{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:SMO4JSFRNDI6MQUPQT56RE7AFC","short_pith_number":"pith:SMO4JSFR","schema_version":"1.0","canonical_sha256":"931dc4c8b168d1e6428f84fbe893e02883ecfe26c94bc12fc06bed8c68c8db55","source":{"kind":"arxiv","id":"2104.06683","version":1},"attestation_state":"computed","paper":{"title":"The Curious Case of Hallucinations in Neural Machine Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Arul Menezes, Marcin Junczys-Dowmunt, Vikas Raunak","submitted_at":"2021-04-14T08:09:57Z","abstract_excerpt":"In this work, we study hallucinations in Neural Machine Translation (NMT), which lie at an extreme end on the spectrum of NMT pathologies. Firstly, we connect the phenomenon of hallucinations under source perturbation to the Long-Tail theory of Feldman (2020), and present an empirically validated hypothesis that explains hallucinations under source perturbation. Secondly, we consider hallucinations under corpus-level noise (without any source perturbation) and demonstrate that two prominent types of natural hallucinations (detached and oscillatory outputs) could be generated and explained thro"},"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":"2104.06683","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-14T08:09:57Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"65cc34a5608fcbf6b5dfc59032d4e4cec48ec44baf90de631ecf096160e16caa","abstract_canon_sha256":"5a2d84fb9679efcfd6ed2d45a805e0f4a9deaeadefe0bebbb69c5629217e90f4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:32:08.396161Z","signature_b64":"ZX/MKdrMiefrqwJdHWVVTXD0qApwgrerHs+g6FSjHFTiWh2AB5OYqlNOF3XnLbUisa5D9FdfEJ1MAqay3SLdBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"931dc4c8b168d1e6428f84fbe893e02883ecfe26c94bc12fc06bed8c68c8db55","last_reissued_at":"2026-07-05T02:32:08.395798Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:32:08.395798Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Curious Case of Hallucinations in Neural Machine Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Arul Menezes, Marcin Junczys-Dowmunt, Vikas Raunak","submitted_at":"2021-04-14T08:09:57Z","abstract_excerpt":"In this work, we study hallucinations in Neural Machine Translation (NMT), which lie at an extreme end on the spectrum of NMT pathologies. Firstly, we connect the phenomenon of hallucinations under source perturbation to the Long-Tail theory of Feldman (2020), and present an empirically validated hypothesis that explains hallucinations under source perturbation. Secondly, we consider hallucinations under corpus-level noise (without any source perturbation) and demonstrate that two prominent types of natural hallucinations (detached and oscillatory outputs) could be generated and explained thro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.06683","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2104.06683/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":"2104.06683","created_at":"2026-07-05T02:32:08.395856+00:00"},{"alias_kind":"arxiv_version","alias_value":"2104.06683v1","created_at":"2026-07-05T02:32:08.395856+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.06683","created_at":"2026-07-05T02:32:08.395856+00:00"},{"alias_kind":"pith_short_12","alias_value":"SMO4JSFRNDI6","created_at":"2026-07-05T02:32:08.395856+00:00"},{"alias_kind":"pith_short_16","alias_value":"SMO4JSFRNDI6MQUP","created_at":"2026-07-05T02:32:08.395856+00:00"},{"alias_kind":"pith_short_8","alias_value":"SMO4JSFR","created_at":"2026-07-05T02:32:08.395856+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2401.03568","citing_title":"Agent AI: Surveying the Horizons of Multimodal Interaction","ref_index":187,"is_internal_anchor":false},{"citing_arxiv_id":"2308.05374","citing_title":"Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignment","ref_index":81,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13660","citing_title":"VRAG-DFD: Verifiable Retrieval-Augmentation for MLLM-based Deepfake Detection","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SMO4JSFRNDI6MQUPQT56RE7AFC","json":"https://pith.science/pith/SMO4JSFRNDI6MQUPQT56RE7AFC.json","graph_json":"https://pith.science/api/pith-number/SMO4JSFRNDI6MQUPQT56RE7AFC/graph.json","events_json":"https://pith.science/api/pith-number/SMO4JSFRNDI6MQUPQT56RE7AFC/events.json","paper":"https://pith.science/paper/SMO4JSFR"},"agent_actions":{"view_html":"https://pith.science/pith/SMO4JSFRNDI6MQUPQT56RE7AFC","download_json":"https://pith.science/pith/SMO4JSFRNDI6MQUPQT56RE7AFC.json","view_paper":"https://pith.science/paper/SMO4JSFR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2104.06683&json=true","fetch_graph":"https://pith.science/api/pith-number/SMO4JSFRNDI6MQUPQT56RE7AFC/graph.json","fetch_events":"https://pith.science/api/pith-number/SMO4JSFRNDI6MQUPQT56RE7AFC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SMO4JSFRNDI6MQUPQT56RE7AFC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SMO4JSFRNDI6MQUPQT56RE7AFC/action/storage_attestation","attest_author":"https://pith.science/pith/SMO4JSFRNDI6MQUPQT56RE7AFC/action/author_attestation","sign_citation":"https://pith.science/pith/SMO4JSFRNDI6MQUPQT56RE7AFC/action/citation_signature","submit_replication":"https://pith.science/pith/SMO4JSFRNDI6MQUPQT56RE7AFC/action/replication_record"}},"created_at":"2026-07-05T02:32:08.395856+00:00","updated_at":"2026-07-05T02:32:08.395856+00:00"}