{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:BCIHT6YR5WW6DWDFTT3MXWGREQ","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":"7df6cb096e0c498006289c4deee5d340e47ea91dc152c97136622330b72785eb","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-26T20:09:34Z","title_canon_sha256":"c7cd7b916a28e460684ce93124d9d15937e1ccb0dc229784b165775e896d9d42"},"schema_version":"1.0","source":{"id":"2605.27649","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.27649","created_at":"2026-05-28T01:04:45Z"},{"alias_kind":"arxiv_version","alias_value":"2605.27649v1","created_at":"2026-05-28T01:04:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27649","created_at":"2026-05-28T01:04:45Z"},{"alias_kind":"pith_short_12","alias_value":"BCIHT6YR5WW6","created_at":"2026-05-28T01:04:45Z"},{"alias_kind":"pith_short_16","alias_value":"BCIHT6YR5WW6DWDF","created_at":"2026-05-28T01:04:45Z"},{"alias_kind":"pith_short_8","alias_value":"BCIHT6YR","created_at":"2026-05-28T01:04:45Z"}],"graph_snapshots":[{"event_id":"sha256:e0d5bc4c7b35a9dd9a233175f38262b55874dd792b13c96bff085aeb5d1102e8","target":"graph","created_at":"2026-05-28T01:04:45Z","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/2605.27649/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multilingual LLMs are increasingly used when instruction, source content, and required response languages do not coincide. Existing benchmarks have expanded multilingual instruction-following evaluation, but they rarely isolate these three roles within a fully crossed design. We introduce MTM-Bench, a controlled benchmark for language-conditioned task execution in which each instance is defined by a triplet \\((L_{\\text{instr}}, L_{\\text{content}}, L_{\\text{resp}})\\). Across English, Spanish, and Chinese, MTM-Bench enumerates all 27 triplets and contains 2{,}430 instances per model across seman","authors_text":"Guansu Wang, Jiaxin Liu, Lei Zhao, Liang He, Man Liang, Minxuan Hu, Qishi Zhan, Seoyeon Jang, Xinyue Xiang, Ziheng Chen","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-26T20:09:34Z","title":"Disentangling Language Roles in Multilingual LLM Task Execution"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27649","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":"sha256:7135d3313f27c999f196ba69282fa8af58fc2fc1dd5c3493bc262afa1fbf4abd","target":"record","created_at":"2026-05-28T01:04:45Z","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":"7df6cb096e0c498006289c4deee5d340e47ea91dc152c97136622330b72785eb","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-26T20:09:34Z","title_canon_sha256":"c7cd7b916a28e460684ce93124d9d15937e1ccb0dc229784b165775e896d9d42"},"schema_version":"1.0","source":{"id":"2605.27649","kind":"arxiv","version":1}},"canonical_sha256":"089079fb11edade1d8659cf6cbd8d1243d22f95a64f402f306c0f3e47c8d5b04","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"089079fb11edade1d8659cf6cbd8d1243d22f95a64f402f306c0f3e47c8d5b04","first_computed_at":"2026-05-28T01:04:45.334823Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T01:04:45.334823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KgvNkfxGT/2zlBwBEJ3nnaOtHpfUVNrGTmQRqjYQxaDfSgyiclMlq7Fgdvl+BQJLnsm01IDpjEuPy0O/qSjmBw==","signature_status":"signed_v1","signed_at":"2026-05-28T01:04:45.335291Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.27649","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7135d3313f27c999f196ba69282fa8af58fc2fc1dd5c3493bc262afa1fbf4abd","sha256:e0d5bc4c7b35a9dd9a233175f38262b55874dd792b13c96bff085aeb5d1102e8"],"state_sha256":"d6bc04e359913a91090054fd4c38e20bc8400acab7d1fce96707c9c427f7392d"}