{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:OY5NB3ZUXG42AGALF2S3FVK5G7","short_pith_number":"pith:OY5NB3ZU","canonical_record":{"source":{"id":"2407.00418","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-29T11:59:20Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d8403fbfd428466ba395d279b22d5a906c4d7104109af6a7948917e398530669","abstract_canon_sha256":"9315d83615c5df74977261d0fde50607bad0b0f69e663cbb9aa50cf194dba45c"},"schema_version":"1.0"},"canonical_sha256":"763ad0ef34b9b9a0180b2ea5b2d55d37f6e7f194947f30ee3559692205d50b2e","source":{"kind":"arxiv","id":"2407.00418","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.00418","created_at":"2026-07-05T08:38:19Z"},{"alias_kind":"arxiv_version","alias_value":"2407.00418v1","created_at":"2026-07-05T08:38:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.00418","created_at":"2026-07-05T08:38:19Z"},{"alias_kind":"pith_short_12","alias_value":"OY5NB3ZUXG42","created_at":"2026-07-05T08:38:19Z"},{"alias_kind":"pith_short_16","alias_value":"OY5NB3ZUXG42AGAL","created_at":"2026-07-05T08:38:19Z"},{"alias_kind":"pith_short_8","alias_value":"OY5NB3ZU","created_at":"2026-07-05T08:38:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:OY5NB3ZUXG42AGALF2S3FVK5G7","target":"record","payload":{"canonical_record":{"source":{"id":"2407.00418","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-29T11:59:20Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d8403fbfd428466ba395d279b22d5a906c4d7104109af6a7948917e398530669","abstract_canon_sha256":"9315d83615c5df74977261d0fde50607bad0b0f69e663cbb9aa50cf194dba45c"},"schema_version":"1.0"},"canonical_sha256":"763ad0ef34b9b9a0180b2ea5b2d55d37f6e7f194947f30ee3559692205d50b2e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:38:19.479067Z","signature_b64":"y2zhNhweKC2L/leGmSVCLzmcTEw2mpacSKzOeIOa1uzX67EM4lNLsjg6SpeOhEcBY/PvR//5UBkP32uOnv0uBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"763ad0ef34b9b9a0180b2ea5b2d55d37f6e7f194947f30ee3559692205d50b2e","last_reissued_at":"2026-07-05T08:38:19.478658Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:38:19.478658Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.00418","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":"2026-07-05T08:38:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EOLWDPQSKUg5RNvvRy4hfaIv1kRLbI1p1j8YwpNJO3ArfkbonBOIr3G77tM/6v3PClkNmA/bGsklo2VS5XEnDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T20:10:08.561017Z"},"content_sha256":"83e5d75192a89d102b17f9bdb5dd61978381118e67c5bf57aa822f1e35a449f2","schema_version":"1.0","event_id":"sha256:83e5d75192a89d102b17f9bdb5dd61978381118e67c5bf57aa822f1e35a449f2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:OY5NB3ZUXG42AGALF2S3FVK5G7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"eFontes. Part of Speech Tagging and Lemmatization of Medieval Latin Texts.A Cross-Genre Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Aleksander Smywi\\'nski-Pohl, J\\k{e}drzej Zi\\k{e}bura, Krzysztof Nowak, Krzysztof Wr\\'obel","submitted_at":"2024-06-29T11:59:20Z","abstract_excerpt":"This study introduces the eFontes models for automatic linguistic annotation of Medieval Latin texts, focusing on lemmatization, part-of-speech tagging, and morphological feature determination. Using the Transformers library, these models were trained on Universal Dependencies (UD) corpora and the newly developed eFontes corpus of Polish Medieval Latin. The research evaluates the models' performance, addressing challenges such as orthographic variations and the integration of Latinized vernacular terms. The models achieved high accuracy rates: lemmatization at 92.60%, part-of-speech tagging at"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.00418","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/2407.00418/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":"2026-07-05T08:38:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mCzYFYLR8WwNEzmqJzsRNMij3Puuwm+2bFBFixBcnCXyxYN6PbGx+cbaS3Lnxr2tjEAOr4B4t05rQb5rMnTbAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T20:10:08.561563Z"},"content_sha256":"abfafe304bbf1e53987e464f6c368897ec9ce0302698d3c8804bc66799063067","schema_version":"1.0","event_id":"sha256:abfafe304bbf1e53987e464f6c368897ec9ce0302698d3c8804bc66799063067"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OY5NB3ZUXG42AGALF2S3FVK5G7/bundle.json","state_url":"https://pith.science/pith/OY5NB3ZUXG42AGALF2S3FVK5G7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OY5NB3ZUXG42AGALF2S3FVK5G7/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":"2026-08-19T20:10:08Z","links":{"resolver":"https://pith.science/pith/OY5NB3ZUXG42AGALF2S3FVK5G7","bundle":"https://pith.science/pith/OY5NB3ZUXG42AGALF2S3FVK5G7/bundle.json","state":"https://pith.science/pith/OY5NB3ZUXG42AGALF2S3FVK5G7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OY5NB3ZUXG42AGALF2S3FVK5G7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OY5NB3ZUXG42AGALF2S3FVK5G7","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":"9315d83615c5df74977261d0fde50607bad0b0f69e663cbb9aa50cf194dba45c","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-29T11:59:20Z","title_canon_sha256":"d8403fbfd428466ba395d279b22d5a906c4d7104109af6a7948917e398530669"},"schema_version":"1.0","source":{"id":"2407.00418","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.00418","created_at":"2026-07-05T08:38:19Z"},{"alias_kind":"arxiv_version","alias_value":"2407.00418v1","created_at":"2026-07-05T08:38:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.00418","created_at":"2026-07-05T08:38:19Z"},{"alias_kind":"pith_short_12","alias_value":"OY5NB3ZUXG42","created_at":"2026-07-05T08:38:19Z"},{"alias_kind":"pith_short_16","alias_value":"OY5NB3ZUXG42AGAL","created_at":"2026-07-05T08:38:19Z"},{"alias_kind":"pith_short_8","alias_value":"OY5NB3ZU","created_at":"2026-07-05T08:38:19Z"}],"graph_snapshots":[{"event_id":"sha256:abfafe304bbf1e53987e464f6c368897ec9ce0302698d3c8804bc66799063067","target":"graph","created_at":"2026-07-05T08:38:19Z","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/2407.00418/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This study introduces the eFontes models for automatic linguistic annotation of Medieval Latin texts, focusing on lemmatization, part-of-speech tagging, and morphological feature determination. Using the Transformers library, these models were trained on Universal Dependencies (UD) corpora and the newly developed eFontes corpus of Polish Medieval Latin. The research evaluates the models' performance, addressing challenges such as orthographic variations and the integration of Latinized vernacular terms. The models achieved high accuracy rates: lemmatization at 92.60%, part-of-speech tagging at","authors_text":"Aleksander Smywi\\'nski-Pohl, J\\k{e}drzej Zi\\k{e}bura, Krzysztof Nowak, Krzysztof Wr\\'obel","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-29T11:59:20Z","title":"eFontes. Part of Speech Tagging and Lemmatization of Medieval Latin Texts.A Cross-Genre Survey"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.00418","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":"sha256:83e5d75192a89d102b17f9bdb5dd61978381118e67c5bf57aa822f1e35a449f2","target":"record","created_at":"2026-07-05T08:38:19Z","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":"9315d83615c5df74977261d0fde50607bad0b0f69e663cbb9aa50cf194dba45c","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-29T11:59:20Z","title_canon_sha256":"d8403fbfd428466ba395d279b22d5a906c4d7104109af6a7948917e398530669"},"schema_version":"1.0","source":{"id":"2407.00418","kind":"arxiv","version":1}},"canonical_sha256":"763ad0ef34b9b9a0180b2ea5b2d55d37f6e7f194947f30ee3559692205d50b2e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"763ad0ef34b9b9a0180b2ea5b2d55d37f6e7f194947f30ee3559692205d50b2e","first_computed_at":"2026-07-05T08:38:19.478658Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:38:19.478658Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"y2zhNhweKC2L/leGmSVCLzmcTEw2mpacSKzOeIOa1uzX67EM4lNLsjg6SpeOhEcBY/PvR//5UBkP32uOnv0uBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:38:19.479067Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.00418","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:83e5d75192a89d102b17f9bdb5dd61978381118e67c5bf57aa822f1e35a449f2","sha256:abfafe304bbf1e53987e464f6c368897ec9ce0302698d3c8804bc66799063067"],"state_sha256":"e184ec068ab5c7b951b997b78584a9fac30027275995a9614ff6bc5934fdbeea"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YK4exJIaflZlH/MPMWVFBfGv7AgTpOil+0afzWi8xJNSsEXNmDN2qZH6SyXTc4ObWzUhfmRxeHJTDJQNZafzAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T20:10:08.566724Z","bundle_sha256":"b9fd1501e7369962fa1fe7a6c37f49850d0e2b52c46ea52500faa1832836365c"}}