{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:LTPHCYAO5P2CAD4VGTMAR3QDZY","short_pith_number":"pith:LTPHCYAO","schema_version":"1.0","canonical_sha256":"5cde71600eebf4200f9534d808ee03ce29be45b82e562c95f9d1eb388f10a68d","source":{"kind":"arxiv","id":"2111.13138","version":1},"attestation_state":"computed","paper":{"title":"TunBERT: Pretrained Contextualized Text Representation for Tunisian Dialect","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Abir Korched, Abir Messaoudi, Ahmed Cheikhrouhou, Amine Kerkeni, Faten Ghriss, Hatem Haddad, Malek Naski, Moez BenHajhmida, Nourchene Ferchichi","submitted_at":"2021-11-25T15:49:50Z","abstract_excerpt":"Pretrained contextualized text representation models learn an effective representation of a natural language to make it machine understandable. After the breakthrough of the attention mechanism, a new generation of pretrained models have been proposed achieving good performances since the introduction of the Transformer. Bidirectional Encoder Representations from Transformers (BERT) has become the state-of-the-art model for language understanding. Despite their success, most of the available models have been trained on Indo-European languages however similar research for under-represented lang"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2111.13138","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2021-11-25T15:49:50Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"911a37ecafeef43fc03704cf9b6fbddd2903e79f1b0530235df688b29a16290f","abstract_canon_sha256":"3d5a80a2b1bfc8fb879f05fee0827f003a26b50a6ec86b198a6af2b704784808"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:35:17.831548Z","signature_b64":"FRJuQ16vnP5DVIARdpL6MwJb8B+XriLginiZ0KKJT2v9pUI6VME3gHbDKO3d4rokSStrVJkHXhZPW4aJf1NsBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5cde71600eebf4200f9534d808ee03ce29be45b82e562c95f9d1eb388f10a68d","last_reissued_at":"2026-07-05T03:35:17.831052Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:35:17.831052Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TunBERT: Pretrained Contextualized Text Representation for Tunisian Dialect","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Abir Korched, Abir Messaoudi, Ahmed Cheikhrouhou, Amine Kerkeni, Faten Ghriss, Hatem Haddad, Malek Naski, Moez BenHajhmida, Nourchene Ferchichi","submitted_at":"2021-11-25T15:49:50Z","abstract_excerpt":"Pretrained contextualized text representation models learn an effective representation of a natural language to make it machine understandable. After the breakthrough of the attention mechanism, a new generation of pretrained models have been proposed achieving good performances since the introduction of the Transformer. Bidirectional Encoder Representations from Transformers (BERT) has become the state-of-the-art model for language understanding. Despite their success, most of the available models have been trained on Indo-European languages however similar research for under-represented lang"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.13138","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/2111.13138/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2111.13138","created_at":"2026-07-05T03:35:17.831111+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.13138v1","created_at":"2026-07-05T03:35:17.831111+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.13138","created_at":"2026-07-05T03:35:17.831111+00:00"},{"alias_kind":"pith_short_12","alias_value":"LTPHCYAO5P2C","created_at":"2026-07-05T03:35:17.831111+00:00"},{"alias_kind":"pith_short_16","alias_value":"LTPHCYAO5P2CAD4V","created_at":"2026-07-05T03:35:17.831111+00:00"},{"alias_kind":"pith_short_8","alias_value":"LTPHCYAO","created_at":"2026-07-05T03:35:17.831111+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LTPHCYAO5P2CAD4VGTMAR3QDZY","json":"https://pith.science/pith/LTPHCYAO5P2CAD4VGTMAR3QDZY.json","graph_json":"https://pith.science/api/pith-number/LTPHCYAO5P2CAD4VGTMAR3QDZY/graph.json","events_json":"https://pith.science/api/pith-number/LTPHCYAO5P2CAD4VGTMAR3QDZY/events.json","paper":"https://pith.science/paper/LTPHCYAO"},"agent_actions":{"view_html":"https://pith.science/pith/LTPHCYAO5P2CAD4VGTMAR3QDZY","download_json":"https://pith.science/pith/LTPHCYAO5P2CAD4VGTMAR3QDZY.json","view_paper":"https://pith.science/paper/LTPHCYAO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.13138&json=true","fetch_graph":"https://pith.science/api/pith-number/LTPHCYAO5P2CAD4VGTMAR3QDZY/graph.json","fetch_events":"https://pith.science/api/pith-number/LTPHCYAO5P2CAD4VGTMAR3QDZY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LTPHCYAO5P2CAD4VGTMAR3QDZY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LTPHCYAO5P2CAD4VGTMAR3QDZY/action/storage_attestation","attest_author":"https://pith.science/pith/LTPHCYAO5P2CAD4VGTMAR3QDZY/action/author_attestation","sign_citation":"https://pith.science/pith/LTPHCYAO5P2CAD4VGTMAR3QDZY/action/citation_signature","submit_replication":"https://pith.science/pith/LTPHCYAO5P2CAD4VGTMAR3QDZY/action/replication_record"}},"created_at":"2026-07-05T03:35:17.831111+00:00","updated_at":"2026-07-05T03:35:17.831111+00:00"}