{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TZCQQK5EYTKDH7UULS3CFJ33AE","short_pith_number":"pith:TZCQQK5E","schema_version":"1.0","canonical_sha256":"9e45082ba4c4d433fe945cb622a77b0118990dca6cffb9cbfe773d16fd375682","source":{"kind":"arxiv","id":"2412.10095","version":2},"attestation_state":"computed","paper":{"title":"HiTZ at VarDial 2025 NorSID: Overcoming Data Scarcity with Language Transfer and Automatic Data Annotation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ekhi Azurmendi, Jaione Bengoetxea, Jeremy Barnes, Julen Etxaniz, Maite Heredia, Markel Ferro, Mikel Zubillaga","submitted_at":"2024-12-13T12:31:06Z","abstract_excerpt":"In this paper we present our submission for the NorSID Shared Task as part of the 2025 VarDial Workshop (Scherrer et al., 2025), consisting of three tasks: Intent Detection, Slot Filling and Dialect Identification, evaluated using data in different dialects of the Norwegian language. For Intent Detection and Slot Filling, we have fine-tuned a multitask model in a cross-lingual setting, to leverage the xSID dataset available in 17 languages. In the case of Dialect Identification, our final submission consists of a model fine-tuned on the provided development set, which has obtained the highest "},"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":"2412.10095","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-13T12:31:06Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"3b275235f90f3f502146d128f97397577062f78a78ff2ceff82ceea02891e27d","abstract_canon_sha256":"7b8bade7f39343637c3ec6dbfb553cf6848f6f7ac155f78d6571034a970b402a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:59:01.607042Z","signature_b64":"akbntO5EpslG5xPmTQWpSg+mjl6YEXgKoPowmjJph2nb+tVJGMxxCf1QReLPVq0cxuwt6pOc9m+TFp0Pk2OWBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e45082ba4c4d433fe945cb622a77b0118990dca6cffb9cbfe773d16fd375682","last_reissued_at":"2026-07-05T09:59:01.606604Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:59:01.606604Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HiTZ at VarDial 2025 NorSID: Overcoming Data Scarcity with Language Transfer and Automatic Data Annotation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ekhi Azurmendi, Jaione Bengoetxea, Jeremy Barnes, Julen Etxaniz, Maite Heredia, Markel Ferro, Mikel Zubillaga","submitted_at":"2024-12-13T12:31:06Z","abstract_excerpt":"In this paper we present our submission for the NorSID Shared Task as part of the 2025 VarDial Workshop (Scherrer et al., 2025), consisting of three tasks: Intent Detection, Slot Filling and Dialect Identification, evaluated using data in different dialects of the Norwegian language. For Intent Detection and Slot Filling, we have fine-tuned a multitask model in a cross-lingual setting, to leverage the xSID dataset available in 17 languages. In the case of Dialect Identification, our final submission consists of a model fine-tuned on the provided development set, which has obtained the highest "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10095","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/2412.10095/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":"2412.10095","created_at":"2026-07-05T09:59:01.606670+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.10095v2","created_at":"2026-07-05T09:59:01.606670+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10095","created_at":"2026-07-05T09:59:01.606670+00:00"},{"alias_kind":"pith_short_12","alias_value":"TZCQQK5EYTKD","created_at":"2026-07-05T09:59:01.606670+00:00"},{"alias_kind":"pith_short_16","alias_value":"TZCQQK5EYTKDH7UU","created_at":"2026-07-05T09:59:01.606670+00:00"},{"alias_kind":"pith_short_8","alias_value":"TZCQQK5E","created_at":"2026-07-05T09:59:01.606670+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/TZCQQK5EYTKDH7UULS3CFJ33AE","json":"https://pith.science/pith/TZCQQK5EYTKDH7UULS3CFJ33AE.json","graph_json":"https://pith.science/api/pith-number/TZCQQK5EYTKDH7UULS3CFJ33AE/graph.json","events_json":"https://pith.science/api/pith-number/TZCQQK5EYTKDH7UULS3CFJ33AE/events.json","paper":"https://pith.science/paper/TZCQQK5E"},"agent_actions":{"view_html":"https://pith.science/pith/TZCQQK5EYTKDH7UULS3CFJ33AE","download_json":"https://pith.science/pith/TZCQQK5EYTKDH7UULS3CFJ33AE.json","view_paper":"https://pith.science/paper/TZCQQK5E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.10095&json=true","fetch_graph":"https://pith.science/api/pith-number/TZCQQK5EYTKDH7UULS3CFJ33AE/graph.json","fetch_events":"https://pith.science/api/pith-number/TZCQQK5EYTKDH7UULS3CFJ33AE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TZCQQK5EYTKDH7UULS3CFJ33AE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TZCQQK5EYTKDH7UULS3CFJ33AE/action/storage_attestation","attest_author":"https://pith.science/pith/TZCQQK5EYTKDH7UULS3CFJ33AE/action/author_attestation","sign_citation":"https://pith.science/pith/TZCQQK5EYTKDH7UULS3CFJ33AE/action/citation_signature","submit_replication":"https://pith.science/pith/TZCQQK5EYTKDH7UULS3CFJ33AE/action/replication_record"}},"created_at":"2026-07-05T09:59:01.606670+00:00","updated_at":"2026-07-05T09:59:01.606670+00:00"}