{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:3ARCV55MUOV66YYCWFBN7Z3YDS","short_pith_number":"pith:3ARCV55M","canonical_record":{"source":{"id":"2103.11189","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-03-20T14:39:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"eb78d7daab94a8b23780058026c3610c0ba01b3a03f7076fa31e407f6d5a071d","abstract_canon_sha256":"1ca841bb14b99410ac03dd6ba5138925f2bedcb3ea088690f4e12598d58dc89b"},"schema_version":"1.0"},"canonical_sha256":"d8222af7aca3abef6302b142dfe7781c845670032ff83111be0a8a2cb1b244a0","source":{"kind":"arxiv","id":"2103.11189","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:3ARCV55MUOV66YYCWFBN7Z3YDS","target":"record","payload":{"canonical_record":{"source":{"id":"2103.11189","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-03-20T14:39:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"eb78d7daab94a8b23780058026c3610c0ba01b3a03f7076fa31e407f6d5a071d","abstract_canon_sha256":"1ca841bb14b99410ac03dd6ba5138925f2bedcb3ea088690f4e12598d58dc89b"},"schema_version":"1.0"},"canonical_sha256":"d8222af7aca3abef6302b142dfe7781c845670032ff83111be0a8a2cb1b244a0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:19:32.298482Z","signature_b64":"fsbRDsPKNqJsRY09EaG1I094mrDEJWiLbqmQL1xtSNSkksC4vX38yfEs0XqJJwt+OqaZHk2rMjuGjJGvx8dZCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d8222af7aca3abef6302b142dfe7781c845670032ff83111be0a8a2cb1b244a0","last_reissued_at":"2026-07-05T08:19:32.297946Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:19:32.297946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.11189","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:19:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oZnCuuEf8xHQMVegO5c7HWVhvdbNQSBitCRRDlGunusOw9Xldew5Xog9rx0Ul6aiqD4kfqMztQzewPvGqAlwDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T14:35:50.164259Z"},"content_sha256":"bbdf0bbf70f98669fbd85fa8f86f27f4bb6d0d6541191f4fbfd0c07510787d32","schema_version":"1.0","event_id":"sha256:bbdf0bbf70f98669fbd85fa8f86f27f4bb6d0d6541191f4fbfd0c07510787d32"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:3ARCV55MUOV66YYCWFBN7Z3YDS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Effectiveness of Morphology-aware Segmentation in Low-Resource Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Constantine Lignos, Jonne S\\\"alev\\\"a","submitted_at":"2021-03-20T14:39:25Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.11189","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/2103.11189/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:19:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vGR8F3AC3eks0PB5S2YdEz1dqVPxzoHzGPZOQ8nTMCGZtY0XLC990dniHTZfPijztcKGkS/HUnq0Sb1c2tA6Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T14:35:50.164821Z"},"content_sha256":"e1a5e45df2d7888b2ff5e46232eaa3d8994914c0a953a2d82574dc076e6d6ccf","schema_version":"1.0","event_id":"sha256:e1a5e45df2d7888b2ff5e46232eaa3d8994914c0a953a2d82574dc076e6d6ccf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3ARCV55MUOV66YYCWFBN7Z3YDS/bundle.json","state_url":"https://pith.science/pith/3ARCV55MUOV66YYCWFBN7Z3YDS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3ARCV55MUOV66YYCWFBN7Z3YDS/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-12T14:35:50Z","links":{"resolver":"https://pith.science/pith/3ARCV55MUOV66YYCWFBN7Z3YDS","bundle":"https://pith.science/pith/3ARCV55MUOV66YYCWFBN7Z3YDS/bundle.json","state":"https://pith.science/pith/3ARCV55MUOV66YYCWFBN7Z3YDS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3ARCV55MUOV66YYCWFBN7Z3YDS/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z8Yp6cs4UU9YvkrZIpkRYre0kxxriCq7gELOx4X1wYOgcjJm2+YE+pJYN93uW4REEwjXSKbHIPfimthjnaNAAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T14:35:50.171642Z","bundle_sha256":"4e71d65fc122d166952055ddaec80ba359c2cd4aa34c41768a5f6d6b352512ed"}}