{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:NSRHUXBVXXHHRGCUVFGAWDI5KA","short_pith_number":"pith:NSRHUXBV","canonical_record":{"source":{"id":"1511.06306","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-19T18:51:08Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"90d3dc2ae21107ff6bff1d9d066f159bc294ab2d02c9ac75713a7f3efa13542b","abstract_canon_sha256":"ec037f2a00f9fab0bc005c28caddccfc3ccea208d4d819b8fe5596159dbbd896"},"schema_version":"1.0"},"canonical_sha256":"6ca27a5c35bdce789854a94c0b0d1d5010b21632408212003a57dde61bc7fccd","source":{"kind":"arxiv","id":"1511.06306","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1511.06306","created_at":"2026-05-18T01:20:01Z"},{"alias_kind":"arxiv_version","alias_value":"1511.06306v2","created_at":"2026-05-18T01:20:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.06306","created_at":"2026-05-18T01:20:01Z"},{"alias_kind":"pith_short_12","alias_value":"NSRHUXBVXXHH","created_at":"2026-05-18T12:29:34Z"},{"alias_kind":"pith_short_16","alias_value":"NSRHUXBVXXHHRGCU","created_at":"2026-05-18T12:29:34Z"},{"alias_kind":"pith_short_8","alias_value":"NSRHUXBV","created_at":"2026-05-18T12:29:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:NSRHUXBVXXHHRGCUVFGAWDI5KA","target":"record","payload":{"canonical_record":{"source":{"id":"1511.06306","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-19T18:51:08Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"90d3dc2ae21107ff6bff1d9d066f159bc294ab2d02c9ac75713a7f3efa13542b","abstract_canon_sha256":"ec037f2a00f9fab0bc005c28caddccfc3ccea208d4d819b8fe5596159dbbd896"},"schema_version":"1.0"},"canonical_sha256":"6ca27a5c35bdce789854a94c0b0d1d5010b21632408212003a57dde61bc7fccd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:20:01.116440Z","signature_b64":"XdkhEZpFObwjietkrCB589Pl4AYrCCGfDk2TiaP5tENLnGriNGmYxeuPTnNURjxBH4WMaG0aDRFZQO7n0GixAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ca27a5c35bdce789854a94c0b0d1d5010b21632408212003a57dde61bc7fccd","last_reissued_at":"2026-05-18T01:20:01.115754Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:20:01.115754Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1511.06306","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":"2026-05-18T01:20:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H8Z/T931QfNpyoKOWjvnKGj6KIaAuHJeszSx9gW0lVmY9JHvgqM7dNjkCxxrB/PSp3HStiljHez+X1wJqhWwAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T13:11:01.140823Z"},"content_sha256":"db38f9247494e91882439851a668e5e3488d7c7c0d8aadfdb0b468ce00e0089b","schema_version":"1.0","event_id":"sha256:db38f9247494e91882439851a668e5e3488d7c7c0d8aadfdb0b468ce00e0089b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:NSRHUXBVXXHHRGCUVFGAWDI5KA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Robust Convolutional Neural Networks under Adversarial Noise","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Aysegul Dundar, Eugenio Culurciello, Jonghoon Jin","submitted_at":"2015-11-19T18:51:08Z","abstract_excerpt":"Recent studies have shown that Convolutional Neural Networks (CNNs) are vulnerable to a small perturbation of input called \"adversarial examples\". In this work, we propose a new feedforward CNN that improves robustness in the presence of adversarial noise. Our model uses stochastic additive noise added to the input image and to the CNN models. The proposed model operates in conjunction with a CNN trained with either standard or adversarial objective function. In particular, convolution, max-pooling, and ReLU layers are modified to benefit from the noise model. Our feedforward model is paramete"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.06306","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":"2026-05-18T01:20:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nK5uHGPoq758GYB3lS0GLCygG7yKeuHG9qEP7r0/vJM3tS/TYXFXQp+nCCilI5aFaEAmpRG8U5d9obgdJAO3AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T13:11:01.141566Z"},"content_sha256":"5d021665ed21b09d62862dac363c5292d0c2b54ce6d5a4da406fdf1826e3a37f","schema_version":"1.0","event_id":"sha256:5d021665ed21b09d62862dac363c5292d0c2b54ce6d5a4da406fdf1826e3a37f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NSRHUXBVXXHHRGCUVFGAWDI5KA/bundle.json","state_url":"https://pith.science/pith/NSRHUXBVXXHHRGCUVFGAWDI5KA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NSRHUXBVXXHHRGCUVFGAWDI5KA/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":"2026-05-30T13:11:01Z","links":{"resolver":"https://pith.science/pith/NSRHUXBVXXHHRGCUVFGAWDI5KA","bundle":"https://pith.science/pith/NSRHUXBVXXHHRGCUVFGAWDI5KA/bundle.json","state":"https://pith.science/pith/NSRHUXBVXXHHRGCUVFGAWDI5KA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NSRHUXBVXXHHRGCUVFGAWDI5KA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:NSRHUXBVXXHHRGCUVFGAWDI5KA","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":"ec037f2a00f9fab0bc005c28caddccfc3ccea208d4d819b8fe5596159dbbd896","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-19T18:51:08Z","title_canon_sha256":"90d3dc2ae21107ff6bff1d9d066f159bc294ab2d02c9ac75713a7f3efa13542b"},"schema_version":"1.0","source":{"id":"1511.06306","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1511.06306","created_at":"2026-05-18T01:20:01Z"},{"alias_kind":"arxiv_version","alias_value":"1511.06306v2","created_at":"2026-05-18T01:20:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.06306","created_at":"2026-05-18T01:20:01Z"},{"alias_kind":"pith_short_12","alias_value":"NSRHUXBVXXHH","created_at":"2026-05-18T12:29:34Z"},{"alias_kind":"pith_short_16","alias_value":"NSRHUXBVXXHHRGCU","created_at":"2026-05-18T12:29:34Z"},{"alias_kind":"pith_short_8","alias_value":"NSRHUXBV","created_at":"2026-05-18T12:29:34Z"}],"graph_snapshots":[{"event_id":"sha256:5d021665ed21b09d62862dac363c5292d0c2b54ce6d5a4da406fdf1826e3a37f","target":"graph","created_at":"2026-05-18T01:20:01Z","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":"Recent studies have shown that Convolutional Neural Networks (CNNs) are vulnerable to a small perturbation of input called \"adversarial examples\". In this work, we propose a new feedforward CNN that improves robustness in the presence of adversarial noise. Our model uses stochastic additive noise added to the input image and to the CNN models. The proposed model operates in conjunction with a CNN trained with either standard or adversarial objective function. In particular, convolution, max-pooling, and ReLU layers are modified to benefit from the noise model. Our feedforward model is paramete","authors_text":"Aysegul Dundar, Eugenio Culurciello, Jonghoon Jin","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-19T18:51:08Z","title":"Robust Convolutional Neural Networks under Adversarial Noise"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.06306","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:db38f9247494e91882439851a668e5e3488d7c7c0d8aadfdb0b468ce00e0089b","target":"record","created_at":"2026-05-18T01:20:01Z","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":"ec037f2a00f9fab0bc005c28caddccfc3ccea208d4d819b8fe5596159dbbd896","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-19T18:51:08Z","title_canon_sha256":"90d3dc2ae21107ff6bff1d9d066f159bc294ab2d02c9ac75713a7f3efa13542b"},"schema_version":"1.0","source":{"id":"1511.06306","kind":"arxiv","version":2}},"canonical_sha256":"6ca27a5c35bdce789854a94c0b0d1d5010b21632408212003a57dde61bc7fccd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6ca27a5c35bdce789854a94c0b0d1d5010b21632408212003a57dde61bc7fccd","first_computed_at":"2026-05-18T01:20:01.115754Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:20:01.115754Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XdkhEZpFObwjietkrCB589Pl4AYrCCGfDk2TiaP5tENLnGriNGmYxeuPTnNURjxBH4WMaG0aDRFZQO7n0GixAA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:20:01.116440Z","signed_message":"canonical_sha256_bytes"},"source_id":"1511.06306","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:db38f9247494e91882439851a668e5e3488d7c7c0d8aadfdb0b468ce00e0089b","sha256:5d021665ed21b09d62862dac363c5292d0c2b54ce6d5a4da406fdf1826e3a37f"],"state_sha256":"90b4d28a3210436390a0b4850ebaf8ea8d77c030ff40f714d80747b8f2c3abb8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Etug/YGs6TDFXWQJ8Up94xstjlBc6bTg8mqJX7d7Vzh0/BL9RWl0qemOM25SyfkAegqpeO8FIFDi5qCiRQqvAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T13:11:01.144976Z","bundle_sha256":"d0302542543757bade5cefcef7ae6c39fa5ca20d1256c62cf29a030ea5ac24f0"}}