{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3B77TNQM6OXE236HDKWFCOIAHW","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":"39b269820bf0b16d090590232c6e47c981a91c4e1615afbf6f756de00fcf42f1","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-28T11:06:54Z","title_canon_sha256":"6a2985aa6cff23f7d57015a066a72e3396800fc5bb62699dac69d7ef67c7699c"},"schema_version":"1.0","source":{"id":"2505.22232","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.22232","created_at":"2026-07-05T11:13:27Z"},{"alias_kind":"arxiv_version","alias_value":"2505.22232v2","created_at":"2026-07-05T11:13:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.22232","created_at":"2026-07-05T11:13:27Z"},{"alias_kind":"pith_short_12","alias_value":"3B77TNQM6OXE","created_at":"2026-07-05T11:13:27Z"},{"alias_kind":"pith_short_16","alias_value":"3B77TNQM6OXE236H","created_at":"2026-07-05T11:13:27Z"},{"alias_kind":"pith_short_8","alias_value":"3B77TNQM","created_at":"2026-07-05T11:13:27Z"}],"graph_snapshots":[{"event_id":"sha256:62a58d9e050114094dbc534d6f4560b77654cd2a090cc8923a4354984c234f05","target":"graph","created_at":"2026-07-05T11:13:27Z","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/2505.22232/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"High-quality multilingual training data is essential for effectively pretraining large language models (LLMs). Yet, the availability of suitable open-source multilingual datasets remains limited. Existing state-of-the-art datasets mostly rely on heuristic filtering methods, restricting both their cross-lingual transferability and scalability. Here, we introduce JQL, a systematic approach that efficiently curates diverse and high-quality multilingual data at scale while significantly reducing computational demands. JQL distills LLMs' annotation capabilities into lightweight annotators based on ","authors_text":"Abbas Goher Khan, Alexander Arno Weber, Alex Jude, David Kacz\\'er, Elias Wendt, Florian Mai, Joachim k\\\"ohler, Kristian Kersting, Lucie Flek, Manuel Brack, Maurice Kraus, Max L\\\"ubbering, Mehdi Ali, Michael Fromm, Nicolas Flores-Herr, Patrick Schramowski, Rafet Sifa, Richard Rutmann","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-28T11:06:54Z","title":"Judging Quality Across Languages: A Multilingual Approach to Pretraining Data Filtering with Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.22232","kind":"arxiv","version":2},"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:a9c6f8705a330afc2bb3be5df15a8ff5f4bcba4c8e703435882649228a2f67f4","target":"record","created_at":"2026-07-05T11:13:27Z","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":"39b269820bf0b16d090590232c6e47c981a91c4e1615afbf6f756de00fcf42f1","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-28T11:06:54Z","title_canon_sha256":"6a2985aa6cff23f7d57015a066a72e3396800fc5bb62699dac69d7ef67c7699c"},"schema_version":"1.0","source":{"id":"2505.22232","kind":"arxiv","version":2}},"canonical_sha256":"d87ff9b60cf3ae4d6fc71aac5139003dbf2b3131a7b07ac1e1fea6aac65d5716","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d87ff9b60cf3ae4d6fc71aac5139003dbf2b3131a7b07ac1e1fea6aac65d5716","first_computed_at":"2026-07-05T11:13:27.426787Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:27.426787Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RRKVP1ltP8DqWRByoXDmjdit5xOArVQxKPbivBL2AZPni0Jv08L+n4VFYdwefMPexzHvRuqqVGcL+kKPm8hbDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:27.427274Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.22232","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a9c6f8705a330afc2bb3be5df15a8ff5f4bcba4c8e703435882649228a2f67f4","sha256:62a58d9e050114094dbc534d6f4560b77654cd2a090cc8923a4354984c234f05"],"state_sha256":"987ec9003f4b80963dda647ab2d3177887806c785cbe478df67a8b7dd8d97137"}