{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:VQ3NNFSFM3CR5EPIEJKVT5DA6G","short_pith_number":"pith:VQ3NNFSF","canonical_record":{"source":{"id":"2501.15773","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-27T04:43:18Z","cross_cats_sorted":[],"title_canon_sha256":"e8da3e37dd13c9ed91882862ffa0f62227214711bce091009c7d4a603caeb3b6","abstract_canon_sha256":"155b72022c353de0808b82591caf60b2bfc56b917543a1aa25e4f1d9413cf068"},"schema_version":"1.0"},"canonical_sha256":"ac36d6964566c51e91e8225559f460f1906d00a0965c72211d95eb576456ce3a","source":{"kind":"arxiv","id":"2501.15773","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.15773","created_at":"2026-07-05T10:12:25Z"},{"alias_kind":"arxiv_version","alias_value":"2501.15773v2","created_at":"2026-07-05T10:12:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.15773","created_at":"2026-07-05T10:12:25Z"},{"alias_kind":"pith_short_12","alias_value":"VQ3NNFSFM3CR","created_at":"2026-07-05T10:12:25Z"},{"alias_kind":"pith_short_16","alias_value":"VQ3NNFSFM3CR5EPI","created_at":"2026-07-05T10:12:25Z"},{"alias_kind":"pith_short_8","alias_value":"VQ3NNFSF","created_at":"2026-07-05T10:12:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:VQ3NNFSFM3CR5EPIEJKVT5DA6G","target":"record","payload":{"canonical_record":{"source":{"id":"2501.15773","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-27T04:43:18Z","cross_cats_sorted":[],"title_canon_sha256":"e8da3e37dd13c9ed91882862ffa0f62227214711bce091009c7d4a603caeb3b6","abstract_canon_sha256":"155b72022c353de0808b82591caf60b2bfc56b917543a1aa25e4f1d9413cf068"},"schema_version":"1.0"},"canonical_sha256":"ac36d6964566c51e91e8225559f460f1906d00a0965c72211d95eb576456ce3a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:12:25.693092Z","signature_b64":"DU5tWR6sBUYRavr1oboxRdOWebpnoZcrdC2Ib/Ukn59RYEOqquoW+ykr7SEA9102FaECdb/LmwdRJT3KxtTHDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac36d6964566c51e91e8225559f460f1906d00a0965c72211d95eb576456ce3a","last_reissued_at":"2026-07-05T10:12:25.691486Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:12:25.691486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.15773","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":"2026-07-05T10:12:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ha/6zzZBRAyjEw/3woMNXtLseg+YBHGhpZL7q5mEjskrhAH68c6eei7xQsMCAGVXr/bENHnuBGLmy5cplUm1AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T11:35:10.796645Z"},"content_sha256":"fd7458ae25b3764ffe0dbee223450c7290f3750e1e4f8819afbc4f1da98efea2","schema_version":"1.0","event_id":"sha256:fd7458ae25b3764ffe0dbee223450c7290f3750e1e4f8819afbc4f1da98efea2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:VQ3NNFSFM3CR5EPIEJKVT5DA6G","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Is It Navajo? Accurate Language Detection in Endangered Athabaskan Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chunhui Zhang, Ivory Yang, Soroush Vosoughi, Weicheng Ma","submitted_at":"2025-01-27T04:43:18Z","abstract_excerpt":"Endangered languages, such as Navajo - the most widely spoken Native American language - are significantly underrepresented in contemporary language technologies, exacerbating the challenges of their preservation and revitalization. This study evaluates Google's Language Identification (LangID) tool, which does not currently support any Native American languages. To address this, we introduce a random forest classifier trained on Navajo and twenty erroneously suggested languages by LangID. Despite its simplicity, the classifier achieves near-perfect accuracy (97-100%). Additionally, the model "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.15773","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/2501.15773/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":"2026-07-05T10:12:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IhlLTGu6hc54f8YNd7S0hR3c6kaph0JLGZd6Oj/Ba470SgbQTBryI4CXUCQesMalvZNXLq92eZelpfW+BjakBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T11:35:10.798519Z"},"content_sha256":"ba7d0e5b9cdaa3031d4e61c1222a709ebd03e078cb6b155b1dc1de3ce9522d79","schema_version":"1.0","event_id":"sha256:ba7d0e5b9cdaa3031d4e61c1222a709ebd03e078cb6b155b1dc1de3ce9522d79"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VQ3NNFSFM3CR5EPIEJKVT5DA6G/bundle.json","state_url":"https://pith.science/pith/VQ3NNFSFM3CR5EPIEJKVT5DA6G/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VQ3NNFSFM3CR5EPIEJKVT5DA6G/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":"2026-08-18T11:35:10Z","links":{"resolver":"https://pith.science/pith/VQ3NNFSFM3CR5EPIEJKVT5DA6G","bundle":"https://pith.science/pith/VQ3NNFSFM3CR5EPIEJKVT5DA6G/bundle.json","state":"https://pith.science/pith/VQ3NNFSFM3CR5EPIEJKVT5DA6G/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VQ3NNFSFM3CR5EPIEJKVT5DA6G/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VQ3NNFSFM3CR5EPIEJKVT5DA6G","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":"155b72022c353de0808b82591caf60b2bfc56b917543a1aa25e4f1d9413cf068","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-27T04:43:18Z","title_canon_sha256":"e8da3e37dd13c9ed91882862ffa0f62227214711bce091009c7d4a603caeb3b6"},"schema_version":"1.0","source":{"id":"2501.15773","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.15773","created_at":"2026-07-05T10:12:25Z"},{"alias_kind":"arxiv_version","alias_value":"2501.15773v2","created_at":"2026-07-05T10:12:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.15773","created_at":"2026-07-05T10:12:25Z"},{"alias_kind":"pith_short_12","alias_value":"VQ3NNFSFM3CR","created_at":"2026-07-05T10:12:25Z"},{"alias_kind":"pith_short_16","alias_value":"VQ3NNFSFM3CR5EPI","created_at":"2026-07-05T10:12:25Z"},{"alias_kind":"pith_short_8","alias_value":"VQ3NNFSF","created_at":"2026-07-05T10:12:25Z"}],"graph_snapshots":[{"event_id":"sha256:ba7d0e5b9cdaa3031d4e61c1222a709ebd03e078cb6b155b1dc1de3ce9522d79","target":"graph","created_at":"2026-07-05T10:12:25Z","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/2501.15773/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Endangered languages, such as Navajo - the most widely spoken Native American language - are significantly underrepresented in contemporary language technologies, exacerbating the challenges of their preservation and revitalization. This study evaluates Google's Language Identification (LangID) tool, which does not currently support any Native American languages. To address this, we introduce a random forest classifier trained on Navajo and twenty erroneously suggested languages by LangID. Despite its simplicity, the classifier achieves near-perfect accuracy (97-100%). Additionally, the model ","authors_text":"Chunhui Zhang, Ivory Yang, Soroush Vosoughi, Weicheng Ma","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-27T04:43:18Z","title":"Is It Navajo? Accurate Language Detection in Endangered Athabaskan Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.15773","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:fd7458ae25b3764ffe0dbee223450c7290f3750e1e4f8819afbc4f1da98efea2","target":"record","created_at":"2026-07-05T10:12:25Z","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":"155b72022c353de0808b82591caf60b2bfc56b917543a1aa25e4f1d9413cf068","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-27T04:43:18Z","title_canon_sha256":"e8da3e37dd13c9ed91882862ffa0f62227214711bce091009c7d4a603caeb3b6"},"schema_version":"1.0","source":{"id":"2501.15773","kind":"arxiv","version":2}},"canonical_sha256":"ac36d6964566c51e91e8225559f460f1906d00a0965c72211d95eb576456ce3a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ac36d6964566c51e91e8225559f460f1906d00a0965c72211d95eb576456ce3a","first_computed_at":"2026-07-05T10:12:25.691486Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:12:25.691486Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DU5tWR6sBUYRavr1oboxRdOWebpnoZcrdC2Ib/Ukn59RYEOqquoW+ykr7SEA9102FaECdb/LmwdRJT3KxtTHDg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:12:25.693092Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.15773","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fd7458ae25b3764ffe0dbee223450c7290f3750e1e4f8819afbc4f1da98efea2","sha256:ba7d0e5b9cdaa3031d4e61c1222a709ebd03e078cb6b155b1dc1de3ce9522d79"],"state_sha256":"f27772f9b82922a50276a796b7eb63a5a2a2e4ff565815c04a9fcb5769540753"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RX8VCconzsYcF75cXbB5/gpG5Eun5mvIjmI/4PHwsWZKWZK+bzHeTi+3gARGu3GiphjxID40eoxSPv4Dkf//BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T11:35:10.809825Z","bundle_sha256":"9f9803f406db80f8fc81e37ae553ce246b06c527502c1bb11713752858e26447"}}