{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:MHUG6RGOBKQBDEUAXMTUGLU5AT","short_pith_number":"pith:MHUG6RGO","canonical_record":{"source":{"id":"2306.07377","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-12T19:10:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"39d02522f76f3dfea74d96b9a5b87f7bf009ba5f941b5f2c4cc06c6dc5adb045","abstract_canon_sha256":"7be70ea0d3287ca638249a5299988e7a45df72bd8824dff533a6e6e30e9c7af3"},"schema_version":"1.0"},"canonical_sha256":"61e86f44ce0aa0119280bb27432e9d04de4e454239306342213f202fb0a2434a","source":{"kind":"arxiv","id":"2306.07377","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.07377","created_at":"2026-07-05T06:20:03Z"},{"alias_kind":"arxiv_version","alias_value":"2306.07377v1","created_at":"2026-07-05T06:20:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.07377","created_at":"2026-07-05T06:20:03Z"},{"alias_kind":"pith_short_12","alias_value":"MHUG6RGOBKQB","created_at":"2026-07-05T06:20:03Z"},{"alias_kind":"pith_short_16","alias_value":"MHUG6RGOBKQBDEUA","created_at":"2026-07-05T06:20:03Z"},{"alias_kind":"pith_short_8","alias_value":"MHUG6RGO","created_at":"2026-07-05T06:20:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:MHUG6RGOBKQBDEUAXMTUGLU5AT","target":"record","payload":{"canonical_record":{"source":{"id":"2306.07377","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-12T19:10:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"39d02522f76f3dfea74d96b9a5b87f7bf009ba5f941b5f2c4cc06c6dc5adb045","abstract_canon_sha256":"7be70ea0d3287ca638249a5299988e7a45df72bd8824dff533a6e6e30e9c7af3"},"schema_version":"1.0"},"canonical_sha256":"61e86f44ce0aa0119280bb27432e9d04de4e454239306342213f202fb0a2434a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:20:03.262617Z","signature_b64":"aoPPoIGlrvFH/09pBseKWx3NHzN2CovSIoRQLNCi7NS4t0rZFcft9Env4YkQ45LTdfnz0+1KDOuuIdMpYcVOCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"61e86f44ce0aa0119280bb27432e9d04de4e454239306342213f202fb0a2434a","last_reissued_at":"2026-07-05T06:20:03.262169Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:20:03.262169Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.07377","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":"2026-07-05T06:20:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0fCqzdtOc+1mIpJxo2xRYGoB4cowixUyh4kjE7FwXutPGPdZ8Zh6ojX7Y80PiIkUZ9KQWveA86f5tu2GXanrAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T22:07:02.665846Z"},"content_sha256":"8ca50a350a6adc2d3c0d404550e86727cbf394d06107ec67797e746e9a7639b1","schema_version":"1.0","event_id":"sha256:8ca50a350a6adc2d3c0d404550e86727cbf394d06107ec67797e746e9a7639b1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:MHUG6RGOBKQBDEUAXMTUGLU5AT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Lost in Translation: Large Language Models in Non-English Content Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aliya Bhatia, Gabriel Nicholas","submitted_at":"2023-06-12T19:10:47Z","abstract_excerpt":"In recent years, large language models (e.g., Open AI's GPT-4, Meta's LLaMa, Google's PaLM) have become the dominant approach for building AI systems to analyze and generate language online. However, the automated systems that increasingly mediate our interactions online -- such as chatbots, content moderation systems, and search engines -- are primarily designed for and work far more effectively in English than in the world's other 7,000 languages. Recently, researchers and technology companies have attempted to extend the capabilities of large language models into languages other than Englis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.07377","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/2306.07377/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":"2026-07-05T06:20:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VIYW2qLKubMCwUO1MufEQdkXfhFeaZ/+8kg2z6BtYa2d5fcorC50P/UTIjJ7wHO+wQ1F55KhVoAWMPV+/R6fAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T22:07:02.666781Z"},"content_sha256":"6872351b2ba7dd68d9e331e2d862e2bd76c240a8ca79218f0c9da8ce96cb1550","schema_version":"1.0","event_id":"sha256:6872351b2ba7dd68d9e331e2d862e2bd76c240a8ca79218f0c9da8ce96cb1550"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MHUG6RGOBKQBDEUAXMTUGLU5AT/bundle.json","state_url":"https://pith.science/pith/MHUG6RGOBKQBDEUAXMTUGLU5AT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MHUG6RGOBKQBDEUAXMTUGLU5AT/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":"2026-08-07T22:07:02Z","links":{"resolver":"https://pith.science/pith/MHUG6RGOBKQBDEUAXMTUGLU5AT","bundle":"https://pith.science/pith/MHUG6RGOBKQBDEUAXMTUGLU5AT/bundle.json","state":"https://pith.science/pith/MHUG6RGOBKQBDEUAXMTUGLU5AT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MHUG6RGOBKQBDEUAXMTUGLU5AT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:MHUG6RGOBKQBDEUAXMTUGLU5AT","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":"7be70ea0d3287ca638249a5299988e7a45df72bd8824dff533a6e6e30e9c7af3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-12T19:10:47Z","title_canon_sha256":"39d02522f76f3dfea74d96b9a5b87f7bf009ba5f941b5f2c4cc06c6dc5adb045"},"schema_version":"1.0","source":{"id":"2306.07377","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.07377","created_at":"2026-07-05T06:20:03Z"},{"alias_kind":"arxiv_version","alias_value":"2306.07377v1","created_at":"2026-07-05T06:20:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.07377","created_at":"2026-07-05T06:20:03Z"},{"alias_kind":"pith_short_12","alias_value":"MHUG6RGOBKQB","created_at":"2026-07-05T06:20:03Z"},{"alias_kind":"pith_short_16","alias_value":"MHUG6RGOBKQBDEUA","created_at":"2026-07-05T06:20:03Z"},{"alias_kind":"pith_short_8","alias_value":"MHUG6RGO","created_at":"2026-07-05T06:20:03Z"}],"graph_snapshots":[{"event_id":"sha256:6872351b2ba7dd68d9e331e2d862e2bd76c240a8ca79218f0c9da8ce96cb1550","target":"graph","created_at":"2026-07-05T06:20:03Z","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/2306.07377/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In recent years, large language models (e.g., Open AI's GPT-4, Meta's LLaMa, Google's PaLM) have become the dominant approach for building AI systems to analyze and generate language online. However, the automated systems that increasingly mediate our interactions online -- such as chatbots, content moderation systems, and search engines -- are primarily designed for and work far more effectively in English than in the world's other 7,000 languages. Recently, researchers and technology companies have attempted to extend the capabilities of large language models into languages other than Englis","authors_text":"Aliya Bhatia, Gabriel Nicholas","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-12T19:10:47Z","title":"Lost in Translation: Large Language Models in Non-English Content Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.07377","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":"sha256:8ca50a350a6adc2d3c0d404550e86727cbf394d06107ec67797e746e9a7639b1","target":"record","created_at":"2026-07-05T06:20:03Z","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":"7be70ea0d3287ca638249a5299988e7a45df72bd8824dff533a6e6e30e9c7af3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-12T19:10:47Z","title_canon_sha256":"39d02522f76f3dfea74d96b9a5b87f7bf009ba5f941b5f2c4cc06c6dc5adb045"},"schema_version":"1.0","source":{"id":"2306.07377","kind":"arxiv","version":1}},"canonical_sha256":"61e86f44ce0aa0119280bb27432e9d04de4e454239306342213f202fb0a2434a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"61e86f44ce0aa0119280bb27432e9d04de4e454239306342213f202fb0a2434a","first_computed_at":"2026-07-05T06:20:03.262169Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:20:03.262169Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aoPPoIGlrvFH/09pBseKWx3NHzN2CovSIoRQLNCi7NS4t0rZFcft9Env4YkQ45LTdfnz0+1KDOuuIdMpYcVOCg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:20:03.262617Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.07377","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8ca50a350a6adc2d3c0d404550e86727cbf394d06107ec67797e746e9a7639b1","sha256:6872351b2ba7dd68d9e331e2d862e2bd76c240a8ca79218f0c9da8ce96cb1550"],"state_sha256":"256819456802752ac7d9838b66dc67653b4279aa8d404ef87b96ce00e2af967e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4xC4nBYpwf9V2EWCaZcfUtPcSOo3nzcbtVxp7HaHhKRJnvwyeAtbhW8sMboB0jWfLE6D1tOdHe6ur2I9vYnaBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T22:07:02.673806Z","bundle_sha256":"da8add11b4e84f5b9274e89c8f2d151ce96e6ef70bcb7c9207e03892160cf4a7"}}