{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:OQIIEALXB2MU2SM6RMVN6THHSG","short_pith_number":"pith:OQIIEALX","canonical_record":{"source":{"id":"2410.01697","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-02T16:05:03Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"dafb5a0ba5bc4efa2310d0838bb20f2040c833c47ad10436f5af106d9357d47a","abstract_canon_sha256":"9b5fdeb6ab66d0d68b27dc72c66ed54eea69b3e51ea55fad0c395012b745daf2"},"schema_version":"1.0"},"canonical_sha256":"74108201770e994d499e8b2adf4ce7919971a1a8f0e29038044df269902f4bab","source":{"kind":"arxiv","id":"2410.01697","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.01697","created_at":"2026-07-05T11:29:02Z"},{"alias_kind":"arxiv_version","alias_value":"2410.01697v4","created_at":"2026-07-05T11:29:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.01697","created_at":"2026-07-05T11:29:02Z"},{"alias_kind":"pith_short_12","alias_value":"OQIIEALXB2MU","created_at":"2026-07-05T11:29:02Z"},{"alias_kind":"pith_short_16","alias_value":"OQIIEALXB2MU2SM6","created_at":"2026-07-05T11:29:02Z"},{"alias_kind":"pith_short_8","alias_value":"OQIIEALX","created_at":"2026-07-05T11:29:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:OQIIEALXB2MU2SM6RMVN6THHSG","target":"record","payload":{"canonical_record":{"source":{"id":"2410.01697","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-02T16:05:03Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"dafb5a0ba5bc4efa2310d0838bb20f2040c833c47ad10436f5af106d9357d47a","abstract_canon_sha256":"9b5fdeb6ab66d0d68b27dc72c66ed54eea69b3e51ea55fad0c395012b745daf2"},"schema_version":"1.0"},"canonical_sha256":"74108201770e994d499e8b2adf4ce7919971a1a8f0e29038044df269902f4bab","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:02.265692Z","signature_b64":"JpWyKqEF0DXc2Op2Ja8n90SP1988jgAQB5l6QCwkvUjXUZuDTjE8abg2gpbPc2oda0GEHEN/JUGES2c+wfcUDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"74108201770e994d499e8b2adf4ce7919971a1a8f0e29038044df269902f4bab","last_reissued_at":"2026-07-05T11:29:02.265106Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:02.265106Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.01697","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":"2026-07-05T11:29:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LDe6to5t4gCrs5JrG88L84/frvTVu1qDWXYFkaXvpInRqrQXbmGt3bob3dT3hSftY68YMyPnNmaIjYK19tXuAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T21:02:42.875061Z"},"content_sha256":"ea9a9c40c019dcb87f90a91841b788f24f1cad8071a8327b4ef3ef6037b33421","schema_version":"1.0","event_id":"sha256:ea9a9c40c019dcb87f90a91841b788f24f1cad8071a8327b4ef3ef6037b33421"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:OQIIEALXB2MU2SM6RMVN6THHSG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enhancing Adversarial Robustness through Multi-Objective Representation Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Sebastian Peitz, Sedjro Salomon Hotegni","submitted_at":"2024-10-02T16:05:03Z","abstract_excerpt":"Deep neural networks (DNNs) are vulnerable to small adversarial perturbations, which are tiny changes to the input data that appear insignificant but cause the model to produce drastically different outputs. Many defense methods require modifying model architectures during evaluation or performing test-time data purification. This not only introduces additional complexity but is often architecture-dependent. We show, however, that robust feature learning during training can significantly enhance DNN robustness. We propose MOREL, a multi-objective approach that aligns natural and adversarial fe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.01697","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2410.01697/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T11:29:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1H9tgkzkn3Y6qw1o7qmc9F073EckFr4TmKVrm5PB0lSsLgbnv4OkGNIH7BucGz+Djl4B2Im6hYEcRHfr3hHjAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T21:02:42.875561Z"},"content_sha256":"19e0fd33b70ca991a8c5a97b0056b4d2426c0c2492f55a27c4a87dcb3434fcc3","schema_version":"1.0","event_id":"sha256:19e0fd33b70ca991a8c5a97b0056b4d2426c0c2492f55a27c4a87dcb3434fcc3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OQIIEALXB2MU2SM6RMVN6THHSG/bundle.json","state_url":"https://pith.science/pith/OQIIEALXB2MU2SM6RMVN6THHSG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OQIIEALXB2MU2SM6RMVN6THHSG/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":"2026-08-12T21:02:42Z","links":{"resolver":"https://pith.science/pith/OQIIEALXB2MU2SM6RMVN6THHSG","bundle":"https://pith.science/pith/OQIIEALXB2MU2SM6RMVN6THHSG/bundle.json","state":"https://pith.science/pith/OQIIEALXB2MU2SM6RMVN6THHSG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OQIIEALXB2MU2SM6RMVN6THHSG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OQIIEALXB2MU2SM6RMVN6THHSG","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":"9b5fdeb6ab66d0d68b27dc72c66ed54eea69b3e51ea55fad0c395012b745daf2","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-02T16:05:03Z","title_canon_sha256":"dafb5a0ba5bc4efa2310d0838bb20f2040c833c47ad10436f5af106d9357d47a"},"schema_version":"1.0","source":{"id":"2410.01697","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.01697","created_at":"2026-07-05T11:29:02Z"},{"alias_kind":"arxiv_version","alias_value":"2410.01697v4","created_at":"2026-07-05T11:29:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.01697","created_at":"2026-07-05T11:29:02Z"},{"alias_kind":"pith_short_12","alias_value":"OQIIEALXB2MU","created_at":"2026-07-05T11:29:02Z"},{"alias_kind":"pith_short_16","alias_value":"OQIIEALXB2MU2SM6","created_at":"2026-07-05T11:29:02Z"},{"alias_kind":"pith_short_8","alias_value":"OQIIEALX","created_at":"2026-07-05T11:29:02Z"}],"graph_snapshots":[{"event_id":"sha256:19e0fd33b70ca991a8c5a97b0056b4d2426c0c2492f55a27c4a87dcb3434fcc3","target":"graph","created_at":"2026-07-05T11:29:02Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2410.01697/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep neural networks (DNNs) are vulnerable to small adversarial perturbations, which are tiny changes to the input data that appear insignificant but cause the model to produce drastically different outputs. Many defense methods require modifying model architectures during evaluation or performing test-time data purification. This not only introduces additional complexity but is often architecture-dependent. We show, however, that robust feature learning during training can significantly enhance DNN robustness. We propose MOREL, a multi-objective approach that aligns natural and adversarial fe","authors_text":"Sebastian Peitz, Sedjro Salomon Hotegni","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-02T16:05:03Z","title":"Enhancing Adversarial Robustness through Multi-Objective Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.01697","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:ea9a9c40c019dcb87f90a91841b788f24f1cad8071a8327b4ef3ef6037b33421","target":"record","created_at":"2026-07-05T11:29:02Z","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":"9b5fdeb6ab66d0d68b27dc72c66ed54eea69b3e51ea55fad0c395012b745daf2","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-02T16:05:03Z","title_canon_sha256":"dafb5a0ba5bc4efa2310d0838bb20f2040c833c47ad10436f5af106d9357d47a"},"schema_version":"1.0","source":{"id":"2410.01697","kind":"arxiv","version":4}},"canonical_sha256":"74108201770e994d499e8b2adf4ce7919971a1a8f0e29038044df269902f4bab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"74108201770e994d499e8b2adf4ce7919971a1a8f0e29038044df269902f4bab","first_computed_at":"2026-07-05T11:29:02.265106Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:29:02.265106Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JpWyKqEF0DXc2Op2Ja8n90SP1988jgAQB5l6QCwkvUjXUZuDTjE8abg2gpbPc2oda0GEHEN/JUGES2c+wfcUDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:29:02.265692Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.01697","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ea9a9c40c019dcb87f90a91841b788f24f1cad8071a8327b4ef3ef6037b33421","sha256:19e0fd33b70ca991a8c5a97b0056b4d2426c0c2492f55a27c4a87dcb3434fcc3"],"state_sha256":"5d417e3c928cc3791c54d8b0d017fabcbec9c4dd0477dc15b93503eba8822442"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mXRT19bspXQLeHN7ywEuk8GiI2ZS+txxKvQTlA2dkKZjxK+nnQj9kumlTsObWykIuF05d8CPIjXPS6A2+OJsAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T21:02:42.880075Z","bundle_sha256":"d97b1abb71f76fca3f020b19794fb62506672f315621e858434e37656bc0aa48"}}