{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3KOTTRBQRL2YXJKJQFU2TQV6DS","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"58ddec1f798f285b5a8b7ce9d3de25b29ccc87515ec43e871a2b2a123bda3871","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-22T15:40:09Z","title_canon_sha256":"9ddbbad47fc24fcabff743840fbf110e0c09d6c24fd7c8ae615c001d030fe342"},"schema_version":"1.0","source":{"id":"2505.16800","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.16800","created_at":"2026-07-05T11:07:41Z"},{"alias_kind":"arxiv_version","alias_value":"2505.16800v1","created_at":"2026-07-05T11:07:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16800","created_at":"2026-07-05T11:07:41Z"},{"alias_kind":"pith_short_12","alias_value":"3KOTTRBQRL2Y","created_at":"2026-07-05T11:07:41Z"},{"alias_kind":"pith_short_16","alias_value":"3KOTTRBQRL2YXJKJ","created_at":"2026-07-05T11:07:41Z"},{"alias_kind":"pith_short_8","alias_value":"3KOTTRBQ","created_at":"2026-07-05T11:07:41Z"}],"graph_snapshots":[{"event_id":"sha256:abd21ac11a3d6d0f9c7d7e6ffb4635bf90316e0e20b4b3b7ea7a223925c0e6ef","target":"graph","created_at":"2026-07-05T11:07:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.16800/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Changbing Yang, Garrett Nicolai","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-22T15:40:09Z","title":"Learning Beyond Limits: Multitask Learning and Synthetic Data for Low-Resource Canonical Morpheme Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16800","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:690cfaedaea6ea0e641953f1358ac748b3cb80a737372772a3c10fc806f95de7","target":"record","created_at":"2026-07-05T11:07:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"58ddec1f798f285b5a8b7ce9d3de25b29ccc87515ec43e871a2b2a123bda3871","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-22T15:40:09Z","title_canon_sha256":"9ddbbad47fc24fcabff743840fbf110e0c09d6c24fd7c8ae615c001d030fe342"},"schema_version":"1.0","source":{"id":"2505.16800","kind":"arxiv","version":1}},"canonical_sha256":"da9d39c4308af58ba5498169a9c2be1cb9e09245c16ff525f0b08b4cc31c40a7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"da9d39c4308af58ba5498169a9c2be1cb9e09245c16ff525f0b08b4cc31c40a7","first_computed_at":"2026-07-05T11:07:41.419264Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:07:41.419264Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pzkopWfJ9d178xRXsauBwQu4b/9C5c86lPfWqYo0WLiP3x3PrqSM/QUpN1CEnkWDocCfcYKh5xT9Ca5sdItoAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:07:41.419762Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.16800","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:690cfaedaea6ea0e641953f1358ac748b3cb80a737372772a3c10fc806f95de7","sha256:abd21ac11a3d6d0f9c7d7e6ffb4635bf90316e0e20b4b3b7ea7a223925c0e6ef"],"state_sha256":"7f80de4f230b79f54dd2b11bd22e7447d507dd6927f624e652f7c7c43eb8c2ff"}