{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:43QHSP3PZIQTDE2BFH2NOGBMI4","short_pith_number":"pith:43QHSP3P","canonical_record":{"source":{"id":"2007.05612","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-07-10T21:11:46Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8f3628e756c41956a064f3a2ee84262819a3ce95a379cefdeaefb765b6b87caf","abstract_canon_sha256":"eca39fdb205296103656342ac5c7f00aec9e81517d7925576c6e47288601cd69"},"schema_version":"1.0"},"canonical_sha256":"e6e0793f6fca2131934129f4d7182c471492a8d3af0f380bcfe1c251c4841d75","source":{"kind":"arxiv","id":"2007.05612","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.05612","created_at":"2026-07-05T01:17:49Z"},{"alias_kind":"arxiv_version","alias_value":"2007.05612v1","created_at":"2026-07-05T01:17:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.05612","created_at":"2026-07-05T01:17:49Z"},{"alias_kind":"pith_short_12","alias_value":"43QHSP3PZIQT","created_at":"2026-07-05T01:17:49Z"},{"alias_kind":"pith_short_16","alias_value":"43QHSP3PZIQTDE2B","created_at":"2026-07-05T01:17:49Z"},{"alias_kind":"pith_short_8","alias_value":"43QHSP3P","created_at":"2026-07-05T01:17:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:43QHSP3PZIQTDE2BFH2NOGBMI4","target":"record","payload":{"canonical_record":{"source":{"id":"2007.05612","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-07-10T21:11:46Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8f3628e756c41956a064f3a2ee84262819a3ce95a379cefdeaefb765b6b87caf","abstract_canon_sha256":"eca39fdb205296103656342ac5c7f00aec9e81517d7925576c6e47288601cd69"},"schema_version":"1.0"},"canonical_sha256":"e6e0793f6fca2131934129f4d7182c471492a8d3af0f380bcfe1c251c4841d75","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:17:49.496779Z","signature_b64":"yezlHoe2DWIdxMqR3+axsA3KG4ukXfnbqX7XWdTgUrI3Ym9jHxwIzg8Yt+XpqiKJ1CYrSXolJbHjyXvOVVN8Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e6e0793f6fca2131934129f4d7182c471492a8d3af0f380bcfe1c251c4841d75","last_reissued_at":"2026-07-05T01:17:49.496291Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:17:49.496291Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2007.05612","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":"2026-07-05T01:17:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AOtVHyO9Xie9spYgnRi84pWpKGHbxlEpTPdBRyztJexk1kjhQdFXlvMSEk3F9tJuVgnEGH8WXVYC9/uceyvPDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T15:14:55.472422Z"},"content_sha256":"3728c6251fca2aa4bc379f1fcbaef0ffb738485168c8e7f3f1ce56854e23e162","schema_version":"1.0","event_id":"sha256:3728c6251fca2aa4bc379f1fcbaef0ffb738485168c8e7f3f1ce56854e23e162"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:43QHSP3PZIQTDE2BFH2NOGBMI4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-Dialect Arabic BERT for Country-Level Dialect Identification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Bashar Talafha, Haitham Seelawi, Hussein T. Al-Natsheh, Ibraheem Tuffaha, Mohammad Ali, Mostafa Samir, Muhy Eddin Za'ter, Wael Farhan","submitted_at":"2020-07-10T21:11:46Z","abstract_excerpt":"Arabic dialect identification is a complex problem for a number of inherent properties of the language itself. In this paper, we present the experiments conducted, and the models developed by our competing team, Mawdoo3 AI, along the way to achieving our winning solution to subtask 1 of the Nuanced Arabic Dialect Identification (NADI) shared task. The dialect identification subtask provides 21,000 country-level labeled tweets covering all 21 Arab countries. An unlabeled corpus of 10M tweets from the same domain is also presented by the competition organizers for optional use. Our winning solut"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.05612","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/2007.05612/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":"2026-07-05T01:17:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gwQHSxI4NC6XO6nYLe/ruIxoh4i3O5A0vU9fK5gzezdX82U8d2HivCZNT43abiBWkdnha3yqoDDuwVJ+AwI+Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T15:14:55.472958Z"},"content_sha256":"a588ed305f22d47908336a62e5aabf8e4d44a19b3993c2d32454fa6d9dbf2ac9","schema_version":"1.0","event_id":"sha256:a588ed305f22d47908336a62e5aabf8e4d44a19b3993c2d32454fa6d9dbf2ac9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/43QHSP3PZIQTDE2BFH2NOGBMI4/bundle.json","state_url":"https://pith.science/pith/43QHSP3PZIQTDE2BFH2NOGBMI4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/43QHSP3PZIQTDE2BFH2NOGBMI4/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":"2026-08-06T15:14:55Z","links":{"resolver":"https://pith.science/pith/43QHSP3PZIQTDE2BFH2NOGBMI4","bundle":"https://pith.science/pith/43QHSP3PZIQTDE2BFH2NOGBMI4/bundle.json","state":"https://pith.science/pith/43QHSP3PZIQTDE2BFH2NOGBMI4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/43QHSP3PZIQTDE2BFH2NOGBMI4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:43QHSP3PZIQTDE2BFH2NOGBMI4","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":"eca39fdb205296103656342ac5c7f00aec9e81517d7925576c6e47288601cd69","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-07-10T21:11:46Z","title_canon_sha256":"8f3628e756c41956a064f3a2ee84262819a3ce95a379cefdeaefb765b6b87caf"},"schema_version":"1.0","source":{"id":"2007.05612","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.05612","created_at":"2026-07-05T01:17:49Z"},{"alias_kind":"arxiv_version","alias_value":"2007.05612v1","created_at":"2026-07-05T01:17:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.05612","created_at":"2026-07-05T01:17:49Z"},{"alias_kind":"pith_short_12","alias_value":"43QHSP3PZIQT","created_at":"2026-07-05T01:17:49Z"},{"alias_kind":"pith_short_16","alias_value":"43QHSP3PZIQTDE2B","created_at":"2026-07-05T01:17:49Z"},{"alias_kind":"pith_short_8","alias_value":"43QHSP3P","created_at":"2026-07-05T01:17:49Z"}],"graph_snapshots":[{"event_id":"sha256:a588ed305f22d47908336a62e5aabf8e4d44a19b3993c2d32454fa6d9dbf2ac9","target":"graph","created_at":"2026-07-05T01:17:49Z","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/2007.05612/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Arabic dialect identification is a complex problem for a number of inherent properties of the language itself. In this paper, we present the experiments conducted, and the models developed by our competing team, Mawdoo3 AI, along the way to achieving our winning solution to subtask 1 of the Nuanced Arabic Dialect Identification (NADI) shared task. The dialect identification subtask provides 21,000 country-level labeled tweets covering all 21 Arab countries. An unlabeled corpus of 10M tweets from the same domain is also presented by the competition organizers for optional use. Our winning solut","authors_text":"Bashar Talafha, Haitham Seelawi, Hussein T. Al-Natsheh, Ibraheem Tuffaha, Mohammad Ali, Mostafa Samir, Muhy Eddin Za'ter, Wael Farhan","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-07-10T21:11:46Z","title":"Multi-Dialect Arabic BERT for Country-Level Dialect Identification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.05612","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":"sha256:3728c6251fca2aa4bc379f1fcbaef0ffb738485168c8e7f3f1ce56854e23e162","target":"record","created_at":"2026-07-05T01:17:49Z","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":"eca39fdb205296103656342ac5c7f00aec9e81517d7925576c6e47288601cd69","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-07-10T21:11:46Z","title_canon_sha256":"8f3628e756c41956a064f3a2ee84262819a3ce95a379cefdeaefb765b6b87caf"},"schema_version":"1.0","source":{"id":"2007.05612","kind":"arxiv","version":1}},"canonical_sha256":"e6e0793f6fca2131934129f4d7182c471492a8d3af0f380bcfe1c251c4841d75","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e6e0793f6fca2131934129f4d7182c471492a8d3af0f380bcfe1c251c4841d75","first_computed_at":"2026-07-05T01:17:49.496291Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:17:49.496291Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yezlHoe2DWIdxMqR3+axsA3KG4ukXfnbqX7XWdTgUrI3Ym9jHxwIzg8Yt+XpqiKJ1CYrSXolJbHjyXvOVVN8Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:17:49.496779Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.05612","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3728c6251fca2aa4bc379f1fcbaef0ffb738485168c8e7f3f1ce56854e23e162","sha256:a588ed305f22d47908336a62e5aabf8e4d44a19b3993c2d32454fa6d9dbf2ac9"],"state_sha256":"faf6f8ada63d4d46c1fe8e483a0a3f8bf2418681fd1315592fe51284db72aa47"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V+LNG7g6ObnClmrYZGv9WgBetJDz6/jqOQ5uSVvlH3s3J6rIP6cJb7LitMobRB6I+qRbRN8p7DWzPxfnw0QwCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T15:14:55.476900Z","bundle_sha256":"cb23e797c26cfd8a40cb3e67f736f9485376a6ff868d9365b8f0db063b67aaac"}}