{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HEDVAEUVYJO3XXRVOBO4QAQBFL","short_pith_number":"pith:HEDVAEUV","schema_version":"1.0","canonical_sha256":"3907501295c25dbbde35705dc802012ac08dbda817a8660fd4393767ce2e8698","source":{"kind":"arxiv","id":"2508.18675","version":1},"attestation_state":"computed","paper":{"title":"Requirements Development and Formalization for Reliable Code Generation: A Multi-Agent Vision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Cong Tian, Ming Hu, Weisong Sun, Xu Lu, Yang Liu, Yiran Zhang, Zhi Jin","submitted_at":"2025-08-26T04:45:04Z","abstract_excerpt":"Automated code generation has long been considered the holy grail of software engineering. The emergence of Large Language Models (LLMs) has catalyzed a revolutionary breakthrough in this area. However, existing methods that only rely on LLMs remain inadequate in the quality of generated code, offering no guarantees of satisfying practical requirements. They lack a systematic strategy for requirements development and modeling. Recently, LLM-based agents typically possess powerful abilities and play an essential role in facilitating the alignment of LLM outputs with user requirements. In this p"},"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":"2508.18675","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-08-26T04:45:04Z","cross_cats_sorted":[],"title_canon_sha256":"4f9e1f109319e649ffd8c35bb8369efd206cde37a96f1019ffde7956bc28faf1","abstract_canon_sha256":"5a27f15b6370ef1a1a68c018110fc444eb7db4bbad54831684edc2332bee345e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:59:29.136875Z","signature_b64":"/lE9H552JOsIZVDAx4eUcIK2e7qqFMhnKFG5fUv5YLPbdryHVhIE6Uzhw7hZR/wsToeeUnZTj5ZVfal0SaPDCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3907501295c25dbbde35705dc802012ac08dbda817a8660fd4393767ce2e8698","last_reissued_at":"2026-07-05T11:59:29.136452Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:59:29.136452Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Requirements Development and Formalization for Reliable Code Generation: A Multi-Agent Vision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Cong Tian, Ming Hu, Weisong Sun, Xu Lu, Yang Liu, Yiran Zhang, Zhi Jin","submitted_at":"2025-08-26T04:45:04Z","abstract_excerpt":"Automated code generation has long been considered the holy grail of software engineering. The emergence of Large Language Models (LLMs) has catalyzed a revolutionary breakthrough in this area. However, existing methods that only rely on LLMs remain inadequate in the quality of generated code, offering no guarantees of satisfying practical requirements. They lack a systematic strategy for requirements development and modeling. Recently, LLM-based agents typically possess powerful abilities and play an essential role in facilitating the alignment of LLM outputs with user requirements. In this p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.18675","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/2508.18675/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":"2508.18675","created_at":"2026-07-05T11:59:29.136508+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.18675v1","created_at":"2026-07-05T11:59:29.136508+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.18675","created_at":"2026-07-05T11:59:29.136508+00:00"},{"alias_kind":"pith_short_12","alias_value":"HEDVAEUVYJO3","created_at":"2026-07-05T11:59:29.136508+00:00"},{"alias_kind":"pith_short_16","alias_value":"HEDVAEUVYJO3XXRV","created_at":"2026-07-05T11:59:29.136508+00:00"},{"alias_kind":"pith_short_8","alias_value":"HEDVAEUV","created_at":"2026-07-05T11:59:29.136508+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.18747","citing_title":"Code as Agent Harness","ref_index":172,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HEDVAEUVYJO3XXRVOBO4QAQBFL","json":"https://pith.science/pith/HEDVAEUVYJO3XXRVOBO4QAQBFL.json","graph_json":"https://pith.science/api/pith-number/HEDVAEUVYJO3XXRVOBO4QAQBFL/graph.json","events_json":"https://pith.science/api/pith-number/HEDVAEUVYJO3XXRVOBO4QAQBFL/events.json","paper":"https://pith.science/paper/HEDVAEUV"},"agent_actions":{"view_html":"https://pith.science/pith/HEDVAEUVYJO3XXRVOBO4QAQBFL","download_json":"https://pith.science/pith/HEDVAEUVYJO3XXRVOBO4QAQBFL.json","view_paper":"https://pith.science/paper/HEDVAEUV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.18675&json=true","fetch_graph":"https://pith.science/api/pith-number/HEDVAEUVYJO3XXRVOBO4QAQBFL/graph.json","fetch_events":"https://pith.science/api/pith-number/HEDVAEUVYJO3XXRVOBO4QAQBFL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HEDVAEUVYJO3XXRVOBO4QAQBFL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HEDVAEUVYJO3XXRVOBO4QAQBFL/action/storage_attestation","attest_author":"https://pith.science/pith/HEDVAEUVYJO3XXRVOBO4QAQBFL/action/author_attestation","sign_citation":"https://pith.science/pith/HEDVAEUVYJO3XXRVOBO4QAQBFL/action/citation_signature","submit_replication":"https://pith.science/pith/HEDVAEUVYJO3XXRVOBO4QAQBFL/action/replication_record"}},"created_at":"2026-07-05T11:59:29.136508+00:00","updated_at":"2026-07-05T11:59:29.136508+00:00"}