{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3UT6RPN3KMPHZL2YZHWRXNK5IB","short_pith_number":"pith:3UT6RPN3","schema_version":"1.0","canonical_sha256":"dd27e8bdbb531e7caf58c9ed1bb55d40770208f93a92de85758a5fc0fdc161d2","source":{"kind":"arxiv","id":"2404.08974","version":2},"attestation_state":"computed","paper":{"title":"OOVs in the Spotlight: How to Inflect them?","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jana Strakov\\'a, Rudolf Rosa, Tom\\'a\\v{s} Sourada","submitted_at":"2024-04-13T11:40:06Z","abstract_excerpt":"We focus on morphological inflection in out-of-vocabulary (OOV) conditions, an under-researched subtask in which state-of-the-art systems usually are less effective. We developed three systems: a retrograde model and two sequence-to-sequence (seq2seq) models based on LSTM and Transformer. For testing in OOV conditions, we automatically extracted a large dataset of nouns in the morphologically rich Czech language, with lemma-disjoint data splits, and we further manually annotated a real-world OOV dataset of neologisms. In the standard OOV conditions, Transformer achieves the best results, with "},"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":"2404.08974","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-13T11:40:06Z","cross_cats_sorted":[],"title_canon_sha256":"9ebe766ccbf9ef6e84d6ec2ba6bdbe309d1528da52fb61e2d0ef6ff47bd5bb6e","abstract_canon_sha256":"59575e8df8bf822e7876c9bb11167e96d878a26cf2366aad560e5fe02dcb8a3c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:24:04.498947Z","signature_b64":"qps/v65Kc8h0aLX6rF7VzoUURwROthKu/fjhQqSm9cdXKCNacwMcKQh55YxsIDKQmTdaJ526bOw6cCxaUT2xBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dd27e8bdbb531e7caf58c9ed1bb55d40770208f93a92de85758a5fc0fdc161d2","last_reissued_at":"2026-07-05T08:24:04.498472Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:24:04.498472Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OOVs in the Spotlight: How to Inflect them?","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jana Strakov\\'a, Rudolf Rosa, Tom\\'a\\v{s} Sourada","submitted_at":"2024-04-13T11:40:06Z","abstract_excerpt":"We focus on morphological inflection in out-of-vocabulary (OOV) conditions, an under-researched subtask in which state-of-the-art systems usually are less effective. We developed three systems: a retrograde model and two sequence-to-sequence (seq2seq) models based on LSTM and Transformer. For testing in OOV conditions, we automatically extracted a large dataset of nouns in the morphologically rich Czech language, with lemma-disjoint data splits, and we further manually annotated a real-world OOV dataset of neologisms. In the standard OOV conditions, Transformer achieves the best results, with "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.08974","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/2404.08974/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":"2404.08974","created_at":"2026-07-05T08:24:04.498533+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.08974v2","created_at":"2026-07-05T08:24:04.498533+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.08974","created_at":"2026-07-05T08:24:04.498533+00:00"},{"alias_kind":"pith_short_12","alias_value":"3UT6RPN3KMPH","created_at":"2026-07-05T08:24:04.498533+00:00"},{"alias_kind":"pith_short_16","alias_value":"3UT6RPN3KMPHZL2Y","created_at":"2026-07-05T08:24:04.498533+00:00"},{"alias_kind":"pith_short_8","alias_value":"3UT6RPN3","created_at":"2026-07-05T08:24:04.498533+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/3UT6RPN3KMPHZL2YZHWRXNK5IB","json":"https://pith.science/pith/3UT6RPN3KMPHZL2YZHWRXNK5IB.json","graph_json":"https://pith.science/api/pith-number/3UT6RPN3KMPHZL2YZHWRXNK5IB/graph.json","events_json":"https://pith.science/api/pith-number/3UT6RPN3KMPHZL2YZHWRXNK5IB/events.json","paper":"https://pith.science/paper/3UT6RPN3"},"agent_actions":{"view_html":"https://pith.science/pith/3UT6RPN3KMPHZL2YZHWRXNK5IB","download_json":"https://pith.science/pith/3UT6RPN3KMPHZL2YZHWRXNK5IB.json","view_paper":"https://pith.science/paper/3UT6RPN3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.08974&json=true","fetch_graph":"https://pith.science/api/pith-number/3UT6RPN3KMPHZL2YZHWRXNK5IB/graph.json","fetch_events":"https://pith.science/api/pith-number/3UT6RPN3KMPHZL2YZHWRXNK5IB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3UT6RPN3KMPHZL2YZHWRXNK5IB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3UT6RPN3KMPHZL2YZHWRXNK5IB/action/storage_attestation","attest_author":"https://pith.science/pith/3UT6RPN3KMPHZL2YZHWRXNK5IB/action/author_attestation","sign_citation":"https://pith.science/pith/3UT6RPN3KMPHZL2YZHWRXNK5IB/action/citation_signature","submit_replication":"https://pith.science/pith/3UT6RPN3KMPHZL2YZHWRXNK5IB/action/replication_record"}},"created_at":"2026-07-05T08:24:04.498533+00:00","updated_at":"2026-07-05T08:24:04.498533+00:00"}