{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MSJ7FJ2C3TIY4COPZ6C7VPQLNM","short_pith_number":"pith:MSJ7FJ2C","schema_version":"1.0","canonical_sha256":"6493f2a742dcd18e09cfcf85fabe0b6b16e5d8c81fa5e1134a7e134f68584932","source":{"kind":"arxiv","id":"2606.25530","version":1},"attestation_state":"computed","paper":{"title":"Evaluating LLMs on Real-World Software Performance Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.SE","authors_text":"Chunyang Chen, Ezgi Sar{\\i}kayak, Hesham Ghonim, Wenchao Gu","submitted_at":"2026-06-24T08:07:41Z","abstract_excerpt":"Software performance optimization is a notoriously complex and manual task. Despite the growing use of Large Language Models (LLMs) for code refinement, we still lack benchmarks that capture how optimization actually happens in real-world codebases. Existing frameworks often oversimplify the problem by focusing on isolated functions or a single performance metric, missing the critical trade-offs between execution time and memory footprint, the inherent noise of the measurement environment, and the variability introduced by different input data and execution conditions. We address this by intro"},"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":"2606.25530","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-06-24T08:07:41Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"922602f997c9919eb44abd50756d5c1596f4e7f89e990b8f8f6fd6a7681a053b","abstract_canon_sha256":"5385e2222426867ea9167413469b7d85bc71a8552e01911c36e6c7dfe00839d0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-25T01:18:08.017039Z","signature_b64":"g9/2C+5NIznY/MkO85C5/0JR2cRU1Lxl45e/gvxWYeA0JBcmAqd+dgc1X8Kf91x1W0l7R+JgxFUsIl+tQmWWDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6493f2a742dcd18e09cfcf85fabe0b6b16e5d8c81fa5e1134a7e134f68584932","last_reissued_at":"2026-06-25T01:18:08.016546Z","signature_status":"signed_v1","first_computed_at":"2026-06-25T01:18:08.016546Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating LLMs on Real-World Software Performance Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.SE","authors_text":"Chunyang Chen, Ezgi Sar{\\i}kayak, Hesham Ghonim, Wenchao Gu","submitted_at":"2026-06-24T08:07:41Z","abstract_excerpt":"Software performance optimization is a notoriously complex and manual task. Despite the growing use of Large Language Models (LLMs) for code refinement, we still lack benchmarks that capture how optimization actually happens in real-world codebases. Existing frameworks often oversimplify the problem by focusing on isolated functions or a single performance metric, missing the critical trade-offs between execution time and memory footprint, the inherent noise of the measurement environment, and the variability introduced by different input data and execution conditions. We address this by intro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.25530","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/2606.25530/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":"2606.25530","created_at":"2026-06-25T01:18:08.016608+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.25530v1","created_at":"2026-06-25T01:18:08.016608+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.25530","created_at":"2026-06-25T01:18:08.016608+00:00"},{"alias_kind":"pith_short_12","alias_value":"MSJ7FJ2C3TIY","created_at":"2026-06-25T01:18:08.016608+00:00"},{"alias_kind":"pith_short_16","alias_value":"MSJ7FJ2C3TIY4COP","created_at":"2026-06-25T01:18:08.016608+00:00"},{"alias_kind":"pith_short_8","alias_value":"MSJ7FJ2C","created_at":"2026-06-25T01:18:08.016608+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/MSJ7FJ2C3TIY4COPZ6C7VPQLNM","json":"https://pith.science/pith/MSJ7FJ2C3TIY4COPZ6C7VPQLNM.json","graph_json":"https://pith.science/api/pith-number/MSJ7FJ2C3TIY4COPZ6C7VPQLNM/graph.json","events_json":"https://pith.science/api/pith-number/MSJ7FJ2C3TIY4COPZ6C7VPQLNM/events.json","paper":"https://pith.science/paper/MSJ7FJ2C"},"agent_actions":{"view_html":"https://pith.science/pith/MSJ7FJ2C3TIY4COPZ6C7VPQLNM","download_json":"https://pith.science/pith/MSJ7FJ2C3TIY4COPZ6C7VPQLNM.json","view_paper":"https://pith.science/paper/MSJ7FJ2C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.25530&json=true","fetch_graph":"https://pith.science/api/pith-number/MSJ7FJ2C3TIY4COPZ6C7VPQLNM/graph.json","fetch_events":"https://pith.science/api/pith-number/MSJ7FJ2C3TIY4COPZ6C7VPQLNM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MSJ7FJ2C3TIY4COPZ6C7VPQLNM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MSJ7FJ2C3TIY4COPZ6C7VPQLNM/action/storage_attestation","attest_author":"https://pith.science/pith/MSJ7FJ2C3TIY4COPZ6C7VPQLNM/action/author_attestation","sign_citation":"https://pith.science/pith/MSJ7FJ2C3TIY4COPZ6C7VPQLNM/action/citation_signature","submit_replication":"https://pith.science/pith/MSJ7FJ2C3TIY4COPZ6C7VPQLNM/action/replication_record"}},"created_at":"2026-06-25T01:18:08.016608+00:00","updated_at":"2026-06-25T01:18:08.016608+00:00"}