{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:BOPHZUGC742TIKANLTWQNTTFSF","short_pith_number":"pith:BOPHZUGC","canonical_record":{"source":{"id":"1712.03162","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-12-08T16:32:56Z","cross_cats_sorted":[],"title_canon_sha256":"f0ed5c4a94575e2d32629f6af5e59fbdd7ed050580c33172b1ef5d74765efa40","abstract_canon_sha256":"f936a239f33d882aa3480c8737f615d38a42a8622ca4d9dc39b2d7b8cab0f2d9"},"schema_version":"1.0"},"canonical_sha256":"0b9e7cd0c2ff3534280d5ced06ce65916d655aec1335f44e3e6345fcc872d9f3","source":{"kind":"arxiv","id":"1712.03162","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.03162","created_at":"2026-05-18T00:28:28Z"},{"alias_kind":"arxiv_version","alias_value":"1712.03162v1","created_at":"2026-05-18T00:28:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.03162","created_at":"2026-05-18T00:28:28Z"},{"alias_kind":"pith_short_12","alias_value":"BOPHZUGC742T","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_16","alias_value":"BOPHZUGC742TIKAN","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_8","alias_value":"BOPHZUGC","created_at":"2026-05-18T12:31:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:BOPHZUGC742TIKANLTWQNTTFSF","target":"record","payload":{"canonical_record":{"source":{"id":"1712.03162","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-12-08T16:32:56Z","cross_cats_sorted":[],"title_canon_sha256":"f0ed5c4a94575e2d32629f6af5e59fbdd7ed050580c33172b1ef5d74765efa40","abstract_canon_sha256":"f936a239f33d882aa3480c8737f615d38a42a8622ca4d9dc39b2d7b8cab0f2d9"},"schema_version":"1.0"},"canonical_sha256":"0b9e7cd0c2ff3534280d5ced06ce65916d655aec1335f44e3e6345fcc872d9f3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:28:28.168727Z","signature_b64":"D2dlELLvbzae81Fgb2WzcaSCWXqQqe1EeRjv7aF6Em9MjUJ2mzBuAz2zF3m3PmF5B1tK3S5drPKpxvZKf6wtDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0b9e7cd0c2ff3534280d5ced06ce65916d655aec1335f44e3e6345fcc872d9f3","last_reissued_at":"2026-05-18T00:28:28.168059Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:28:28.168059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1712.03162","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":"2026-05-18T00:28:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OmPYQwtEVtC7v2UVFQUpvrKjrGXX8V/tYqWt5U/nx8uuP1dvHxC5elyJbWzeBl4sTtbsV7xQULzfrMMXAP9sDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T10:40:50.778239Z"},"content_sha256":"389bef35684f67662451815782f6c366662e18afdf00a20e15444f06edf60384","schema_version":"1.0","event_id":"sha256:389bef35684f67662451815782f6c366662e18afdf00a20e15444f06edf60384"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:BOPHZUGC742TIKANLTWQNTTFSF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Class Rectification Hard Mining for Imbalanced Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Qi Dong, Shaogang Gong, Xiatian Zhu","submitted_at":"2017-12-08T16:32:56Z","abstract_excerpt":"Recognising detailed facial or clothing attributes in images of people is a challenging task for computer vision, especially when the training data are both in very large scale and extremely imbalanced among different attribute classes. To address this problem, we formulate a novel scheme for batch incremental hard sample mining of minority attribute classes from imbalanced large scale training data. We develop an end-to-end deep learning framework capable of avoiding the dominant effect of majority classes by discovering sparsely sampled boundaries of minority classes. This is made possible b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.03162","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":"2026-05-18T00:28:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qSJdMjSKxNTxvx+8/R8C0nLZ9Mg4xddVSLZZnuoS1MfeHiLbJvqtsEETi8ix6tFcz5cGsYa3MR7BEieFoGuBAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T10:40:50.778944Z"},"content_sha256":"d3a18ddbf64a7198fb19dd58e04763d37ea7322c1de738d17be0036c07a64887","schema_version":"1.0","event_id":"sha256:d3a18ddbf64a7198fb19dd58e04763d37ea7322c1de738d17be0036c07a64887"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BOPHZUGC742TIKANLTWQNTTFSF/bundle.json","state_url":"https://pith.science/pith/BOPHZUGC742TIKANLTWQNTTFSF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BOPHZUGC742TIKANLTWQNTTFSF/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":"2026-05-31T10:40:50Z","links":{"resolver":"https://pith.science/pith/BOPHZUGC742TIKANLTWQNTTFSF","bundle":"https://pith.science/pith/BOPHZUGC742TIKANLTWQNTTFSF/bundle.json","state":"https://pith.science/pith/BOPHZUGC742TIKANLTWQNTTFSF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BOPHZUGC742TIKANLTWQNTTFSF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:BOPHZUGC742TIKANLTWQNTTFSF","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":"f936a239f33d882aa3480c8737f615d38a42a8622ca4d9dc39b2d7b8cab0f2d9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-12-08T16:32:56Z","title_canon_sha256":"f0ed5c4a94575e2d32629f6af5e59fbdd7ed050580c33172b1ef5d74765efa40"},"schema_version":"1.0","source":{"id":"1712.03162","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.03162","created_at":"2026-05-18T00:28:28Z"},{"alias_kind":"arxiv_version","alias_value":"1712.03162v1","created_at":"2026-05-18T00:28:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.03162","created_at":"2026-05-18T00:28:28Z"},{"alias_kind":"pith_short_12","alias_value":"BOPHZUGC742T","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_16","alias_value":"BOPHZUGC742TIKAN","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_8","alias_value":"BOPHZUGC","created_at":"2026-05-18T12:31:08Z"}],"graph_snapshots":[{"event_id":"sha256:d3a18ddbf64a7198fb19dd58e04763d37ea7322c1de738d17be0036c07a64887","target":"graph","created_at":"2026-05-18T00:28:28Z","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":"Recognising detailed facial or clothing attributes in images of people is a challenging task for computer vision, especially when the training data are both in very large scale and extremely imbalanced among different attribute classes. To address this problem, we formulate a novel scheme for batch incremental hard sample mining of minority attribute classes from imbalanced large scale training data. We develop an end-to-end deep learning framework capable of avoiding the dominant effect of majority classes by discovering sparsely sampled boundaries of minority classes. This is made possible b","authors_text":"Qi Dong, Shaogang Gong, Xiatian Zhu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-12-08T16:32:56Z","title":"Class Rectification Hard Mining for Imbalanced Deep Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.03162","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":"sha256:389bef35684f67662451815782f6c366662e18afdf00a20e15444f06edf60384","target":"record","created_at":"2026-05-18T00:28:28Z","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":"f936a239f33d882aa3480c8737f615d38a42a8622ca4d9dc39b2d7b8cab0f2d9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-12-08T16:32:56Z","title_canon_sha256":"f0ed5c4a94575e2d32629f6af5e59fbdd7ed050580c33172b1ef5d74765efa40"},"schema_version":"1.0","source":{"id":"1712.03162","kind":"arxiv","version":1}},"canonical_sha256":"0b9e7cd0c2ff3534280d5ced06ce65916d655aec1335f44e3e6345fcc872d9f3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0b9e7cd0c2ff3534280d5ced06ce65916d655aec1335f44e3e6345fcc872d9f3","first_computed_at":"2026-05-18T00:28:28.168059Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:28:28.168059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"D2dlELLvbzae81Fgb2WzcaSCWXqQqe1EeRjv7aF6Em9MjUJ2mzBuAz2zF3m3PmF5B1tK3S5drPKpxvZKf6wtDg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:28:28.168727Z","signed_message":"canonical_sha256_bytes"},"source_id":"1712.03162","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:389bef35684f67662451815782f6c366662e18afdf00a20e15444f06edf60384","sha256:d3a18ddbf64a7198fb19dd58e04763d37ea7322c1de738d17be0036c07a64887"],"state_sha256":"4a26fe5093861fd51b680d70ceaabd024feef95f1131e1ed92b3a08b0acf76d8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"17spVT1++5bSrmQU2LNy4sJbyBRZ1xwLD0uGl0yPOyXIVw/pRsVn0ef+d3Lw6lj+ckA6NC9Fs5ZpCyAlKU1xCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T10:40:50.782472Z","bundle_sha256":"31bb3a710f981762fed24c11ac38ef489129b2f31cdbba1494e3d3bd35143858"}}