{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:I7NABJGANAFUXFLBVUYGD4PIUU","short_pith_number":"pith:I7NABJGA","schema_version":"1.0","canonical_sha256":"47da00a4c0680b4b9561ad3061f1e8a53ea27454f44c92fb1c46196cd2a9e176","source":{"kind":"arxiv","id":"2412.11919","version":1},"attestation_state":"computed","paper":{"title":"RetroLLM: Empowering Large Language Models to Retrieve Fine-grained Evidence within Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Jiajie Jin, Qi Ye, Xiaoxi Li, Yongkang Wu, Yujia Zhou, Zhicheng Dou, Zhonghua Li","submitted_at":"2024-12-16T16:03:25Z","abstract_excerpt":"Large language models (LLMs) exhibit remarkable generative capabilities but often suffer from hallucinations. Retrieval-augmented generation (RAG) offers an effective solution by incorporating external knowledge, but existing methods still face several limitations: additional deployment costs of separate retrievers, redundant input tokens from retrieved text chunks, and the lack of joint optimization of retrieval and generation. To address these issues, we propose \\textbf{RetroLLM}, a unified framework that integrates retrieval and generation into a single, cohesive process, enabling LLMs to d"},"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":"2412.11919","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-16T16:03:25Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"373badaf413c997d09ed4b9897caa6e6f16d724fa36643114e4913d945697fc1","abstract_canon_sha256":"6edb31ca32583732564f03442578d2161a842f12c9ffd13cc03ab53cf00dae69"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:53.523074Z","signature_b64":"4Fe4mljV7qa1PC5rvqKr4XrogXx6JgiF5GQg1FS+dHWM92L1iQ06BGHzSiIoT6aFB5aPn+NB3z3ht58y947KAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47da00a4c0680b4b9561ad3061f1e8a53ea27454f44c92fb1c46196cd2a9e176","last_reissued_at":"2026-07-05T09:49:53.522565Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:53.522565Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RetroLLM: Empowering Large Language Models to Retrieve Fine-grained Evidence within Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Jiajie Jin, Qi Ye, Xiaoxi Li, Yongkang Wu, Yujia Zhou, Zhicheng Dou, Zhonghua Li","submitted_at":"2024-12-16T16:03:25Z","abstract_excerpt":"Large language models (LLMs) exhibit remarkable generative capabilities but often suffer from hallucinations. Retrieval-augmented generation (RAG) offers an effective solution by incorporating external knowledge, but existing methods still face several limitations: additional deployment costs of separate retrievers, redundant input tokens from retrieved text chunks, and the lack of joint optimization of retrieval and generation. To address these issues, we propose \\textbf{RetroLLM}, a unified framework that integrates retrieval and generation into a single, cohesive process, enabling LLMs to d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11919","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/2412.11919/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":"2412.11919","created_at":"2026-07-05T09:49:53.522629+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.11919v1","created_at":"2026-07-05T09:49:53.522629+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11919","created_at":"2026-07-05T09:49:53.522629+00:00"},{"alias_kind":"pith_short_12","alias_value":"I7NABJGANAFU","created_at":"2026-07-05T09:49:53.522629+00:00"},{"alias_kind":"pith_short_16","alias_value":"I7NABJGANAFUXFLB","created_at":"2026-07-05T09:49:53.522629+00:00"},{"alias_kind":"pith_short_8","alias_value":"I7NABJGA","created_at":"2026-07-05T09:49:53.522629+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2505.04588","citing_title":"ZeroSearch: Incentivize the Search Capability of LLMs without Searching","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2505.04588","citing_title":"ZeroSearch: Incentivize the Search Capability of LLMs without Searching","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2501.05366","citing_title":"Search-o1: Agentic Search-Enhanced Large Reasoning Models","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I7NABJGANAFUXFLBVUYGD4PIUU","json":"https://pith.science/pith/I7NABJGANAFUXFLBVUYGD4PIUU.json","graph_json":"https://pith.science/api/pith-number/I7NABJGANAFUXFLBVUYGD4PIUU/graph.json","events_json":"https://pith.science/api/pith-number/I7NABJGANAFUXFLBVUYGD4PIUU/events.json","paper":"https://pith.science/paper/I7NABJGA"},"agent_actions":{"view_html":"https://pith.science/pith/I7NABJGANAFUXFLBVUYGD4PIUU","download_json":"https://pith.science/pith/I7NABJGANAFUXFLBVUYGD4PIUU.json","view_paper":"https://pith.science/paper/I7NABJGA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.11919&json=true","fetch_graph":"https://pith.science/api/pith-number/I7NABJGANAFUXFLBVUYGD4PIUU/graph.json","fetch_events":"https://pith.science/api/pith-number/I7NABJGANAFUXFLBVUYGD4PIUU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I7NABJGANAFUXFLBVUYGD4PIUU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I7NABJGANAFUXFLBVUYGD4PIUU/action/storage_attestation","attest_author":"https://pith.science/pith/I7NABJGANAFUXFLBVUYGD4PIUU/action/author_attestation","sign_citation":"https://pith.science/pith/I7NABJGANAFUXFLBVUYGD4PIUU/action/citation_signature","submit_replication":"https://pith.science/pith/I7NABJGANAFUXFLBVUYGD4PIUU/action/replication_record"}},"created_at":"2026-07-05T09:49:53.522629+00:00","updated_at":"2026-07-05T09:49:53.522629+00:00"}