{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GYCJRBBS6NCATWDQXOWPGDF57Q","short_pith_number":"pith:GYCJRBBS","schema_version":"1.0","canonical_sha256":"3604988432f34409d870bbacf30cbdfc0f53d12d7020be46db2a7de9f8b99a41","source":{"kind":"arxiv","id":"2505.03075","version":1},"attestation_state":"computed","paper":{"title":"Direct Retrieval-augmented Optimization: Synergizing Knowledge Selection and Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Dawei Yin, Lingyong Yan, Maarten de Rijke, Pengjie Ren, Shuaiqiang Wang, Weiwei Sun, Xinyu Ma, Yue Feng, Zhaochun Ren, Zhengliang Shi","submitted_at":"2025-05-05T23:54:53Z","abstract_excerpt":"Retrieval-augmented generation (RAG) integrates large language models ( LLM s) with retrievers to access external knowledge, improving the factuality of LLM generation in knowledge-grounded tasks. To optimize the RAG performance, most previous work independently fine-tunes the retriever to adapt to frozen LLM s or trains the LLMs to use documents retrieved by off-the-shelf retrievers, lacking end-to-end training supervision. Recent work addresses this limitation by jointly training these two components but relies on overly simplifying assumptions of document independence, which has been critic"},"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":"2505.03075","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-05-05T23:54:53Z","cross_cats_sorted":[],"title_canon_sha256":"322ec1ddf40d09b577bbff20971cff9ae6e1d29923b4225e13b91dbda835cd97","abstract_canon_sha256":"4cdb9a100d1256e4b54465fa7366d39809a1a68741139379a2393a0a6307adfc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:58:52.254198Z","signature_b64":"2PwWEWM2gprU34+DJZFfPJURBCP0653PtxIE8iYj4qXmp9HitEjL6WyJ34FhcAng1ycScJ1/j4mbVnrqu3UKAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3604988432f34409d870bbacf30cbdfc0f53d12d7020be46db2a7de9f8b99a41","last_reissued_at":"2026-07-05T10:58:52.253707Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:58:52.253707Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Direct Retrieval-augmented Optimization: Synergizing Knowledge Selection and Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Dawei Yin, Lingyong Yan, Maarten de Rijke, Pengjie Ren, Shuaiqiang Wang, Weiwei Sun, Xinyu Ma, Yue Feng, Zhaochun Ren, Zhengliang Shi","submitted_at":"2025-05-05T23:54:53Z","abstract_excerpt":"Retrieval-augmented generation (RAG) integrates large language models ( LLM s) with retrievers to access external knowledge, improving the factuality of LLM generation in knowledge-grounded tasks. To optimize the RAG performance, most previous work independently fine-tunes the retriever to adapt to frozen LLM s or trains the LLMs to use documents retrieved by off-the-shelf retrievers, lacking end-to-end training supervision. Recent work addresses this limitation by jointly training these two components but relies on overly simplifying assumptions of document independence, which has been critic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.03075","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/2505.03075/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":"2505.03075","created_at":"2026-07-05T10:58:52.253761+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.03075v1","created_at":"2026-07-05T10:58:52.253761+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.03075","created_at":"2026-07-05T10:58:52.253761+00:00"},{"alias_kind":"pith_short_12","alias_value":"GYCJRBBS6NCA","created_at":"2026-07-05T10:58:52.253761+00:00"},{"alias_kind":"pith_short_16","alias_value":"GYCJRBBS6NCATWDQ","created_at":"2026-07-05T10:58:52.253761+00:00"},{"alias_kind":"pith_short_8","alias_value":"GYCJRBBS","created_at":"2026-07-05T10:58:52.253761+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.03986","citing_title":"From Intent to Execution: Composing Agentic Workflows with Agent Recommendation","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18026","citing_title":"RASP-Tuner: Retrieval-Augmented Soft Prompts for Context-Aware Black-Box Optimization in Non-Stationary Environments","ref_index":59,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GYCJRBBS6NCATWDQXOWPGDF57Q","json":"https://pith.science/pith/GYCJRBBS6NCATWDQXOWPGDF57Q.json","graph_json":"https://pith.science/api/pith-number/GYCJRBBS6NCATWDQXOWPGDF57Q/graph.json","events_json":"https://pith.science/api/pith-number/GYCJRBBS6NCATWDQXOWPGDF57Q/events.json","paper":"https://pith.science/paper/GYCJRBBS"},"agent_actions":{"view_html":"https://pith.science/pith/GYCJRBBS6NCATWDQXOWPGDF57Q","download_json":"https://pith.science/pith/GYCJRBBS6NCATWDQXOWPGDF57Q.json","view_paper":"https://pith.science/paper/GYCJRBBS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.03075&json=true","fetch_graph":"https://pith.science/api/pith-number/GYCJRBBS6NCATWDQXOWPGDF57Q/graph.json","fetch_events":"https://pith.science/api/pith-number/GYCJRBBS6NCATWDQXOWPGDF57Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GYCJRBBS6NCATWDQXOWPGDF57Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GYCJRBBS6NCATWDQXOWPGDF57Q/action/storage_attestation","attest_author":"https://pith.science/pith/GYCJRBBS6NCATWDQXOWPGDF57Q/action/author_attestation","sign_citation":"https://pith.science/pith/GYCJRBBS6NCATWDQXOWPGDF57Q/action/citation_signature","submit_replication":"https://pith.science/pith/GYCJRBBS6NCATWDQXOWPGDF57Q/action/replication_record"}},"created_at":"2026-07-05T10:58:52.253761+00:00","updated_at":"2026-07-05T10:58:52.253761+00:00"}