{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:J2WP42HOPNSFQD6533RCCPFGWE","short_pith_number":"pith:J2WP42HO","schema_version":"1.0","canonical_sha256":"4eacfe68ee7b64580fdddee2213ca6b121c2ced09e6f4731c7337e90a349fcb5","source":{"kind":"arxiv","id":"2208.05309","version":2},"attestation_state":"computed","paper":{"title":"Looking for a Needle in a Haystack: A Comprehensive Study of Hallucinations in Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Andr\\'e F.T. Martins, Elena Voita, Nuno M. Guerreiro","submitted_at":"2022-08-10T12:44:13Z","abstract_excerpt":"Although the problem of hallucinations in neural machine translation (NMT) has received some attention, research on this highly pathological phenomenon lacks solid ground. Previous work has been limited in several ways: it often resorts to artificial settings where the problem is amplified, it disregards some (common) types of hallucinations, and it does not validate adequacy of detection heuristics. In this paper, we set foundations for the study of NMT hallucinations. First, we work in a natural setting, i.e., in-domain data without artificial noise neither in training nor in inference. Next"},"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":"2208.05309","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-08-10T12:44:13Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"16267048d18ad25e8f458118dcee2508fd361ca123fa4af6d8ef2ac9856fd0e2","abstract_canon_sha256":"5c10ccfc8c6ba1c08a3decc3ea5ec15a0f61d200dab7c6297257d4e0c4f96e76"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:48:00.784080Z","signature_b64":"lqZ3x4bIuQeBuuBH5g+qMTrfX5ymdohfejGPkcYgqJF6dWgWgTfnlmbsDc1mSQpzh/fO7mUwQGbd89e2VgW2DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4eacfe68ee7b64580fdddee2213ca6b121c2ced09e6f4731c7337e90a349fcb5","last_reissued_at":"2026-07-05T05:48:00.783593Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:48:00.783593Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Looking for a Needle in a Haystack: A Comprehensive Study of Hallucinations in Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Andr\\'e F.T. Martins, Elena Voita, Nuno M. Guerreiro","submitted_at":"2022-08-10T12:44:13Z","abstract_excerpt":"Although the problem of hallucinations in neural machine translation (NMT) has received some attention, research on this highly pathological phenomenon lacks solid ground. Previous work has been limited in several ways: it often resorts to artificial settings where the problem is amplified, it disregards some (common) types of hallucinations, and it does not validate adequacy of detection heuristics. In this paper, we set foundations for the study of NMT hallucinations. First, we work in a natural setting, i.e., in-domain data without artificial noise neither in training nor in inference. Next"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.05309","kind":"arxiv","version":2},"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/2208.05309/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":"2208.05309","created_at":"2026-07-05T05:48:00.783651+00:00"},{"alias_kind":"arxiv_version","alias_value":"2208.05309v2","created_at":"2026-07-05T05:48:00.783651+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.05309","created_at":"2026-07-05T05:48:00.783651+00:00"},{"alias_kind":"pith_short_12","alias_value":"J2WP42HOPNSF","created_at":"2026-07-05T05:48:00.783651+00:00"},{"alias_kind":"pith_short_16","alias_value":"J2WP42HOPNSFQD65","created_at":"2026-07-05T05:48:00.783651+00:00"},{"alias_kind":"pith_short_8","alias_value":"J2WP42HO","created_at":"2026-07-05T05:48:00.783651+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2405.16755","citing_title":"CHESS: Contextual Harnessing for Efficient SQL Synthesis","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18490","citing_title":"LQM: Linguistically Motivated Multidimensional Quality Metrics for Machine Translation","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J2WP42HOPNSFQD6533RCCPFGWE","json":"https://pith.science/pith/J2WP42HOPNSFQD6533RCCPFGWE.json","graph_json":"https://pith.science/api/pith-number/J2WP42HOPNSFQD6533RCCPFGWE/graph.json","events_json":"https://pith.science/api/pith-number/J2WP42HOPNSFQD6533RCCPFGWE/events.json","paper":"https://pith.science/paper/J2WP42HO"},"agent_actions":{"view_html":"https://pith.science/pith/J2WP42HOPNSFQD6533RCCPFGWE","download_json":"https://pith.science/pith/J2WP42HOPNSFQD6533RCCPFGWE.json","view_paper":"https://pith.science/paper/J2WP42HO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2208.05309&json=true","fetch_graph":"https://pith.science/api/pith-number/J2WP42HOPNSFQD6533RCCPFGWE/graph.json","fetch_events":"https://pith.science/api/pith-number/J2WP42HOPNSFQD6533RCCPFGWE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J2WP42HOPNSFQD6533RCCPFGWE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J2WP42HOPNSFQD6533RCCPFGWE/action/storage_attestation","attest_author":"https://pith.science/pith/J2WP42HOPNSFQD6533RCCPFGWE/action/author_attestation","sign_citation":"https://pith.science/pith/J2WP42HOPNSFQD6533RCCPFGWE/action/citation_signature","submit_replication":"https://pith.science/pith/J2WP42HOPNSFQD6533RCCPFGWE/action/replication_record"}},"created_at":"2026-07-05T05:48:00.783651+00:00","updated_at":"2026-07-05T05:48:00.783651+00:00"}