{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Y7WDCT2XWTP7IWFF432DKVC5V2","short_pith_number":"pith:Y7WDCT2X","schema_version":"1.0","canonical_sha256":"c7ec314f57b4dff458a5e6f435545daea74b66e626730c81ef714a35de8855a3","source":{"kind":"arxiv","id":"2410.07551","version":1},"attestation_state":"computed","paper":{"title":"KRAG Framework for Enhancing LLMs in the Legal Domain","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ken Satoh, Nguyen Ha Thanh","submitted_at":"2024-10-10T02:48:06Z","abstract_excerpt":"This paper introduces Knowledge Representation Augmented Generation (KRAG), a novel framework designed to enhance the capabilities of Large Language Models (LLMs) within domain-specific applications. KRAG points to the strategic inclusion of critical knowledge entities and relationships that are typically absent in standard data sets and which LLMs do not inherently learn. In the context of legal applications, we present Soft PROLEG, an implementation model under KRAG, which uses inference graphs to aid LLMs in delivering structured legal reasoning, argumentation, and explanations tailored to "},"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":"2410.07551","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-10-10T02:48:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"43151fcf718e311e4dc3912c3873f929bc4a6c18b7a058205da14baf00c1f6a0","abstract_canon_sha256":"056c292ba162924a5a29ee21d2cc6e36da9d20d52824c239e4b7f6dfa6c0c2be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:18:39.583652Z","signature_b64":"H1m7lWu8RzFieRjumYJtuZGfQQ+JCr0lSNqb12LLxELVdrsuHcLp1xAR0cegP9WyBb/xHE89j7dA1q30F2/TCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7ec314f57b4dff458a5e6f435545daea74b66e626730c81ef714a35de8855a3","last_reissued_at":"2026-07-05T09:18:39.583092Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:18:39.583092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"KRAG Framework for Enhancing LLMs in the Legal Domain","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ken Satoh, Nguyen Ha Thanh","submitted_at":"2024-10-10T02:48:06Z","abstract_excerpt":"This paper introduces Knowledge Representation Augmented Generation (KRAG), a novel framework designed to enhance the capabilities of Large Language Models (LLMs) within domain-specific applications. KRAG points to the strategic inclusion of critical knowledge entities and relationships that are typically absent in standard data sets and which LLMs do not inherently learn. In the context of legal applications, we present Soft PROLEG, an implementation model under KRAG, which uses inference graphs to aid LLMs in delivering structured legal reasoning, argumentation, and explanations tailored to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.07551","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/2410.07551/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":"2410.07551","created_at":"2026-07-05T09:18:39.583152+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.07551v1","created_at":"2026-07-05T09:18:39.583152+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.07551","created_at":"2026-07-05T09:18:39.583152+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y7WDCT2XWTP7","created_at":"2026-07-05T09:18:39.583152+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y7WDCT2XWTP7IWFF","created_at":"2026-07-05T09:18:39.583152+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y7WDCT2X","created_at":"2026-07-05T09:18:39.583152+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/Y7WDCT2XWTP7IWFF432DKVC5V2","json":"https://pith.science/pith/Y7WDCT2XWTP7IWFF432DKVC5V2.json","graph_json":"https://pith.science/api/pith-number/Y7WDCT2XWTP7IWFF432DKVC5V2/graph.json","events_json":"https://pith.science/api/pith-number/Y7WDCT2XWTP7IWFF432DKVC5V2/events.json","paper":"https://pith.science/paper/Y7WDCT2X"},"agent_actions":{"view_html":"https://pith.science/pith/Y7WDCT2XWTP7IWFF432DKVC5V2","download_json":"https://pith.science/pith/Y7WDCT2XWTP7IWFF432DKVC5V2.json","view_paper":"https://pith.science/paper/Y7WDCT2X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.07551&json=true","fetch_graph":"https://pith.science/api/pith-number/Y7WDCT2XWTP7IWFF432DKVC5V2/graph.json","fetch_events":"https://pith.science/api/pith-number/Y7WDCT2XWTP7IWFF432DKVC5V2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y7WDCT2XWTP7IWFF432DKVC5V2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y7WDCT2XWTP7IWFF432DKVC5V2/action/storage_attestation","attest_author":"https://pith.science/pith/Y7WDCT2XWTP7IWFF432DKVC5V2/action/author_attestation","sign_citation":"https://pith.science/pith/Y7WDCT2XWTP7IWFF432DKVC5V2/action/citation_signature","submit_replication":"https://pith.science/pith/Y7WDCT2XWTP7IWFF432DKVC5V2/action/replication_record"}},"created_at":"2026-07-05T09:18:39.583152+00:00","updated_at":"2026-07-05T09:18:39.583152+00:00"}