{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RN7ZQPRLRKHBST47NXN2IMINNN","short_pith_number":"pith:RN7ZQPRL","schema_version":"1.0","canonical_sha256":"8b7f983e2b8a8e194f9f6ddba4310d6b78b283613041d7c2ae7e980309881a79","source":{"kind":"arxiv","id":"2606.09389","version":1},"attestation_state":"computed","paper":{"title":"LexRubric: A Rubric-Guided Diagnostic Benchmark for Open-Ended Legal Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Haitao Li, Jun Lin, Kaisong Song, Min Zhang, Qingyao Ai, Yifan Chen, Yiqun Liu, Yiran Hu, Yueyue Wu","submitted_at":"2026-06-08T12:04:47Z","abstract_excerpt":"As large language models (LLMs) are increasingly applied to real-world legal tasks, evaluating the reliability of their open-ended legal responses has become essential. These tasks require context-sensitive answers and allow little room for error, motivating fine-grained and diagnostic evaluation that can identify specific sources of response quality failures. We introduce LexRubric, a rubric-based benchmark for evaluating open-ended Chinese legal tasks. LexRubric contains 649 instances from legal consultation and judicial examination, which reflect both everyday legal needs and professional l"},"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":"2606.09389","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-08T12:04:47Z","cross_cats_sorted":[],"title_canon_sha256":"44e3a3b5f1be592989611bbd6012faf3db26cbb000df4b2c9655f6d9319edf2b","abstract_canon_sha256":"e1f877bafb55929e78cdd8679176c3cc768ca8c333f32ed38b3916d15e0c0a33"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:08:19.444570Z","signature_b64":"jOzB83AoG44277Ch+6+hAPZ6pBqJepuXIn1RxRFxpQquZlMiCjKq1oJfpGJmY+9P0IRA4axqujFzftCVrKucDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b7f983e2b8a8e194f9f6ddba4310d6b78b283613041d7c2ae7e980309881a79","last_reissued_at":"2026-06-09T02:08:19.443728Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:08:19.443728Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LexRubric: A Rubric-Guided Diagnostic Benchmark for Open-Ended Legal Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Haitao Li, Jun Lin, Kaisong Song, Min Zhang, Qingyao Ai, Yifan Chen, Yiqun Liu, Yiran Hu, Yueyue Wu","submitted_at":"2026-06-08T12:04:47Z","abstract_excerpt":"As large language models (LLMs) are increasingly applied to real-world legal tasks, evaluating the reliability of their open-ended legal responses has become essential. These tasks require context-sensitive answers and allow little room for error, motivating fine-grained and diagnostic evaluation that can identify specific sources of response quality failures. We introduce LexRubric, a rubric-based benchmark for evaluating open-ended Chinese legal tasks. LexRubric contains 649 instances from legal consultation and judicial examination, which reflect both everyday legal needs and professional l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09389","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/2606.09389/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":"2606.09389","created_at":"2026-06-09T02:08:19.443851+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.09389v1","created_at":"2026-06-09T02:08:19.443851+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09389","created_at":"2026-06-09T02:08:19.443851+00:00"},{"alias_kind":"pith_short_12","alias_value":"RN7ZQPRLRKHB","created_at":"2026-06-09T02:08:19.443851+00:00"},{"alias_kind":"pith_short_16","alias_value":"RN7ZQPRLRKHBST47","created_at":"2026-06-09T02:08:19.443851+00:00"},{"alias_kind":"pith_short_8","alias_value":"RN7ZQPRL","created_at":"2026-06-09T02:08:19.443851+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/RN7ZQPRLRKHBST47NXN2IMINNN","json":"https://pith.science/pith/RN7ZQPRLRKHBST47NXN2IMINNN.json","graph_json":"https://pith.science/api/pith-number/RN7ZQPRLRKHBST47NXN2IMINNN/graph.json","events_json":"https://pith.science/api/pith-number/RN7ZQPRLRKHBST47NXN2IMINNN/events.json","paper":"https://pith.science/paper/RN7ZQPRL"},"agent_actions":{"view_html":"https://pith.science/pith/RN7ZQPRLRKHBST47NXN2IMINNN","download_json":"https://pith.science/pith/RN7ZQPRLRKHBST47NXN2IMINNN.json","view_paper":"https://pith.science/paper/RN7ZQPRL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.09389&json=true","fetch_graph":"https://pith.science/api/pith-number/RN7ZQPRLRKHBST47NXN2IMINNN/graph.json","fetch_events":"https://pith.science/api/pith-number/RN7ZQPRLRKHBST47NXN2IMINNN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RN7ZQPRLRKHBST47NXN2IMINNN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RN7ZQPRLRKHBST47NXN2IMINNN/action/storage_attestation","attest_author":"https://pith.science/pith/RN7ZQPRLRKHBST47NXN2IMINNN/action/author_attestation","sign_citation":"https://pith.science/pith/RN7ZQPRLRKHBST47NXN2IMINNN/action/citation_signature","submit_replication":"https://pith.science/pith/RN7ZQPRLRKHBST47NXN2IMINNN/action/replication_record"}},"created_at":"2026-06-09T02:08:19.443851+00:00","updated_at":"2026-06-09T02:08:19.443851+00:00"}