{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XOFMGYIBTDWFYSAXQESJJNFI6X","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"28b9192b3ad33c2b6e0852859a499de196cf7932df7a72e83022f7431219e4d1","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-23T15:24:16Z","title_canon_sha256":"0d11bd6ce341cf6b5fcdd719f5bfca0984d9d156d10e40d415dd8951f72f1874"},"schema_version":"1.0","source":{"id":"2410.17952","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.17952","created_at":"2026-07-05T10:05:13Z"},{"alias_kind":"arxiv_version","alias_value":"2410.17952v2","created_at":"2026-07-05T10:05:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.17952","created_at":"2026-07-05T10:05:13Z"},{"alias_kind":"pith_short_12","alias_value":"XOFMGYIBTDWF","created_at":"2026-07-05T10:05:13Z"},{"alias_kind":"pith_short_16","alias_value":"XOFMGYIBTDWFYSAX","created_at":"2026-07-05T10:05:13Z"},{"alias_kind":"pith_short_8","alias_value":"XOFMGYIB","created_at":"2026-07-05T10:05:13Z"}],"graph_snapshots":[{"event_id":"sha256:7b482b44e52758fbc743d5c5dbba7f9f1b8b4dab78d415cc0543cf5eaec5b60e","target":"graph","created_at":"2026-07-05T10:05:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2410.17952/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Retrieval-augmented generation (RAG) enhances the question-answering (QA) abilities of large language models (LLMs) by integrating external knowledge. However, adapting general-purpose RAG systems to specialized fields such as science and medicine poses unique challenges due to distribution shifts and limited access to domain-specific data. To tackle this, we propose SimRAG, a self-training approach that equips the LLM with joint capabilities of question answering and question generation for domain adaptation. Our method first fine-tunes the LLM on instruction-following, question-answering, an","authors_text":"Carl Yang, Chen Luo, Hui Liu, Joyce C. Ho, Qi He, Ran Xu, Sreyashi Nag, Xianfeng Tang, Yang Li, Yaochen Xie, Zhenwei Dai","cross_cats":["cs.AI","cs.IR","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-23T15:24:16Z","title":"SimRAG: Self-Improving Retrieval-Augmented Generation for Adapting Large Language Models to Specialized Domains"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.17952","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b5368fd295dbd3ec897224ea33e27ca906b96449af19b9dd4d1d6b0f6f1ba146","target":"record","created_at":"2026-07-05T10:05:13Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"28b9192b3ad33c2b6e0852859a499de196cf7932df7a72e83022f7431219e4d1","cross_cats_sorted":["cs.AI","cs.IR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-23T15:24:16Z","title_canon_sha256":"0d11bd6ce341cf6b5fcdd719f5bfca0984d9d156d10e40d415dd8951f72f1874"},"schema_version":"1.0","source":{"id":"2410.17952","kind":"arxiv","version":2}},"canonical_sha256":"bb8ac3610198ec5c4817812494b4a8f5e5b0dd5ab6dfb2c9f8fb36c8dd024ed8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bb8ac3610198ec5c4817812494b4a8f5e5b0dd5ab6dfb2c9f8fb36c8dd024ed8","first_computed_at":"2026-07-05T10:05:13.928752Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:05:13.928752Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Jm0Gb2L6mdWJ8Kf8m8b7xsVNRBryaxHZyTE/bHP22XlZ+hiA5SzVFGU/szHPjS0X0dUn6LAHwk9lTIYVzNotDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:05:13.929374Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.17952","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b5368fd295dbd3ec897224ea33e27ca906b96449af19b9dd4d1d6b0f6f1ba146","sha256:7b482b44e52758fbc743d5c5dbba7f9f1b8b4dab78d415cc0543cf5eaec5b60e"],"state_sha256":"c9cc38136e0270676de1708ddcbe458644edc31ba7fa708701e24dbe65ddaabe"}