{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:6OZJYRIWZULFKVUIJ26HJP7DQK","short_pith_number":"pith:6OZJYRIW","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"},"canonical_sha256":"f3b29c4516cd165556884ebc74bfe382b5fb70fce695763d78937257b83660d2","source":{"kind":"arxiv","id":"2401.18059","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.18059","created_at":"2026-05-17T23:38:52Z"},{"alias_kind":"arxiv_version","alias_value":"2401.18059v1","created_at":"2026-05-17T23:38:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.18059","created_at":"2026-05-17T23:38:52Z"},{"alias_kind":"pith_short_12","alias_value":"6OZJYRIWZULF","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"6OZJYRIWZULFKVUI","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"6OZJYRIW","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:6OZJYRIWZULFKVUIJ26HJP7DQK","target":"record","payload":{"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"},"canonical_sha256":"f3b29c4516cd165556884ebc74bfe382b5fb70fce695763d78937257b83660d2","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"},"source_kind":"arxiv","source_id":"2401.18059","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":"2026-05-17T23:38:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7L30Mlw6umWJBzxphGbI3VFgOP3d2NocpMmV7NMvU44b5bd9jqU8MiLJAtNVutQZEHzN2iJwqvQ/nPmGFI5QCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T21:22:08.085286Z"},"content_sha256":"7626a2b04d3f77dd799316ab1fa3a61ba36dad52f696611015c9ee3cbeeb76f6","schema_version":"1.0","event_id":"sha256:7626a2b04d3f77dd799316ab1fa3a61ba36dad52f696611015c9ee3cbeeb76f6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:6OZJYRIWZULFKVUIJ26HJP7DQK","target":"graph","payload":{"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"},"verdict_id":"3e39f47c-b446-44f2-8a05-1632aa62bd84"},"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":"OURh6kkD2e/v4z6T3l4PmyFNR1PXagEDZ1gN5hmWQ9uB2ZqlrwQ5h/jOXUvQJY8vF64YbtX0qkAt530Hdhj1Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T21:22:08.086382Z"},"content_sha256":"eb367115de3add9a09abc89d7a4f8ab08416b8463c3f518cae48f447483c5727","schema_version":"1.0","event_id":"sha256:eb367115de3add9a09abc89d7a4f8ab08416b8463c3f518cae48f447483c5727"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6OZJYRIWZULFKVUIJ26HJP7DQK/bundle.json","state_url":"https://pith.science/pith/6OZJYRIWZULFKVUIJ26HJP7DQK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6OZJYRIWZULFKVUIJ26HJP7DQK/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":"2026-05-28T21:22:08Z","links":{"resolver":"https://pith.science/pith/6OZJYRIWZULFKVUIJ26HJP7DQK","bundle":"https://pith.science/pith/6OZJYRIWZULFKVUIJ26HJP7DQK/bundle.json","state":"https://pith.science/pith/6OZJYRIWZULFKVUIJ26HJP7DQK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6OZJYRIWZULFKVUIJ26HJP7DQK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6OZJYRIWZULFKVUIJ26HJP7DQK","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":"4b4e8795849e2575548f7f664081a1408d6d307b2d61c069211c535628b89293","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-31T18:30:21Z","title_canon_sha256":"a7ff4b20c4ee1b6df25b8a18f737d4ad1efe8efe0ae5bf44c02ac57cc8869243"},"schema_version":"1.0","source":{"id":"2401.18059","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.18059","created_at":"2026-05-17T23:38:52Z"},{"alias_kind":"arxiv_version","alias_value":"2401.18059v1","created_at":"2026-05-17T23:38:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.18059","created_at":"2026-05-17T23:38:52Z"},{"alias_kind":"pith_short_12","alias_value":"6OZJYRIWZULF","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"6OZJYRIWZULFKVUI","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"6OZJYRIW","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:eb367115de3add9a09abc89d7a4f8ab08416b8463c3f518cae48f447483c5727","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":"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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The recursive clustering and summarization process effectively captures and preserves all relevant information from the original document without significant loss or distortion."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Recursive clustering and summarization builds a tree that improves retrieval-augmented reasoning over long documents."}],"snapshot_sha256":"363e72ddfd188b5c4b3d91e533f2c9b06efd2f14e3eb35f861aa145e81ededa2"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"46400d8dae9eb0ac558d85941795d229d9b4566ce33b36048c2ee2df75745546"},"paper":{"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","authors_text":"Aditi Tuli, Anna Goldie, Christopher D. Manning, Parth Sarthi, Salman Abdullah, Shubh Khanna","cross_cats":["cs.LG"],"headline":"Recursive clustering and summarization builds a tree that improves retrieval-augmented reasoning over long documents.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-31T18:30:21Z","title":"RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval"},"references":{"count":124,"internal_anchors":25,"resolved_work":124,"sample":[{"cited_arxiv_id":"","doi":"10.1007/3-540-44503-x_27","is_internal_anchor":false,"ref_index":1,"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","year":2001},{"cited_arxiv_id":"2112.04426","doi":"","is_internal_anchor":true,"ref_index":7,"title":"Improving language models by retrieving from trillions of tokens","work_id":"c8e7ce21-2f18-4c10-b0cf-16cd3574fe33","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":8,"title":"L anguage M odels are F ew- S hot L earners","work_id":"e21d9ea5-09df-4873-a892-f6f44ddd45ef","year":1901},{"cited_arxiv_id":"2204.02311","doi":"","is_internal_anchor":true,"ref_index":12,"title":"PaLM: Scaling Language Modeling with Pathways","work_id":"a94f3ef7-2c49-4445-93fe-6ec16aafd966","year":2022},{"cited_arxiv_id":"","doi":"10.1145/3077136.3080740","is_internal_anchor":false,"ref_index":13,"title":"Contextualizing citations for scientific summarization using word embeddings and domain knowledge","work_id":"771354f2-4a97-4e9a-ab55-7fbe34c0a2aa","year":2017}],"snapshot_sha256":"533ec12270f67a4525f66fbe7f1d804cd3a8a0cd092f4250f70015eed7dfa3c6"},"source":{"id":"2401.18059","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T13:02:10.149769Z","id":"3e39f47c-b446-44f2-8a05-1632aa62bd84","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"Recursive clustering and summarization builds a tree that improves retrieval-augmented reasoning over long documents.","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.","weakest_assumption":"The recursive clustering and summarization process effectively captures and preserves all relevant information from the original document without significant loss or distortion."}},"verdict_id":"3e39f47c-b446-44f2-8a05-1632aa62bd84"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7626a2b04d3f77dd799316ab1fa3a61ba36dad52f696611015c9ee3cbeeb76f6","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":"4b4e8795849e2575548f7f664081a1408d6d307b2d61c069211c535628b89293","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-31T18:30:21Z","title_canon_sha256":"a7ff4b20c4ee1b6df25b8a18f737d4ad1efe8efe0ae5bf44c02ac57cc8869243"},"schema_version":"1.0","source":{"id":"2401.18059","kind":"arxiv","version":1}},"canonical_sha256":"f3b29c4516cd165556884ebc74bfe382b5fb70fce695763d78937257b83660d2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f3b29c4516cd165556884ebc74bfe382b5fb70fce695763d78937257b83660d2","first_computed_at":"2026-05-17T23:38:52.495670Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:52.495670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vJbkM2jSNY/1n/JkxbDoN07o5Uc2OUtkSHSvall38/8nwpGgLvmo+kybMyg9iD7OQTIjXu7znfhclRO+DHHRBw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:52.496148Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.18059","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7626a2b04d3f77dd799316ab1fa3a61ba36dad52f696611015c9ee3cbeeb76f6","sha256:eb367115de3add9a09abc89d7a4f8ab08416b8463c3f518cae48f447483c5727"],"state_sha256":"7afcb0d75f7b03d3c10ecb3f1afe41e8faf7fc3b521514a54be8485a51065853"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AQYrsYpanguNy7ayJdwYB9Wlk9d0nkERYWHqlAPnh/dAK93GDFtdbBnlejukDhcdZfbBhxvgYxsZqmE+VL/YDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T21:22:08.091153Z","bundle_sha256":"4f36827d34b0b459b8c892b4e81ac5d931d9f8b0a9656ba4f784044324a9276b"}}