{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SVYDKV72ULOLNWHYX27LMBT6UX","short_pith_number":"pith:SVYDKV72","schema_version":"1.0","canonical_sha256":"95703557faa2dcb6d8f8bebeb6067ea5e11e4fe0b68a7a234faeb4a27920ad89","source":{"kind":"arxiv","id":"2506.01954","version":1},"attestation_state":"computed","paper":{"title":"DRAG: Distilling RAG for SLMs from LLMs to Transfer Knowledge and Mitigate Hallucination via Evidence and Graph-based Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Aidar Myrzakhan, Hassaan Muhammad Khan, Jennifer Chen, Sondos Mahmoud Bsharat, Yaxin Luo, Zhiqiang Shen","submitted_at":"2025-06-02T17:59:51Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) methods have proven highly effective for tasks requiring factual consistency and robust knowledge retrieval. However, large-scale RAG systems consume significant computational resources and are prone to generating hallucinated content from Humans. In this work, we introduce $\\texttt{DRAG}$, a novel framework for distilling RAG knowledge from large-scale Language Models (LLMs) into small LMs (SLMs). Our approach leverages evidence- and knowledge graph-based distillation, ensuring that the distilled model retains critical factual knowledge while significantly"},"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":"2506.01954","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-02T17:59:51Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"0135501941a5ec85ffb1848d5a218cb3c1279b6fd54e378b4023dd5b74732d93","abstract_canon_sha256":"bf577c3fbab578eefed03ff2e0aff15965227e8a5091cbfff1551278f0209e27"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:22.048831Z","signature_b64":"mKEN509K9492aU5nTDjPukL0X0P0BQvXyzibyigubsd8yd7dm3B7qEKq+nxHoK56lFUWHKbYMM0frlWzkgt9AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95703557faa2dcb6d8f8bebeb6067ea5e11e4fe0b68a7a234faeb4a27920ad89","last_reissued_at":"2026-07-05T11:14:22.048408Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:22.048408Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DRAG: Distilling RAG for SLMs from LLMs to Transfer Knowledge and Mitigate Hallucination via Evidence and Graph-based Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Aidar Myrzakhan, Hassaan Muhammad Khan, Jennifer Chen, Sondos Mahmoud Bsharat, Yaxin Luo, Zhiqiang Shen","submitted_at":"2025-06-02T17:59:51Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) methods have proven highly effective for tasks requiring factual consistency and robust knowledge retrieval. However, large-scale RAG systems consume significant computational resources and are prone to generating hallucinated content from Humans. In this work, we introduce $\\texttt{DRAG}$, a novel framework for distilling RAG knowledge from large-scale Language Models (LLMs) into small LMs (SLMs). Our approach leverages evidence- and knowledge graph-based distillation, ensuring that the distilled model retains critical factual knowledge while significantly"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01954","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/2506.01954/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":"2506.01954","created_at":"2026-07-05T11:14:22.048459+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.01954v1","created_at":"2026-07-05T11:14:22.048459+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01954","created_at":"2026-07-05T11:14:22.048459+00:00"},{"alias_kind":"pith_short_12","alias_value":"SVYDKV72ULOL","created_at":"2026-07-05T11:14:22.048459+00:00"},{"alias_kind":"pith_short_16","alias_value":"SVYDKV72ULOLNWHY","created_at":"2026-07-05T11:14:22.048459+00:00"},{"alias_kind":"pith_short_8","alias_value":"SVYDKV72","created_at":"2026-07-05T11:14:22.048459+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/SVYDKV72ULOLNWHYX27LMBT6UX","json":"https://pith.science/pith/SVYDKV72ULOLNWHYX27LMBT6UX.json","graph_json":"https://pith.science/api/pith-number/SVYDKV72ULOLNWHYX27LMBT6UX/graph.json","events_json":"https://pith.science/api/pith-number/SVYDKV72ULOLNWHYX27LMBT6UX/events.json","paper":"https://pith.science/paper/SVYDKV72"},"agent_actions":{"view_html":"https://pith.science/pith/SVYDKV72ULOLNWHYX27LMBT6UX","download_json":"https://pith.science/pith/SVYDKV72ULOLNWHYX27LMBT6UX.json","view_paper":"https://pith.science/paper/SVYDKV72","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.01954&json=true","fetch_graph":"https://pith.science/api/pith-number/SVYDKV72ULOLNWHYX27LMBT6UX/graph.json","fetch_events":"https://pith.science/api/pith-number/SVYDKV72ULOLNWHYX27LMBT6UX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SVYDKV72ULOLNWHYX27LMBT6UX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SVYDKV72ULOLNWHYX27LMBT6UX/action/storage_attestation","attest_author":"https://pith.science/pith/SVYDKV72ULOLNWHYX27LMBT6UX/action/author_attestation","sign_citation":"https://pith.science/pith/SVYDKV72ULOLNWHYX27LMBT6UX/action/citation_signature","submit_replication":"https://pith.science/pith/SVYDKV72ULOLNWHYX27LMBT6UX/action/replication_record"}},"created_at":"2026-07-05T11:14:22.048459+00:00","updated_at":"2026-07-05T11:14:22.048459+00:00"}