{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:2KFIOIM25NIAZ4BDBJI2AZNZA4","short_pith_number":"pith:2KFIOIM2","canonical_record":{"source":{"id":"2408.10811","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-20T13:05:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a67c12798d463392d838d9f035b9536a27e619330175b606940093fa599816ee","abstract_canon_sha256":"85eb8c81673cca138b5778dfc5b9346f43946ae7c6e2d3aa89072c91bb975982"},"schema_version":"1.0"},"canonical_sha256":"d28a87219aeb500cf0230a51a065b907087a714be78b8ca60287d572ff383b94","source":{"kind":"arxiv","id":"2408.10811","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.10811","created_at":"2026-07-05T08:57:17Z"},{"alias_kind":"arxiv_version","alias_value":"2408.10811v1","created_at":"2026-07-05T08:57:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.10811","created_at":"2026-07-05T08:57:17Z"},{"alias_kind":"pith_short_12","alias_value":"2KFIOIM25NIA","created_at":"2026-07-05T08:57:17Z"},{"alias_kind":"pith_short_16","alias_value":"2KFIOIM25NIAZ4BD","created_at":"2026-07-05T08:57:17Z"},{"alias_kind":"pith_short_8","alias_value":"2KFIOIM2","created_at":"2026-07-05T08:57:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:2KFIOIM25NIAZ4BDBJI2AZNZA4","target":"record","payload":{"canonical_record":{"source":{"id":"2408.10811","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-20T13:05:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a67c12798d463392d838d9f035b9536a27e619330175b606940093fa599816ee","abstract_canon_sha256":"85eb8c81673cca138b5778dfc5b9346f43946ae7c6e2d3aa89072c91bb975982"},"schema_version":"1.0"},"canonical_sha256":"d28a87219aeb500cf0230a51a065b907087a714be78b8ca60287d572ff383b94","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:57:17.807695Z","signature_b64":"qf0oX3CX9hdzW419UDBZmbtBN6JMmIDkslENUvtdjxDQOkhKxh8cJo3Ypz2zKR4nHqFs5aS/31d4RKsmHe2eBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d28a87219aeb500cf0230a51a065b907087a714be78b8ca60287d572ff383b94","last_reissued_at":"2026-07-05T08:57:17.807193Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:57:17.807193Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.10811","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:57:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3qU3wh+IeU0qqCEMQ8bbbpbeWUy4Q+q8BkSM0mvRW7U4/rMfr2XqSJ4r8yAMJ+iDKf891AoTvwOyjTgBWjmFCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:20:14.651508Z"},"content_sha256":"c0652331b790d2552f0953128bffdea7f856ad093962d363de0471f54ab99bef","schema_version":"1.0","event_id":"sha256:c0652331b790d2552f0953128bffdea7f856ad093962d363de0471f54ab99bef"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:2KFIOIM25NIAZ4BDBJI2AZNZA4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond English-Centric LLMs: What Language Do Multilingual Language Models Think in?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chengzhi Zhong, Chenhui Chu, Fei Cheng, Junfeng Jiang, Qianying Liu, Sadao Kurohashi, Yugo Murawaki, Zhen Wan","submitted_at":"2024-08-20T13:05:41Z","abstract_excerpt":"In this study, we investigate whether non-English-centric LLMs, despite their strong performance, `think' in their respective dominant language: more precisely, `think' refers to how the representations of intermediate layers, when un-embedded into the vocabulary space, exhibit higher probabilities for certain dominant languages during generation. We term such languages as internal $\\textbf{latent languages}$.\n  We examine the latent language of three typical categories of models for Japanese processing: Llama2, an English-centric model; Swallow, an English-centric model with continued pre-tra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.10811","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2408.10811/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:57:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IO7NPAJL80eC3jWE9BC6exYkbpVAFoKc6WfGmdBmmperbPvmi1Il4RGJFvbCPSurPAV62OU2JqUWVWvz0NybAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:20:14.652052Z"},"content_sha256":"49c4ae41c338dc7adbb54bf99063980dea8ca2bdfb5b5b088209c2a476f41ccd","schema_version":"1.0","event_id":"sha256:49c4ae41c338dc7adbb54bf99063980dea8ca2bdfb5b5b088209c2a476f41ccd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2KFIOIM25NIAZ4BDBJI2AZNZA4/bundle.json","state_url":"https://pith.science/pith/2KFIOIM25NIAZ4BDBJI2AZNZA4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2KFIOIM25NIAZ4BDBJI2AZNZA4/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T16:20:14Z","links":{"resolver":"https://pith.science/pith/2KFIOIM25NIAZ4BDBJI2AZNZA4","bundle":"https://pith.science/pith/2KFIOIM25NIAZ4BDBJI2AZNZA4/bundle.json","state":"https://pith.science/pith/2KFIOIM25NIAZ4BDBJI2AZNZA4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2KFIOIM25NIAZ4BDBJI2AZNZA4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2KFIOIM25NIAZ4BDBJI2AZNZA4","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":"85eb8c81673cca138b5778dfc5b9346f43946ae7c6e2d3aa89072c91bb975982","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-20T13:05:41Z","title_canon_sha256":"a67c12798d463392d838d9f035b9536a27e619330175b606940093fa599816ee"},"schema_version":"1.0","source":{"id":"2408.10811","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.10811","created_at":"2026-07-05T08:57:17Z"},{"alias_kind":"arxiv_version","alias_value":"2408.10811v1","created_at":"2026-07-05T08:57:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.10811","created_at":"2026-07-05T08:57:17Z"},{"alias_kind":"pith_short_12","alias_value":"2KFIOIM25NIA","created_at":"2026-07-05T08:57:17Z"},{"alias_kind":"pith_short_16","alias_value":"2KFIOIM25NIAZ4BD","created_at":"2026-07-05T08:57:17Z"},{"alias_kind":"pith_short_8","alias_value":"2KFIOIM2","created_at":"2026-07-05T08:57:17Z"}],"graph_snapshots":[{"event_id":"sha256:49c4ae41c338dc7adbb54bf99063980dea8ca2bdfb5b5b088209c2a476f41ccd","target":"graph","created_at":"2026-07-05T08:57:17Z","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/2408.10811/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this study, we investigate whether non-English-centric LLMs, despite their strong performance, `think' in their respective dominant language: more precisely, `think' refers to how the representations of intermediate layers, when un-embedded into the vocabulary space, exhibit higher probabilities for certain dominant languages during generation. We term such languages as internal $\\textbf{latent languages}$.\n  We examine the latent language of three typical categories of models for Japanese processing: Llama2, an English-centric model; Swallow, an English-centric model with continued pre-tra","authors_text":"Chengzhi Zhong, Chenhui Chu, Fei Cheng, Junfeng Jiang, Qianying Liu, Sadao Kurohashi, Yugo Murawaki, Zhen Wan","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-20T13:05:41Z","title":"Beyond English-Centric LLMs: What Language Do Multilingual Language Models Think in?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.10811","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:c0652331b790d2552f0953128bffdea7f856ad093962d363de0471f54ab99bef","target":"record","created_at":"2026-07-05T08:57:17Z","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":"85eb8c81673cca138b5778dfc5b9346f43946ae7c6e2d3aa89072c91bb975982","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-08-20T13:05:41Z","title_canon_sha256":"a67c12798d463392d838d9f035b9536a27e619330175b606940093fa599816ee"},"schema_version":"1.0","source":{"id":"2408.10811","kind":"arxiv","version":1}},"canonical_sha256":"d28a87219aeb500cf0230a51a065b907087a714be78b8ca60287d572ff383b94","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d28a87219aeb500cf0230a51a065b907087a714be78b8ca60287d572ff383b94","first_computed_at":"2026-07-05T08:57:17.807193Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:57:17.807193Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qf0oX3CX9hdzW419UDBZmbtBN6JMmIDkslENUvtdjxDQOkhKxh8cJo3Ypz2zKR4nHqFs5aS/31d4RKsmHe2eBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:57:17.807695Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.10811","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c0652331b790d2552f0953128bffdea7f856ad093962d363de0471f54ab99bef","sha256:49c4ae41c338dc7adbb54bf99063980dea8ca2bdfb5b5b088209c2a476f41ccd"],"state_sha256":"56380648769804de1635bf317ece11b80970e4cd8a6b58d9181c201ee4d497da"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yFS965dDqyg4uEx1+Ukt+QF1DMOsXij1xMp+pc5XD+tYC7eK4Qub/o0BIniuKZA7ql8FOOTZfW8dGuJ0pEItAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T16:20:14.657575Z","bundle_sha256":"6f8348e0767076ae40e562fa20da881eb2362ae5fd7e9b92158a9576712c08b9"}}