{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RVAIF7DZMDU6L2LHFF5IOF3FLA","short_pith_number":"pith:RVAIF7DZ","schema_version":"1.0","canonical_sha256":"8d4082fc7960e9e5e967297a8717655837cb6b8ed2c1211ebd4af9a93271aba9","source":{"kind":"arxiv","id":"2506.17715","version":1},"attestation_state":"computed","paper":{"title":"Unveiling Factors for Enhanced POS Tagging: A Study of Low-Resource Medieval Romance Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Christian Heumann, Esteban Garces Arias, Marinus Wiedner, Matthias A{\\ss}enmacher, Matthias Sch\\\"offel, Meimingwei Li, Paula Ruppert","submitted_at":"2025-06-21T13:33:07Z","abstract_excerpt":"Part-of-speech (POS) tagging remains a foundational component in natural language processing pipelines, particularly critical for historical text analysis at the intersection of computational linguistics and digital humanities. Despite significant advancements in modern large language models (LLMs) for ancient languages, their application to Medieval Romance languages presents distinctive challenges stemming from diachronic linguistic evolution, spelling variations, and labeled data scarcity. This study systematically investigates the central determinants of POS tagging performance across dive"},"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":"2506.17715","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-21T13:33:07Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"43f2569f51048eb7d76482696e6a7f9a0683a034c4e30536688bc31e1dcf0f9d","abstract_canon_sha256":"0c8835350bb85a8c2ae6b61f738c5fba2003b4198af0f43d8bbfe976f2c2b82e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:25:22.312765Z","signature_b64":"6VNssH0KnGsdcX0gQSGcXB8+d1S3dG34rouPk3E4kXGzdFsSyEX5ODAdHJT9UgTXOj22YnhHDVUmYJtev0fXDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d4082fc7960e9e5e967297a8717655837cb6b8ed2c1211ebd4af9a93271aba9","last_reissued_at":"2026-07-05T11:25:22.312321Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:25:22.312321Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unveiling Factors for Enhanced POS Tagging: A Study of Low-Resource Medieval Romance Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Christian Heumann, Esteban Garces Arias, Marinus Wiedner, Matthias A{\\ss}enmacher, Matthias Sch\\\"offel, Meimingwei Li, Paula Ruppert","submitted_at":"2025-06-21T13:33:07Z","abstract_excerpt":"Part-of-speech (POS) tagging remains a foundational component in natural language processing pipelines, particularly critical for historical text analysis at the intersection of computational linguistics and digital humanities. Despite significant advancements in modern large language models (LLMs) for ancient languages, their application to Medieval Romance languages presents distinctive challenges stemming from diachronic linguistic evolution, spelling variations, and labeled data scarcity. This study systematically investigates the central determinants of POS tagging performance across dive"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.17715","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/2506.17715/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":"2506.17715","created_at":"2026-07-05T11:25:22.312381+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.17715v1","created_at":"2026-07-05T11:25:22.312381+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.17715","created_at":"2026-07-05T11:25:22.312381+00:00"},{"alias_kind":"pith_short_12","alias_value":"RVAIF7DZMDU6","created_at":"2026-07-05T11:25:22.312381+00:00"},{"alias_kind":"pith_short_16","alias_value":"RVAIF7DZMDU6L2LH","created_at":"2026-07-05T11:25:22.312381+00:00"},{"alias_kind":"pith_short_8","alias_value":"RVAIF7DZ","created_at":"2026-07-05T11:25:22.312381+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.09156","citing_title":"Lost in Translation? Exploring the Shift in Grammatical Gender from Latin to Occitan","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09156","citing_title":"Lost in Translation? Exploring the Shift in Grammatical Gender from Latin to Occitan","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RVAIF7DZMDU6L2LHFF5IOF3FLA","json":"https://pith.science/pith/RVAIF7DZMDU6L2LHFF5IOF3FLA.json","graph_json":"https://pith.science/api/pith-number/RVAIF7DZMDU6L2LHFF5IOF3FLA/graph.json","events_json":"https://pith.science/api/pith-number/RVAIF7DZMDU6L2LHFF5IOF3FLA/events.json","paper":"https://pith.science/paper/RVAIF7DZ"},"agent_actions":{"view_html":"https://pith.science/pith/RVAIF7DZMDU6L2LHFF5IOF3FLA","download_json":"https://pith.science/pith/RVAIF7DZMDU6L2LHFF5IOF3FLA.json","view_paper":"https://pith.science/paper/RVAIF7DZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.17715&json=true","fetch_graph":"https://pith.science/api/pith-number/RVAIF7DZMDU6L2LHFF5IOF3FLA/graph.json","fetch_events":"https://pith.science/api/pith-number/RVAIF7DZMDU6L2LHFF5IOF3FLA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RVAIF7DZMDU6L2LHFF5IOF3FLA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RVAIF7DZMDU6L2LHFF5IOF3FLA/action/storage_attestation","attest_author":"https://pith.science/pith/RVAIF7DZMDU6L2LHFF5IOF3FLA/action/author_attestation","sign_citation":"https://pith.science/pith/RVAIF7DZMDU6L2LHFF5IOF3FLA/action/citation_signature","submit_replication":"https://pith.science/pith/RVAIF7DZMDU6L2LHFF5IOF3FLA/action/replication_record"}},"created_at":"2026-07-05T11:25:22.312381+00:00","updated_at":"2026-07-05T11:25:22.312381+00:00"}