{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YN3MVNQ6J4IQ4MZTW3FB257SMN","short_pith_number":"pith:YN3MVNQ6","schema_version":"1.0","canonical_sha256":"c376cab61e4f110e3333b6ca1d77f2635819a2b8cdec654e938de1789819b873","source":{"kind":"arxiv","id":"2409.09046","version":2},"attestation_state":"computed","paper":{"title":"HyPA-RAG: A Hybrid Parameter Adaptive Retrieval-Augmented Generation System for AI Legal and Policy Applications","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.IR","authors_text":"Adriano Koshiyama, Airlie Hilliard, Ayesha Gulley, Philip Treleaven, Rishi Kalra, Xin Guan, Zekun Wu","submitted_at":"2024-08-29T16:11:20Z","abstract_excerpt":"Large Language Models (LLMs) face limitations in AI legal and policy applications due to outdated knowledge, hallucinations, and poor reasoning in complex contexts. Retrieval-Augmented Generation (RAG) systems address these issues by incorporating external knowledge, but suffer from retrieval errors, ineffective context integration, and high operational costs. This paper presents the Hybrid Parameter-Adaptive RAG (HyPA-RAG) system, designed for the AI legal domain, with NYC Local Law 144 (LL144) as the test case. HyPA-RAG integrates a query complexity classifier for adaptive parameter tuning, "},"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":"2409.09046","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2024-08-29T16:11:20Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"3ec402b6de7b4e9edd0e2b6a426b222caff26275febafe3b522ab9f5f64f4be2","abstract_canon_sha256":"5ad9298f0aee22b878604937ab554170b90dffb5de1958f51cf4a3a1f7d36021"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:19:28.283102Z","signature_b64":"uQRJCH/oy9PNKlKu1e32WdhG1CVXuT2gI4hwYqc2ynHcBJ7xCzBZaiRwoJVDpirdjudbdZCKCTqHSdIPkVtUDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c376cab61e4f110e3333b6ca1d77f2635819a2b8cdec654e938de1789819b873","last_reissued_at":"2026-07-05T10:19:28.282521Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:19:28.282521Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HyPA-RAG: A Hybrid Parameter Adaptive Retrieval-Augmented Generation System for AI Legal and Policy Applications","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.IR","authors_text":"Adriano Koshiyama, Airlie Hilliard, Ayesha Gulley, Philip Treleaven, Rishi Kalra, Xin Guan, Zekun Wu","submitted_at":"2024-08-29T16:11:20Z","abstract_excerpt":"Large Language Models (LLMs) face limitations in AI legal and policy applications due to outdated knowledge, hallucinations, and poor reasoning in complex contexts. Retrieval-Augmented Generation (RAG) systems address these issues by incorporating external knowledge, but suffer from retrieval errors, ineffective context integration, and high operational costs. This paper presents the Hybrid Parameter-Adaptive RAG (HyPA-RAG) system, designed for the AI legal domain, with NYC Local Law 144 (LL144) as the test case. HyPA-RAG integrates a query complexity classifier for adaptive parameter tuning, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.09046","kind":"arxiv","version":2},"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/2409.09046/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":"2409.09046","created_at":"2026-07-05T10:19:28.282599+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.09046v2","created_at":"2026-07-05T10:19:28.282599+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.09046","created_at":"2026-07-05T10:19:28.282599+00:00"},{"alias_kind":"pith_short_12","alias_value":"YN3MVNQ6J4IQ","created_at":"2026-07-05T10:19:28.282599+00:00"},{"alias_kind":"pith_short_16","alias_value":"YN3MVNQ6J4IQ4MZT","created_at":"2026-07-05T10:19:28.282599+00:00"},{"alias_kind":"pith_short_8","alias_value":"YN3MVNQ6","created_at":"2026-07-05T10:19:28.282599+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.09003","citing_title":"Orchestration for Domain-specific Edge-Cloud Language Models","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YN3MVNQ6J4IQ4MZTW3FB257SMN","json":"https://pith.science/pith/YN3MVNQ6J4IQ4MZTW3FB257SMN.json","graph_json":"https://pith.science/api/pith-number/YN3MVNQ6J4IQ4MZTW3FB257SMN/graph.json","events_json":"https://pith.science/api/pith-number/YN3MVNQ6J4IQ4MZTW3FB257SMN/events.json","paper":"https://pith.science/paper/YN3MVNQ6"},"agent_actions":{"view_html":"https://pith.science/pith/YN3MVNQ6J4IQ4MZTW3FB257SMN","download_json":"https://pith.science/pith/YN3MVNQ6J4IQ4MZTW3FB257SMN.json","view_paper":"https://pith.science/paper/YN3MVNQ6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.09046&json=true","fetch_graph":"https://pith.science/api/pith-number/YN3MVNQ6J4IQ4MZTW3FB257SMN/graph.json","fetch_events":"https://pith.science/api/pith-number/YN3MVNQ6J4IQ4MZTW3FB257SMN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YN3MVNQ6J4IQ4MZTW3FB257SMN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YN3MVNQ6J4IQ4MZTW3FB257SMN/action/storage_attestation","attest_author":"https://pith.science/pith/YN3MVNQ6J4IQ4MZTW3FB257SMN/action/author_attestation","sign_citation":"https://pith.science/pith/YN3MVNQ6J4IQ4MZTW3FB257SMN/action/citation_signature","submit_replication":"https://pith.science/pith/YN3MVNQ6J4IQ4MZTW3FB257SMN/action/replication_record"}},"created_at":"2026-07-05T10:19:28.282599+00:00","updated_at":"2026-07-05T10:19:28.282599+00:00"}