{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:OK7EDLEZDOZL2HVROSLWC4GGW5","short_pith_number":"pith:OK7EDLEZ","canonical_record":{"source":{"id":"2311.00668","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-01T17:17:14Z","cross_cats_sorted":[],"title_canon_sha256":"7b2968b7d444ff6a454e70ae4ffef09fcabc0be2697086167fa382f539de3c6f","abstract_canon_sha256":"1f855b201c59b87eee126de0b51c1edd6f52576911c5d9f37dca792960eae031"},"schema_version":"1.0"},"canonical_sha256":"72be41ac991bb2bd1eb174976170c6b76337ebffea488f4d0f144224d6ff4dfb","source":{"kind":"arxiv","id":"2311.00668","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.00668","created_at":"2026-07-05T07:08:01Z"},{"alias_kind":"arxiv_version","alias_value":"2311.00668v1","created_at":"2026-07-05T07:08:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.00668","created_at":"2026-07-05T07:08:01Z"},{"alias_kind":"pith_short_12","alias_value":"OK7EDLEZDOZL","created_at":"2026-07-05T07:08:01Z"},{"alias_kind":"pith_short_16","alias_value":"OK7EDLEZDOZL2HVR","created_at":"2026-07-05T07:08:01Z"},{"alias_kind":"pith_short_8","alias_value":"OK7EDLEZ","created_at":"2026-07-05T07:08:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:OK7EDLEZDOZL2HVROSLWC4GGW5","target":"record","payload":{"canonical_record":{"source":{"id":"2311.00668","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-01T17:17:14Z","cross_cats_sorted":[],"title_canon_sha256":"7b2968b7d444ff6a454e70ae4ffef09fcabc0be2697086167fa382f539de3c6f","abstract_canon_sha256":"1f855b201c59b87eee126de0b51c1edd6f52576911c5d9f37dca792960eae031"},"schema_version":"1.0"},"canonical_sha256":"72be41ac991bb2bd1eb174976170c6b76337ebffea488f4d0f144224d6ff4dfb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:08:01.451348Z","signature_b64":"kHExaWNAWas3BnrtzEUbvEg2Fk+LMXTAEA3D6jp9mPVRwTqWVYBmHqBYtoEp9IaDVkSeEqQbVrpZDXaxeBvcDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72be41ac991bb2bd1eb174976170c6b76337ebffea488f4d0f144224d6ff4dfb","last_reissued_at":"2026-07-05T07:08:01.450885Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:08:01.450885Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.00668","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:08:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EhysRLZNdEk8bGp7/P7GdHfmcP/sRXPgk1zNH7I/AGrouMVZkY9ACbM+RpwUMrF8VeurQkTi4uWKu6tqD6BIDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T22:57:34.630339Z"},"content_sha256":"1bf5fe2275f758a335f614f4914dab8a04d6046dfe38187b55e7b4db1e7bf48b","schema_version":"1.0","event_id":"sha256:1bf5fe2275f758a335f614f4914dab8a04d6046dfe38187b55e7b4db1e7bf48b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:OK7EDLEZDOZL2HVROSLWC4GGW5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ProcSim: Proxy-based Confidence for Robust Similarity Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Arnab Dhua, Muhammet Bastan, Oriol Barbany, Xiaofan Lin","submitted_at":"2023-11-01T17:17:14Z","abstract_excerpt":"Deep Metric Learning (DML) methods aim at learning an embedding space in which distances are closely related to the inherent semantic similarity of the inputs. Previous studies have shown that popular benchmark datasets often contain numerous wrong labels, and DML methods are susceptible to them. Intending to study the effect of realistic noise, we create an ontology of the classes in a dataset and use it to simulate semantically coherent labeling mistakes. To train robust DML models, we propose ProcSim, a simple framework that assigns a confidence score to each sample using the normalized dis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.00668","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2311.00668/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":"2026-07-05T07:08:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"99LEVHgo6Qs1TckCx4bxgyPBfkCfHFGqtZCLLSTw4r1yWilAxmIFn7EoibwnlVyOopeP9aRl1RscgBN9VdkRCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T22:57:34.630754Z"},"content_sha256":"dca8cab2be858ab9ba579f4169b45112a658fc5b1507a3a21db4b31af9dd8e78","schema_version":"1.0","event_id":"sha256:dca8cab2be858ab9ba579f4169b45112a658fc5b1507a3a21db4b31af9dd8e78"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OK7EDLEZDOZL2HVROSLWC4GGW5/bundle.json","state_url":"https://pith.science/pith/OK7EDLEZDOZL2HVROSLWC4GGW5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OK7EDLEZDOZL2HVROSLWC4GGW5/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":"2026-07-08T22:57:34Z","links":{"resolver":"https://pith.science/pith/OK7EDLEZDOZL2HVROSLWC4GGW5","bundle":"https://pith.science/pith/OK7EDLEZDOZL2HVROSLWC4GGW5/bundle.json","state":"https://pith.science/pith/OK7EDLEZDOZL2HVROSLWC4GGW5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OK7EDLEZDOZL2HVROSLWC4GGW5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:OK7EDLEZDOZL2HVROSLWC4GGW5","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":"1f855b201c59b87eee126de0b51c1edd6f52576911c5d9f37dca792960eae031","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-01T17:17:14Z","title_canon_sha256":"7b2968b7d444ff6a454e70ae4ffef09fcabc0be2697086167fa382f539de3c6f"},"schema_version":"1.0","source":{"id":"2311.00668","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.00668","created_at":"2026-07-05T07:08:01Z"},{"alias_kind":"arxiv_version","alias_value":"2311.00668v1","created_at":"2026-07-05T07:08:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.00668","created_at":"2026-07-05T07:08:01Z"},{"alias_kind":"pith_short_12","alias_value":"OK7EDLEZDOZL","created_at":"2026-07-05T07:08:01Z"},{"alias_kind":"pith_short_16","alias_value":"OK7EDLEZDOZL2HVR","created_at":"2026-07-05T07:08:01Z"},{"alias_kind":"pith_short_8","alias_value":"OK7EDLEZ","created_at":"2026-07-05T07:08:01Z"}],"graph_snapshots":[{"event_id":"sha256:dca8cab2be858ab9ba579f4169b45112a658fc5b1507a3a21db4b31af9dd8e78","target":"graph","created_at":"2026-07-05T07:08:01Z","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/2311.00668/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep Metric Learning (DML) methods aim at learning an embedding space in which distances are closely related to the inherent semantic similarity of the inputs. Previous studies have shown that popular benchmark datasets often contain numerous wrong labels, and DML methods are susceptible to them. Intending to study the effect of realistic noise, we create an ontology of the classes in a dataset and use it to simulate semantically coherent labeling mistakes. To train robust DML models, we propose ProcSim, a simple framework that assigns a confidence score to each sample using the normalized dis","authors_text":"Arnab Dhua, Muhammet Bastan, Oriol Barbany, Xiaofan Lin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-01T17:17:14Z","title":"ProcSim: Proxy-based Confidence for Robust Similarity Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.00668","kind":"arxiv","version":1},"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":"sha256:1bf5fe2275f758a335f614f4914dab8a04d6046dfe38187b55e7b4db1e7bf48b","target":"record","created_at":"2026-07-05T07:08:01Z","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":"1f855b201c59b87eee126de0b51c1edd6f52576911c5d9f37dca792960eae031","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-01T17:17:14Z","title_canon_sha256":"7b2968b7d444ff6a454e70ae4ffef09fcabc0be2697086167fa382f539de3c6f"},"schema_version":"1.0","source":{"id":"2311.00668","kind":"arxiv","version":1}},"canonical_sha256":"72be41ac991bb2bd1eb174976170c6b76337ebffea488f4d0f144224d6ff4dfb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"72be41ac991bb2bd1eb174976170c6b76337ebffea488f4d0f144224d6ff4dfb","first_computed_at":"2026-07-05T07:08:01.450885Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:08:01.450885Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kHExaWNAWas3BnrtzEUbvEg2Fk+LMXTAEA3D6jp9mPVRwTqWVYBmHqBYtoEp9IaDVkSeEqQbVrpZDXaxeBvcDg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:08:01.451348Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.00668","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1bf5fe2275f758a335f614f4914dab8a04d6046dfe38187b55e7b4db1e7bf48b","sha256:dca8cab2be858ab9ba579f4169b45112a658fc5b1507a3a21db4b31af9dd8e78"],"state_sha256":"a518ab663048cd02c26b27c26bcaf9e31ed3066fb201f0fc4473b4cf70274b96"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MsbyxfsInJYbaDBRCalAUydl529hOdswFwZindoaWnphV5cFCgVP44LGvVJ+ASi/ATNNelPXoXftNT6+FHZ/Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T22:57:34.632737Z","bundle_sha256":"de4880e1950f29752f5c50bf10fde5b0fac4c1859b9cf0ad6ced4eb115640850"}}