{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:U75YBUGWGHBEVXS4VL4MAW7VJ7","short_pith_number":"pith:U75YBUGW","schema_version":"1.0","canonical_sha256":"a7fb80d0d631c24ade5caaf8c05bf54fd33f862259bc799ec3fd800a7a021897","source":{"kind":"arxiv","id":"2506.09003","version":2},"attestation_state":"computed","paper":{"title":"SWE-Flow: Synthesizing Software Engineering Data in a Test-Driven Manner","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Binyuan Hui, Jiajun Zhang, Jian Yang, Jiaxi Yang, Junyang Lin, Lei Zhang, Min Yang, Mouxiang Chen, Zeyu Cui","submitted_at":"2025-06-10T17:23:33Z","abstract_excerpt":"We introduce **SWE-Flow**, a novel data synthesis framework grounded in Test-Driven Development (TDD). Unlike existing software engineering data that rely on human-submitted issues, **SWE-Flow** automatically infers incremental development steps directly from unit tests, which inherently encapsulate high-level requirements. The core of **SWE-Flow** is the construction of a Runtime Dependency Graph (RDG), which precisely captures function interactions, enabling the generation of a structured, step-by-step *development schedule*. At each step, **SWE-Flow** produces a partial codebase, the corres"},"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":"2506.09003","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-10T17:23:33Z","cross_cats_sorted":[],"title_canon_sha256":"b63928e79f2bc02d85a4b42183cd51206e1b70434c322ed187514e649ba81fda","abstract_canon_sha256":"17f8c31626b3a8d38c7ebfc5aef52941b1d5ebc5eb2aa22c6622bb3cc8a254e8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:30.352290Z","signature_b64":"4t1laVak4FeBtDqdJDoNDruPplR9IkVtct6NgFfHHUpC+bmIgcLIupsZ/SWV+vOe7LMkd0m2NwPG169mpMEOCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7fb80d0d631c24ade5caaf8c05bf54fd33f862259bc799ec3fd800a7a021897","last_reissued_at":"2026-07-05T11:19:30.351692Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:30.351692Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SWE-Flow: Synthesizing Software Engineering Data in a Test-Driven Manner","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Binyuan Hui, Jiajun Zhang, Jian Yang, Jiaxi Yang, Junyang Lin, Lei Zhang, Min Yang, Mouxiang Chen, Zeyu Cui","submitted_at":"2025-06-10T17:23:33Z","abstract_excerpt":"We introduce **SWE-Flow**, a novel data synthesis framework grounded in Test-Driven Development (TDD). Unlike existing software engineering data that rely on human-submitted issues, **SWE-Flow** automatically infers incremental development steps directly from unit tests, which inherently encapsulate high-level requirements. The core of **SWE-Flow** is the construction of a Runtime Dependency Graph (RDG), which precisely captures function interactions, enabling the generation of a structured, step-by-step *development schedule*. At each step, **SWE-Flow** produces a partial codebase, the corres"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.09003","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/2506.09003/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":"2506.09003","created_at":"2026-07-05T11:19:30.351751+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.09003v2","created_at":"2026-07-05T11:19:30.351751+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.09003","created_at":"2026-07-05T11:19:30.351751+00:00"},{"alias_kind":"pith_short_12","alias_value":"U75YBUGWGHBE","created_at":"2026-07-05T11:19:30.351751+00:00"},{"alias_kind":"pith_short_16","alias_value":"U75YBUGWGHBEVXS4","created_at":"2026-07-05T11:19:30.351751+00:00"},{"alias_kind":"pith_short_8","alias_value":"U75YBUGW","created_at":"2026-07-05T11:19:30.351751+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18284","citing_title":"Breaking the Solver Bottleneck: Training Task Generators at the Learnable Frontier","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15226","citing_title":"Is Agentic AI Ready for Real-World Hardware Engineering? A Deep Dive with Phoenix-bench","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U75YBUGWGHBEVXS4VL4MAW7VJ7","json":"https://pith.science/pith/U75YBUGWGHBEVXS4VL4MAW7VJ7.json","graph_json":"https://pith.science/api/pith-number/U75YBUGWGHBEVXS4VL4MAW7VJ7/graph.json","events_json":"https://pith.science/api/pith-number/U75YBUGWGHBEVXS4VL4MAW7VJ7/events.json","paper":"https://pith.science/paper/U75YBUGW"},"agent_actions":{"view_html":"https://pith.science/pith/U75YBUGWGHBEVXS4VL4MAW7VJ7","download_json":"https://pith.science/pith/U75YBUGWGHBEVXS4VL4MAW7VJ7.json","view_paper":"https://pith.science/paper/U75YBUGW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.09003&json=true","fetch_graph":"https://pith.science/api/pith-number/U75YBUGWGHBEVXS4VL4MAW7VJ7/graph.json","fetch_events":"https://pith.science/api/pith-number/U75YBUGWGHBEVXS4VL4MAW7VJ7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U75YBUGWGHBEVXS4VL4MAW7VJ7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U75YBUGWGHBEVXS4VL4MAW7VJ7/action/storage_attestation","attest_author":"https://pith.science/pith/U75YBUGWGHBEVXS4VL4MAW7VJ7/action/author_attestation","sign_citation":"https://pith.science/pith/U75YBUGWGHBEVXS4VL4MAW7VJ7/action/citation_signature","submit_replication":"https://pith.science/pith/U75YBUGWGHBEVXS4VL4MAW7VJ7/action/replication_record"}},"created_at":"2026-07-05T11:19:30.351751+00:00","updated_at":"2026-07-05T11:19:30.351751+00:00"}