{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EBDAISMP44LPDOFHFBXV4JBBTZ","short_pith_number":"pith:EBDAISMP","schema_version":"1.0","canonical_sha256":"204604498fe716f1b8a7286f5e24219e6b44bba9dc0338308a5a4de02ce6a176","source":{"kind":"arxiv","id":"2605.22368","version":1},"attestation_state":"computed","paper":{"title":"VeriScale: Adversarial Test-Suite Scaling for Verifiable Code Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SE"],"primary_cat":"cs.LG","authors_text":"Guihong Wang, Jian Yu, Jingwei Liang, Shuhan Xie, Tao Luo, Xiaoyang Liu, Yangyu Zhang, Yantao Li, Yifan Bai, Zihao Mou","submitted_at":"2026-05-21T12:00:45Z","abstract_excerpt":"As large language models (LLMs) are increasingly deployed for software engineering, constructing high-quality benchmarks is crucial for evaluating not just the functional correctness, but also the formal verifiability of generated code. However, existing benchmarks are limited by the quantity and quality of positive and negative test cases, leading to an overestimation of model capabilities in generating specifications and implementations. To address this, we propose VeriScale, a novel framework driven by the adversarial implementations. It consists of two stages: test-suite expansion to const"},"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":"2605.22368","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-21T12:00:45Z","cross_cats_sorted":["cs.AI","cs.SE"],"title_canon_sha256":"6b70f45387510f3d51d2f4df62f2ed4d386c4177ec20f481b3b6b662fb87c069","abstract_canon_sha256":"563d3c328c34a3faf2f8f4a959450a427b80d452b1d843a86929da33643ae241"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:04:40.096625Z","signature_b64":"B0BuFmRK4P2X7Cghg2TIOiIe0PoMyG42pJddYVXcokg4gOraTqA1g/4i0PxhIrhuQGEYAUtAr5Uko8qBvVPyAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"204604498fe716f1b8a7286f5e24219e6b44bba9dc0338308a5a4de02ce6a176","last_reissued_at":"2026-05-22T01:04:40.095844Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:04:40.095844Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VeriScale: Adversarial Test-Suite Scaling for Verifiable Code Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SE"],"primary_cat":"cs.LG","authors_text":"Guihong Wang, Jian Yu, Jingwei Liang, Shuhan Xie, Tao Luo, Xiaoyang Liu, Yangyu Zhang, Yantao Li, Yifan Bai, Zihao Mou","submitted_at":"2026-05-21T12:00:45Z","abstract_excerpt":"As large language models (LLMs) are increasingly deployed for software engineering, constructing high-quality benchmarks is crucial for evaluating not just the functional correctness, but also the formal verifiability of generated code. However, existing benchmarks are limited by the quantity and quality of positive and negative test cases, leading to an overestimation of model capabilities in generating specifications and implementations. To address this, we propose VeriScale, a novel framework driven by the adversarial implementations. It consists of two stages: test-suite expansion to const"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22368","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/2605.22368/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":"2605.22368","created_at":"2026-05-22T01:04:40.095973+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.22368v1","created_at":"2026-05-22T01:04:40.095973+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22368","created_at":"2026-05-22T01:04:40.095973+00:00"},{"alias_kind":"pith_short_12","alias_value":"EBDAISMP44LP","created_at":"2026-05-22T01:04:40.095973+00:00"},{"alias_kind":"pith_short_16","alias_value":"EBDAISMP44LPDOFH","created_at":"2026-05-22T01:04:40.095973+00:00"},{"alias_kind":"pith_short_8","alias_value":"EBDAISMP","created_at":"2026-05-22T01:04:40.095973+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/EBDAISMP44LPDOFHFBXV4JBBTZ","json":"https://pith.science/pith/EBDAISMP44LPDOFHFBXV4JBBTZ.json","graph_json":"https://pith.science/api/pith-number/EBDAISMP44LPDOFHFBXV4JBBTZ/graph.json","events_json":"https://pith.science/api/pith-number/EBDAISMP44LPDOFHFBXV4JBBTZ/events.json","paper":"https://pith.science/paper/EBDAISMP"},"agent_actions":{"view_html":"https://pith.science/pith/EBDAISMP44LPDOFHFBXV4JBBTZ","download_json":"https://pith.science/pith/EBDAISMP44LPDOFHFBXV4JBBTZ.json","view_paper":"https://pith.science/paper/EBDAISMP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.22368&json=true","fetch_graph":"https://pith.science/api/pith-number/EBDAISMP44LPDOFHFBXV4JBBTZ/graph.json","fetch_events":"https://pith.science/api/pith-number/EBDAISMP44LPDOFHFBXV4JBBTZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EBDAISMP44LPDOFHFBXV4JBBTZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EBDAISMP44LPDOFHFBXV4JBBTZ/action/storage_attestation","attest_author":"https://pith.science/pith/EBDAISMP44LPDOFHFBXV4JBBTZ/action/author_attestation","sign_citation":"https://pith.science/pith/EBDAISMP44LPDOFHFBXV4JBBTZ/action/citation_signature","submit_replication":"https://pith.science/pith/EBDAISMP44LPDOFHFBXV4JBBTZ/action/replication_record"}},"created_at":"2026-05-22T01:04:40.095973+00:00","updated_at":"2026-05-22T01:04:40.095973+00:00"}