{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:BJJRNUW3TFUSPP376AT5YSUEOJ","short_pith_number":"pith:BJJRNUW3","canonical_record":{"source":{"id":"1811.01459","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-04T23:47:18Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"3c05f7952b0c8c00cd9631e9fb981135cb5f0586131392e1a1476e5a255d2991","abstract_canon_sha256":"39ab215b7769bf11bb7f22d2b0ede55ac48233b444bd2d8acc067adb11058ec1"},"schema_version":"1.0"},"canonical_sha256":"0a5316d2db996927bf7ff027dc4a84726f180fbdce393f90aa356441e1c4d23b","source":{"kind":"arxiv","id":"1811.01459","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.01459","created_at":"2026-07-05T00:23:47Z"},{"alias_kind":"arxiv_version","alias_value":"1811.01459v3","created_at":"2026-07-05T00:23:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.01459","created_at":"2026-07-05T00:23:47Z"},{"alias_kind":"pith_short_12","alias_value":"BJJRNUW3TFUS","created_at":"2026-07-05T00:23:47Z"},{"alias_kind":"pith_short_16","alias_value":"BJJRNUW3TFUSPP37","created_at":"2026-07-05T00:23:47Z"},{"alias_kind":"pith_short_8","alias_value":"BJJRNUW3","created_at":"2026-07-05T00:23:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:BJJRNUW3TFUSPP376AT5YSUEOJ","target":"record","payload":{"canonical_record":{"source":{"id":"1811.01459","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-04T23:47:18Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"3c05f7952b0c8c00cd9631e9fb981135cb5f0586131392e1a1476e5a255d2991","abstract_canon_sha256":"39ab215b7769bf11bb7f22d2b0ede55ac48233b444bd2d8acc067adb11058ec1"},"schema_version":"1.0"},"canonical_sha256":"0a5316d2db996927bf7ff027dc4a84726f180fbdce393f90aa356441e1c4d23b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:23:47.897566Z","signature_b64":"DjmoTvqd5M5qktvMdd8Gv2aKVklIKDF5ENImgq4HSy5qh+XA+MFm5gN6gW8sVZmyctn5G/uE14lzCrjU5eb/DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a5316d2db996927bf7ff027dc4a84726f180fbdce393f90aa356441e1c4d23b","last_reissued_at":"2026-07-05T00:23:47.896981Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:23:47.896981Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.01459","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:23:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mIZg9Q93YbcWjIvQdPpi8whVN6P5rhWq9i9fQWnc4dVkEB1+lr1Sel6+cT2TEReLgNUiWoydVt/sOMCZRfQ/Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T10:38:38.284618Z"},"content_sha256":"1b7e6144e06f151ba1229de7db1d5fd66651f26c7ce5de9a299d6b945e69277a","schema_version":"1.0","event_id":"sha256:1b7e6144e06f151ba1229de7db1d5fd66651f26c7ce5de9a299d6b945e69277a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:BJJRNUW3TFUSPP376AT5YSUEOJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Metric Learning by Online Soft Mining and Class-Aware Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Elyor Kodirov, Guosheng Hu, Neil M. Robertson, Xinshao Wang, Yang Hua","submitted_at":"2018-11-04T23:47:18Z","abstract_excerpt":"Deep metric learning aims to learn a deep embedding that can capture the semantic similarity of data points. Given the availability of massive training samples, deep metric learning is known to suffer from slow convergence due to a large fraction of trivial samples. Therefore, most existing methods generally resort to sample mining strategies for selecting nontrivial samples to accelerate convergence and improve performance. In this work, we identify two critical limitations of the sample mining methods, and provide solutions for both of them. First, previous mining methods assign one binary s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.01459","kind":"arxiv","version":3},"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/1811.01459/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":"2026-07-05T00:23:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sy6Rg8HXZSwQf7VjkT3u5e1okmEVZDBChwoEKszhe0njdbqMXGgS7Y0uBZl1AcZNjEytd6Xx4gzFZ6SRB2ZECA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T10:38:38.285004Z"},"content_sha256":"ce265c45aae771fca889fd3f18707a14090655d9841c6e50b0912ed27a743d47","schema_version":"1.0","event_id":"sha256:ce265c45aae771fca889fd3f18707a14090655d9841c6e50b0912ed27a743d47"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BJJRNUW3TFUSPP376AT5YSUEOJ/bundle.json","state_url":"https://pith.science/pith/BJJRNUW3TFUSPP376AT5YSUEOJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BJJRNUW3TFUSPP376AT5YSUEOJ/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":"2026-07-05T10:38:38Z","links":{"resolver":"https://pith.science/pith/BJJRNUW3TFUSPP376AT5YSUEOJ","bundle":"https://pith.science/pith/BJJRNUW3TFUSPP376AT5YSUEOJ/bundle.json","state":"https://pith.science/pith/BJJRNUW3TFUSPP376AT5YSUEOJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BJJRNUW3TFUSPP376AT5YSUEOJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:BJJRNUW3TFUSPP376AT5YSUEOJ","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":"39ab215b7769bf11bb7f22d2b0ede55ac48233b444bd2d8acc067adb11058ec1","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-04T23:47:18Z","title_canon_sha256":"3c05f7952b0c8c00cd9631e9fb981135cb5f0586131392e1a1476e5a255d2991"},"schema_version":"1.0","source":{"id":"1811.01459","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.01459","created_at":"2026-07-05T00:23:47Z"},{"alias_kind":"arxiv_version","alias_value":"1811.01459v3","created_at":"2026-07-05T00:23:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.01459","created_at":"2026-07-05T00:23:47Z"},{"alias_kind":"pith_short_12","alias_value":"BJJRNUW3TFUS","created_at":"2026-07-05T00:23:47Z"},{"alias_kind":"pith_short_16","alias_value":"BJJRNUW3TFUSPP37","created_at":"2026-07-05T00:23:47Z"},{"alias_kind":"pith_short_8","alias_value":"BJJRNUW3","created_at":"2026-07-05T00:23:47Z"}],"graph_snapshots":[{"event_id":"sha256:ce265c45aae771fca889fd3f18707a14090655d9841c6e50b0912ed27a743d47","target":"graph","created_at":"2026-07-05T00:23:47Z","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/1811.01459/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep metric learning aims to learn a deep embedding that can capture the semantic similarity of data points. Given the availability of massive training samples, deep metric learning is known to suffer from slow convergence due to a large fraction of trivial samples. Therefore, most existing methods generally resort to sample mining strategies for selecting nontrivial samples to accelerate convergence and improve performance. In this work, we identify two critical limitations of the sample mining methods, and provide solutions for both of them. First, previous mining methods assign one binary s","authors_text":"Elyor Kodirov, Guosheng Hu, Neil M. Robertson, Xinshao Wang, Yang Hua","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-04T23:47:18Z","title":"Deep Metric Learning by Online Soft Mining and Class-Aware Attention"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.01459","kind":"arxiv","version":3},"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":"sha256:1b7e6144e06f151ba1229de7db1d5fd66651f26c7ce5de9a299d6b945e69277a","target":"record","created_at":"2026-07-05T00:23:47Z","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":"39ab215b7769bf11bb7f22d2b0ede55ac48233b444bd2d8acc067adb11058ec1","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-04T23:47:18Z","title_canon_sha256":"3c05f7952b0c8c00cd9631e9fb981135cb5f0586131392e1a1476e5a255d2991"},"schema_version":"1.0","source":{"id":"1811.01459","kind":"arxiv","version":3}},"canonical_sha256":"0a5316d2db996927bf7ff027dc4a84726f180fbdce393f90aa356441e1c4d23b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0a5316d2db996927bf7ff027dc4a84726f180fbdce393f90aa356441e1c4d23b","first_computed_at":"2026-07-05T00:23:47.896981Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:23:47.896981Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DjmoTvqd5M5qktvMdd8Gv2aKVklIKDF5ENImgq4HSy5qh+XA+MFm5gN6gW8sVZmyctn5G/uE14lzCrjU5eb/DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:23:47.897566Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.01459","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1b7e6144e06f151ba1229de7db1d5fd66651f26c7ce5de9a299d6b945e69277a","sha256:ce265c45aae771fca889fd3f18707a14090655d9841c6e50b0912ed27a743d47"],"state_sha256":"f303df545d70cadb8ea8ea700613e08ac64e8810a5939fb51548bff4c55f99c2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QpiPo6V2OEN2bTkzb8deD3TgnwN/J3Mj99xll+HQgDaXSH09p2H9kNOaj2fAyf5icmo7EMSMaPydjNGxYhmtAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T10:38:38.287152Z","bundle_sha256":"46cc4b973560016d353fab061a7c8677940750f02cfb6fc46719e1bfd9ecf4bc"}}