{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:33IGKBYM4PKHZ436VPVKSD26NL","short_pith_number":"pith:33IGKBYM","canonical_record":{"source":{"id":"2407.03020","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-03T11:30:03Z","cross_cats_sorted":[],"title_canon_sha256":"011b9a24d7a192ac1883f3cad2592f497d8cb58b7110f7a460ffe6fdc448f62b","abstract_canon_sha256":"f0b6eb808bb16a38b5eacada19c56ca72e9d794d0c10a0fd98e4ed3446a88a7e"},"schema_version":"1.0"},"canonical_sha256":"ded065070ce3d47cf37eabeaa90f5e6ae9be56893660d21e9f2aece7d203bf6e","source":{"kind":"arxiv","id":"2407.03020","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.03020","created_at":"2026-07-05T11:12:18Z"},{"alias_kind":"arxiv_version","alias_value":"2407.03020v1","created_at":"2026-07-05T11:12:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.03020","created_at":"2026-07-05T11:12:18Z"},{"alias_kind":"pith_short_12","alias_value":"33IGKBYM4PKH","created_at":"2026-07-05T11:12:18Z"},{"alias_kind":"pith_short_16","alias_value":"33IGKBYM4PKHZ436","created_at":"2026-07-05T11:12:18Z"},{"alias_kind":"pith_short_8","alias_value":"33IGKBYM","created_at":"2026-07-05T11:12:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:33IGKBYM4PKHZ436VPVKSD26NL","target":"record","payload":{"canonical_record":{"source":{"id":"2407.03020","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-03T11:30:03Z","cross_cats_sorted":[],"title_canon_sha256":"011b9a24d7a192ac1883f3cad2592f497d8cb58b7110f7a460ffe6fdc448f62b","abstract_canon_sha256":"f0b6eb808bb16a38b5eacada19c56ca72e9d794d0c10a0fd98e4ed3446a88a7e"},"schema_version":"1.0"},"canonical_sha256":"ded065070ce3d47cf37eabeaa90f5e6ae9be56893660d21e9f2aece7d203bf6e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:18.555221Z","signature_b64":"GnNc/oY3U0k4FwWKjYFjMoR5MqcTQMKQXg2yOoUFL9XhTCFFA79ew3FRs8fUl+LmyTGzlPP8HxQ9LLpTHSnxDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ded065070ce3d47cf37eabeaa90f5e6ae9be56893660d21e9f2aece7d203bf6e","last_reissued_at":"2026-07-05T11:12:18.554678Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:18.554678Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.03020","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":"2026-07-05T11:12:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ChX40BSzAafE0Y1xcbucUSkMBqZtFY/d3GFb6cGchnNxrFQbstaa5Wva5L8xl2R9H9JQ8o/yFu2BvEGf4taMBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T01:13:39.182187Z"},"content_sha256":"8199acc06dbea76f560a4edc297e79ea02cd74de08de838238121d81a96f6a17","schema_version":"1.0","event_id":"sha256:8199acc06dbea76f560a4edc297e79ea02cd74de08de838238121d81a96f6a17"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:33IGKBYM4PKHZ436VPVKSD26NL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Exploiting Dialect Identification in Automatic Dialectal Text Normalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bashar Alhafni, Fadhl Eryani, Fatema Nassar, Houda Bouamor, Nizar Habash, Sarah Al-Towaity, Ziyad Fawzy","submitted_at":"2024-07-03T11:30:03Z","abstract_excerpt":"Dialectal Arabic is the primary spoken language used by native Arabic speakers in daily communication. The rise of social media platforms has notably expanded its use as a written language. However, Arabic dialects do not have standard orthographies. This, combined with the inherent noise in user-generated content on social media, presents a major challenge to NLP applications dealing with Dialectal Arabic. In this paper, we explore and report on the task of CODAfication, which aims to normalize Dialectal Arabic into the Conventional Orthography for Dialectal Arabic (CODA). We work with a uniq"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.03020","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/2407.03020/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":"2026-07-05T11:12:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"scDZWNYWd7q1EFVh1gWT5J7h+K7Pv+2II7weg+gkz13FMZCBWvzIdanEjRUPVITiKqvMIOi9BPPhT67v/nauDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T01:13:39.182745Z"},"content_sha256":"f385385ec1e5758245d71a065a3271ec600e5cb271705fdfcd1909f9f485131a","schema_version":"1.0","event_id":"sha256:f385385ec1e5758245d71a065a3271ec600e5cb271705fdfcd1909f9f485131a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/33IGKBYM4PKHZ436VPVKSD26NL/bundle.json","state_url":"https://pith.science/pith/33IGKBYM4PKHZ436VPVKSD26NL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/33IGKBYM4PKHZ436VPVKSD26NL/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":"2026-08-06T01:13:39Z","links":{"resolver":"https://pith.science/pith/33IGKBYM4PKHZ436VPVKSD26NL","bundle":"https://pith.science/pith/33IGKBYM4PKHZ436VPVKSD26NL/bundle.json","state":"https://pith.science/pith/33IGKBYM4PKHZ436VPVKSD26NL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/33IGKBYM4PKHZ436VPVKSD26NL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:33IGKBYM4PKHZ436VPVKSD26NL","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":"f0b6eb808bb16a38b5eacada19c56ca72e9d794d0c10a0fd98e4ed3446a88a7e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-03T11:30:03Z","title_canon_sha256":"011b9a24d7a192ac1883f3cad2592f497d8cb58b7110f7a460ffe6fdc448f62b"},"schema_version":"1.0","source":{"id":"2407.03020","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.03020","created_at":"2026-07-05T11:12:18Z"},{"alias_kind":"arxiv_version","alias_value":"2407.03020v1","created_at":"2026-07-05T11:12:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.03020","created_at":"2026-07-05T11:12:18Z"},{"alias_kind":"pith_short_12","alias_value":"33IGKBYM4PKH","created_at":"2026-07-05T11:12:18Z"},{"alias_kind":"pith_short_16","alias_value":"33IGKBYM4PKHZ436","created_at":"2026-07-05T11:12:18Z"},{"alias_kind":"pith_short_8","alias_value":"33IGKBYM","created_at":"2026-07-05T11:12:18Z"}],"graph_snapshots":[{"event_id":"sha256:f385385ec1e5758245d71a065a3271ec600e5cb271705fdfcd1909f9f485131a","target":"graph","created_at":"2026-07-05T11:12:18Z","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/2407.03020/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Dialectal Arabic is the primary spoken language used by native Arabic speakers in daily communication. The rise of social media platforms has notably expanded its use as a written language. However, Arabic dialects do not have standard orthographies. This, combined with the inherent noise in user-generated content on social media, presents a major challenge to NLP applications dealing with Dialectal Arabic. In this paper, we explore and report on the task of CODAfication, which aims to normalize Dialectal Arabic into the Conventional Orthography for Dialectal Arabic (CODA). We work with a uniq","authors_text":"Bashar Alhafni, Fadhl Eryani, Fatema Nassar, Houda Bouamor, Nizar Habash, Sarah Al-Towaity, Ziyad Fawzy","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-03T11:30:03Z","title":"Exploiting Dialect Identification in Automatic Dialectal Text Normalization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.03020","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":"sha256:8199acc06dbea76f560a4edc297e79ea02cd74de08de838238121d81a96f6a17","target":"record","created_at":"2026-07-05T11:12:18Z","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":"f0b6eb808bb16a38b5eacada19c56ca72e9d794d0c10a0fd98e4ed3446a88a7e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-03T11:30:03Z","title_canon_sha256":"011b9a24d7a192ac1883f3cad2592f497d8cb58b7110f7a460ffe6fdc448f62b"},"schema_version":"1.0","source":{"id":"2407.03020","kind":"arxiv","version":1}},"canonical_sha256":"ded065070ce3d47cf37eabeaa90f5e6ae9be56893660d21e9f2aece7d203bf6e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ded065070ce3d47cf37eabeaa90f5e6ae9be56893660d21e9f2aece7d203bf6e","first_computed_at":"2026-07-05T11:12:18.554678Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:12:18.554678Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GnNc/oY3U0k4FwWKjYFjMoR5MqcTQMKQXg2yOoUFL9XhTCFFA79ew3FRs8fUl+LmyTGzlPP8HxQ9LLpTHSnxDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:12:18.555221Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.03020","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8199acc06dbea76f560a4edc297e79ea02cd74de08de838238121d81a96f6a17","sha256:f385385ec1e5758245d71a065a3271ec600e5cb271705fdfcd1909f9f485131a"],"state_sha256":"9fdb63d9311da6ae8196a36375503a675416950f26ceac05ae84ecbf7d4ebd59"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nd4ZoaPQNaP/fYYsoSUM6MpfHVwIDTbh0Znf1YqIod8es2pD2SFTN35/4+8M2CJfYJ0l3ywRWdS6c+q5PNo4Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T01:13:39.188348Z","bundle_sha256":"bff080f95629d9b4551e07bdae0b78e9bb16780de186b247ce49f813a1c7349f"}}