{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:XX4ILJI763WWQO77THTYI2XSMT","short_pith_number":"pith:XX4ILJI7","schema_version":"1.0","canonical_sha256":"bdf885a51ff6ed683bff99e7846af264eb3b52da6e9a0d3d2d3b74390fbdfc74","source":{"kind":"arxiv","id":"2003.09606","version":1},"attestation_state":"computed","paper":{"title":"A Joint Approach to Compound Splitting and Idiomatic Compound Detection","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ekaterina Artemova, Irina Krotova, Sergey Aksenov","submitted_at":"2020-03-21T09:00:52Z","abstract_excerpt":"Applications such as machine translation, speech recognition, and information retrieval require efficient handling of noun compounds as they are one of the possible sources for out-of-vocabulary (OOV) words. In-depth processing of noun compounds requires not only splitting them into smaller components (or even roots) but also the identification of instances that should remain unsplitted as they are of idiomatic nature. We develop a two-fold deep learning-based approach of noun compound splitting and idiomatic compound detection for the German language that we train using a newly collected corp"},"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":"2003.09606","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2020-03-21T09:00:52Z","cross_cats_sorted":[],"title_canon_sha256":"e46db2fe3deb68dd84e1b5a171be77479879656b3cc1f467f3bbd48552ded6e1","abstract_canon_sha256":"3045f03ba5e1c594a30fee6c03f4d44a0ee4293b813e6e54a65f468553e22548"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:49:45.296903Z","signature_b64":"/BlRuSg+KBxZRfl/dbPtCpC4BMx+YXyUFqwSRUeEKEdg4I2TniuYZcuMF8VUsNewF8BK4P2SucHnrdwuG4ViBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bdf885a51ff6ed683bff99e7846af264eb3b52da6e9a0d3d2d3b74390fbdfc74","last_reissued_at":"2026-07-05T00:49:45.296456Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:49:45.296456Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Joint Approach to Compound Splitting and Idiomatic Compound Detection","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ekaterina Artemova, Irina Krotova, Sergey Aksenov","submitted_at":"2020-03-21T09:00:52Z","abstract_excerpt":"Applications such as machine translation, speech recognition, and information retrieval require efficient handling of noun compounds as they are one of the possible sources for out-of-vocabulary (OOV) words. In-depth processing of noun compounds requires not only splitting them into smaller components (or even roots) but also the identification of instances that should remain unsplitted as they are of idiomatic nature. We develop a two-fold deep learning-based approach of noun compound splitting and idiomatic compound detection for the German language that we train using a newly collected corp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.09606","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/2003.09606/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":"2003.09606","created_at":"2026-07-05T00:49:45.296519+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.09606v1","created_at":"2026-07-05T00:49:45.296519+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.09606","created_at":"2026-07-05T00:49:45.296519+00:00"},{"alias_kind":"pith_short_12","alias_value":"XX4ILJI763WW","created_at":"2026-07-05T00:49:45.296519+00:00"},{"alias_kind":"pith_short_16","alias_value":"XX4ILJI763WWQO77","created_at":"2026-07-05T00:49:45.296519+00:00"},{"alias_kind":"pith_short_8","alias_value":"XX4ILJI7","created_at":"2026-07-05T00:49:45.296519+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/XX4ILJI763WWQO77THTYI2XSMT","json":"https://pith.science/pith/XX4ILJI763WWQO77THTYI2XSMT.json","graph_json":"https://pith.science/api/pith-number/XX4ILJI763WWQO77THTYI2XSMT/graph.json","events_json":"https://pith.science/api/pith-number/XX4ILJI763WWQO77THTYI2XSMT/events.json","paper":"https://pith.science/paper/XX4ILJI7"},"agent_actions":{"view_html":"https://pith.science/pith/XX4ILJI763WWQO77THTYI2XSMT","download_json":"https://pith.science/pith/XX4ILJI763WWQO77THTYI2XSMT.json","view_paper":"https://pith.science/paper/XX4ILJI7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.09606&json=true","fetch_graph":"https://pith.science/api/pith-number/XX4ILJI763WWQO77THTYI2XSMT/graph.json","fetch_events":"https://pith.science/api/pith-number/XX4ILJI763WWQO77THTYI2XSMT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XX4ILJI763WWQO77THTYI2XSMT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XX4ILJI763WWQO77THTYI2XSMT/action/storage_attestation","attest_author":"https://pith.science/pith/XX4ILJI763WWQO77THTYI2XSMT/action/author_attestation","sign_citation":"https://pith.science/pith/XX4ILJI763WWQO77THTYI2XSMT/action/citation_signature","submit_replication":"https://pith.science/pith/XX4ILJI763WWQO77THTYI2XSMT/action/replication_record"}},"created_at":"2026-07-05T00:49:45.296519+00:00","updated_at":"2026-07-05T00:49:45.296519+00:00"}