{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:YZZVZBRA7REFTZE7BWTHK37FAG","short_pith_number":"pith:YZZVZBRA","canonical_record":{"source":{"id":"1512.05227","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-12-16T16:14:22Z","cross_cats_sorted":[],"title_canon_sha256":"1daa6017b5698e10a49de249b8ac559d87ac0d600da427339593728481ab4918","abstract_canon_sha256":"64f1708c618dfc5019f365ad0c32de46ff21e5cdd231b648cb79ab309ba4dbb0"},"schema_version":"1.0"},"canonical_sha256":"c6735c8620fc4859e49f0da6756fe501afcbaab43d9d9c093a352366b74b1863","source":{"kind":"arxiv","id":"1512.05227","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1512.05227","created_at":"2026-05-18T01:17:24Z"},{"alias_kind":"arxiv_version","alias_value":"1512.05227v2","created_at":"2026-05-18T01:17:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1512.05227","created_at":"2026-05-18T01:17:24Z"},{"alias_kind":"pith_short_12","alias_value":"YZZVZBRA7REF","created_at":"2026-05-18T12:29:52Z"},{"alias_kind":"pith_short_16","alias_value":"YZZVZBRA7REFTZE7","created_at":"2026-05-18T12:29:52Z"},{"alias_kind":"pith_short_8","alias_value":"YZZVZBRA","created_at":"2026-05-18T12:29:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:YZZVZBRA7REFTZE7BWTHK37FAG","target":"record","payload":{"canonical_record":{"source":{"id":"1512.05227","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-12-16T16:14:22Z","cross_cats_sorted":[],"title_canon_sha256":"1daa6017b5698e10a49de249b8ac559d87ac0d600da427339593728481ab4918","abstract_canon_sha256":"64f1708c618dfc5019f365ad0c32de46ff21e5cdd231b648cb79ab309ba4dbb0"},"schema_version":"1.0"},"canonical_sha256":"c6735c8620fc4859e49f0da6756fe501afcbaab43d9d9c093a352366b74b1863","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:17:24.852496Z","signature_b64":"FSbbct1CCpHfoV4vJDszS5wigN0/L0HvEokEu23xW1CGjS7s+/Ohsb82H1c7eoC9/kpMBoNG3wTuOlD7cUtnDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6735c8620fc4859e49f0da6756fe501afcbaab43d9d9c093a352366b74b1863","last_reissued_at":"2026-05-18T01:17:24.851898Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:17:24.851898Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1512.05227","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:17:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kSy19maSuAVjkj4iZAH3phmy01sz74YFEqtDId0/VROwMOeVgiDZaaRGHc31zblSsTL2cZbNdfq/EBiXKdbQDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T19:24:57.839458Z"},"content_sha256":"b59382ab30e66298248ec9965a1fa6da8486aa169c30ad3f1ca5d9c8c3c985b2","schema_version":"1.0","event_id":"sha256:b59382ab30e66298248ec9965a1fa6da8486aa169c30ad3f1ca5d9c8c3c985b2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:YZZVZBRA7REFTZE7BWTHK37FAG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fine-grained Categorization and Dataset Bootstrapping using Deep Metric Learning with Humans in the Loop","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feng Zhou, Serge Belongie, Yin Cui, Yuanqing Lin","submitted_at":"2015-12-16T16:14:22Z","abstract_excerpt":"Existing fine-grained visual categorization methods often suffer from three challenges: lack of training data, large number of fine-grained categories, and high intraclass vs. low inter-class variance. In this work we propose a generic iterative framework for fine-grained categorization and dataset bootstrapping that handles these three challenges. Using deep metric learning with humans in the loop, we learn a low dimensional feature embedding with anchor points on manifolds for each category. These anchor points capture intra-class variances and remain discriminative between classes. In each "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1512.05227","kind":"arxiv","version":2},"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":"2026-05-18T01:17:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y/shkJ0OiwnBCIlmiR/vwIljkptNNZ4FSOc1w+ZIppk+JuodPoqt7MxOpuoFE96/HdM05hmbLSfup+y+7IPZCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T19:24:57.839795Z"},"content_sha256":"7a37ae8636a2e0d094a195d43309e56d093fae154ee059c02fd8c3eb40770a7e","schema_version":"1.0","event_id":"sha256:7a37ae8636a2e0d094a195d43309e56d093fae154ee059c02fd8c3eb40770a7e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YZZVZBRA7REFTZE7BWTHK37FAG/bundle.json","state_url":"https://pith.science/pith/YZZVZBRA7REFTZE7BWTHK37FAG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YZZVZBRA7REFTZE7BWTHK37FAG/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":"2026-05-30T19:24:57Z","links":{"resolver":"https://pith.science/pith/YZZVZBRA7REFTZE7BWTHK37FAG","bundle":"https://pith.science/pith/YZZVZBRA7REFTZE7BWTHK37FAG/bundle.json","state":"https://pith.science/pith/YZZVZBRA7REFTZE7BWTHK37FAG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YZZVZBRA7REFTZE7BWTHK37FAG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:YZZVZBRA7REFTZE7BWTHK37FAG","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":"64f1708c618dfc5019f365ad0c32de46ff21e5cdd231b648cb79ab309ba4dbb0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-12-16T16:14:22Z","title_canon_sha256":"1daa6017b5698e10a49de249b8ac559d87ac0d600da427339593728481ab4918"},"schema_version":"1.0","source":{"id":"1512.05227","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1512.05227","created_at":"2026-05-18T01:17:24Z"},{"alias_kind":"arxiv_version","alias_value":"1512.05227v2","created_at":"2026-05-18T01:17:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1512.05227","created_at":"2026-05-18T01:17:24Z"},{"alias_kind":"pith_short_12","alias_value":"YZZVZBRA7REF","created_at":"2026-05-18T12:29:52Z"},{"alias_kind":"pith_short_16","alias_value":"YZZVZBRA7REFTZE7","created_at":"2026-05-18T12:29:52Z"},{"alias_kind":"pith_short_8","alias_value":"YZZVZBRA","created_at":"2026-05-18T12:29:52Z"}],"graph_snapshots":[{"event_id":"sha256:7a37ae8636a2e0d094a195d43309e56d093fae154ee059c02fd8c3eb40770a7e","target":"graph","created_at":"2026-05-18T01:17:24Z","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":"Existing fine-grained visual categorization methods often suffer from three challenges: lack of training data, large number of fine-grained categories, and high intraclass vs. low inter-class variance. In this work we propose a generic iterative framework for fine-grained categorization and dataset bootstrapping that handles these three challenges. Using deep metric learning with humans in the loop, we learn a low dimensional feature embedding with anchor points on manifolds for each category. These anchor points capture intra-class variances and remain discriminative between classes. In each ","authors_text":"Feng Zhou, Serge Belongie, Yin Cui, Yuanqing Lin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-12-16T16:14:22Z","title":"Fine-grained Categorization and Dataset Bootstrapping using Deep Metric Learning with Humans in the Loop"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1512.05227","kind":"arxiv","version":2},"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:b59382ab30e66298248ec9965a1fa6da8486aa169c30ad3f1ca5d9c8c3c985b2","target":"record","created_at":"2026-05-18T01:17:24Z","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":"64f1708c618dfc5019f365ad0c32de46ff21e5cdd231b648cb79ab309ba4dbb0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-12-16T16:14:22Z","title_canon_sha256":"1daa6017b5698e10a49de249b8ac559d87ac0d600da427339593728481ab4918"},"schema_version":"1.0","source":{"id":"1512.05227","kind":"arxiv","version":2}},"canonical_sha256":"c6735c8620fc4859e49f0da6756fe501afcbaab43d9d9c093a352366b74b1863","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c6735c8620fc4859e49f0da6756fe501afcbaab43d9d9c093a352366b74b1863","first_computed_at":"2026-05-18T01:17:24.851898Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:17:24.851898Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FSbbct1CCpHfoV4vJDszS5wigN0/L0HvEokEu23xW1CGjS7s+/Ohsb82H1c7eoC9/kpMBoNG3wTuOlD7cUtnDw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:17:24.852496Z","signed_message":"canonical_sha256_bytes"},"source_id":"1512.05227","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b59382ab30e66298248ec9965a1fa6da8486aa169c30ad3f1ca5d9c8c3c985b2","sha256:7a37ae8636a2e0d094a195d43309e56d093fae154ee059c02fd8c3eb40770a7e"],"state_sha256":"96d97b6cf80c19f2793d52b6cefb0aebb31420980dccfcd9db148a02a7d912d4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7aIkA/IAPeWgew/Jlthv+R6ed1wX0/ezaVR/N2GehtmsGSdZU5On734RurmK+kajBIEcHDwBgFsE/CuJSh2UDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T19:24:57.841729Z","bundle_sha256":"cb0d62eb1b38653f0ff0a1d6f9472bb6fe5750fdd349faffcaa07322aee319c3"}}