{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:HJHNNXQ6YYUXINSAAW2JCRQFDC","short_pith_number":"pith:HJHNNXQ6","canonical_record":{"source":{"id":"2402.18025","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-28T03:44:01Z","cross_cats_sorted":[],"title_canon_sha256":"c13372a21c489c2fa0fa2102d1352707121174ee781e8b8cf9c8e73bdd6bddd6","abstract_canon_sha256":"18f46d51e0ac86feaf86719c2efd8c450633893e1d9161201205d5b8677a8e14"},"schema_version":"1.0"},"canonical_sha256":"3a4ed6de1ec62974364005b491460518bdebfad67462d969bee9aa8ee208a4ac","source":{"kind":"arxiv","id":"2402.18025","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.18025","created_at":"2026-07-05T09:33:59Z"},{"alias_kind":"arxiv_version","alias_value":"2402.18025v2","created_at":"2026-07-05T09:33:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.18025","created_at":"2026-07-05T09:33:59Z"},{"alias_kind":"pith_short_12","alias_value":"HJHNNXQ6YYUX","created_at":"2026-07-05T09:33:59Z"},{"alias_kind":"pith_short_16","alias_value":"HJHNNXQ6YYUXINSA","created_at":"2026-07-05T09:33:59Z"},{"alias_kind":"pith_short_8","alias_value":"HJHNNXQ6","created_at":"2026-07-05T09:33:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:HJHNNXQ6YYUXINSAAW2JCRQFDC","target":"record","payload":{"canonical_record":{"source":{"id":"2402.18025","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-28T03:44:01Z","cross_cats_sorted":[],"title_canon_sha256":"c13372a21c489c2fa0fa2102d1352707121174ee781e8b8cf9c8e73bdd6bddd6","abstract_canon_sha256":"18f46d51e0ac86feaf86719c2efd8c450633893e1d9161201205d5b8677a8e14"},"schema_version":"1.0"},"canonical_sha256":"3a4ed6de1ec62974364005b491460518bdebfad67462d969bee9aa8ee208a4ac","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:33:59.792775Z","signature_b64":"UG0wXO0PmyWu7WVhZqTa6VH0C0etI+Z7Nl4LLUn5ypyD3UUHAqC8X+hv2v8ZmKkPjUVOtYVCSXhP/Kaa8KdmAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a4ed6de1ec62974364005b491460518bdebfad67462d969bee9aa8ee208a4ac","last_reissued_at":"2026-07-05T09:33:59.792272Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:33:59.792272Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.18025","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:33:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SU9y8dw6s3IQbUV5msYThnNDQ8zzjJVUrUb4JM/BgbQYGBpVA9GUXpkPBF9l4jhWHbjM5AfwK1xwZ1BPDTbLDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T15:47:19.193915Z"},"content_sha256":"99e46aafec2cc79b5b4c88794d966d9dc51d8e9cdbd2ac73d6c625437f9545d6","schema_version":"1.0","event_id":"sha256:99e46aafec2cc79b5b4c88794d966d9dc51d8e9cdbd2ac73d6c625437f9545d6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:HJHNNXQ6YYUXINSAAW2JCRQFDC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hire a Linguist!: Learning Endangered Languages with In-Context Linguistic Descriptions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kexun Zhang, Lei Li, Taiqi He, William Yang Wang, Yee Man Choi, Zhenqiao Song","submitted_at":"2024-02-28T03:44:01Z","abstract_excerpt":"How can large language models (LLMs) process and translate endangered languages? Many languages lack a large corpus to train a decent LLM; therefore existing LLMs rarely perform well in unseen, endangered languages. On the contrary, we observe that 2000 endangered languages, though without a large corpus, have a grammar book or a dictionary. We propose LINGOLLM, a training-free approach to enable an LLM to process unseen languages that hardly occur in its pre-training. Our key insight is to demonstrate linguistic knowledge of an unseen language in an LLM's prompt, including a dictionary, a gra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.18025","kind":"arxiv","version":2},"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/2402.18025/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":"2026-07-05T09:33:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yud2+bIMahMzZsd06WDeb8Ir5Jfa08aGCBlogtQGltorOPsD2I2Y7xjzdo3fS43WGbRmgKyXnwUVsATvqE01AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T15:47:19.194827Z"},"content_sha256":"7323d8e1ee389024701f404caee05c667cdf83c25e044641e7a9afc47e7de2db","schema_version":"1.0","event_id":"sha256:7323d8e1ee389024701f404caee05c667cdf83c25e044641e7a9afc47e7de2db"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HJHNNXQ6YYUXINSAAW2JCRQFDC/bundle.json","state_url":"https://pith.science/pith/HJHNNXQ6YYUXINSAAW2JCRQFDC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HJHNNXQ6YYUXINSAAW2JCRQFDC/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":"2026-08-19T15:47:19Z","links":{"resolver":"https://pith.science/pith/HJHNNXQ6YYUXINSAAW2JCRQFDC","bundle":"https://pith.science/pith/HJHNNXQ6YYUXINSAAW2JCRQFDC/bundle.json","state":"https://pith.science/pith/HJHNNXQ6YYUXINSAAW2JCRQFDC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HJHNNXQ6YYUXINSAAW2JCRQFDC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HJHNNXQ6YYUXINSAAW2JCRQFDC","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":"18f46d51e0ac86feaf86719c2efd8c450633893e1d9161201205d5b8677a8e14","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-28T03:44:01Z","title_canon_sha256":"c13372a21c489c2fa0fa2102d1352707121174ee781e8b8cf9c8e73bdd6bddd6"},"schema_version":"1.0","source":{"id":"2402.18025","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.18025","created_at":"2026-07-05T09:33:59Z"},{"alias_kind":"arxiv_version","alias_value":"2402.18025v2","created_at":"2026-07-05T09:33:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.18025","created_at":"2026-07-05T09:33:59Z"},{"alias_kind":"pith_short_12","alias_value":"HJHNNXQ6YYUX","created_at":"2026-07-05T09:33:59Z"},{"alias_kind":"pith_short_16","alias_value":"HJHNNXQ6YYUXINSA","created_at":"2026-07-05T09:33:59Z"},{"alias_kind":"pith_short_8","alias_value":"HJHNNXQ6","created_at":"2026-07-05T09:33:59Z"}],"graph_snapshots":[{"event_id":"sha256:7323d8e1ee389024701f404caee05c667cdf83c25e044641e7a9afc47e7de2db","target":"graph","created_at":"2026-07-05T09:33:59Z","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/2402.18025/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"How can large language models (LLMs) process and translate endangered languages? Many languages lack a large corpus to train a decent LLM; therefore existing LLMs rarely perform well in unseen, endangered languages. On the contrary, we observe that 2000 endangered languages, though without a large corpus, have a grammar book or a dictionary. We propose LINGOLLM, a training-free approach to enable an LLM to process unseen languages that hardly occur in its pre-training. Our key insight is to demonstrate linguistic knowledge of an unseen language in an LLM's prompt, including a dictionary, a gra","authors_text":"Kexun Zhang, Lei Li, Taiqi He, William Yang Wang, Yee Man Choi, Zhenqiao Song","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-28T03:44:01Z","title":"Hire a Linguist!: Learning Endangered Languages with In-Context Linguistic Descriptions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.18025","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":"sha256:99e46aafec2cc79b5b4c88794d966d9dc51d8e9cdbd2ac73d6c625437f9545d6","target":"record","created_at":"2026-07-05T09:33:59Z","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":"18f46d51e0ac86feaf86719c2efd8c450633893e1d9161201205d5b8677a8e14","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-28T03:44:01Z","title_canon_sha256":"c13372a21c489c2fa0fa2102d1352707121174ee781e8b8cf9c8e73bdd6bddd6"},"schema_version":"1.0","source":{"id":"2402.18025","kind":"arxiv","version":2}},"canonical_sha256":"3a4ed6de1ec62974364005b491460518bdebfad67462d969bee9aa8ee208a4ac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3a4ed6de1ec62974364005b491460518bdebfad67462d969bee9aa8ee208a4ac","first_computed_at":"2026-07-05T09:33:59.792272Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:33:59.792272Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UG0wXO0PmyWu7WVhZqTa6VH0C0etI+Z7Nl4LLUn5ypyD3UUHAqC8X+hv2v8ZmKkPjUVOtYVCSXhP/Kaa8KdmAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:33:59.792775Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.18025","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:99e46aafec2cc79b5b4c88794d966d9dc51d8e9cdbd2ac73d6c625437f9545d6","sha256:7323d8e1ee389024701f404caee05c667cdf83c25e044641e7a9afc47e7de2db"],"state_sha256":"8e85ab0730386c56e10ce45ca65d4fe2143db2c3d5d331243348eb2cbf149aa7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Rj9NTTKRNM3pfxUUij14LsXxhA7R8qUBWGcHqV0hAiNuyIGqbXKSJun7YG3PFZ+otHD9mBTmOk0fqh+RdRjBAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T15:47:19.200510Z","bundle_sha256":"bfdecb22e438665a8200bb6be9cc63796610fd98cf1a4f09168618422469fb9e"}}