{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:BE5RFNYKQNF22K6XG6YQIGH4F6","short_pith_number":"pith:BE5RFNYK","canonical_record":{"source":{"id":"1710.00870","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2017-10-02T19:11:58Z","cross_cats_sorted":[],"title_canon_sha256":"5f27a287b9bebdb1f1c26fe75dc9c7f00c08bc44d4bbaa2c96954947e5c819c1","abstract_canon_sha256":"3be2728541bff1248fe66dcf70e967399a97e2444f0f2d4dd8a41b00012b8359"},"schema_version":"1.0"},"canonical_sha256":"093b12b70a834bad2bd737b10418fc2fab7eef7ccf5bc6f4cbc2468c5cda52bd","source":{"kind":"arxiv","id":"1710.00870","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.00870","created_at":"2026-05-18T00:31:50Z"},{"alias_kind":"arxiv_version","alias_value":"1710.00870v2","created_at":"2026-05-18T00:31:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.00870","created_at":"2026-05-18T00:31:50Z"},{"alias_kind":"pith_short_12","alias_value":"BE5RFNYKQNF2","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_16","alias_value":"BE5RFNYKQNF22K6X","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_8","alias_value":"BE5RFNYK","created_at":"2026-05-18T12:31:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:BE5RFNYKQNF22K6XG6YQIGH4F6","target":"record","payload":{"canonical_record":{"source":{"id":"1710.00870","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2017-10-02T19:11:58Z","cross_cats_sorted":[],"title_canon_sha256":"5f27a287b9bebdb1f1c26fe75dc9c7f00c08bc44d4bbaa2c96954947e5c819c1","abstract_canon_sha256":"3be2728541bff1248fe66dcf70e967399a97e2444f0f2d4dd8a41b00012b8359"},"schema_version":"1.0"},"canonical_sha256":"093b12b70a834bad2bd737b10418fc2fab7eef7ccf5bc6f4cbc2468c5cda52bd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:31:50.312144Z","signature_b64":"OBYQm8ve/9c/H9WufjRrADbM36OpsSaf/lxhdMx7SoUyFTYxydyS6EZD50v0sQd+Oz96LAuWAGo2oHZK4h2TCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"093b12b70a834bad2bd737b10418fc2fab7eef7ccf5bc6f4cbc2468c5cda52bd","last_reissued_at":"2026-05-18T00:31:50.311428Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:31:50.311428Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1710.00870","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":"2026-05-18T00:31:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2a2nhqVgWIH7YW+k8+4vzsCuRrD2Ff7Gk7LT3cNZKoqXViCqw7CjVQTu7/kLdjDeDqAr1xH1l2GC+jo8MAeXAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T22:30:17.643902Z"},"content_sha256":"c469cdeaa5e544baee814c5479d62165d24fb07b1fd3fef4fbe89e2c70107a2c","schema_version":"1.0","event_id":"sha256:c469cdeaa5e544baee814c5479d62165d24fb07b1fd3fef4fbe89e2c70107a2c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:BE5RFNYKQNF22K6XG6YQIGH4F6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Rethinking Feature Discrimination and Polymerization for Large-scale Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongyang Li, Xiaogang Wang, Yu Liu","submitted_at":"2017-10-02T19:11:58Z","abstract_excerpt":"Feature matters. How to train a deep network to acquire discriminative features across categories and polymerized features within classes has always been at the core of many computer vision tasks, specially for large-scale recognition systems where test identities are unseen during training and the number of classes could be at million scale. In this paper, we address this problem based on the simple intuition that the cosine distance of features in high-dimensional space should be close enough within one class and far away across categories. To this end, we proposed the congenerous cosine (CO"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.00870","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":"2026-05-18T00:31:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0xcprp1zg+ZFY4GLcYgr+7SnD5LRJVVXYGfrm3RSpj89f9UDjy3GhKhIo6HkORRt+OD2+WwjGIwAfVrROZ+wBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-29T22:30:17.644676Z"},"content_sha256":"9d0c72979438aa48ae558abc3dc7e4f42896f23e4cd385bc76657dabca5ff0e1","schema_version":"1.0","event_id":"sha256:9d0c72979438aa48ae558abc3dc7e4f42896f23e4cd385bc76657dabca5ff0e1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BE5RFNYKQNF22K6XG6YQIGH4F6/bundle.json","state_url":"https://pith.science/pith/BE5RFNYKQNF22K6XG6YQIGH4F6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BE5RFNYKQNF22K6XG6YQIGH4F6/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":"2026-05-29T22:30:17Z","links":{"resolver":"https://pith.science/pith/BE5RFNYKQNF22K6XG6YQIGH4F6","bundle":"https://pith.science/pith/BE5RFNYKQNF22K6XG6YQIGH4F6/bundle.json","state":"https://pith.science/pith/BE5RFNYKQNF22K6XG6YQIGH4F6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BE5RFNYKQNF22K6XG6YQIGH4F6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:BE5RFNYKQNF22K6XG6YQIGH4F6","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":"3be2728541bff1248fe66dcf70e967399a97e2444f0f2d4dd8a41b00012b8359","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2017-10-02T19:11:58Z","title_canon_sha256":"5f27a287b9bebdb1f1c26fe75dc9c7f00c08bc44d4bbaa2c96954947e5c819c1"},"schema_version":"1.0","source":{"id":"1710.00870","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.00870","created_at":"2026-05-18T00:31:50Z"},{"alias_kind":"arxiv_version","alias_value":"1710.00870v2","created_at":"2026-05-18T00:31:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.00870","created_at":"2026-05-18T00:31:50Z"},{"alias_kind":"pith_short_12","alias_value":"BE5RFNYKQNF2","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_16","alias_value":"BE5RFNYKQNF22K6X","created_at":"2026-05-18T12:31:08Z"},{"alias_kind":"pith_short_8","alias_value":"BE5RFNYK","created_at":"2026-05-18T12:31:08Z"}],"graph_snapshots":[{"event_id":"sha256:9d0c72979438aa48ae558abc3dc7e4f42896f23e4cd385bc76657dabca5ff0e1","target":"graph","created_at":"2026-05-18T00:31:50Z","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":"Feature matters. How to train a deep network to acquire discriminative features across categories and polymerized features within classes has always been at the core of many computer vision tasks, specially for large-scale recognition systems where test identities are unseen during training and the number of classes could be at million scale. In this paper, we address this problem based on the simple intuition that the cosine distance of features in high-dimensional space should be close enough within one class and far away across categories. To this end, we proposed the congenerous cosine (CO","authors_text":"Hongyang Li, Xiaogang Wang, Yu Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2017-10-02T19:11:58Z","title":"Rethinking Feature Discrimination and Polymerization for Large-scale Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.00870","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:c469cdeaa5e544baee814c5479d62165d24fb07b1fd3fef4fbe89e2c70107a2c","target":"record","created_at":"2026-05-18T00:31:50Z","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":"3be2728541bff1248fe66dcf70e967399a97e2444f0f2d4dd8a41b00012b8359","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2017-10-02T19:11:58Z","title_canon_sha256":"5f27a287b9bebdb1f1c26fe75dc9c7f00c08bc44d4bbaa2c96954947e5c819c1"},"schema_version":"1.0","source":{"id":"1710.00870","kind":"arxiv","version":2}},"canonical_sha256":"093b12b70a834bad2bd737b10418fc2fab7eef7ccf5bc6f4cbc2468c5cda52bd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"093b12b70a834bad2bd737b10418fc2fab7eef7ccf5bc6f4cbc2468c5cda52bd","first_computed_at":"2026-05-18T00:31:50.311428Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:31:50.311428Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OBYQm8ve/9c/H9WufjRrADbM36OpsSaf/lxhdMx7SoUyFTYxydyS6EZD50v0sQd+Oz96LAuWAGo2oHZK4h2TCw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:31:50.312144Z","signed_message":"canonical_sha256_bytes"},"source_id":"1710.00870","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c469cdeaa5e544baee814c5479d62165d24fb07b1fd3fef4fbe89e2c70107a2c","sha256:9d0c72979438aa48ae558abc3dc7e4f42896f23e4cd385bc76657dabca5ff0e1"],"state_sha256":"96c61cab7d62812ab0eb413881234fb29e84e30028002565941583b0a68a090d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NHDulxKTRWe9UQ4IWK0Rp12tzSe773dNrA5Qb/R4+AaRibk3sQfaSIol6XQsXYuA0pq7Uv+zMBXMsh5nI8o1Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-29T22:30:17.648905Z","bundle_sha256":"231c648e96865728862c0c15635b6a70b9269ab8d686f6b49b98b936958e3ac2"}}