{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:5ESWMXDADW2EHHK3FGARUE4MJD","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":"fc8aa51bfc7bb856d7681359c2508095d5c3d4cdbb745f06c9fb0c07dda4cacf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-11-02T09:27:01Z","title_canon_sha256":"088a385ca7e4d166393d8fd58076381f791b10e843cf6a92194ef13ead17ae65"},"schema_version":"1.0","source":{"id":"2211.00974","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.00974","created_at":"2026-07-05T05:15:00Z"},{"alias_kind":"arxiv_version","alias_value":"2211.00974v2","created_at":"2026-07-05T05:15:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.00974","created_at":"2026-07-05T05:15:00Z"},{"alias_kind":"pith_short_12","alias_value":"5ESWMXDADW2E","created_at":"2026-07-05T05:15:00Z"},{"alias_kind":"pith_short_16","alias_value":"5ESWMXDADW2EHHK3","created_at":"2026-07-05T05:15:00Z"},{"alias_kind":"pith_short_8","alias_value":"5ESWMXDA","created_at":"2026-07-05T05:15:00Z"}],"graph_snapshots":[{"event_id":"sha256:3ea5ab7bcb7d9b2d4d65618a7c3759f6b5ba1931b3113d496991f88d15544d38","target":"graph","created_at":"2026-07-05T05:15:00Z","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/2211.00974/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-trained Transformers currently dominate most NLP tasks. They impose, however, limits on the maximum input length (512 sub-words in BERT), which are too restrictive in the legal domain. Even sparse-attention models, such as Longformer and BigBird, which increase the maximum input length to 4,096 sub-words, severely truncate texts in three of the six datasets of LexGLUE. Simpler linear classifiers with TF-IDF features can handle texts of any length, require far less resources to train and deploy, but are usually outperformed by pre-trained Transformers. We explore two directions to cope with","authors_text":"Dimitris Mamakas, Ilias Chalkidis, Ion Androutsopoulos, Petros Tsotsi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-11-02T09:27:01Z","title":"Processing Long Legal Documents with Pre-trained Transformers: Modding LegalBERT and Longformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.00974","kind":"arxiv","version":2},"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":"sha256:1dd96b168706cf84f55d92698d2c2eec20ad4886f36c8d3724f7da8fffb76f6b","target":"record","created_at":"2026-07-05T05:15:00Z","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":"fc8aa51bfc7bb856d7681359c2508095d5c3d4cdbb745f06c9fb0c07dda4cacf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-11-02T09:27:01Z","title_canon_sha256":"088a385ca7e4d166393d8fd58076381f791b10e843cf6a92194ef13ead17ae65"},"schema_version":"1.0","source":{"id":"2211.00974","kind":"arxiv","version":2}},"canonical_sha256":"e925665c601db4439d5b29811a138c48d8c5872dea8d0e3a2d08a47d3858d3c7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e925665c601db4439d5b29811a138c48d8c5872dea8d0e3a2d08a47d3858d3c7","first_computed_at":"2026-07-05T05:15:00.767856Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:15:00.767856Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"78eWGYWsJtppeY+STzy92dUdMzXfEy+a7BIhtNJirQmBmRua1qaGoszfJVcoeU61N+rG5D9oSYwYxSzlHVQHBA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:15:00.768303Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.00974","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1dd96b168706cf84f55d92698d2c2eec20ad4886f36c8d3724f7da8fffb76f6b","sha256:3ea5ab7bcb7d9b2d4d65618a7c3759f6b5ba1931b3113d496991f88d15544d38"],"state_sha256":"5b0e4929794ab6c2143dae2fa66017b64cca55ea6002735fb33b9a0517b739a4"}