{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:E7QQY2TIWQE6Y5GCYJZYSVDLSD","short_pith_number":"pith:E7QQY2TI","schema_version":"1.0","canonical_sha256":"27e10c6a68b409ec74c2c27389546b90f8c9999df51491e6cbd29cf9d672d4f7","source":{"kind":"arxiv","id":"1905.10892","version":1},"attestation_state":"computed","paper":{"title":"Extreme Multi-Label Legal Text Classification: A case study in EU Legislation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ilias Chalkidis, Ion Androutsopoulos, Manos Fergadiotis, Nikolaos Aletras, Prodromos Malakasiotis","submitted_at":"2019-05-26T21:50:15Z","abstract_excerpt":"We consider the task of Extreme Multi-Label Text Classification (XMTC) in the legal domain. We release a new dataset of 57k legislative documents from EURLEX, the European Union's public document database, annotated with concepts from EUROVOC, a multidisciplinary thesaurus. The dataset is substantially larger than previous EURLEX datasets and suitable for XMTC, few-shot and zero-shot learning. Experimenting with several neural classifiers, we show that BIGRUs with self-attention outperform the current multi-label state-of-the-art methods, which employ label-wise attention. Replacing CNNs with "},"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":"1905.10892","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-26T21:50:15Z","cross_cats_sorted":[],"title_canon_sha256":"3025f3c5aab770f03248410fb7313be508e73490c4d6aea3ae9ddc678d636749","abstract_canon_sha256":"f70f776873c04f21ef2ba8cf548edc006330700da05d426d1ee08c2676181172"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:03.487102Z","signature_b64":"SFsEylmAeU3+E0PrT5Aum7NV+F6ScVWARpQnM2L9X1XTRzmPL4O5NIYmxfYpA/dudVK+LUDeXTXK0Dm5SwAiDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"27e10c6a68b409ec74c2c27389546b90f8c9999df51491e6cbd29cf9d672d4f7","last_reissued_at":"2026-05-17T23:45:03.486469Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:03.486469Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Extreme Multi-Label Legal Text Classification: A case study in EU Legislation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ilias Chalkidis, Ion Androutsopoulos, Manos Fergadiotis, Nikolaos Aletras, Prodromos Malakasiotis","submitted_at":"2019-05-26T21:50:15Z","abstract_excerpt":"We consider the task of Extreme Multi-Label Text Classification (XMTC) in the legal domain. We release a new dataset of 57k legislative documents from EURLEX, the European Union's public document database, annotated with concepts from EUROVOC, a multidisciplinary thesaurus. The dataset is substantially larger than previous EURLEX datasets and suitable for XMTC, few-shot and zero-shot learning. Experimenting with several neural classifiers, we show that BIGRUs with self-attention outperform the current multi-label state-of-the-art methods, which employ label-wise attention. Replacing CNNs with "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.10892","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":""},"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":"1905.10892","created_at":"2026-05-17T23:45:03.486551+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.10892v1","created_at":"2026-05-17T23:45:03.486551+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.10892","created_at":"2026-05-17T23:45:03.486551+00:00"},{"alias_kind":"pith_short_12","alias_value":"E7QQY2TIWQE6","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_16","alias_value":"E7QQY2TIWQE6Y5GC","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_8","alias_value":"E7QQY2TI","created_at":"2026-05-18T12:33:15.570797+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E7QQY2TIWQE6Y5GCYJZYSVDLSD","json":"https://pith.science/pith/E7QQY2TIWQE6Y5GCYJZYSVDLSD.json","graph_json":"https://pith.science/api/pith-number/E7QQY2TIWQE6Y5GCYJZYSVDLSD/graph.json","events_json":"https://pith.science/api/pith-number/E7QQY2TIWQE6Y5GCYJZYSVDLSD/events.json","paper":"https://pith.science/paper/E7QQY2TI"},"agent_actions":{"view_html":"https://pith.science/pith/E7QQY2TIWQE6Y5GCYJZYSVDLSD","download_json":"https://pith.science/pith/E7QQY2TIWQE6Y5GCYJZYSVDLSD.json","view_paper":"https://pith.science/paper/E7QQY2TI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.10892&json=true","fetch_graph":"https://pith.science/api/pith-number/E7QQY2TIWQE6Y5GCYJZYSVDLSD/graph.json","fetch_events":"https://pith.science/api/pith-number/E7QQY2TIWQE6Y5GCYJZYSVDLSD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E7QQY2TIWQE6Y5GCYJZYSVDLSD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E7QQY2TIWQE6Y5GCYJZYSVDLSD/action/storage_attestation","attest_author":"https://pith.science/pith/E7QQY2TIWQE6Y5GCYJZYSVDLSD/action/author_attestation","sign_citation":"https://pith.science/pith/E7QQY2TIWQE6Y5GCYJZYSVDLSD/action/citation_signature","submit_replication":"https://pith.science/pith/E7QQY2TIWQE6Y5GCYJZYSVDLSD/action/replication_record"}},"created_at":"2026-05-17T23:45:03.486551+00:00","updated_at":"2026-05-17T23:45:03.486551+00:00"}