{"_canonicalization":{"envelope_id":"axm_ + sha256(envelope minus {signature, axiom_id, anchors})","envelope_signature":"ed25519(envelope minus {signature, axiom_id})","json":"sort_keys=True, separators=(',',':'), ensure_ascii=False, allow_nan=False, utf-8","leaf_hash":"sha256(0x00 || canonical_json(envelope_full))","seal_signature":"ed25519(seal minus {signature, sig_algorithm})"},"axiom_id":"axm_c0fc4187786928e90e4d625a0ae22bc991a59fe1d933168dfa3d3dd531ba694c","bitcoin_anchor":{"bitcoin_attestations":[],"calendar_attestations":[],"ots_url":"","stamped_at":"","status":"pending_next_stamp"},"envelope":{"anchors":[{"chain":"crovia.axiom_graph","height":0,"merkle_proof":"spider_vendor_press_v1","root_at_anchor":"spider_vendor_press_v1"}],"axiom_id":"axm_c0fc4187786928e90e4d625a0ae22bc991a59fe1d933168dfa3d3dd531ba694c","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"6f73763a84251d194b003019ff80a2a11a852acb35fa08ac3ddaad8a6f0fcbcc","published":"Thu, 02 Jul 2026 00:00:00 -0400","receipt_hash":"6f73763a84251d194b003019ff80a2a11a852acb35fa08ac3ddaad8a6f0fcbcc","schema":"spider.news.vendor_press.v1","spider":"vendor_press","spider_record":{"axiom_subtype":"news.vendor_press.v1","category":"news","decision_hint":"POSITIVE","envelope_target":"AX.OBS","fingerprint":"6f73763a84251d194b003019ff80a2a11a852acb35fa08ac3ddaad8a6f0fcbcc","observed_at":"2026-07-02T04:43:28.872255Z","parent_run_hash":"9f528c2a80e5b201c2a66ae885c05dd596ad2c3532bb4c6809c7c9704d10e650","published":"Thu, 02 Jul 2026 00:00:00 -0400","runtime_version":"0.1.0","schema":"spider.news.vendor_press.v1","source_status":200,"source_url":"https://export.arxiv.org/rss/cs.AI","spider":"vendor_press","summary_excerpt":"arXiv:2602.11103v2 Announce Type: replace \nAbstract: Despite rapid progress on coding agents, progress on their multimodal counterparts has lagged behind. A key challenge is the scarcity of evaluation testbeds that combine the complexity of software development with the need for deep multimodal understanding. In game development, agents must navigate large, dense codebases while manipulating intrinsically multimodal assets such as shaders, sprites, and animations within a visual game scene. We present GameDevBench, the first benchmark for evaluating agents on game development tasks. GameDevBench consists of 333 tasks derived from web and video tutorials. Tasks require significant multimodal understanding and are complex: the average solution requires over three times the lines of code and file changes compared to prior software development benchmarks. Agents struggle with game development, with the best agent and method solving only 53.8% of tasks. We find a strong correlation between ","title":"GameDevBench: Evaluating Agentic Capabilities Through Game Development","url":"https://arxiv.org/abs/2602.11103","vendor":"arxiv_cs_ai"},"summary":"arXiv:2602.11103v2 Announce Type: replace \nAbstract: Despite rapid progress on coding agents, progress on their multimodal counterparts has lagged behind. A key challenge is the scarcity of evaluation testbeds that combine the complexity of software development with the need for deep multimodal understanding. In game development, agents must navigate large, dense codebases while manipulating intrinsically multimodal assets such as shaders, sprites, and animations within a visual game scene. We present GameDevBench, the first benchmark for evaluating agents on game development tasks. GameDevBench consists of 333 tasks derived from web and video tutorials. Tasks require significant multimodal understanding and are complex: the average solution requires over three times the lines of code and file changes compared to prior software development benchmarks. Agents struggle with game development, with the best agent and method solving only 53.8% of tasks. We find a strong correlation between ","title":"GameDevBench: Evaluating Agentic Capabilities Through Game Development","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-07-02T04:43:28Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2602.11103"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:1adac5c0e336320891bc01b6ae0d72142abb48f22ab83076a0101fdbfc029116354d5628c76a0f6e788a674cdb9ea1bbce39e3b7dc9cef6ff42fc84fb76d8a01","signer":"crovia.substrate","subject":{"observed_at":"2026-07-02T04:43:28Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2602.11103"},"tsa":{"authority":"crovia.substrate.bootstrap","rfc3161_token":"{\"kind\":\"crovia.bootstrap.tsa\",\"source_jsonl\":\"/opt/crovia/spider/data/news/vendor_press_v1.jsonl\",\"source_seal_merkle_root\":\"spider_vendor_press_v1\",\"upgrade_path\":\"Sessione H \\u2014 OpenTimestamps weekly anchor\"}"},"zk_mode":"clear","zk_proof":null},"ledger":{"leaf_hash":"d8e8ce641e1878ee451a1419a7037e7787251ab0fdc3f156e379d1d95355f877","leaf_index":272104,"ledger_path":"/opt/crovia/substrate/axiom_ledger.jsonl"},"merkle_proof":{"hash_alg":"sha256","leaf_prefix":"0x00","node_prefix":"0x01","odd_leaf_rule":"duplicate_last","path":[{"sibling":"fb7c972a8c762fae248d31f3905e074cf1a7353a3d1ad914ed79c9d2efdef43b","side":"right"},{"sibling":"a6cf37d1a2e639e739695f5d9e9968ce79ae395cc647ed081728d2efbd0ba6ac","side":"right"},{"sibling":"35a7e024a2f5f72d6682582f9d144d4d20ff6fed15e2910acadb05edda8512bd","side":"right"},{"sibling":"fbccbe8863bfffd09d8df172f4d1e649020d0a16512f4604c7fc61743092173f","side":"left"},{"sibling":"02e4aa3dd2ae65df51ef02c59dfdb4aa79a242b6e652be62a6bac947859e4e0a","side":"right"},{"sibling":"2d9b7d2630f289e75e4d58914c09891b903ae22e4878dd904a83cf912580008c","side":"left"},{"sibling":"61aa717d01a37f6d73883a96ce7d0ce502f92b54290435293c16656f03a61a45","side":"left"},{"sibling":"940858731d5be758fd8a2eb1da57b23657abab31e76c3d2d4ca6f9ae60489517","side":"left"},{"sibling":"155ae596a5c6a5260be50ff412642fbd25f4587b43e04c56950c1dc544719be1","side":"right"},{"sibling":"4cfdd7f7072619c015edc477162c2cf29c6f70370acb8dbddf1eb590876d82fe","side":"left"},{"sibling":"43990c9db8fcb3172d821965dfac69152981af4108b8dc87bd32f15c0e56f4cf","side":"left"},{"sibling":"15dbacc2e5845fe3bb835797bb7647ab6f091e79adadd39f40c636980716c622","side":"right"},{"sibling":"7ecc1d0d471643b88d886db58cb02a77af4d1495674760c3867834550b143757","side":"right"},{"sibling":"8a09562f6b247c1c3cd1fea36cb3b8f1cf5c575479dd514573856a380a964bf5","side":"left"},{"sibling":"7b681d50e7d0a7b8d2a749507aed58030072539a90fab18de4f698743685cc00","side":"right"},{"sibling":"9b262645232510ff15bb7325ab858256f2914f711d2726caeafd49f5ca0fb7a9","side":"right"},{"sibling":"5bd94446b5721b713c5e4dcf4624b9bc682657ab2784af927caae7b80c297d7d","side":"right"},{"sibling":"21ac0b7091fe1133859bcd17b4f8da2fe37a2489d472dad508305740b483221b","side":"right"},{"sibling":"1cecb7f447febd025aac272837c80de218aecc6485d2395a509b2a1f1b9c746e","side":"left"}]},"schema":"crovia.axiom_proof.v1","seal":{"first_collector_run_id":"","first_receipt_hash":"","jsonl_path":"/opt/crovia/substrate/axiom_ledger.jsonl","key_id":"430895f101d38164","last_collector_run_id":"","last_receipt_hash":"","leaf_count":272319,"merkle_root":"dd4fa4deb1f207e8a7756821b4f940f39e9f06a25e6fa8500a21dd403318a5a7","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260702T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-07-02T05:38:06Z","sig_algorithm":"ed25519","signature":"68eb2e3bbc0f593bea7b5c3c110c90b6f4fe4fd8277d8dee7c866ba0471c1a50684aa4539c8a493e6d9c9202d8c03f4d897a0df3477e9ecd5b0ff03eb1016f00","signer_version":"1.1.0"},"trust_root":{"key_id":"430895f101d38164","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","signature_algorithm":"ed25519","url":"/registry/canon/TRUST_ROOT.md"},"verifier":{"spec":"/registry/canon/AXIOM_RECEIPT_v1.md","url":"/v/axm_c0fc4187786928e90e4d625a0ae22bc991a59fe1d933168dfa3d3dd531ba694c"}}