{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JDZPQQEXEOAL2IPKKY6ASLZZTJ","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":"92ff4fe8657b61e2436727e4c33c708423af61528d3850d374a13fd92d60a5eb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-29T19:19:03Z","title_canon_sha256":"fc2ce032442641a13764b03813db692c07b88cffbb671e1b15043f6d5cc4354b"},"schema_version":"1.0","source":{"id":"2606.00285","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.00285","created_at":"2026-06-02T01:03:50Z"},{"alias_kind":"arxiv_version","alias_value":"2606.00285v1","created_at":"2026-06-02T01:03:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.00285","created_at":"2026-06-02T01:03:50Z"},{"alias_kind":"pith_short_12","alias_value":"JDZPQQEXEOAL","created_at":"2026-06-02T01:03:50Z"},{"alias_kind":"pith_short_16","alias_value":"JDZPQQEXEOAL2IPK","created_at":"2026-06-02T01:03:50Z"},{"alias_kind":"pith_short_8","alias_value":"JDZPQQEX","created_at":"2026-06-02T01:03:50Z"}],"graph_snapshots":[{"event_id":"sha256:aca3625f3a62e076dcee46f67c7634ceaf7f7bf77299a2b952269fd41753a738","target":"graph","created_at":"2026-06-02T01:03:50Z","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/2606.00285/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Abdelaziz M.A. Ibrahim, J\\\"org Tiedemann, Shaoxiong Ji, Zihao Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-29T19:19:03Z","title":"Model-Based Quality Assessment for Massively Multilingual Parallel Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.00285","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":"sha256:0a0e1302491704e60fbc2e6c9f4ca068d597da2ffefc7c818042921e843ea61d","target":"record","created_at":"2026-06-02T01:03:50Z","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":"92ff4fe8657b61e2436727e4c33c708423af61528d3850d374a13fd92d60a5eb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-29T19:19:03Z","title_canon_sha256":"fc2ce032442641a13764b03813db692c07b88cffbb671e1b15043f6d5cc4354b"},"schema_version":"1.0","source":{"id":"2606.00285","kind":"arxiv","version":1}},"canonical_sha256":"48f2f840972380bd21ea563c092f399a72d83c307022d17682ca7f7721e21f22","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"48f2f840972380bd21ea563c092f399a72d83c307022d17682ca7f7721e21f22","first_computed_at":"2026-06-02T01:03:50.702889Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T01:03:50.702889Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RJO3uYy1nZzDsKN/g6TDSWZ7S7PNl03aZ5EKg4Rfni5BeM6LSUzCSRdddVLN8o8zFQBOM/MyBcewa8y9jji8DA==","signature_status":"signed_v1","signed_at":"2026-06-02T01:03:50.703352Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.00285","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0a0e1302491704e60fbc2e6c9f4ca068d597da2ffefc7c818042921e843ea61d","sha256:aca3625f3a62e076dcee46f67c7634ceaf7f7bf77299a2b952269fd41753a738"],"state_sha256":"fd492ff667f090a6c0af7e6bb3d30c4c18c872cf8e54d049f6f9945170d346e7"}