{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:HWIIX32FSUXQTG5CMNEILE4YNS","short_pith_number":"pith:HWIIX32F","schema_version":"1.0","canonical_sha256":"3d908bef45952f099ba263488593986c928f3f1a7408f7943d80d026d6e117a4","source":{"kind":"arxiv","id":"2102.01886","version":4},"attestation_state":"computed","paper":{"title":"Learning Diverse-Structured Networks for Adversarial Robustness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Bo Han, Gang Niu, Jingfeng Zhang, Junzhou Huang, Masashi Sugiyama, Tongliang Liu, Xuefeng Du, Yu Rong","submitted_at":"2021-02-03T05:52:11Z","abstract_excerpt":"In adversarial training (AT), the main focus has been the objective and optimizer while the model has been less studied, so that the models being used are still those classic ones in standard training (ST). Classic network architectures (NAs) are generally worse than searched NAs in ST, which should be the same in AT. In this paper, we argue that NA and AT cannot be handled independently, since given a dataset, the optimal NA in ST would be no longer optimal in AT. That being said, AT is time-consuming itself; if we directly search NAs in AT over large search spaces, the computation will be pr"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2102.01886","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-03T05:52:11Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"985badd450baffbe1d1caa84170790e6980e5843704cd322a4420ab7b82f331b","abstract_canon_sha256":"ac0b1d1855a8b848a8ef461747a037c12c397cbf6ebaa7a9cda2d839f8b257a1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:50:28.925092Z","signature_b64":"iBPGHE4wKQN6q71U6Ln87WnREB23n24OFg6X0Fi4l7WD48fldImOrZkYSd6WVSuK6hZiD/rMiqvPL9y2UAEBBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3d908bef45952f099ba263488593986c928f3f1a7408f7943d80d026d6e117a4","last_reissued_at":"2026-07-05T02:50:28.924616Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:50:28.924616Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Diverse-Structured Networks for Adversarial Robustness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Bo Han, Gang Niu, Jingfeng Zhang, Junzhou Huang, Masashi Sugiyama, Tongliang Liu, Xuefeng Du, Yu Rong","submitted_at":"2021-02-03T05:52:11Z","abstract_excerpt":"In adversarial training (AT), the main focus has been the objective and optimizer while the model has been less studied, so that the models being used are still those classic ones in standard training (ST). Classic network architectures (NAs) are generally worse than searched NAs in ST, which should be the same in AT. In this paper, we argue that NA and AT cannot be handled independently, since given a dataset, the optimal NA in ST would be no longer optimal in AT. That being said, AT is time-consuming itself; if we directly search NAs in AT over large search spaces, the computation will be pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.01886","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/2102.01886/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2102.01886","created_at":"2026-07-05T02:50:28.924674+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.01886v4","created_at":"2026-07-05T02:50:28.924674+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.01886","created_at":"2026-07-05T02:50:28.924674+00:00"},{"alias_kind":"pith_short_12","alias_value":"HWIIX32FSUXQ","created_at":"2026-07-05T02:50:28.924674+00:00"},{"alias_kind":"pith_short_16","alias_value":"HWIIX32FSUXQTG5C","created_at":"2026-07-05T02:50:28.924674+00:00"},{"alias_kind":"pith_short_8","alias_value":"HWIIX32F","created_at":"2026-07-05T02:50:28.924674+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HWIIX32FSUXQTG5CMNEILE4YNS","json":"https://pith.science/pith/HWIIX32FSUXQTG5CMNEILE4YNS.json","graph_json":"https://pith.science/api/pith-number/HWIIX32FSUXQTG5CMNEILE4YNS/graph.json","events_json":"https://pith.science/api/pith-number/HWIIX32FSUXQTG5CMNEILE4YNS/events.json","paper":"https://pith.science/paper/HWIIX32F"},"agent_actions":{"view_html":"https://pith.science/pith/HWIIX32FSUXQTG5CMNEILE4YNS","download_json":"https://pith.science/pith/HWIIX32FSUXQTG5CMNEILE4YNS.json","view_paper":"https://pith.science/paper/HWIIX32F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.01886&json=true","fetch_graph":"https://pith.science/api/pith-number/HWIIX32FSUXQTG5CMNEILE4YNS/graph.json","fetch_events":"https://pith.science/api/pith-number/HWIIX32FSUXQTG5CMNEILE4YNS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HWIIX32FSUXQTG5CMNEILE4YNS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HWIIX32FSUXQTG5CMNEILE4YNS/action/storage_attestation","attest_author":"https://pith.science/pith/HWIIX32FSUXQTG5CMNEILE4YNS/action/author_attestation","sign_citation":"https://pith.science/pith/HWIIX32FSUXQTG5CMNEILE4YNS/action/citation_signature","submit_replication":"https://pith.science/pith/HWIIX32FSUXQTG5CMNEILE4YNS/action/replication_record"}},"created_at":"2026-07-05T02:50:28.924674+00:00","updated_at":"2026-07-05T02:50:28.924674+00:00"}