{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:MHIMPFWBWQBFYRLLINLA6XNOKR","short_pith_number":"pith:MHIMPFWB","schema_version":"1.0","canonical_sha256":"61d0c796c1b4025c456b43560f5dae546eee9a8f4aa5e49cfcf2a8452cda5fbc","source":{"kind":"arxiv","id":"1804.06059","version":1},"attestation_state":"computed","paper":{"title":"Adversarial Example Generation with Syntactically Controlled Paraphrase Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"John Wieting, Kevin Gimpel, Luke Zettlemoyer, Mohit Iyyer","submitted_at":"2018-04-17T06:12:36Z","abstract_excerpt":"We propose syntactically controlled paraphrase networks (SCPNs) and use them to generate adversarial examples. Given a sentence and a target syntactic form (e.g., a constituency parse), SCPNs are trained to produce a paraphrase of the sentence with the desired syntax. We show it is possible to create training data for this task by first doing backtranslation at a very large scale, and then using a parser to label the syntactic transformations that naturally occur during this process. Such data allows us to train a neural encoder-decoder model with extra inputs to specify the target syntax. A c"},"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":"1804.06059","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-17T06:12:36Z","cross_cats_sorted":[],"title_canon_sha256":"9c5de60a686fa34eecf47302665e9efca1f392b248d7c9dc903b7d5c710be707","abstract_canon_sha256":"c0f5eade6f7792e1c5a215429b62832360401dae8e39e4172a91731e2cdc1b0f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:18:21.865198Z","signature_b64":"P5VUixi3BQh7VauipMHnG+Yp1zI0NXENEoLzyUwIYKIFrUo65E/s02TmdeCu5klzmrCxY/LCQZc1rQT3dHgtCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"61d0c796c1b4025c456b43560f5dae546eee9a8f4aa5e49cfcf2a8452cda5fbc","last_reissued_at":"2026-05-18T00:18:21.864465Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:18:21.864465Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adversarial Example Generation with Syntactically Controlled Paraphrase Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"John Wieting, Kevin Gimpel, Luke Zettlemoyer, Mohit Iyyer","submitted_at":"2018-04-17T06:12:36Z","abstract_excerpt":"We propose syntactically controlled paraphrase networks (SCPNs) and use them to generate adversarial examples. Given a sentence and a target syntactic form (e.g., a constituency parse), SCPNs are trained to produce a paraphrase of the sentence with the desired syntax. We show it is possible to create training data for this task by first doing backtranslation at a very large scale, and then using a parser to label the syntactic transformations that naturally occur during this process. Such data allows us to train a neural encoder-decoder model with extra inputs to specify the target syntax. A c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.06059","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":"1804.06059","created_at":"2026-05-18T00:18:21.864592+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.06059v1","created_at":"2026-05-18T00:18:21.864592+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.06059","created_at":"2026-05-18T00:18:21.864592+00:00"},{"alias_kind":"pith_short_12","alias_value":"MHIMPFWBWQBF","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_16","alias_value":"MHIMPFWBWQBFYRLL","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_8","alias_value":"MHIMPFWB","created_at":"2026-05-18T12:32:37.024351+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.09700","citing_title":"What the Eyes See, the LLMs Miss: Exploiting Human Perception for Adversarial Text Attacks","ref_index":32,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MHIMPFWBWQBFYRLLINLA6XNOKR","json":"https://pith.science/pith/MHIMPFWBWQBFYRLLINLA6XNOKR.json","graph_json":"https://pith.science/api/pith-number/MHIMPFWBWQBFYRLLINLA6XNOKR/graph.json","events_json":"https://pith.science/api/pith-number/MHIMPFWBWQBFYRLLINLA6XNOKR/events.json","paper":"https://pith.science/paper/MHIMPFWB"},"agent_actions":{"view_html":"https://pith.science/pith/MHIMPFWBWQBFYRLLINLA6XNOKR","download_json":"https://pith.science/pith/MHIMPFWBWQBFYRLLINLA6XNOKR.json","view_paper":"https://pith.science/paper/MHIMPFWB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.06059&json=true","fetch_graph":"https://pith.science/api/pith-number/MHIMPFWBWQBFYRLLINLA6XNOKR/graph.json","fetch_events":"https://pith.science/api/pith-number/MHIMPFWBWQBFYRLLINLA6XNOKR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MHIMPFWBWQBFYRLLINLA6XNOKR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MHIMPFWBWQBFYRLLINLA6XNOKR/action/storage_attestation","attest_author":"https://pith.science/pith/MHIMPFWBWQBFYRLLINLA6XNOKR/action/author_attestation","sign_citation":"https://pith.science/pith/MHIMPFWBWQBFYRLLINLA6XNOKR/action/citation_signature","submit_replication":"https://pith.science/pith/MHIMPFWBWQBFYRLLINLA6XNOKR/action/replication_record"}},"created_at":"2026-05-18T00:18:21.864592+00:00","updated_at":"2026-05-18T00:18:21.864592+00:00"}