{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CRUBDBWVOVLZETL2WEB4PHWEAS","short_pith_number":"pith:CRUBDBWV","schema_version":"1.0","canonical_sha256":"14681186d57557924d7ab103c79ec4049f4b51c92c69add0ac7e1be782bafbda","source":{"kind":"arxiv","id":"2605.28258","version":1},"attestation_state":"computed","paper":{"title":"GUI Agents for Continual Game Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.HC"],"primary_cat":"cs.SE","authors_text":"Bo Li, Guangjing Wang, Haonan Ge, Hongcheng Guo, Kaijie Chen, Na Li, Qingyi Si, Ruihan Yang, Yixu Huang, Yuanzhe Shen, Zhe Wang","submitted_at":"2026-05-27T10:08:48Z","abstract_excerpt":"Generating a game is not the same as making one that can be played. Despite advances in code generation, existing approaches treat game generation as one-shot translation from prompt to artifact, leaving interaction-level failures undetected. We argue that evaluating and improving game generation requires a player, and study two roles for graphical user interface (GUI) agents in this process: (1) as an objective evaluator, for which we introduce PlaytestArena, a new evaluation environment that pairs 200 browser-based game generation tasks across eight genres with rubrics of expected in-play be"},"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":"2605.28258","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-05-27T10:08:48Z","cross_cats_sorted":["cs.AI","cs.CV","cs.HC"],"title_canon_sha256":"5947c85304426240f692693d5c5100ce305eb6d8ea1480443eda5cde6f0557b9","abstract_canon_sha256":"83aaffb3218282643092a36b09dad058c5951c97c6512a9218cb6ea79781702b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:05:04.387193Z","signature_b64":"Cdu6qkSTReqcXxPIkHxyG4CAYXBaXk/ZHFswjO9IyP+MEuNDXZdvE1Toh+jlGR/RKgOWMOWwn5/kLuAMIFWGCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14681186d57557924d7ab103c79ec4049f4b51c92c69add0ac7e1be782bafbda","last_reissued_at":"2026-05-28T01:05:04.386765Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:05:04.386765Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GUI Agents for Continual Game Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.HC"],"primary_cat":"cs.SE","authors_text":"Bo Li, Guangjing Wang, Haonan Ge, Hongcheng Guo, Kaijie Chen, Na Li, Qingyi Si, Ruihan Yang, Yixu Huang, Yuanzhe Shen, Zhe Wang","submitted_at":"2026-05-27T10:08:48Z","abstract_excerpt":"Generating a game is not the same as making one that can be played. Despite advances in code generation, existing approaches treat game generation as one-shot translation from prompt to artifact, leaving interaction-level failures undetected. We argue that evaluating and improving game generation requires a player, and study two roles for graphical user interface (GUI) agents in this process: (1) as an objective evaluator, for which we introduce PlaytestArena, a new evaluation environment that pairs 200 browser-based game generation tasks across eight genres with rubrics of expected in-play be"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28258","kind":"arxiv","version":1},"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/2605.28258/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":"2605.28258","created_at":"2026-05-28T01:05:04.386828+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.28258v1","created_at":"2026-05-28T01:05:04.386828+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28258","created_at":"2026-05-28T01:05:04.386828+00:00"},{"alias_kind":"pith_short_12","alias_value":"CRUBDBWVOVLZ","created_at":"2026-05-28T01:05:04.386828+00:00"},{"alias_kind":"pith_short_16","alias_value":"CRUBDBWVOVLZETL2","created_at":"2026-05-28T01:05:04.386828+00:00"},{"alias_kind":"pith_short_8","alias_value":"CRUBDBWV","created_at":"2026-05-28T01:05:04.386828+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CRUBDBWVOVLZETL2WEB4PHWEAS","json":"https://pith.science/pith/CRUBDBWVOVLZETL2WEB4PHWEAS.json","graph_json":"https://pith.science/api/pith-number/CRUBDBWVOVLZETL2WEB4PHWEAS/graph.json","events_json":"https://pith.science/api/pith-number/CRUBDBWVOVLZETL2WEB4PHWEAS/events.json","paper":"https://pith.science/paper/CRUBDBWV"},"agent_actions":{"view_html":"https://pith.science/pith/CRUBDBWVOVLZETL2WEB4PHWEAS","download_json":"https://pith.science/pith/CRUBDBWVOVLZETL2WEB4PHWEAS.json","view_paper":"https://pith.science/paper/CRUBDBWV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.28258&json=true","fetch_graph":"https://pith.science/api/pith-number/CRUBDBWVOVLZETL2WEB4PHWEAS/graph.json","fetch_events":"https://pith.science/api/pith-number/CRUBDBWVOVLZETL2WEB4PHWEAS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CRUBDBWVOVLZETL2WEB4PHWEAS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CRUBDBWVOVLZETL2WEB4PHWEAS/action/storage_attestation","attest_author":"https://pith.science/pith/CRUBDBWVOVLZETL2WEB4PHWEAS/action/author_attestation","sign_citation":"https://pith.science/pith/CRUBDBWVOVLZETL2WEB4PHWEAS/action/citation_signature","submit_replication":"https://pith.science/pith/CRUBDBWVOVLZETL2WEB4PHWEAS/action/replication_record"}},"created_at":"2026-05-28T01:05:04.386828+00:00","updated_at":"2026-05-28T01:05:04.386828+00:00"}