{"schema_version":"papers/paper-detail-v1","title":"ClawForge: Generating Executable Interactive Benchmarks for Command-Line Agents","surface":"papers","opportunity_kernel":{"paper_id":"5d5ab333-2103-446b-b63e-d41c35a4f95f","title":"ClawForge: Generating Executable Interactive Benchmarks for Command-Line Agents","authors":["Yuxiang Lai","Peng Xia","Haonian Ji","Kaiwen Xiong","Kaide Zeng","Jiaqi Liu","Fang Wu","Jike Zhong","Zeyu Zheng","Cihang Xie","Huaxiu Yao"],"arxiv_id":"2605.14133v1","doi":null,"published_at":"2026-05-13T21:34:08.000Z","score_object":{"overall":{"value":7,"scale":"0-10","confidence":0.85,"confidence_reason":"Backfilled from persisted papers.viability_score.","model_version":"phase0-web-fallback-v1","pipeline_version":"phase0-kernel-v1","computed_at":"2026-05-15T20:12:56.418Z","fresh_until":"2026-06-14T20:12:56.418Z","is_stale":false,"source_count":1,"missingness":[]},"technical":{"value":0,"scale":"0-10","confidence":0.15,"confidence_reason":"No canonical technical score row was available yet; marked low confidence.","model_version":"phase0-web-fallback-v1","pipeline_version":"phase0-kernel-v1","computed_at":"2026-05-15T20:12:56.418Z","fresh_until":"2026-05-29T20:12:56.418Z","is_stale":true,"source_count":0,"missingness":["paper_score_objects.technical"]},"commercial":{"value":4,"scale":"0-10","confidence":0.7,"confidence_reason":"Backfilled from persisted commercial_flags and repo availability.","model_version":"phase0-web-fallback-v1","pipeline_version":"phase0-kernel-v1","computed_at":"2026-05-15T20:12:56.418Z","fresh_until":"2026-06-14T20:12:56.418Z","is_stale":false,"source_count":1,"missingness":[]},"market":{"value":0,"scale":"0-10","confidence":0.15,"confidence_reason":"No canonical market score row was available yet; marked low confidence.","model_version":"phase0-web-fallback-v1","pipeline_version":"phase0-kernel-v1","computed_at":"2026-05-15T20:12:56.418Z","fresh_until":"2026-05-29T20:12:56.418Z","is_stale":true,"source_count":0,"missingness":["paper_score_objects.market"]},"team":{"value":0,"scale":"0-10","confidence":0.15,"confidence_reason":"No canonical team score row was available yet; marked low confidence.","model_version":"phase0-web-fallback-v1","pipeline_version":"phase0-kernel-v1","computed_at":"2026-05-15T20:12:56.418Z","fresh_until":"2026-05-29T20:12:56.418Z","is_stale":true,"source_count":0,"missingness":["paper_score_objects.team"]},"methodology":{"value":0,"scale":"0-10","confidence":0.15,"confidence_reason":"No canonical methodology score row was available yet; marked low confidence.","model_version":"phase0-web-fallback-v1","pipeline_version":"phase0-kernel-v1","computed_at":"2026-05-15T20:12:56.418Z","fresh_until":"2026-06-14T20:12:56.418Z","is_stale":false,"source_count":0,"missingness":["paper_score_objects.methodology"]}},"evidence_receipt":{"freshness":"fresh","proof_status":"unverified","repo_status":"unknown","references_count":0,"source_count":0,"coverage":0,"missingness":["paper_evidence_receipts.references_count","paper_evidence_receipts.coverage"],"unresolved_unknowns":["Canonical evidence receipt has not been materialized yet."],"last_verification_at":"2026-05-15T20:12:56.418Z"},"lineage_hash":"a7a4c77aa13d21b13e61b00e2dc0d9e7257c8bd697b52610c607c4fba69b0e28"},"distribution":null,"replication_evidence":[],"author_dna":[]}