{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:LBBXNYSHTZFZQSEZLGQWYHN3ZU","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":"2e11d312547040a8bd102ca96b0f8480a92e2c92961df05169385b56b1630724","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-27T02:46:08Z","title_canon_sha256":"6a4d84fc77e9d29cf8678a01bb7f0daf6386babccb62b000151c89009353921a"},"schema_version":"1.0","source":{"id":"2306.15164","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.15164","created_at":"2026-07-05T06:24:55Z"},{"alias_kind":"arxiv_version","alias_value":"2306.15164v1","created_at":"2026-07-05T06:24:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.15164","created_at":"2026-07-05T06:24:55Z"},{"alias_kind":"pith_short_12","alias_value":"LBBXNYSHTZFZ","created_at":"2026-07-05T06:24:55Z"},{"alias_kind":"pith_short_16","alias_value":"LBBXNYSHTZFZQSEZ","created_at":"2026-07-05T06:24:55Z"},{"alias_kind":"pith_short_8","alias_value":"LBBXNYSH","created_at":"2026-07-05T06:24:55Z"}],"graph_snapshots":[{"event_id":"sha256:e6d9e79016f5979e57251ec30521ee7d02b57f412afc89b4fce6789c4613cdc1","target":"graph","created_at":"2026-07-05T06:24:55Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2306.15164/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Adversarial training is one of the best-performing methods in improving the robustness of deep language models. However, robust models come at the cost of high time consumption, as they require multi-step gradient ascents or word substitutions to obtain adversarial samples. In addition, these generated samples are deficient in grammatical quality and semantic consistency, which impairs the effectiveness of adversarial training. To address these problems, we introduce a novel, effective procedure for instead adversarial training with only clean data. Our procedure, distribution shift risk minim","authors_text":"Jin Ma, Qi Zhang, Shihan Dou, Songyang Gao, Xiao Wang, Yan Liu, Ying Shan, Zhongyu Wei","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-27T02:46:08Z","title":"DSRM: Boost Textual Adversarial Training with Distribution Shift Risk Minimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.15164","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":"sha256:891a07f46279fdc94193098a4301ce422032507bcbd55d3e24b41c10028f431e","target":"record","created_at":"2026-07-05T06:24:55Z","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":"2e11d312547040a8bd102ca96b0f8480a92e2c92961df05169385b56b1630724","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-27T02:46:08Z","title_canon_sha256":"6a4d84fc77e9d29cf8678a01bb7f0daf6386babccb62b000151c89009353921a"},"schema_version":"1.0","source":{"id":"2306.15164","kind":"arxiv","version":1}},"canonical_sha256":"584376e2479e4b98489959a16c1dbbcd329ff517236708822735b2242689cffa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"584376e2479e4b98489959a16c1dbbcd329ff517236708822735b2242689cffa","first_computed_at":"2026-07-05T06:24:55.083208Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:24:55.083208Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"C2qPkwI5HH7Z8MnuWvAr07icU2p/LJQ0M/9gK/K24E1nfLJcInqNRxWx0FIH0n37VSiI+6Xvs8po035C+8DgBw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:24:55.083608Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.15164","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:891a07f46279fdc94193098a4301ce422032507bcbd55d3e24b41c10028f431e","sha256:e6d9e79016f5979e57251ec30521ee7d02b57f412afc89b4fce6789c4613cdc1"],"state_sha256":"1f08399cc9c49e179a8b5fd4ca91cfac3efa008871272c483527360340268299"}