{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:7OS6E4A5AXLKZZA2QCVXZGWWUI","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":"804c908522a9b88b2e219db99fb317ca9727a82529bc4c47a0229d311033ba62","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-24T11:03:01Z","title_canon_sha256":"0e9873384831395f5d854e4f3f8be518ebdf19fcf6ef2c5d49b97f8fa86259e7"},"schema_version":"1.0","source":{"id":"2010.12871","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.12871","created_at":"2026-07-05T01:45:49Z"},{"alias_kind":"arxiv_version","alias_value":"2010.12871v1","created_at":"2026-07-05T01:45:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.12871","created_at":"2026-07-05T01:45:49Z"},{"alias_kind":"pith_short_12","alias_value":"7OS6E4A5AXLK","created_at":"2026-07-05T01:45:49Z"},{"alias_kind":"pith_short_16","alias_value":"7OS6E4A5AXLKZZA2","created_at":"2026-07-05T01:45:49Z"},{"alias_kind":"pith_short_8","alias_value":"7OS6E4A5","created_at":"2026-07-05T01:45:49Z"}],"graph_snapshots":[{"event_id":"sha256:897b7eb33dfaa00db00edfbc4575416a02ca0d52d900538fb8e0826505e49d57","target":"graph","created_at":"2026-07-05T01:45:49Z","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/2010.12871/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large multi-label text classification is a challenging Natural Language Processing (NLP) problem that is concerned with text classification for datasets with thousands of labels. We tackle this problem in the legal domain, where datasets, such as JRC-Acquis and EURLEX57K labeled with the EuroVoc vocabulary were created within the legal information systems of the European Union. The EuroVoc taxonomy includes around 7000 concepts. In this work, we study the performance of various recent transformer-based models in combination with strategies such as generative pretraining, gradual unfreezing and","authors_text":"Erwin Filtz, Gerhard Wohlgenannt, Zein Shaheen","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-24T11:03:01Z","title":"Large Scale Legal Text Classification Using Transformer Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.12871","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":"sha256:7750d126e4dc3280d8c375f7c2f657e827c357c6cab5ecb8787187bbd37662a7","target":"record","created_at":"2026-07-05T01:45:49Z","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":"804c908522a9b88b2e219db99fb317ca9727a82529bc4c47a0229d311033ba62","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-24T11:03:01Z","title_canon_sha256":"0e9873384831395f5d854e4f3f8be518ebdf19fcf6ef2c5d49b97f8fa86259e7"},"schema_version":"1.0","source":{"id":"2010.12871","kind":"arxiv","version":1}},"canonical_sha256":"fba5e2701d05d6ace41a80ab7c9ad6a20215dde2c70e64c55573cc8e7290221e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fba5e2701d05d6ace41a80ab7c9ad6a20215dde2c70e64c55573cc8e7290221e","first_computed_at":"2026-07-05T01:45:49.280123Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:45:49.280123Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VKB3hCPNclpf2PN6NwIwnw6Zkm5jmIjfNdDIoUjuGOTyg7hODfPgiLUH6viguuvMGttUmFvGt5tU8dvyRJwzCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:45:49.280530Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.12871","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7750d126e4dc3280d8c375f7c2f657e827c357c6cab5ecb8787187bbd37662a7","sha256:897b7eb33dfaa00db00edfbc4575416a02ca0d52d900538fb8e0826505e49d57"],"state_sha256":"e1edd59183078ce2a2a1ba08b925468bdb07f219708b0f366122c28e2fbad9d5"}