{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CQVXM2DWY4ZUU6O3IO3KEYIAM4","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":"f3f0c64a73dbabd802e823f7597b3c5749f7c5eaf55b009a517c8b415ed5684c","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-24T16:45:13Z","title_canon_sha256":"a4bf0c8cf5f66efdf122a744d5c34e0f4ea8a278498ad400ecc2cc5321738b8a"},"schema_version":"1.0","source":{"id":"2406.16783","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.16783","created_at":"2026-07-05T10:23:20Z"},{"alias_kind":"arxiv_version","alias_value":"2406.16783v3","created_at":"2026-07-05T10:23:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.16783","created_at":"2026-07-05T10:23:20Z"},{"alias_kind":"pith_short_12","alias_value":"CQVXM2DWY4ZU","created_at":"2026-07-05T10:23:20Z"},{"alias_kind":"pith_short_16","alias_value":"CQVXM2DWY4ZUU6O3","created_at":"2026-07-05T10:23:20Z"},{"alias_kind":"pith_short_8","alias_value":"CQVXM2DW","created_at":"2026-07-05T10:23:20Z"}],"graph_snapshots":[{"event_id":"sha256:2d5b3a4cbacfd49ca46c6e68b3b4d182a9f84e9c08af1cb0ce69dac5d1b2eecb","target":"graph","created_at":"2026-07-05T10:23:20Z","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/2406.16783/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Instruction finetuning (IFT) is critical for aligning Large Language Models (LLMs) to follow instructions. While many effective IFT datasets have been introduced recently, they predominantly focus on high-resource languages like English. To better align LLMs across a broad spectrum of languages and tasks, we propose a fully synthetic, novel taxonomy (Evol) guided Multilingual, Multi-turn instruction finetuning dataset, called M2Lingual. It is constructed by first selecting a diverse set of seed examples and then utilizing the proposed Evol taxonomy to convert these seeds into complex and chall","authors_text":"Hoang Nguyen, Khyati Mahajan, Rishabh Maheshwary, Sathwik Tejaswi Madhusudhan, Vikas Yadav","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-24T16:45:13Z","title":"M2Lingual: Enhancing Multilingual, Multi-Turn Instruction Alignment in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.16783","kind":"arxiv","version":3},"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":"sha256:33c62754e4abfb1ba3d92792c1b0a072574fb8c66b01f02c24c92159ace8d96d","target":"record","created_at":"2026-07-05T10:23:20Z","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":"f3f0c64a73dbabd802e823f7597b3c5749f7c5eaf55b009a517c8b415ed5684c","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-24T16:45:13Z","title_canon_sha256":"a4bf0c8cf5f66efdf122a744d5c34e0f4ea8a278498ad400ecc2cc5321738b8a"},"schema_version":"1.0","source":{"id":"2406.16783","kind":"arxiv","version":3}},"canonical_sha256":"142b766876c7334a79db43b6a26100671e50ee05a19616107992986fd515cfde","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"142b766876c7334a79db43b6a26100671e50ee05a19616107992986fd515cfde","first_computed_at":"2026-07-05T10:23:20.456685Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:23:20.456685Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xm6SbdghQoGEmy+G8Gyd8/Q9GvLbpcSLmZnwJryGTc9/hG13R6LYPuigBnnEr184mV/wfvDJ6QFCEXenSRcfCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:23:20.457301Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.16783","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:33c62754e4abfb1ba3d92792c1b0a072574fb8c66b01f02c24c92159ace8d96d","sha256:2d5b3a4cbacfd49ca46c6e68b3b4d182a9f84e9c08af1cb0ce69dac5d1b2eecb"],"state_sha256":"6ed19faec744ca16036961afe589706bc1984952ce006799d8238af55a9a532c"}