{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WWBTLEBQBHQQAJMAD2FR2VWHUA","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":"4d590bc8148bd87735f468e8b09304da41e1bc5443afae1d1dbee05ad1396347","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-14T18:44:13Z","title_canon_sha256":"7cb6f891f78f9a8763cc996d5856e3efd0da4a05cb9e1706d81eafc2f25d012a"},"schema_version":"1.0","source":{"id":"2508.11017","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.11017","created_at":"2026-07-05T12:00:51Z"},{"alias_kind":"arxiv_version","alias_value":"2508.11017v2","created_at":"2026-07-05T12:00:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.11017","created_at":"2026-07-05T12:00:51Z"},{"alias_kind":"pith_short_12","alias_value":"WWBTLEBQBHQQ","created_at":"2026-07-05T12:00:51Z"},{"alias_kind":"pith_short_16","alias_value":"WWBTLEBQBHQQAJMA","created_at":"2026-07-05T12:00:51Z"},{"alias_kind":"pith_short_8","alias_value":"WWBTLEBQ","created_at":"2026-07-05T12:00:51Z"}],"graph_snapshots":[{"event_id":"sha256:c58069a39820233a502840645b8803f1719ffe275845d2b3c7f0ef6ab28b7f05","target":"graph","created_at":"2026-07-05T12:00:51Z","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/2508.11017/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) struggle with cross-lingual knowledge transfer: they hallucinate when asked in one language about facts expressed in a different language during training. This work introduces a controlled setting to study the causes and dynamics of this phenomenon by training small Transformer models from scratch on synthetic multilingual datasets. We identify a learning phase wherein a model develops either separate or unified representations of the same facts across languages, and show that unification is essential for cross-lingual transfer. We also show that the degree of unif","authors_text":"Ann Yuan, Asma Ghandeharioun, Carter Blum, Fred Zhang, Jessica Hoffmann, Julian Zimmert, Katja Filippova, Lucas Dixon, Martin Wattenberg, Mor Geva, Tal Linzen","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-14T18:44:13Z","title":"Beyond the Rosetta Stone: Unification Forces in Generalization Dynamics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.11017","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:ab28641b2eb5fd8762b6a70af2c412b810ba7d6d201f8dfa3cc38dc423bfe9fc","target":"record","created_at":"2026-07-05T12:00:51Z","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":"4d590bc8148bd87735f468e8b09304da41e1bc5443afae1d1dbee05ad1396347","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-14T18:44:13Z","title_canon_sha256":"7cb6f891f78f9a8763cc996d5856e3efd0da4a05cb9e1706d81eafc2f25d012a"},"schema_version":"1.0","source":{"id":"2508.11017","kind":"arxiv","version":2}},"canonical_sha256":"b58335903009e10025801e8b1d56c7a03a0da5566a2cebd60b1e8f6a22014b8b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b58335903009e10025801e8b1d56c7a03a0da5566a2cebd60b1e8f6a22014b8b","first_computed_at":"2026-07-05T12:00:51.632222Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:00:51.632222Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"noJGBK8HezpjHItnxKeKPgF1ua7CH7KuTfgy2FcQqPNVDD4V72cQmT8DFn7N8vNGSA9Wp7I6mwTEeJy49O7BAA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:00:51.632796Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.11017","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ab28641b2eb5fd8762b6a70af2c412b810ba7d6d201f8dfa3cc38dc423bfe9fc","sha256:c58069a39820233a502840645b8803f1719ffe275845d2b3c7f0ef6ab28b7f05"],"state_sha256":"6884aa4b1b00af505c48ef7dcf98420978ce67e273c9dec81ddbc2e6fc2ea3f4"}