{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:PFZJSTZFREOEM4BPD76SF4IKCL","short_pith_number":"pith:PFZJSTZF","canonical_record":{"source":{"id":"2402.19473","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-29T18:59:01Z","cross_cats_sorted":[],"title_canon_sha256":"9e1255553cc92620ddda38ffb254a74f40b20f789a98f2df953ef94cf5c4c0ac","abstract_canon_sha256":"dd05be16be6a8078428a33cb6c7f10a637840084d1458463db62c00796e4d110"},"schema_version":"1.0"},"canonical_sha256":"7972994f25891c46702f1ffd22f10a12ea81c80ec2692339f4ca73dfaf63c5b5","source":{"kind":"arxiv","id":"2402.19473","version":6},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.19473","created_at":"2026-05-17T23:38:52Z"},{"alias_kind":"arxiv_version","alias_value":"2402.19473v6","created_at":"2026-05-17T23:38:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.19473","created_at":"2026-05-17T23:38:52Z"},{"alias_kind":"pith_short_12","alias_value":"PFZJSTZFREOE","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"PFZJSTZFREOEM4BP","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"PFZJSTZF","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:PFZJSTZFREOEM4BPD76SF4IKCL","target":"record","payload":{"canonical_record":{"source":{"id":"2402.19473","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-29T18:59:01Z","cross_cats_sorted":[],"title_canon_sha256":"9e1255553cc92620ddda38ffb254a74f40b20f789a98f2df953ef94cf5c4c0ac","abstract_canon_sha256":"dd05be16be6a8078428a33cb6c7f10a637840084d1458463db62c00796e4d110"},"schema_version":"1.0"},"canonical_sha256":"7972994f25891c46702f1ffd22f10a12ea81c80ec2692339f4ca73dfaf63c5b5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:52.444074Z","signature_b64":"Qn1b9iV2J5i4MFKqWAIltKE0vP1rRjHet8a4+DJANISHE3JvA5FsnDOFM9iixT0ARI9kKqbyePhMNXsUQtxdCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7972994f25891c46702f1ffd22f10a12ea81c80ec2692339f4ca73dfaf63c5b5","last_reissued_at":"2026-05-17T23:38:52.443477Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:52.443477Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.19473","source_version":6,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oQq9KTwotNVIMVbambO+jmN+8aVAhU4YiL7ay+tBfCUuef+Gz1FqKkAS0D/SQFHYJiwNXQLCEQ4QbUwYCWZwAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T05:22:40.040642Z"},"content_sha256":"42e05eb9a28fe61730452f130b2af2407ffc4dda015509efd4c76a86f38d86c9","schema_version":"1.0","event_id":"sha256:42e05eb9a28fe61730452f130b2af2407ffc4dda015509efd4c76a86f38d86c9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:PFZJSTZFREOEM4BPD76SF4IKCL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Retrieval-Augmented Generation for AI-Generated Content: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"RAG integrates retrieval into AI-generated content to pull relevant data and raise accuracy plus robustness.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Cui, Fangcheng Fu, Hailin Zhang, Jie Jiang, Ling Yang, Penghao Zhao, Qinhan Yu, Wentao Zhang, Yunteng Geng, Zhengren Wang","submitted_at":"2024-02-29T18:59:01Z","abstract_excerpt":"Advancements in model algorithms, the growth of foundational models, and access to high-quality datasets have propelled the evolution of Artificial Intelligence Generated Content (AIGC). Despite its notable successes, AIGC still faces hurdles such as updating knowledge, handling long-tail data, mitigating data leakage, and managing high training and inference costs. Retrieval-Augmented Generation (RAG) has recently emerged as a paradigm to address such challenges. In particular, RAG introduces the information retrieval process, which enhances the generation process by retrieving relevant objec"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"RAG introduces the information retrieval process, which enhances the generation process by retrieving relevant objects from available data stores, leading to higher accuracy and better robustness.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the collected literature and proposed classification of augmentation methodologies comprehensively represent the space of RAG-AIGC integrations without significant omissions or overlaps.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A survey classifying RAG foundations for AIGC, summarizing enhancements, cross-modal applications, benchmarks, limitations, and future directions.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"RAG integrates retrieval into AI-generated content to pull relevant data and raise accuracy plus robustness.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"33df38043a3987f6ff2bfb5bdad0a8c61c37a6110ce8d99da426a5509212ff65"},"source":{"id":"2402.19473","kind":"arxiv","version":6},"verdict":{"id":"df559452-f8ee-414b-ac30-e96b2a61ab14","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T13:27:39.327825Z","strongest_claim":"RAG introduces the information retrieval process, which enhances the generation process by retrieving relevant objects from available data stores, leading to higher accuracy and better robustness.","one_line_summary":"A survey classifying RAG foundations for AIGC, summarizing enhancements, cross-modal applications, benchmarks, limitations, and future directions.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the collected literature and proposed classification of augmentation methodologies comprehensively represent the space of RAG-AIGC integrations without significant omissions or overlaps.","pith_extraction_headline":"RAG integrates retrieval into AI-generated content to pull relevant data and raise accuracy plus robustness."},"references":{"count":298,"sample":[{"doi":"","year":2020,"title":"Language models are few-shot learners,","work_id":"0bea6c6b-769a-474f-bb43-fe4d93230958","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Evaluating Large Language Models Trained on Code","work_id":"042493e9-b26f-4b4e-bbde-382072ca9b08","ref_index":2,"cited_arxiv_id":"2107.03374","is_internal_anchor":true},{"doi":"","year":2023,"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","ref_index":3,"cited_arxiv_id":"2303.08774","is_internal_anchor":true},{"doi":"","year":2023,"title":"LLaMA: Open and Efficient Foundation Language Models","work_id":"c018fc23-6f3f-4035-9d02-28a2173b2b9d","ref_index":4,"cited_arxiv_id":"2302.13971","is_internal_anchor":true},{"doi":"","year":2023,"title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","work_id":"68a5177f-d644-44c1-bd4f-4e5278c22f5d","ref_index":5,"cited_arxiv_id":"2307.09288","is_internal_anchor":true}],"resolved_work":298,"snapshot_sha256":"5db19b5ea030054dddd3b827cb80c2b8d079f39053cbb77629a66f59da93d4b5","internal_anchors":16},"formal_canon":{"evidence_count":2,"snapshot_sha256":"7c414884d81b2eebfbe30d23ce7c3c38ebf69e740d0eba8efb5e59f6f54488fa"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"df559452-f8ee-414b-ac30-e96b2a61ab14"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FB5bksmu1oaOaY2B9x2IXw0irqgEI1WjOazgATNomwtpTXr0KhPCu9KOLWhA4N1ZIpnKHnLlETJpqKOe7zwMDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T05:22:40.041163Z"},"content_sha256":"cc5c3eb4b278d02c956dfdea1e9894c3181b9cc079caf5273e40afc5bba179ca","schema_version":"1.0","event_id":"sha256:cc5c3eb4b278d02c956dfdea1e9894c3181b9cc079caf5273e40afc5bba179ca"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PFZJSTZFREOEM4BPD76SF4IKCL/bundle.json","state_url":"https://pith.science/pith/PFZJSTZFREOEM4BPD76SF4IKCL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PFZJSTZFREOEM4BPD76SF4IKCL/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":"2026-06-02T05:22:40Z","links":{"resolver":"https://pith.science/pith/PFZJSTZFREOEM4BPD76SF4IKCL","bundle":"https://pith.science/pith/PFZJSTZFREOEM4BPD76SF4IKCL/bundle.json","state":"https://pith.science/pith/PFZJSTZFREOEM4BPD76SF4IKCL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PFZJSTZFREOEM4BPD76SF4IKCL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PFZJSTZFREOEM4BPD76SF4IKCL","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":"dd05be16be6a8078428a33cb6c7f10a637840084d1458463db62c00796e4d110","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-29T18:59:01Z","title_canon_sha256":"9e1255553cc92620ddda38ffb254a74f40b20f789a98f2df953ef94cf5c4c0ac"},"schema_version":"1.0","source":{"id":"2402.19473","kind":"arxiv","version":6}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.19473","created_at":"2026-05-17T23:38:52Z"},{"alias_kind":"arxiv_version","alias_value":"2402.19473v6","created_at":"2026-05-17T23:38:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.19473","created_at":"2026-05-17T23:38:52Z"},{"alias_kind":"pith_short_12","alias_value":"PFZJSTZFREOE","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"PFZJSTZFREOEM4BP","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"PFZJSTZF","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:cc5c3eb4b278d02c956dfdea1e9894c3181b9cc079caf5273e40afc5bba179ca","target":"graph","created_at":"2026-05-17T23:38:52Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"RAG introduces the information retrieval process, which enhances the generation process by retrieving relevant objects from available data stores, leading to higher accuracy and better robustness."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the collected literature and proposed classification of augmentation methodologies comprehensively represent the space of RAG-AIGC integrations without significant omissions or overlaps."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A survey classifying RAG foundations for AIGC, summarizing enhancements, cross-modal applications, benchmarks, limitations, and future directions."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"RAG integrates retrieval into AI-generated content to pull relevant data and raise accuracy plus robustness."}],"snapshot_sha256":"33df38043a3987f6ff2bfb5bdad0a8c61c37a6110ce8d99da426a5509212ff65"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"7c414884d81b2eebfbe30d23ce7c3c38ebf69e740d0eba8efb5e59f6f54488fa"},"paper":{"abstract_excerpt":"Advancements in model algorithms, the growth of foundational models, and access to high-quality datasets have propelled the evolution of Artificial Intelligence Generated Content (AIGC). Despite its notable successes, AIGC still faces hurdles such as updating knowledge, handling long-tail data, mitigating data leakage, and managing high training and inference costs. Retrieval-Augmented Generation (RAG) has recently emerged as a paradigm to address such challenges. In particular, RAG introduces the information retrieval process, which enhances the generation process by retrieving relevant objec","authors_text":"Bin Cui, Fangcheng Fu, Hailin Zhang, Jie Jiang, Ling Yang, Penghao Zhao, Qinhan Yu, Wentao Zhang, Yunteng Geng, Zhengren Wang","cross_cats":[],"headline":"RAG integrates retrieval into AI-generated content to pull relevant data and raise accuracy plus robustness.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-29T18:59:01Z","title":"Retrieval-Augmented Generation for AI-Generated Content: A Survey"},"references":{"count":298,"internal_anchors":16,"resolved_work":298,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Language models are few-shot learners,","work_id":"0bea6c6b-769a-474f-bb43-fe4d93230958","year":2020},{"cited_arxiv_id":"2107.03374","doi":"","is_internal_anchor":true,"ref_index":2,"title":"Evaluating Large Language Models Trained on Code","work_id":"042493e9-b26f-4b4e-bbde-382072ca9b08","year":2021},{"cited_arxiv_id":"2303.08774","doi":"","is_internal_anchor":true,"ref_index":3,"title":"GPT-4 Technical Report","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","year":2023},{"cited_arxiv_id":"2302.13971","doi":"","is_internal_anchor":true,"ref_index":4,"title":"LLaMA: Open and Efficient Foundation Language Models","work_id":"c018fc23-6f3f-4035-9d02-28a2173b2b9d","year":2023},{"cited_arxiv_id":"2307.09288","doi":"","is_internal_anchor":true,"ref_index":5,"title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","work_id":"68a5177f-d644-44c1-bd4f-4e5278c22f5d","year":2023}],"snapshot_sha256":"5db19b5ea030054dddd3b827cb80c2b8d079f39053cbb77629a66f59da93d4b5"},"source":{"id":"2402.19473","kind":"arxiv","version":6},"verdict":{"created_at":"2026-05-15T13:27:39.327825Z","id":"df559452-f8ee-414b-ac30-e96b2a61ab14","model_set":{"reader":"grok-4.3"},"one_line_summary":"A survey classifying RAG foundations for AIGC, summarizing enhancements, cross-modal applications, benchmarks, limitations, and future directions.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"RAG integrates retrieval into AI-generated content to pull relevant data and raise accuracy plus robustness.","strongest_claim":"RAG introduces the information retrieval process, which enhances the generation process by retrieving relevant objects from available data stores, leading to higher accuracy and better robustness.","weakest_assumption":"That the collected literature and proposed classification of augmentation methodologies comprehensively represent the space of RAG-AIGC integrations without significant omissions or overlaps."}},"verdict_id":"df559452-f8ee-414b-ac30-e96b2a61ab14"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:42e05eb9a28fe61730452f130b2af2407ffc4dda015509efd4c76a86f38d86c9","target":"record","created_at":"2026-05-17T23:38:52Z","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":"dd05be16be6a8078428a33cb6c7f10a637840084d1458463db62c00796e4d110","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-29T18:59:01Z","title_canon_sha256":"9e1255553cc92620ddda38ffb254a74f40b20f789a98f2df953ef94cf5c4c0ac"},"schema_version":"1.0","source":{"id":"2402.19473","kind":"arxiv","version":6}},"canonical_sha256":"7972994f25891c46702f1ffd22f10a12ea81c80ec2692339f4ca73dfaf63c5b5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7972994f25891c46702f1ffd22f10a12ea81c80ec2692339f4ca73dfaf63c5b5","first_computed_at":"2026-05-17T23:38:52.443477Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:52.443477Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Qn1b9iV2J5i4MFKqWAIltKE0vP1rRjHet8a4+DJANISHE3JvA5FsnDOFM9iixT0ARI9kKqbyePhMNXsUQtxdCA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:52.444074Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.19473","source_kind":"arxiv","source_version":6}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:42e05eb9a28fe61730452f130b2af2407ffc4dda015509efd4c76a86f38d86c9","sha256:cc5c3eb4b278d02c956dfdea1e9894c3181b9cc079caf5273e40afc5bba179ca"],"state_sha256":"972d0c51e5524ea018ea5913ca3982a58172c00bc07ca89ded97b6c9ddf57213"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"prtRJhJ5olsDp6gEVyw3nouTMu4NLFwu+qjYdQ63PLQm+r/FgqqtuQNJDtsq7LU1cjUqkJnpSt1zGlG6ANi6Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T05:22:40.043587Z","bundle_sha256":"20ed9a136eee42cfc5ac831acc6d24484cf0d984a2fbf8ad7bd6e500f53b354d"}}