{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7O2VJFYRH7TDHF73KSKNHJXGHV","short_pith_number":"pith:7O2VJFYR","schema_version":"1.0","canonical_sha256":"fbb55497113fe63397fb5494d3a6e63d6ccdd837e87343a47a602001bf326a80","source":{"kind":"arxiv","id":"2503.14269","version":1},"attestation_state":"computed","paper":{"title":"DARS: Dynamic Action Re-Sampling to Enhance Coding Agent Performance by Adaptive Tree Traversal","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.CL","authors_text":"Abhinav Japesh, Bernhard Sch\\\"olkopf, Ojasv Kamal, Vaibhav Aggarwal, Zhijing Jin","submitted_at":"2025-03-18T14:02:59Z","abstract_excerpt":"Large Language Models (LLMs) have revolutionized various domains, including natural language processing, data analysis, and software development, by enabling automation. In software engineering, LLM-powered coding agents have garnered significant attention due to their potential to automate complex development tasks, assist in debugging, and enhance productivity. However, existing approaches often struggle with sub-optimal decision-making, requiring either extensive manual intervention or inefficient compute scaling strategies. To improve coding agent performance, we present Dynamic Action Re-"},"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":"2503.14269","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-18T14:02:59Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"37c10da8828e3a0c0517cbbb4650355392a196f05ec0635d017682534600d5f3","abstract_canon_sha256":"c8bc82cf31b4d4ade11d8614314b7aa8494918da7bca68329706f997cb9d745c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:33:59.139193Z","signature_b64":"xG9MVBd5d5HP4xA8I6KQHqQwyt03VmDMqhQZ+qAHnhid+0Catn2bVnfOHfJFv4IltJ/J1XxLiLFxaReVI9/pBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fbb55497113fe63397fb5494d3a6e63d6ccdd837e87343a47a602001bf326a80","last_reissued_at":"2026-07-05T10:33:59.138673Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:33:59.138673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DARS: Dynamic Action Re-Sampling to Enhance Coding Agent Performance by Adaptive Tree Traversal","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.CL","authors_text":"Abhinav Japesh, Bernhard Sch\\\"olkopf, Ojasv Kamal, Vaibhav Aggarwal, Zhijing Jin","submitted_at":"2025-03-18T14:02:59Z","abstract_excerpt":"Large Language Models (LLMs) have revolutionized various domains, including natural language processing, data analysis, and software development, by enabling automation. In software engineering, LLM-powered coding agents have garnered significant attention due to their potential to automate complex development tasks, assist in debugging, and enhance productivity. However, existing approaches often struggle with sub-optimal decision-making, requiring either extensive manual intervention or inefficient compute scaling strategies. To improve coding agent performance, we present Dynamic Action Re-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.14269","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/2503.14269/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":"2503.14269","created_at":"2026-07-05T10:33:59.138752+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.14269v1","created_at":"2026-07-05T10:33:59.138752+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.14269","created_at":"2026-07-05T10:33:59.138752+00:00"},{"alias_kind":"pith_short_12","alias_value":"7O2VJFYRH7TD","created_at":"2026-07-05T10:33:59.138752+00:00"},{"alias_kind":"pith_short_16","alias_value":"7O2VJFYRH7TDHF73","created_at":"2026-07-05T10:33:59.138752+00:00"},{"alias_kind":"pith_short_8","alias_value":"7O2VJFYR","created_at":"2026-07-05T10:33:59.138752+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.10484","citing_title":"EXPEREPAIR: Dual-Memory Enhanced LLM-based Repository-Level Program Repair","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2504.19678","citing_title":"From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review","ref_index":181,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04580","citing_title":"Beyond Fixed Tests: Repository-Level Issue Resolution as Coevolution of Code and Behavioral Constraints","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7O2VJFYRH7TDHF73KSKNHJXGHV","json":"https://pith.science/pith/7O2VJFYRH7TDHF73KSKNHJXGHV.json","graph_json":"https://pith.science/api/pith-number/7O2VJFYRH7TDHF73KSKNHJXGHV/graph.json","events_json":"https://pith.science/api/pith-number/7O2VJFYRH7TDHF73KSKNHJXGHV/events.json","paper":"https://pith.science/paper/7O2VJFYR"},"agent_actions":{"view_html":"https://pith.science/pith/7O2VJFYRH7TDHF73KSKNHJXGHV","download_json":"https://pith.science/pith/7O2VJFYRH7TDHF73KSKNHJXGHV.json","view_paper":"https://pith.science/paper/7O2VJFYR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.14269&json=true","fetch_graph":"https://pith.science/api/pith-number/7O2VJFYRH7TDHF73KSKNHJXGHV/graph.json","fetch_events":"https://pith.science/api/pith-number/7O2VJFYRH7TDHF73KSKNHJXGHV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7O2VJFYRH7TDHF73KSKNHJXGHV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7O2VJFYRH7TDHF73KSKNHJXGHV/action/storage_attestation","attest_author":"https://pith.science/pith/7O2VJFYRH7TDHF73KSKNHJXGHV/action/author_attestation","sign_citation":"https://pith.science/pith/7O2VJFYRH7TDHF73KSKNHJXGHV/action/citation_signature","submit_replication":"https://pith.science/pith/7O2VJFYRH7TDHF73KSKNHJXGHV/action/replication_record"}},"created_at":"2026-07-05T10:33:59.138752+00:00","updated_at":"2026-07-05T10:33:59.138752+00:00"}