{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:BRUKXP6KBL7CSIMGF2PDGGWGW3","short_pith_number":"pith:BRUKXP6K","schema_version":"1.0","canonical_sha256":"0c68abbfca0afe2921862e9e331ac6b6d550a27f0f7d33ad35a63f295cd0f6f4","source":{"kind":"arxiv","id":"2403.15450","version":1},"attestation_state":"computed","paper":{"title":"Loops On Retrieval Augmented Generation (LoRAG)","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Ayush Thakur, Rashmi Vashisth","submitted_at":"2024-03-18T15:19:17Z","abstract_excerpt":"This paper presents Loops On Retrieval Augmented Generation (LoRAG), a new framework designed to enhance the quality of retrieval-augmented text generation through the incorporation of an iterative loop mechanism. The architecture integrates a generative model, a retrieval mechanism, and a dynamic loop module, allowing for iterative refinement of the generated text through interactions with relevant information retrieved from the input context. Experimental evaluations on benchmark datasets demonstrate that LoRAG surpasses existing state-of-the-art models in terms of BLEU score, ROUGE score, a"},"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":"2403.15450","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-18T15:19:17Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"e5468b7454564830f031005a2763fffd6f4ae2bbc5327b86319702845ee26f5a","abstract_canon_sha256":"22f05a3599c2a2b64730954abc9cdd8524b359b28c338b908ae0607d82f777ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:59:37.221572Z","signature_b64":"+7eZMlaTLFyM16v9cMkEj4AkZd94JE2Q4xZfC05FdmZq3Tl1ZJWwhfjIv3JsMnpEF7skPC95njK3yVXxUDOlBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c68abbfca0afe2921862e9e331ac6b6d550a27f0f7d33ad35a63f295cd0f6f4","last_reissued_at":"2026-07-05T07:59:37.221071Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:59:37.221071Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Loops On Retrieval Augmented Generation (LoRAG)","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Ayush Thakur, Rashmi Vashisth","submitted_at":"2024-03-18T15:19:17Z","abstract_excerpt":"This paper presents Loops On Retrieval Augmented Generation (LoRAG), a new framework designed to enhance the quality of retrieval-augmented text generation through the incorporation of an iterative loop mechanism. The architecture integrates a generative model, a retrieval mechanism, and a dynamic loop module, allowing for iterative refinement of the generated text through interactions with relevant information retrieved from the input context. Experimental evaluations on benchmark datasets demonstrate that LoRAG surpasses existing state-of-the-art models in terms of BLEU score, ROUGE score, a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.15450","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/2403.15450/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":"2403.15450","created_at":"2026-07-05T07:59:37.221134+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.15450v1","created_at":"2026-07-05T07:59:37.221134+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.15450","created_at":"2026-07-05T07:59:37.221134+00:00"},{"alias_kind":"pith_short_12","alias_value":"BRUKXP6KBL7C","created_at":"2026-07-05T07:59:37.221134+00:00"},{"alias_kind":"pith_short_16","alias_value":"BRUKXP6KBL7CSIMG","created_at":"2026-07-05T07:59:37.221134+00:00"},{"alias_kind":"pith_short_8","alias_value":"BRUKXP6K","created_at":"2026-07-05T07:59:37.221134+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.01302","citing_title":"Beyond Semantic Relevance: Counterfactual Risk Minimization for Robust Retrieval-Augmented Generation","ref_index":71,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BRUKXP6KBL7CSIMGF2PDGGWGW3","json":"https://pith.science/pith/BRUKXP6KBL7CSIMGF2PDGGWGW3.json","graph_json":"https://pith.science/api/pith-number/BRUKXP6KBL7CSIMGF2PDGGWGW3/graph.json","events_json":"https://pith.science/api/pith-number/BRUKXP6KBL7CSIMGF2PDGGWGW3/events.json","paper":"https://pith.science/paper/BRUKXP6K"},"agent_actions":{"view_html":"https://pith.science/pith/BRUKXP6KBL7CSIMGF2PDGGWGW3","download_json":"https://pith.science/pith/BRUKXP6KBL7CSIMGF2PDGGWGW3.json","view_paper":"https://pith.science/paper/BRUKXP6K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.15450&json=true","fetch_graph":"https://pith.science/api/pith-number/BRUKXP6KBL7CSIMGF2PDGGWGW3/graph.json","fetch_events":"https://pith.science/api/pith-number/BRUKXP6KBL7CSIMGF2PDGGWGW3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BRUKXP6KBL7CSIMGF2PDGGWGW3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BRUKXP6KBL7CSIMGF2PDGGWGW3/action/storage_attestation","attest_author":"https://pith.science/pith/BRUKXP6KBL7CSIMGF2PDGGWGW3/action/author_attestation","sign_citation":"https://pith.science/pith/BRUKXP6KBL7CSIMGF2PDGGWGW3/action/citation_signature","submit_replication":"https://pith.science/pith/BRUKXP6KBL7CSIMGF2PDGGWGW3/action/replication_record"}},"created_at":"2026-07-05T07:59:37.221134+00:00","updated_at":"2026-07-05T07:59:37.221134+00:00"}