{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:EE2J7NHHPUMEKMM4DCV6Q4LWHK","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":"9999d7e83c1ba616c29727dbc12d6aa8090a3f64a596ee6b0d068024b35f68bf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-17T20:07:12Z","title_canon_sha256":"48167c873137a1d2b9bc41c8c89f70ec595c17cf36771ac007ee1f498356d287"},"schema_version":"1.0","source":{"id":"2605.17637","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.17637","created_at":"2026-05-20T00:04:49Z"},{"alias_kind":"arxiv_version","alias_value":"2605.17637v1","created_at":"2026-05-20T00:04:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.17637","created_at":"2026-05-20T00:04:49Z"},{"alias_kind":"pith_short_12","alias_value":"EE2J7NHHPUME","created_at":"2026-05-20T00:04:49Z"},{"alias_kind":"pith_short_16","alias_value":"EE2J7NHHPUMEKMM4","created_at":"2026-05-20T00:04:49Z"},{"alias_kind":"pith_short_8","alias_value":"EE2J7NHH","created_at":"2026-05-20T00:04:49Z"}],"graph_snapshots":[{"event_id":"sha256:01c873c25e9926d4826f84cfaa15b3747617a8803961f041d04a2f94c3065b8b","target":"graph","created_at":"2026-05-20T00:04:49Z","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":[{"findings_count":0,"name":"cited_work_retraction","ran_at":"2026-05-19T22:51:57.287241Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T21:33:23.555049Z","status":"skipped","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T21:21:57.477577Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.17637/integrity.json","findings":[],"snapshot_sha256":"11e501630281cfe3799708531605edfc8656fb9d8a9dbf05e99f5eee05e85e20","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Coding agents are increasingly used as application builders, yet many evaluations still focus on source code, repository-level tests, or intermediate traces rather than the delivered application. We introduce WebGameBench, a requirement-to-application benchmark that evaluates whether coding agents can turn a frozen Structured WebGame Specification into a browser-accessible game. Browser-native games provide a compact but behavior-dense testbed: even simple games require coordinated input handling, spatial mapping, rule execution, state transitions, terminal conditions, restart behavior, and vi","authors_text":"Daxiang Dong, Guoliang You, Haoran Wang, Haotian Zhao, Jianmin Wu, Jingnan Gu, Mingyang Dai, Tianlun, Tianshu Zhu, Wenyu Zhang, Xiaoxuan Tang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-17T20:07:12Z","title":"WebGameBench: Requirement-to-Application Evaluation for Coding Agents via Browser-Native Games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.17637","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":"sha256:2c5e36a4b80f0534fe390b95eff16c449bf56bb90731c895efb2ee4cc6a4d09d","target":"record","created_at":"2026-05-20T00:04:49Z","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":"9999d7e83c1ba616c29727dbc12d6aa8090a3f64a596ee6b0d068024b35f68bf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-17T20:07:12Z","title_canon_sha256":"48167c873137a1d2b9bc41c8c89f70ec595c17cf36771ac007ee1f498356d287"},"schema_version":"1.0","source":{"id":"2605.17637","kind":"arxiv","version":1}},"canonical_sha256":"21349fb4e77d1845319c18abe871763aa9456b772f783e66da7cf13b3ab52931","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"21349fb4e77d1845319c18abe871763aa9456b772f783e66da7cf13b3ab52931","first_computed_at":"2026-05-20T00:04:49.886954Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:04:49.886954Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"A0ZVWJEPkky/4tcbyZxqvyfvstmaBFxUktmuDPW3BWVtrza9GyJ4U/LkjOqZzLvD3Wikg2N173bGT2KPqSrwBg==","signature_status":"signed_v1","signed_at":"2026-05-20T00:04:49.887991Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.17637","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2c5e36a4b80f0534fe390b95eff16c449bf56bb90731c895efb2ee4cc6a4d09d","sha256:01c873c25e9926d4826f84cfaa15b3747617a8803961f041d04a2f94c3065b8b"],"state_sha256":"c888dc6613a7b19f2d36a09e2e89a1808de224d92d8ba15464fa6f1ecddce907"}