{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:W6UCWMSO63JEPGITLPQF7FLBJJ","short_pith_number":"pith:W6UCWMSO","canonical_record":{"source":{"id":"2102.11000","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-02-07T01:39:52Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a1c6dbc3f33c315a2bdd6ead212128c01daf527b15d719d611b2ba4b261557a2","abstract_canon_sha256":"cbb03ba43c43c8210d5668831c74d9caa798ee251e23a3af453acf3e86fb201d"},"schema_version":"1.0"},"canonical_sha256":"b7a82b324ef6d24799135be05f95614a6c794c7b69af1b37b936b6409ecf4211","source":{"kind":"arxiv","id":"2102.11000","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.11000","created_at":"2026-07-05T02:17:03Z"},{"alias_kind":"arxiv_version","alias_value":"2102.11000v1","created_at":"2026-07-05T02:17:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.11000","created_at":"2026-07-05T02:17:03Z"},{"alias_kind":"pith_short_12","alias_value":"W6UCWMSO63JE","created_at":"2026-07-05T02:17:03Z"},{"alias_kind":"pith_short_16","alias_value":"W6UCWMSO63JEPGIT","created_at":"2026-07-05T02:17:03Z"},{"alias_kind":"pith_short_8","alias_value":"W6UCWMSO","created_at":"2026-07-05T02:17:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:W6UCWMSO63JEPGITLPQF7FLBJJ","target":"record","payload":{"canonical_record":{"source":{"id":"2102.11000","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-02-07T01:39:52Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a1c6dbc3f33c315a2bdd6ead212128c01daf527b15d719d611b2ba4b261557a2","abstract_canon_sha256":"cbb03ba43c43c8210d5668831c74d9caa798ee251e23a3af453acf3e86fb201d"},"schema_version":"1.0"},"canonical_sha256":"b7a82b324ef6d24799135be05f95614a6c794c7b69af1b37b936b6409ecf4211","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:17:03.609755Z","signature_b64":"BoIG74cePAWdwqjXlQ7x/3sHHB4CxY8AmFCt6KG8Cd7XAQI05ieAyS71v6k/65aw915F1eri0rVJ/ov/v+jXAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7a82b324ef6d24799135be05f95614a6c794c7b69af1b37b936b6409ecf4211","last_reissued_at":"2026-07-05T02:17:03.609322Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:17:03.609322Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2102.11000","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":"2026-07-05T02:17:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gohIQ2dfVC9xJ8VA2x6nvzjzQBTw84voY36+DU9s5zwn1ISNHyu5AAp1yOfkX6QJua6QyRh91PlP4Wmq/cvBBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T12:49:01.659569Z"},"content_sha256":"f808cbbe04b927dd015edf96eb9255a08a20874d92a1d951093f117db961e12e","schema_version":"1.0","event_id":"sha256:f808cbbe04b927dd015edf96eb9255a08a20874d92a1d951093f117db961e12e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:W6UCWMSO63JEPGITLPQF7FLBJJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An open access NLP dataset for Arabic dialects : Data collection, labeling, and model construction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Abdellah El Mekki, ElMehdi Boujou, Hamza Chataoui, Ikram Chairi, Ismail Berrada, Saad Benjelloun","submitted_at":"2021-02-07T01:39:52Z","abstract_excerpt":"Natural Language Processing (NLP) is today a very active field of research and innovation. Many applications need however big sets of data for supervised learning, suitably labelled for the training purpose. This includes applications for the Arabic language and its national dialects. However, such open access labeled data sets in Arabic and its dialects are lacking in the Data Science ecosystem and this lack can be a burden to innovation and research in this field. In this work, we present an open data set of social data content in several Arabic dialects. This data was collected from the Twi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.11000","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/2102.11000/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":"2026-07-05T02:17:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TZ9iXZrIr2M+varXHMhdZgpEmiuyU+u+zcApTIUpxnwx4CSJaD85VcSf8fZYGrCLOJE9tSSt3xhKY9iW/gauBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T12:49:01.660089Z"},"content_sha256":"644061f25507a5d69f6fb70a6c62139d17d33cd47f47747b80064d988b4111d2","schema_version":"1.0","event_id":"sha256:644061f25507a5d69f6fb70a6c62139d17d33cd47f47747b80064d988b4111d2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/W6UCWMSO63JEPGITLPQF7FLBJJ/bundle.json","state_url":"https://pith.science/pith/W6UCWMSO63JEPGITLPQF7FLBJJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/W6UCWMSO63JEPGITLPQF7FLBJJ/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":"2026-08-09T12:49:01Z","links":{"resolver":"https://pith.science/pith/W6UCWMSO63JEPGITLPQF7FLBJJ","bundle":"https://pith.science/pith/W6UCWMSO63JEPGITLPQF7FLBJJ/bundle.json","state":"https://pith.science/pith/W6UCWMSO63JEPGITLPQF7FLBJJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/W6UCWMSO63JEPGITLPQF7FLBJJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:W6UCWMSO63JEPGITLPQF7FLBJJ","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":"cbb03ba43c43c8210d5668831c74d9caa798ee251e23a3af453acf3e86fb201d","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-02-07T01:39:52Z","title_canon_sha256":"a1c6dbc3f33c315a2bdd6ead212128c01daf527b15d719d611b2ba4b261557a2"},"schema_version":"1.0","source":{"id":"2102.11000","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.11000","created_at":"2026-07-05T02:17:03Z"},{"alias_kind":"arxiv_version","alias_value":"2102.11000v1","created_at":"2026-07-05T02:17:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.11000","created_at":"2026-07-05T02:17:03Z"},{"alias_kind":"pith_short_12","alias_value":"W6UCWMSO63JE","created_at":"2026-07-05T02:17:03Z"},{"alias_kind":"pith_short_16","alias_value":"W6UCWMSO63JEPGIT","created_at":"2026-07-05T02:17:03Z"},{"alias_kind":"pith_short_8","alias_value":"W6UCWMSO","created_at":"2026-07-05T02:17:03Z"}],"graph_snapshots":[{"event_id":"sha256:644061f25507a5d69f6fb70a6c62139d17d33cd47f47747b80064d988b4111d2","target":"graph","created_at":"2026-07-05T02:17:03Z","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/2102.11000/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Natural Language Processing (NLP) is today a very active field of research and innovation. Many applications need however big sets of data for supervised learning, suitably labelled for the training purpose. This includes applications for the Arabic language and its national dialects. However, such open access labeled data sets in Arabic and its dialects are lacking in the Data Science ecosystem and this lack can be a burden to innovation and research in this field. In this work, we present an open data set of social data content in several Arabic dialects. This data was collected from the Twi","authors_text":"Abdellah El Mekki, ElMehdi Boujou, Hamza Chataoui, Ikram Chairi, Ismail Berrada, Saad Benjelloun","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-02-07T01:39:52Z","title":"An open access NLP dataset for Arabic dialects : Data collection, labeling, and model construction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.11000","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:f808cbbe04b927dd015edf96eb9255a08a20874d92a1d951093f117db961e12e","target":"record","created_at":"2026-07-05T02:17:03Z","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":"cbb03ba43c43c8210d5668831c74d9caa798ee251e23a3af453acf3e86fb201d","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-02-07T01:39:52Z","title_canon_sha256":"a1c6dbc3f33c315a2bdd6ead212128c01daf527b15d719d611b2ba4b261557a2"},"schema_version":"1.0","source":{"id":"2102.11000","kind":"arxiv","version":1}},"canonical_sha256":"b7a82b324ef6d24799135be05f95614a6c794c7b69af1b37b936b6409ecf4211","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b7a82b324ef6d24799135be05f95614a6c794c7b69af1b37b936b6409ecf4211","first_computed_at":"2026-07-05T02:17:03.609322Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:17:03.609322Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BoIG74cePAWdwqjXlQ7x/3sHHB4CxY8AmFCt6KG8Cd7XAQI05ieAyS71v6k/65aw915F1eri0rVJ/ov/v+jXAw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:17:03.609755Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.11000","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f808cbbe04b927dd015edf96eb9255a08a20874d92a1d951093f117db961e12e","sha256:644061f25507a5d69f6fb70a6c62139d17d33cd47f47747b80064d988b4111d2"],"state_sha256":"5bc74c955dd5df0c4fde4b6ac048b27458584a4311964e3d64233e8057376212"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hclBsh6JEkLzSFyft5MiYi9eELCORbOd1gLriddo8j6OfJHLWLEfCwscfu6wc58i+sZCEQ2gNmzFitzjWljfCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T12:49:01.665451Z","bundle_sha256":"9bad2e724e9f204436b2a3bbc663d31132740944c23b1a6aa26d78721f083d71"}}