{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TI2R6JQGX7GJUFDMUU7GSK3E5F","short_pith_number":"pith:TI2R6JQG","schema_version":"1.0","canonical_sha256":"9a351f2606bfcc9a146ca53e692b64e967edff471918a9a4d90fd31f03bf7111","source":{"kind":"arxiv","id":"2504.06271","version":1},"attestation_state":"computed","paper":{"title":"ER-RAG: Enhance RAG with ER-Based Unified Modeling of Heterogeneous Data Sources","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Bo Bai, Chaorui Zhang, Jiazun Chen, Jun Gao, Suifeng Zhao, Wei Han, Weipeng Jiang, Yikuan Xia, Yirui Zhan","submitted_at":"2025-03-02T06:21:56Z","abstract_excerpt":"Large language models (LLMs) excel in question-answering (QA) tasks, and retrieval-augmented generation (RAG) enhances their precision by incorporating external evidence from diverse sources like web pages, databases, and knowledge graphs. However, current RAG methods rely on agent-specific strategies for individual data sources, posing challenges low-resource or black-box environments and complicates operations when evidence is fragmented across sources. To address these limitations, we propose ER-RAG, a framework that unifies evidence integration across heterogeneous data sources using the E"},"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":"2504.06271","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-03-02T06:21:56Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"1b18d7ee5e9a3017f40d19cff0a69473a7c46bab6e041093050beda8c9317a0d","abstract_canon_sha256":"4b2af82e96ab9fbc38bb768db088629a91f413466ae2c173505332e4ae0050e0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:46:24.205037Z","signature_b64":"jIUUaokgcgQ+OI+hjw9XviwdRcqIySLDX7D6kgf1s4YKIWDpyh1YIYYuwUY9Ygtdo5MKlVl2yQNzvn2BCNOoBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a351f2606bfcc9a146ca53e692b64e967edff471918a9a4d90fd31f03bf7111","last_reissued_at":"2026-07-05T10:46:24.204461Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:46:24.204461Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ER-RAG: Enhance RAG with ER-Based Unified Modeling of Heterogeneous Data Sources","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.IR","authors_text":"Bo Bai, Chaorui Zhang, Jiazun Chen, Jun Gao, Suifeng Zhao, Wei Han, Weipeng Jiang, Yikuan Xia, Yirui Zhan","submitted_at":"2025-03-02T06:21:56Z","abstract_excerpt":"Large language models (LLMs) excel in question-answering (QA) tasks, and retrieval-augmented generation (RAG) enhances their precision by incorporating external evidence from diverse sources like web pages, databases, and knowledge graphs. However, current RAG methods rely on agent-specific strategies for individual data sources, posing challenges low-resource or black-box environments and complicates operations when evidence is fragmented across sources. To address these limitations, we propose ER-RAG, a framework that unifies evidence integration across heterogeneous data sources using the E"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.06271","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/2504.06271/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":"2504.06271","created_at":"2026-07-05T10:46:24.204518+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.06271v1","created_at":"2026-07-05T10:46:24.204518+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.06271","created_at":"2026-07-05T10:46:24.204518+00:00"},{"alias_kind":"pith_short_12","alias_value":"TI2R6JQGX7GJ","created_at":"2026-07-05T10:46:24.204518+00:00"},{"alias_kind":"pith_short_16","alias_value":"TI2R6JQGX7GJUFDM","created_at":"2026-07-05T10:46:24.204518+00:00"},{"alias_kind":"pith_short_8","alias_value":"TI2R6JQG","created_at":"2026-07-05T10:46:24.204518+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/TI2R6JQGX7GJUFDMUU7GSK3E5F","json":"https://pith.science/pith/TI2R6JQGX7GJUFDMUU7GSK3E5F.json","graph_json":"https://pith.science/api/pith-number/TI2R6JQGX7GJUFDMUU7GSK3E5F/graph.json","events_json":"https://pith.science/api/pith-number/TI2R6JQGX7GJUFDMUU7GSK3E5F/events.json","paper":"https://pith.science/paper/TI2R6JQG"},"agent_actions":{"view_html":"https://pith.science/pith/TI2R6JQGX7GJUFDMUU7GSK3E5F","download_json":"https://pith.science/pith/TI2R6JQGX7GJUFDMUU7GSK3E5F.json","view_paper":"https://pith.science/paper/TI2R6JQG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.06271&json=true","fetch_graph":"https://pith.science/api/pith-number/TI2R6JQGX7GJUFDMUU7GSK3E5F/graph.json","fetch_events":"https://pith.science/api/pith-number/TI2R6JQGX7GJUFDMUU7GSK3E5F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TI2R6JQGX7GJUFDMUU7GSK3E5F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TI2R6JQGX7GJUFDMUU7GSK3E5F/action/storage_attestation","attest_author":"https://pith.science/pith/TI2R6JQGX7GJUFDMUU7GSK3E5F/action/author_attestation","sign_citation":"https://pith.science/pith/TI2R6JQGX7GJUFDMUU7GSK3E5F/action/citation_signature","submit_replication":"https://pith.science/pith/TI2R6JQGX7GJUFDMUU7GSK3E5F/action/replication_record"}},"created_at":"2026-07-05T10:46:24.204518+00:00","updated_at":"2026-07-05T10:46:24.204518+00:00"}