{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AOVMPQ5KDEOKNMLPZHABK2FRJ3","short_pith_number":"pith:AOVMPQ5K","schema_version":"1.0","canonical_sha256":"03aac7c3aa191ca6b16fc9c01568b14eedeead36b87dc14280799f8dd04451e8","source":{"kind":"arxiv","id":"2406.18895","version":3},"attestation_state":"computed","paper":{"title":"Can we teach language models to gloss endangered languages?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexis Palmer, Mans Hulden, Michael Ginn","submitted_at":"2024-06-27T05:17:04Z","abstract_excerpt":"Interlinear glossed text (IGT) is a popular format in language documentation projects, where each morpheme is labeled with a descriptive annotation. Automating the creation of interlinear glossed text would be desirable to reduce annotator effort and maintain consistency across annotated corpora. Prior research has explored a number of statistical and neural methods for automatically producing IGT.\n  As large language models (LLMs) have showed promising results across multilingual tasks, even for rare, endangered languages, it is natural to wonder whether they can be utilized for the task of g"},"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":"2406.18895","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-27T05:17:04Z","cross_cats_sorted":[],"title_canon_sha256":"379b57155ccf4024f139982455407e55ca4cf24c734a49dccbf03c86d66c0057","abstract_canon_sha256":"b12ac15269fec1a799f68fd1195db5cc6c59adab87e1470566b8e8143646cdc6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:15:34.408937Z","signature_b64":"2W06furGMLnh4u2FR01ezZDIfJSNTBnztbnI+4/hnAjETaF4KL+TOntd7ZvlUC+EpM+gBVukS/inKYTtbqHRCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03aac7c3aa191ca6b16fc9c01568b14eedeead36b87dc14280799f8dd04451e8","last_reissued_at":"2026-07-05T09:15:34.408439Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:15:34.408439Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can we teach language models to gloss endangered languages?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexis Palmer, Mans Hulden, Michael Ginn","submitted_at":"2024-06-27T05:17:04Z","abstract_excerpt":"Interlinear glossed text (IGT) is a popular format in language documentation projects, where each morpheme is labeled with a descriptive annotation. Automating the creation of interlinear glossed text would be desirable to reduce annotator effort and maintain consistency across annotated corpora. Prior research has explored a number of statistical and neural methods for automatically producing IGT.\n  As large language models (LLMs) have showed promising results across multilingual tasks, even for rare, endangered languages, it is natural to wonder whether they can be utilized for the task of g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.18895","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/2406.18895/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":"2406.18895","created_at":"2026-07-05T09:15:34.408495+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.18895v3","created_at":"2026-07-05T09:15:34.408495+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.18895","created_at":"2026-07-05T09:15:34.408495+00:00"},{"alias_kind":"pith_short_12","alias_value":"AOVMPQ5KDEOK","created_at":"2026-07-05T09:15:34.408495+00:00"},{"alias_kind":"pith_short_16","alias_value":"AOVMPQ5KDEOKNMLP","created_at":"2026-07-05T09:15:34.408495+00:00"},{"alias_kind":"pith_short_8","alias_value":"AOVMPQ5K","created_at":"2026-07-05T09:15:34.408495+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/AOVMPQ5KDEOKNMLPZHABK2FRJ3","json":"https://pith.science/pith/AOVMPQ5KDEOKNMLPZHABK2FRJ3.json","graph_json":"https://pith.science/api/pith-number/AOVMPQ5KDEOKNMLPZHABK2FRJ3/graph.json","events_json":"https://pith.science/api/pith-number/AOVMPQ5KDEOKNMLPZHABK2FRJ3/events.json","paper":"https://pith.science/paper/AOVMPQ5K"},"agent_actions":{"view_html":"https://pith.science/pith/AOVMPQ5KDEOKNMLPZHABK2FRJ3","download_json":"https://pith.science/pith/AOVMPQ5KDEOKNMLPZHABK2FRJ3.json","view_paper":"https://pith.science/paper/AOVMPQ5K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.18895&json=true","fetch_graph":"https://pith.science/api/pith-number/AOVMPQ5KDEOKNMLPZHABK2FRJ3/graph.json","fetch_events":"https://pith.science/api/pith-number/AOVMPQ5KDEOKNMLPZHABK2FRJ3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AOVMPQ5KDEOKNMLPZHABK2FRJ3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AOVMPQ5KDEOKNMLPZHABK2FRJ3/action/storage_attestation","attest_author":"https://pith.science/pith/AOVMPQ5KDEOKNMLPZHABK2FRJ3/action/author_attestation","sign_citation":"https://pith.science/pith/AOVMPQ5KDEOKNMLPZHABK2FRJ3/action/citation_signature","submit_replication":"https://pith.science/pith/AOVMPQ5KDEOKNMLPZHABK2FRJ3/action/replication_record"}},"created_at":"2026-07-05T09:15:34.408495+00:00","updated_at":"2026-07-05T09:15:34.408495+00:00"}