{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7OTEIBFHUTCNZYJNW63KKT55MP","short_pith_number":"pith:7OTEIBFH","schema_version":"1.0","canonical_sha256":"fba64404a7a4c4dce12db7b6a54fbd63d8152a226fa2c7eff2baced7abcf1e05","source":{"kind":"arxiv","id":"2503.20568","version":1},"attestation_state":"computed","paper":{"title":"Low-resource Information Extraction with the European Clinical Case Corpus","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alberto Lavelli, Begona Altuna, Bernardo Magnini, Giulia Mezzanotte, Manuela Speranza, Pietro Ferrazzi, Saeed Farzi, Soumitra Ghosh","submitted_at":"2025-03-26T14:07:40Z","abstract_excerpt":"We present E3C-3.0, a multilingual dataset in the medical domain, comprising clinical cases annotated with diseases and test-result relations. The dataset includes both native texts in five languages (English, French, Italian, Spanish and Basque) and texts translated and projected from the English source into five target languages (Greek, Italian, Polish, Slovak, and Slovenian). A semi-automatic approach has been implemented, including automatic annotation projection based on Large Language Models (LLMs) and human revision. We present several experiments showing that current state-of-the-art L"},"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":"2503.20568","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-26T14:07:40Z","cross_cats_sorted":[],"title_canon_sha256":"8507c2be87f44abb0a8823299b744e195c8866441ed66958372cc4aec9f3a1ec","abstract_canon_sha256":"63c13a00576c3db1331dde100de49d40d65280154edb186491bd3fb8305fc9c7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:39:40.571601Z","signature_b64":"58weUMChJsihXQDT8CddUCBtuZChyAO2xt8wckj7FgwUyZlfL6AKwEQ3l3R2MbA999yKsuYqRAdBGocut1E8CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fba64404a7a4c4dce12db7b6a54fbd63d8152a226fa2c7eff2baced7abcf1e05","last_reissued_at":"2026-07-05T10:39:40.571043Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:39:40.571043Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Low-resource Information Extraction with the European Clinical Case Corpus","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alberto Lavelli, Begona Altuna, Bernardo Magnini, Giulia Mezzanotte, Manuela Speranza, Pietro Ferrazzi, Saeed Farzi, Soumitra Ghosh","submitted_at":"2025-03-26T14:07:40Z","abstract_excerpt":"We present E3C-3.0, a multilingual dataset in the medical domain, comprising clinical cases annotated with diseases and test-result relations. The dataset includes both native texts in five languages (English, French, Italian, Spanish and Basque) and texts translated and projected from the English source into five target languages (Greek, Italian, Polish, Slovak, and Slovenian). A semi-automatic approach has been implemented, including automatic annotation projection based on Large Language Models (LLMs) and human revision. We present several experiments showing that current state-of-the-art L"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.20568","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/2503.20568/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":"2503.20568","created_at":"2026-07-05T10:39:40.571102+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.20568v1","created_at":"2026-07-05T10:39:40.571102+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.20568","created_at":"2026-07-05T10:39:40.571102+00:00"},{"alias_kind":"pith_short_12","alias_value":"7OTEIBFHUTCN","created_at":"2026-07-05T10:39:40.571102+00:00"},{"alias_kind":"pith_short_16","alias_value":"7OTEIBFHUTCNZYJN","created_at":"2026-07-05T10:39:40.571102+00:00"},{"alias_kind":"pith_short_8","alias_value":"7OTEIBFH","created_at":"2026-07-05T10:39:40.571102+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12569","citing_title":"eCREAM-MedCorpus A Large-Scale Corpus of Clinical Notes for Italian","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12569","citing_title":"eCREAM-MedCorpus A Large-Scale Corpus of Clinical Notes for Italian","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12569","citing_title":"eCREAM-MedCorpus A Large-Scale Corpus of Clinical Notes for Italian","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12569","citing_title":"eCREAM-MedCorpus A Large-Scale Corpus of Clinical Notes for Italian","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7OTEIBFHUTCNZYJNW63KKT55MP","json":"https://pith.science/pith/7OTEIBFHUTCNZYJNW63KKT55MP.json","graph_json":"https://pith.science/api/pith-number/7OTEIBFHUTCNZYJNW63KKT55MP/graph.json","events_json":"https://pith.science/api/pith-number/7OTEIBFHUTCNZYJNW63KKT55MP/events.json","paper":"https://pith.science/paper/7OTEIBFH"},"agent_actions":{"view_html":"https://pith.science/pith/7OTEIBFHUTCNZYJNW63KKT55MP","download_json":"https://pith.science/pith/7OTEIBFHUTCNZYJNW63KKT55MP.json","view_paper":"https://pith.science/paper/7OTEIBFH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.20568&json=true","fetch_graph":"https://pith.science/api/pith-number/7OTEIBFHUTCNZYJNW63KKT55MP/graph.json","fetch_events":"https://pith.science/api/pith-number/7OTEIBFHUTCNZYJNW63KKT55MP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7OTEIBFHUTCNZYJNW63KKT55MP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7OTEIBFHUTCNZYJNW63KKT55MP/action/storage_attestation","attest_author":"https://pith.science/pith/7OTEIBFHUTCNZYJNW63KKT55MP/action/author_attestation","sign_citation":"https://pith.science/pith/7OTEIBFHUTCNZYJNW63KKT55MP/action/citation_signature","submit_replication":"https://pith.science/pith/7OTEIBFHUTCNZYJNW63KKT55MP/action/replication_record"}},"created_at":"2026-07-05T10:39:40.571102+00:00","updated_at":"2026-07-05T10:39:40.571102+00:00"}