{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:PTQ2SU4LYSUKIWHAO44YEAH6GE","short_pith_number":"pith:PTQ2SU4L","canonical_record":{"source":{"id":"1803.01442","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-05T00:17:05Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"0c031fddbbd167aaf0560bcb649fc2d3ef1a19d1e419ee87495fe4976da747d2","abstract_canon_sha256":"6bfec492eebf016e11e713ba66ac366589fa3073a2265ea41020a01a5c85fac0"},"schema_version":"1.0"},"canonical_sha256":"7ce1a9538bc4a8a458e077398200fe310eac3d2846ee7151ea09b442ff4acb20","source":{"kind":"arxiv","id":"1803.01442","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.01442","created_at":"2026-05-18T00:22:00Z"},{"alias_kind":"arxiv_version","alias_value":"1803.01442v1","created_at":"2026-05-18T00:22:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.01442","created_at":"2026-05-18T00:22:00Z"},{"alias_kind":"pith_short_12","alias_value":"PTQ2SU4LYSUK","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"PTQ2SU4LYSUKIWHA","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"PTQ2SU4L","created_at":"2026-05-18T12:32:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:PTQ2SU4LYSUKIWHAO44YEAH6GE","target":"record","payload":{"canonical_record":{"source":{"id":"1803.01442","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-05T00:17:05Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"0c031fddbbd167aaf0560bcb649fc2d3ef1a19d1e419ee87495fe4976da747d2","abstract_canon_sha256":"6bfec492eebf016e11e713ba66ac366589fa3073a2265ea41020a01a5c85fac0"},"schema_version":"1.0"},"canonical_sha256":"7ce1a9538bc4a8a458e077398200fe310eac3d2846ee7151ea09b442ff4acb20","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:00.679914Z","signature_b64":"tob19dxWuxpTrZpA3lWzxtGA+/CBXaZwUm3L9vBKBrm2EYaShGXqCr45d5jYTOJbXOm/k/oeJqUovjZUbSIwDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ce1a9538bc4a8a458e077398200fe310eac3d2846ee7151ea09b442ff4acb20","last_reissued_at":"2026-05-18T00:22:00.679155Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:00.679155Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1803.01442","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:22:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uHaFAit00rKLLcP/7BkGaTHIxbV2mzrelEJDH9GKnngjEDGcXJ7jVf4vjWHPjwN5qOXyKZ11tk7Q23df8wL0BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T19:25:01.420872Z"},"content_sha256":"3afb215e0d5854219593dc447c38dd1e2e208fb9011c2e6a44f0e38c51aa10f8","schema_version":"1.0","event_id":"sha256:3afb215e0d5854219593dc447c38dd1e2e208fb9011c2e6a44f0e38c51aa10f8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:PTQ2SU4LYSUKIWHAO44YEAH6GE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Stochastic Activation Pruning for Robust Adversarial Defense","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Anima Anandkumar, Aran Khanna, Guneet S. Dhillon, Jean Kossaifi, Jeremy Bernstein, Kamyar Azizzadenesheli, Zachary C. Lipton","submitted_at":"2018-03-05T00:17:05Z","abstract_excerpt":"Neural networks are known to be vulnerable to adversarial examples. Carefully chosen perturbations to real images, while imperceptible to humans, induce misclassification and threaten the reliability of deep learning systems in the wild. To guard against adversarial examples, we take inspiration from game theory and cast the problem as a minimax zero-sum game between the adversary and the model. In general, for such games, the optimal strategy for both players requires a stochastic policy, also known as a mixed strategy. In this light, we propose Stochastic Activation Pruning (SAP), a mixed st"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.01442","kind":"arxiv","version":1},"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":"2026-05-18T00:22:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6PeQaBGGx66HxN3CmXqdczeLULoB9UCXj1WmVqvdFUBFPVkwNnm+nGU8c2w2SZTKAwreiAlb31cK8JjrXv2aAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-02T19:25:01.421219Z"},"content_sha256":"d0489a01955a89bc36fd0c570622dda653bc998e73bf07563c6a1f16909ae7ee","schema_version":"1.0","event_id":"sha256:d0489a01955a89bc36fd0c570622dda653bc998e73bf07563c6a1f16909ae7ee"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PTQ2SU4LYSUKIWHAO44YEAH6GE/bundle.json","state_url":"https://pith.science/pith/PTQ2SU4LYSUKIWHAO44YEAH6GE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PTQ2SU4LYSUKIWHAO44YEAH6GE/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":"2026-07-02T19:25:01Z","links":{"resolver":"https://pith.science/pith/PTQ2SU4LYSUKIWHAO44YEAH6GE","bundle":"https://pith.science/pith/PTQ2SU4LYSUKIWHAO44YEAH6GE/bundle.json","state":"https://pith.science/pith/PTQ2SU4LYSUKIWHAO44YEAH6GE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PTQ2SU4LYSUKIWHAO44YEAH6GE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:PTQ2SU4LYSUKIWHAO44YEAH6GE","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":"6bfec492eebf016e11e713ba66ac366589fa3073a2265ea41020a01a5c85fac0","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-05T00:17:05Z","title_canon_sha256":"0c031fddbbd167aaf0560bcb649fc2d3ef1a19d1e419ee87495fe4976da747d2"},"schema_version":"1.0","source":{"id":"1803.01442","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.01442","created_at":"2026-05-18T00:22:00Z"},{"alias_kind":"arxiv_version","alias_value":"1803.01442v1","created_at":"2026-05-18T00:22:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.01442","created_at":"2026-05-18T00:22:00Z"},{"alias_kind":"pith_short_12","alias_value":"PTQ2SU4LYSUK","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"PTQ2SU4LYSUKIWHA","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"PTQ2SU4L","created_at":"2026-05-18T12:32:46Z"}],"graph_snapshots":[{"event_id":"sha256:d0489a01955a89bc36fd0c570622dda653bc998e73bf07563c6a1f16909ae7ee","target":"graph","created_at":"2026-05-18T00:22:00Z","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":"Neural networks are known to be vulnerable to adversarial examples. Carefully chosen perturbations to real images, while imperceptible to humans, induce misclassification and threaten the reliability of deep learning systems in the wild. To guard against adversarial examples, we take inspiration from game theory and cast the problem as a minimax zero-sum game between the adversary and the model. In general, for such games, the optimal strategy for both players requires a stochastic policy, also known as a mixed strategy. In this light, we propose Stochastic Activation Pruning (SAP), a mixed st","authors_text":"Anima Anandkumar, Aran Khanna, Guneet S. Dhillon, Jean Kossaifi, Jeremy Bernstein, Kamyar Azizzadenesheli, Zachary C. Lipton","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-05T00:17:05Z","title":"Stochastic Activation Pruning for Robust Adversarial Defense"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.01442","kind":"arxiv","version":1},"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":"sha256:3afb215e0d5854219593dc447c38dd1e2e208fb9011c2e6a44f0e38c51aa10f8","target":"record","created_at":"2026-05-18T00:22:00Z","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":"6bfec492eebf016e11e713ba66ac366589fa3073a2265ea41020a01a5c85fac0","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-05T00:17:05Z","title_canon_sha256":"0c031fddbbd167aaf0560bcb649fc2d3ef1a19d1e419ee87495fe4976da747d2"},"schema_version":"1.0","source":{"id":"1803.01442","kind":"arxiv","version":1}},"canonical_sha256":"7ce1a9538bc4a8a458e077398200fe310eac3d2846ee7151ea09b442ff4acb20","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7ce1a9538bc4a8a458e077398200fe310eac3d2846ee7151ea09b442ff4acb20","first_computed_at":"2026-05-18T00:22:00.679155Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:22:00.679155Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tob19dxWuxpTrZpA3lWzxtGA+/CBXaZwUm3L9vBKBrm2EYaShGXqCr45d5jYTOJbXOm/k/oeJqUovjZUbSIwDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:22:00.679914Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.01442","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3afb215e0d5854219593dc447c38dd1e2e208fb9011c2e6a44f0e38c51aa10f8","sha256:d0489a01955a89bc36fd0c570622dda653bc998e73bf07563c6a1f16909ae7ee"],"state_sha256":"15dc926d056692ad0f5162602c4efb7db752ac7d089cb8b1bf19b9eed26d84cc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vvUn2eThVORo/sRRwvW6P7z/upGPg/12AWPT2LZQZKqcr59n3YQkpGgWEAI0zm6qVvlROAf+lp5acyFUJy+MCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-02T19:25:01.423358Z","bundle_sha256":"f0ca378d61aeddf1b222b04a7edc84a63d0133cd61ed1b5ef9751ac499b04fb2"}}