{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NWBHZJK4LW56JCHVIJZIINEELS","short_pith_number":"pith:NWBHZJK4","schema_version":"1.0","canonical_sha256":"6d827ca55c5dbbe488f542728434845cac7d65d9e320fd63510cbcfdea854958","source":{"kind":"arxiv","id":"2607.19101","version":1},"attestation_state":"computed","paper":{"title":"Translation as Augmentation: Effect of Translated Data on Assessment of Difficulty","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Jue Hou, Roman Yangarber, Yiheng Wu","submitted_at":"2026-07-21T13:43:46Z","abstract_excerpt":"Reliable Text Difficulty Assessment is a prerequisite for valid text simplification workflows and personalized learning applications. However, the development of robust assessment models is severely hindered by a critical bottleneck: the scarcity of expert-annotated corpora containing fine-grained difficulty levels (e.g., CEFR), particularly for lower-resource languages. This paper addresses this data scarcity problem in the context of a low-resource European language. We propose a cross-lingual data augmentation strategy that leverages machine translation to transfer labeled resources from hi"},"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":"2607.19101","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-21T13:43:46Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"30043ddb4fad413d418aa91370bf7f5f4cebce18c22d25f8f52d5bc16b2ac966","abstract_canon_sha256":"0893037fb61a89315ba618b16e0518157304a1dd1502579137a49a4e1f42d2af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-22T01:24:08.692618Z","signature_b64":"j1yP5hbuueNE+yRb5TxNUg/4JhOFI2oIjAGkmNpmIpzejal3/D+5JPirTpuKJhXfsgqVYqdVyQHpVTSjnF03CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d827ca55c5dbbe488f542728434845cac7d65d9e320fd63510cbcfdea854958","last_reissued_at":"2026-07-22T01:24:08.691771Z","signature_status":"signed_v1","first_computed_at":"2026-07-22T01:24:08.691771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Translation as Augmentation: Effect of Translated Data on Assessment of Difficulty","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Jue Hou, Roman Yangarber, Yiheng Wu","submitted_at":"2026-07-21T13:43:46Z","abstract_excerpt":"Reliable Text Difficulty Assessment is a prerequisite for valid text simplification workflows and personalized learning applications. However, the development of robust assessment models is severely hindered by a critical bottleneck: the scarcity of expert-annotated corpora containing fine-grained difficulty levels (e.g., CEFR), particularly for lower-resource languages. This paper addresses this data scarcity problem in the context of a low-resource European language. We propose a cross-lingual data augmentation strategy that leverages machine translation to transfer labeled resources from hi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.19101","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/2607.19101/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":"2607.19101","created_at":"2026-07-22T01:24:08.692204+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.19101v1","created_at":"2026-07-22T01:24:08.692204+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.19101","created_at":"2026-07-22T01:24:08.692204+00:00"},{"alias_kind":"pith_short_12","alias_value":"NWBHZJK4LW56","created_at":"2026-07-22T01:24:08.692204+00:00"},{"alias_kind":"pith_short_16","alias_value":"NWBHZJK4LW56JCHV","created_at":"2026-07-22T01:24:08.692204+00:00"},{"alias_kind":"pith_short_8","alias_value":"NWBHZJK4","created_at":"2026-07-22T01:24:08.692204+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/NWBHZJK4LW56JCHVIJZIINEELS","json":"https://pith.science/pith/NWBHZJK4LW56JCHVIJZIINEELS.json","graph_json":"https://pith.science/api/pith-number/NWBHZJK4LW56JCHVIJZIINEELS/graph.json","events_json":"https://pith.science/api/pith-number/NWBHZJK4LW56JCHVIJZIINEELS/events.json","paper":"https://pith.science/paper/NWBHZJK4"},"agent_actions":{"view_html":"https://pith.science/pith/NWBHZJK4LW56JCHVIJZIINEELS","download_json":"https://pith.science/pith/NWBHZJK4LW56JCHVIJZIINEELS.json","view_paper":"https://pith.science/paper/NWBHZJK4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.19101&json=true","fetch_graph":"https://pith.science/api/pith-number/NWBHZJK4LW56JCHVIJZIINEELS/graph.json","fetch_events":"https://pith.science/api/pith-number/NWBHZJK4LW56JCHVIJZIINEELS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NWBHZJK4LW56JCHVIJZIINEELS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NWBHZJK4LW56JCHVIJZIINEELS/action/storage_attestation","attest_author":"https://pith.science/pith/NWBHZJK4LW56JCHVIJZIINEELS/action/author_attestation","sign_citation":"https://pith.science/pith/NWBHZJK4LW56JCHVIJZIINEELS/action/citation_signature","submit_replication":"https://pith.science/pith/NWBHZJK4LW56JCHVIJZIINEELS/action/replication_record"}},"created_at":"2026-07-22T01:24:08.692204+00:00","updated_at":"2026-07-22T01:24:08.692204+00:00"}