{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SSSZBJCJTFP5DKUYER6OJSCG66","short_pith_number":"pith:SSSZBJCJ","schema_version":"1.0","canonical_sha256":"94a590a449995fd1aa98247ce4c846f795ec622b0fae0c18463ce71a6fa2a1da","source":{"kind":"arxiv","id":"2410.18702","version":2},"attestation_state":"computed","paper":{"title":"GrammaMT: Improving Machine Translation with Grammar-Informed In-Context Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Everlyn Asiko Chimoto, Maartje ter Hoeve, Natalie Schluter, Rita Ramos","submitted_at":"2024-10-24T12:56:01Z","abstract_excerpt":"We introduce GrammaMT, a grammatically-aware prompting approach for machine translation that uses Interlinear Glossed Text (IGT), a common form of linguistic description providing morphological and lexical annotations for source sentences. GrammaMT proposes three prompting strategies: gloss-shot, chain-gloss and model-gloss. All are training-free, requiring only a few examples that involve minimal effort to collect, and making them well-suited for low-resource setups. Experiments show that GrammaMT enhances translation performance on open-source instruction-tuned LLMs for various low- to high-"},"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":"2410.18702","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-24T12:56:01Z","cross_cats_sorted":[],"title_canon_sha256":"a7cf7f1c4029c05125c5beb16b974ac9272dd0118aca48d89688873c067523fa","abstract_canon_sha256":"92d79fe56c8d42f4f5fb1518107ba668fecc3882ce82aa629071d0fce3a1b86b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:59.278234Z","signature_b64":"9T4p8P2IyaNNnvbCwRyzC8prvN9COoSbohiVP6+hyeesvfcT3VjoilLXUEQnIq7lwaaztKlOlWynrQ7Lt1q+Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94a590a449995fd1aa98247ce4c846f795ec622b0fae0c18463ce71a6fa2a1da","last_reissued_at":"2026-07-05T11:13:59.277728Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:59.277728Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GrammaMT: Improving Machine Translation with Grammar-Informed In-Context Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Everlyn Asiko Chimoto, Maartje ter Hoeve, Natalie Schluter, Rita Ramos","submitted_at":"2024-10-24T12:56:01Z","abstract_excerpt":"We introduce GrammaMT, a grammatically-aware prompting approach for machine translation that uses Interlinear Glossed Text (IGT), a common form of linguistic description providing morphological and lexical annotations for source sentences. GrammaMT proposes three prompting strategies: gloss-shot, chain-gloss and model-gloss. All are training-free, requiring only a few examples that involve minimal effort to collect, and making them well-suited for low-resource setups. Experiments show that GrammaMT enhances translation performance on open-source instruction-tuned LLMs for various low- to high-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.18702","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/2410.18702/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":"2410.18702","created_at":"2026-07-05T11:13:59.277791+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.18702v2","created_at":"2026-07-05T11:13:59.277791+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.18702","created_at":"2026-07-05T11:13:59.277791+00:00"},{"alias_kind":"pith_short_12","alias_value":"SSSZBJCJTFP5","created_at":"2026-07-05T11:13:59.277791+00:00"},{"alias_kind":"pith_short_16","alias_value":"SSSZBJCJTFP5DKUY","created_at":"2026-07-05T11:13:59.277791+00:00"},{"alias_kind":"pith_short_8","alias_value":"SSSZBJCJ","created_at":"2026-07-05T11:13:59.277791+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/SSSZBJCJTFP5DKUYER6OJSCG66","json":"https://pith.science/pith/SSSZBJCJTFP5DKUYER6OJSCG66.json","graph_json":"https://pith.science/api/pith-number/SSSZBJCJTFP5DKUYER6OJSCG66/graph.json","events_json":"https://pith.science/api/pith-number/SSSZBJCJTFP5DKUYER6OJSCG66/events.json","paper":"https://pith.science/paper/SSSZBJCJ"},"agent_actions":{"view_html":"https://pith.science/pith/SSSZBJCJTFP5DKUYER6OJSCG66","download_json":"https://pith.science/pith/SSSZBJCJTFP5DKUYER6OJSCG66.json","view_paper":"https://pith.science/paper/SSSZBJCJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.18702&json=true","fetch_graph":"https://pith.science/api/pith-number/SSSZBJCJTFP5DKUYER6OJSCG66/graph.json","fetch_events":"https://pith.science/api/pith-number/SSSZBJCJTFP5DKUYER6OJSCG66/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SSSZBJCJTFP5DKUYER6OJSCG66/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SSSZBJCJTFP5DKUYER6OJSCG66/action/storage_attestation","attest_author":"https://pith.science/pith/SSSZBJCJTFP5DKUYER6OJSCG66/action/author_attestation","sign_citation":"https://pith.science/pith/SSSZBJCJTFP5DKUYER6OJSCG66/action/citation_signature","submit_replication":"https://pith.science/pith/SSSZBJCJTFP5DKUYER6OJSCG66/action/replication_record"}},"created_at":"2026-07-05T11:13:59.277791+00:00","updated_at":"2026-07-05T11:13:59.277791+00:00"}