{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:25PWL2DJRD7ZWMEP6RJL7YFTCX","short_pith_number":"pith:25PWL2DJ","canonical_record":{"source":{"id":"1805.03922","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-10T10:47:13Z","cross_cats_sorted":[],"title_canon_sha256":"e1862ee3eb52d52200ac3880ccbf2e3165dcdcdf4ee4b34c8f0a09802a9fb67d","abstract_canon_sha256":"6d948a6d85a3cc6b0ed2c0c776e7e1622bdca08a0c7293b90d4318826e57b1dc"},"schema_version":"1.0"},"canonical_sha256":"d75f65e86988ff9b308ff452bfe0b315cf410fb162376ad79e2226635a0b333c","source":{"kind":"arxiv","id":"1805.03922","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.03922","created_at":"2026-05-18T00:16:15Z"},{"alias_kind":"arxiv_version","alias_value":"1805.03922v1","created_at":"2026-05-18T00:16:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.03922","created_at":"2026-05-18T00:16:15Z"},{"alias_kind":"pith_short_12","alias_value":"25PWL2DJRD7Z","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_16","alias_value":"25PWL2DJRD7ZWMEP","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_8","alias_value":"25PWL2DJ","created_at":"2026-05-18T12:31:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:25PWL2DJRD7ZWMEP6RJL7YFTCX","target":"record","payload":{"canonical_record":{"source":{"id":"1805.03922","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-10T10:47:13Z","cross_cats_sorted":[],"title_canon_sha256":"e1862ee3eb52d52200ac3880ccbf2e3165dcdcdf4ee4b34c8f0a09802a9fb67d","abstract_canon_sha256":"6d948a6d85a3cc6b0ed2c0c776e7e1622bdca08a0c7293b90d4318826e57b1dc"},"schema_version":"1.0"},"canonical_sha256":"d75f65e86988ff9b308ff452bfe0b315cf410fb162376ad79e2226635a0b333c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:16:15.747872Z","signature_b64":"eg27XIcu2VZV4+Ap8/fgN99r7JG831kezRwEGQo9QoRWMYjur11SiBw/r/7lqawNyv1GqvXcF4qo3HYXK/STCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d75f65e86988ff9b308ff452bfe0b315cf410fb162376ad79e2226635a0b333c","last_reissued_at":"2026-05-18T00:16:15.747176Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:16:15.747176Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.03922","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":"2026-05-18T00:16:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tyLsviZMZWQWbKOrEBLYGq3lCUk+bLbhXeKGmwZvV/f0k5BBRW+kI8nV0S67GE3iZNPFYB+OqTz8mkgmTAplBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T01:55:58.205717Z"},"content_sha256":"ad6ca742c363c70e160af93deab3a992d805f8add544a3f3a4f8ccc542014edb","schema_version":"1.0","event_id":"sha256:ad6ca742c363c70e160af93deab3a992d805f8add544a3f3a4f8ccc542014edb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:25PWL2DJRD7ZWMEP6RJL7YFTCX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Ensemble Soft-Margin Softmax Loss for Image Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Shifeng Zhang, Si Liu, Stan Z. Li, Xiaobo Wang, Xiaojie Guo, Zhen Lei","submitted_at":"2018-05-10T10:47:13Z","abstract_excerpt":"Softmax loss is arguably one of the most popular losses to train CNN models for image classification. However, recent works have exposed its limitation on feature discriminability. This paper casts a new viewpoint on the weakness of softmax loss. On the one hand, the CNN features learned using the softmax loss are often inadequately discriminative. We hence introduce a soft-margin softmax function to explicitly encourage the discrimination between different classes. On the other hand, the learned classifier of softmax loss is weak. We propose to assemble multiple these weak classifiers to a st"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.03922","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":"2026-05-18T00:16:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"32GmtZABHzJdc0SIc+/3+AwN1pxhzCBBbkr7eKqJf8TmpS7bBr8WtR86FuQzqlu7sxrarE537+v1uSZTtOqACA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T01:55:58.206429Z"},"content_sha256":"c4826ccf693886cb007a4ef3bc33dfbedf18d691e75358eadec76f1f892b8c29","schema_version":"1.0","event_id":"sha256:c4826ccf693886cb007a4ef3bc33dfbedf18d691e75358eadec76f1f892b8c29"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/25PWL2DJRD7ZWMEP6RJL7YFTCX/bundle.json","state_url":"https://pith.science/pith/25PWL2DJRD7ZWMEP6RJL7YFTCX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/25PWL2DJRD7ZWMEP6RJL7YFTCX/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":"2026-06-05T01:55:58Z","links":{"resolver":"https://pith.science/pith/25PWL2DJRD7ZWMEP6RJL7YFTCX","bundle":"https://pith.science/pith/25PWL2DJRD7ZWMEP6RJL7YFTCX/bundle.json","state":"https://pith.science/pith/25PWL2DJRD7ZWMEP6RJL7YFTCX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/25PWL2DJRD7ZWMEP6RJL7YFTCX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:25PWL2DJRD7ZWMEP6RJL7YFTCX","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":"6d948a6d85a3cc6b0ed2c0c776e7e1622bdca08a0c7293b90d4318826e57b1dc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-10T10:47:13Z","title_canon_sha256":"e1862ee3eb52d52200ac3880ccbf2e3165dcdcdf4ee4b34c8f0a09802a9fb67d"},"schema_version":"1.0","source":{"id":"1805.03922","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.03922","created_at":"2026-05-18T00:16:15Z"},{"alias_kind":"arxiv_version","alias_value":"1805.03922v1","created_at":"2026-05-18T00:16:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.03922","created_at":"2026-05-18T00:16:15Z"},{"alias_kind":"pith_short_12","alias_value":"25PWL2DJRD7Z","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_16","alias_value":"25PWL2DJRD7ZWMEP","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_8","alias_value":"25PWL2DJ","created_at":"2026-05-18T12:31:59Z"}],"graph_snapshots":[{"event_id":"sha256:c4826ccf693886cb007a4ef3bc33dfbedf18d691e75358eadec76f1f892b8c29","target":"graph","created_at":"2026-05-18T00:16:15Z","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":"Softmax loss is arguably one of the most popular losses to train CNN models for image classification. However, recent works have exposed its limitation on feature discriminability. This paper casts a new viewpoint on the weakness of softmax loss. On the one hand, the CNN features learned using the softmax loss are often inadequately discriminative. We hence introduce a soft-margin softmax function to explicitly encourage the discrimination between different classes. On the other hand, the learned classifier of softmax loss is weak. We propose to assemble multiple these weak classifiers to a st","authors_text":"Shifeng Zhang, Si Liu, Stan Z. Li, Xiaobo Wang, Xiaojie Guo, Zhen Lei","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-10T10:47:13Z","title":"Ensemble Soft-Margin Softmax Loss for Image Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.03922","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:ad6ca742c363c70e160af93deab3a992d805f8add544a3f3a4f8ccc542014edb","target":"record","created_at":"2026-05-18T00:16:15Z","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":"6d948a6d85a3cc6b0ed2c0c776e7e1622bdca08a0c7293b90d4318826e57b1dc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-05-10T10:47:13Z","title_canon_sha256":"e1862ee3eb52d52200ac3880ccbf2e3165dcdcdf4ee4b34c8f0a09802a9fb67d"},"schema_version":"1.0","source":{"id":"1805.03922","kind":"arxiv","version":1}},"canonical_sha256":"d75f65e86988ff9b308ff452bfe0b315cf410fb162376ad79e2226635a0b333c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d75f65e86988ff9b308ff452bfe0b315cf410fb162376ad79e2226635a0b333c","first_computed_at":"2026-05-18T00:16:15.747176Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:16:15.747176Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eg27XIcu2VZV4+Ap8/fgN99r7JG831kezRwEGQo9QoRWMYjur11SiBw/r/7lqawNyv1GqvXcF4qo3HYXK/STCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:16:15.747872Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.03922","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ad6ca742c363c70e160af93deab3a992d805f8add544a3f3a4f8ccc542014edb","sha256:c4826ccf693886cb007a4ef3bc33dfbedf18d691e75358eadec76f1f892b8c29"],"state_sha256":"18b8dc3f4aca7c772a491538a56957f5287c961f874d108a83574c9c0f426b85"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q9ZAuxza3mKKW058ZSs/2FXbWw3qcJ5PAr2+ji6ZEzV/uY3I3ErewGBvsROrs6NyoNyCLr4dbnGrPI7wgkDBBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T01:55:58.212220Z","bundle_sha256":"4f3ea29960c3c240032845cce93448327ddc9f6a871aa7e784bbf88f3634baf7"}}