{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:N4KZ2OBIRTN5N3JZNDSUEJ32MB","short_pith_number":"pith:N4KZ2OBI","schema_version":"1.0","canonical_sha256":"6f159d38288cdbd6ed3968e542277a606c3a9018c70d554fc56d073f3c7f8f89","source":{"kind":"arxiv","id":"2605.15281","version":1},"attestation_state":"computed","paper":{"title":"Autonomous Intelligent Agents for Natural-Language-Driven Web Execution with Integrated Security Assurance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"An AI agent framework converts natural-language instructions into reliable web test scripts and OWASP-aligned security probes.","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Shrey Tyagi, Siva Rama Krishna Varma Bayyavarapu, Vinil Pasupuleti","submitted_at":"2026-05-14T18:00:30Z","abstract_excerpt":"Modern web test suites rot. A UI refactor breaks locators, a timing change causes race conditions, and within weeks developers abandon the suite entirely. This paper presents an AI-driven autonomous testing framework that addresses these failure modes through five integrated strategies - navigation reliability, context-aware selector generation, post-generation validation, smart wait injection, and failure learning - implemented over a containerised worker architecture that decouples orchestration from long-running browser execution. Evaluated across four production applications and 176 scenar"},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.15281","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2026-05-14T18:00:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0533a52c9c6ddc4216dc7de3c863b7574648ef8b55b1f10de75e9f6d13384a85","abstract_canon_sha256":"e07d5247f2ccda85101ec29a435e4016fbd108ec239017796ddec4550acc8d87"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:00:50.510780Z","signature_b64":"4V2YDhrES556D+D7wIT3t2htISH+FVHIi3ZBlH7PrnRvCSORYWdfOA/SwR4lB80ry6LOMk4RxGAHoROUgku6AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f159d38288cdbd6ed3968e542277a606c3a9018c70d554fc56d073f3c7f8f89","last_reissued_at":"2026-05-20T00:00:50.510046Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:00:50.510046Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Autonomous Intelligent Agents for Natural-Language-Driven Web Execution with Integrated Security Assurance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"An AI agent framework converts natural-language instructions into reliable web test scripts and OWASP-aligned security probes.","cross_cats":["cs.AI"],"primary_cat":"cs.CR","authors_text":"Shrey Tyagi, Siva Rama Krishna Varma Bayyavarapu, Vinil Pasupuleti","submitted_at":"2026-05-14T18:00:30Z","abstract_excerpt":"Modern web test suites rot. A UI refactor breaks locators, a timing change causes race conditions, and within weeks developers abandon the suite entirely. This paper presents an AI-driven autonomous testing framework that addresses these failure modes through five integrated strategies - navigation reliability, context-aware selector generation, post-generation validation, smart wait injection, and failure learning - implemented over a containerised worker architecture that decouples orchestration from long-running browser execution. Evaluated across four production applications and 176 scenar"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Evaluated across four production applications and 176 scenarios, the framework improves script generation success from 55% to 93%, achieves an 8x reduction in navigation failures, eliminates 80% of timing-related race conditions, and reduces test creation time by 75% compared to manual Selenium authoring. It detects 85% of authentication bypass vulnerabilities and 95% of input validation flaws with false positive rates below 12%.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The four production applications and 176 scenarios used for evaluation are representative of typical web applications and that natural-language descriptions of attack scenarios can be reliably mapped to complete OWASP-aligned probes without missing critical edge cases or introducing bias in the reported detection rates.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"AI agents generate and execute natural-language web tests with built-in security validation, raising success rates and cutting failures in production applications.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"An AI agent framework converts natural-language instructions into reliable web test scripts and OWASP-aligned security probes.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"d80ed0b79a292823cf63faf10700447685d4807cbe96ea796bc8cc38507236d8"},"source":{"id":"2605.15281","kind":"arxiv","version":1},"verdict":{"id":"763c3b3e-822a-4865-9c2a-ed9673d1eb6b","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T15:18:20.196900Z","strongest_claim":"Evaluated across four production applications and 176 scenarios, the framework improves script generation success from 55% to 93%, achieves an 8x reduction in navigation failures, eliminates 80% of timing-related race conditions, and reduces test creation time by 75% compared to manual Selenium authoring. It detects 85% of authentication bypass vulnerabilities and 95% of input validation flaws with false positive rates below 12%.","one_line_summary":"AI agents generate and execute natural-language web tests with built-in security validation, raising success rates and cutting failures in production applications.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The four production applications and 176 scenarios used for evaluation are representative of typical web applications and that natural-language descriptions of attack scenarios can be reliably mapped to complete OWASP-aligned probes without missing critical edge cases or introducing bias in the reported detection rates.","pith_extraction_headline":"An AI agent framework converts natural-language instructions into reliable web test scripts and OWASP-aligned security probes."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.15281/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_compliance","ran_at":"2026-05-19T15:31:34.045612Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T15:31:17.914015Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T14:41:54.250330Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T13:33:22.797186Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"7fc53c4f6aa1336730949671d7ca1605b0ca85d2951c6e833672f7c97ca01e84"},"references":{"count":21,"sample":[{"doi":"","year":2021,"title":"Evaluating Large Language Models Trained on Code","work_id":"042493e9-b26f-4b4e-bbde-382072ca9b08","ref_index":1,"cited_arxiv_id":"2107.03374","is_internal_anchor":true},{"doi":"","year":2014,"title":"Reducing Web Test Cases Aging by Means of Robust XPath Locators,","work_id":"96bf3264-554a-4cea-9bd7-5b0cabf0ce71","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"OW ASP Testing Guide v4.2,","work_id":"8146fee6-f8de-4d6d-ada7-77a1549e15fc","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2011,"title":"The Tangled Web: A Guide to Securing Modern Web Applications,","work_id":"1682fc12-7326-4fc6-8d78-ed18a161f7e7","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2012,"title":"Enemy of the State: A State-Aware Black-Box Web Vulnerability Scanner,","work_id":"95da4900-58f1-471d-a9c1-03406e9a961f","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":21,"snapshot_sha256":"749340b1eb862ae44695e1e6bb8ee6504ddee1f5edd7d33b90b0402553ec9f5c","internal_anchors":4},"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":"2605.15281","created_at":"2026-05-20T00:00:50.510166+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.15281v1","created_at":"2026-05-20T00:00:50.510166+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15281","created_at":"2026-05-20T00:00:50.510166+00:00"},{"alias_kind":"pith_short_12","alias_value":"N4KZ2OBIRTN5","created_at":"2026-05-20T00:00:50.510166+00:00"},{"alias_kind":"pith_short_16","alias_value":"N4KZ2OBIRTN5N3JZ","created_at":"2026-05-20T00:00:50.510166+00:00"},{"alias_kind":"pith_short_8","alias_value":"N4KZ2OBI","created_at":"2026-05-20T00:00:50.510166+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/N4KZ2OBIRTN5N3JZNDSUEJ32MB","json":"https://pith.science/pith/N4KZ2OBIRTN5N3JZNDSUEJ32MB.json","graph_json":"https://pith.science/api/pith-number/N4KZ2OBIRTN5N3JZNDSUEJ32MB/graph.json","events_json":"https://pith.science/api/pith-number/N4KZ2OBIRTN5N3JZNDSUEJ32MB/events.json","paper":"https://pith.science/paper/N4KZ2OBI"},"agent_actions":{"view_html":"https://pith.science/pith/N4KZ2OBIRTN5N3JZNDSUEJ32MB","download_json":"https://pith.science/pith/N4KZ2OBIRTN5N3JZNDSUEJ32MB.json","view_paper":"https://pith.science/paper/N4KZ2OBI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.15281&json=true","fetch_graph":"https://pith.science/api/pith-number/N4KZ2OBIRTN5N3JZNDSUEJ32MB/graph.json","fetch_events":"https://pith.science/api/pith-number/N4KZ2OBIRTN5N3JZNDSUEJ32MB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N4KZ2OBIRTN5N3JZNDSUEJ32MB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N4KZ2OBIRTN5N3JZNDSUEJ32MB/action/storage_attestation","attest_author":"https://pith.science/pith/N4KZ2OBIRTN5N3JZNDSUEJ32MB/action/author_attestation","sign_citation":"https://pith.science/pith/N4KZ2OBIRTN5N3JZNDSUEJ32MB/action/citation_signature","submit_replication":"https://pith.science/pith/N4KZ2OBIRTN5N3JZNDSUEJ32MB/action/replication_record"}},"created_at":"2026-05-20T00:00:50.510166+00:00","updated_at":"2026-05-20T00:00:50.510166+00:00"}