{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4TN2BK5JCQDGAS5ODCY3YCPPFQ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"7bcb07742fd781a5c0f6b12a11a6d74a04b160c6b6b359b7a63f990982e22cd1","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-06-04T09:24:30Z","title_canon_sha256":"d656bbf9c4d6515be730a0e9b3a5fea1497d42309a46c3bdc50d43ca55f39a2e"},"schema_version":"1.0","source":{"id":"2606.05920","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.05920","created_at":"2026-06-05T01:15:27Z"},{"alias_kind":"arxiv_version","alias_value":"2606.05920v1","created_at":"2026-06-05T01:15:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05920","created_at":"2026-06-05T01:15:27Z"},{"alias_kind":"pith_short_12","alias_value":"4TN2BK5JCQDG","created_at":"2026-06-05T01:15:27Z"},{"alias_kind":"pith_short_16","alias_value":"4TN2BK5JCQDGAS5O","created_at":"2026-06-05T01:15:27Z"},{"alias_kind":"pith_short_8","alias_value":"4TN2BK5J","created_at":"2026-06-05T01:15:27Z"}],"graph_snapshots":[{"event_id":"sha256:c64e6e5669dec41f00397a7d5970dec61fefaf30a4c96ce163fe36f398aa85f7","target":"graph","created_at":"2026-06-05T01:15:27Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2606.05920/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing code-generation benchmarks score a single mapping from a complete prompt to a one-shot output. However, real web development is different. Users seldom write a full spec at the start; many requirements only become clear once they look at an intermediate result and react to it. We present Asuka-Bench, a benchmark that pairs underspecified user intent with multi-round refinement, grounded in browser-rendered behavior. Each task is resolved through a closed loop: a Code Agent generates a web project, a UI Agent executes test cases on the deployed site, and a User LLM turns evaluation out","authors_text":"Fengjiao Chen, Jiaxing Liu, Liangtai Sun, Licheng Zhang, Lin Qiu, Shuang Zhou, Xin Wang, Xuezhi Cao, Xunliang Cai, Yaoming Zhu, Zhendong Mao","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-06-04T09:24:30Z","title":"Asuka-Bench: Benchmarking Code Agents on Underspecified User Intent and Multi-Round Refinement"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05920","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:331d123da8b46a798b261c4d47317f1ccb8fccf7979f41db8ec4ff0b9141e801","target":"record","created_at":"2026-06-05T01:15:27Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"7bcb07742fd781a5c0f6b12a11a6d74a04b160c6b6b359b7a63f990982e22cd1","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-06-04T09:24:30Z","title_canon_sha256":"d656bbf9c4d6515be730a0e9b3a5fea1497d42309a46c3bdc50d43ca55f39a2e"},"schema_version":"1.0","source":{"id":"2606.05920","kind":"arxiv","version":1}},"canonical_sha256":"e4dba0aba91406604bae18b1bc09ef2c3f95de1ebd7cb15cef0e7d54d989dfbc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e4dba0aba91406604bae18b1bc09ef2c3f95de1ebd7cb15cef0e7d54d989dfbc","first_computed_at":"2026-06-05T01:15:27.605362Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-05T01:15:27.605362Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"n9eDpAqZi5rr0xYj5UELk2IudzTIXL0BWrd7UWwg9G12lBuYstnDRNw8na2fqg1bzUgxMfnbiFrkaVDvVDqvAQ==","signature_status":"signed_v1","signed_at":"2026-06-05T01:15:27.605912Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.05920","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:331d123da8b46a798b261c4d47317f1ccb8fccf7979f41db8ec4ff0b9141e801","sha256:c64e6e5669dec41f00397a7d5970dec61fefaf30a4c96ce163fe36f398aa85f7"],"state_sha256":"5afd1f36a2823e22fae69707e02af2c38f7363b6506e4403531380228ff0d4e7"}