{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:6IUQJHPLRJF75ULAGVQV47QYCD","short_pith_number":"pith:6IUQJHPL","schema_version":"1.0","canonical_sha256":"f229049deb8a4bfed16035615e7e1810d7b00649abcce8e107eefebef585c0f0","source":{"kind":"arxiv","id":"1908.05453","version":1},"attestation_state":"computed","paper":{"title":"What's Wrong with Hebrew NLP? And How to Make it Right","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amit Seker, Reut Tsarfaty, Shoval Sadde, Stav Klein","submitted_at":"2019-08-15T08:09:52Z","abstract_excerpt":"For languages with simple morphology, such as English, automatic annotation pipelines such as spaCy or Stanford's CoreNLP successfully serve projects in academia and the industry. For many morphologically-rich languages (MRLs), similar pipelines show sub-optimal performance that limits their applicability for text analysis in research and the industry.The sub-optimal performance is mainly due to errors in early morphological disambiguation decisions, which cannot be recovered later in the pipeline, yielding incoherent annotations on the whole. In this paper we describe the design and use of th"},"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":"1908.05453","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-08-15T08:09:52Z","cross_cats_sorted":[],"title_canon_sha256":"10ae222195efbd14875f3dc2d2caea8d77d953c7165e8dc6be726aade98bb124","abstract_canon_sha256":"f29746e0fecd7cd2cbfae7404672021f312118486535c4dac812fa83d8cb2cbf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:56:52.272546Z","signature_b64":"/CeVAhOUDsnmN35c2JU50PDqIYZk5T+GUcpdSNsxxaibE7GCFTT5Gnl80TTHyTAN9UyDzE4xqQbeX/HcibgfBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f229049deb8a4bfed16035615e7e1810d7b00649abcce8e107eefebef585c0f0","last_reissued_at":"2026-07-04T23:56:52.272065Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:56:52.272065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"What's Wrong with Hebrew NLP? And How to Make it Right","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amit Seker, Reut Tsarfaty, Shoval Sadde, Stav Klein","submitted_at":"2019-08-15T08:09:52Z","abstract_excerpt":"For languages with simple morphology, such as English, automatic annotation pipelines such as spaCy or Stanford's CoreNLP successfully serve projects in academia and the industry. For many morphologically-rich languages (MRLs), similar pipelines show sub-optimal performance that limits their applicability for text analysis in research and the industry.The sub-optimal performance is mainly due to errors in early morphological disambiguation decisions, which cannot be recovered later in the pipeline, yielding incoherent annotations on the whole. In this paper we describe the design and use of th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.05453","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/1908.05453/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":"1908.05453","created_at":"2026-07-04T23:56:52.272124+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.05453v1","created_at":"2026-07-04T23:56:52.272124+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.05453","created_at":"2026-07-04T23:56:52.272124+00:00"},{"alias_kind":"pith_short_12","alias_value":"6IUQJHPLRJF7","created_at":"2026-07-04T23:56:52.272124+00:00"},{"alias_kind":"pith_short_16","alias_value":"6IUQJHPLRJF75ULA","created_at":"2026-07-04T23:56:52.272124+00:00"},{"alias_kind":"pith_short_8","alias_value":"6IUQJHPL","created_at":"2026-07-04T23:56:52.272124+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.08342","citing_title":"Beyond N-Grams: Rethinking Evaluation Metrics and Strategies for Multilingual Abstractive Summarization","ref_index":52,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6IUQJHPLRJF75ULAGVQV47QYCD","json":"https://pith.science/pith/6IUQJHPLRJF75ULAGVQV47QYCD.json","graph_json":"https://pith.science/api/pith-number/6IUQJHPLRJF75ULAGVQV47QYCD/graph.json","events_json":"https://pith.science/api/pith-number/6IUQJHPLRJF75ULAGVQV47QYCD/events.json","paper":"https://pith.science/paper/6IUQJHPL"},"agent_actions":{"view_html":"https://pith.science/pith/6IUQJHPLRJF75ULAGVQV47QYCD","download_json":"https://pith.science/pith/6IUQJHPLRJF75ULAGVQV47QYCD.json","view_paper":"https://pith.science/paper/6IUQJHPL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.05453&json=true","fetch_graph":"https://pith.science/api/pith-number/6IUQJHPLRJF75ULAGVQV47QYCD/graph.json","fetch_events":"https://pith.science/api/pith-number/6IUQJHPLRJF75ULAGVQV47QYCD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6IUQJHPLRJF75ULAGVQV47QYCD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6IUQJHPLRJF75ULAGVQV47QYCD/action/storage_attestation","attest_author":"https://pith.science/pith/6IUQJHPLRJF75ULAGVQV47QYCD/action/author_attestation","sign_citation":"https://pith.science/pith/6IUQJHPLRJF75ULAGVQV47QYCD/action/citation_signature","submit_replication":"https://pith.science/pith/6IUQJHPLRJF75ULAGVQV47QYCD/action/replication_record"}},"created_at":"2026-07-04T23:56:52.272124+00:00","updated_at":"2026-07-04T23:56:52.272124+00:00"}