{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ZXRBHVRWTF3LSO3VUVNVU5TDUD","short_pith_number":"pith:ZXRBHVRW","canonical_record":{"source":{"id":"2501.11063","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-19T14:41:55Z","cross_cats_sorted":[],"title_canon_sha256":"5a8d877991879e6387562dca821414cd7577f9f8a65f21c7cb28b16250f539c9","abstract_canon_sha256":"56bc4fcb3dba38d0efef6d384262e2c8552812063c7d872a001a64432a8dcd4f"},"schema_version":"1.0"},"canonical_sha256":"cde213d6369976b93b75a55b5a7663a0d8e373144ba2eea73473c8ea0afdb0cc","source":{"kind":"arxiv","id":"2501.11063","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.11063","created_at":"2026-07-05T10:03:02Z"},{"alias_kind":"arxiv_version","alias_value":"2501.11063v1","created_at":"2026-07-05T10:03:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.11063","created_at":"2026-07-05T10:03:02Z"},{"alias_kind":"pith_short_12","alias_value":"ZXRBHVRWTF3L","created_at":"2026-07-05T10:03:02Z"},{"alias_kind":"pith_short_16","alias_value":"ZXRBHVRWTF3LSO3V","created_at":"2026-07-05T10:03:02Z"},{"alias_kind":"pith_short_8","alias_value":"ZXRBHVRW","created_at":"2026-07-05T10:03:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ZXRBHVRWTF3LSO3VUVNVU5TDUD","target":"record","payload":{"canonical_record":{"source":{"id":"2501.11063","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-19T14:41:55Z","cross_cats_sorted":[],"title_canon_sha256":"5a8d877991879e6387562dca821414cd7577f9f8a65f21c7cb28b16250f539c9","abstract_canon_sha256":"56bc4fcb3dba38d0efef6d384262e2c8552812063c7d872a001a64432a8dcd4f"},"schema_version":"1.0"},"canonical_sha256":"cde213d6369976b93b75a55b5a7663a0d8e373144ba2eea73473c8ea0afdb0cc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:03:02.783733Z","signature_b64":"l8VQZ3IQJOvR2ZXgcgrFo4VP64lXgglbZMFGXxlCYKZXg3rASMaX8wfur8vop3XoUu/M/Aio54A0OoDBJ310Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cde213d6369976b93b75a55b5a7663a0d8e373144ba2eea73473c8ea0afdb0cc","last_reissued_at":"2026-07-05T10:03:02.783340Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:03:02.783340Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.11063","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":"2026-07-05T10:03:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YtKUMknKQVIo+CzJEqN+a1lDtViTKvk20kuAPGrSeXuC+tNHqZy/NQOZVO0p5zQ73lMY6RJucDj4L5ZGQtZ7DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T14:12:09.222323Z"},"content_sha256":"78c6ecf97afce823fd7742303b5427da1901c78220ebbf3b1716f4929d396aba","schema_version":"1.0","event_id":"sha256:78c6ecf97afce823fd7742303b5427da1901c78220ebbf3b1716f4929d396aba"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ZXRBHVRWTF3LSO3VUVNVU5TDUD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Qianqian Xu, Qingming Huang, Yangbangyan Jiang, Yingfei Sun, Zhipeng Yu","submitted_at":"2025-01-19T14:41:55Z","abstract_excerpt":"The existence of noisy labels in real-world data negatively impacts the performance of deep learning models. Although much research effort has been devoted to improving the robustness towards noisy labels in classification tasks, the problem of noisy labels in deep metric learning (DML) remains under-explored. Existing noisy label learning methods designed for DML mainly discard suspicious noisy samples, resulting in a waste of the training data. To address this issue, we propose a noise-robust DML framework with SubGroup-based Positive-pair Selection (SGPS), which constructs reliable positive"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.11063","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/2501.11063/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":"2026-07-05T10:03:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oqQneeX2lnmVl1/uKclBKQyLt4vZ/FX2DCFXU3l5RT1z/J5J+9zegbprSc6BEniht3/ULxDz/FTvom7PAiZ3DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T14:12:09.222854Z"},"content_sha256":"f25e67a6421d2553c1b05101980990b97dbd7e0ab89f6bf75e3c656966010492","schema_version":"1.0","event_id":"sha256:f25e67a6421d2553c1b05101980990b97dbd7e0ab89f6bf75e3c656966010492"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZXRBHVRWTF3LSO3VUVNVU5TDUD/bundle.json","state_url":"https://pith.science/pith/ZXRBHVRWTF3LSO3VUVNVU5TDUD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZXRBHVRWTF3LSO3VUVNVU5TDUD/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":"2026-08-11T14:12:09Z","links":{"resolver":"https://pith.science/pith/ZXRBHVRWTF3LSO3VUVNVU5TDUD","bundle":"https://pith.science/pith/ZXRBHVRWTF3LSO3VUVNVU5TDUD/bundle.json","state":"https://pith.science/pith/ZXRBHVRWTF3LSO3VUVNVU5TDUD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZXRBHVRWTF3LSO3VUVNVU5TDUD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZXRBHVRWTF3LSO3VUVNVU5TDUD","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":"56bc4fcb3dba38d0efef6d384262e2c8552812063c7d872a001a64432a8dcd4f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-19T14:41:55Z","title_canon_sha256":"5a8d877991879e6387562dca821414cd7577f9f8a65f21c7cb28b16250f539c9"},"schema_version":"1.0","source":{"id":"2501.11063","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.11063","created_at":"2026-07-05T10:03:02Z"},{"alias_kind":"arxiv_version","alias_value":"2501.11063v1","created_at":"2026-07-05T10:03:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.11063","created_at":"2026-07-05T10:03:02Z"},{"alias_kind":"pith_short_12","alias_value":"ZXRBHVRWTF3L","created_at":"2026-07-05T10:03:02Z"},{"alias_kind":"pith_short_16","alias_value":"ZXRBHVRWTF3LSO3V","created_at":"2026-07-05T10:03:02Z"},{"alias_kind":"pith_short_8","alias_value":"ZXRBHVRW","created_at":"2026-07-05T10:03:02Z"}],"graph_snapshots":[{"event_id":"sha256:f25e67a6421d2553c1b05101980990b97dbd7e0ab89f6bf75e3c656966010492","target":"graph","created_at":"2026-07-05T10:03:02Z","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/2501.11063/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The existence of noisy labels in real-world data negatively impacts the performance of deep learning models. Although much research effort has been devoted to improving the robustness towards noisy labels in classification tasks, the problem of noisy labels in deep metric learning (DML) remains under-explored. Existing noisy label learning methods designed for DML mainly discard suspicious noisy samples, resulting in a waste of the training data. To address this issue, we propose a noise-robust DML framework with SubGroup-based Positive-pair Selection (SGPS), which constructs reliable positive","authors_text":"Qianqian Xu, Qingming Huang, Yangbangyan Jiang, Yingfei Sun, Zhipeng Yu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-19T14:41:55Z","title":"Enhancing Sample Utilization in Noise-Robust Deep Metric Learning With Subgroup-Based Positive-Pair Selection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.11063","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":"sha256:78c6ecf97afce823fd7742303b5427da1901c78220ebbf3b1716f4929d396aba","target":"record","created_at":"2026-07-05T10:03:02Z","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":"56bc4fcb3dba38d0efef6d384262e2c8552812063c7d872a001a64432a8dcd4f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-19T14:41:55Z","title_canon_sha256":"5a8d877991879e6387562dca821414cd7577f9f8a65f21c7cb28b16250f539c9"},"schema_version":"1.0","source":{"id":"2501.11063","kind":"arxiv","version":1}},"canonical_sha256":"cde213d6369976b93b75a55b5a7663a0d8e373144ba2eea73473c8ea0afdb0cc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cde213d6369976b93b75a55b5a7663a0d8e373144ba2eea73473c8ea0afdb0cc","first_computed_at":"2026-07-05T10:03:02.783340Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:03:02.783340Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"l8VQZ3IQJOvR2ZXgcgrFo4VP64lXgglbZMFGXxlCYKZXg3rASMaX8wfur8vop3XoUu/M/Aio54A0OoDBJ310Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:03:02.783733Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.11063","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:78c6ecf97afce823fd7742303b5427da1901c78220ebbf3b1716f4929d396aba","sha256:f25e67a6421d2553c1b05101980990b97dbd7e0ab89f6bf75e3c656966010492"],"state_sha256":"59e6733bbfc951c9526902ef1e82c9791ebefcd4af87a6038fc9c475d4970775"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E2zs/Hcky/pxiY/1SnifCk7D8xjyW3mKmzzNfw5tA9m+Jio9HmvEpLXT8Wa0BucHwf9nJt8OUKVBBbWKoOuPDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T14:12:09.226421Z","bundle_sha256":"7df944acc2d8266ab842d7ad4569731870f02dbbf951da41cddde6dd36078077"}}