{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:EJG3RSPD6MGUUN6EZVNH5NPGFM","short_pith_number":"pith:EJG3RSPD","canonical_record":{"source":{"id":"2203.09632","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-17T22:02:25Z","cross_cats_sorted":[],"title_canon_sha256":"aefb9fd87cd8970530a83fe9614a603b53a98b8985bc1951feee319ad8fc3ba0","abstract_canon_sha256":"4ad00311533a19645666ea517de42c927f6ecfca1986ebf31a6073bec2dc7cd0"},"schema_version":"1.0"},"canonical_sha256":"224db8c9e3f30d4a37c4cd5a7eb5e62b151c7f0f8f148fb0c3b97420db888e8f","source":{"kind":"arxiv","id":"2203.09632","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.09632","created_at":"2026-07-05T04:06:21Z"},{"alias_kind":"arxiv_version","alias_value":"2203.09632v1","created_at":"2026-07-05T04:06:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.09632","created_at":"2026-07-05T04:06:21Z"},{"alias_kind":"pith_short_12","alias_value":"EJG3RSPD6MGU","created_at":"2026-07-05T04:06:21Z"},{"alias_kind":"pith_short_16","alias_value":"EJG3RSPD6MGUUN6E","created_at":"2026-07-05T04:06:21Z"},{"alias_kind":"pith_short_8","alias_value":"EJG3RSPD","created_at":"2026-07-05T04:06:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:EJG3RSPD6MGUUN6EZVNH5NPGFM","target":"record","payload":{"canonical_record":{"source":{"id":"2203.09632","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-17T22:02:25Z","cross_cats_sorted":[],"title_canon_sha256":"aefb9fd87cd8970530a83fe9614a603b53a98b8985bc1951feee319ad8fc3ba0","abstract_canon_sha256":"4ad00311533a19645666ea517de42c927f6ecfca1986ebf31a6073bec2dc7cd0"},"schema_version":"1.0"},"canonical_sha256":"224db8c9e3f30d4a37c4cd5a7eb5e62b151c7f0f8f148fb0c3b97420db888e8f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:06:21.995826Z","signature_b64":"sgA7TIWJeQfnODBpdmZgUojhSmbSFlGEv6J5pQZQK0mGMiJmkE+pNRj14QYSdgH9744YU9sxfSbpIFMKcCk0Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"224db8c9e3f30d4a37c4cd5a7eb5e62b151c7f0f8f148fb0c3b97420db888e8f","last_reissued_at":"2026-07-05T04:06:21.995323Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:06:21.995323Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.09632","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":"2026-07-05T04:06:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"joyfpU+EDVc6JO7PsWarEnFHWhiA22Kait8MkGxXvfjHTcToPh8EBRgcgLA3XpNUyDo7dd78Q/E/X3LmKC2qCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T11:32:31.175628Z"},"content_sha256":"39f483e3c0e698978e4788eb78e621c390a37d504e9eda0750bdb1c82a246da3","schema_version":"1.0","event_id":"sha256:39f483e3c0e698978e4788eb78e621c390a37d504e9eda0750bdb1c82a246da3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:EJG3RSPD6MGUUN6EZVNH5NPGFM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Dim Wihl Gat Tun: The Case for Linguistic Expertise in NLP for Underdocumented Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bruce Harold Oliver, Changbing Yang, Clarissa Forbes, Edith Coates, Farhan Samir, Garrett Nicolai, Miikka Silfverberg","submitted_at":"2022-03-17T22:02:25Z","abstract_excerpt":"Recent progress in NLP is driven by pretrained models leveraging massive datasets and has predominantly benefited the world's political and economic superpowers. Technologically underserved languages are left behind because they lack such resources. Hundreds of underserved languages, nevertheless, have available data sources in the form of interlinear glossed text (IGT) from language documentation efforts. IGT remains underutilized in NLP work, perhaps because its annotations are only semi-structured and often language-specific. With this paper, we make the case that IGT data can be leveraged "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.09632","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/2203.09632/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":"2026-07-05T04:06:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7/hkcfwyWsgIQdLNTrhSbUiXj1pOx7Hff403r6DrB1lYHwEHpBmEkNXsg1GTu7PkSUy+mjLwCWeC+UVhvwBYDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T11:32:31.176155Z"},"content_sha256":"2360f4e127a5298349137066b83db50afdb7455b89f822329f3c2c06cabd7a51","schema_version":"1.0","event_id":"sha256:2360f4e127a5298349137066b83db50afdb7455b89f822329f3c2c06cabd7a51"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EJG3RSPD6MGUUN6EZVNH5NPGFM/bundle.json","state_url":"https://pith.science/pith/EJG3RSPD6MGUUN6EZVNH5NPGFM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EJG3RSPD6MGUUN6EZVNH5NPGFM/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":"2026-08-21T11:32:31Z","links":{"resolver":"https://pith.science/pith/EJG3RSPD6MGUUN6EZVNH5NPGFM","bundle":"https://pith.science/pith/EJG3RSPD6MGUUN6EZVNH5NPGFM/bundle.json","state":"https://pith.science/pith/EJG3RSPD6MGUUN6EZVNH5NPGFM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EJG3RSPD6MGUUN6EZVNH5NPGFM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:EJG3RSPD6MGUUN6EZVNH5NPGFM","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":"4ad00311533a19645666ea517de42c927f6ecfca1986ebf31a6073bec2dc7cd0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-17T22:02:25Z","title_canon_sha256":"aefb9fd87cd8970530a83fe9614a603b53a98b8985bc1951feee319ad8fc3ba0"},"schema_version":"1.0","source":{"id":"2203.09632","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.09632","created_at":"2026-07-05T04:06:21Z"},{"alias_kind":"arxiv_version","alias_value":"2203.09632v1","created_at":"2026-07-05T04:06:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.09632","created_at":"2026-07-05T04:06:21Z"},{"alias_kind":"pith_short_12","alias_value":"EJG3RSPD6MGU","created_at":"2026-07-05T04:06:21Z"},{"alias_kind":"pith_short_16","alias_value":"EJG3RSPD6MGUUN6E","created_at":"2026-07-05T04:06:21Z"},{"alias_kind":"pith_short_8","alias_value":"EJG3RSPD","created_at":"2026-07-05T04:06:21Z"}],"graph_snapshots":[{"event_id":"sha256:2360f4e127a5298349137066b83db50afdb7455b89f822329f3c2c06cabd7a51","target":"graph","created_at":"2026-07-05T04:06:21Z","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/2203.09632/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent progress in NLP is driven by pretrained models leveraging massive datasets and has predominantly benefited the world's political and economic superpowers. Technologically underserved languages are left behind because they lack such resources. Hundreds of underserved languages, nevertheless, have available data sources in the form of interlinear glossed text (IGT) from language documentation efforts. IGT remains underutilized in NLP work, perhaps because its annotations are only semi-structured and often language-specific. With this paper, we make the case that IGT data can be leveraged ","authors_text":"Bruce Harold Oliver, Changbing Yang, Clarissa Forbes, Edith Coates, Farhan Samir, Garrett Nicolai, Miikka Silfverberg","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-17T22:02:25Z","title":"Dim Wihl Gat Tun: The Case for Linguistic Expertise in NLP for Underdocumented Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.09632","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":"sha256:39f483e3c0e698978e4788eb78e621c390a37d504e9eda0750bdb1c82a246da3","target":"record","created_at":"2026-07-05T04:06:21Z","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":"4ad00311533a19645666ea517de42c927f6ecfca1986ebf31a6073bec2dc7cd0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-17T22:02:25Z","title_canon_sha256":"aefb9fd87cd8970530a83fe9614a603b53a98b8985bc1951feee319ad8fc3ba0"},"schema_version":"1.0","source":{"id":"2203.09632","kind":"arxiv","version":1}},"canonical_sha256":"224db8c9e3f30d4a37c4cd5a7eb5e62b151c7f0f8f148fb0c3b97420db888e8f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"224db8c9e3f30d4a37c4cd5a7eb5e62b151c7f0f8f148fb0c3b97420db888e8f","first_computed_at":"2026-07-05T04:06:21.995323Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:06:21.995323Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sgA7TIWJeQfnODBpdmZgUojhSmbSFlGEv6J5pQZQK0mGMiJmkE+pNRj14QYSdgH9744YU9sxfSbpIFMKcCk0Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:06:21.995826Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.09632","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:39f483e3c0e698978e4788eb78e621c390a37d504e9eda0750bdb1c82a246da3","sha256:2360f4e127a5298349137066b83db50afdb7455b89f822329f3c2c06cabd7a51"],"state_sha256":"3b003faa906f3fd05df35fb98ff73012697a5b23d85b64228b1559ff1808425b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"90UYpHAc0AJw9e68go8N8/NJK0D79hRB/xh/OZQfbgz04Dgp/L9ZDvZwY3pp5ItGOdzT0xli3vZxzTTqpCcYBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T11:32:31.181956Z","bundle_sha256":"a8e4d467b0d627501fadbf8144eb45c5e96a0dbae884d610522fd212b71468f7"}}