{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6FVGTDQS54ZABDYIUPSR5KOFEZ","short_pith_number":"pith:6FVGTDQS","schema_version":"1.0","canonical_sha256":"f16a698e12ef32008f08a3e51ea9c5265f959aa6bacc4e4270fd1b75b6417537","source":{"kind":"arxiv","id":"2606.15834","version":2},"attestation_state":"computed","paper":{"title":"AIChilles: Automatically Uncovering Hidden Weaknesses in AI-Evolved Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","cs.SY","eess.SY"],"primary_cat":"cs.AI","authors_text":"Ao Li, Ashwin Silla, Vyas Sekar, Yajie Zhou, Zaoxing Liu","submitted_at":"2026-06-14T14:24:25Z","abstract_excerpt":"The computer systems community has recently seen growing interest in AI-driven system evolution, where AI agents iteratively rewrite systems. Frameworks such as AdaEvolve and Engram report 12-60% score improvements over human-designed algorithms. While these results are promising, there are practical concerns if these AI-evolved programs can perform worse on unseen workloads and exhibit scalability regressions. Given the speed and scale of AI-generated code, we need automated mechanisms to uncover such identify hidden weaknesses in AI-evolved systems programs. To this end, we develop AIChilles"},"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":"2606.15834","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-14T14:24:25Z","cross_cats_sorted":["cs.CR","cs.SY","eess.SY"],"title_canon_sha256":"b98f3ff9120e1de72e61e6eeb162f4c274a45e33ecc386e3894173cb46c58d7a","abstract_canon_sha256":"411b92e258a18b8e257e89beabb62836ef53a4cf6035a98c034d709dd0eefeee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-25T01:18:38.922413Z","signature_b64":"GyyvCDcoxZibBhKvqtiHxQ/hXmCxQBZF/7WCVrQQ6+WD6nVXC+2ZevUaUdVwsrODO670K0YmnuSypU7OoLc9DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f16a698e12ef32008f08a3e51ea9c5265f959aa6bacc4e4270fd1b75b6417537","last_reissued_at":"2026-06-25T01:18:38.921922Z","signature_status":"signed_v1","first_computed_at":"2026-06-25T01:18:38.921922Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AIChilles: Automatically Uncovering Hidden Weaknesses in AI-Evolved Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","cs.SY","eess.SY"],"primary_cat":"cs.AI","authors_text":"Ao Li, Ashwin Silla, Vyas Sekar, Yajie Zhou, Zaoxing Liu","submitted_at":"2026-06-14T14:24:25Z","abstract_excerpt":"The computer systems community has recently seen growing interest in AI-driven system evolution, where AI agents iteratively rewrite systems. Frameworks such as AdaEvolve and Engram report 12-60% score improvements over human-designed algorithms. While these results are promising, there are practical concerns if these AI-evolved programs can perform worse on unseen workloads and exhibit scalability regressions. Given the speed and scale of AI-generated code, we need automated mechanisms to uncover such identify hidden weaknesses in AI-evolved systems programs. To this end, we develop AIChilles"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.15834","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/2606.15834/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":"2606.15834","created_at":"2026-06-25T01:18:38.921979+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.15834v2","created_at":"2026-06-25T01:18:38.921979+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.15834","created_at":"2026-06-25T01:18:38.921979+00:00"},{"alias_kind":"pith_short_12","alias_value":"6FVGTDQS54ZA","created_at":"2026-06-25T01:18:38.921979+00:00"},{"alias_kind":"pith_short_16","alias_value":"6FVGTDQS54ZABDYI","created_at":"2026-06-25T01:18:38.921979+00:00"},{"alias_kind":"pith_short_8","alias_value":"6FVGTDQS","created_at":"2026-06-25T01:18:38.921979+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/6FVGTDQS54ZABDYIUPSR5KOFEZ","json":"https://pith.science/pith/6FVGTDQS54ZABDYIUPSR5KOFEZ.json","graph_json":"https://pith.science/api/pith-number/6FVGTDQS54ZABDYIUPSR5KOFEZ/graph.json","events_json":"https://pith.science/api/pith-number/6FVGTDQS54ZABDYIUPSR5KOFEZ/events.json","paper":"https://pith.science/paper/6FVGTDQS"},"agent_actions":{"view_html":"https://pith.science/pith/6FVGTDQS54ZABDYIUPSR5KOFEZ","download_json":"https://pith.science/pith/6FVGTDQS54ZABDYIUPSR5KOFEZ.json","view_paper":"https://pith.science/paper/6FVGTDQS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.15834&json=true","fetch_graph":"https://pith.science/api/pith-number/6FVGTDQS54ZABDYIUPSR5KOFEZ/graph.json","fetch_events":"https://pith.science/api/pith-number/6FVGTDQS54ZABDYIUPSR5KOFEZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6FVGTDQS54ZABDYIUPSR5KOFEZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6FVGTDQS54ZABDYIUPSR5KOFEZ/action/storage_attestation","attest_author":"https://pith.science/pith/6FVGTDQS54ZABDYIUPSR5KOFEZ/action/author_attestation","sign_citation":"https://pith.science/pith/6FVGTDQS54ZABDYIUPSR5KOFEZ/action/citation_signature","submit_replication":"https://pith.science/pith/6FVGTDQS54ZABDYIUPSR5KOFEZ/action/replication_record"}},"created_at":"2026-06-25T01:18:38.921979+00:00","updated_at":"2026-06-25T01:18:38.921979+00:00"}