{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JDZPQQEXEOAL2IPKKY6ASLZZTJ","short_pith_number":"pith:JDZPQQEX","schema_version":"1.0","canonical_sha256":"48f2f840972380bd21ea563c092f399a72d83c307022d17682ca7f7721e21f22","source":{"kind":"arxiv","id":"2606.00285","version":1},"attestation_state":"computed","paper":{"title":"Model-Based Quality Assessment for Massively Multilingual Parallel Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abdelaziz M.A. Ibrahim, J\\\"org Tiedemann, Shaoxiong Ji, Zihao Li","submitted_at":"2026-05-29T19:19:03Z","abstract_excerpt":"Large-scale multilingual bitext often contains two distinct problems: non-parallel sentence pairs and low-quality translations. We decompose model-based assessment for such data into two independent components: parallelism assessment with multilingual embeddings and reference-free quality estimation (QE). For parallelism, we benchmark four embedding models on FLORES-200 and BOUQuET retrieval tasks, covering 6,654 source--target directions in our target language-pair inventory. For QE, we evaluate nine reference-free evaluators on professional FLORES-200 translations across 41,412 ordered sourc"},"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":"2606.00285","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-29T19:19:03Z","cross_cats_sorted":[],"title_canon_sha256":"fc2ce032442641a13764b03813db692c07b88cffbb671e1b15043f6d5cc4354b","abstract_canon_sha256":"92ff4fe8657b61e2436727e4c33c708423af61528d3850d374a13fd92d60a5eb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:03:50.703352Z","signature_b64":"RJO3uYy1nZzDsKN/g6TDSWZ7S7PNl03aZ5EKg4Rfni5BeM6LSUzCSRdddVLN8o8zFQBOM/MyBcewa8y9jji8DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"48f2f840972380bd21ea563c092f399a72d83c307022d17682ca7f7721e21f22","last_reissued_at":"2026-06-02T01:03:50.702889Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:03:50.702889Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Model-Based Quality Assessment for Massively Multilingual Parallel Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abdelaziz M.A. Ibrahim, J\\\"org Tiedemann, Shaoxiong Ji, Zihao Li","submitted_at":"2026-05-29T19:19:03Z","abstract_excerpt":"Large-scale multilingual bitext often contains two distinct problems: non-parallel sentence pairs and low-quality translations. We decompose model-based assessment for such data into two independent components: parallelism assessment with multilingual embeddings and reference-free quality estimation (QE). For parallelism, we benchmark four embedding models on FLORES-200 and BOUQuET retrieval tasks, covering 6,654 source--target directions in our target language-pair inventory. For QE, we evaluate nine reference-free evaluators on professional FLORES-200 translations across 41,412 ordered sourc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00285","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/2606.00285/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":"2606.00285","created_at":"2026-06-02T01:03:50.702944+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.00285v1","created_at":"2026-06-02T01:03:50.702944+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00285","created_at":"2026-06-02T01:03:50.702944+00:00"},{"alias_kind":"pith_short_12","alias_value":"JDZPQQEXEOAL","created_at":"2026-06-02T01:03:50.702944+00:00"},{"alias_kind":"pith_short_16","alias_value":"JDZPQQEXEOAL2IPK","created_at":"2026-06-02T01:03:50.702944+00:00"},{"alias_kind":"pith_short_8","alias_value":"JDZPQQEX","created_at":"2026-06-02T01:03:50.702944+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/JDZPQQEXEOAL2IPKKY6ASLZZTJ","json":"https://pith.science/pith/JDZPQQEXEOAL2IPKKY6ASLZZTJ.json","graph_json":"https://pith.science/api/pith-number/JDZPQQEXEOAL2IPKKY6ASLZZTJ/graph.json","events_json":"https://pith.science/api/pith-number/JDZPQQEXEOAL2IPKKY6ASLZZTJ/events.json","paper":"https://pith.science/paper/JDZPQQEX"},"agent_actions":{"view_html":"https://pith.science/pith/JDZPQQEXEOAL2IPKKY6ASLZZTJ","download_json":"https://pith.science/pith/JDZPQQEXEOAL2IPKKY6ASLZZTJ.json","view_paper":"https://pith.science/paper/JDZPQQEX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.00285&json=true","fetch_graph":"https://pith.science/api/pith-number/JDZPQQEXEOAL2IPKKY6ASLZZTJ/graph.json","fetch_events":"https://pith.science/api/pith-number/JDZPQQEXEOAL2IPKKY6ASLZZTJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JDZPQQEXEOAL2IPKKY6ASLZZTJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JDZPQQEXEOAL2IPKKY6ASLZZTJ/action/storage_attestation","attest_author":"https://pith.science/pith/JDZPQQEXEOAL2IPKKY6ASLZZTJ/action/author_attestation","sign_citation":"https://pith.science/pith/JDZPQQEXEOAL2IPKKY6ASLZZTJ/action/citation_signature","submit_replication":"https://pith.science/pith/JDZPQQEXEOAL2IPKKY6ASLZZTJ/action/replication_record"}},"created_at":"2026-06-02T01:03:50.702944+00:00","updated_at":"2026-06-02T01:03:50.702944+00:00"}