{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:S6S35RSQIZFLOKDD5YZAIWUM75","short_pith_number":"pith:S6S35RSQ","canonical_record":{"source":{"id":"2401.05632","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-11T03:04:38Z","cross_cats_sorted":[],"title_canon_sha256":"012fbb91c5509ecedd46e91bcffdad8a6ad06a75565b67d7c21e16cba0fd8e3b","abstract_canon_sha256":"79bb183535b2149de40efb6b97132dc4b32b7f13e58da28dda3ee7053da48bfd"},"schema_version":"1.0"},"canonical_sha256":"97a5bec650464ab72863ee32045a8cff44576f06833f9af809b8df13249ca2fd","source":{"kind":"arxiv","id":"2401.05632","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.05632","created_at":"2026-07-05T09:45:43Z"},{"alias_kind":"arxiv_version","alias_value":"2401.05632v4","created_at":"2026-07-05T09:45:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.05632","created_at":"2026-07-05T09:45:43Z"},{"alias_kind":"pith_short_12","alias_value":"S6S35RSQIZFL","created_at":"2026-07-05T09:45:43Z"},{"alias_kind":"pith_short_16","alias_value":"S6S35RSQIZFLOKDD","created_at":"2026-07-05T09:45:43Z"},{"alias_kind":"pith_short_8","alias_value":"S6S35RSQ","created_at":"2026-07-05T09:45:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:S6S35RSQIZFLOKDD5YZAIWUM75","target":"record","payload":{"canonical_record":{"source":{"id":"2401.05632","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-11T03:04:38Z","cross_cats_sorted":[],"title_canon_sha256":"012fbb91c5509ecedd46e91bcffdad8a6ad06a75565b67d7c21e16cba0fd8e3b","abstract_canon_sha256":"79bb183535b2149de40efb6b97132dc4b32b7f13e58da28dda3ee7053da48bfd"},"schema_version":"1.0"},"canonical_sha256":"97a5bec650464ab72863ee32045a8cff44576f06833f9af809b8df13249ca2fd","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:43.035798Z","signature_b64":"Kn5a0vvjgjJD0FBScL6oq+zRevM9pHU8INAzhu/kEv3FrNz+BVg6jLE2Qei4Ul96z4X9hknROVXQgWeel9OCAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97a5bec650464ab72863ee32045a8cff44576f06833f9af809b8df13249ca2fd","last_reissued_at":"2026-07-05T09:45:43.035290Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:43.035290Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.05632","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:45:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iISgpXqN4PcnGoS9rDOvlc8TqS6L9c6TrfwGb0bngmR3ly0XiY8kU8mawvo3tlKY/KZBhMYmJQkT9S9wMxKTAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:26:56.679365Z"},"content_sha256":"bb3cbf2fccc7a5ceabcb412da2a2e095d59ebfba6cd6f507d33633288acadd79","schema_version":"1.0","event_id":"sha256:bb3cbf2fccc7a5ceabcb412da2a2e095d59ebfba6cd6f507d33633288acadd79"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:S6S35RSQIZFLOKDD5YZAIWUM75","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Natural Language Processing for Dialects of a Language: A Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aditya Joshi, Diptesh Kanojia, Doris Dippold, Gholamreza Haffari, Haolan Zhan, Raj Dabre, Zhuang Li","submitted_at":"2024-01-11T03:04:38Z","abstract_excerpt":"State-of-the-art natural language processing (NLP) models are trained on massive training corpora, and report a superlative performance on evaluation datasets. This survey delves into an important attribute of these datasets: the dialect of a language. Motivated by the performance degradation of NLP models for dialectal datasets and its implications for the equity of language technologies, we survey past research in NLP for dialects in terms of datasets, and approaches. We describe a wide range of NLP tasks in terms of two categories: natural language understanding (NLU) (for tasks such as dia"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.05632","kind":"arxiv","version":4},"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/2401.05632/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":"2026-07-05T09:45:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AsEDU7Yfd39oAEoEAZXoS55cIfQnwE9lLZro57rfyVOOU5kGQLs3FtkFSXDtCao33HkTUEFHtV8RI54d5eB9Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:26:56.679861Z"},"content_sha256":"f5b55209e03f0dcbe7b9000f53a0ce1ae5ff6d9c08da85548b251de8ee31cc99","schema_version":"1.0","event_id":"sha256:f5b55209e03f0dcbe7b9000f53a0ce1ae5ff6d9c08da85548b251de8ee31cc99"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/S6S35RSQIZFLOKDD5YZAIWUM75/bundle.json","state_url":"https://pith.science/pith/S6S35RSQIZFLOKDD5YZAIWUM75/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/S6S35RSQIZFLOKDD5YZAIWUM75/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":"2026-08-08T22:26:56Z","links":{"resolver":"https://pith.science/pith/S6S35RSQIZFLOKDD5YZAIWUM75","bundle":"https://pith.science/pith/S6S35RSQIZFLOKDD5YZAIWUM75/bundle.json","state":"https://pith.science/pith/S6S35RSQIZFLOKDD5YZAIWUM75/state.json","well_known_bundle":"https://pith.science/.well-known/pith/S6S35RSQIZFLOKDD5YZAIWUM75/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:S6S35RSQIZFLOKDD5YZAIWUM75","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":"79bb183535b2149de40efb6b97132dc4b32b7f13e58da28dda3ee7053da48bfd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-11T03:04:38Z","title_canon_sha256":"012fbb91c5509ecedd46e91bcffdad8a6ad06a75565b67d7c21e16cba0fd8e3b"},"schema_version":"1.0","source":{"id":"2401.05632","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.05632","created_at":"2026-07-05T09:45:43Z"},{"alias_kind":"arxiv_version","alias_value":"2401.05632v4","created_at":"2026-07-05T09:45:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.05632","created_at":"2026-07-05T09:45:43Z"},{"alias_kind":"pith_short_12","alias_value":"S6S35RSQIZFL","created_at":"2026-07-05T09:45:43Z"},{"alias_kind":"pith_short_16","alias_value":"S6S35RSQIZFLOKDD","created_at":"2026-07-05T09:45:43Z"},{"alias_kind":"pith_short_8","alias_value":"S6S35RSQ","created_at":"2026-07-05T09:45:43Z"}],"graph_snapshots":[{"event_id":"sha256:f5b55209e03f0dcbe7b9000f53a0ce1ae5ff6d9c08da85548b251de8ee31cc99","target":"graph","created_at":"2026-07-05T09:45:43Z","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/2401.05632/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"State-of-the-art natural language processing (NLP) models are trained on massive training corpora, and report a superlative performance on evaluation datasets. This survey delves into an important attribute of these datasets: the dialect of a language. Motivated by the performance degradation of NLP models for dialectal datasets and its implications for the equity of language technologies, we survey past research in NLP for dialects in terms of datasets, and approaches. We describe a wide range of NLP tasks in terms of two categories: natural language understanding (NLU) (for tasks such as dia","authors_text":"Aditya Joshi, Diptesh Kanojia, Doris Dippold, Gholamreza Haffari, Haolan Zhan, Raj Dabre, Zhuang Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-11T03:04:38Z","title":"Natural Language Processing for Dialects of a Language: A Survey"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.05632","kind":"arxiv","version":4},"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:bb3cbf2fccc7a5ceabcb412da2a2e095d59ebfba6cd6f507d33633288acadd79","target":"record","created_at":"2026-07-05T09:45:43Z","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":"79bb183535b2149de40efb6b97132dc4b32b7f13e58da28dda3ee7053da48bfd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-11T03:04:38Z","title_canon_sha256":"012fbb91c5509ecedd46e91bcffdad8a6ad06a75565b67d7c21e16cba0fd8e3b"},"schema_version":"1.0","source":{"id":"2401.05632","kind":"arxiv","version":4}},"canonical_sha256":"97a5bec650464ab72863ee32045a8cff44576f06833f9af809b8df13249ca2fd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"97a5bec650464ab72863ee32045a8cff44576f06833f9af809b8df13249ca2fd","first_computed_at":"2026-07-05T09:45:43.035290Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:45:43.035290Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Kn5a0vvjgjJD0FBScL6oq+zRevM9pHU8INAzhu/kEv3FrNz+BVg6jLE2Qei4Ul96z4X9hknROVXQgWeel9OCAw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:45:43.035798Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.05632","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bb3cbf2fccc7a5ceabcb412da2a2e095d59ebfba6cd6f507d33633288acadd79","sha256:f5b55209e03f0dcbe7b9000f53a0ce1ae5ff6d9c08da85548b251de8ee31cc99"],"state_sha256":"38f4b7c05570f4ec7951fa71430c64c5c0ab13d7e40838074ce5f4f953638555"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aNUoiGy8jXzcVoRgyOPG44YwdLPAUnM0qSdf3suMvtKd/PaW5NAe4DoFZ9vTbwVMMJiYsSYSOOozsGOYp20/BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T22:26:56.683262Z","bundle_sha256":"467d30e72d944603932646b845c3cd6d8fcbedf5530a1a3cb313b4f8a858400c"}}