{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:NHXAA6ULA3LZUDJCR3NHXIXOOV","short_pith_number":"pith:NHXAA6UL","schema_version":"1.0","canonical_sha256":"69ee007a8b06d79a0d228eda7ba2ee757cdc39020b8416b1c73dc6b17328cd00","source":{"kind":"arxiv","id":"2202.06768","version":2},"attestation_state":"computed","paper":{"title":"Probabilistic Embeddings Revisited","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ivan Karpukhin, Sergey Kolesnikov, Stanislav Dereka","submitted_at":"2022-02-14T14:37:54Z","abstract_excerpt":"In recent years, deep metric learning and its probabilistic extensions claimed state-of-the-art results in the face verification task. Despite improvements in face verification, probabilistic methods received little attention in the research community and practical applications. In this paper, we, for the first time, perform an in-depth analysis of known probabilistic methods in verification and retrieval tasks. We study different design choices and propose a simple extension, achieving new state-of-the-art results among probabilistic methods. Finally, we study confidence prediction and show t"},"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":"2202.06768","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-02-14T14:37:54Z","cross_cats_sorted":[],"title_canon_sha256":"55a53e7ef211c90e20a3c26ba0fea44e7b56820f2422f05d34848fbfa435a11d","abstract_canon_sha256":"1a3312d57edd8b52e5857e599ff848494c67d4eab5f697b7353c28094953941b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:14:56.410697Z","signature_b64":"QjOoUtytAQWpVdGcYL+WHlOHJH67z+VOWQSje0OpRCnsa2cAdg5/0JHzdaMKSO+e+nbuUsdRss/++7LUsItbAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"69ee007a8b06d79a0d228eda7ba2ee757cdc39020b8416b1c73dc6b17328cd00","last_reissued_at":"2026-07-05T05:14:56.410208Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:14:56.410208Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Probabilistic Embeddings Revisited","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ivan Karpukhin, Sergey Kolesnikov, Stanislav Dereka","submitted_at":"2022-02-14T14:37:54Z","abstract_excerpt":"In recent years, deep metric learning and its probabilistic extensions claimed state-of-the-art results in the face verification task. Despite improvements in face verification, probabilistic methods received little attention in the research community and practical applications. In this paper, we, for the first time, perform an in-depth analysis of known probabilistic methods in verification and retrieval tasks. We study different design choices and propose a simple extension, achieving new state-of-the-art results among probabilistic methods. Finally, we study confidence prediction and show t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.06768","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/2202.06768/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":"2202.06768","created_at":"2026-07-05T05:14:56.410271+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.06768v2","created_at":"2026-07-05T05:14:56.410271+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.06768","created_at":"2026-07-05T05:14:56.410271+00:00"},{"alias_kind":"pith_short_12","alias_value":"NHXAA6ULA3LZ","created_at":"2026-07-05T05:14:56.410271+00:00"},{"alias_kind":"pith_short_16","alias_value":"NHXAA6ULA3LZUDJC","created_at":"2026-07-05T05:14:56.410271+00:00"},{"alias_kind":"pith_short_8","alias_value":"NHXAA6UL","created_at":"2026-07-05T05:14:56.410271+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03069","citing_title":"ROBUST-WT: Robust Uncertainty-aware Segmentation Transform via Whitening and Training Enhancements","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NHXAA6ULA3LZUDJCR3NHXIXOOV","json":"https://pith.science/pith/NHXAA6ULA3LZUDJCR3NHXIXOOV.json","graph_json":"https://pith.science/api/pith-number/NHXAA6ULA3LZUDJCR3NHXIXOOV/graph.json","events_json":"https://pith.science/api/pith-number/NHXAA6ULA3LZUDJCR3NHXIXOOV/events.json","paper":"https://pith.science/paper/NHXAA6UL"},"agent_actions":{"view_html":"https://pith.science/pith/NHXAA6ULA3LZUDJCR3NHXIXOOV","download_json":"https://pith.science/pith/NHXAA6ULA3LZUDJCR3NHXIXOOV.json","view_paper":"https://pith.science/paper/NHXAA6UL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.06768&json=true","fetch_graph":"https://pith.science/api/pith-number/NHXAA6ULA3LZUDJCR3NHXIXOOV/graph.json","fetch_events":"https://pith.science/api/pith-number/NHXAA6ULA3LZUDJCR3NHXIXOOV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NHXAA6ULA3LZUDJCR3NHXIXOOV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NHXAA6ULA3LZUDJCR3NHXIXOOV/action/storage_attestation","attest_author":"https://pith.science/pith/NHXAA6ULA3LZUDJCR3NHXIXOOV/action/author_attestation","sign_citation":"https://pith.science/pith/NHXAA6ULA3LZUDJCR3NHXIXOOV/action/citation_signature","submit_replication":"https://pith.science/pith/NHXAA6ULA3LZUDJCR3NHXIXOOV/action/replication_record"}},"created_at":"2026-07-05T05:14:56.410271+00:00","updated_at":"2026-07-05T05:14:56.410271+00:00"}