{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LQK42CWT66FWZR42H2KFI5GJDQ","short_pith_number":"pith:LQK42CWT","schema_version":"1.0","canonical_sha256":"5c15cd0ad3f78b6cc79a3e945474c91c1dbfef530cf4a41a6f86405ce80c1dcc","source":{"kind":"arxiv","id":"2605.17691","version":1},"attestation_state":"computed","paper":{"title":"Validate Your Authority: Benchmarking LLMs on Multi-Label Precedent Treatment Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"M. Abdullah Canbaz, M. Mikail Demir","submitted_at":"2026-05-17T23:15:27Z","abstract_excerpt":"Automating the classification of negative treatment in legal precedent is a critical yet nuanced NLP task where misclassification carries significant risk. To address the shortcomings of standard accuracy, this paper introduces a more robust evaluation framework. We benchmark modern Large Language Models on a new, expert-annotated dataset of 239 real-world legal citations and propose a novel Average Severity Error metric to better measure the practical impact of classification errors. Our experiments reveal a performance split. Google's Gemini 2.5 Flash achieved the highest accuracy on a high-"},"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":"2605.17691","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-17T23:15:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a1086ad253d06f29a6d87e9b4655a03232972aa8193f952a477d7c6ae3189111","abstract_canon_sha256":"aeb02fb0e518b4459a797654ebdd8469ecbf2f2bd49534252f74eac3630d4db5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:53.031892Z","signature_b64":"Wv9lKhHPmpLl3Ue1h6M7SxVdMFlDYcWgZ383l5ydo7RygzeM7pBz/y07d+EhJqJPpTP70Ey9Gb94Y4Hg8VyHBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c15cd0ad3f78b6cc79a3e945474c91c1dbfef530cf4a41a6f86405ce80c1dcc","last_reissued_at":"2026-05-20T00:04:53.031042Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:53.031042Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Validate Your Authority: Benchmarking LLMs on Multi-Label Precedent Treatment Classification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"M. Abdullah Canbaz, M. Mikail Demir","submitted_at":"2026-05-17T23:15:27Z","abstract_excerpt":"Automating the classification of negative treatment in legal precedent is a critical yet nuanced NLP task where misclassification carries significant risk. To address the shortcomings of standard accuracy, this paper introduces a more robust evaluation framework. We benchmark modern Large Language Models on a new, expert-annotated dataset of 239 real-world legal citations and propose a novel Average Severity Error metric to better measure the practical impact of classification errors. Our experiments reveal a performance split. Google's Gemini 2.5 Flash achieved the highest accuracy on a high-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17691","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/2605.17691/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"cited_work_retraction","ran_at":"2026-05-19T21:51:57.629375Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"shingle_duplication","ran_at":"2026-05-19T21:49:43.949542Z","status":"skipped","version":"0.1.0","findings_count":0},{"name":"citation_quote_validity","ran_at":"2026-05-19T21:49:43.748452Z","status":"skipped","version":"0.1.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T21:33:23.521568Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T21:21:57.431740Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"96feeefa5dd04c785c186df370d5ffb19504a89d630dd0ae736859729b8d70b1"},"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":"2605.17691","created_at":"2026-05-20T00:04:53.031181+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.17691v1","created_at":"2026-05-20T00:04:53.031181+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17691","created_at":"2026-05-20T00:04:53.031181+00:00"},{"alias_kind":"pith_short_12","alias_value":"LQK42CWT66FW","created_at":"2026-05-20T00:04:53.031181+00:00"},{"alias_kind":"pith_short_16","alias_value":"LQK42CWT66FWZR42","created_at":"2026-05-20T00:04:53.031181+00:00"},{"alias_kind":"pith_short_8","alias_value":"LQK42CWT","created_at":"2026-05-20T00:04:53.031181+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/LQK42CWT66FWZR42H2KFI5GJDQ","json":"https://pith.science/pith/LQK42CWT66FWZR42H2KFI5GJDQ.json","graph_json":"https://pith.science/api/pith-number/LQK42CWT66FWZR42H2KFI5GJDQ/graph.json","events_json":"https://pith.science/api/pith-number/LQK42CWT66FWZR42H2KFI5GJDQ/events.json","paper":"https://pith.science/paper/LQK42CWT"},"agent_actions":{"view_html":"https://pith.science/pith/LQK42CWT66FWZR42H2KFI5GJDQ","download_json":"https://pith.science/pith/LQK42CWT66FWZR42H2KFI5GJDQ.json","view_paper":"https://pith.science/paper/LQK42CWT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.17691&json=true","fetch_graph":"https://pith.science/api/pith-number/LQK42CWT66FWZR42H2KFI5GJDQ/graph.json","fetch_events":"https://pith.science/api/pith-number/LQK42CWT66FWZR42H2KFI5GJDQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LQK42CWT66FWZR42H2KFI5GJDQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LQK42CWT66FWZR42H2KFI5GJDQ/action/storage_attestation","attest_author":"https://pith.science/pith/LQK42CWT66FWZR42H2KFI5GJDQ/action/author_attestation","sign_citation":"https://pith.science/pith/LQK42CWT66FWZR42H2KFI5GJDQ/action/citation_signature","submit_replication":"https://pith.science/pith/LQK42CWT66FWZR42H2KFI5GJDQ/action/replication_record"}},"created_at":"2026-05-20T00:04:53.031181+00:00","updated_at":"2026-05-20T00:04:53.031181+00:00"}