{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:3ARCV55MUOV66YYCWFBN7Z3YDS","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":"1ca841bb14b99410ac03dd6ba5138925f2bedcb3ea088690f4e12598d58dc89b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-03-20T14:39:25Z","title_canon_sha256":"eb78d7daab94a8b23780058026c3610c0ba01b3a03f7076fa31e407f6d5a071d"},"schema_version":"1.0","source":{"id":"2103.11189","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.11189","created_at":"2026-07-05T08:19:32Z"},{"alias_kind":"arxiv_version","alias_value":"2103.11189v1","created_at":"2026-07-05T08:19:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.11189","created_at":"2026-07-05T08:19:32Z"},{"alias_kind":"pith_short_12","alias_value":"3ARCV55MUOV6","created_at":"2026-07-05T08:19:32Z"},{"alias_kind":"pith_short_16","alias_value":"3ARCV55MUOV66YYC","created_at":"2026-07-05T08:19:32Z"},{"alias_kind":"pith_short_8","alias_value":"3ARCV55M","created_at":"2026-07-05T08:19:32Z"}],"graph_snapshots":[{"event_id":"sha256:e1a5e45df2d7888b2ff5e46232eaa3d8994914c0a953a2d82574dc076e6d6ccf","target":"graph","created_at":"2026-07-05T08:19:32Z","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/2103.11189/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper evaluates the performance of several modern subword segmentation methods in a low-resource neural machine translation setting. We compare segmentations produced by applying BPE at the token or sentence level with morphologically-based segmentations from LMVR and MORSEL. We evaluate translation tasks between English and each of Nepali, Sinhala, and Kazakh, and predict that using morphologically-based segmentation methods would lead to better performance in this setting. However, comparing to BPE, we find that no consistent and reliable differences emerge between the segmentation meth","authors_text":"Constantine Lignos, Jonne S\\\"alev\\\"a","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-03-20T14:39:25Z","title":"The Effectiveness of Morphology-aware Segmentation in Low-Resource Neural Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.11189","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:bbdf0bbf70f98669fbd85fa8f86f27f4bb6d0d6541191f4fbfd0c07510787d32","target":"record","created_at":"2026-07-05T08:19:32Z","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":"1ca841bb14b99410ac03dd6ba5138925f2bedcb3ea088690f4e12598d58dc89b","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-03-20T14:39:25Z","title_canon_sha256":"eb78d7daab94a8b23780058026c3610c0ba01b3a03f7076fa31e407f6d5a071d"},"schema_version":"1.0","source":{"id":"2103.11189","kind":"arxiv","version":1}},"canonical_sha256":"d8222af7aca3abef6302b142dfe7781c845670032ff83111be0a8a2cb1b244a0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d8222af7aca3abef6302b142dfe7781c845670032ff83111be0a8a2cb1b244a0","first_computed_at":"2026-07-05T08:19:32.297946Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:19:32.297946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fsbRDsPKNqJsRY09EaG1I094mrDEJWiLbqmQL1xtSNSkksC4vX38yfEs0XqJJwt+OqaZHk2rMjuGjJGvx8dZCA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:19:32.298482Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.11189","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bbdf0bbf70f98669fbd85fa8f86f27f4bb6d0d6541191f4fbfd0c07510787d32","sha256:e1a5e45df2d7888b2ff5e46232eaa3d8994914c0a953a2d82574dc076e6d6ccf"],"state_sha256":"595521b733084f3e8ee5a7fc8f3746e56681130498a95437c147e511bb86882e"}