{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:UVBHJJSKGEAX4SG3X4DJFNI2ES","short_pith_number":"pith:UVBHJJSK","canonical_record":{"source":{"id":"2003.00104","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-02-28T22:59:24Z","cross_cats_sorted":[],"title_canon_sha256":"3a85558e31d53ab310f9fce911d7e5ad3ea43da08541c7f3e4b516ae907bdb01","abstract_canon_sha256":"63b180b11c99c9631cd98cfef3348cf2beb713662aff0bf752f1a531a1fc6b33"},"schema_version":"1.0"},"canonical_sha256":"a54274a64a31017e48dbbf0692b51a249e4fd74f97dcafb0e05bd46f83db0ae0","source":{"kind":"arxiv","id":"2003.00104","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.00104","created_at":"2026-07-05T02:20:53Z"},{"alias_kind":"arxiv_version","alias_value":"2003.00104v4","created_at":"2026-07-05T02:20:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.00104","created_at":"2026-07-05T02:20:53Z"},{"alias_kind":"pith_short_12","alias_value":"UVBHJJSKGEAX","created_at":"2026-07-05T02:20:53Z"},{"alias_kind":"pith_short_16","alias_value":"UVBHJJSKGEAX4SG3","created_at":"2026-07-05T02:20:53Z"},{"alias_kind":"pith_short_8","alias_value":"UVBHJJSK","created_at":"2026-07-05T02:20:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:UVBHJJSKGEAX4SG3X4DJFNI2ES","target":"record","payload":{"canonical_record":{"source":{"id":"2003.00104","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-02-28T22:59:24Z","cross_cats_sorted":[],"title_canon_sha256":"3a85558e31d53ab310f9fce911d7e5ad3ea43da08541c7f3e4b516ae907bdb01","abstract_canon_sha256":"63b180b11c99c9631cd98cfef3348cf2beb713662aff0bf752f1a531a1fc6b33"},"schema_version":"1.0"},"canonical_sha256":"a54274a64a31017e48dbbf0692b51a249e4fd74f97dcafb0e05bd46f83db0ae0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:20:53.903591Z","signature_b64":"fZmuSGWNGLmh/LigHveUx9xLE436ONGNk0AnzFvCqOBNN7WtgVed8N9Nt3bdZ9qDna0G8tb7y8e1cfS3c2f1CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a54274a64a31017e48dbbf0692b51a249e4fd74f97dcafb0e05bd46f83db0ae0","last_reissued_at":"2026-07-05T02:20:53.903167Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:20:53.903167Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2003.00104","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":"2026-07-05T02:20:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ks3/2vtuyHWYRmvEXi8zELkFBZD+V8SjVTuFsDYbDCW6L/w7+65kHE5e6pWO/e0wskqAJ4sOkykqayGQDZ/ODA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T21:01:44.045761Z"},"content_sha256":"d6a2e27ed4b25d8ca1b57c10f47136526be40199be206f0e28b4f4442032a7d0","schema_version":"1.0","event_id":"sha256:d6a2e27ed4b25d8ca1b57c10f47136526be40199be206f0e28b4f4442032a7d0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:UVBHJJSKGEAX4SG3X4DJFNI2ES","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AraBERT: Transformer-based Model for Arabic Language Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fady Baly, Hazem Hajj, Wissam Antoun","submitted_at":"2020-02-28T22:59:24Z","abstract_excerpt":"The Arabic language is a morphologically rich language with relatively few resources and a less explored syntax compared to English. Given these limitations, Arabic Natural Language Processing (NLP) tasks like Sentiment Analysis (SA), Named Entity Recognition (NER), and Question Answering (QA), have proven to be very challenging to tackle. Recently, with the surge of transformers based models, language-specific BERT based models have proven to be very efficient at language understanding, provided they are pre-trained on a very large corpus. Such models were able to set new standards and achiev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.00104","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/2003.00104/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":"2026-07-05T02:20:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wS2OR6dKBF8KTB8czDCH2q7hr1IagcgkfVQIiZxDAfd3pG0TX7sx1KIKubKE1uZOaa6Qo4AgmID8OTP3k+dcCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T21:01:44.046256Z"},"content_sha256":"0078d2f8fb40379cfea2339aa9de93ef370bb9038e60786ff84978c227f3858e","schema_version":"1.0","event_id":"sha256:0078d2f8fb40379cfea2339aa9de93ef370bb9038e60786ff84978c227f3858e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UVBHJJSKGEAX4SG3X4DJFNI2ES/bundle.json","state_url":"https://pith.science/pith/UVBHJJSKGEAX4SG3X4DJFNI2ES/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UVBHJJSKGEAX4SG3X4DJFNI2ES/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":"2026-08-09T21:01:44Z","links":{"resolver":"https://pith.science/pith/UVBHJJSKGEAX4SG3X4DJFNI2ES","bundle":"https://pith.science/pith/UVBHJJSKGEAX4SG3X4DJFNI2ES/bundle.json","state":"https://pith.science/pith/UVBHJJSKGEAX4SG3X4DJFNI2ES/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UVBHJJSKGEAX4SG3X4DJFNI2ES/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:UVBHJJSKGEAX4SG3X4DJFNI2ES","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":"63b180b11c99c9631cd98cfef3348cf2beb713662aff0bf752f1a531a1fc6b33","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-02-28T22:59:24Z","title_canon_sha256":"3a85558e31d53ab310f9fce911d7e5ad3ea43da08541c7f3e4b516ae907bdb01"},"schema_version":"1.0","source":{"id":"2003.00104","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.00104","created_at":"2026-07-05T02:20:53Z"},{"alias_kind":"arxiv_version","alias_value":"2003.00104v4","created_at":"2026-07-05T02:20:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.00104","created_at":"2026-07-05T02:20:53Z"},{"alias_kind":"pith_short_12","alias_value":"UVBHJJSKGEAX","created_at":"2026-07-05T02:20:53Z"},{"alias_kind":"pith_short_16","alias_value":"UVBHJJSKGEAX4SG3","created_at":"2026-07-05T02:20:53Z"},{"alias_kind":"pith_short_8","alias_value":"UVBHJJSK","created_at":"2026-07-05T02:20:53Z"}],"graph_snapshots":[{"event_id":"sha256:0078d2f8fb40379cfea2339aa9de93ef370bb9038e60786ff84978c227f3858e","target":"graph","created_at":"2026-07-05T02:20:53Z","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/2003.00104/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The Arabic language is a morphologically rich language with relatively few resources and a less explored syntax compared to English. Given these limitations, Arabic Natural Language Processing (NLP) tasks like Sentiment Analysis (SA), Named Entity Recognition (NER), and Question Answering (QA), have proven to be very challenging to tackle. Recently, with the surge of transformers based models, language-specific BERT based models have proven to be very efficient at language understanding, provided they are pre-trained on a very large corpus. Such models were able to set new standards and achiev","authors_text":"Fady Baly, Hazem Hajj, Wissam Antoun","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-02-28T22:59:24Z","title":"AraBERT: Transformer-based Model for Arabic Language Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.00104","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:d6a2e27ed4b25d8ca1b57c10f47136526be40199be206f0e28b4f4442032a7d0","target":"record","created_at":"2026-07-05T02:20:53Z","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":"63b180b11c99c9631cd98cfef3348cf2beb713662aff0bf752f1a531a1fc6b33","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-02-28T22:59:24Z","title_canon_sha256":"3a85558e31d53ab310f9fce911d7e5ad3ea43da08541c7f3e4b516ae907bdb01"},"schema_version":"1.0","source":{"id":"2003.00104","kind":"arxiv","version":4}},"canonical_sha256":"a54274a64a31017e48dbbf0692b51a249e4fd74f97dcafb0e05bd46f83db0ae0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a54274a64a31017e48dbbf0692b51a249e4fd74f97dcafb0e05bd46f83db0ae0","first_computed_at":"2026-07-05T02:20:53.903167Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:20:53.903167Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fZmuSGWNGLmh/LigHveUx9xLE436ONGNk0AnzFvCqOBNN7WtgVed8N9Nt3bdZ9qDna0G8tb7y8e1cfS3c2f1CA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:20:53.903591Z","signed_message":"canonical_sha256_bytes"},"source_id":"2003.00104","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d6a2e27ed4b25d8ca1b57c10f47136526be40199be206f0e28b4f4442032a7d0","sha256:0078d2f8fb40379cfea2339aa9de93ef370bb9038e60786ff84978c227f3858e"],"state_sha256":"bed5cfcd5ca89de9c362f33c7f7f3a8bdb04df92d2f7c6ad5e544e5b5c3ac8c4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"64lQemtqIkGC+RmCsM87rOF8PI9DJLXtOeGs8ld/emuS2qEOVbgwnX2/PfKyg7rC2rC7iOeeoy1NJbgjH+kmBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T21:01:44.050871Z","bundle_sha256":"ba64e993454f72661face1e8c55ddc56b2dc482720d9845208a845c5b71a221f"}}