{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:ICNHV7EEOOT6ZIUCEVPVDHR7Q5","short_pith_number":"pith:ICNHV7EE","canonical_record":{"source":{"id":"2112.04329","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-08T15:19:24Z","cross_cats_sorted":[],"title_canon_sha256":"17d41493d4338018af50346ee49073b1a9403ef8c8383ad0b4008d269d647efc","abstract_canon_sha256":"9721ab1acee23c9daff2202cb40ebb1b23fd74eb0cf4cfc5cb7f64ba2ee7ce99"},"schema_version":"1.0"},"canonical_sha256":"409a7afc8473a7eca282255f519e3f877eba1a81d0de37860c266642a7bbc385","source":{"kind":"arxiv","id":"2112.04329","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.04329","created_at":"2026-07-05T03:47:02Z"},{"alias_kind":"arxiv_version","alias_value":"2112.04329v3","created_at":"2026-07-05T03:47:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.04329","created_at":"2026-07-05T03:47:02Z"},{"alias_kind":"pith_short_12","alias_value":"ICNHV7EEOOT6","created_at":"2026-07-05T03:47:02Z"},{"alias_kind":"pith_short_16","alias_value":"ICNHV7EEOOT6ZIUC","created_at":"2026-07-05T03:47:02Z"},{"alias_kind":"pith_short_8","alias_value":"ICNHV7EE","created_at":"2026-07-05T03:47:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:ICNHV7EEOOT6ZIUCEVPVDHR7Q5","target":"record","payload":{"canonical_record":{"source":{"id":"2112.04329","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-08T15:19:24Z","cross_cats_sorted":[],"title_canon_sha256":"17d41493d4338018af50346ee49073b1a9403ef8c8383ad0b4008d269d647efc","abstract_canon_sha256":"9721ab1acee23c9daff2202cb40ebb1b23fd74eb0cf4cfc5cb7f64ba2ee7ce99"},"schema_version":"1.0"},"canonical_sha256":"409a7afc8473a7eca282255f519e3f877eba1a81d0de37860c266642a7bbc385","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:47:02.991629Z","signature_b64":"vVNJ/8v0r1IR1yXb0pmyl+GrhePrWf3iIijPn8SG6zjK95UWxqeaTp8MS8Al1ZY7F42tf1mXDytQz0RZs1kWDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"409a7afc8473a7eca282255f519e3f877eba1a81d0de37860c266642a7bbc385","last_reissued_at":"2026-07-05T03:47:02.991065Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:47:02.991065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2112.04329","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:47:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RfDWR040U/qoL5P+J6JbhhQHTzlZ05G0R0PytmXoaQNxEGPlPGq3PQ/VkINVnKHzx+q33TssQjxTzRCHGWUBAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T12:50:32.982129Z"},"content_sha256":"baf00b3065798a701450fff82ebeced52e5fee58b88de0a7f2cee65c98d2dd6f","schema_version":"1.0","event_id":"sha256:baf00b3065798a701450fff82ebeced52e5fee58b88de0a7f2cee65c98d2dd6f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:ICNHV7EEOOT6ZIUCEVPVDHR7Q5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"JABER and SABER: Junior and Senior Arabic BERt","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abbas Ghaddar, Ahmad Rashid, Baoxing Huai, Chao Xing, Duan Xinyu, Khalil Bibi, Mehdi Rezagholizadeh, Philippe Langlais, Qun Liu, Xin Jiang, Yasheng Wang, Yimeng Wu, Zhefeng Wang","submitted_at":"2021-12-08T15:19:24Z","abstract_excerpt":"Language-specific pre-trained models have proven to be more accurate than multilingual ones in a monolingual evaluation setting, Arabic is no exception. However, we found that previously released Arabic BERT models were significantly under-trained. In this technical report, we present JABER and SABER, Junior and Senior Arabic BERt respectively, our pre-trained language model prototypes dedicated for Arabic. We conduct an empirical study to systematically evaluate the performance of models across a diverse set of existing Arabic NLU tasks. Experimental results show that JABER and SABER achieve "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.04329","kind":"arxiv","version":3},"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/2112.04329/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":"2026-07-05T03:47:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"coIJD68i8iHZxVd/unfEowrt+OC4t+7BQNjmrAaWwWKjXIrLFzMmULkHRYG5LkJun9lmGt4kEFG6RGG0bwujBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T12:50:32.982516Z"},"content_sha256":"b3e18ff7a1beb56c52b38ed484ecd4cd562180d2acb5fde89f1550c83109635a","schema_version":"1.0","event_id":"sha256:b3e18ff7a1beb56c52b38ed484ecd4cd562180d2acb5fde89f1550c83109635a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ICNHV7EEOOT6ZIUCEVPVDHR7Q5/bundle.json","state_url":"https://pith.science/pith/ICNHV7EEOOT6ZIUCEVPVDHR7Q5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ICNHV7EEOOT6ZIUCEVPVDHR7Q5/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":"2026-08-20T12:50:32Z","links":{"resolver":"https://pith.science/pith/ICNHV7EEOOT6ZIUCEVPVDHR7Q5","bundle":"https://pith.science/pith/ICNHV7EEOOT6ZIUCEVPVDHR7Q5/bundle.json","state":"https://pith.science/pith/ICNHV7EEOOT6ZIUCEVPVDHR7Q5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ICNHV7EEOOT6ZIUCEVPVDHR7Q5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ICNHV7EEOOT6ZIUCEVPVDHR7Q5","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":"9721ab1acee23c9daff2202cb40ebb1b23fd74eb0cf4cfc5cb7f64ba2ee7ce99","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-08T15:19:24Z","title_canon_sha256":"17d41493d4338018af50346ee49073b1a9403ef8c8383ad0b4008d269d647efc"},"schema_version":"1.0","source":{"id":"2112.04329","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.04329","created_at":"2026-07-05T03:47:02Z"},{"alias_kind":"arxiv_version","alias_value":"2112.04329v3","created_at":"2026-07-05T03:47:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.04329","created_at":"2026-07-05T03:47:02Z"},{"alias_kind":"pith_short_12","alias_value":"ICNHV7EEOOT6","created_at":"2026-07-05T03:47:02Z"},{"alias_kind":"pith_short_16","alias_value":"ICNHV7EEOOT6ZIUC","created_at":"2026-07-05T03:47:02Z"},{"alias_kind":"pith_short_8","alias_value":"ICNHV7EE","created_at":"2026-07-05T03:47:02Z"}],"graph_snapshots":[{"event_id":"sha256:b3e18ff7a1beb56c52b38ed484ecd4cd562180d2acb5fde89f1550c83109635a","target":"graph","created_at":"2026-07-05T03:47:02Z","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/2112.04329/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language-specific pre-trained models have proven to be more accurate than multilingual ones in a monolingual evaluation setting, Arabic is no exception. However, we found that previously released Arabic BERT models were significantly under-trained. In this technical report, we present JABER and SABER, Junior and Senior Arabic BERt respectively, our pre-trained language model prototypes dedicated for Arabic. We conduct an empirical study to systematically evaluate the performance of models across a diverse set of existing Arabic NLU tasks. Experimental results show that JABER and SABER achieve ","authors_text":"Abbas Ghaddar, Ahmad Rashid, Baoxing Huai, Chao Xing, Duan Xinyu, Khalil Bibi, Mehdi Rezagholizadeh, Philippe Langlais, Qun Liu, Xin Jiang, Yasheng Wang, Yimeng Wu, Zhefeng Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-08T15:19:24Z","title":"JABER and SABER: Junior and Senior Arabic BERt"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.04329","kind":"arxiv","version":3},"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:baf00b3065798a701450fff82ebeced52e5fee58b88de0a7f2cee65c98d2dd6f","target":"record","created_at":"2026-07-05T03:47:02Z","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":"9721ab1acee23c9daff2202cb40ebb1b23fd74eb0cf4cfc5cb7f64ba2ee7ce99","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-12-08T15:19:24Z","title_canon_sha256":"17d41493d4338018af50346ee49073b1a9403ef8c8383ad0b4008d269d647efc"},"schema_version":"1.0","source":{"id":"2112.04329","kind":"arxiv","version":3}},"canonical_sha256":"409a7afc8473a7eca282255f519e3f877eba1a81d0de37860c266642a7bbc385","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"409a7afc8473a7eca282255f519e3f877eba1a81d0de37860c266642a7bbc385","first_computed_at":"2026-07-05T03:47:02.991065Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:47:02.991065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vVNJ/8v0r1IR1yXb0pmyl+GrhePrWf3iIijPn8SG6zjK95UWxqeaTp8MS8Al1ZY7F42tf1mXDytQz0RZs1kWDw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:47:02.991629Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.04329","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:baf00b3065798a701450fff82ebeced52e5fee58b88de0a7f2cee65c98d2dd6f","sha256:b3e18ff7a1beb56c52b38ed484ecd4cd562180d2acb5fde89f1550c83109635a"],"state_sha256":"b64821cb8905d0538b3be00274201690e0f758cc2736ca1b92a2cef872438004"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PSP0TL042QVeRXhn1eV7waqrhgLIO4V+FkhhwL+dFSKDMDieKuamJsKPQwMGPaIqukIQUq0h0FxC4DMsrQYTAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T12:50:32.984980Z","bundle_sha256":"026ee4f9d95f3ff1fc70b51827806e898e1755f2b96f94db363d9b5637615360"}}