{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KTYVPIZ4M374ZICWPK67MSGEBE","short_pith_number":"pith:KTYVPIZ4","schema_version":"1.0","canonical_sha256":"54f157a33c66ffcca0567abdf648c4093ff34a67d1d5fb09048b5fd1022e9c3a","source":{"kind":"arxiv","id":"2411.05010","version":2},"attestation_state":"computed","paper":{"title":"Scattered Forest Search: Smarter Code Space Exploration with LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.SE","authors_text":"Haifeng Chen, Jonathan Light, Wei Cheng, Wenchao Yu, Xujiang Zhao, Yanchi Liu, Yiyou Sun, Yue Wu, Ziniu Hu","submitted_at":"2024-10-22T01:58:29Z","abstract_excerpt":"We frame code generation as a black-box optimization problem within the code space and demonstrate how optimization-inspired techniques can enhance inference scaling. Based on this perspective, we propose SCATTERED FOREST SEARCH (SFS), a novel approach that improves solution diversity and better exploits feedback during evolutionary search. Our theoretical analysis illustrates how these methods help avoid local optima during optimization, leading to more efficient exploration. Extensive experiments on HumanEval, MBPP, APPS, CodeContests, and Leetcode reveal significant performance gains. For i"},"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":"2411.05010","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-10-22T01:58:29Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"0a3304d1ad64302ef73faf72970c403ccb46c6fe4d7bf1a95e227935222f0758","abstract_canon_sha256":"8f331d600cc58260a813bd1a479e63d8b956f313b5f40c88d23ff7850fb492a2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:19:30.818417Z","signature_b64":"iCqlEa54EdGrWoWNETngZISwFDN9Rc9MV0thFHgad7Go95jpqK1z4/ZGJ8jpNjUEMMA6ehl99fcjI7kCjAxnDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54f157a33c66ffcca0567abdf648c4093ff34a67d1d5fb09048b5fd1022e9c3a","last_reissued_at":"2026-07-05T10:19:30.817928Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:19:30.817928Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scattered Forest Search: Smarter Code Space Exploration with LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.SE","authors_text":"Haifeng Chen, Jonathan Light, Wei Cheng, Wenchao Yu, Xujiang Zhao, Yanchi Liu, Yiyou Sun, Yue Wu, Ziniu Hu","submitted_at":"2024-10-22T01:58:29Z","abstract_excerpt":"We frame code generation as a black-box optimization problem within the code space and demonstrate how optimization-inspired techniques can enhance inference scaling. Based on this perspective, we propose SCATTERED FOREST SEARCH (SFS), a novel approach that improves solution diversity and better exploits feedback during evolutionary search. Our theoretical analysis illustrates how these methods help avoid local optima during optimization, leading to more efficient exploration. Extensive experiments on HumanEval, MBPP, APPS, CodeContests, and Leetcode reveal significant performance gains. For i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.05010","kind":"arxiv","version":2},"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/2411.05010/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":"2411.05010","created_at":"2026-07-05T10:19:30.817984+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.05010v2","created_at":"2026-07-05T10:19:30.817984+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.05010","created_at":"2026-07-05T10:19:30.817984+00:00"},{"alias_kind":"pith_short_12","alias_value":"KTYVPIZ4M374","created_at":"2026-07-05T10:19:30.817984+00:00"},{"alias_kind":"pith_short_16","alias_value":"KTYVPIZ4M374ZICW","created_at":"2026-07-05T10:19:30.817984+00:00"},{"alias_kind":"pith_short_8","alias_value":"KTYVPIZ4","created_at":"2026-07-05T10:19:30.817984+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.08057","citing_title":"CA-SQL: Complexity-Aware Inference Time Reasoning for Text-to-SQL via Exploration and Compute Budget Allocation","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16625","citing_title":"AdaExplore: Failure-Driven Adaptation and Diversity-Preserving Search for Efficient Kernel Generation","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KTYVPIZ4M374ZICWPK67MSGEBE","json":"https://pith.science/pith/KTYVPIZ4M374ZICWPK67MSGEBE.json","graph_json":"https://pith.science/api/pith-number/KTYVPIZ4M374ZICWPK67MSGEBE/graph.json","events_json":"https://pith.science/api/pith-number/KTYVPIZ4M374ZICWPK67MSGEBE/events.json","paper":"https://pith.science/paper/KTYVPIZ4"},"agent_actions":{"view_html":"https://pith.science/pith/KTYVPIZ4M374ZICWPK67MSGEBE","download_json":"https://pith.science/pith/KTYVPIZ4M374ZICWPK67MSGEBE.json","view_paper":"https://pith.science/paper/KTYVPIZ4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.05010&json=true","fetch_graph":"https://pith.science/api/pith-number/KTYVPIZ4M374ZICWPK67MSGEBE/graph.json","fetch_events":"https://pith.science/api/pith-number/KTYVPIZ4M374ZICWPK67MSGEBE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KTYVPIZ4M374ZICWPK67MSGEBE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KTYVPIZ4M374ZICWPK67MSGEBE/action/storage_attestation","attest_author":"https://pith.science/pith/KTYVPIZ4M374ZICWPK67MSGEBE/action/author_attestation","sign_citation":"https://pith.science/pith/KTYVPIZ4M374ZICWPK67MSGEBE/action/citation_signature","submit_replication":"https://pith.science/pith/KTYVPIZ4M374ZICWPK67MSGEBE/action/replication_record"}},"created_at":"2026-07-05T10:19:30.817984+00:00","updated_at":"2026-07-05T10:19:30.817984+00:00"}