{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XS6UREEJUZPPMDUKJC6TWB3UID","short_pith_number":"pith:XS6UREEJ","schema_version":"1.0","canonical_sha256":"bcbd489089a65ef60e8a48bd3b077440f3500c178dcbcd2d34b78a4e9f4d74a0","source":{"kind":"arxiv","id":"2605.25665","version":1},"attestation_state":"computed","paper":{"title":"Meta-Engineering Harnesses for AI-Native Software Production: A Contract-Driven Adversarial Verification Architecture with Early Deployment Report","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Ivan Myshakivskyi, Satadru Sengupta, Tamunokorite Briggs","submitted_at":"2026-05-25T10:15:24Z","abstract_excerpt":"AI-native software development is often evaluated at the level of individual models, prompts, or generated artifacts. This framing is insufficient for production environments where software must be continuously produced, verified, deployed, maintained, and adapted across many operational contexts and long time horizons.\n  We present a meta-engineering harness: a software-production architecture that transforms operational and product feature requirements into explicit contracts, routes work through role-specialized AI agents, performs independent and adversarial verification, and continuously "},"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":"2605.25665","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-05-25T10:15:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"177b070dcbf1aa8e3393361543af50c808096a0f1843c1bbec648dea0f727abf","abstract_canon_sha256":"b5bc5f5c8561bac5b8c78709dafc35ddb6cb6c25378d816cc4b79cef9bcc8691"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:04:49.013490Z","signature_b64":"lzpBJ9nI8LntcX8gnn93+2nWoHbuNuqHRUOW7/EjAbvixydR+KfzGuVJxHFmZWO/3SOF/h3jktB6hYQnxcSGDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bcbd489089a65ef60e8a48bd3b077440f3500c178dcbcd2d34b78a4e9f4d74a0","last_reissued_at":"2026-05-26T02:04:49.012736Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:04:49.012736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Meta-Engineering Harnesses for AI-Native Software Production: A Contract-Driven Adversarial Verification Architecture with Early Deployment Report","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Ivan Myshakivskyi, Satadru Sengupta, Tamunokorite Briggs","submitted_at":"2026-05-25T10:15:24Z","abstract_excerpt":"AI-native software development is often evaluated at the level of individual models, prompts, or generated artifacts. This framing is insufficient for production environments where software must be continuously produced, verified, deployed, maintained, and adapted across many operational contexts and long time horizons.\n  We present a meta-engineering harness: a software-production architecture that transforms operational and product feature requirements into explicit contracts, routes work through role-specialized AI agents, performs independent and adversarial verification, and continuously "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25665","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/2605.25665/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":"2605.25665","created_at":"2026-05-26T02:04:49.012851+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.25665v1","created_at":"2026-05-26T02:04:49.012851+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25665","created_at":"2026-05-26T02:04:49.012851+00:00"},{"alias_kind":"pith_short_12","alias_value":"XS6UREEJUZPP","created_at":"2026-05-26T02:04:49.012851+00:00"},{"alias_kind":"pith_short_16","alias_value":"XS6UREEJUZPPMDUK","created_at":"2026-05-26T02:04:49.012851+00:00"},{"alias_kind":"pith_short_8","alias_value":"XS6UREEJ","created_at":"2026-05-26T02:04:49.012851+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.04967","citing_title":"From Prompt to Process: a Process Taxonomy and Comparative Assessment of Frameworks Supporting AI Software Development Agents","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XS6UREEJUZPPMDUKJC6TWB3UID","json":"https://pith.science/pith/XS6UREEJUZPPMDUKJC6TWB3UID.json","graph_json":"https://pith.science/api/pith-number/XS6UREEJUZPPMDUKJC6TWB3UID/graph.json","events_json":"https://pith.science/api/pith-number/XS6UREEJUZPPMDUKJC6TWB3UID/events.json","paper":"https://pith.science/paper/XS6UREEJ"},"agent_actions":{"view_html":"https://pith.science/pith/XS6UREEJUZPPMDUKJC6TWB3UID","download_json":"https://pith.science/pith/XS6UREEJUZPPMDUKJC6TWB3UID.json","view_paper":"https://pith.science/paper/XS6UREEJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.25665&json=true","fetch_graph":"https://pith.science/api/pith-number/XS6UREEJUZPPMDUKJC6TWB3UID/graph.json","fetch_events":"https://pith.science/api/pith-number/XS6UREEJUZPPMDUKJC6TWB3UID/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XS6UREEJUZPPMDUKJC6TWB3UID/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XS6UREEJUZPPMDUKJC6TWB3UID/action/storage_attestation","attest_author":"https://pith.science/pith/XS6UREEJUZPPMDUKJC6TWB3UID/action/author_attestation","sign_citation":"https://pith.science/pith/XS6UREEJUZPPMDUKJC6TWB3UID/action/citation_signature","submit_replication":"https://pith.science/pith/XS6UREEJUZPPMDUKJC6TWB3UID/action/replication_record"}},"created_at":"2026-05-26T02:04:49.012851+00:00","updated_at":"2026-05-26T02:04:49.012851+00:00"}