{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:32TGYPCVOYYYSX5XPOPHPYKN6J","short_pith_number":"pith:32TGYPCV","schema_version":"1.0","canonical_sha256":"dea66c3c557631895fb77b9e77e14df2640c4193a88618105fa446b6bb0c4aa6","source":{"kind":"arxiv","id":"2108.01139","version":3},"attestation_state":"computed","paper":{"title":"PyEuroVoc: A Tool for Multilingual Legal Document Classification with EuroVoc Descriptors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Andrei-Marius Avram, Dan Tufis, Vasile Pais","submitted_at":"2021-08-02T19:46:21Z","abstract_excerpt":"EuroVoc is a multilingual thesaurus that was built for organizing the legislative documentary of the European Union institutions. It contains thousands of categories at different levels of specificity and its descriptors are targeted by legal texts in almost thirty languages. In this work we propose a unified framework for EuroVoc classification on 22 languages by fine-tuning modern Transformer-based pretrained language models. We study extensively the performance of our trained models and show that they significantly improve the results obtained by a similar tool - JEX - on the same dataset. "},"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":"2108.01139","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-08-02T19:46:21Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"70118b7b6f2ca4de6ceddde03b4d3bed94bd2bdc863acf44d36888ee55e87318","abstract_canon_sha256":"d1c383c0ba9253fe708d330aac459b95cf84aa791f08b246b4fb90ce6e2c35cb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:04:28.036069Z","signature_b64":"WnW8acKOmi14fKpqJVcl0dcuh+3QsvwI8zIzfkt0tPY/C9HXwNul939xXVF4x88eSQUB3nUAqqLY9OaC0jBWAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dea66c3c557631895fb77b9e77e14df2640c4193a88618105fa446b6bb0c4aa6","last_reissued_at":"2026-07-05T03:04:28.035593Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:04:28.035593Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PyEuroVoc: A Tool for Multilingual Legal Document Classification with EuroVoc Descriptors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Andrei-Marius Avram, Dan Tufis, Vasile Pais","submitted_at":"2021-08-02T19:46:21Z","abstract_excerpt":"EuroVoc is a multilingual thesaurus that was built for organizing the legislative documentary of the European Union institutions. It contains thousands of categories at different levels of specificity and its descriptors are targeted by legal texts in almost thirty languages. In this work we propose a unified framework for EuroVoc classification on 22 languages by fine-tuning modern Transformer-based pretrained language models. We study extensively the performance of our trained models and show that they significantly improve the results obtained by a similar tool - JEX - on the same dataset. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.01139","kind":"arxiv","version":3},"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/2108.01139/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":"2108.01139","created_at":"2026-07-05T03:04:28.035652+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.01139v3","created_at":"2026-07-05T03:04:28.035652+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.01139","created_at":"2026-07-05T03:04:28.035652+00:00"},{"alias_kind":"pith_short_12","alias_value":"32TGYPCVOYYY","created_at":"2026-07-05T03:04:28.035652+00:00"},{"alias_kind":"pith_short_16","alias_value":"32TGYPCVOYYYSX5X","created_at":"2026-07-05T03:04:28.035652+00:00"},{"alias_kind":"pith_short_8","alias_value":"32TGYPCV","created_at":"2026-07-05T03:04:28.035652+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.09204","citing_title":"Logical Lease Litigation: Prolog and LLMs for Rental Law Compliance in New York","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/32TGYPCVOYYYSX5XPOPHPYKN6J","json":"https://pith.science/pith/32TGYPCVOYYYSX5XPOPHPYKN6J.json","graph_json":"https://pith.science/api/pith-number/32TGYPCVOYYYSX5XPOPHPYKN6J/graph.json","events_json":"https://pith.science/api/pith-number/32TGYPCVOYYYSX5XPOPHPYKN6J/events.json","paper":"https://pith.science/paper/32TGYPCV"},"agent_actions":{"view_html":"https://pith.science/pith/32TGYPCVOYYYSX5XPOPHPYKN6J","download_json":"https://pith.science/pith/32TGYPCVOYYYSX5XPOPHPYKN6J.json","view_paper":"https://pith.science/paper/32TGYPCV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.01139&json=true","fetch_graph":"https://pith.science/api/pith-number/32TGYPCVOYYYSX5XPOPHPYKN6J/graph.json","fetch_events":"https://pith.science/api/pith-number/32TGYPCVOYYYSX5XPOPHPYKN6J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/32TGYPCVOYYYSX5XPOPHPYKN6J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/32TGYPCVOYYYSX5XPOPHPYKN6J/action/storage_attestation","attest_author":"https://pith.science/pith/32TGYPCVOYYYSX5XPOPHPYKN6J/action/author_attestation","sign_citation":"https://pith.science/pith/32TGYPCVOYYYSX5XPOPHPYKN6J/action/citation_signature","submit_replication":"https://pith.science/pith/32TGYPCVOYYYSX5XPOPHPYKN6J/action/replication_record"}},"created_at":"2026-07-05T03:04:28.035652+00:00","updated_at":"2026-07-05T03:04:28.035652+00:00"}