{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LSOGNVMB3PE2JN24O6XW4SAYJL","short_pith_number":"pith:LSOGNVMB","schema_version":"1.0","canonical_sha256":"5c9c66d581dbc9a4b75c77af6e48184adb9f83622d6071757f4e002f8ee61654","source":{"kind":"arxiv","id":"2407.01964","version":4},"attestation_state":"computed","paper":{"title":"Enabling Discriminative Reasoning in LLMs for Legal Judgment Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenlong Deng, Kelong Mao, Yuyao Zhang, Zhicheng Dou","submitted_at":"2024-07-02T05:43:15Z","abstract_excerpt":"Legal judgment prediction is essential for enhancing judicial efficiency. In this work, we identify that existing large language models (LLMs) underperform in this domain due to challenges in understanding case complexities and distinguishing between similar charges. To adapt LLMs for effective legal judgment prediction, we introduce the Ask-Discriminate-Predict (ADAPT) reasoning framework inspired by human judicial reasoning. ADAPT involves decomposing case facts, discriminating among potential charges, and predicting the final judgment. We further enhance LLMs through fine-tuning with multi-"},"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":"2407.01964","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-02T05:43:15Z","cross_cats_sorted":[],"title_canon_sha256":"af246b2287e702f33550c08a183f17689872c63fe605ae155279b9f6252e71a8","abstract_canon_sha256":"d5e8dce0a0ba0565c30fe7f1f430628066cfef105f001997e389eeec86adc594"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:52:34.180047Z","signature_b64":"08tHEMQObn5VmiIk9twdhEFrZzK/2vQUuoMoAyXa79OLMl3xmHc0EHQYEFxmBSDjeFxfYtb/6FHkaRZwcGEaAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c9c66d581dbc9a4b75c77af6e48184adb9f83622d6071757f4e002f8ee61654","last_reissued_at":"2026-07-05T08:52:34.179536Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:52:34.179536Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enabling Discriminative Reasoning in LLMs for Legal Judgment Prediction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenlong Deng, Kelong Mao, Yuyao Zhang, Zhicheng Dou","submitted_at":"2024-07-02T05:43:15Z","abstract_excerpt":"Legal judgment prediction is essential for enhancing judicial efficiency. In this work, we identify that existing large language models (LLMs) underperform in this domain due to challenges in understanding case complexities and distinguishing between similar charges. To adapt LLMs for effective legal judgment prediction, we introduce the Ask-Discriminate-Predict (ADAPT) reasoning framework inspired by human judicial reasoning. ADAPT involves decomposing case facts, discriminating among potential charges, and predicting the final judgment. We further enhance LLMs through fine-tuning with multi-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.01964","kind":"arxiv","version":4},"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/2407.01964/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":"2407.01964","created_at":"2026-07-05T08:52:34.179603+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.01964v4","created_at":"2026-07-05T08:52:34.179603+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.01964","created_at":"2026-07-05T08:52:34.179603+00:00"},{"alias_kind":"pith_short_12","alias_value":"LSOGNVMB3PE2","created_at":"2026-07-05T08:52:34.179603+00:00"},{"alias_kind":"pith_short_16","alias_value":"LSOGNVMB3PE2JN24","created_at":"2026-07-05T08:52:34.179603+00:00"},{"alias_kind":"pith_short_8","alias_value":"LSOGNVMB","created_at":"2026-07-05T08:52:34.179603+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.29076","citing_title":"Structured Prompt Optimization Meets Reinforcement Learning for Global and Local Interpretability over Complex Text","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LSOGNVMB3PE2JN24O6XW4SAYJL","json":"https://pith.science/pith/LSOGNVMB3PE2JN24O6XW4SAYJL.json","graph_json":"https://pith.science/api/pith-number/LSOGNVMB3PE2JN24O6XW4SAYJL/graph.json","events_json":"https://pith.science/api/pith-number/LSOGNVMB3PE2JN24O6XW4SAYJL/events.json","paper":"https://pith.science/paper/LSOGNVMB"},"agent_actions":{"view_html":"https://pith.science/pith/LSOGNVMB3PE2JN24O6XW4SAYJL","download_json":"https://pith.science/pith/LSOGNVMB3PE2JN24O6XW4SAYJL.json","view_paper":"https://pith.science/paper/LSOGNVMB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.01964&json=true","fetch_graph":"https://pith.science/api/pith-number/LSOGNVMB3PE2JN24O6XW4SAYJL/graph.json","fetch_events":"https://pith.science/api/pith-number/LSOGNVMB3PE2JN24O6XW4SAYJL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LSOGNVMB3PE2JN24O6XW4SAYJL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LSOGNVMB3PE2JN24O6XW4SAYJL/action/storage_attestation","attest_author":"https://pith.science/pith/LSOGNVMB3PE2JN24O6XW4SAYJL/action/author_attestation","sign_citation":"https://pith.science/pith/LSOGNVMB3PE2JN24O6XW4SAYJL/action/citation_signature","submit_replication":"https://pith.science/pith/LSOGNVMB3PE2JN24O6XW4SAYJL/action/replication_record"}},"created_at":"2026-07-05T08:52:34.179603+00:00","updated_at":"2026-07-05T08:52:34.179603+00:00"}