{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2003:2XXZPWLXYA6ADJH5GWPTAMWWED","short_pith_number":"pith:2XXZPWLX","schema_version":"1.0","canonical_sha256":"d5ef97d977c03c01a4fd359f3032d620cf35e5ac1f4720dd685e7548c36ecc62","source":{"kind":"arxiv","id":"cs/0302032","version":1},"attestation_state":"computed","paper":{"title":"Empirical Methods for Compound Splitting","license":"","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kevin Knight, Philipp Koehn","submitted_at":"2003-02-22T23:37:26Z","abstract_excerpt":"Compounded words are a challenge for NLP applications such as machine translation (MT). We introduce methods to learn splitting rules from monolingual and parallel corpora. We evaluate them against a gold standard and measure their impact on performance of statistical MT systems. Results show accuracy of 99.1% and performance gains for MT of 0.039 BLEU on a German-English noun phrase translation task."},"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":"cs/0302032","kind":"arxiv","version":1},"metadata":{"license":"","primary_cat":"cs.CL","submitted_at":"2003-02-22T23:37:26Z","cross_cats_sorted":[],"title_canon_sha256":"22184bda45a46a113decc8894e4e2ee2c8b3633531102c868edf2cf3e89582f0","abstract_canon_sha256":"d740cb552a5b20a9b7bbc56232d8b759678839d3b6012bcc0585f42a3dd53acc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T14:24:30.696497Z","signature_b64":"whZs/YBi/LibtbwwFglD9YQ0RxgpJ/wqe4C8v9rmiSZloURnnuit5tnUNmUwksjkq35IYrXgU3w4no0DfJZtAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d5ef97d977c03c01a4fd359f3032d620cf35e5ac1f4720dd685e7548c36ecc62","last_reissued_at":"2026-07-04T14:24:30.696098Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T14:24:30.696098Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Empirical Methods for Compound Splitting","license":"","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kevin Knight, Philipp Koehn","submitted_at":"2003-02-22T23:37:26Z","abstract_excerpt":"Compounded words are a challenge for NLP applications such as machine translation (MT). We introduce methods to learn splitting rules from monolingual and parallel corpora. We evaluate them against a gold standard and measure their impact on performance of statistical MT systems. Results show accuracy of 99.1% and performance gains for MT of 0.039 BLEU on a German-English noun phrase translation task."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"cs/0302032","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/cs/0302032/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":"cs/0302032","created_at":"2026-07-04T14:24:30.696156+00:00"},{"alias_kind":"arxiv_version","alias_value":"cs/0302032v1","created_at":"2026-07-04T14:24:30.696156+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.cs/0302032","created_at":"2026-07-04T14:24:30.696156+00:00"},{"alias_kind":"pith_short_12","alias_value":"2XXZPWLXYA6A","created_at":"2026-07-04T14:24:30.696156+00:00"},{"alias_kind":"pith_short_16","alias_value":"2XXZPWLXYA6ADJH5","created_at":"2026-07-04T14:24:30.696156+00:00"},{"alias_kind":"pith_short_8","alias_value":"2XXZPWLX","created_at":"2026-07-04T14:24:30.696156+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/2XXZPWLXYA6ADJH5GWPTAMWWED","json":"https://pith.science/pith/2XXZPWLXYA6ADJH5GWPTAMWWED.json","graph_json":"https://pith.science/api/pith-number/2XXZPWLXYA6ADJH5GWPTAMWWED/graph.json","events_json":"https://pith.science/api/pith-number/2XXZPWLXYA6ADJH5GWPTAMWWED/events.json","paper":"https://pith.science/paper/2XXZPWLX"},"agent_actions":{"view_html":"https://pith.science/pith/2XXZPWLXYA6ADJH5GWPTAMWWED","download_json":"https://pith.science/pith/2XXZPWLXYA6ADJH5GWPTAMWWED.json","view_paper":"https://pith.science/paper/2XXZPWLX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=cs/0302032&json=true","fetch_graph":"https://pith.science/api/pith-number/2XXZPWLXYA6ADJH5GWPTAMWWED/graph.json","fetch_events":"https://pith.science/api/pith-number/2XXZPWLXYA6ADJH5GWPTAMWWED/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2XXZPWLXYA6ADJH5GWPTAMWWED/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2XXZPWLXYA6ADJH5GWPTAMWWED/action/storage_attestation","attest_author":"https://pith.science/pith/2XXZPWLXYA6ADJH5GWPTAMWWED/action/author_attestation","sign_citation":"https://pith.science/pith/2XXZPWLXYA6ADJH5GWPTAMWWED/action/citation_signature","submit_replication":"https://pith.science/pith/2XXZPWLXYA6ADJH5GWPTAMWWED/action/replication_record"}},"created_at":"2026-07-04T14:24:30.696156+00:00","updated_at":"2026-07-04T14:24:30.696156+00:00"}