{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3XCQZ7JJSQXOCW7SHIVRU4O3EQ","short_pith_number":"pith:3XCQZ7JJ","schema_version":"1.0","canonical_sha256":"ddc50cfd29942ee15bf23a2b1a71db2410a5a63d5302299c604e55740ba67147","source":{"kind":"arxiv","id":"2508.17862","version":1},"attestation_state":"computed","paper":{"title":"Retrieval Feedback Memory Enhancement Large Model Retrieval Generation Method","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Dianxi Shi, Jialu Zhou, Leqian Li, Mingyue Yang, Shaowu Yang, Songchang Jin, Xinyu Wei","submitted_at":"2025-08-25T10:13:02Z","abstract_excerpt":"Large Language Models (LLMs) have shown remarkable capabilities across diverse tasks, yet they face inherent limitations such as constrained parametric knowledge and high retraining costs. Retrieval-Augmented Generation (RAG) augments the generation process by retrieving externally stored knowledge absent from the models internal parameters. However, RAG methods face challenges such as information loss and redundant retrievals during multi-round queries, accompanying the difficulties in precisely characterizing knowledge gaps for complex tasks. To address these problems, we propose Retrieval F"},"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":"2508.17862","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-08-25T10:13:02Z","cross_cats_sorted":[],"title_canon_sha256":"a376e0eaccc4eed19153fd88fda8301e912a9b097ec6f9f0e7e7366df6582f93","abstract_canon_sha256":"bdac53ea6e53f749835e7c18fc6c9d87f8fb55107875a7695895fc6a0e7ec63b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:58:49.230310Z","signature_b64":"EHIDz/8drRvOU67k/c+minBq6cBHXi7X3NQeZP5QgIFrfBA08RhvtWgb0WKGTYxgWgleFfRQw7JnEvpoQjapBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ddc50cfd29942ee15bf23a2b1a71db2410a5a63d5302299c604e55740ba67147","last_reissued_at":"2026-07-05T11:58:49.229911Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:58:49.229911Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Retrieval Feedback Memory Enhancement Large Model Retrieval Generation Method","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Dianxi Shi, Jialu Zhou, Leqian Li, Mingyue Yang, Shaowu Yang, Songchang Jin, Xinyu Wei","submitted_at":"2025-08-25T10:13:02Z","abstract_excerpt":"Large Language Models (LLMs) have shown remarkable capabilities across diverse tasks, yet they face inherent limitations such as constrained parametric knowledge and high retraining costs. Retrieval-Augmented Generation (RAG) augments the generation process by retrieving externally stored knowledge absent from the models internal parameters. However, RAG methods face challenges such as information loss and redundant retrievals during multi-round queries, accompanying the difficulties in precisely characterizing knowledge gaps for complex tasks. To address these problems, we propose Retrieval F"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.17862","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/2508.17862/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":"2508.17862","created_at":"2026-07-05T11:58:49.229974+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.17862v1","created_at":"2026-07-05T11:58:49.229974+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.17862","created_at":"2026-07-05T11:58:49.229974+00:00"},{"alias_kind":"pith_short_12","alias_value":"3XCQZ7JJSQXO","created_at":"2026-07-05T11:58:49.229974+00:00"},{"alias_kind":"pith_short_16","alias_value":"3XCQZ7JJSQXOCW7S","created_at":"2026-07-05T11:58:49.229974+00:00"},{"alias_kind":"pith_short_8","alias_value":"3XCQZ7JJ","created_at":"2026-07-05T11:58:49.229974+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.01149","citing_title":"PATH-Bench: Path-Dependent Evaluation of Lifelong Agents","ref_index":45,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3XCQZ7JJSQXOCW7SHIVRU4O3EQ","json":"https://pith.science/pith/3XCQZ7JJSQXOCW7SHIVRU4O3EQ.json","graph_json":"https://pith.science/api/pith-number/3XCQZ7JJSQXOCW7SHIVRU4O3EQ/graph.json","events_json":"https://pith.science/api/pith-number/3XCQZ7JJSQXOCW7SHIVRU4O3EQ/events.json","paper":"https://pith.science/paper/3XCQZ7JJ"},"agent_actions":{"view_html":"https://pith.science/pith/3XCQZ7JJSQXOCW7SHIVRU4O3EQ","download_json":"https://pith.science/pith/3XCQZ7JJSQXOCW7SHIVRU4O3EQ.json","view_paper":"https://pith.science/paper/3XCQZ7JJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.17862&json=true","fetch_graph":"https://pith.science/api/pith-number/3XCQZ7JJSQXOCW7SHIVRU4O3EQ/graph.json","fetch_events":"https://pith.science/api/pith-number/3XCQZ7JJSQXOCW7SHIVRU4O3EQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3XCQZ7JJSQXOCW7SHIVRU4O3EQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3XCQZ7JJSQXOCW7SHIVRU4O3EQ/action/storage_attestation","attest_author":"https://pith.science/pith/3XCQZ7JJSQXOCW7SHIVRU4O3EQ/action/author_attestation","sign_citation":"https://pith.science/pith/3XCQZ7JJSQXOCW7SHIVRU4O3EQ/action/citation_signature","submit_replication":"https://pith.science/pith/3XCQZ7JJSQXOCW7SHIVRU4O3EQ/action/replication_record"}},"created_at":"2026-07-05T11:58:49.229974+00:00","updated_at":"2026-07-05T11:58:49.229974+00:00"}