{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GFY6LI2H5DJBQLQFUUDL4F3JZY","short_pith_number":"pith:GFY6LI2H","schema_version":"1.0","canonical_sha256":"3171e5a347e8d2182e05a506be1769ce1ef47e63aca21df835dc555bace0cebe","source":{"kind":"arxiv","id":"2504.20412","version":2},"attestation_state":"computed","paper":{"title":"CrashFixer: A crash resolution agent for the Linux kernel","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.OS"],"primary_cat":"cs.SE","authors_text":"Aleksandr Nogikh, Alex Mathai, Baishakhi Ray, Chenxi Huang, Franjo Ivan\\v{c}i\\'c, Hailie Mitchell, Jihwan Kim, Junfeng Yang, Petros Maniatis, Suwei Ma","submitted_at":"2025-04-29T04:18:51Z","abstract_excerpt":"Code large language models (LLMs) have shown impressive capabilities on a multitude of software engineering tasks. In particular, they have demonstrated remarkable utility in the task of code repair. However, common benchmarks used to evaluate the performance of code LLMs are often limited to small-scale settings. In this work, we build upon kGym, which shares a benchmark for system-level Linux kernel bugs and a platform to run experiments on the Linux kernel.\n  This paper introduces CrashFixer, the first LLM-based software repair agent that is applicable to Linux kernel bugs. Inspired by the "},"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":"2504.20412","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-04-29T04:18:51Z","cross_cats_sorted":["cs.AI","cs.OS"],"title_canon_sha256":"2c233d70470d9e64537a3b3eaccd4fdd5a66fea483c019dad83cd1d4c63b946e","abstract_canon_sha256":"a8b271b3d8bc1b27368e5ad80f1d034b68b757352fd66fa02eeb9bebc2757f62"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:02:43.326755Z","signature_b64":"8XchnlymFCnr4QE0B2CN1UG7/IzY45kUtTXXOp25Ohhg3zWSEDoBP6+4LS2CGKUrc1IPdntyqz+7hNBi1eDqBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3171e5a347e8d2182e05a506be1769ce1ef47e63aca21df835dc555bace0cebe","last_reissued_at":"2026-07-05T11:02:43.325937Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:02:43.325937Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CrashFixer: A crash resolution agent for the Linux kernel","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.OS"],"primary_cat":"cs.SE","authors_text":"Aleksandr Nogikh, Alex Mathai, Baishakhi Ray, Chenxi Huang, Franjo Ivan\\v{c}i\\'c, Hailie Mitchell, Jihwan Kim, Junfeng Yang, Petros Maniatis, Suwei Ma","submitted_at":"2025-04-29T04:18:51Z","abstract_excerpt":"Code large language models (LLMs) have shown impressive capabilities on a multitude of software engineering tasks. In particular, they have demonstrated remarkable utility in the task of code repair. However, common benchmarks used to evaluate the performance of code LLMs are often limited to small-scale settings. In this work, we build upon kGym, which shares a benchmark for system-level Linux kernel bugs and a platform to run experiments on the Linux kernel.\n  This paper introduces CrashFixer, the first LLM-based software repair agent that is applicable to Linux kernel bugs. Inspired by the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.20412","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/2504.20412/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":"2504.20412","created_at":"2026-07-05T11:02:43.326038+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.20412v2","created_at":"2026-07-05T11:02:43.326038+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.20412","created_at":"2026-07-05T11:02:43.326038+00:00"},{"alias_kind":"pith_short_12","alias_value":"GFY6LI2H5DJB","created_at":"2026-07-05T11:02:43.326038+00:00"},{"alias_kind":"pith_short_16","alias_value":"GFY6LI2H5DJBQLQF","created_at":"2026-07-05T11:02:43.326038+00:00"},{"alias_kind":"pith_short_8","alias_value":"GFY6LI2H","created_at":"2026-07-05T11:02:43.326038+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.11060","citing_title":"Code Researcher: Deep Research Agent for Large Systems Code and Commit History","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GFY6LI2H5DJBQLQFUUDL4F3JZY","json":"https://pith.science/pith/GFY6LI2H5DJBQLQFUUDL4F3JZY.json","graph_json":"https://pith.science/api/pith-number/GFY6LI2H5DJBQLQFUUDL4F3JZY/graph.json","events_json":"https://pith.science/api/pith-number/GFY6LI2H5DJBQLQFUUDL4F3JZY/events.json","paper":"https://pith.science/paper/GFY6LI2H"},"agent_actions":{"view_html":"https://pith.science/pith/GFY6LI2H5DJBQLQFUUDL4F3JZY","download_json":"https://pith.science/pith/GFY6LI2H5DJBQLQFUUDL4F3JZY.json","view_paper":"https://pith.science/paper/GFY6LI2H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.20412&json=true","fetch_graph":"https://pith.science/api/pith-number/GFY6LI2H5DJBQLQFUUDL4F3JZY/graph.json","fetch_events":"https://pith.science/api/pith-number/GFY6LI2H5DJBQLQFUUDL4F3JZY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GFY6LI2H5DJBQLQFUUDL4F3JZY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GFY6LI2H5DJBQLQFUUDL4F3JZY/action/storage_attestation","attest_author":"https://pith.science/pith/GFY6LI2H5DJBQLQFUUDL4F3JZY/action/author_attestation","sign_citation":"https://pith.science/pith/GFY6LI2H5DJBQLQFUUDL4F3JZY/action/citation_signature","submit_replication":"https://pith.science/pith/GFY6LI2H5DJBQLQFUUDL4F3JZY/action/replication_record"}},"created_at":"2026-07-05T11:02:43.326038+00:00","updated_at":"2026-07-05T11:02:43.326038+00:00"}