{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:URXZU7UMGJWIAPYY2MBHOA4CXA","short_pith_number":"pith:URXZU7UM","schema_version":"1.0","canonical_sha256":"a46f9a7e8c326c803f18d302770382b83590af62b766490dd06f644694d09717","source":{"kind":"arxiv","id":"2603.16011","version":2},"attestation_state":"computed","paper":{"title":"FormulaCode: Evaluating Agentic Optimization on Large Codebases","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.SE","authors_text":"Akanksha Sarkar, Atharva Sehgal, Ishaan Mantripragada, James Hou, Jennifer J. Sun, Swarat Chaudhuri, Yisong Yue","submitted_at":"2026-03-16T23:40:19Z","abstract_excerpt":"Large language model (LLM) coding agents increasingly operate at the repository level, motivating benchmarks that evaluate their ability to optimize entire codebases under realistic constraints. Existing code benchmarks largely rely on synthetic tasks, binary correctness signals, or single-objective evaluation, limiting their ability to assess holistic optimization behavior. We introduce FormulaCode, a benchmark for evaluating agentic optimization on large, real-world codebases with fine-grained, multi-objective performance metrics. FormulaCode comprises 957 performance bottlenecks mined from "},"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":"2603.16011","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-03-16T23:40:19Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"8441450a42d14a5a9f886232fd3751c8f33be93fd62fd5c5a3f7d2d62dfa15f6","abstract_canon_sha256":"cc8c935f9e5c839725d4072a13f5b962a53af67f20765735b68eb3e0038692df"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:00:36.795721Z","signature_b64":"msbZ2CM9fbOnMvyHeS3AGKIk8SyzRz+qjyMxg9tadsbBp3ItFNgaTgW8jEfiVKncEMBpmQ7NJOsGMXOH7wd9DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a46f9a7e8c326c803f18d302770382b83590af62b766490dd06f644694d09717","last_reissued_at":"2026-05-20T00:00:36.795077Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:00:36.795077Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FormulaCode: Evaluating Agentic Optimization on Large Codebases","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.SE","authors_text":"Akanksha Sarkar, Atharva Sehgal, Ishaan Mantripragada, James Hou, Jennifer J. Sun, Swarat Chaudhuri, Yisong Yue","submitted_at":"2026-03-16T23:40:19Z","abstract_excerpt":"Large language model (LLM) coding agents increasingly operate at the repository level, motivating benchmarks that evaluate their ability to optimize entire codebases under realistic constraints. Existing code benchmarks largely rely on synthetic tasks, binary correctness signals, or single-objective evaluation, limiting their ability to assess holistic optimization behavior. We introduce FormulaCode, a benchmark for evaluating agentic optimization on large, real-world codebases with fine-grained, multi-objective performance metrics. FormulaCode comprises 957 performance bottlenecks mined from "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.16011","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/2603.16011/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":"2603.16011","created_at":"2026-05-20T00:00:36.795181+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.16011v2","created_at":"2026-05-20T00:00:36.795181+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.16011","created_at":"2026-05-20T00:00:36.795181+00:00"},{"alias_kind":"pith_short_12","alias_value":"URXZU7UMGJWI","created_at":"2026-05-20T00:00:36.795181+00:00"},{"alias_kind":"pith_short_16","alias_value":"URXZU7UMGJWIAPYY","created_at":"2026-05-20T00:00:36.795181+00:00"},{"alias_kind":"pith_short_8","alias_value":"URXZU7UM","created_at":"2026-05-20T00:00:36.795181+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/URXZU7UMGJWIAPYY2MBHOA4CXA","json":"https://pith.science/pith/URXZU7UMGJWIAPYY2MBHOA4CXA.json","graph_json":"https://pith.science/api/pith-number/URXZU7UMGJWIAPYY2MBHOA4CXA/graph.json","events_json":"https://pith.science/api/pith-number/URXZU7UMGJWIAPYY2MBHOA4CXA/events.json","paper":"https://pith.science/paper/URXZU7UM"},"agent_actions":{"view_html":"https://pith.science/pith/URXZU7UMGJWIAPYY2MBHOA4CXA","download_json":"https://pith.science/pith/URXZU7UMGJWIAPYY2MBHOA4CXA.json","view_paper":"https://pith.science/paper/URXZU7UM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.16011&json=true","fetch_graph":"https://pith.science/api/pith-number/URXZU7UMGJWIAPYY2MBHOA4CXA/graph.json","fetch_events":"https://pith.science/api/pith-number/URXZU7UMGJWIAPYY2MBHOA4CXA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/URXZU7UMGJWIAPYY2MBHOA4CXA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/URXZU7UMGJWIAPYY2MBHOA4CXA/action/storage_attestation","attest_author":"https://pith.science/pith/URXZU7UMGJWIAPYY2MBHOA4CXA/action/author_attestation","sign_citation":"https://pith.science/pith/URXZU7UMGJWIAPYY2MBHOA4CXA/action/citation_signature","submit_replication":"https://pith.science/pith/URXZU7UMGJWIAPYY2MBHOA4CXA/action/replication_record"}},"created_at":"2026-05-20T00:00:36.795181+00:00","updated_at":"2026-05-20T00:00:36.795181+00:00"}