{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WKDAOM7IRE7UXLK5HVMB6UCKBW","short_pith_number":"pith:WKDAOM7I","schema_version":"1.0","canonical_sha256":"b2860733e8893f4bad5d3d581f504a0d9374c632ff9720482fd6432365c74b4d","source":{"kind":"arxiv","id":"2605.24452","version":1},"attestation_state":"computed","paper":{"title":"Temporal Concept Drift in Legal Judgment Prediction: Neural Baselines Across Three Epochs of Ukrainian Court Decisions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Volodymyr Ovcharov","submitted_at":"2026-05-23T08:01:14Z","abstract_excerpt":"Legal NLP benchmarks evaluate models on randomly split data, implicitly assuming that legal language is stationary. We test this assumption by fine-tuning four transformer encoders -- XLM-RoBERTa (base and large) and their legal-domain variants -- on Ukrainian court decisions from three temporal epochs defined by geopolitical disruptions: pre-war (2008-2013), hybrid war (2014-2021), and full-scale invasion (2022-2026). Each model is trained on one epoch and evaluated on all three, producing a 3x3 cross-temporal generalization matrix. Four findings emerge. (1) Forward degradation is severe: mod"},"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":"2605.24452","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-23T08:01:14Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"2cd57f400fe6429e1196c02dcbec9e3d5beb52394e4556ec4e50665b9b557bba","abstract_canon_sha256":"10d85f8386f6059345b982cd0d253dfcc58df946235de2dfde1caffaa518b600"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:40.378825Z","signature_b64":"/o0D869cKeHba5gJe7UDT4uinO08BnKcz60TWlKy/GeQq9YNQ/Wy6AG/ZNhROubZ7ZzJgy9EN5L1NiU6YP4ZBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2860733e8893f4bad5d3d581f504a0d9374c632ff9720482fd6432365c74b4d","last_reissued_at":"2026-05-26T01:03:40.378007Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:40.378007Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Temporal Concept Drift in Legal Judgment Prediction: Neural Baselines Across Three Epochs of Ukrainian Court Decisions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Volodymyr Ovcharov","submitted_at":"2026-05-23T08:01:14Z","abstract_excerpt":"Legal NLP benchmarks evaluate models on randomly split data, implicitly assuming that legal language is stationary. We test this assumption by fine-tuning four transformer encoders -- XLM-RoBERTa (base and large) and their legal-domain variants -- on Ukrainian court decisions from three temporal epochs defined by geopolitical disruptions: pre-war (2008-2013), hybrid war (2014-2021), and full-scale invasion (2022-2026). Each model is trained on one epoch and evaluated on all three, producing a 3x3 cross-temporal generalization matrix. Four findings emerge. (1) Forward degradation is severe: mod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24452","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/2605.24452/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":"2605.24452","created_at":"2026-05-26T01:03:40.378157+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.24452v1","created_at":"2026-05-26T01:03:40.378157+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24452","created_at":"2026-05-26T01:03:40.378157+00:00"},{"alias_kind":"pith_short_12","alias_value":"WKDAOM7IRE7U","created_at":"2026-05-26T01:03:40.378157+00:00"},{"alias_kind":"pith_short_16","alias_value":"WKDAOM7IRE7UXLK5","created_at":"2026-05-26T01:03:40.378157+00:00"},{"alias_kind":"pith_short_8","alias_value":"WKDAOM7I","created_at":"2026-05-26T01:03:40.378157+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/WKDAOM7IRE7UXLK5HVMB6UCKBW","json":"https://pith.science/pith/WKDAOM7IRE7UXLK5HVMB6UCKBW.json","graph_json":"https://pith.science/api/pith-number/WKDAOM7IRE7UXLK5HVMB6UCKBW/graph.json","events_json":"https://pith.science/api/pith-number/WKDAOM7IRE7UXLK5HVMB6UCKBW/events.json","paper":"https://pith.science/paper/WKDAOM7I"},"agent_actions":{"view_html":"https://pith.science/pith/WKDAOM7IRE7UXLK5HVMB6UCKBW","download_json":"https://pith.science/pith/WKDAOM7IRE7UXLK5HVMB6UCKBW.json","view_paper":"https://pith.science/paper/WKDAOM7I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.24452&json=true","fetch_graph":"https://pith.science/api/pith-number/WKDAOM7IRE7UXLK5HVMB6UCKBW/graph.json","fetch_events":"https://pith.science/api/pith-number/WKDAOM7IRE7UXLK5HVMB6UCKBW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WKDAOM7IRE7UXLK5HVMB6UCKBW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WKDAOM7IRE7UXLK5HVMB6UCKBW/action/storage_attestation","attest_author":"https://pith.science/pith/WKDAOM7IRE7UXLK5HVMB6UCKBW/action/author_attestation","sign_citation":"https://pith.science/pith/WKDAOM7IRE7UXLK5HVMB6UCKBW/action/citation_signature","submit_replication":"https://pith.science/pith/WKDAOM7IRE7UXLK5HVMB6UCKBW/action/replication_record"}},"created_at":"2026-05-26T01:03:40.378157+00:00","updated_at":"2026-05-26T01:03:40.378157+00:00"}