{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:V2DRBLMAVOXN5RO2BQZPEDOF5L","short_pith_number":"pith:V2DRBLMA","schema_version":"1.0","canonical_sha256":"ae8710ad80abaedec5da0c32f20dc5eadefd306a088e99ac432a955b9dcac172","source":{"kind":"arxiv","id":"2503.07827","version":1},"attestation_state":"computed","paper":{"title":"Modern Models, Medieval Texts: A POS Tagging Study of Old Occitan","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Christian Heumann, Esteban Garces Arias, Marinus Wiedner, Matthias A{\\ss}enmacher, Matthias Sch\\\"offel, Paula Ruppert","submitted_at":"2025-03-10T20:16:01Z","abstract_excerpt":"Large language models (LLMs) have demonstrated remarkable capabilities in natural language processing, yet their effectiveness in handling historical languages remains largely unexplored. This study examines the performance of open-source LLMs in part-of-speech (POS) tagging for Old Occitan, a historical language characterized by non-standardized orthography and significant diachronic variation. Through comparative analysis of two distinct corpora-hagiographical and medical texts-we evaluate how current models handle the inherent challenges of processing a low-resource historical language. Our"},"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":"2503.07827","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-10T20:16:01Z","cross_cats_sorted":[],"title_canon_sha256":"06140568302653d24adbfdbc24fc5a7d1f6bdb2e0d437b00221786fb58c2838f","abstract_canon_sha256":"aed68eba4026151aff0fd38eda042df8544afa396621610e06ecf498197a4ad9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:28:44.698412Z","signature_b64":"ZSsDbDiycVR/AWW3Lp+eKsomB7JHR1NcbcMruT5khY7wEUHDgrSbWaVAX5wRBceqDndZ3FxDguJcjvX/Z4UbCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae8710ad80abaedec5da0c32f20dc5eadefd306a088e99ac432a955b9dcac172","last_reissued_at":"2026-07-05T10:28:44.697724Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:28:44.697724Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Modern Models, Medieval Texts: A POS Tagging Study of Old Occitan","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Christian Heumann, Esteban Garces Arias, Marinus Wiedner, Matthias A{\\ss}enmacher, Matthias Sch\\\"offel, Paula Ruppert","submitted_at":"2025-03-10T20:16:01Z","abstract_excerpt":"Large language models (LLMs) have demonstrated remarkable capabilities in natural language processing, yet their effectiveness in handling historical languages remains largely unexplored. This study examines the performance of open-source LLMs in part-of-speech (POS) tagging for Old Occitan, a historical language characterized by non-standardized orthography and significant diachronic variation. Through comparative analysis of two distinct corpora-hagiographical and medical texts-we evaluate how current models handle the inherent challenges of processing a low-resource historical language. Our"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.07827","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/2503.07827/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":"2503.07827","created_at":"2026-07-05T10:28:44.697812+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.07827v1","created_at":"2026-07-05T10:28:44.697812+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.07827","created_at":"2026-07-05T10:28:44.697812+00:00"},{"alias_kind":"pith_short_12","alias_value":"V2DRBLMAVOXN","created_at":"2026-07-05T10:28:44.697812+00:00"},{"alias_kind":"pith_short_16","alias_value":"V2DRBLMAVOXN5RO2","created_at":"2026-07-05T10:28:44.697812+00:00"},{"alias_kind":"pith_short_8","alias_value":"V2DRBLMA","created_at":"2026-07-05T10:28:44.697812+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.17715","citing_title":"Unveiling Factors for Enhanced POS Tagging: A Study of Low-Resource Medieval Romance Languages","ref_index":42,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V2DRBLMAVOXN5RO2BQZPEDOF5L","json":"https://pith.science/pith/V2DRBLMAVOXN5RO2BQZPEDOF5L.json","graph_json":"https://pith.science/api/pith-number/V2DRBLMAVOXN5RO2BQZPEDOF5L/graph.json","events_json":"https://pith.science/api/pith-number/V2DRBLMAVOXN5RO2BQZPEDOF5L/events.json","paper":"https://pith.science/paper/V2DRBLMA"},"agent_actions":{"view_html":"https://pith.science/pith/V2DRBLMAVOXN5RO2BQZPEDOF5L","download_json":"https://pith.science/pith/V2DRBLMAVOXN5RO2BQZPEDOF5L.json","view_paper":"https://pith.science/paper/V2DRBLMA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.07827&json=true","fetch_graph":"https://pith.science/api/pith-number/V2DRBLMAVOXN5RO2BQZPEDOF5L/graph.json","fetch_events":"https://pith.science/api/pith-number/V2DRBLMAVOXN5RO2BQZPEDOF5L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V2DRBLMAVOXN5RO2BQZPEDOF5L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V2DRBLMAVOXN5RO2BQZPEDOF5L/action/storage_attestation","attest_author":"https://pith.science/pith/V2DRBLMAVOXN5RO2BQZPEDOF5L/action/author_attestation","sign_citation":"https://pith.science/pith/V2DRBLMAVOXN5RO2BQZPEDOF5L/action/citation_signature","submit_replication":"https://pith.science/pith/V2DRBLMAVOXN5RO2BQZPEDOF5L/action/replication_record"}},"created_at":"2026-07-05T10:28:44.697812+00:00","updated_at":"2026-07-05T10:28:44.697812+00:00"}