{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UNSIYQ2EGKBYGVDSEAIDCQIHHX","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":"6303d2272e8714d27c55811e4870fdc00e631e9f32095e373573cc8da443e624","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-29T22:02:00Z","title_canon_sha256":"3270ab89bc3fd16aa0b7ce7f358f30a4ab3bc290144d9c87e8b07c93d2fe3179"},"schema_version":"1.0","source":{"id":"2412.20597","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.20597","created_at":"2026-07-05T09:59:58Z"},{"alias_kind":"arxiv_version","alias_value":"2412.20597v3","created_at":"2026-07-05T09:59:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.20597","created_at":"2026-07-05T09:59:58Z"},{"alias_kind":"pith_short_12","alias_value":"UNSIYQ2EGKBY","created_at":"2026-07-05T09:59:58Z"},{"alias_kind":"pith_short_16","alias_value":"UNSIYQ2EGKBYGVDS","created_at":"2026-07-05T09:59:58Z"},{"alias_kind":"pith_short_8","alias_value":"UNSIYQ2E","created_at":"2026-07-05T09:59:58Z"}],"graph_snapshots":[{"event_id":"sha256:9453b77e2df6ccc979a2b4537ffa33f28ffc5245ab1ff1589936e2c314a1284f","target":"graph","created_at":"2026-07-05T09:59:58Z","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/2412.20597/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present GliLem -- a novel hybrid lemmatization system for Estonian that enhances the highly accurate rule-based morphological analyzer Vabamorf with an external disambiguation module based on GliNER -- an open vocabulary NER model that is able to match text spans with text labels in natural language. We leverage the flexibility of a pre-trained GliNER model to improve the lemmatization accuracy of Vabamorf by 10% compared to its original disambiguation module and achieve an improvement over the token classification-based baseline. To measure the impact of improvements in lemmatization accur","authors_text":"Aleksei Dorkin, Kairit Sirts","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-29T22:02:00Z","title":"GliLem: Leveraging GliNER for Contextualized Lemmatization in Estonian"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.20597","kind":"arxiv","version":3},"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":"sha256:86276e5a236a7fedcd03bca23f4d926fdd186b829d78206701dd7d14245ba73b","target":"record","created_at":"2026-07-05T09:59:58Z","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":"6303d2272e8714d27c55811e4870fdc00e631e9f32095e373573cc8da443e624","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-29T22:02:00Z","title_canon_sha256":"3270ab89bc3fd16aa0b7ce7f358f30a4ab3bc290144d9c87e8b07c93d2fe3179"},"schema_version":"1.0","source":{"id":"2412.20597","kind":"arxiv","version":3}},"canonical_sha256":"a3648c4344328383547220103141073df34566ac2a09d900aa9b80c72d7a4138","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a3648c4344328383547220103141073df34566ac2a09d900aa9b80c72d7a4138","first_computed_at":"2026-07-05T09:59:58.123212Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:59:58.123212Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"z7AvWGs80rtZ1EV5nFjf9dBz+bG3XYrGCcGRNnnsLnA955exQpy1AgVwQjgpPUU4ybQ9HTj4TPJC1CyAe81kDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:59:58.123895Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.20597","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:86276e5a236a7fedcd03bca23f4d926fdd186b829d78206701dd7d14245ba73b","sha256:9453b77e2df6ccc979a2b4537ffa33f28ffc5245ab1ff1589936e2c314a1284f"],"state_sha256":"5bbe2ddb191d7800a92095c3278405f4b9d48a620b2e927850d840649f98aa1e"}