{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:YAI5RUKYRKDUQVQV5SIWNY6TRO","short_pith_number":"pith:YAI5RUKY","canonical_record":{"source":{"id":"2402.14086","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-21T19:20:06Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"1419b7b14fc559abaebbc6204c869c47e8e787e90e95560ba2765f5cc7b46bcb","abstract_canon_sha256":"a9a587cd9c5498da8a187acfe698c73c5fa962680283a9a1b830706d8396d11d"},"schema_version":"1.0"},"canonical_sha256":"c011d8d1588a87485615ec9166e3d38ba252f6c664e48db6faa516de69afec38","source":{"kind":"arxiv","id":"2402.14086","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.14086","created_at":"2026-07-05T09:26:58Z"},{"alias_kind":"arxiv_version","alias_value":"2402.14086v3","created_at":"2026-07-05T09:26:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.14086","created_at":"2026-07-05T09:26:58Z"},{"alias_kind":"pith_short_12","alias_value":"YAI5RUKYRKDU","created_at":"2026-07-05T09:26:58Z"},{"alias_kind":"pith_short_16","alias_value":"YAI5RUKYRKDUQVQV","created_at":"2026-07-05T09:26:58Z"},{"alias_kind":"pith_short_8","alias_value":"YAI5RUKY","created_at":"2026-07-05T09:26:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:YAI5RUKYRKDUQVQV5SIWNY6TRO","target":"record","payload":{"canonical_record":{"source":{"id":"2402.14086","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-21T19:20:06Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"1419b7b14fc559abaebbc6204c869c47e8e787e90e95560ba2765f5cc7b46bcb","abstract_canon_sha256":"a9a587cd9c5498da8a187acfe698c73c5fa962680283a9a1b830706d8396d11d"},"schema_version":"1.0"},"canonical_sha256":"c011d8d1588a87485615ec9166e3d38ba252f6c664e48db6faa516de69afec38","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:26:58.327182Z","signature_b64":"2rJWL3NzE17QIJGbadEXgI9dIdcnt2iJKKC0CTl6eR87I/rPTBbmm2W5YcYk/JVwXTVAwsGb1Jw/c9v65zTnAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c011d8d1588a87485615ec9166e3d38ba252f6c664e48db6faa516de69afec38","last_reissued_at":"2026-07-05T09:26:58.326609Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:26:58.326609Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.14086","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:26:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"96gfTBSkA03QPpQde8KK9Zm+bdAJyx3FHPH6V1SqA2gZjqJtYt6BvDG0PcOP8x0zcZiTejlriYAmjuNsJ3XNCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T09:56:39.620323Z"},"content_sha256":"b2430e304beb5a6e7726df6c2a215df8ec9827c4e3a6ef8f3e07dc11318f98a3","schema_version":"1.0","event_id":"sha256:b2430e304beb5a6e7726df6c2a215df8ec9827c4e3a6ef8f3e07dc11318f98a3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:YAI5RUKYRKDUQVQV5SIWNY6TRO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LexC-Gen: Generating Data for Extremely Low-Resource Languages with Large Language Models and Bilingual Lexicons","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Cristina Menghini, Stephen H. Bach, Zheng-Xin Yong","submitted_at":"2024-02-21T19:20:06Z","abstract_excerpt":"Data scarcity in low-resource languages can be addressed with word-to-word translations from labeled task data in high-resource languages using bilingual lexicons. However, bilingual lexicons often have limited lexical overlap with task data, which results in poor translation coverage and lexicon utilization. We propose lexicon-conditioned data generation LexC-Gen, a method that generates low-resource-language classification task data at scale. Specifically, LexC-Gen first uses high-resource-language words from bilingual lexicons to generate lexicon-compatible task data, and then it translates"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.14086","kind":"arxiv","version":3},"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/2402.14086/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":"2026-07-05T09:26:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RFsZPyeZPPfwFQDZYvnOWOevpMvYfmHK9O0XzoGV1KxbiYshAMHvSKd5wibkPbD2kbB+haHrDNzV98z2RqobCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T09:56:39.621053Z"},"content_sha256":"c448a34847516cfbf6c6767353ffeb40aa9aa596b66275d1b1b95ae88b817c93","schema_version":"1.0","event_id":"sha256:c448a34847516cfbf6c6767353ffeb40aa9aa596b66275d1b1b95ae88b817c93"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YAI5RUKYRKDUQVQV5SIWNY6TRO/bundle.json","state_url":"https://pith.science/pith/YAI5RUKYRKDUQVQV5SIWNY6TRO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YAI5RUKYRKDUQVQV5SIWNY6TRO/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":"2026-08-20T09:56:39Z","links":{"resolver":"https://pith.science/pith/YAI5RUKYRKDUQVQV5SIWNY6TRO","bundle":"https://pith.science/pith/YAI5RUKYRKDUQVQV5SIWNY6TRO/bundle.json","state":"https://pith.science/pith/YAI5RUKYRKDUQVQV5SIWNY6TRO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YAI5RUKYRKDUQVQV5SIWNY6TRO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YAI5RUKYRKDUQVQV5SIWNY6TRO","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":"a9a587cd9c5498da8a187acfe698c73c5fa962680283a9a1b830706d8396d11d","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-21T19:20:06Z","title_canon_sha256":"1419b7b14fc559abaebbc6204c869c47e8e787e90e95560ba2765f5cc7b46bcb"},"schema_version":"1.0","source":{"id":"2402.14086","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.14086","created_at":"2026-07-05T09:26:58Z"},{"alias_kind":"arxiv_version","alias_value":"2402.14086v3","created_at":"2026-07-05T09:26:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.14086","created_at":"2026-07-05T09:26:58Z"},{"alias_kind":"pith_short_12","alias_value":"YAI5RUKYRKDU","created_at":"2026-07-05T09:26:58Z"},{"alias_kind":"pith_short_16","alias_value":"YAI5RUKYRKDUQVQV","created_at":"2026-07-05T09:26:58Z"},{"alias_kind":"pith_short_8","alias_value":"YAI5RUKY","created_at":"2026-07-05T09:26:58Z"}],"graph_snapshots":[{"event_id":"sha256:c448a34847516cfbf6c6767353ffeb40aa9aa596b66275d1b1b95ae88b817c93","target":"graph","created_at":"2026-07-05T09:26:58Z","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/2402.14086/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data scarcity in low-resource languages can be addressed with word-to-word translations from labeled task data in high-resource languages using bilingual lexicons. However, bilingual lexicons often have limited lexical overlap with task data, which results in poor translation coverage and lexicon utilization. We propose lexicon-conditioned data generation LexC-Gen, a method that generates low-resource-language classification task data at scale. Specifically, LexC-Gen first uses high-resource-language words from bilingual lexicons to generate lexicon-compatible task data, and then it translates","authors_text":"Cristina Menghini, Stephen H. Bach, Zheng-Xin Yong","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-21T19:20:06Z","title":"LexC-Gen: Generating Data for Extremely Low-Resource Languages with Large Language Models and Bilingual Lexicons"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.14086","kind":"arxiv","version":3},"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:b2430e304beb5a6e7726df6c2a215df8ec9827c4e3a6ef8f3e07dc11318f98a3","target":"record","created_at":"2026-07-05T09:26:58Z","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":"a9a587cd9c5498da8a187acfe698c73c5fa962680283a9a1b830706d8396d11d","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-21T19:20:06Z","title_canon_sha256":"1419b7b14fc559abaebbc6204c869c47e8e787e90e95560ba2765f5cc7b46bcb"},"schema_version":"1.0","source":{"id":"2402.14086","kind":"arxiv","version":3}},"canonical_sha256":"c011d8d1588a87485615ec9166e3d38ba252f6c664e48db6faa516de69afec38","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c011d8d1588a87485615ec9166e3d38ba252f6c664e48db6faa516de69afec38","first_computed_at":"2026-07-05T09:26:58.326609Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:26:58.326609Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2rJWL3NzE17QIJGbadEXgI9dIdcnt2iJKKC0CTl6eR87I/rPTBbmm2W5YcYk/JVwXTVAwsGb1Jw/c9v65zTnAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:26:58.327182Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.14086","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b2430e304beb5a6e7726df6c2a215df8ec9827c4e3a6ef8f3e07dc11318f98a3","sha256:c448a34847516cfbf6c6767353ffeb40aa9aa596b66275d1b1b95ae88b817c93"],"state_sha256":"b8bf131fdc98c910ef494699dfb5daa2ae4c9049eb2e0b4b03f4226a01d7c5bf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wgyQ712yZL9Nx19lU4q5vrmQdIs8KUFYdoKZdHkUjop0lvBTbTev4BwRzmCvc6Y7FGe8G6FU6DQnkUuUTRlkCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T09:56:39.637362Z","bundle_sha256":"1a06c890f1c74a73ae5247e17f977f11a71b0b0179cbc08cd5af2ec3457cd794"}}