{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:CJLQBXKLD35WAITNEIEHX5QT22","short_pith_number":"pith:CJLQBXKL","canonical_record":{"source":{"id":"1809.04157","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-11T20:56:02Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"14b6697fb424aae9230a5b9fd9b825a0f2e134f5ccc4bb627abe62a7a38365fb","abstract_canon_sha256":"8cc6d3c071b78ab453640f997fc701382c4939fcdf7258f12ceb531a2c119222"},"schema_version":"1.0"},"canonical_sha256":"125700dd4b1efb60226d22087bf613d69b99478d3d253618f53078ca47ba88ee","source":{"kind":"arxiv","id":"1809.04157","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.04157","created_at":"2026-05-18T00:05:55Z"},{"alias_kind":"arxiv_version","alias_value":"1809.04157v1","created_at":"2026-05-18T00:05:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.04157","created_at":"2026-05-18T00:05:55Z"},{"alias_kind":"pith_short_12","alias_value":"CJLQBXKLD35W","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_16","alias_value":"CJLQBXKLD35WAITN","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_8","alias_value":"CJLQBXKL","created_at":"2026-05-18T12:32:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:CJLQBXKLD35WAITNEIEHX5QT22","target":"record","payload":{"canonical_record":{"source":{"id":"1809.04157","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-11T20:56:02Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"14b6697fb424aae9230a5b9fd9b825a0f2e134f5ccc4bb627abe62a7a38365fb","abstract_canon_sha256":"8cc6d3c071b78ab453640f997fc701382c4939fcdf7258f12ceb531a2c119222"},"schema_version":"1.0"},"canonical_sha256":"125700dd4b1efb60226d22087bf613d69b99478d3d253618f53078ca47ba88ee","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:05:55.325759Z","signature_b64":"g4ndxIhAEWcLLTJI/rSQAnX3gnz+bO112ZHHeBDWjI1obDaY6RhYUmGdnxueDDy1NHV+SUAGszm2i081vjYvDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"125700dd4b1efb60226d22087bf613d69b99478d3d253618f53078ca47ba88ee","last_reissued_at":"2026-05-18T00:05:55.325238Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:05:55.325238Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1809.04157","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":"2026-05-18T00:05:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dgKs3UKRXVB/hA48MmAKiErZFiUD3Qyv963jdJLthFn9CFVgfdHE8uhunoT7TUIs/MpUk37UtXniJU5rgnNZDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T06:23:46.552664Z"},"content_sha256":"d0c23888843e748fa066382ed7092f0c45072fe8ce57b6d3b575663eaac914ee","schema_version":"1.0","event_id":"sha256:d0c23888843e748fa066382ed7092f0c45072fe8ce57b6d3b575663eaac914ee"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:CJLQBXKLD35WAITNEIEHX5QT22","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Heated-Up Softmax Embedding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Felix Xinnan Yu, Shih-Fu Chang, Svebor Karaman, Wei Zhang, Xu Zhang","submitted_at":"2018-09-11T20:56:02Z","abstract_excerpt":"Metric learning aims at learning a distance which is consistent with the semantic meaning of the samples. The problem is generally solved by learning an embedding for each sample such that the embeddings of samples of the same category are compact while the embeddings of samples of different categories are spread-out in the feature space. We study the features extracted from the second last layer of a deep neural network based classifier trained with the cross entropy loss on top of the softmax layer. We show that training classifiers with different temperature values of softmax function leads"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.04157","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":"2026-05-18T00:05:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TtAXRQtbZYKMSHX59eMT6pcDbavHfuJkqLm2f6VSWz+6YCz68v/uSxMUOqjpIOO/oAy8iCE4GQIZ/v/pTsIJAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T06:23:46.553015Z"},"content_sha256":"e1db2136e91ee32f9db5f60c86e083e68f598e0e1635c5673c0db56b72ef3df7","schema_version":"1.0","event_id":"sha256:e1db2136e91ee32f9db5f60c86e083e68f598e0e1635c5673c0db56b72ef3df7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CJLQBXKLD35WAITNEIEHX5QT22/bundle.json","state_url":"https://pith.science/pith/CJLQBXKLD35WAITNEIEHX5QT22/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CJLQBXKLD35WAITNEIEHX5QT22/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":"2026-05-28T06:23:46Z","links":{"resolver":"https://pith.science/pith/CJLQBXKLD35WAITNEIEHX5QT22","bundle":"https://pith.science/pith/CJLQBXKLD35WAITNEIEHX5QT22/bundle.json","state":"https://pith.science/pith/CJLQBXKLD35WAITNEIEHX5QT22/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CJLQBXKLD35WAITNEIEHX5QT22/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:CJLQBXKLD35WAITNEIEHX5QT22","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":"8cc6d3c071b78ab453640f997fc701382c4939fcdf7258f12ceb531a2c119222","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-11T20:56:02Z","title_canon_sha256":"14b6697fb424aae9230a5b9fd9b825a0f2e134f5ccc4bb627abe62a7a38365fb"},"schema_version":"1.0","source":{"id":"1809.04157","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.04157","created_at":"2026-05-18T00:05:55Z"},{"alias_kind":"arxiv_version","alias_value":"1809.04157v1","created_at":"2026-05-18T00:05:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.04157","created_at":"2026-05-18T00:05:55Z"},{"alias_kind":"pith_short_12","alias_value":"CJLQBXKLD35W","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_16","alias_value":"CJLQBXKLD35WAITN","created_at":"2026-05-18T12:32:16Z"},{"alias_kind":"pith_short_8","alias_value":"CJLQBXKL","created_at":"2026-05-18T12:32:16Z"}],"graph_snapshots":[{"event_id":"sha256:e1db2136e91ee32f9db5f60c86e083e68f598e0e1635c5673c0db56b72ef3df7","target":"graph","created_at":"2026-05-18T00:05:55Z","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":"Metric learning aims at learning a distance which is consistent with the semantic meaning of the samples. The problem is generally solved by learning an embedding for each sample such that the embeddings of samples of the same category are compact while the embeddings of samples of different categories are spread-out in the feature space. We study the features extracted from the second last layer of a deep neural network based classifier trained with the cross entropy loss on top of the softmax layer. We show that training classifiers with different temperature values of softmax function leads","authors_text":"Felix Xinnan Yu, Shih-Fu Chang, Svebor Karaman, Wei Zhang, Xu Zhang","cross_cats":["cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-11T20:56:02Z","title":"Heated-Up Softmax Embedding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.04157","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:d0c23888843e748fa066382ed7092f0c45072fe8ce57b6d3b575663eaac914ee","target":"record","created_at":"2026-05-18T00:05:55Z","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":"8cc6d3c071b78ab453640f997fc701382c4939fcdf7258f12ceb531a2c119222","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-11T20:56:02Z","title_canon_sha256":"14b6697fb424aae9230a5b9fd9b825a0f2e134f5ccc4bb627abe62a7a38365fb"},"schema_version":"1.0","source":{"id":"1809.04157","kind":"arxiv","version":1}},"canonical_sha256":"125700dd4b1efb60226d22087bf613d69b99478d3d253618f53078ca47ba88ee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"125700dd4b1efb60226d22087bf613d69b99478d3d253618f53078ca47ba88ee","first_computed_at":"2026-05-18T00:05:55.325238Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:05:55.325238Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"g4ndxIhAEWcLLTJI/rSQAnX3gnz+bO112ZHHeBDWjI1obDaY6RhYUmGdnxueDDy1NHV+SUAGszm2i081vjYvDw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:05:55.325759Z","signed_message":"canonical_sha256_bytes"},"source_id":"1809.04157","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d0c23888843e748fa066382ed7092f0c45072fe8ce57b6d3b575663eaac914ee","sha256:e1db2136e91ee32f9db5f60c86e083e68f598e0e1635c5673c0db56b72ef3df7"],"state_sha256":"1acdcfb539d446ca8c0ae4037fd91aca77de0d7d6cbf87061e5b6a27a4e06e03"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mIZvTylz+UrDDLSvAleFEZaQCKKm+VS/EhNhMMLmUf0TvIPYo2Ahtzb5dg4jVrCpPKjnS6IG0u+fKdHEqIERBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T06:23:46.555036Z","bundle_sha256":"a4ae97cbeb653a3257af4a1e915b97e1d65eb46052080b2501f7ef2afb9daa56"}}