{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:ZBT5NYP3HRT2W2WSH5V5CZKZYN","short_pith_number":"pith:ZBT5NYP3","schema_version":"1.0","canonical_sha256":"c867d6e1fb3c67ab6ad23f6bd16559c37359eca5e78c0e2abfaeade3d693179d","source":{"kind":"arxiv","id":"1905.12864","version":1},"attestation_state":"computed","paper":{"title":"Interpretable Adversarial Training for Text","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Samuel Barham, Soheil Feizi","submitted_at":"2019-05-30T05:55:58Z","abstract_excerpt":"Generating high-quality and interpretable adversarial examples in the text domain is a much more daunting task than it is in the image domain. This is due partly to the discrete nature of text, partly to the problem of ensuring that the adversarial examples are still probable and interpretable, and partly to the problem of maintaining label invariance under input perturbations. In order to address some of these challenges, we introduce sparse projected gradient descent (SPGD), a new approach to crafting interpretable adversarial examples for text. SPGD imposes a directional regularization cons"},"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":"1905.12864","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-30T05:55:58Z","cross_cats_sorted":["cs.CL","stat.ML"],"title_canon_sha256":"8a58682595e70d832e50bdd4d9c395064d18d59c960788bdd70e3f6745c47e94","abstract_canon_sha256":"471c1a773c66b506243f39c99097ae20aaad4cde6ec0f5cb6c1b556bf44ff402"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:39.454199Z","signature_b64":"ypdaYqwGheh4+LUXxyAw1TNdRac2zv9tINgirjsHSbvBaHIKpZPGtQlUMwjg0zF7bXqbW3WuN3tkkF/uu1O1AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c867d6e1fb3c67ab6ad23f6bd16559c37359eca5e78c0e2abfaeade3d693179d","last_reissued_at":"2026-05-17T23:44:39.453645Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:39.453645Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Interpretable Adversarial Training for Text","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Samuel Barham, Soheil Feizi","submitted_at":"2019-05-30T05:55:58Z","abstract_excerpt":"Generating high-quality and interpretable adversarial examples in the text domain is a much more daunting task than it is in the image domain. This is due partly to the discrete nature of text, partly to the problem of ensuring that the adversarial examples are still probable and interpretable, and partly to the problem of maintaining label invariance under input perturbations. In order to address some of these challenges, we introduce sparse projected gradient descent (SPGD), a new approach to crafting interpretable adversarial examples for text. SPGD imposes a directional regularization cons"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.12864","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1905.12864","created_at":"2026-05-17T23:44:39.453727+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.12864v1","created_at":"2026-05-17T23:44:39.453727+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.12864","created_at":"2026-05-17T23:44:39.453727+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZBT5NYP3HRT2","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZBT5NYP3HRT2W2WS","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZBT5NYP3","created_at":"2026-05-18T12:33:33.725879+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/ZBT5NYP3HRT2W2WSH5V5CZKZYN","json":"https://pith.science/pith/ZBT5NYP3HRT2W2WSH5V5CZKZYN.json","graph_json":"https://pith.science/api/pith-number/ZBT5NYP3HRT2W2WSH5V5CZKZYN/graph.json","events_json":"https://pith.science/api/pith-number/ZBT5NYP3HRT2W2WSH5V5CZKZYN/events.json","paper":"https://pith.science/paper/ZBT5NYP3"},"agent_actions":{"view_html":"https://pith.science/pith/ZBT5NYP3HRT2W2WSH5V5CZKZYN","download_json":"https://pith.science/pith/ZBT5NYP3HRT2W2WSH5V5CZKZYN.json","view_paper":"https://pith.science/paper/ZBT5NYP3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.12864&json=true","fetch_graph":"https://pith.science/api/pith-number/ZBT5NYP3HRT2W2WSH5V5CZKZYN/graph.json","fetch_events":"https://pith.science/api/pith-number/ZBT5NYP3HRT2W2WSH5V5CZKZYN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZBT5NYP3HRT2W2WSH5V5CZKZYN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZBT5NYP3HRT2W2WSH5V5CZKZYN/action/storage_attestation","attest_author":"https://pith.science/pith/ZBT5NYP3HRT2W2WSH5V5CZKZYN/action/author_attestation","sign_citation":"https://pith.science/pith/ZBT5NYP3HRT2W2WSH5V5CZKZYN/action/citation_signature","submit_replication":"https://pith.science/pith/ZBT5NYP3HRT2W2WSH5V5CZKZYN/action/replication_record"}},"created_at":"2026-05-17T23:44:39.453727+00:00","updated_at":"2026-05-17T23:44:39.453727+00:00"}