{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6OZJYRIWZULFKVUIJ26HJP7DQK","short_pith_number":"pith:6OZJYRIW","schema_version":"1.0","canonical_sha256":"f3b29c4516cd165556884ebc74bfe382b5fb70fce695763d78937257b83660d2","source":{"kind":"arxiv","id":"2401.18059","version":1},"attestation_state":"computed","paper":{"title":"RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Recursive clustering and summarization builds a tree that improves retrieval-augmented reasoning over long documents.","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Aditi Tuli, Anna Goldie, Christopher D. Manning, Parth Sarthi, Salman Abdullah, Shubh Khanna","submitted_at":"2024-01-31T18:30:21Z","abstract_excerpt":"Retrieval-augmented language models can better adapt to changes in world state and incorporate long-tail knowledge. However, most existing methods retrieve only short contiguous chunks from a retrieval corpus, limiting holistic understanding of the overall document context. We introduce the novel approach of recursively embedding, clustering, and summarizing chunks of text, constructing a tree with differing levels of summarization from the bottom up. At inference time, our RAPTOR model retrieves from this tree, integrating information across lengthy documents at different levels of abstractio"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2401.18059","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-31T18:30:21Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a7ff4b20c4ee1b6df25b8a18f737d4ad1efe8efe0ae5bf44c02ac57cc8869243","abstract_canon_sha256":"4b4e8795849e2575548f7f664081a1408d6d307b2d61c069211c535628b89293"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:52.496148Z","signature_b64":"vJbkM2jSNY/1n/JkxbDoN07o5Uc2OUtkSHSvall38/8nwpGgLvmo+kybMyg9iD7OQTIjXu7znfhclRO+DHHRBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f3b29c4516cd165556884ebc74bfe382b5fb70fce695763d78937257b83660d2","last_reissued_at":"2026-05-17T23:38:52.495670Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:52.495670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Recursive clustering and summarization builds a tree that improves retrieval-augmented reasoning over long documents.","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Aditi Tuli, Anna Goldie, Christopher D. Manning, Parth Sarthi, Salman Abdullah, Shubh Khanna","submitted_at":"2024-01-31T18:30:21Z","abstract_excerpt":"Retrieval-augmented language models can better adapt to changes in world state and incorporate long-tail knowledge. However, most existing methods retrieve only short contiguous chunks from a retrieval corpus, limiting holistic understanding of the overall document context. We introduce the novel approach of recursively embedding, clustering, and summarizing chunks of text, constructing a tree with differing levels of summarization from the bottom up. At inference time, our RAPTOR model retrieves from this tree, integrating information across lengthy documents at different levels of abstractio"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"by coupling RAPTOR retrieval with the use of GPT-4, we can improve the best performance on the QuALITY benchmark by 20% in absolute accuracy.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The recursive clustering and summarization process effectively captures and preserves all relevant information from the original document without significant loss or distortion.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"RAPTOR introduces a tree-organized retrieval method using recursive abstractive summaries, achieving a 20% absolute accuracy improvement on the QuALITY benchmark when paired with GPT-4.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Recursive clustering and summarization builds a tree that improves retrieval-augmented reasoning over long documents.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"363e72ddfd188b5c4b3d91e533f2c9b06efd2f14e3eb35f861aa145e81ededa2"},"source":{"id":"2401.18059","kind":"arxiv","version":1},"verdict":{"id":"3e39f47c-b446-44f2-8a05-1632aa62bd84","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T13:02:10.149769Z","strongest_claim":"by coupling RAPTOR retrieval with the use of GPT-4, we can improve the best performance on the QuALITY benchmark by 20% in absolute accuracy.","one_line_summary":"RAPTOR introduces a tree-organized retrieval method using recursive abstractive summaries, achieving a 20% absolute accuracy improvement on the QuALITY benchmark when paired with GPT-4.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The recursive clustering and summarization process effectively captures and preserves all relevant information from the original document without significant loss or distortion.","pith_extraction_headline":"Recursive clustering and summarization builds a tree that improves retrieval-augmented reasoning over long documents."},"references":{"count":124,"sample":[{"doi":"10.1007/3-540-44503-x_27","year":2001,"title":"On the S urprising B ehavior of D istance M etrics in H igh D imensional S pace","work_id":"a97fe484-1064-458f-b442-b0cca45b2093","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"Improving language models by retrieving from trillions of tokens","work_id":"c8e7ce21-2f18-4c10-b0cf-16cd3574fe33","ref_index":7,"cited_arxiv_id":"2112.04426","is_internal_anchor":true},{"doi":"","year":1901,"title":"L anguage M odels are F ew- S hot L earners","work_id":"e21d9ea5-09df-4873-a892-f6f44ddd45ef","ref_index":8,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"PaLM: Scaling Language Modeling with Pathways","work_id":"a94f3ef7-2c49-4445-93fe-6ec16aafd966","ref_index":12,"cited_arxiv_id":"2204.02311","is_internal_anchor":true},{"doi":"10.1145/3077136.3080740","year":2017,"title":"Contextualizing citations for scientific summarization using word embeddings and domain knowledge","work_id":"771354f2-4a97-4e9a-ab55-7fbe34c0a2aa","ref_index":13,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":124,"snapshot_sha256":"533ec12270f67a4525f66fbe7f1d804cd3a8a0cd092f4250f70015eed7dfa3c6","internal_anchors":25},"formal_canon":{"evidence_count":2,"snapshot_sha256":"46400d8dae9eb0ac558d85941795d229d9b4566ce33b36048c2ee2df75745546"},"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":"2401.18059","created_at":"2026-05-17T23:38:52.495757+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.18059v1","created_at":"2026-05-17T23:38:52.495757+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.18059","created_at":"2026-05-17T23:38:52.495757+00:00"},{"alias_kind":"pith_short_12","alias_value":"6OZJYRIWZULF","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"6OZJYRIWZULFKVUI","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"6OZJYRIW","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":32,"internal_anchor_count":32,"sample":[{"citing_arxiv_id":"2312.10997","citing_title":"Retrieval-Augmented Generation for Large Language Models: A Survey","ref_index":63,"is_internal_anchor":true},{"citing_arxiv_id":"2502.09891","citing_title":"ArchRAG: Attributed Community-based Hierarchical Retrieval-Augmented Generation","ref_index":48,"is_internal_anchor":true},{"citing_arxiv_id":"2503.04338","citing_title":"In-depth Analysis of Graph-based RAG in a Unified Framework","ref_index":74,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20724","citing_title":"CALMem : Application-Layer Dual Memory for Conversational AI","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19806","citing_title":"Chunking German Legal Code","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09033","citing_title":"ShadowMerge: A Novel Poisoning Attack on Graph-Based Agent Memory via Relation-Channel Conflicts","ref_index":53,"is_internal_anchor":true},{"citing_arxiv_id":"2506.18027","citing_title":"PDF Retrieval Augmented Question Answering","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2511.16326","citing_title":"ARK: Answer-Centric Retriever Tuning via KG-augmented Curriculum Learning","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2601.02845","citing_title":"TiMem: Temporal-Hierarchical Memory Consolidation for Long-Horizon Conversational Agents","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2603.29875","citing_title":"UnWeaving the knots of GraphRAG -- turns out VectorRAG is almost enough","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2604.20844","citing_title":"AtomicRAG: Atom-Entity Graphs for Retrieval-Augmented Generation","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2603.15421","citing_title":"CLAG: Adaptive Memory Organization via Agent-Driven Clustering for Small Language Model Agents","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09033","citing_title":"ShadowMerge: A Novel Poisoning Attack on Graph-Based Agent Memory via Relation-Channel Conflicts","ref_index":53,"is_internal_anchor":true},{"citing_arxiv_id":"2604.14170","citing_title":"Stateful Evidence-Driven Retrieval-Augmented Generation with Iterative Reasoning","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2604.16401","citing_title":"GraphRAG-Router: Learning Cost-Efficient Routing over GraphRAGs and LLMs with Reinforcement Learning","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2604.09666","citing_title":"Do We Still Need GraphRAG? Benchmarking RAG and GraphRAG for Agentic Search Systems","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2604.01707","citing_title":"Memory in the LLM Era: Modular Architectures and Strategies in a Unified Framework","ref_index":83,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12213","citing_title":"Goal-Oriented Reasoning for RAG-based Memory in Conversational Agentic LLM Systems","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2311.05232","citing_title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","ref_index":280,"is_internal_anchor":true},{"citing_arxiv_id":"2604.26622","citing_title":"OCR-Memory: Optical Context Retrieval for Long-Horizon Agent Memory","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09033","citing_title":"ShadowMerge: A Novel Poisoning Attack on Graph-Based Agent Memory via Relation-Channel Conflicts","ref_index":54,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10168","citing_title":"ASTRA-QA: A Benchmark for Abstract Question Answering over Documents","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2605.03989","citing_title":"An Agent-Oriented Pluggable Experience-RAG Skill for Experience-Driven Retrieval Strategy Orchestration","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2604.24334","citing_title":"Reducing Redundancy in Retrieval-Augmented Generation through Chunk Filtering","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2604.23129","citing_title":"MindTrellis: Co-Creating Knowledge Structures with AI through Interactive Visual Exploration","ref_index":48,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6OZJYRIWZULFKVUIJ26HJP7DQK","json":"https://pith.science/pith/6OZJYRIWZULFKVUIJ26HJP7DQK.json","graph_json":"https://pith.science/api/pith-number/6OZJYRIWZULFKVUIJ26HJP7DQK/graph.json","events_json":"https://pith.science/api/pith-number/6OZJYRIWZULFKVUIJ26HJP7DQK/events.json","paper":"https://pith.science/paper/6OZJYRIW"},"agent_actions":{"view_html":"https://pith.science/pith/6OZJYRIWZULFKVUIJ26HJP7DQK","download_json":"https://pith.science/pith/6OZJYRIWZULFKVUIJ26HJP7DQK.json","view_paper":"https://pith.science/paper/6OZJYRIW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.18059&json=true","fetch_graph":"https://pith.science/api/pith-number/6OZJYRIWZULFKVUIJ26HJP7DQK/graph.json","fetch_events":"https://pith.science/api/pith-number/6OZJYRIWZULFKVUIJ26HJP7DQK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6OZJYRIWZULFKVUIJ26HJP7DQK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6OZJYRIWZULFKVUIJ26HJP7DQK/action/storage_attestation","attest_author":"https://pith.science/pith/6OZJYRIWZULFKVUIJ26HJP7DQK/action/author_attestation","sign_citation":"https://pith.science/pith/6OZJYRIWZULFKVUIJ26HJP7DQK/action/citation_signature","submit_replication":"https://pith.science/pith/6OZJYRIWZULFKVUIJ26HJP7DQK/action/replication_record"}},"created_at":"2026-05-17T23:38:52.495757+00:00","updated_at":"2026-05-17T23:38:52.495757+00:00"}