{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:EDMCJCZ3X35NJR56BQM7STYBZ2","short_pith_number":"pith:EDMCJCZ3","canonical_record":{"source":{"id":"1611.01236","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-11-04T01:11:02Z","cross_cats_sorted":["cs.CR","cs.LG","stat.ML"],"title_canon_sha256":"b29db9b466b4050f16d529f3e5f7a0840734f55080ba6ea688ec061b4fc75f70","abstract_canon_sha256":"984b46bfdc29c2c3ec5d218cc8a5cb58bdf791ed37ed96e33bc86881af55474e"},"schema_version":"1.0"},"canonical_sha256":"20d8248b3bbefad4c7be0c19f94f01ceba06453631b591c4fd4d8caa9cddba52","source":{"kind":"arxiv","id":"1611.01236","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.01236","created_at":"2026-05-18T00:50:56Z"},{"alias_kind":"arxiv_version","alias_value":"1611.01236v2","created_at":"2026-05-18T00:50:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.01236","created_at":"2026-05-18T00:50:56Z"},{"alias_kind":"pith_short_12","alias_value":"EDMCJCZ3X35N","created_at":"2026-05-18T12:30:12Z"},{"alias_kind":"pith_short_16","alias_value":"EDMCJCZ3X35NJR56","created_at":"2026-05-18T12:30:12Z"},{"alias_kind":"pith_short_8","alias_value":"EDMCJCZ3","created_at":"2026-05-18T12:30:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:EDMCJCZ3X35NJR56BQM7STYBZ2","target":"record","payload":{"canonical_record":{"source":{"id":"1611.01236","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-11-04T01:11:02Z","cross_cats_sorted":["cs.CR","cs.LG","stat.ML"],"title_canon_sha256":"b29db9b466b4050f16d529f3e5f7a0840734f55080ba6ea688ec061b4fc75f70","abstract_canon_sha256":"984b46bfdc29c2c3ec5d218cc8a5cb58bdf791ed37ed96e33bc86881af55474e"},"schema_version":"1.0"},"canonical_sha256":"20d8248b3bbefad4c7be0c19f94f01ceba06453631b591c4fd4d8caa9cddba52","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:50:56.425336Z","signature_b64":"1Tt7dWNuH/irIZPraRaR44wsDCZ5ua8CMtlpXjdM4L/Aj4YatpnljiD1sMfPXEM+pnvBvJ8WT7dthEjdU78sBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"20d8248b3bbefad4c7be0c19f94f01ceba06453631b591c4fd4d8caa9cddba52","last_reissued_at":"2026-05-18T00:50:56.424594Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:50:56.424594Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1611.01236","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":"2026-05-18T00:50:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bcrNSGQsQLXbQVIq3TLsTlepkj9cYTYk8nW/O3iSzV95uN3OENU3AxkASwkgRhuFgozT4+ha/qEkl331hnLNBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T07:23:35.480788Z"},"content_sha256":"5a5f741db5234eb0a0d831aced5de3b0d37c88a50cbabfe8edf0e3eb8d017ad5","schema_version":"1.0","event_id":"sha256:5a5f741db5234eb0a0d831aced5de3b0d37c88a50cbabfe8edf0e3eb8d017ad5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:EDMCJCZ3X35NJR56BQM7STYBZ2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adversarial Machine Learning at Scale","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Alexey Kurakin, Ian Goodfellow, Samy Bengio","submitted_at":"2016-11-04T01:11:02Z","abstract_excerpt":"Adversarial examples are malicious inputs designed to fool machine learning models. They often transfer from one model to another, allowing attackers to mount black box attacks without knowledge of the target model's parameters. Adversarial training is the process of explicitly training a model on adversarial examples, in order to make it more robust to attack or to reduce its test error on clean inputs. So far, adversarial training has primarily been applied to small problems. In this research, we apply adversarial training to ImageNet. Our contributions include: (1) recommendations for how t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.01236","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":"2026-05-18T00:50:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZcMEU/9XuDPRQPglO6OF6i9SEAo1MCIiqVw2dupj29ekPxMRO/SeMF1qsYlNT2ZR2RxI8EBCmHSziCSN4jKzAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T07:23:35.481387Z"},"content_sha256":"a92e455401f12465b1cd2e0807eb850d41c6104b3b3c9d00c61cd884cab0b411","schema_version":"1.0","event_id":"sha256:a92e455401f12465b1cd2e0807eb850d41c6104b3b3c9d00c61cd884cab0b411"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EDMCJCZ3X35NJR56BQM7STYBZ2/bundle.json","state_url":"https://pith.science/pith/EDMCJCZ3X35NJR56BQM7STYBZ2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EDMCJCZ3X35NJR56BQM7STYBZ2/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":"2026-05-19T07:23:35Z","links":{"resolver":"https://pith.science/pith/EDMCJCZ3X35NJR56BQM7STYBZ2","bundle":"https://pith.science/pith/EDMCJCZ3X35NJR56BQM7STYBZ2/bundle.json","state":"https://pith.science/pith/EDMCJCZ3X35NJR56BQM7STYBZ2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EDMCJCZ3X35NJR56BQM7STYBZ2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:EDMCJCZ3X35NJR56BQM7STYBZ2","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":"984b46bfdc29c2c3ec5d218cc8a5cb58bdf791ed37ed96e33bc86881af55474e","cross_cats_sorted":["cs.CR","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-11-04T01:11:02Z","title_canon_sha256":"b29db9b466b4050f16d529f3e5f7a0840734f55080ba6ea688ec061b4fc75f70"},"schema_version":"1.0","source":{"id":"1611.01236","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1611.01236","created_at":"2026-05-18T00:50:56Z"},{"alias_kind":"arxiv_version","alias_value":"1611.01236v2","created_at":"2026-05-18T00:50:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.01236","created_at":"2026-05-18T00:50:56Z"},{"alias_kind":"pith_short_12","alias_value":"EDMCJCZ3X35N","created_at":"2026-05-18T12:30:12Z"},{"alias_kind":"pith_short_16","alias_value":"EDMCJCZ3X35NJR56","created_at":"2026-05-18T12:30:12Z"},{"alias_kind":"pith_short_8","alias_value":"EDMCJCZ3","created_at":"2026-05-18T12:30:12Z"}],"graph_snapshots":[{"event_id":"sha256:a92e455401f12465b1cd2e0807eb850d41c6104b3b3c9d00c61cd884cab0b411","target":"graph","created_at":"2026-05-18T00:50:56Z","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":"Adversarial examples are malicious inputs designed to fool machine learning models. They often transfer from one model to another, allowing attackers to mount black box attacks without knowledge of the target model's parameters. Adversarial training is the process of explicitly training a model on adversarial examples, in order to make it more robust to attack or to reduce its test error on clean inputs. So far, adversarial training has primarily been applied to small problems. In this research, we apply adversarial training to ImageNet. Our contributions include: (1) recommendations for how t","authors_text":"Alexey Kurakin, Ian Goodfellow, Samy Bengio","cross_cats":["cs.CR","cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-11-04T01:11:02Z","title":"Adversarial Machine Learning at Scale"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.01236","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":"sha256:5a5f741db5234eb0a0d831aced5de3b0d37c88a50cbabfe8edf0e3eb8d017ad5","target":"record","created_at":"2026-05-18T00:50:56Z","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":"984b46bfdc29c2c3ec5d218cc8a5cb58bdf791ed37ed96e33bc86881af55474e","cross_cats_sorted":["cs.CR","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-11-04T01:11:02Z","title_canon_sha256":"b29db9b466b4050f16d529f3e5f7a0840734f55080ba6ea688ec061b4fc75f70"},"schema_version":"1.0","source":{"id":"1611.01236","kind":"arxiv","version":2}},"canonical_sha256":"20d8248b3bbefad4c7be0c19f94f01ceba06453631b591c4fd4d8caa9cddba52","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"20d8248b3bbefad4c7be0c19f94f01ceba06453631b591c4fd4d8caa9cddba52","first_computed_at":"2026-05-18T00:50:56.424594Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:50:56.424594Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1Tt7dWNuH/irIZPraRaR44wsDCZ5ua8CMtlpXjdM4L/Aj4YatpnljiD1sMfPXEM+pnvBvJ8WT7dthEjdU78sBg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:50:56.425336Z","signed_message":"canonical_sha256_bytes"},"source_id":"1611.01236","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5a5f741db5234eb0a0d831aced5de3b0d37c88a50cbabfe8edf0e3eb8d017ad5","sha256:a92e455401f12465b1cd2e0807eb850d41c6104b3b3c9d00c61cd884cab0b411"],"state_sha256":"7ceb06848a1496e2c6f1772e40ef72782d3f5fcadc503b0dc1ef517d05d6e4b8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"91pGEeCkD+9JpHfwb+c6soyZ3h5m9Snzet2CWLHanAHHRG+WN0XwcCuf9ZVSMrEQvD3hlgNZ3VBBOhIkxQAUCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-19T07:23:35.484128Z","bundle_sha256":"871f7e649293f8abe85614673514e9e257a0cec5019dc24d0ffa4337c1b0982a"}}