{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3KOTTRBQRL2YXJKJQFU2TQV6DS","short_pith_number":"pith:3KOTTRBQ","schema_version":"1.0","canonical_sha256":"da9d39c4308af58ba5498169a9c2be1cb9e09245c16ff525f0b08b4cc31c40a7","source":{"kind":"arxiv","id":"2505.16800","version":1},"attestation_state":"computed","paper":{"title":"Learning Beyond Limits: Multitask Learning and Synthetic Data for Low-Resource Canonical Morpheme Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Changbing Yang, Garrett Nicolai","submitted_at":"2025-05-22T15:40:09Z","abstract_excerpt":"We introduce a transformer-based morpheme segmentation system that augments a low-resource training signal through multitask learning and LLM-generated synthetic data. Our framework jointly predicts morphological segments and glosses from orthographic input, leveraging shared linguistic representations obtained through a common documentary process to enhance model generalization. To further address data scarcity, we integrate synthetic training data generated by large language models (LLMs) using in-context learning. Experimental results on the SIGMORPHON 2023 dataset show that our approach si"},"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":"2505.16800","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-22T15:40:09Z","cross_cats_sorted":[],"title_canon_sha256":"9ddbbad47fc24fcabff743840fbf110e0c09d6c24fd7c8ae615c001d030fe342","abstract_canon_sha256":"58ddec1f798f285b5a8b7ce9d3de25b29ccc87515ec43e871a2b2a123bda3871"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:07:41.419762Z","signature_b64":"pzkopWfJ9d178xRXsauBwQu4b/9C5c86lPfWqYo0WLiP3x3PrqSM/QUpN1CEnkWDocCfcYKh5xT9Ca5sdItoAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da9d39c4308af58ba5498169a9c2be1cb9e09245c16ff525f0b08b4cc31c40a7","last_reissued_at":"2026-07-05T11:07:41.419264Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:07:41.419264Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Beyond Limits: Multitask Learning and Synthetic Data for Low-Resource Canonical Morpheme Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Changbing Yang, Garrett Nicolai","submitted_at":"2025-05-22T15:40:09Z","abstract_excerpt":"We introduce a transformer-based morpheme segmentation system that augments a low-resource training signal through multitask learning and LLM-generated synthetic data. Our framework jointly predicts morphological segments and glosses from orthographic input, leveraging shared linguistic representations obtained through a common documentary process to enhance model generalization. To further address data scarcity, we integrate synthetic training data generated by large language models (LLMs) using in-context learning. Experimental results on the SIGMORPHON 2023 dataset show that our approach si"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16800","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/2505.16800/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":"2505.16800","created_at":"2026-07-05T11:07:41.419327+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.16800v1","created_at":"2026-07-05T11:07:41.419327+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16800","created_at":"2026-07-05T11:07:41.419327+00:00"},{"alias_kind":"pith_short_12","alias_value":"3KOTTRBQRL2Y","created_at":"2026-07-05T11:07:41.419327+00:00"},{"alias_kind":"pith_short_16","alias_value":"3KOTTRBQRL2YXJKJ","created_at":"2026-07-05T11:07:41.419327+00:00"},{"alias_kind":"pith_short_8","alias_value":"3KOTTRBQ","created_at":"2026-07-05T11:07:41.419327+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/3KOTTRBQRL2YXJKJQFU2TQV6DS","json":"https://pith.science/pith/3KOTTRBQRL2YXJKJQFU2TQV6DS.json","graph_json":"https://pith.science/api/pith-number/3KOTTRBQRL2YXJKJQFU2TQV6DS/graph.json","events_json":"https://pith.science/api/pith-number/3KOTTRBQRL2YXJKJQFU2TQV6DS/events.json","paper":"https://pith.science/paper/3KOTTRBQ"},"agent_actions":{"view_html":"https://pith.science/pith/3KOTTRBQRL2YXJKJQFU2TQV6DS","download_json":"https://pith.science/pith/3KOTTRBQRL2YXJKJQFU2TQV6DS.json","view_paper":"https://pith.science/paper/3KOTTRBQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.16800&json=true","fetch_graph":"https://pith.science/api/pith-number/3KOTTRBQRL2YXJKJQFU2TQV6DS/graph.json","fetch_events":"https://pith.science/api/pith-number/3KOTTRBQRL2YXJKJQFU2TQV6DS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3KOTTRBQRL2YXJKJQFU2TQV6DS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3KOTTRBQRL2YXJKJQFU2TQV6DS/action/storage_attestation","attest_author":"https://pith.science/pith/3KOTTRBQRL2YXJKJQFU2TQV6DS/action/author_attestation","sign_citation":"https://pith.science/pith/3KOTTRBQRL2YXJKJQFU2TQV6DS/action/citation_signature","submit_replication":"https://pith.science/pith/3KOTTRBQRL2YXJKJQFU2TQV6DS/action/replication_record"}},"created_at":"2026-07-05T11:07:41.419327+00:00","updated_at":"2026-07-05T11:07:41.419327+00:00"}