{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:23AWN7LFZBJVBL6UAS7CGSUTVS","short_pith_number":"pith:23AWN7LF","canonical_record":{"source":{"id":"2210.04402","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-10T02:24:21Z","cross_cats_sorted":[],"title_canon_sha256":"27caf36ff6f8f9e9f7389e4d48ea11ae76e1a09e4d2a233cbfdbadb1c923fd74","abstract_canon_sha256":"e478cdb0cd8c7d37a5c9f4ffacd0894bb6a636473da6c216d555dfae3f199048"},"schema_version":"1.0"},"canonical_sha256":"d6c166fd65c85350afd404be234a93ac8ad126d387f136f4b8d3f54870889482","source":{"kind":"arxiv","id":"2210.04402","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.04402","created_at":"2026-07-05T05:13:38Z"},{"alias_kind":"arxiv_version","alias_value":"2210.04402v2","created_at":"2026-07-05T05:13:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.04402","created_at":"2026-07-05T05:13:38Z"},{"alias_kind":"pith_short_12","alias_value":"23AWN7LFZBJV","created_at":"2026-07-05T05:13:38Z"},{"alias_kind":"pith_short_16","alias_value":"23AWN7LFZBJVBL6U","created_at":"2026-07-05T05:13:38Z"},{"alias_kind":"pith_short_8","alias_value":"23AWN7LF","created_at":"2026-07-05T05:13:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:23AWN7LFZBJVBL6UAS7CGSUTVS","target":"record","payload":{"canonical_record":{"source":{"id":"2210.04402","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-10T02:24:21Z","cross_cats_sorted":[],"title_canon_sha256":"27caf36ff6f8f9e9f7389e4d48ea11ae76e1a09e4d2a233cbfdbadb1c923fd74","abstract_canon_sha256":"e478cdb0cd8c7d37a5c9f4ffacd0894bb6a636473da6c216d555dfae3f199048"},"schema_version":"1.0"},"canonical_sha256":"d6c166fd65c85350afd404be234a93ac8ad126d387f136f4b8d3f54870889482","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:13:38.599997Z","signature_b64":"n3ZUOL1uQJ9PVTnvQ7LqNhaM9U8cVp9cRzcrzwISCG3tVKdt+zwQRVUizgZDVJInFgR2tgKwht7QpHd3SCNdCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d6c166fd65c85350afd404be234a93ac8ad126d387f136f4b8d3f54870889482","last_reissued_at":"2026-07-05T05:13:38.599509Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:13:38.599509Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.04402","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:13:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PQYhjgUXswQFBj3rNPSrApF55AYv76LM1Wia4nWDmmcxYx/v/1XtdIo3inTYuwemCgO0WUlyDGY11sk07k/EDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T19:09:59.356770Z"},"content_sha256":"9e05d40b220f2bd17d81a945a056539b962aaad38b85439b4ffe8522e7c1fbb9","schema_version":"1.0","event_id":"sha256:9e05d40b220f2bd17d81a945a056539b962aaad38b85439b4ffe8522e7c1fbb9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:23AWN7LFZBJVBL6UAS7CGSUTVS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Contrastive Bayesian Analysis for Deep Metric Learning","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Shichao Kan, Vladimir Mladenovic, Yang Li, Yigang Cen, Zhihai He, Zhiquan He","submitted_at":"2022-10-10T02:24:21Z","abstract_excerpt":"Recent methods for deep metric learning have been focusing on designing different contrastive loss functions between positive and negative pairs of samples so that the learned feature embedding is able to pull positive samples of the same class closer and push negative samples from different classes away from each other. In this work, we recognize that there is a significant semantic gap between features at the intermediate feature layer and class labels at the final output layer. To bridge this gap, we develop a contrastive Bayesian analysis to characterize and model the posterior probabiliti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.04402","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/2210.04402/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:13:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m+czF7jo7aWuqNLdwDy85coKBwLqhiwz7TZqgOPNemFWV1AcQIBbF3IhcnRPsd4mk5GZefhhOnbUXToeMJOGCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T19:09:59.357056Z"},"content_sha256":"c69fe3644ad43106c5c763fcf5ea007ebb3c71022d035a03d5609844b7d6f427","schema_version":"1.0","event_id":"sha256:c69fe3644ad43106c5c763fcf5ea007ebb3c71022d035a03d5609844b7d6f427"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/23AWN7LFZBJVBL6UAS7CGSUTVS/bundle.json","state_url":"https://pith.science/pith/23AWN7LFZBJVBL6UAS7CGSUTVS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/23AWN7LFZBJVBL6UAS7CGSUTVS/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":"2026-07-31T19:09:59Z","links":{"resolver":"https://pith.science/pith/23AWN7LFZBJVBL6UAS7CGSUTVS","bundle":"https://pith.science/pith/23AWN7LFZBJVBL6UAS7CGSUTVS/bundle.json","state":"https://pith.science/pith/23AWN7LFZBJVBL6UAS7CGSUTVS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/23AWN7LFZBJVBL6UAS7CGSUTVS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:23AWN7LFZBJVBL6UAS7CGSUTVS","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":"e478cdb0cd8c7d37a5c9f4ffacd0894bb6a636473da6c216d555dfae3f199048","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-10T02:24:21Z","title_canon_sha256":"27caf36ff6f8f9e9f7389e4d48ea11ae76e1a09e4d2a233cbfdbadb1c923fd74"},"schema_version":"1.0","source":{"id":"2210.04402","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.04402","created_at":"2026-07-05T05:13:38Z"},{"alias_kind":"arxiv_version","alias_value":"2210.04402v2","created_at":"2026-07-05T05:13:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.04402","created_at":"2026-07-05T05:13:38Z"},{"alias_kind":"pith_short_12","alias_value":"23AWN7LFZBJV","created_at":"2026-07-05T05:13:38Z"},{"alias_kind":"pith_short_16","alias_value":"23AWN7LFZBJVBL6U","created_at":"2026-07-05T05:13:38Z"},{"alias_kind":"pith_short_8","alias_value":"23AWN7LF","created_at":"2026-07-05T05:13:38Z"}],"graph_snapshots":[{"event_id":"sha256:c69fe3644ad43106c5c763fcf5ea007ebb3c71022d035a03d5609844b7d6f427","target":"graph","created_at":"2026-07-05T05:13:38Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2210.04402/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent methods for deep metric learning have been focusing on designing different contrastive loss functions between positive and negative pairs of samples so that the learned feature embedding is able to pull positive samples of the same class closer and push negative samples from different classes away from each other. In this work, we recognize that there is a significant semantic gap between features at the intermediate feature layer and class labels at the final output layer. To bridge this gap, we develop a contrastive Bayesian analysis to characterize and model the posterior probabiliti","authors_text":"Shichao Kan, Vladimir Mladenovic, Yang Li, Yigang Cen, Zhihai He, Zhiquan He","cross_cats":[],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-10T02:24:21Z","title":"Contrastive Bayesian Analysis for Deep Metric Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.04402","kind":"arxiv","version":2},"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":"sha256:9e05d40b220f2bd17d81a945a056539b962aaad38b85439b4ffe8522e7c1fbb9","target":"record","created_at":"2026-07-05T05:13:38Z","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":"e478cdb0cd8c7d37a5c9f4ffacd0894bb6a636473da6c216d555dfae3f199048","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-10T02:24:21Z","title_canon_sha256":"27caf36ff6f8f9e9f7389e4d48ea11ae76e1a09e4d2a233cbfdbadb1c923fd74"},"schema_version":"1.0","source":{"id":"2210.04402","kind":"arxiv","version":2}},"canonical_sha256":"d6c166fd65c85350afd404be234a93ac8ad126d387f136f4b8d3f54870889482","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d6c166fd65c85350afd404be234a93ac8ad126d387f136f4b8d3f54870889482","first_computed_at":"2026-07-05T05:13:38.599509Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:13:38.599509Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"n3ZUOL1uQJ9PVTnvQ7LqNhaM9U8cVp9cRzcrzwISCG3tVKdt+zwQRVUizgZDVJInFgR2tgKwht7QpHd3SCNdCA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:13:38.599997Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.04402","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9e05d40b220f2bd17d81a945a056539b962aaad38b85439b4ffe8522e7c1fbb9","sha256:c69fe3644ad43106c5c763fcf5ea007ebb3c71022d035a03d5609844b7d6f427"],"state_sha256":"644ff5ad36b911ba5ced059ffd82a822bfeb9f3c4b085acc00f50639388c8207"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FXkBurgrPt0xcxZnk1dg1FosooNN99WrBlN3lZaftgT1z/rj8hBQvXgp0CFh1bCioCtYll0K5MTVGeYWEAj3AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T19:09:59.359987Z","bundle_sha256":"edd96f917a3b9e1e06e00be0e32588176a6959e4abb3221854fe8ecb0eab099b"}}