{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:OLYJGKVGSR633XRX32FDRKYOSF","short_pith_number":"pith:OLYJGKVG","canonical_record":{"source":{"id":"1705.09780","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-05-27T07:34:48Z","cross_cats_sorted":[],"title_canon_sha256":"2f7680e364a5ab08e2e0ac48ad644649f51697e674cfdbb95a5ba989e6ace918","abstract_canon_sha256":"64e83c581ca99f97ffd86a21dc6a1e916d1a48ddb2d6f6432d9bf1b94e68f42a"},"schema_version":"1.0"},"canonical_sha256":"72f0932aa6947dbdde37de8a38ab0e917125c7e4bb3d89c344f1976fe00cc69c","source":{"kind":"arxiv","id":"1705.09780","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.09780","created_at":"2026-05-18T00:12:00Z"},{"alias_kind":"arxiv_version","alias_value":"1705.09780v3","created_at":"2026-05-18T00:12:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.09780","created_at":"2026-05-18T00:12:00Z"},{"alias_kind":"pith_short_12","alias_value":"OLYJGKVGSR63","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_16","alias_value":"OLYJGKVGSR633XRX","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_8","alias_value":"OLYJGKVG","created_at":"2026-05-18T12:31:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:OLYJGKVGSR633XRX32FDRKYOSF","target":"record","payload":{"canonical_record":{"source":{"id":"1705.09780","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-05-27T07:34:48Z","cross_cats_sorted":[],"title_canon_sha256":"2f7680e364a5ab08e2e0ac48ad644649f51697e674cfdbb95a5ba989e6ace918","abstract_canon_sha256":"64e83c581ca99f97ffd86a21dc6a1e916d1a48ddb2d6f6432d9bf1b94e68f42a"},"schema_version":"1.0"},"canonical_sha256":"72f0932aa6947dbdde37de8a38ab0e917125c7e4bb3d89c344f1976fe00cc69c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:12:00.415541Z","signature_b64":"RzQ0m/m+0Jq+EBJuJ+2RTC37chT6kU8Sa15M+etRwH0a+K9tnDg4QmZIGH8s/svgLrCDr6DUFQ288K6nrpSHAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72f0932aa6947dbdde37de8a38ab0e917125c7e4bb3d89c344f1976fe00cc69c","last_reissued_at":"2026-05-18T00:12:00.414857Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:12:00.414857Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1705.09780","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:12:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BLcBYvmqpvB/YR/keLU5S8yYybXiD+OQ7YleS3MncYJ13Hrkva7DizhjdjlHN+ERawuWBObPDOCpDW7nGq3rAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T05:02:41.722022Z"},"content_sha256":"2aa4048b726018daa898b04ca58f1ed23cfa591a480cfd54b76f441e80eaf415","schema_version":"1.0","event_id":"sha256:2aa4048b726018daa898b04ca58f1ed23cfa591a480cfd54b76f441e80eaf415"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:OLYJGKVGSR633XRX32FDRKYOSF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Metric Learning and Image Classification with Nearest Neighbour Gaussian Kernels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ben Harwood, Benjamin J. Meyer, Tom Drummond","submitted_at":"2017-05-27T07:34:48Z","abstract_excerpt":"We present a Gaussian kernel loss function and training algorithm for convolutional neural networks that can be directly applied to both distance metric learning and image classification problems. Our method treats all training features from a deep neural network as Gaussian kernel centres and computes loss by summing the influence of a feature's nearby centres in the feature embedding space. Our approach is made scalable by treating it as an approximate nearest neighbour search problem. We show how to make end-to-end learning feasible, resulting in a well formed embedding space, in which sema"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.09780","kind":"arxiv","version":3},"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":"2026-05-18T00:12:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NKxdzh80N8bLi8oX781cXTR1LfMq+i39e6BqFy+QDBLvm0bFLdD+uXDirjaPqiskwfbExunZJVoSZJClhwqjDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T05:02:41.722378Z"},"content_sha256":"2be30e6371232a2ed017b3f42ffa6c7df8659e27de97412e019b8ee4418979b8","schema_version":"1.0","event_id":"sha256:2be30e6371232a2ed017b3f42ffa6c7df8659e27de97412e019b8ee4418979b8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OLYJGKVGSR633XRX32FDRKYOSF/bundle.json","state_url":"https://pith.science/pith/OLYJGKVGSR633XRX32FDRKYOSF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OLYJGKVGSR633XRX32FDRKYOSF/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":"2026-06-02T05:02:41Z","links":{"resolver":"https://pith.science/pith/OLYJGKVGSR633XRX32FDRKYOSF","bundle":"https://pith.science/pith/OLYJGKVGSR633XRX32FDRKYOSF/bundle.json","state":"https://pith.science/pith/OLYJGKVGSR633XRX32FDRKYOSF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OLYJGKVGSR633XRX32FDRKYOSF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:OLYJGKVGSR633XRX32FDRKYOSF","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":"64e83c581ca99f97ffd86a21dc6a1e916d1a48ddb2d6f6432d9bf1b94e68f42a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-05-27T07:34:48Z","title_canon_sha256":"2f7680e364a5ab08e2e0ac48ad644649f51697e674cfdbb95a5ba989e6ace918"},"schema_version":"1.0","source":{"id":"1705.09780","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.09780","created_at":"2026-05-18T00:12:00Z"},{"alias_kind":"arxiv_version","alias_value":"1705.09780v3","created_at":"2026-05-18T00:12:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.09780","created_at":"2026-05-18T00:12:00Z"},{"alias_kind":"pith_short_12","alias_value":"OLYJGKVGSR63","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_16","alias_value":"OLYJGKVGSR633XRX","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_8","alias_value":"OLYJGKVG","created_at":"2026-05-18T12:31:34Z"}],"graph_snapshots":[{"event_id":"sha256:2be30e6371232a2ed017b3f42ffa6c7df8659e27de97412e019b8ee4418979b8","target":"graph","created_at":"2026-05-18T00:12:00Z","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":"We present a Gaussian kernel loss function and training algorithm for convolutional neural networks that can be directly applied to both distance metric learning and image classification problems. Our method treats all training features from a deep neural network as Gaussian kernel centres and computes loss by summing the influence of a feature's nearby centres in the feature embedding space. Our approach is made scalable by treating it as an approximate nearest neighbour search problem. We show how to make end-to-end learning feasible, resulting in a well formed embedding space, in which sema","authors_text":"Ben Harwood, Benjamin J. Meyer, Tom Drummond","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-05-27T07:34:48Z","title":"Deep Metric Learning and Image Classification with Nearest Neighbour Gaussian Kernels"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.09780","kind":"arxiv","version":3},"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":"sha256:2aa4048b726018daa898b04ca58f1ed23cfa591a480cfd54b76f441e80eaf415","target":"record","created_at":"2026-05-18T00:12:00Z","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":"64e83c581ca99f97ffd86a21dc6a1e916d1a48ddb2d6f6432d9bf1b94e68f42a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-05-27T07:34:48Z","title_canon_sha256":"2f7680e364a5ab08e2e0ac48ad644649f51697e674cfdbb95a5ba989e6ace918"},"schema_version":"1.0","source":{"id":"1705.09780","kind":"arxiv","version":3}},"canonical_sha256":"72f0932aa6947dbdde37de8a38ab0e917125c7e4bb3d89c344f1976fe00cc69c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"72f0932aa6947dbdde37de8a38ab0e917125c7e4bb3d89c344f1976fe00cc69c","first_computed_at":"2026-05-18T00:12:00.414857Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:12:00.414857Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RzQ0m/m+0Jq+EBJuJ+2RTC37chT6kU8Sa15M+etRwH0a+K9tnDg4QmZIGH8s/svgLrCDr6DUFQ288K6nrpSHAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:12:00.415541Z","signed_message":"canonical_sha256_bytes"},"source_id":"1705.09780","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2aa4048b726018daa898b04ca58f1ed23cfa591a480cfd54b76f441e80eaf415","sha256:2be30e6371232a2ed017b3f42ffa6c7df8659e27de97412e019b8ee4418979b8"],"state_sha256":"3e060e401f695c876b1ca6cde7a8853d452edf2693ad39dff12ad718f90efb5f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"unIiJrDoPnO0JuxVx8oylDRSO9ajI9+k/ayeD8xSQ+tVzR4lML05o4sqvBXWHQr3bKrWI4vnPvYRlmSoy7O4Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T05:02:41.724256Z","bundle_sha256":"1e984efa7946bbad9ba532d30f056fd164fae610a234c21177cd263ad93ff035"}}