{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:PCMURXQPOLQO6GBWGRTNFJNRLW","short_pith_number":"pith:PCMURXQP","canonical_record":{"source":{"id":"1511.06328","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-19T19:46:39Z","cross_cats_sorted":[],"title_canon_sha256":"78188734815b1dfe5c3fc531f29fba8566974c72be6eaba58ec1c7545f5b6f6f","abstract_canon_sha256":"7bace4d7f7c2709b1253ee727713114d1cab058d70eb45157813b3b574b503d6"},"schema_version":"1.0"},"canonical_sha256":"789948de0f72e0ef18363466d2a5b15da7533a053a322967c868e7b9c4f90161","source":{"kind":"arxiv","id":"1511.06328","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1511.06328","created_at":"2026-05-18T01:23:11Z"},{"alias_kind":"arxiv_version","alias_value":"1511.06328v3","created_at":"2026-05-18T01:23:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.06328","created_at":"2026-05-18T01:23:11Z"},{"alias_kind":"pith_short_12","alias_value":"PCMURXQPOLQO","created_at":"2026-05-18T12:29:37Z"},{"alias_kind":"pith_short_16","alias_value":"PCMURXQPOLQO6GBW","created_at":"2026-05-18T12:29:37Z"},{"alias_kind":"pith_short_8","alias_value":"PCMURXQP","created_at":"2026-05-18T12:29:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:PCMURXQPOLQO6GBWGRTNFJNRLW","target":"record","payload":{"canonical_record":{"source":{"id":"1511.06328","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-19T19:46:39Z","cross_cats_sorted":[],"title_canon_sha256":"78188734815b1dfe5c3fc531f29fba8566974c72be6eaba58ec1c7545f5b6f6f","abstract_canon_sha256":"7bace4d7f7c2709b1253ee727713114d1cab058d70eb45157813b3b574b503d6"},"schema_version":"1.0"},"canonical_sha256":"789948de0f72e0ef18363466d2a5b15da7533a053a322967c868e7b9c4f90161","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:23:11.821874Z","signature_b64":"kgJNwhLtsZUpBFy210dOG/2t1CFFYVbCKl55WGeK1rKZptFnZLNGyU7wAdbVdUNPd0ufPO1D56MHbk32p096Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"789948de0f72e0ef18363466d2a5b15da7533a053a322967c868e7b9c4f90161","last_reissued_at":"2026-05-18T01:23:11.821428Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:23:11.821428Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1511.06328","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":"2026-05-18T01:23:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/XyezIY1M/Pg8gzU4FkCY/KdzeNUbHCbhWGVWJZRt3drMS5M85peAJ255ZQDLldWY7SwxxYiG4Y7QXyB6le4Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T07:00:12.698885Z"},"content_sha256":"5387896c36610e10b324705026a7918daba57ac545a2f71c77bde6e3425466fc","schema_version":"1.0","event_id":"sha256:5387896c36610e10b324705026a7918daba57ac545a2f71c77bde6e3425466fc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:PCMURXQPOLQO6GBWGRTNFJNRLW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Manifold Regularized Discriminative Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Shuangfei Zhai, Zhongfei Zhang","submitted_at":"2015-11-19T19:46:39Z","abstract_excerpt":"Unregularized deep neural networks (DNNs) can be easily overfit with a limited sample size. We argue that this is mostly due to the disriminative nature of DNNs which directly model the conditional probability (or score) of labels given the input. The ignorance of input distribution makes DNNs difficult to generalize to unseen data. Recent advances in regularization techniques, such as pretraining and dropout, indicate that modeling input data distribution (either explicitly or implicitly) greatly improves the generalization ability of a DNN. In this work, we explore the manifold hypothesis wh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.06328","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":"2026-05-18T01:23:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"duvRvEWBNEyMetKm6ijZuR59oESnYoe6iqrZ3cGTL6M2N8H9R/0OS1iiv4cSGfdnPYkmXlJMnzywlzWlbBHkCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T07:00:12.699235Z"},"content_sha256":"715e7241e3e64a3deca39acaf2b2b80ab61a8535fc5606c79afd382b1306761d","schema_version":"1.0","event_id":"sha256:715e7241e3e64a3deca39acaf2b2b80ab61a8535fc5606c79afd382b1306761d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PCMURXQPOLQO6GBWGRTNFJNRLW/bundle.json","state_url":"https://pith.science/pith/PCMURXQPOLQO6GBWGRTNFJNRLW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PCMURXQPOLQO6GBWGRTNFJNRLW/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":"2026-05-30T07:00:12Z","links":{"resolver":"https://pith.science/pith/PCMURXQPOLQO6GBWGRTNFJNRLW","bundle":"https://pith.science/pith/PCMURXQPOLQO6GBWGRTNFJNRLW/bundle.json","state":"https://pith.science/pith/PCMURXQPOLQO6GBWGRTNFJNRLW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PCMURXQPOLQO6GBWGRTNFJNRLW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:PCMURXQPOLQO6GBWGRTNFJNRLW","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":"7bace4d7f7c2709b1253ee727713114d1cab058d70eb45157813b3b574b503d6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-19T19:46:39Z","title_canon_sha256":"78188734815b1dfe5c3fc531f29fba8566974c72be6eaba58ec1c7545f5b6f6f"},"schema_version":"1.0","source":{"id":"1511.06328","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1511.06328","created_at":"2026-05-18T01:23:11Z"},{"alias_kind":"arxiv_version","alias_value":"1511.06328v3","created_at":"2026-05-18T01:23:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.06328","created_at":"2026-05-18T01:23:11Z"},{"alias_kind":"pith_short_12","alias_value":"PCMURXQPOLQO","created_at":"2026-05-18T12:29:37Z"},{"alias_kind":"pith_short_16","alias_value":"PCMURXQPOLQO6GBW","created_at":"2026-05-18T12:29:37Z"},{"alias_kind":"pith_short_8","alias_value":"PCMURXQP","created_at":"2026-05-18T12:29:37Z"}],"graph_snapshots":[{"event_id":"sha256:715e7241e3e64a3deca39acaf2b2b80ab61a8535fc5606c79afd382b1306761d","target":"graph","created_at":"2026-05-18T01:23:11Z","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":"Unregularized deep neural networks (DNNs) can be easily overfit with a limited sample size. We argue that this is mostly due to the disriminative nature of DNNs which directly model the conditional probability (or score) of labels given the input. The ignorance of input distribution makes DNNs difficult to generalize to unseen data. Recent advances in regularization techniques, such as pretraining and dropout, indicate that modeling input data distribution (either explicitly or implicitly) greatly improves the generalization ability of a DNN. In this work, we explore the manifold hypothesis wh","authors_text":"Shuangfei Zhai, Zhongfei Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-19T19:46:39Z","title":"Manifold Regularized Discriminative Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.06328","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":"sha256:5387896c36610e10b324705026a7918daba57ac545a2f71c77bde6e3425466fc","target":"record","created_at":"2026-05-18T01:23:11Z","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":"7bace4d7f7c2709b1253ee727713114d1cab058d70eb45157813b3b574b503d6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-19T19:46:39Z","title_canon_sha256":"78188734815b1dfe5c3fc531f29fba8566974c72be6eaba58ec1c7545f5b6f6f"},"schema_version":"1.0","source":{"id":"1511.06328","kind":"arxiv","version":3}},"canonical_sha256":"789948de0f72e0ef18363466d2a5b15da7533a053a322967c868e7b9c4f90161","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"789948de0f72e0ef18363466d2a5b15da7533a053a322967c868e7b9c4f90161","first_computed_at":"2026-05-18T01:23:11.821428Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:23:11.821428Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kgJNwhLtsZUpBFy210dOG/2t1CFFYVbCKl55WGeK1rKZptFnZLNGyU7wAdbVdUNPd0ufPO1D56MHbk32p096Cg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:23:11.821874Z","signed_message":"canonical_sha256_bytes"},"source_id":"1511.06328","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5387896c36610e10b324705026a7918daba57ac545a2f71c77bde6e3425466fc","sha256:715e7241e3e64a3deca39acaf2b2b80ab61a8535fc5606c79afd382b1306761d"],"state_sha256":"60c55d9c4541d2de0263d42fa6805e2cf98e455eb7a5ef885add28bddaf2456c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jKpwYgOr0yD+ewnUrTJsahtzm5Z23Xwgcbdn/dNhZ9gESA1C0oXTy/8uijdDYh2CZ1YfY7KmmOwA2EAy+tBBBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T07:00:12.701330Z","bundle_sha256":"e30e43c282e7eaed33f629428290c26d937a3545a2fe898ba0322a6b8ebeee34"}}