{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:T5Z2JT5O3LPT6MXOVG7YHCACSO","short_pith_number":"pith:T5Z2JT5O","canonical_record":{"source":{"id":"1612.02295","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-12-07T15:36:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3a85580c93be221f93588b085574a9e7c0c7aa23b540f5bbecd4f3110912148d","abstract_canon_sha256":"3fc2f243bfbfc366dbf80e73b6c849107b79961cc8519c7d751eaa9d27be53be"},"schema_version":"1.0"},"canonical_sha256":"9f73a4cfaedadf3f32eea9bf838802939a4c942a69b8c6ab37cd119bed25cbaa","source":{"kind":"arxiv","id":"1612.02295","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.02295","created_at":"2026-05-18T00:30:17Z"},{"alias_kind":"arxiv_version","alias_value":"1612.02295v4","created_at":"2026-05-18T00:30:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.02295","created_at":"2026-05-18T00:30:17Z"},{"alias_kind":"pith_short_12","alias_value":"T5Z2JT5O3LPT","created_at":"2026-05-18T12:30:44Z"},{"alias_kind":"pith_short_16","alias_value":"T5Z2JT5O3LPT6MXO","created_at":"2026-05-18T12:30:44Z"},{"alias_kind":"pith_short_8","alias_value":"T5Z2JT5O","created_at":"2026-05-18T12:30:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:T5Z2JT5O3LPT6MXOVG7YHCACSO","target":"record","payload":{"canonical_record":{"source":{"id":"1612.02295","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-12-07T15:36:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3a85580c93be221f93588b085574a9e7c0c7aa23b540f5bbecd4f3110912148d","abstract_canon_sha256":"3fc2f243bfbfc366dbf80e73b6c849107b79961cc8519c7d751eaa9d27be53be"},"schema_version":"1.0"},"canonical_sha256":"9f73a4cfaedadf3f32eea9bf838802939a4c942a69b8c6ab37cd119bed25cbaa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:30:17.378819Z","signature_b64":"Uq4rjRWKyyn1NaPQj+LUOSDfEqZaNOw02mUS7cGWC/uTuUBQTwFXEtfHxfsQJEQjhJiSEjbQO4a8wEeAcfxMCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f73a4cfaedadf3f32eea9bf838802939a4c942a69b8c6ab37cd119bed25cbaa","last_reissued_at":"2026-05-18T00:30:17.378117Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:30:17.378117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1612.02295","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:30:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wr78vhkGql12kes3Hy3Esxg+pJAENd6PTSmH22ZRGyU8geNBXFUf/TMofG0ytr/zlH+F6ZP/hGkWfWGoxLbJCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T16:51:29.138914Z"},"content_sha256":"56278c49da805ed1013ca45351414ae9dbb57d995c1be53c3427e9f599979c10","schema_version":"1.0","event_id":"sha256:56278c49da805ed1013ca45351414ae9dbb57d995c1be53c3427e9f599979c10"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:T5Z2JT5O3LPT6MXOVG7YHCACSO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Large-Margin Softmax Loss for Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Meng Yang, Weiyang Liu, Yandong Wen, Zhiding Yu","submitted_at":"2016-12-07T15:36:11Z","abstract_excerpt":"Cross-entropy loss together with softmax is arguably one of the most common used supervision components in convolutional neural networks (CNNs). Despite its simplicity, popularity and excellent performance, the component does not explicitly encourage discriminative learning of features. In this paper, we propose a generalized large-margin softmax (L-Softmax) loss which explicitly encourages intra-class compactness and inter-class separability between learned features. Moreover, L-Softmax not only can adjust the desired margin but also can avoid overfitting. We also show that the L-Softmax loss"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.02295","kind":"arxiv","version":4},"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":"2026-05-18T00:30:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GVWWXZ2N2LCUW2KQlOOJOYcP+8QbFFEMKtsJwrPgOG/w+ODib0nezGPOjdk+X0PJWo49JwvPkVJfRqAL4ve8Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T16:51:29.139276Z"},"content_sha256":"f73a33627d5648fbb6782f39da4ac1aaef12c10cd668e43735d4569e714a2b1b","schema_version":"1.0","event_id":"sha256:f73a33627d5648fbb6782f39da4ac1aaef12c10cd668e43735d4569e714a2b1b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/T5Z2JT5O3LPT6MXOVG7YHCACSO/bundle.json","state_url":"https://pith.science/pith/T5Z2JT5O3LPT6MXOVG7YHCACSO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/T5Z2JT5O3LPT6MXOVG7YHCACSO/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":"2026-06-09T16:51:29Z","links":{"resolver":"https://pith.science/pith/T5Z2JT5O3LPT6MXOVG7YHCACSO","bundle":"https://pith.science/pith/T5Z2JT5O3LPT6MXOVG7YHCACSO/bundle.json","state":"https://pith.science/pith/T5Z2JT5O3LPT6MXOVG7YHCACSO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/T5Z2JT5O3LPT6MXOVG7YHCACSO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:T5Z2JT5O3LPT6MXOVG7YHCACSO","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":"3fc2f243bfbfc366dbf80e73b6c849107b79961cc8519c7d751eaa9d27be53be","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-12-07T15:36:11Z","title_canon_sha256":"3a85580c93be221f93588b085574a9e7c0c7aa23b540f5bbecd4f3110912148d"},"schema_version":"1.0","source":{"id":"1612.02295","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.02295","created_at":"2026-05-18T00:30:17Z"},{"alias_kind":"arxiv_version","alias_value":"1612.02295v4","created_at":"2026-05-18T00:30:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.02295","created_at":"2026-05-18T00:30:17Z"},{"alias_kind":"pith_short_12","alias_value":"T5Z2JT5O3LPT","created_at":"2026-05-18T12:30:44Z"},{"alias_kind":"pith_short_16","alias_value":"T5Z2JT5O3LPT6MXO","created_at":"2026-05-18T12:30:44Z"},{"alias_kind":"pith_short_8","alias_value":"T5Z2JT5O","created_at":"2026-05-18T12:30:44Z"}],"graph_snapshots":[{"event_id":"sha256:f73a33627d5648fbb6782f39da4ac1aaef12c10cd668e43735d4569e714a2b1b","target":"graph","created_at":"2026-05-18T00:30:17Z","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":"Cross-entropy loss together with softmax is arguably one of the most common used supervision components in convolutional neural networks (CNNs). Despite its simplicity, popularity and excellent performance, the component does not explicitly encourage discriminative learning of features. In this paper, we propose a generalized large-margin softmax (L-Softmax) loss which explicitly encourages intra-class compactness and inter-class separability between learned features. Moreover, L-Softmax not only can adjust the desired margin but also can avoid overfitting. We also show that the L-Softmax loss","authors_text":"Meng Yang, Weiyang Liu, Yandong Wen, Zhiding Yu","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-12-07T15:36:11Z","title":"Large-Margin Softmax Loss for Convolutional Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.02295","kind":"arxiv","version":4},"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":"sha256:56278c49da805ed1013ca45351414ae9dbb57d995c1be53c3427e9f599979c10","target":"record","created_at":"2026-05-18T00:30:17Z","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":"3fc2f243bfbfc366dbf80e73b6c849107b79961cc8519c7d751eaa9d27be53be","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-12-07T15:36:11Z","title_canon_sha256":"3a85580c93be221f93588b085574a9e7c0c7aa23b540f5bbecd4f3110912148d"},"schema_version":"1.0","source":{"id":"1612.02295","kind":"arxiv","version":4}},"canonical_sha256":"9f73a4cfaedadf3f32eea9bf838802939a4c942a69b8c6ab37cd119bed25cbaa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9f73a4cfaedadf3f32eea9bf838802939a4c942a69b8c6ab37cd119bed25cbaa","first_computed_at":"2026-05-18T00:30:17.378117Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:30:17.378117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Uq4rjRWKyyn1NaPQj+LUOSDfEqZaNOw02mUS7cGWC/uTuUBQTwFXEtfHxfsQJEQjhJiSEjbQO4a8wEeAcfxMCA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:30:17.378819Z","signed_message":"canonical_sha256_bytes"},"source_id":"1612.02295","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:56278c49da805ed1013ca45351414ae9dbb57d995c1be53c3427e9f599979c10","sha256:f73a33627d5648fbb6782f39da4ac1aaef12c10cd668e43735d4569e714a2b1b"],"state_sha256":"41d6e45aa10a37267108448afcf1f7eb9b59b4ee355ce66f05d77a60cba991b8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/SlGRo0T4cY8yQ1Qqnq/xJ44aPhaCTS1443yi2cEfvK5VP6ATk/KT2JmH5GWvfVx2V3ehvD51eLlsDbErEsGDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T16:51:29.141326Z","bundle_sha256":"da02696de691269a9ad160cdb270cfef677afd48407960adc70a95ba31468cfd"}}