{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:I7NABJGANAFUXFLBVUYGD4PIUU","short_pith_number":"pith:I7NABJGA","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"},"canonical_sha256":"47da00a4c0680b4b9561ad3061f1e8a53ea27454f44c92fb1c46196cd2a9e176","source":{"kind":"arxiv","id":"2412.11919","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.11919","created_at":"2026-07-05T09:49:53Z"},{"alias_kind":"arxiv_version","alias_value":"2412.11919v1","created_at":"2026-07-05T09:49:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11919","created_at":"2026-07-05T09:49:53Z"},{"alias_kind":"pith_short_12","alias_value":"I7NABJGANAFU","created_at":"2026-07-05T09:49:53Z"},{"alias_kind":"pith_short_16","alias_value":"I7NABJGANAFUXFLB","created_at":"2026-07-05T09:49:53Z"},{"alias_kind":"pith_short_8","alias_value":"I7NABJGA","created_at":"2026-07-05T09:49:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:I7NABJGANAFUXFLBVUYGD4PIUU","target":"record","payload":{"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"},"canonical_sha256":"47da00a4c0680b4b9561ad3061f1e8a53ea27454f44c92fb1c46196cd2a9e176","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"},"source_kind":"arxiv","source_id":"2412.11919","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:49:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I1x6AktTWOpz6QfB+U3fjTLgm9pcmiOfnQ0afRgwlAJFfOcskPt9cMhiyfuSqrhnsdxxl/jfehXdxxF1fps1AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T17:51:56.913124Z"},"content_sha256":"890d6069334472cc2549d75b7b5f9721a2e58b1a27b05d426514dcf6d0628071","schema_version":"1.0","event_id":"sha256:890d6069334472cc2549d75b7b5f9721a2e58b1a27b05d426514dcf6d0628071"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:I7NABJGANAFUXFLBVUYGD4PIUU","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:49:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ATQr9kfCx1fME8/HKahuasSjtNJgR0cNKbkdYsOcgcksOWJOyMLJdnIm7QKoDhg4Sk15dHPSGZaO2ybJ2r7FDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T17:51:56.914144Z"},"content_sha256":"0da026ccff4ac6dcaf2922c7f8fe63978afc793d3f8b606c6eabbbe3a9e150ad","schema_version":"1.0","event_id":"sha256:0da026ccff4ac6dcaf2922c7f8fe63978afc793d3f8b606c6eabbbe3a9e150ad"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/I7NABJGANAFUXFLBVUYGD4PIUU/bundle.json","state_url":"https://pith.science/pith/I7NABJGANAFUXFLBVUYGD4PIUU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/I7NABJGANAFUXFLBVUYGD4PIUU/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T17:51:56Z","links":{"resolver":"https://pith.science/pith/I7NABJGANAFUXFLBVUYGD4PIUU","bundle":"https://pith.science/pith/I7NABJGANAFUXFLBVUYGD4PIUU/bundle.json","state":"https://pith.science/pith/I7NABJGANAFUXFLBVUYGD4PIUU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/I7NABJGANAFUXFLBVUYGD4PIUU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:I7NABJGANAFUXFLBVUYGD4PIUU","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":"6edb31ca32583732564f03442578d2161a842f12c9ffd13cc03ab53cf00dae69","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-16T16:03:25Z","title_canon_sha256":"373badaf413c997d09ed4b9897caa6e6f16d724fa36643114e4913d945697fc1"},"schema_version":"1.0","source":{"id":"2412.11919","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.11919","created_at":"2026-07-05T09:49:53Z"},{"alias_kind":"arxiv_version","alias_value":"2412.11919v1","created_at":"2026-07-05T09:49:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11919","created_at":"2026-07-05T09:49:53Z"},{"alias_kind":"pith_short_12","alias_value":"I7NABJGANAFU","created_at":"2026-07-05T09:49:53Z"},{"alias_kind":"pith_short_16","alias_value":"I7NABJGANAFUXFLB","created_at":"2026-07-05T09:49:53Z"},{"alias_kind":"pith_short_8","alias_value":"I7NABJGA","created_at":"2026-07-05T09:49:53Z"}],"graph_snapshots":[{"event_id":"sha256:0da026ccff4ac6dcaf2922c7f8fe63978afc793d3f8b606c6eabbbe3a9e150ad","target":"graph","created_at":"2026-07-05T09:49:53Z","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/2412.11919/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jiajie Jin, Qi Ye, Xiaoxi Li, Yongkang Wu, Yujia Zhou, Zhicheng Dou, Zhonghua Li","cross_cats":["cs.AI","cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-16T16:03:25Z","title":"RetroLLM: Empowering Large Language Models to Retrieve Fine-grained Evidence within Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11919","kind":"arxiv","version":1},"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":"sha256:890d6069334472cc2549d75b7b5f9721a2e58b1a27b05d426514dcf6d0628071","target":"record","created_at":"2026-07-05T09:49:53Z","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":"6edb31ca32583732564f03442578d2161a842f12c9ffd13cc03ab53cf00dae69","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-16T16:03:25Z","title_canon_sha256":"373badaf413c997d09ed4b9897caa6e6f16d724fa36643114e4913d945697fc1"},"schema_version":"1.0","source":{"id":"2412.11919","kind":"arxiv","version":1}},"canonical_sha256":"47da00a4c0680b4b9561ad3061f1e8a53ea27454f44c92fb1c46196cd2a9e176","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"47da00a4c0680b4b9561ad3061f1e8a53ea27454f44c92fb1c46196cd2a9e176","first_computed_at":"2026-07-05T09:49:53.522565Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:49:53.522565Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4Fe4mljV7qa1PC5rvqKr4XrogXx6JgiF5GQg1FS+dHWM92L1iQ06BGHzSiIoT6aFB5aPn+NB3z3ht58y947KAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:49:53.523074Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.11919","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:890d6069334472cc2549d75b7b5f9721a2e58b1a27b05d426514dcf6d0628071","sha256:0da026ccff4ac6dcaf2922c7f8fe63978afc793d3f8b606c6eabbbe3a9e150ad"],"state_sha256":"636a52b04f81470193fcb17652904027396960ebae3a06048e9c739e0c8b09c6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R2jp3XLJKSC74PqCEsQG/lgCGEDvP9T2a7OwdQDkVnYq4jMfRRckDxW7TtUhsFxyuoil5i+h4s4wSEg6YQxGCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T17:51:56.920891Z","bundle_sha256":"6c1d80984cf7887d036c9e90e914604b23226c2455bccd52053b463800d9ce05"}}