{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7C5LXJ5F7C76VGIYX2IF4XCEEX","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":"a167a7fda7da4716ee5a450442ba5424472906e39bb4e2ffcf2b14ef9176e52c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-25T12:15:31Z","title_canon_sha256":"eefccfcd5653c93a9ebe7c388c9c12aabbf6225e640458c3f13fc9449a89523f"},"schema_version":"1.0","source":{"id":"2505.19116","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.19116","created_at":"2026-07-05T11:39:54Z"},{"alias_kind":"arxiv_version","alias_value":"2505.19116v2","created_at":"2026-07-05T11:39:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19116","created_at":"2026-07-05T11:39:54Z"},{"alias_kind":"pith_short_12","alias_value":"7C5LXJ5F7C76","created_at":"2026-07-05T11:39:54Z"},{"alias_kind":"pith_short_16","alias_value":"7C5LXJ5F7C76VGIY","created_at":"2026-07-05T11:39:54Z"},{"alias_kind":"pith_short_8","alias_value":"7C5LXJ5F","created_at":"2026-07-05T11:39:54Z"}],"graph_snapshots":[{"event_id":"sha256:e4c64ccdbf342f2880c07f7b725b9531f1647b2c9a0ec0eb102cfb695bcd13de","target":"graph","created_at":"2026-07-05T11:39:54Z","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/2505.19116/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models often suffer from language confusion, a phenomenon in which responses are partially or entirely generated in unintended languages. This critically degrades the user experience, especially in low-resource settings. We hypothesize that this issue stems from limitations in conventional fine-tuning objectives, such as supervised learning, which optimize the likelihood of correct tokens without explicitly penalizing undesired outputs such as cross-lingual mixing. Analysis of loss trajectories during pretraining further reveals that models fail to distinguish between monolingua","authors_text":"Guijin Son, Hyunwoo Ko, Nahyun Lee, Yeongseo Woo","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-25T12:15:31Z","title":"Controlling Language Confusion in Multilingual LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19116","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:f62516a005cac2ca71b28333e98e7bcaf44753f02199063635b2b555993a168c","target":"record","created_at":"2026-07-05T11:39:54Z","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":"a167a7fda7da4716ee5a450442ba5424472906e39bb4e2ffcf2b14ef9176e52c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-25T12:15:31Z","title_canon_sha256":"eefccfcd5653c93a9ebe7c388c9c12aabbf6225e640458c3f13fc9449a89523f"},"schema_version":"1.0","source":{"id":"2505.19116","kind":"arxiv","version":2}},"canonical_sha256":"f8babba7a5f8bfea9918be905e5c4425f17de7745874a2cfc9805159d957ab86","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f8babba7a5f8bfea9918be905e5c4425f17de7745874a2cfc9805159d957ab86","first_computed_at":"2026-07-05T11:39:54.278603Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:39:54.278603Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"stCak3Ku8zVkQdXCmBVsm31/yry/5t0Qqb5o0bk8pV9cT+AHZwbNvltjoyk7QLAnyG2TTHmIeaqiIASMULWvDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:39:54.279125Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.19116","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f62516a005cac2ca71b28333e98e7bcaf44753f02199063635b2b555993a168c","sha256:e4c64ccdbf342f2880c07f7b725b9531f1647b2c9a0ec0eb102cfb695bcd13de"],"state_sha256":"a2ca7e0dd5a5301724f32c603c1b5663cd59487845982f371bfab6c7d3a25813"}