{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:DPDGTXDUUEHMBMYNFMVB56GBVH","short_pith_number":"pith:DPDGTXDU","canonical_record":{"source":{"id":"2201.09227","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-01-23T11:17:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f2931e8c0b2c3544760f895843fc3c9256c3f642fdeb1866a51a9015b4ac8ff9","abstract_canon_sha256":"6858448c8d1a999830e00dd94dc8a842904d1950db6d3fdf51273cc3a26fd4fc"},"schema_version":"1.0"},"canonical_sha256":"1bc669dc74a10ec0b30d2b2a1ef8c1a9e89999339adb0aa75b60d96275166973","source":{"kind":"arxiv","id":"2201.09227","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.09227","created_at":"2026-07-05T06:07:58Z"},{"alias_kind":"arxiv_version","alias_value":"2201.09227v3","created_at":"2026-07-05T06:07:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.09227","created_at":"2026-07-05T06:07:58Z"},{"alias_kind":"pith_short_12","alias_value":"DPDGTXDUUEHM","created_at":"2026-07-05T06:07:58Z"},{"alias_kind":"pith_short_16","alias_value":"DPDGTXDUUEHMBMYN","created_at":"2026-07-05T06:07:58Z"},{"alias_kind":"pith_short_8","alias_value":"DPDGTXDU","created_at":"2026-07-05T06:07:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:DPDGTXDUUEHMBMYNFMVB56GBVH","target":"record","payload":{"canonical_record":{"source":{"id":"2201.09227","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-01-23T11:17:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f2931e8c0b2c3544760f895843fc3c9256c3f642fdeb1866a51a9015b4ac8ff9","abstract_canon_sha256":"6858448c8d1a999830e00dd94dc8a842904d1950db6d3fdf51273cc3a26fd4fc"},"schema_version":"1.0"},"canonical_sha256":"1bc669dc74a10ec0b30d2b2a1ef8c1a9e89999339adb0aa75b60d96275166973","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:07:58.946096Z","signature_b64":"OU99L8INDfiyhjU9w1exQgEbldJaA8HBcMQU8/TRoxjhBhfHMO4iQHISkpAxGEJVi77jlwPkAyybWwxOMM3OBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1bc669dc74a10ec0b30d2b2a1ef8c1a9e89999339adb0aa75b60d96275166973","last_reissued_at":"2026-07-05T06:07:58.945676Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:07:58.945676Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2201.09227","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":"2026-07-05T06:07:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IhdQqBYrZGaF2yx6SGnim0ha7YCSPEP//KJN1m4+ibfPwtXExyfriy17P2oJBqmcNNDNPCldR5shw6S6Zt1ZBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T13:26:25.835953Z"},"content_sha256":"349c325063246052b35a4a55c45a353510658995e53ed3dc3018cc2339062a09","schema_version":"1.0","event_id":"sha256:349c325063246052b35a4a55c45a353510658995e53ed3dc3018cc2339062a09"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:DPDGTXDUUEHMBMYNFMVB56GBVH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Large and Diverse Arabic Corpus for Language Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Abbas Raza Ali, Hasan Raza Ali, Muhammad Ajmal Siddiqui, Rema Algunaibet","submitted_at":"2022-01-23T11:17:53Z","abstract_excerpt":"Language models (LMs) have introduced a major paradigm shift in Natural Language Processing (NLP) modeling where large pre-trained LMs became integral to most of the NLP tasks. The LMs are intelligent enough to find useful and relevant representations of the language without any supervision. Perhaps, these models are used to fine-tune typical NLP tasks with significantly high accuracy as compared to the traditional approaches. Conversely, the training of these models requires a massively large corpus that is a good representation of the language. English LMs generally perform better than their"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.09227","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/2201.09227/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":"2026-07-05T06:07:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VnffhQ5CviAEypCVas/InRuumD/PNAwxubrssrPRaZjl8LAy6JUcmBQpT5VyeYPmXEsRtkuEYpd3AcI57iqjAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T13:26:25.836334Z"},"content_sha256":"99da4733f1de2e12a8e9772b81a1a6c0d9f96eadc0e8998ac8fe6820710fbd74","schema_version":"1.0","event_id":"sha256:99da4733f1de2e12a8e9772b81a1a6c0d9f96eadc0e8998ac8fe6820710fbd74"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DPDGTXDUUEHMBMYNFMVB56GBVH/bundle.json","state_url":"https://pith.science/pith/DPDGTXDUUEHMBMYNFMVB56GBVH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DPDGTXDUUEHMBMYNFMVB56GBVH/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":"2026-08-23T13:26:25Z","links":{"resolver":"https://pith.science/pith/DPDGTXDUUEHMBMYNFMVB56GBVH","bundle":"https://pith.science/pith/DPDGTXDUUEHMBMYNFMVB56GBVH/bundle.json","state":"https://pith.science/pith/DPDGTXDUUEHMBMYNFMVB56GBVH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DPDGTXDUUEHMBMYNFMVB56GBVH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:DPDGTXDUUEHMBMYNFMVB56GBVH","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":"6858448c8d1a999830e00dd94dc8a842904d1950db6d3fdf51273cc3a26fd4fc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-01-23T11:17:53Z","title_canon_sha256":"f2931e8c0b2c3544760f895843fc3c9256c3f642fdeb1866a51a9015b4ac8ff9"},"schema_version":"1.0","source":{"id":"2201.09227","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.09227","created_at":"2026-07-05T06:07:58Z"},{"alias_kind":"arxiv_version","alias_value":"2201.09227v3","created_at":"2026-07-05T06:07:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.09227","created_at":"2026-07-05T06:07:58Z"},{"alias_kind":"pith_short_12","alias_value":"DPDGTXDUUEHM","created_at":"2026-07-05T06:07:58Z"},{"alias_kind":"pith_short_16","alias_value":"DPDGTXDUUEHMBMYN","created_at":"2026-07-05T06:07:58Z"},{"alias_kind":"pith_short_8","alias_value":"DPDGTXDU","created_at":"2026-07-05T06:07:58Z"}],"graph_snapshots":[{"event_id":"sha256:99da4733f1de2e12a8e9772b81a1a6c0d9f96eadc0e8998ac8fe6820710fbd74","target":"graph","created_at":"2026-07-05T06:07:58Z","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/2201.09227/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language models (LMs) have introduced a major paradigm shift in Natural Language Processing (NLP) modeling where large pre-trained LMs became integral to most of the NLP tasks. The LMs are intelligent enough to find useful and relevant representations of the language without any supervision. Perhaps, these models are used to fine-tune typical NLP tasks with significantly high accuracy as compared to the traditional approaches. Conversely, the training of these models requires a massively large corpus that is a good representation of the language. English LMs generally perform better than their","authors_text":"Abbas Raza Ali, Hasan Raza Ali, Muhammad Ajmal Siddiqui, Rema Algunaibet","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-01-23T11:17:53Z","title":"A Large and Diverse Arabic Corpus for Language Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.09227","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":"sha256:349c325063246052b35a4a55c45a353510658995e53ed3dc3018cc2339062a09","target":"record","created_at":"2026-07-05T06:07:58Z","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":"6858448c8d1a999830e00dd94dc8a842904d1950db6d3fdf51273cc3a26fd4fc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-01-23T11:17:53Z","title_canon_sha256":"f2931e8c0b2c3544760f895843fc3c9256c3f642fdeb1866a51a9015b4ac8ff9"},"schema_version":"1.0","source":{"id":"2201.09227","kind":"arxiv","version":3}},"canonical_sha256":"1bc669dc74a10ec0b30d2b2a1ef8c1a9e89999339adb0aa75b60d96275166973","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1bc669dc74a10ec0b30d2b2a1ef8c1a9e89999339adb0aa75b60d96275166973","first_computed_at":"2026-07-05T06:07:58.945676Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:07:58.945676Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OU99L8INDfiyhjU9w1exQgEbldJaA8HBcMQU8/TRoxjhBhfHMO4iQHISkpAxGEJVi77jlwPkAyybWwxOMM3OBw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:07:58.946096Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.09227","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:349c325063246052b35a4a55c45a353510658995e53ed3dc3018cc2339062a09","sha256:99da4733f1de2e12a8e9772b81a1a6c0d9f96eadc0e8998ac8fe6820710fbd74"],"state_sha256":"9b47c4aee91e3f19551055af972520482b3274929a12b14bec50db76cc801b79"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O7CwY5JW39qQJ4+51fRyjhCp+8DgzxdwZjdTvGQAJu/v0FjSX9GoNR7oKEbB1ecYbdnLdcmFz3XPgSKjPx92Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T13:26:25.839355Z","bundle_sha256":"926d954b7a0b4c4529a0bf90ef6b9f8b8e1b9ce87814ad0af34a51640b5613fa"}}