{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FQQRPSVB2B343PAZXCFJJPHFAK","short_pith_number":"pith:FQQRPSVB","schema_version":"1.0","canonical_sha256":"2c2117caa1d077cdbc19b88a94bce5029c7081a69160704f2bc06003314a904f","source":{"kind":"arxiv","id":"2308.16687","version":2},"attestation_state":"computed","paper":{"title":"DictaBERT: A State-of-the-Art BERT Suite for Modern Hebrew","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Avi Shmidman, Moshe Koppel, Shaltiel Shmidman","submitted_at":"2023-08-31T12:43:18Z","abstract_excerpt":"We present DictaBERT, a new state-of-the-art pre-trained BERT model for modern Hebrew, outperforming existing models on most benchmarks. Additionally, we release three fine-tuned versions of the model, designed to perform three specific foundational tasks in the analysis of Hebrew texts: prefix segmentation, morphological tagging and question answering. These fine-tuned models allow any developer to perform prefix segmentation, morphological tagging and question answering of a Hebrew input with a single call to a HuggingFace model, without the need to integrate any additional libraries or code"},"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":"2308.16687","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-31T12:43:18Z","cross_cats_sorted":[],"title_canon_sha256":"d9285ed262bffee31f45c9973f7e35485831572b5b06ca65b37265a848695e10","abstract_canon_sha256":"317aa41e9325d87f3b30238ad427bc8a30e77a64da4d129b79c83c049c444085"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:00:27.787429Z","signature_b64":"5udX1ahnzKsSuymUz7P8FrFXeW+wSsnwALtkkNoxWWkYt9WwlHbVEa9HAGzV0FHT6BxldQr6JO+cV8jOSJ4tBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c2117caa1d077cdbc19b88a94bce5029c7081a69160704f2bc06003314a904f","last_reissued_at":"2026-07-05T07:00:27.786966Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:00:27.786966Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DictaBERT: A State-of-the-Art BERT Suite for Modern Hebrew","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Avi Shmidman, Moshe Koppel, Shaltiel Shmidman","submitted_at":"2023-08-31T12:43:18Z","abstract_excerpt":"We present DictaBERT, a new state-of-the-art pre-trained BERT model for modern Hebrew, outperforming existing models on most benchmarks. Additionally, we release three fine-tuned versions of the model, designed to perform three specific foundational tasks in the analysis of Hebrew texts: prefix segmentation, morphological tagging and question answering. These fine-tuned models allow any developer to perform prefix segmentation, morphological tagging and question answering of a Hebrew input with a single call to a HuggingFace model, without the need to integrate any additional libraries or code"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.16687","kind":"arxiv","version":2},"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/2308.16687/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":"2308.16687","created_at":"2026-07-05T07:00:27.787023+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.16687v2","created_at":"2026-07-05T07:00:27.787023+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.16687","created_at":"2026-07-05T07:00:27.787023+00:00"},{"alias_kind":"pith_short_12","alias_value":"FQQRPSVB2B34","created_at":"2026-07-05T07:00:27.787023+00:00"},{"alias_kind":"pith_short_16","alias_value":"FQQRPSVB2B343PAZ","created_at":"2026-07-05T07:00:27.787023+00:00"},{"alias_kind":"pith_short_8","alias_value":"FQQRPSVB","created_at":"2026-07-05T07:00:27.787023+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19638","citing_title":"MiqraBERT: Regression-Based Sentence-BERT Finetuning for Biblical Hebrew Parallel Detection","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07647","citing_title":"Quality-Conditioned Agreement in Automated Short Answer Scoring: Mid-Range Degradation and the Impact of Task-Specific Adaptation","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07647","citing_title":"Quality-Conditioned Agreement in Automated Short Answer Scoring: Mid-Range Degradation and the Impact of Task-Specific Adaptation","ref_index":55,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FQQRPSVB2B343PAZXCFJJPHFAK","json":"https://pith.science/pith/FQQRPSVB2B343PAZXCFJJPHFAK.json","graph_json":"https://pith.science/api/pith-number/FQQRPSVB2B343PAZXCFJJPHFAK/graph.json","events_json":"https://pith.science/api/pith-number/FQQRPSVB2B343PAZXCFJJPHFAK/events.json","paper":"https://pith.science/paper/FQQRPSVB"},"agent_actions":{"view_html":"https://pith.science/pith/FQQRPSVB2B343PAZXCFJJPHFAK","download_json":"https://pith.science/pith/FQQRPSVB2B343PAZXCFJJPHFAK.json","view_paper":"https://pith.science/paper/FQQRPSVB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.16687&json=true","fetch_graph":"https://pith.science/api/pith-number/FQQRPSVB2B343PAZXCFJJPHFAK/graph.json","fetch_events":"https://pith.science/api/pith-number/FQQRPSVB2B343PAZXCFJJPHFAK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FQQRPSVB2B343PAZXCFJJPHFAK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FQQRPSVB2B343PAZXCFJJPHFAK/action/storage_attestation","attest_author":"https://pith.science/pith/FQQRPSVB2B343PAZXCFJJPHFAK/action/author_attestation","sign_citation":"https://pith.science/pith/FQQRPSVB2B343PAZXCFJJPHFAK/action/citation_signature","submit_replication":"https://pith.science/pith/FQQRPSVB2B343PAZXCFJJPHFAK/action/replication_record"}},"created_at":"2026-07-05T07:00:27.787023+00:00","updated_at":"2026-07-05T07:00:27.787023+00:00"}