{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YKH7N7P6JWGHKG2LC72YAOJD2Q","short_pith_number":"pith:YKH7N7P6","schema_version":"1.0","canonical_sha256":"c28ff6fdfe4d8c751b4b17f5803923d4156ab238ce89f621741c2c859d6978ee","source":{"kind":"arxiv","id":"2508.02721","version":2},"attestation_state":"computed","paper":{"title":"Blueprint First, Model Second: A Framework for Deterministic LLM Workflow","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.PL"],"primary_cat":"cs.SE","authors_text":"Junfu Chen, Kun Zhao, Libin Qiu, Weizhi Huang, Wenkai Qiu, Xiaobo Xue, Xide Zou, Yuhang Ye, Zhirong Gao, Ziming Gui","submitted_at":"2025-08-01T03:10:00Z","abstract_excerpt":"While powerful, the inherent non-determinism of large language model (LLM) agents limits their application in structured operational environments where procedural fidelity and predictable execution are strict requirements. This limitation stems from current architectures that conflate probabilistic, high-level planning with low-level action execution within a single generative process. To address this, we introduce the \\textsc{Source Code Agent} framework, a new paradigm built on the ``Blueprint First, Model Second'' philosophy that decouples workflow logic from the generative model. An expert"},"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":"2508.02721","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-08-01T03:10:00Z","cross_cats_sorted":["cs.AI","cs.PL"],"title_canon_sha256":"58e11afbb9930376f55f6722f2f117ce9d5f813e1399e683c41955df114f766b","abstract_canon_sha256":"7f4ed43f829b6f4f62281b601d59e67b13dd36c5f8a7cb8894f0bcc1923224d5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:10:30.745869Z","signature_b64":"3VPvApPdct/CXiycZO2qHam5AJ5UPGKwIqyMbeuqbHSMAwT08wpDVeODMyHGYS4YsMez5JI6dq5o2WfwxHAVDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c28ff6fdfe4d8c751b4b17f5803923d4156ab238ce89f621741c2c859d6978ee","last_reissued_at":"2026-06-19T16:10:30.745444Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:10:30.745444Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Blueprint First, Model Second: A Framework for Deterministic LLM Workflow","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.PL"],"primary_cat":"cs.SE","authors_text":"Junfu Chen, Kun Zhao, Libin Qiu, Weizhi Huang, Wenkai Qiu, Xiaobo Xue, Xide Zou, Yuhang Ye, Zhirong Gao, Ziming Gui","submitted_at":"2025-08-01T03:10:00Z","abstract_excerpt":"While powerful, the inherent non-determinism of large language model (LLM) agents limits their application in structured operational environments where procedural fidelity and predictable execution are strict requirements. This limitation stems from current architectures that conflate probabilistic, high-level planning with low-level action execution within a single generative process. To address this, we introduce the \\textsc{Source Code Agent} framework, a new paradigm built on the ``Blueprint First, Model Second'' philosophy that decouples workflow logic from the generative model. An expert"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.02721","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/2508.02721/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":"2508.02721","created_at":"2026-06-19T16:10:30.745502+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.02721v2","created_at":"2026-06-19T16:10:30.745502+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.02721","created_at":"2026-06-19T16:10:30.745502+00:00"},{"alias_kind":"pith_short_12","alias_value":"YKH7N7P6JWGH","created_at":"2026-06-19T16:10:30.745502+00:00"},{"alias_kind":"pith_short_16","alias_value":"YKH7N7P6JWGHKG2L","created_at":"2026-06-19T16:10:30.745502+00:00"},{"alias_kind":"pith_short_8","alias_value":"YKH7N7P6","created_at":"2026-06-19T16:10:30.745502+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"2606.00288","citing_title":"Model-Native Computing Architecture: Envisioning Future System Architecture Through the Lens of Computer Architecture","ref_index":129,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21712","citing_title":"Broadening Access to Transportation Safety Data with Generative AI: A Schema-Grounded Framework for Spatial Natural Language Queries","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13848","citing_title":"GraphBit: A Graph-based Agentic Framework for Non-Linear Agent Orchestration","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09894","citing_title":"Deterministic vs. LLM-Controlled Orchestration for COBOL-to-Python Modernization","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YKH7N7P6JWGHKG2LC72YAOJD2Q","json":"https://pith.science/pith/YKH7N7P6JWGHKG2LC72YAOJD2Q.json","graph_json":"https://pith.science/api/pith-number/YKH7N7P6JWGHKG2LC72YAOJD2Q/graph.json","events_json":"https://pith.science/api/pith-number/YKH7N7P6JWGHKG2LC72YAOJD2Q/events.json","paper":"https://pith.science/paper/YKH7N7P6"},"agent_actions":{"view_html":"https://pith.science/pith/YKH7N7P6JWGHKG2LC72YAOJD2Q","download_json":"https://pith.science/pith/YKH7N7P6JWGHKG2LC72YAOJD2Q.json","view_paper":"https://pith.science/paper/YKH7N7P6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.02721&json=true","fetch_graph":"https://pith.science/api/pith-number/YKH7N7P6JWGHKG2LC72YAOJD2Q/graph.json","fetch_events":"https://pith.science/api/pith-number/YKH7N7P6JWGHKG2LC72YAOJD2Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YKH7N7P6JWGHKG2LC72YAOJD2Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YKH7N7P6JWGHKG2LC72YAOJD2Q/action/storage_attestation","attest_author":"https://pith.science/pith/YKH7N7P6JWGHKG2LC72YAOJD2Q/action/author_attestation","sign_citation":"https://pith.science/pith/YKH7N7P6JWGHKG2LC72YAOJD2Q/action/citation_signature","submit_replication":"https://pith.science/pith/YKH7N7P6JWGHKG2LC72YAOJD2Q/action/replication_record"}},"created_at":"2026-06-19T16:10:30.745502+00:00","updated_at":"2026-06-19T16:10:30.745502+00:00"}