{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:PYRHPLAAOK2FLHW7EE4S3Y7F2C","short_pith_number":"pith:PYRHPLAA","canonical_record":{"source":{"id":"2302.01332","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-02T18:59:23Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"6ec57669bbb7ce550be1ee7035b759ade4d3925138c024fd365999db59462536","abstract_canon_sha256":"34dafa02af07bbb827dd580f154bfff1fac590feddcdc7ac8b4c9b8cdbaf414f"},"schema_version":"1.0"},"canonical_sha256":"7e2277ac0072b4559edf21392de3e5d0a01419d057b1d3491f99dcd9bced9492","source":{"kind":"arxiv","id":"2302.01332","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.01332","created_at":"2026-07-05T05:38:47Z"},{"alias_kind":"arxiv_version","alias_value":"2302.01332v2","created_at":"2026-07-05T05:38:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.01332","created_at":"2026-07-05T05:38:47Z"},{"alias_kind":"pith_short_12","alias_value":"PYRHPLAAOK2F","created_at":"2026-07-05T05:38:47Z"},{"alias_kind":"pith_short_16","alias_value":"PYRHPLAAOK2FLHW7","created_at":"2026-07-05T05:38:47Z"},{"alias_kind":"pith_short_8","alias_value":"PYRHPLAA","created_at":"2026-07-05T05:38:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:PYRHPLAAOK2FLHW7EE4S3Y7F2C","target":"record","payload":{"canonical_record":{"source":{"id":"2302.01332","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-02T18:59:23Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"6ec57669bbb7ce550be1ee7035b759ade4d3925138c024fd365999db59462536","abstract_canon_sha256":"34dafa02af07bbb827dd580f154bfff1fac590feddcdc7ac8b4c9b8cdbaf414f"},"schema_version":"1.0"},"canonical_sha256":"7e2277ac0072b4559edf21392de3e5d0a01419d057b1d3491f99dcd9bced9492","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:38:47.069535Z","signature_b64":"kjVToCGQXnVb19zgGu/yascxlQXGVY8B7icbdssQj4+lnUUc6iTLShznPhWryunAdr5yKe7fwAMFSzLjA1llBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e2277ac0072b4559edf21392de3e5d0a01419d057b1d3491f99dcd9bced9492","last_reissued_at":"2026-07-05T05:38:47.068919Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:38:47.068919Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.01332","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":"2026-07-05T05:38:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D1tYLoFgWB+DdNzD/QhNkKWfqbOuyuzDKILRetEaikMucHbTM5cLYIYclnXxqy2eSe3Elh+8CW6n4KRnyvDvAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:37:55.325784Z"},"content_sha256":"94ed73d36c610223be7d17f7f281564da9714eea55ac7830840dd04d503ff59e","schema_version":"1.0","event_id":"sha256:94ed73d36c610223be7d17f7f281564da9714eea55ac7830840dd04d503ff59e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:PYRHPLAAOK2FLHW7EE4S3Y7F2C","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bayesian Metric Learning for Uncertainty Quantification in Image Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Frederik Warburg, Marco Miani, Silas Brack, Soren Hauberg","submitted_at":"2023-02-02T18:59:23Z","abstract_excerpt":"We propose the first Bayesian encoder for metric learning. Rather than relying on neural amortization as done in prior works, we learn a distribution over the network weights with the Laplace Approximation. We actualize this by first proving that the contrastive loss is a valid log-posterior. We then propose three methods that ensure a positive definite Hessian. Lastly, we present a novel decomposition of the Generalized Gauss-Newton approximation. Empirically, we show that our Laplacian Metric Learner (LAM) estimates well-calibrated uncertainties, reliably detects out-of-distribution examples"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.01332","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/2302.01332/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":"2026-07-05T05:38:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0K2dOOMqkCg9chq2u+0vkR2R6BBqVHQu4g1MpX8TaExynJfrTQo7rvgOrI16qx+S3mlvuSQWz+cI9sjhg/+fDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:37:55.326163Z"},"content_sha256":"03dcaa26bb65679dfb17c537473dcff9088ab10ab88b88df54d96a5649a16f4a","schema_version":"1.0","event_id":"sha256:03dcaa26bb65679dfb17c537473dcff9088ab10ab88b88df54d96a5649a16f4a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PYRHPLAAOK2FLHW7EE4S3Y7F2C/bundle.json","state_url":"https://pith.science/pith/PYRHPLAAOK2FLHW7EE4S3Y7F2C/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PYRHPLAAOK2FLHW7EE4S3Y7F2C/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":"2026-07-06T18:37:55Z","links":{"resolver":"https://pith.science/pith/PYRHPLAAOK2FLHW7EE4S3Y7F2C","bundle":"https://pith.science/pith/PYRHPLAAOK2FLHW7EE4S3Y7F2C/bundle.json","state":"https://pith.science/pith/PYRHPLAAOK2FLHW7EE4S3Y7F2C/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PYRHPLAAOK2FLHW7EE4S3Y7F2C/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:PYRHPLAAOK2FLHW7EE4S3Y7F2C","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":"34dafa02af07bbb827dd580f154bfff1fac590feddcdc7ac8b4c9b8cdbaf414f","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-02T18:59:23Z","title_canon_sha256":"6ec57669bbb7ce550be1ee7035b759ade4d3925138c024fd365999db59462536"},"schema_version":"1.0","source":{"id":"2302.01332","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.01332","created_at":"2026-07-05T05:38:47Z"},{"alias_kind":"arxiv_version","alias_value":"2302.01332v2","created_at":"2026-07-05T05:38:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.01332","created_at":"2026-07-05T05:38:47Z"},{"alias_kind":"pith_short_12","alias_value":"PYRHPLAAOK2F","created_at":"2026-07-05T05:38:47Z"},{"alias_kind":"pith_short_16","alias_value":"PYRHPLAAOK2FLHW7","created_at":"2026-07-05T05:38:47Z"},{"alias_kind":"pith_short_8","alias_value":"PYRHPLAA","created_at":"2026-07-05T05:38:47Z"}],"graph_snapshots":[{"event_id":"sha256:03dcaa26bb65679dfb17c537473dcff9088ab10ab88b88df54d96a5649a16f4a","target":"graph","created_at":"2026-07-05T05:38:47Z","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/2302.01332/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose the first Bayesian encoder for metric learning. Rather than relying on neural amortization as done in prior works, we learn a distribution over the network weights with the Laplace Approximation. We actualize this by first proving that the contrastive loss is a valid log-posterior. We then propose three methods that ensure a positive definite Hessian. Lastly, we present a novel decomposition of the Generalized Gauss-Newton approximation. Empirically, we show that our Laplacian Metric Learner (LAM) estimates well-calibrated uncertainties, reliably detects out-of-distribution examples","authors_text":"Frederik Warburg, Marco Miani, Silas Brack, Soren Hauberg","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-02T18:59:23Z","title":"Bayesian Metric Learning for Uncertainty Quantification in Image Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.01332","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":"sha256:94ed73d36c610223be7d17f7f281564da9714eea55ac7830840dd04d503ff59e","target":"record","created_at":"2026-07-05T05:38:47Z","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":"34dafa02af07bbb827dd580f154bfff1fac590feddcdc7ac8b4c9b8cdbaf414f","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-02T18:59:23Z","title_canon_sha256":"6ec57669bbb7ce550be1ee7035b759ade4d3925138c024fd365999db59462536"},"schema_version":"1.0","source":{"id":"2302.01332","kind":"arxiv","version":2}},"canonical_sha256":"7e2277ac0072b4559edf21392de3e5d0a01419d057b1d3491f99dcd9bced9492","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7e2277ac0072b4559edf21392de3e5d0a01419d057b1d3491f99dcd9bced9492","first_computed_at":"2026-07-05T05:38:47.068919Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:38:47.068919Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kjVToCGQXnVb19zgGu/yascxlQXGVY8B7icbdssQj4+lnUUc6iTLShznPhWryunAdr5yKe7fwAMFSzLjA1llBg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:38:47.069535Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.01332","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:94ed73d36c610223be7d17f7f281564da9714eea55ac7830840dd04d503ff59e","sha256:03dcaa26bb65679dfb17c537473dcff9088ab10ab88b88df54d96a5649a16f4a"],"state_sha256":"168f795c4a632f2a3a88d953f3876e51ab1e576b1994bce973139a2063dbbdf3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3NKlfbvFUGMaPbxY/+yGHFOpFr81uZ+MQK4NH9hiJC6o+rZNhJ7RGjPnymxcUawFnVDMdZtV3ZuyYv71TudpAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T18:37:55.328132Z","bundle_sha256":"a0a6bca010dfec520ece0fa9f6aec2b704c40ade18a4c93b8c0bff2584bf6141"}}