{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QQSEEI6VBCBNN6LU37VH4ROSOY","short_pith_number":"pith:QQSEEI6V","schema_version":"1.0","canonical_sha256":"84244223d50882d6f974dfea7e45d276012ccff22cb413a5aaa0199c88b11af5","source":{"kind":"arxiv","id":"2305.14214","version":2},"attestation_state":"computed","paper":{"title":"CompoundPiece: Evaluating and Improving Decompounding Performance of Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Benjamin Minixhofer, Ivan Vuli\\'c, Jonas Pfeiffer","submitted_at":"2023-05-23T16:32:27Z","abstract_excerpt":"While many languages possess processes of joining two or more words to create compound words, previous studies have been typically limited only to languages with excessively productive compound formation (e.g., German, Dutch) and there is no public dataset containing compound and non-compound words across a large number of languages. In this work, we systematically study decompounding, the task of splitting compound words into their constituents, at a wide scale. We first address the data gap by introducing a dataset of 255k compound and non-compound words across 56 diverse languages obtained "},"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":"2305.14214","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T16:32:27Z","cross_cats_sorted":[],"title_canon_sha256":"b5de599ad856e6c3bb67590ff34bf730ce9f5921686ab1bd559d630327d1fc00","abstract_canon_sha256":"0bc5dafe87bf01e56cb6214d3d0e13ca166d30f026b8240977237cf542dee916"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:03:58.983427Z","signature_b64":"hmlcL9rFDhukbkeneTU0DcYhn2tarQ1jPI6gTNHrQ0LR0Idpk1pTBAcqrZk5+dLVrUcIhJLioZO/y7q8l0boBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"84244223d50882d6f974dfea7e45d276012ccff22cb413a5aaa0199c88b11af5","last_reissued_at":"2026-07-05T07:03:58.982913Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:03:58.982913Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CompoundPiece: Evaluating and Improving Decompounding Performance of Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Benjamin Minixhofer, Ivan Vuli\\'c, Jonas Pfeiffer","submitted_at":"2023-05-23T16:32:27Z","abstract_excerpt":"While many languages possess processes of joining two or more words to create compound words, previous studies have been typically limited only to languages with excessively productive compound formation (e.g., German, Dutch) and there is no public dataset containing compound and non-compound words across a large number of languages. In this work, we systematically study decompounding, the task of splitting compound words into their constituents, at a wide scale. We first address the data gap by introducing a dataset of 255k compound and non-compound words across 56 diverse languages obtained "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14214","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/2305.14214/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":"2305.14214","created_at":"2026-07-05T07:03:58.982977+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.14214v2","created_at":"2026-07-05T07:03:58.982977+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14214","created_at":"2026-07-05T07:03:58.982977+00:00"},{"alias_kind":"pith_short_12","alias_value":"QQSEEI6VBCBN","created_at":"2026-07-05T07:03:58.982977+00:00"},{"alias_kind":"pith_short_16","alias_value":"QQSEEI6VBCBNN6LU","created_at":"2026-07-05T07:03:58.982977+00:00"},{"alias_kind":"pith_short_8","alias_value":"QQSEEI6V","created_at":"2026-07-05T07:03:58.982977+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/QQSEEI6VBCBNN6LU37VH4ROSOY","json":"https://pith.science/pith/QQSEEI6VBCBNN6LU37VH4ROSOY.json","graph_json":"https://pith.science/api/pith-number/QQSEEI6VBCBNN6LU37VH4ROSOY/graph.json","events_json":"https://pith.science/api/pith-number/QQSEEI6VBCBNN6LU37VH4ROSOY/events.json","paper":"https://pith.science/paper/QQSEEI6V"},"agent_actions":{"view_html":"https://pith.science/pith/QQSEEI6VBCBNN6LU37VH4ROSOY","download_json":"https://pith.science/pith/QQSEEI6VBCBNN6LU37VH4ROSOY.json","view_paper":"https://pith.science/paper/QQSEEI6V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.14214&json=true","fetch_graph":"https://pith.science/api/pith-number/QQSEEI6VBCBNN6LU37VH4ROSOY/graph.json","fetch_events":"https://pith.science/api/pith-number/QQSEEI6VBCBNN6LU37VH4ROSOY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QQSEEI6VBCBNN6LU37VH4ROSOY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QQSEEI6VBCBNN6LU37VH4ROSOY/action/storage_attestation","attest_author":"https://pith.science/pith/QQSEEI6VBCBNN6LU37VH4ROSOY/action/author_attestation","sign_citation":"https://pith.science/pith/QQSEEI6VBCBNN6LU37VH4ROSOY/action/citation_signature","submit_replication":"https://pith.science/pith/QQSEEI6VBCBNN6LU37VH4ROSOY/action/replication_record"}},"created_at":"2026-07-05T07:03:58.982977+00:00","updated_at":"2026-07-05T07:03:58.982977+00:00"}