{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:HWLZIWXTAX54XJCN65GR2YNQEI","short_pith_number":"pith:HWLZIWXT","canonical_record":{"source":{"id":"1904.11138","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-25T03:24:53Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"edb3563d9967f981953ebc4f8ba5df417ec21a9a1df91a0be743a815109f8cf7","abstract_canon_sha256":"6717047d27871145e1ba9c94a83bca90666063511f9df10a87ee86ce6294a656"},"schema_version":"1.0"},"canonical_sha256":"3d97945af305fbcba44df74d1d61b0221279d536b6633479fd0629435723d91e","source":{"kind":"arxiv","id":"1904.11138","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.11138","created_at":"2026-05-17T23:47:45Z"},{"alias_kind":"arxiv_version","alias_value":"1904.11138v1","created_at":"2026-05-17T23:47:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.11138","created_at":"2026-05-17T23:47:45Z"},{"alias_kind":"pith_short_12","alias_value":"HWLZIWXTAX54","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"HWLZIWXTAX54XJCN","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"HWLZIWXT","created_at":"2026-05-18T12:33:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:HWLZIWXTAX54XJCN65GR2YNQEI","target":"record","payload":{"canonical_record":{"source":{"id":"1904.11138","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-25T03:24:53Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"edb3563d9967f981953ebc4f8ba5df417ec21a9a1df91a0be743a815109f8cf7","abstract_canon_sha256":"6717047d27871145e1ba9c94a83bca90666063511f9df10a87ee86ce6294a656"},"schema_version":"1.0"},"canonical_sha256":"3d97945af305fbcba44df74d1d61b0221279d536b6633479fd0629435723d91e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:47:45.671185Z","signature_b64":"Rm0ost8kBHMp93PsGpjT7hPdqzKtyEz+l8/Zqcd3/lL4gj91j9pnX6EozlGs0BG86Wa1hosfm0IU19My9tRvDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d97945af305fbcba44df74d1d61b0221279d536b6633479fd0629435723d91e","last_reissued_at":"2026-05-17T23:47:45.670555Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:47:45.670555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1904.11138","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":"2026-05-17T23:47:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V8Pc3sVC7A5A1M0+i5+hNm00oIpqiFVkL88seIK68EQohk/NUR6ojaABzd5DFWBgp+/ToQOekdik5mjXxitZAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T10:28:26.605578Z"},"content_sha256":"c7e2f32a7b0ea72e7f980165bfabdf2eed794626a1026314808e806d4fbb0367","schema_version":"1.0","event_id":"sha256:c7e2f32a7b0ea72e7f980165bfabdf2eed794626a1026314808e806d4fbb0367"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:HWLZIWXTAX54XJCN65GR2YNQEI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Discriminative Features Via Weights-biased Softmax Loss","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Weiqiang Wang, Xiaobin Li","submitted_at":"2019-04-25T03:24:53Z","abstract_excerpt":"Loss functions play a key role in training superior deep neural networks. In convolutional neural networks (CNNs), the popular cross entropy loss together with softmax does not explicitly guarantee minimization of intra-class variance or maximization of inter-class variance. In the early studies, there is no theoretical analysis and experiments explicitly indicating how to choose the number of units in fully connected layer. To help CNNs learn features more fast and discriminative, there are two contributions in this paper. First, we determine the minimum number of units in FC layer by rigorou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.11138","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":"2026-05-17T23:47:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QfyAutgiwwsNTmp178WtLKkFhsAL7LDG4a+zNtY1EexoB9tjJSvgBk1xGIOuHQQrvAvFcP/6/xhFXOXZ80kGAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T10:28:26.605913Z"},"content_sha256":"03af33e59e9649097e5a17ea68c5977cb846c295cbe742eecbf38825a6ace082","schema_version":"1.0","event_id":"sha256:03af33e59e9649097e5a17ea68c5977cb846c295cbe742eecbf38825a6ace082"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HWLZIWXTAX54XJCN65GR2YNQEI/bundle.json","state_url":"https://pith.science/pith/HWLZIWXTAX54XJCN65GR2YNQEI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HWLZIWXTAX54XJCN65GR2YNQEI/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":"2026-06-12T10:28:26Z","links":{"resolver":"https://pith.science/pith/HWLZIWXTAX54XJCN65GR2YNQEI","bundle":"https://pith.science/pith/HWLZIWXTAX54XJCN65GR2YNQEI/bundle.json","state":"https://pith.science/pith/HWLZIWXTAX54XJCN65GR2YNQEI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HWLZIWXTAX54XJCN65GR2YNQEI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:HWLZIWXTAX54XJCN65GR2YNQEI","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":"6717047d27871145e1ba9c94a83bca90666063511f9df10a87ee86ce6294a656","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-25T03:24:53Z","title_canon_sha256":"edb3563d9967f981953ebc4f8ba5df417ec21a9a1df91a0be743a815109f8cf7"},"schema_version":"1.0","source":{"id":"1904.11138","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.11138","created_at":"2026-05-17T23:47:45Z"},{"alias_kind":"arxiv_version","alias_value":"1904.11138v1","created_at":"2026-05-17T23:47:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.11138","created_at":"2026-05-17T23:47:45Z"},{"alias_kind":"pith_short_12","alias_value":"HWLZIWXTAX54","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_16","alias_value":"HWLZIWXTAX54XJCN","created_at":"2026-05-18T12:33:18Z"},{"alias_kind":"pith_short_8","alias_value":"HWLZIWXT","created_at":"2026-05-18T12:33:18Z"}],"graph_snapshots":[{"event_id":"sha256:03af33e59e9649097e5a17ea68c5977cb846c295cbe742eecbf38825a6ace082","target":"graph","created_at":"2026-05-17T23:47:45Z","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":"Loss functions play a key role in training superior deep neural networks. In convolutional neural networks (CNNs), the popular cross entropy loss together with softmax does not explicitly guarantee minimization of intra-class variance or maximization of inter-class variance. In the early studies, there is no theoretical analysis and experiments explicitly indicating how to choose the number of units in fully connected layer. To help CNNs learn features more fast and discriminative, there are two contributions in this paper. First, we determine the minimum number of units in FC layer by rigorou","authors_text":"Weiqiang Wang, Xiaobin Li","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-25T03:24:53Z","title":"Learning Discriminative Features Via Weights-biased Softmax Loss"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.11138","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:c7e2f32a7b0ea72e7f980165bfabdf2eed794626a1026314808e806d4fbb0367","target":"record","created_at":"2026-05-17T23:47:45Z","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":"6717047d27871145e1ba9c94a83bca90666063511f9df10a87ee86ce6294a656","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-04-25T03:24:53Z","title_canon_sha256":"edb3563d9967f981953ebc4f8ba5df417ec21a9a1df91a0be743a815109f8cf7"},"schema_version":"1.0","source":{"id":"1904.11138","kind":"arxiv","version":1}},"canonical_sha256":"3d97945af305fbcba44df74d1d61b0221279d536b6633479fd0629435723d91e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3d97945af305fbcba44df74d1d61b0221279d536b6633479fd0629435723d91e","first_computed_at":"2026-05-17T23:47:45.670555Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:47:45.670555Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Rm0ost8kBHMp93PsGpjT7hPdqzKtyEz+l8/Zqcd3/lL4gj91j9pnX6EozlGs0BG86Wa1hosfm0IU19My9tRvDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:47:45.671185Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.11138","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c7e2f32a7b0ea72e7f980165bfabdf2eed794626a1026314808e806d4fbb0367","sha256:03af33e59e9649097e5a17ea68c5977cb846c295cbe742eecbf38825a6ace082"],"state_sha256":"86a34003f0e21022a27004dbb4ab6335cd13f61797c3aed229d4a63bbbce8e76"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9TmWv3eJzJJsWipoAWvqSCmq938ld642l3oA/xTHhyI9vwF4rstZ8wVwxqyj2/LeKCTcg4lTVO0irgjZbNCCCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-12T10:28:26.607829Z","bundle_sha256":"bf21f25e1884a5cd58a3583bb4707d04ce358e99a9998188da898b6eaad938f8"}}