{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6UXASP56WWWSNNCTIBYSW5IAGR","short_pith_number":"pith:6UXASP56","schema_version":"1.0","canonical_sha256":"f52e093fbeb5ad26b45340712b7500347339c5454bd0f1c70532042a29da2771","source":{"kind":"arxiv","id":"2407.04787","version":1},"attestation_state":"computed","paper":{"title":"Re-Tuning: Overcoming the Compositionality Limits of Large Language Models with Recursive Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chenguang Wang, Dawn Song, Eric Pasewark, Kefei Duan, Kyle Montgomery","submitted_at":"2024-07-05T18:02:28Z","abstract_excerpt":"We present a new method for large language models to solve compositional tasks. Although they have shown strong performance on traditional language understanding tasks, large language models struggle to solve compositional tasks, where the solution depends on solving smaller instances of the same problem. We propose a natural approach to solve compositional tasks recursively. Our method, Re-Tuning, tunes models to break down a problem into subproblems, solve those subproblems, and combine the results. We show that our method significantly improves model performance on three representative comp"},"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":"2407.04787","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-05T18:02:28Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d3a4482d3257f3db9b345d1342bb2bda85334dbb14273ce4a584f3882516fe1f","abstract_canon_sha256":"a42b2589d7dd29a3f8c75f774f61e3962769dba110126bdcd22f673330f1fd31"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:40:41.924156Z","signature_b64":"FemJDwMkyC5Kgl/AZ6UrGXF7xNEfxwKBkVBK5KcjigMLxNC+lYpFpzLUZ5ExQhqSGtXH/3ZiQUl5kKGN4ibWAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f52e093fbeb5ad26b45340712b7500347339c5454bd0f1c70532042a29da2771","last_reissued_at":"2026-07-05T08:40:41.923643Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:40:41.923643Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Re-Tuning: Overcoming the Compositionality Limits of Large Language Models with Recursive Tuning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chenguang Wang, Dawn Song, Eric Pasewark, Kefei Duan, Kyle Montgomery","submitted_at":"2024-07-05T18:02:28Z","abstract_excerpt":"We present a new method for large language models to solve compositional tasks. Although they have shown strong performance on traditional language understanding tasks, large language models struggle to solve compositional tasks, where the solution depends on solving smaller instances of the same problem. We propose a natural approach to solve compositional tasks recursively. Our method, Re-Tuning, tunes models to break down a problem into subproblems, solve those subproblems, and combine the results. We show that our method significantly improves model performance on three representative comp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.04787","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/2407.04787/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":"2407.04787","created_at":"2026-07-05T08:40:41.923706+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.04787v1","created_at":"2026-07-05T08:40:41.923706+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.04787","created_at":"2026-07-05T08:40:41.923706+00:00"},{"alias_kind":"pith_short_12","alias_value":"6UXASP56WWWS","created_at":"2026-07-05T08:40:41.923706+00:00"},{"alias_kind":"pith_short_16","alias_value":"6UXASP56WWWSNNCT","created_at":"2026-07-05T08:40:41.923706+00:00"},{"alias_kind":"pith_short_8","alias_value":"6UXASP56","created_at":"2026-07-05T08:40:41.923706+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6UXASP56WWWSNNCTIBYSW5IAGR","json":"https://pith.science/pith/6UXASP56WWWSNNCTIBYSW5IAGR.json","graph_json":"https://pith.science/api/pith-number/6UXASP56WWWSNNCTIBYSW5IAGR/graph.json","events_json":"https://pith.science/api/pith-number/6UXASP56WWWSNNCTIBYSW5IAGR/events.json","paper":"https://pith.science/paper/6UXASP56"},"agent_actions":{"view_html":"https://pith.science/pith/6UXASP56WWWSNNCTIBYSW5IAGR","download_json":"https://pith.science/pith/6UXASP56WWWSNNCTIBYSW5IAGR.json","view_paper":"https://pith.science/paper/6UXASP56","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.04787&json=true","fetch_graph":"https://pith.science/api/pith-number/6UXASP56WWWSNNCTIBYSW5IAGR/graph.json","fetch_events":"https://pith.science/api/pith-number/6UXASP56WWWSNNCTIBYSW5IAGR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6UXASP56WWWSNNCTIBYSW5IAGR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6UXASP56WWWSNNCTIBYSW5IAGR/action/storage_attestation","attest_author":"https://pith.science/pith/6UXASP56WWWSNNCTIBYSW5IAGR/action/author_attestation","sign_citation":"https://pith.science/pith/6UXASP56WWWSNNCTIBYSW5IAGR/action/citation_signature","submit_replication":"https://pith.science/pith/6UXASP56WWWSNNCTIBYSW5IAGR/action/replication_record"}},"created_at":"2026-07-05T08:40:41.923706+00:00","updated_at":"2026-07-05T08:40:41.923706+00:00"}