{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:YMEKEQMVHKLCGS5ZNDDF3OGCC6","short_pith_number":"pith:YMEKEQMV","canonical_record":{"source":{"id":"1804.08087","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-22T08:49:59Z","cross_cats_sorted":[],"title_canon_sha256":"f3c067263bf1d95744dc0af57d8e4cd6635fe6dc42ecf039cc56c405c6541b81","abstract_canon_sha256":"988c0e2838236e6347f556315226a86ae52ea26b005122d93ce804886f95404e"},"schema_version":"1.0"},"canonical_sha256":"c308a241953a96234bb968c65db8c217b479507e5a507713d2692b00cf7b7e05","source":{"kind":"arxiv","id":"1804.08087","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.08087","created_at":"2026-05-18T00:17:49Z"},{"alias_kind":"arxiv_version","alias_value":"1804.08087v1","created_at":"2026-05-18T00:17:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.08087","created_at":"2026-05-18T00:17:49Z"},{"alias_kind":"pith_short_12","alias_value":"YMEKEQMVHKLC","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"YMEKEQMVHKLCGS5Z","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"YMEKEQMV","created_at":"2026-05-18T12:33:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:YMEKEQMVHKLCGS5ZNDDF3OGCC6","target":"record","payload":{"canonical_record":{"source":{"id":"1804.08087","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-22T08:49:59Z","cross_cats_sorted":[],"title_canon_sha256":"f3c067263bf1d95744dc0af57d8e4cd6635fe6dc42ecf039cc56c405c6541b81","abstract_canon_sha256":"988c0e2838236e6347f556315226a86ae52ea26b005122d93ce804886f95404e"},"schema_version":"1.0"},"canonical_sha256":"c308a241953a96234bb968c65db8c217b479507e5a507713d2692b00cf7b7e05","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:17:49.579871Z","signature_b64":"QHFvScnF0caLGPzg5x5KqAjn9uSqQp9f1ujQ25N5GAStFCt4sT6ULBMLl1PS0V7sipxE1n9KbLczxcFXbFbuDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c308a241953a96234bb968c65db8c217b479507e5a507713d2692b00cf7b7e05","last_reissued_at":"2026-05-18T00:17:49.579183Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:17:49.579183Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1804.08087","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":"2026-05-18T00:17:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qXQS0twEUiNmUhEFNVwLQ3DJmMohxdnSSWsX0v9YpB5QDZi4fzcfi42fO4W9U30fYuRcXoZeeXdRDQsr7ozhCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T07:42:32.853309Z"},"content_sha256":"90a3ab1c551ef88187802c3eb08de886d4d17f09d59e569ea1ff03952081a8f2","schema_version":"1.0","event_id":"sha256:90a3ab1c551ef88187802c3eb08de886d4d17f09d59e569ea1ff03952081a8f2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:YMEKEQMVHKLCGS5ZNDDF3OGCC6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Anchor-based Nearest Class Mean Loss for Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dapeng Tao, Fusheng Hao, Jianzhong Cao, Jun Cheng, Lei Wang, Xinchao Wang, Xiping Hu","submitted_at":"2018-04-22T08:49:59Z","abstract_excerpt":"Discriminative features are critical for machine learning applications. Most existing deep learning approaches, however, rely on convolutional neural networks (CNNs) for learning features, whose discriminant power is not explicitly enforced. In this paper, we propose a novel approach to train deep CNNs by imposing the intra-class compactness and the inter-class separability, so as to enhance the learned features' discriminant power. To this end, we introduce anchors, which are predefined vectors regarded as the centers for each class and fixed during training. Discriminative features are obtai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.08087","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":"2026-05-18T00:17:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"igGB2CSVcVT5+tE5f+WEfUsiLvTIMSnEN2f80N6PnMRbDLcy7QWQ4K+nQGtVs77c6zthP7FovKSWRbG4pV3aDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T07:42:32.854026Z"},"content_sha256":"97e51949a3f8b1e4cd7808dd3550275c0dac95f8508366a850d2f52c830104e5","schema_version":"1.0","event_id":"sha256:97e51949a3f8b1e4cd7808dd3550275c0dac95f8508366a850d2f52c830104e5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YMEKEQMVHKLCGS5ZNDDF3OGCC6/bundle.json","state_url":"https://pith.science/pith/YMEKEQMVHKLCGS5ZNDDF3OGCC6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YMEKEQMVHKLCGS5ZNDDF3OGCC6/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":"2026-06-06T07:42:32Z","links":{"resolver":"https://pith.science/pith/YMEKEQMVHKLCGS5ZNDDF3OGCC6","bundle":"https://pith.science/pith/YMEKEQMVHKLCGS5ZNDDF3OGCC6/bundle.json","state":"https://pith.science/pith/YMEKEQMVHKLCGS5ZNDDF3OGCC6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YMEKEQMVHKLCGS5ZNDDF3OGCC6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:YMEKEQMVHKLCGS5ZNDDF3OGCC6","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":"988c0e2838236e6347f556315226a86ae52ea26b005122d93ce804886f95404e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-22T08:49:59Z","title_canon_sha256":"f3c067263bf1d95744dc0af57d8e4cd6635fe6dc42ecf039cc56c405c6541b81"},"schema_version":"1.0","source":{"id":"1804.08087","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.08087","created_at":"2026-05-18T00:17:49Z"},{"alias_kind":"arxiv_version","alias_value":"1804.08087v1","created_at":"2026-05-18T00:17:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.08087","created_at":"2026-05-18T00:17:49Z"},{"alias_kind":"pith_short_12","alias_value":"YMEKEQMVHKLC","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_16","alias_value":"YMEKEQMVHKLCGS5Z","created_at":"2026-05-18T12:33:04Z"},{"alias_kind":"pith_short_8","alias_value":"YMEKEQMV","created_at":"2026-05-18T12:33:04Z"}],"graph_snapshots":[{"event_id":"sha256:97e51949a3f8b1e4cd7808dd3550275c0dac95f8508366a850d2f52c830104e5","target":"graph","created_at":"2026-05-18T00:17:49Z","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":"Discriminative features are critical for machine learning applications. Most existing deep learning approaches, however, rely on convolutional neural networks (CNNs) for learning features, whose discriminant power is not explicitly enforced. In this paper, we propose a novel approach to train deep CNNs by imposing the intra-class compactness and the inter-class separability, so as to enhance the learned features' discriminant power. To this end, we introduce anchors, which are predefined vectors regarded as the centers for each class and fixed during training. Discriminative features are obtai","authors_text":"Dapeng Tao, Fusheng Hao, Jianzhong Cao, Jun Cheng, Lei Wang, Xinchao Wang, Xiping Hu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-22T08:49:59Z","title":"Anchor-based Nearest Class Mean Loss for Convolutional Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.08087","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":"sha256:90a3ab1c551ef88187802c3eb08de886d4d17f09d59e569ea1ff03952081a8f2","target":"record","created_at":"2026-05-18T00:17:49Z","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":"988c0e2838236e6347f556315226a86ae52ea26b005122d93ce804886f95404e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-04-22T08:49:59Z","title_canon_sha256":"f3c067263bf1d95744dc0af57d8e4cd6635fe6dc42ecf039cc56c405c6541b81"},"schema_version":"1.0","source":{"id":"1804.08087","kind":"arxiv","version":1}},"canonical_sha256":"c308a241953a96234bb968c65db8c217b479507e5a507713d2692b00cf7b7e05","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c308a241953a96234bb968c65db8c217b479507e5a507713d2692b00cf7b7e05","first_computed_at":"2026-05-18T00:17:49.579183Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:17:49.579183Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QHFvScnF0caLGPzg5x5KqAjn9uSqQp9f1ujQ25N5GAStFCt4sT6ULBMLl1PS0V7sipxE1n9KbLczxcFXbFbuDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:17:49.579871Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.08087","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:90a3ab1c551ef88187802c3eb08de886d4d17f09d59e569ea1ff03952081a8f2","sha256:97e51949a3f8b1e4cd7808dd3550275c0dac95f8508366a850d2f52c830104e5"],"state_sha256":"c33a6e75bc5824b62613baac12b5617fe36950ebc02c1ded1f122ba5eee3817c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dqGMsXGd8UEuT5UYPDw3Lh5iPDKDM6yy1QT6GPrU+rQzLVi8rl/Anyaf87dD4YoCQSGn2r7JNtgjFMbEYP+UBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T07:42:32.858175Z","bundle_sha256":"8f79632ad64bb890a473c47bc96534be6da45f46fbe7a32aa6fde0230940334e"}}