{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:YCWDLMVUHLOHIRYYPHJX4N47DY","short_pith_number":"pith:YCWDLMVU","canonical_record":{"source":{"id":"1907.10839","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-07-25T05:02:02Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"bc4429a215752cdb719e50c1654b5e6eedb2d7fea5ebeec75c86171572f0a1d0","abstract_canon_sha256":"9575327351971857a552c0729e37c2d771bdaba4fe134dda62f38778194b1616"},"schema_version":"1.0"},"canonical_sha256":"c0ac35b2b43adc74471879d37e379f1e05bb06f5b70c4ccab368baf2a9d82f77","source":{"kind":"arxiv","id":"1907.10839","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.10839","created_at":"2026-05-17T23:39:34Z"},{"alias_kind":"arxiv_version","alias_value":"1907.10839v1","created_at":"2026-05-17T23:39:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.10839","created_at":"2026-05-17T23:39:34Z"},{"alias_kind":"pith_short_12","alias_value":"YCWDLMVUHLOH","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"YCWDLMVUHLOHIRYY","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"YCWDLMVU","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:YCWDLMVUHLOHIRYYPHJX4N47DY","target":"record","payload":{"canonical_record":{"source":{"id":"1907.10839","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-07-25T05:02:02Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"bc4429a215752cdb719e50c1654b5e6eedb2d7fea5ebeec75c86171572f0a1d0","abstract_canon_sha256":"9575327351971857a552c0729e37c2d771bdaba4fe134dda62f38778194b1616"},"schema_version":"1.0"},"canonical_sha256":"c0ac35b2b43adc74471879d37e379f1e05bb06f5b70c4ccab368baf2a9d82f77","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:34.343355Z","signature_b64":"aMFIxIBYQBLkBkPugY+Tb1sLXeFYqPGt4C/UX7Uc7D2GNcPl6UCBv1D6YUGN4dkuh8L2QdPnDXcQ05V8PeK9Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0ac35b2b43adc74471879d37e379f1e05bb06f5b70c4ccab368baf2a9d82f77","last_reissued_at":"2026-05-17T23:39:34.342822Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:34.342822Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1907.10839","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":"2026-05-17T23:39:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GuLYWEIqM/gPGZuQb1d9zwapd5AEj+vGkS5FbMoaRHE8dB3KwwqTZYaVeQzgyY0+4MlhuT00YzmYZjOZhePmCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T16:08:53.738483Z"},"content_sha256":"9bfb46569dcd3cd7fe414015e497b7b9224385ebf96ff2487a44d9dc83f81b02","schema_version":"1.0","event_id":"sha256:9bfb46569dcd3cd7fe414015e497b7b9224385ebf96ff2487a44d9dc83f81b02"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:YCWDLMVUHLOHIRYYPHJX4N47DY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hard-Aware Fashion Attribute Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Bo Wu, Lingyu Duan, Tao Mei, Wei Zhang, Yixin Li, Yun Ye","submitted_at":"2019-07-25T05:02:02Z","abstract_excerpt":"Fashion attribute classification is of great importance to many high-level tasks such as fashion item search, fashion trend analysis, fashion recommendation, etc. The task is challenging due to the extremely imbalanced data distribution, particularly the attributes with only a few positive samples. In this paper, we introduce a hard-aware pipeline to make full use of \"hard\" samples/attributes. We first propose Hard-Aware BackPropagation (HABP) to efficiently and adaptively focus on training \"hard\" data. Then for the identified hard labels, we propose to synthesize more complementary samples fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.10839","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":""},"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":"2026-05-17T23:39:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ArIui3xCwKJ8LbQZJe0KkeoG7QjN6KGrIsPqwj+SOAC7QBKWfyqvBW2K9v9bQoR7kSzc2YDt2Bm4sr6tS1BMAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T16:08:53.739114Z"},"content_sha256":"6cfc1822d6c59054fea378362502162a4002ae6564313cdbc5d0a09bc63148e5","schema_version":"1.0","event_id":"sha256:6cfc1822d6c59054fea378362502162a4002ae6564313cdbc5d0a09bc63148e5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YCWDLMVUHLOHIRYYPHJX4N47DY/bundle.json","state_url":"https://pith.science/pith/YCWDLMVUHLOHIRYYPHJX4N47DY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YCWDLMVUHLOHIRYYPHJX4N47DY/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":"2026-05-28T16:08:53Z","links":{"resolver":"https://pith.science/pith/YCWDLMVUHLOHIRYYPHJX4N47DY","bundle":"https://pith.science/pith/YCWDLMVUHLOHIRYYPHJX4N47DY/bundle.json","state":"https://pith.science/pith/YCWDLMVUHLOHIRYYPHJX4N47DY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YCWDLMVUHLOHIRYYPHJX4N47DY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:YCWDLMVUHLOHIRYYPHJX4N47DY","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":"9575327351971857a552c0729e37c2d771bdaba4fe134dda62f38778194b1616","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-07-25T05:02:02Z","title_canon_sha256":"bc4429a215752cdb719e50c1654b5e6eedb2d7fea5ebeec75c86171572f0a1d0"},"schema_version":"1.0","source":{"id":"1907.10839","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1907.10839","created_at":"2026-05-17T23:39:34Z"},{"alias_kind":"arxiv_version","alias_value":"1907.10839v1","created_at":"2026-05-17T23:39:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1907.10839","created_at":"2026-05-17T23:39:34Z"},{"alias_kind":"pith_short_12","alias_value":"YCWDLMVUHLOH","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"YCWDLMVUHLOHIRYY","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"YCWDLMVU","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:6cfc1822d6c59054fea378362502162a4002ae6564313cdbc5d0a09bc63148e5","target":"graph","created_at":"2026-05-17T23:39:34Z","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"},"paper":{"abstract_excerpt":"Fashion attribute classification is of great importance to many high-level tasks such as fashion item search, fashion trend analysis, fashion recommendation, etc. The task is challenging due to the extremely imbalanced data distribution, particularly the attributes with only a few positive samples. In this paper, we introduce a hard-aware pipeline to make full use of \"hard\" samples/attributes. We first propose Hard-Aware BackPropagation (HABP) to efficiently and adaptively focus on training \"hard\" data. Then for the identified hard labels, we propose to synthesize more complementary samples fo","authors_text":"Bo Wu, Lingyu Duan, Tao Mei, Wei Zhang, Yixin Li, Yun Ye","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-07-25T05:02:02Z","title":"Hard-Aware Fashion Attribute Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1907.10839","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":"sha256:9bfb46569dcd3cd7fe414015e497b7b9224385ebf96ff2487a44d9dc83f81b02","target":"record","created_at":"2026-05-17T23:39:34Z","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":"9575327351971857a552c0729e37c2d771bdaba4fe134dda62f38778194b1616","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-07-25T05:02:02Z","title_canon_sha256":"bc4429a215752cdb719e50c1654b5e6eedb2d7fea5ebeec75c86171572f0a1d0"},"schema_version":"1.0","source":{"id":"1907.10839","kind":"arxiv","version":1}},"canonical_sha256":"c0ac35b2b43adc74471879d37e379f1e05bb06f5b70c4ccab368baf2a9d82f77","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c0ac35b2b43adc74471879d37e379f1e05bb06f5b70c4ccab368baf2a9d82f77","first_computed_at":"2026-05-17T23:39:34.342822Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:34.342822Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aMFIxIBYQBLkBkPugY+Tb1sLXeFYqPGt4C/UX7Uc7D2GNcPl6UCBv1D6YUGN4dkuh8L2QdPnDXcQ05V8PeK9Dw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:34.343355Z","signed_message":"canonical_sha256_bytes"},"source_id":"1907.10839","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9bfb46569dcd3cd7fe414015e497b7b9224385ebf96ff2487a44d9dc83f81b02","sha256:6cfc1822d6c59054fea378362502162a4002ae6564313cdbc5d0a09bc63148e5"],"state_sha256":"3311d677806876c523164a382bdd8eb5a70ef313f0f91b4327baebc1fbc7b050"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qLn7PkDNMcdfVG6w5FsprFUBG6hVI7I7gxq+AYXT2S4gl7WIGiVjXjxdXgjAV6Uq692Ib4+v2ynvoU3q9nCaDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T16:08:53.742259Z","bundle_sha256":"3558f78ece0e54839c46e2b851dd40e76ca38ff91cc865b543ab2504f06b9a2a"}}