{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:V2DRBLMAVOXN5RO2BQZPEDOF5L","short_pith_number":"pith:V2DRBLMA","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"},"canonical_sha256":"ae8710ad80abaedec5da0c32f20dc5eadefd306a088e99ac432a955b9dcac172","source":{"kind":"arxiv","id":"2503.07827","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.07827","created_at":"2026-07-05T10:28:44Z"},{"alias_kind":"arxiv_version","alias_value":"2503.07827v1","created_at":"2026-07-05T10:28:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.07827","created_at":"2026-07-05T10:28:44Z"},{"alias_kind":"pith_short_12","alias_value":"V2DRBLMAVOXN","created_at":"2026-07-05T10:28:44Z"},{"alias_kind":"pith_short_16","alias_value":"V2DRBLMAVOXN5RO2","created_at":"2026-07-05T10:28:44Z"},{"alias_kind":"pith_short_8","alias_value":"V2DRBLMA","created_at":"2026-07-05T10:28:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:V2DRBLMAVOXN5RO2BQZPEDOF5L","target":"record","payload":{"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"},"canonical_sha256":"ae8710ad80abaedec5da0c32f20dc5eadefd306a088e99ac432a955b9dcac172","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"},"source_kind":"arxiv","source_id":"2503.07827","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:28:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LHBaQvsmVa5qwHvYNmHa2Ez1sHo6lMX3doY7ApzxrXVkPsXPFOlA9liGAUt8YFsxEeZYFdQMUOX+7ks5zJhfBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T09:09:42.474367Z"},"content_sha256":"d83a8a09490d848b07e692e0137c60c0beaade4b250d9af15464b961182d35da","schema_version":"1.0","event_id":"sha256:d83a8a09490d848b07e692e0137c60c0beaade4b250d9af15464b961182d35da"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:V2DRBLMAVOXN5RO2BQZPEDOF5L","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:28:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FG+mgh/+zHaKtaYb8K2pX1a8/oxTvwfD9iKSt9xqtlRmxVnpokE9FX17fhKK1fnHmKQNrh/2foxzOpCVtk/iBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T09:09:42.474893Z"},"content_sha256":"7fbb05cd4ec2183830ac2c2c34b6f76872b25eba5a5863d8a89f6e14414a623d","schema_version":"1.0","event_id":"sha256:7fbb05cd4ec2183830ac2c2c34b6f76872b25eba5a5863d8a89f6e14414a623d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V2DRBLMAVOXN5RO2BQZPEDOF5L/bundle.json","state_url":"https://pith.science/pith/V2DRBLMAVOXN5RO2BQZPEDOF5L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V2DRBLMAVOXN5RO2BQZPEDOF5L/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-19T09:09:42Z","links":{"resolver":"https://pith.science/pith/V2DRBLMAVOXN5RO2BQZPEDOF5L","bundle":"https://pith.science/pith/V2DRBLMAVOXN5RO2BQZPEDOF5L/bundle.json","state":"https://pith.science/pith/V2DRBLMAVOXN5RO2BQZPEDOF5L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V2DRBLMAVOXN5RO2BQZPEDOF5L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:V2DRBLMAVOXN5RO2BQZPEDOF5L","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"aed68eba4026151aff0fd38eda042df8544afa396621610e06ecf498197a4ad9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-10T20:16:01Z","title_canon_sha256":"06140568302653d24adbfdbc24fc5a7d1f6bdb2e0d437b00221786fb58c2838f"},"schema_version":"1.0","source":{"id":"2503.07827","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.07827","created_at":"2026-07-05T10:28:44Z"},{"alias_kind":"arxiv_version","alias_value":"2503.07827v1","created_at":"2026-07-05T10:28:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.07827","created_at":"2026-07-05T10:28:44Z"},{"alias_kind":"pith_short_12","alias_value":"V2DRBLMAVOXN","created_at":"2026-07-05T10:28:44Z"},{"alias_kind":"pith_short_16","alias_value":"V2DRBLMAVOXN5RO2","created_at":"2026-07-05T10:28:44Z"},{"alias_kind":"pith_short_8","alias_value":"V2DRBLMA","created_at":"2026-07-05T10:28:44Z"}],"graph_snapshots":[{"event_id":"sha256:7fbb05cd4ec2183830ac2c2c34b6f76872b25eba5a5863d8a89f6e14414a623d","target":"graph","created_at":"2026-07-05T10:28:44Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2503.07827/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Christian Heumann, Esteban Garces Arias, Marinus Wiedner, Matthias A{\\ss}enmacher, Matthias Sch\\\"offel, Paula Ruppert","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-10T20:16:01Z","title":"Modern Models, Medieval Texts: A POS Tagging Study of Old Occitan"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.07827","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d83a8a09490d848b07e692e0137c60c0beaade4b250d9af15464b961182d35da","target":"record","created_at":"2026-07-05T10:28:44Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"aed68eba4026151aff0fd38eda042df8544afa396621610e06ecf498197a4ad9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-10T20:16:01Z","title_canon_sha256":"06140568302653d24adbfdbc24fc5a7d1f6bdb2e0d437b00221786fb58c2838f"},"schema_version":"1.0","source":{"id":"2503.07827","kind":"arxiv","version":1}},"canonical_sha256":"ae8710ad80abaedec5da0c32f20dc5eadefd306a088e99ac432a955b9dcac172","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ae8710ad80abaedec5da0c32f20dc5eadefd306a088e99ac432a955b9dcac172","first_computed_at":"2026-07-05T10:28:44.697724Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:28:44.697724Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZSsDbDiycVR/AWW3Lp+eKsomB7JHR1NcbcMruT5khY7wEUHDgrSbWaVAX5wRBceqDndZ3FxDguJcjvX/Z4UbCA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:28:44.698412Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.07827","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d83a8a09490d848b07e692e0137c60c0beaade4b250d9af15464b961182d35da","sha256:7fbb05cd4ec2183830ac2c2c34b6f76872b25eba5a5863d8a89f6e14414a623d"],"state_sha256":"552fe765e23bdbd4595d0330d1dbef166a6a3fca3245ba3a7e04f37ca656f6c8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oW1s1UICORjLa4Kb7N43n92zPwxT/hSZr0TIemkSfuMFHPcznWTcL4sgg1bKS3p7fZkgREQH+FAhzqd7cPUzAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T09:09:42.479072Z","bundle_sha256":"04ceecd99cd3ab973b4ea74463ee3285cecd710cb72cd54b17b05d0c2a55785e"}}