{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:KXY3472OAJVUDKIZWWV7ER2DPK","short_pith_number":"pith:KXY3472O","canonical_record":{"source":{"id":"1905.13074","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-30T14:32:21Z","cross_cats_sorted":[],"title_canon_sha256":"1d6f37198581095f15c7bd5bed994b47224a9d34cce45fab8fce6d08a78c64a6","abstract_canon_sha256":"912cd96df3743782bb3868bab48c95be5ab5b3b365d389653cf1f87d5cf2bbc1"},"schema_version":"1.0"},"canonical_sha256":"55f1be7f4e026b41a919b5abf247437aa627ea9cc9ffaaabffc8643bf664bd24","source":{"kind":"arxiv","id":"1905.13074","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.13074","created_at":"2026-05-17T23:44:38Z"},{"alias_kind":"arxiv_version","alias_value":"1905.13074v1","created_at":"2026-05-17T23:44:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.13074","created_at":"2026-05-17T23:44:38Z"},{"alias_kind":"pith_short_12","alias_value":"KXY3472OAJVU","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"KXY3472OAJVUDKIZ","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"KXY3472O","created_at":"2026-05-18T12:33:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:KXY3472OAJVUDKIZWWV7ER2DPK","target":"record","payload":{"canonical_record":{"source":{"id":"1905.13074","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-30T14:32:21Z","cross_cats_sorted":[],"title_canon_sha256":"1d6f37198581095f15c7bd5bed994b47224a9d34cce45fab8fce6d08a78c64a6","abstract_canon_sha256":"912cd96df3743782bb3868bab48c95be5ab5b3b365d389653cf1f87d5cf2bbc1"},"schema_version":"1.0"},"canonical_sha256":"55f1be7f4e026b41a919b5abf247437aa627ea9cc9ffaaabffc8643bf664bd24","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:38.985777Z","signature_b64":"gLj9H5tofSmqVAhfuOzDJcZTv5lYMpFh96BfGYGDYTgqJvWaAFJRhHBlia4A2fR2pP6kZFbkr1rxcufzm2yPDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55f1be7f4e026b41a919b5abf247437aa627ea9cc9ffaaabffc8643bf664bd24","last_reissued_at":"2026-05-17T23:44:38.985253Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:38.985253Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.13074","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":"2026-05-17T23:44:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bA1PnkMqJirhutEbfpEqzWD5SIZZX0PLh3aPglUbK+BdoAZVzmlnpb7NXL3pgdbP4tSHgpJ8Tgopyi5ovQG9BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T16:18:17.254197Z"},"content_sha256":"cd02fc21f4dfa385b87e37b6eb53866eaafd443e5ca30dadbc42b9c981ef4f0d","schema_version":"1.0","event_id":"sha256:cd02fc21f4dfa385b87e37b6eb53866eaafd443e5ca30dadbc42b9c981ef4f0d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:KXY3472OAJVUDKIZWWV7ER2DPK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Robust Sparse Regularization: Simultaneously Optimizing Neural Network Robustness and Compactness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adnan Siraj Rakin, Deliang Fan, Liqiang Wang, Li Yang, Yanzhi Wang, Zhezhi He","submitted_at":"2019-05-30T14:32:21Z","abstract_excerpt":"Deep Neural Network (DNN) trained by the gradient descent method is known to be vulnerable to maliciously perturbed adversarial input, aka. adversarial attack. As one of the countermeasures against adversarial attack, increasing the model capacity for DNN robustness enhancement was discussed and reported as an effective approach by many recent works. In this work, we show that shrinking the model size through proper weight pruning can even be helpful to improve the DNN robustness under adversarial attack. For obtaining a simultaneously robust and compact DNN model, we propose a multi-objective"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.13074","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":"2026-05-17T23:44:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zp16wKcFU+ig9FZDiP7Qm5DGVpplzSrycg39az+0jIOC2Mzy0vFFZ1BdxSjK2fe6iAOsq3UNfxAjJ0dk2/w2Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T16:18:17.254574Z"},"content_sha256":"3277b2fb9aff2903ac2289676c1d07b84494f352885dfb9ab6e98d8f42058c9c","schema_version":"1.0","event_id":"sha256:3277b2fb9aff2903ac2289676c1d07b84494f352885dfb9ab6e98d8f42058c9c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KXY3472OAJVUDKIZWWV7ER2DPK/bundle.json","state_url":"https://pith.science/pith/KXY3472OAJVUDKIZWWV7ER2DPK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KXY3472OAJVUDKIZWWV7ER2DPK/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":"2026-05-20T16:18:17Z","links":{"resolver":"https://pith.science/pith/KXY3472OAJVUDKIZWWV7ER2DPK","bundle":"https://pith.science/pith/KXY3472OAJVUDKIZWWV7ER2DPK/bundle.json","state":"https://pith.science/pith/KXY3472OAJVUDKIZWWV7ER2DPK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KXY3472OAJVUDKIZWWV7ER2DPK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:KXY3472OAJVUDKIZWWV7ER2DPK","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":"912cd96df3743782bb3868bab48c95be5ab5b3b365d389653cf1f87d5cf2bbc1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-30T14:32:21Z","title_canon_sha256":"1d6f37198581095f15c7bd5bed994b47224a9d34cce45fab8fce6d08a78c64a6"},"schema_version":"1.0","source":{"id":"1905.13074","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.13074","created_at":"2026-05-17T23:44:38Z"},{"alias_kind":"arxiv_version","alias_value":"1905.13074v1","created_at":"2026-05-17T23:44:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.13074","created_at":"2026-05-17T23:44:38Z"},{"alias_kind":"pith_short_12","alias_value":"KXY3472OAJVU","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"KXY3472OAJVUDKIZ","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"KXY3472O","created_at":"2026-05-18T12:33:21Z"}],"graph_snapshots":[{"event_id":"sha256:3277b2fb9aff2903ac2289676c1d07b84494f352885dfb9ab6e98d8f42058c9c","target":"graph","created_at":"2026-05-17T23:44:38Z","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":"Deep Neural Network (DNN) trained by the gradient descent method is known to be vulnerable to maliciously perturbed adversarial input, aka. adversarial attack. As one of the countermeasures against adversarial attack, increasing the model capacity for DNN robustness enhancement was discussed and reported as an effective approach by many recent works. In this work, we show that shrinking the model size through proper weight pruning can even be helpful to improve the DNN robustness under adversarial attack. For obtaining a simultaneously robust and compact DNN model, we propose a multi-objective","authors_text":"Adnan Siraj Rakin, Deliang Fan, Liqiang Wang, Li Yang, Yanzhi Wang, Zhezhi He","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-30T14:32:21Z","title":"Robust Sparse Regularization: Simultaneously Optimizing Neural Network Robustness and Compactness"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.13074","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:cd02fc21f4dfa385b87e37b6eb53866eaafd443e5ca30dadbc42b9c981ef4f0d","target":"record","created_at":"2026-05-17T23:44:38Z","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":"912cd96df3743782bb3868bab48c95be5ab5b3b365d389653cf1f87d5cf2bbc1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-30T14:32:21Z","title_canon_sha256":"1d6f37198581095f15c7bd5bed994b47224a9d34cce45fab8fce6d08a78c64a6"},"schema_version":"1.0","source":{"id":"1905.13074","kind":"arxiv","version":1}},"canonical_sha256":"55f1be7f4e026b41a919b5abf247437aa627ea9cc9ffaaabffc8643bf664bd24","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"55f1be7f4e026b41a919b5abf247437aa627ea9cc9ffaaabffc8643bf664bd24","first_computed_at":"2026-05-17T23:44:38.985253Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:44:38.985253Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gLj9H5tofSmqVAhfuOzDJcZTv5lYMpFh96BfGYGDYTgqJvWaAFJRhHBlia4A2fR2pP6kZFbkr1rxcufzm2yPDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:44:38.985777Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.13074","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cd02fc21f4dfa385b87e37b6eb53866eaafd443e5ca30dadbc42b9c981ef4f0d","sha256:3277b2fb9aff2903ac2289676c1d07b84494f352885dfb9ab6e98d8f42058c9c"],"state_sha256":"57f35d4e053fdde30c1790cc0052c88af972ca5116d52723fc7a3ff4863732dd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xcrvrVK6Y+rG8uNoNpiHZ9i8O6igBVNI7VRQQ9qQ1t5yn2FPqaDOitJmveRC4fRiGEiBBGglFYEfENu8vTAtDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-20T16:18:17.256532Z","bundle_sha256":"33b10543411271a1422dfdd2c1b8c7e33e5fdb18870bf2f40b1da44223951db5"}}