version":2},"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/2306.00630/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2306.00630","created_at":"2026-07-05T06:17:08.451402+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.00630v2","created_at":"2026-07-05T06:17:08.451402+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.00630","created_at":"2026-07-05T06:17:08.451402+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZXMFJSH3EGWU","created_at":"2026-07-05T06:17:08.451402+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZXMFJSH3EGWUL4GF","created_at":"2026-07-05T06:17:08.451402+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZXMFJSH3","created_at":"2026-07-05T06:17:08.451402+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/ZXMFJSH3EGWUL4GF73SVILW545","json":"https://pith.science/pith/ZXMFJSH3EGWUL4GF73SVILW545.json","graph_json":"https://pith.science/api/pith-number/ZXMFJSH3EGWUL4GF73SVILW545/graph.json","events_json":"https://pith.science/api/pith-number/ZXMFJSH3EGWUL4GF73SVILW545/events.json","paper":"https://pith.science/paper/ZXMFJSH3"},"agent_actions":{"view_html":"https://pith.science/pith/ZXMFJSH3EGWUL4GF73SVILW545","download_json":"https://pith.science/pith/ZXMFJSH3EGWUL4GF73SVILW545.json","view_paper":"https://pith.science/paper/ZXMFJSH3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.00630&json=true","fetch_graph":"https://pith.science/api/pith-number/ZXMFJSH3EGWUL4GF73SVILW545/graph.json","fetch_events":"https://pith.science/api/pith-number/ZXMFJSH3EGWUL4GF73SVILW545/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZXMFJSH3EGWUL4GF73SVILW545/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZXMFJSH3EGWUL4GF73SVILW545/action/storage_attestation","attest_author":"https://pith.science/pith/ZXMFJSH3EGWUL4GF73SVILW545/action/author_attestation","sign_citation":"https://pith.science/pith/ZXMFJSH3EGWUL4GF73SVILW545/action/citation_signature","submit_replication":"https://pith.science/pith/ZXMFJSH3EGWUL4GF73SVILW545/action/replication_record"}},"created_at":"2026-07-05T06:17:08.451402+00:00","updated_at":"2026-07-05T06:17:08.451402+00:00"}