{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:M62LOABI64USMZFR777GV5IMKS","short_pith_number":"pith:M62LOABI","schema_version":"1.0","canonical_sha256":"67b4b70028f7292664b1fffe6af50c5483a39f8a43d3f59054a85b1f3a001697","source":{"kind":"arxiv","id":"2210.11620","version":2},"attestation_state":"computed","paper":{"title":"LOT: Layer-wise Orthogonal Training on Improving $\\ell_2$ Certified Robustness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bo Li, Linyi Li, Xiaojun Xu","submitted_at":"2022-10-20T22:31:26Z","abstract_excerpt":"Recent studies show that training deep neural networks (DNNs) with Lipschitz constraints are able to enhance adversarial robustness and other model properties such as stability. In this paper, we propose a layer-wise orthogonal training method (LOT) to effectively train 1-Lipschitz convolution layers via parametrizing an orthogonal matrix with an unconstrained matrix. We then efficiently compute the inverse square root of a convolution kernel by transforming the input domain to the Fourier frequency domain. On the other hand, as existing works show that semi-supervised training helps improve e"},"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":"2210.11620","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-20T22:31:26Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"6ec5a84ffbceff489aec3136fecdabaef14226ae38e017d589d8dd3b18563798","abstract_canon_sha256":"6ba84cdef8c5e73fd93a3b41b3b8e125ddb025485130de7c9fe1a33b0417e34d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:54:32.240797Z","signature_b64":"CokkDzCimQoPPo+6IBbRqT9mp1D5DvrZe7ZK/BIXMW3N0FY9Oqiek7xu9qrcFm1EcqvP5jswfzyoMlSX5cCZAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67b4b70028f7292664b1fffe6af50c5483a39f8a43d3f59054a85b1f3a001697","last_reissued_at":"2026-07-05T05:54:32.240333Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:54:32.240333Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LOT: Layer-wise Orthogonal Training on Improving $\\ell_2$ Certified Robustness","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bo Li, Linyi Li, Xiaojun Xu","submitted_at":"2022-10-20T22:31:26Z","abstract_excerpt":"Recent studies show that training deep neural networks (DNNs) with Lipschitz constraints are able to enhance adversarial robustness and other model properties such as stability. In this paper, we propose a layer-wise orthogonal training method (LOT) to effectively train 1-Lipschitz convolution layers via parametrizing an orthogonal matrix with an unconstrained matrix. We then efficiently compute the inverse square root of a convolution kernel by transforming the input domain to the Fourier frequency domain. On the other hand, as existing works show that semi-supervised training helps improve e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.11620","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2210.11620/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":"2210.11620","created_at":"2026-07-05T05:54:32.240397+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.11620v2","created_at":"2026-07-05T05:54:32.240397+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.11620","created_at":"2026-07-05T05:54:32.240397+00:00"},{"alias_kind":"pith_short_12","alias_value":"M62LOABI64US","created_at":"2026-07-05T05:54:32.240397+00:00"},{"alias_kind":"pith_short_16","alias_value":"M62LOABI64USMZFR","created_at":"2026-07-05T05:54:32.240397+00:00"},{"alias_kind":"pith_short_8","alias_value":"M62LOABI","created_at":"2026-07-05T05:54:32.240397+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/M62LOABI64USMZFR777GV5IMKS","json":"https://pith.science/pith/M62LOABI64USMZFR777GV5IMKS.json","graph_json":"https://pith.science/api/pith-number/M62LOABI64USMZFR777GV5IMKS/graph.json","events_json":"https://pith.science/api/pith-number/M62LOABI64USMZFR777GV5IMKS/events.json","paper":"https://pith.science/paper/M62LOABI"},"agent_actions":{"view_html":"https://pith.science/pith/M62LOABI64USMZFR777GV5IMKS","download_json":"https://pith.science/pith/M62LOABI64USMZFR777GV5IMKS.json","view_paper":"https://pith.science/paper/M62LOABI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.11620&json=true","fetch_graph":"https://pith.science/api/pith-number/M62LOABI64USMZFR777GV5IMKS/graph.json","fetch_events":"https://pith.science/api/pith-number/M62LOABI64USMZFR777GV5IMKS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M62LOABI64USMZFR777GV5IMKS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M62LOABI64USMZFR777GV5IMKS/action/storage_attestation","attest_author":"https://pith.science/pith/M62LOABI64USMZFR777GV5IMKS/action/author_attestation","sign_citation":"https://pith.science/pith/M62LOABI64USMZFR777GV5IMKS/action/citation_signature","submit_replication":"https://pith.science/pith/M62LOABI64USMZFR777GV5IMKS/action/replication_record"}},"created_at":"2026-07-05T05:54:32.240397+00:00","updated_at":"2026-07-05T05:54:32.240397+00:00"}