{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YSQUUTZMCRYETQYL3SF4BPECIT","short_pith_number":"pith:YSQUUTZM","schema_version":"1.0","canonical_sha256":"c4a14a4f2c147049c30bdc8bc0bc8244ff71b31cbaa72d1f2030779cb4fee142","source":{"kind":"arxiv","id":"2603.04390","version":2},"attestation_state":"computed","paper":{"title":"A Dual-Helix Governance Approach Towards Reliable Agentic Artificial Intelligence for WebGIS Development","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.AI","authors_text":"Boyuan Guan, Levente Juhasz, Wencong Cui","submitted_at":"2026-03-04T18:53:25Z","abstract_excerpt":"WebGIS development requires consistency, yet agentic AI often fails due to LLM context constraints, forgetting, stochasticity, instruction failure, and adaptation rigidity. We propose a dual-helix governance framework reframing these as structural problems rather than capacity deficits. Using a 3-track architecture (Knowledge, Behavior, Skills) and a persistent knowledge graph, it stabilizes execution by externalizing facts and enforcing protocols. Validation shows a governed agent successfully refactored a legacy WebGIS codebase (reducing cyclomatic complexity and improving maintainability), "},"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":"2603.04390","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-03-04T18:53:25Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"e5161db0c8d8fc2d11a5f73f6c00d97db24dd0d8c88be78d7b435298c47520ee","abstract_canon_sha256":"c97805eddd814b139519187be6b7053b315f03bc1a0583228d23c2ef3aee000d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T01:17:18.217877Z","signature_b64":"QRDAdCtNC+OwtBE77jSgtu9PQMZtdgBSwmEBwATDdqp51puurMpGOxLtQTB38IJs9I6uQ/unGIm/jLBXg0EaBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c4a14a4f2c147049c30bdc8bc0bc8244ff71b31cbaa72d1f2030779cb4fee142","last_reissued_at":"2026-07-03T01:17:18.217462Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T01:17:18.217462Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Dual-Helix Governance Approach Towards Reliable Agentic Artificial Intelligence for WebGIS Development","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.AI","authors_text":"Boyuan Guan, Levente Juhasz, Wencong Cui","submitted_at":"2026-03-04T18:53:25Z","abstract_excerpt":"WebGIS development requires consistency, yet agentic AI often fails due to LLM context constraints, forgetting, stochasticity, instruction failure, and adaptation rigidity. We propose a dual-helix governance framework reframing these as structural problems rather than capacity deficits. Using a 3-track architecture (Knowledge, Behavior, Skills) and a persistent knowledge graph, it stabilizes execution by externalizing facts and enforcing protocols. Validation shows a governed agent successfully refactored a legacy WebGIS codebase (reducing cyclomatic complexity and improving maintainability), "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.04390","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/2603.04390/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":"2603.04390","created_at":"2026-07-03T01:17:18.217515+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.04390v2","created_at":"2026-07-03T01:17:18.217515+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.04390","created_at":"2026-07-03T01:17:18.217515+00:00"},{"alias_kind":"pith_short_12","alias_value":"YSQUUTZMCRYE","created_at":"2026-07-03T01:17:18.217515+00:00"},{"alias_kind":"pith_short_16","alias_value":"YSQUUTZMCRYETQYL","created_at":"2026-07-03T01:17:18.217515+00:00"},{"alias_kind":"pith_short_8","alias_value":"YSQUUTZM","created_at":"2026-07-03T01:17:18.217515+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.22484","citing_title":"Governed AI-Assisted Engineering: Graduated Human Oversight for Agentic Code Generation in Regulated Domains","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YSQUUTZMCRYETQYL3SF4BPECIT","json":"https://pith.science/pith/YSQUUTZMCRYETQYL3SF4BPECIT.json","graph_json":"https://pith.science/api/pith-number/YSQUUTZMCRYETQYL3SF4BPECIT/graph.json","events_json":"https://pith.science/api/pith-number/YSQUUTZMCRYETQYL3SF4BPECIT/events.json","paper":"https://pith.science/paper/YSQUUTZM"},"agent_actions":{"view_html":"https://pith.science/pith/YSQUUTZMCRYETQYL3SF4BPECIT","download_json":"https://pith.science/pith/YSQUUTZMCRYETQYL3SF4BPECIT.json","view_paper":"https://pith.science/paper/YSQUUTZM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.04390&json=true","fetch_graph":"https://pith.science/api/pith-number/YSQUUTZMCRYETQYL3SF4BPECIT/graph.json","fetch_events":"https://pith.science/api/pith-number/YSQUUTZMCRYETQYL3SF4BPECIT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YSQUUTZMCRYETQYL3SF4BPECIT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YSQUUTZMCRYETQYL3SF4BPECIT/action/storage_attestation","attest_author":"https://pith.science/pith/YSQUUTZMCRYETQYL3SF4BPECIT/action/author_attestation","sign_citation":"https://pith.science/pith/YSQUUTZMCRYETQYL3SF4BPECIT/action/citation_signature","submit_replication":"https://pith.science/pith/YSQUUTZMCRYETQYL3SF4BPECIT/action/replication_record"}},"created_at":"2026-07-03T01:17:18.217515+00:00","updated_at":"2026-07-03T01:17:18.217515+00:00"}