{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:QGZQ3N5PX2J3KFEBGOLSBEVRUF","short_pith_number":"pith:QGZQ3N5P","canonical_record":{"source":{"id":"1802.09308","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-26T14:07:18Z","cross_cats_sorted":[],"title_canon_sha256":"9d60d7130a4f0b75cc7189906b75d40a42aa4fe6821847b80c9f3fa352fc5d9e","abstract_canon_sha256":"53e025670b4b7275272a1233338f556c37aecd7010cb133f96e7de53785d9392"},"schema_version":"1.0"},"canonical_sha256":"81b30db7afbe93b5148133972092b1a1460b980515d6a7672269b5e58333008d","source":{"kind":"arxiv","id":"1802.09308","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.09308","created_at":"2026-05-18T00:12:53Z"},{"alias_kind":"arxiv_version","alias_value":"1802.09308v2","created_at":"2026-05-18T00:12:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.09308","created_at":"2026-05-18T00:12:53Z"},{"alias_kind":"pith_short_12","alias_value":"QGZQ3N5PX2J3","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"QGZQ3N5PX2J3KFEB","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"QGZQ3N5P","created_at":"2026-05-18T12:32:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:QGZQ3N5PX2J3KFEBGOLSBEVRUF","target":"record","payload":{"canonical_record":{"source":{"id":"1802.09308","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-26T14:07:18Z","cross_cats_sorted":[],"title_canon_sha256":"9d60d7130a4f0b75cc7189906b75d40a42aa4fe6821847b80c9f3fa352fc5d9e","abstract_canon_sha256":"53e025670b4b7275272a1233338f556c37aecd7010cb133f96e7de53785d9392"},"schema_version":"1.0"},"canonical_sha256":"81b30db7afbe93b5148133972092b1a1460b980515d6a7672269b5e58333008d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:12:53.081947Z","signature_b64":"rSPIDAI361bfdwR6egTLvjn6RLpc1C7/fvbYDu9yJjGFdVL7C9Z+wu6MjoYvbqWNr6s3aRVej1EtQkI3RPHOCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81b30db7afbe93b5148133972092b1a1460b980515d6a7672269b5e58333008d","last_reissued_at":"2026-05-18T00:12:53.081160Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:12:53.081160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.09308","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:12:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kqepFZUIt3grlYT3ahL4g24zFbQA3Xomzw8hrqd3Aw0jOM0G7d+CL5r3VA19jSCUmP4yKaHnXFwZzEnR+qdfAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T14:42:43.458914Z"},"content_sha256":"d9045f52bae9d68a59f5356aac649906e54b35fb1526732bae2e11d0a28503e7","schema_version":"1.0","event_id":"sha256:d9045f52bae9d68a59f5356aac649906e54b35fb1526732bae2e11d0a28503e7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:QGZQ3N5PX2J3KFEBGOLSBEVRUF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Max-Mahalanobis Linear Discriminant Analysis Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chao Du, Jun Zhu, Tianyu Pang","submitted_at":"2018-02-26T14:07:18Z","abstract_excerpt":"A deep neural network (DNN) consists of a nonlinear transformation from an input to a feature representation, followed by a common softmax linear classifier. Though many efforts have been devoted to designing a proper architecture for nonlinear transformation, little investigation has been done on the classifier part. In this paper, we show that a properly designed classifier can improve robustness to adversarial attacks and lead to better prediction results. Specifically, we define a Max-Mahalanobis distribution (MMD) and theoretically show that if the input distributes as a MMD, the linear d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.09308","kind":"arxiv","version":2},"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":"2026-05-18T00:12:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G4sy0MIr/8UtB54f+lwTLDxbazUgPmn3YpOKeH+ZqJhaMiyiSbbTb2x9ybj5rWteoFgm7J4IbyyRy4gz6EkbAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T14:42:43.459281Z"},"content_sha256":"8ff4ea0f1edd4856d65f5c2cffa0eee3d6e7318e0251d8cc90be6e91840e42cf","schema_version":"1.0","event_id":"sha256:8ff4ea0f1edd4856d65f5c2cffa0eee3d6e7318e0251d8cc90be6e91840e42cf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QGZQ3N5PX2J3KFEBGOLSBEVRUF/bundle.json","state_url":"https://pith.science/pith/QGZQ3N5PX2J3KFEBGOLSBEVRUF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QGZQ3N5PX2J3KFEBGOLSBEVRUF/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":"2026-05-30T14:42:43Z","links":{"resolver":"https://pith.science/pith/QGZQ3N5PX2J3KFEBGOLSBEVRUF","bundle":"https://pith.science/pith/QGZQ3N5PX2J3KFEBGOLSBEVRUF/bundle.json","state":"https://pith.science/pith/QGZQ3N5PX2J3KFEBGOLSBEVRUF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QGZQ3N5PX2J3KFEBGOLSBEVRUF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:QGZQ3N5PX2J3KFEBGOLSBEVRUF","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":"53e025670b4b7275272a1233338f556c37aecd7010cb133f96e7de53785d9392","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-26T14:07:18Z","title_canon_sha256":"9d60d7130a4f0b75cc7189906b75d40a42aa4fe6821847b80c9f3fa352fc5d9e"},"schema_version":"1.0","source":{"id":"1802.09308","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.09308","created_at":"2026-05-18T00:12:53Z"},{"alias_kind":"arxiv_version","alias_value":"1802.09308v2","created_at":"2026-05-18T00:12:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.09308","created_at":"2026-05-18T00:12:53Z"},{"alias_kind":"pith_short_12","alias_value":"QGZQ3N5PX2J3","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"QGZQ3N5PX2J3KFEB","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"QGZQ3N5P","created_at":"2026-05-18T12:32:46Z"}],"graph_snapshots":[{"event_id":"sha256:8ff4ea0f1edd4856d65f5c2cffa0eee3d6e7318e0251d8cc90be6e91840e42cf","target":"graph","created_at":"2026-05-18T00:12:53Z","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":"A deep neural network (DNN) consists of a nonlinear transformation from an input to a feature representation, followed by a common softmax linear classifier. Though many efforts have been devoted to designing a proper architecture for nonlinear transformation, little investigation has been done on the classifier part. In this paper, we show that a properly designed classifier can improve robustness to adversarial attacks and lead to better prediction results. Specifically, we define a Max-Mahalanobis distribution (MMD) and theoretically show that if the input distributes as a MMD, the linear d","authors_text":"Chao Du, Jun Zhu, Tianyu Pang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-26T14:07:18Z","title":"Max-Mahalanobis Linear Discriminant Analysis Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.09308","kind":"arxiv","version":2},"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:d9045f52bae9d68a59f5356aac649906e54b35fb1526732bae2e11d0a28503e7","target":"record","created_at":"2026-05-18T00:12:53Z","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":"53e025670b4b7275272a1233338f556c37aecd7010cb133f96e7de53785d9392","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-26T14:07:18Z","title_canon_sha256":"9d60d7130a4f0b75cc7189906b75d40a42aa4fe6821847b80c9f3fa352fc5d9e"},"schema_version":"1.0","source":{"id":"1802.09308","kind":"arxiv","version":2}},"canonical_sha256":"81b30db7afbe93b5148133972092b1a1460b980515d6a7672269b5e58333008d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"81b30db7afbe93b5148133972092b1a1460b980515d6a7672269b5e58333008d","first_computed_at":"2026-05-18T00:12:53.081160Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:12:53.081160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rSPIDAI361bfdwR6egTLvjn6RLpc1C7/fvbYDu9yJjGFdVL7C9Z+wu6MjoYvbqWNr6s3aRVej1EtQkI3RPHOCw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:12:53.081947Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.09308","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d9045f52bae9d68a59f5356aac649906e54b35fb1526732bae2e11d0a28503e7","sha256:8ff4ea0f1edd4856d65f5c2cffa0eee3d6e7318e0251d8cc90be6e91840e42cf"],"state_sha256":"be5046b7ff3ea468e9efd7b75a88e3e230d95b507dc934d4fae788cdd23da9e2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WYHSE86m0/5gJtWyA74dOtKnGdkLhCFPLnXJ8SN3NsdGFPhwFjg0BZ0u5k0i2P+GkwEyA1nmzOUgz/XKttAiBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T14:42:43.461553Z","bundle_sha256":"2a9f31035f339c914ec657233e7654a18a3b3853c324a28cc16e7b175a85ffb4"}}