{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:ZXNKIN6P5FGW6YHBIX2CASJ6ZF","short_pith_number":"pith:ZXNKIN6P","schema_version":"1.0","canonical_sha256":"cddaa437cfe94d6f60e145f420493ec9615c5bc886c8a67dcb3ba9edf3131bf6","source":{"kind":"arxiv","id":"1908.01165","version":3},"attestation_state":"computed","paper":{"title":"Exploring the Robustness of NMT Systems to Nonsensical Inputs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abijith KP, Akshay Chaturvedi, Utpal Garain","submitted_at":"2019-08-03T12:59:40Z","abstract_excerpt":"Neural machine translation (NMT) systems have been shown to give undesirable translation when a small change is made in the source sentence. In this paper, we study the behaviour of NMT systems when multiple changes are made to the source sentence. In particular, we ask the following question \"Is it possible for an NMT system to predict same translation even when multiple words in the source sentence have been replaced?\". To this end, we propose a soft-attention based technique to make the aforementioned word replacements. The experiments are conducted on two language pairs: English-German (en"},"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":"1908.01165","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-03T12:59:40Z","cross_cats_sorted":["cs.CL","cs.CR","stat.ML"],"title_canon_sha256":"9c1ea92718083cfce86bc76e2989ddc734cc12ce6e75afaa5d3909189d5fc91a","abstract_canon_sha256":"71b851a2637e38f147880996ec8ec0f19f7730ce50dd47552b05500275c104a4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:44:26.364371Z","signature_b64":"oE8PC0/vlai7lFKLU5jm3SpcIr5quYJNFadvBjruTnWgD5Qnmmga6IGAUI7k7dvIVGbq7/hLWM61kwidTj2ZCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cddaa437cfe94d6f60e145f420493ec9615c5bc886c8a67dcb3ba9edf3131bf6","last_reissued_at":"2026-07-05T00:44:26.363963Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:44:26.363963Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring the Robustness of NMT Systems to Nonsensical Inputs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Abijith KP, Akshay Chaturvedi, Utpal Garain","submitted_at":"2019-08-03T12:59:40Z","abstract_excerpt":"Neural machine translation (NMT) systems have been shown to give undesirable translation when a small change is made in the source sentence. In this paper, we study the behaviour of NMT systems when multiple changes are made to the source sentence. In particular, we ask the following question \"Is it possible for an NMT system to predict same translation even when multiple words in the source sentence have been replaced?\". To this end, we propose a soft-attention based technique to make the aforementioned word replacements. The experiments are conducted on two language pairs: English-German (en"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.01165","kind":"arxiv","version":3},"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/1908.01165/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":"1908.01165","created_at":"2026-07-05T00:44:26.364017+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.01165v3","created_at":"2026-07-05T00:44:26.364017+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.01165","created_at":"2026-07-05T00:44:26.364017+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZXNKIN6P5FGW","created_at":"2026-07-05T00:44:26.364017+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZXNKIN6P5FGW6YHB","created_at":"2026-07-05T00:44:26.364017+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZXNKIN6P","created_at":"2026-07-05T00:44:26.364017+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.12183","citing_title":"Extend Adversarial Policy Against Neural Machine Translation via Unknown Token","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZXNKIN6P5FGW6YHBIX2CASJ6ZF","json":"https://pith.science/pith/ZXNKIN6P5FGW6YHBIX2CASJ6ZF.json","graph_json":"https://pith.science/api/pith-number/ZXNKIN6P5FGW6YHBIX2CASJ6ZF/graph.json","events_json":"https://pith.science/api/pith-number/ZXNKIN6P5FGW6YHBIX2CASJ6ZF/events.json","paper":"https://pith.science/paper/ZXNKIN6P"},"agent_actions":{"view_html":"https://pith.science/pith/ZXNKIN6P5FGW6YHBIX2CASJ6ZF","download_json":"https://pith.science/pith/ZXNKIN6P5FGW6YHBIX2CASJ6ZF.json","view_paper":"https://pith.science/paper/ZXNKIN6P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.01165&json=true","fetch_graph":"https://pith.science/api/pith-number/ZXNKIN6P5FGW6YHBIX2CASJ6ZF/graph.json","fetch_events":"https://pith.science/api/pith-number/ZXNKIN6P5FGW6YHBIX2CASJ6ZF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZXNKIN6P5FGW6YHBIX2CASJ6ZF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZXNKIN6P5FGW6YHBIX2CASJ6ZF/action/storage_attestation","attest_author":"https://pith.science/pith/ZXNKIN6P5FGW6YHBIX2CASJ6ZF/action/author_attestation","sign_citation":"https://pith.science/pith/ZXNKIN6P5FGW6YHBIX2CASJ6ZF/action/citation_signature","submit_replication":"https://pith.science/pith/ZXNKIN6P5FGW6YHBIX2CASJ6ZF/action/replication_record"}},"created_at":"2026-07-05T00:44:26.364017+00:00","updated_at":"2026-07-05T00:44:26.364017+00:00"}