{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DHA2AANDVEFUGYFI36C3MC5RZI","short_pith_number":"pith:DHA2AAND","schema_version":"1.0","canonical_sha256":"19c1a001a3a90b4360a8df85b60bb1ca0558de83fc565a85400cef74cf0d2404","source":{"kind":"arxiv","id":"2505.18247","version":3},"attestation_state":"computed","paper":{"title":"MetaGen Blended RAG: Unlocking Zero-Shot Precision for Specialized Domain Question-Answering","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Abhilasha Mangal, Kunal Sawarkar, Shivam R. Solanki","submitted_at":"2025-05-23T17:18:45Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) struggles with domain-specific enterprise datasets, often isolated behind firewalls and rich in complex, specialized terminology unseen by LLMs during pre-training. Semantic variability across domains like medicine, networking, or law hampers RAG's context precision, while fine-tuning solutions are costly, slow, and lack generalization as new data emerges. Achieving zero-shot precision with retrievers without fine-tuning still remains a key challenge. We introduce 'MetaGen Blended RAG', a novel enterprise search approach that enhances semantic retrievers th"},"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":"2505.18247","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-23T17:18:45Z","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"title_canon_sha256":"934459f644349221441071352b5cb5ced2d401fedb950852195188ba16b2148d","abstract_canon_sha256":"3ad819a1843b461cd45bfc53ea0ffd59a0b5b358ddcd2e4e3e644ea0cc4f967b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:48:49.214518Z","signature_b64":"1vpsr7yV4qLv7Fyj2nx22yLbvusHgMyFhAoFJdQemBupXIWYLbmXkK5mtSKNEMUDW+lFcvURtRoKOvl3j6FtDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19c1a001a3a90b4360a8df85b60bb1ca0558de83fc565a85400cef74cf0d2404","last_reissued_at":"2026-07-05T11:48:49.214058Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:48:49.214058Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MetaGen Blended RAG: Unlocking Zero-Shot Precision for Specialized Domain Question-Answering","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Abhilasha Mangal, Kunal Sawarkar, Shivam R. Solanki","submitted_at":"2025-05-23T17:18:45Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) struggles with domain-specific enterprise datasets, often isolated behind firewalls and rich in complex, specialized terminology unseen by LLMs during pre-training. Semantic variability across domains like medicine, networking, or law hampers RAG's context precision, while fine-tuning solutions are costly, slow, and lack generalization as new data emerges. Achieving zero-shot precision with retrievers without fine-tuning still remains a key challenge. We introduce 'MetaGen Blended RAG', a novel enterprise search approach that enhances semantic retrievers th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18247","kind":"arxiv","version":3},"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/2505.18247/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":"2505.18247","created_at":"2026-07-05T11:48:49.214115+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.18247v3","created_at":"2026-07-05T11:48:49.214115+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18247","created_at":"2026-07-05T11:48:49.214115+00:00"},{"alias_kind":"pith_short_12","alias_value":"DHA2AANDVEFU","created_at":"2026-07-05T11:48:49.214115+00:00"},{"alias_kind":"pith_short_16","alias_value":"DHA2AANDVEFUGYFI","created_at":"2026-07-05T11:48:49.214115+00:00"},{"alias_kind":"pith_short_8","alias_value":"DHA2AAND","created_at":"2026-07-05T11:48:49.214115+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/DHA2AANDVEFUGYFI36C3MC5RZI","json":"https://pith.science/pith/DHA2AANDVEFUGYFI36C3MC5RZI.json","graph_json":"https://pith.science/api/pith-number/DHA2AANDVEFUGYFI36C3MC5RZI/graph.json","events_json":"https://pith.science/api/pith-number/DHA2AANDVEFUGYFI36C3MC5RZI/events.json","paper":"https://pith.science/paper/DHA2AAND"},"agent_actions":{"view_html":"https://pith.science/pith/DHA2AANDVEFUGYFI36C3MC5RZI","download_json":"https://pith.science/pith/DHA2AANDVEFUGYFI36C3MC5RZI.json","view_paper":"https://pith.science/paper/DHA2AAND","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.18247&json=true","fetch_graph":"https://pith.science/api/pith-number/DHA2AANDVEFUGYFI36C3MC5RZI/graph.json","fetch_events":"https://pith.science/api/pith-number/DHA2AANDVEFUGYFI36C3MC5RZI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DHA2AANDVEFUGYFI36C3MC5RZI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DHA2AANDVEFUGYFI36C3MC5RZI/action/storage_attestation","attest_author":"https://pith.science/pith/DHA2AANDVEFUGYFI36C3MC5RZI/action/author_attestation","sign_citation":"https://pith.science/pith/DHA2AANDVEFUGYFI36C3MC5RZI/action/citation_signature","submit_replication":"https://pith.science/pith/DHA2AANDVEFUGYFI36C3MC5RZI/action/replication_record"}},"created_at":"2026-07-05T11:48:49.214115+00:00","updated_at":"2026-07-05T11:48:49.214115+00:00"}