{"_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_f389412215f585cc6111c2bc93b5faa519abf68fcd6f732c05816712fd2edc19","bitcoin_anchor":{"bitcoin_attestations":["bitcoin_block_949451"],"calendar_attestations":["https://finney.calendar.eternitywall.com","https://btc.calendar.catallaxy.com","https://alice.btc.calendar.opentimestamps.org","https://bob.btc.calendar.opentimestamps.org"],"ots_url":"/registry/data/substrate/anchors/77fc9c28fae777b81da5b495b3115474df6592dfac590333213d3bdf8b94a9b3.ots","stamped_at":"2026-05-15T03:00:03Z","status":"bitcoin"},"envelope":{"anchors":[{"chain":"crovia.axiom_graph","height":0,"merkle_proof":"spider_vendor_press_v1","root_at_anchor":"spider_vendor_press_v1"}],"axiom_id":"axm_f389412215f585cc6111c2bc93b5faa519abf68fcd6f732c05816712fd2edc19","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"384aa1e63516caa799499df2e69e8d5b0db232d4b2b195e6fef3859794b443ce","published":"Thu, 07 May 2026 00:00:00 -0400","receipt_hash":"384aa1e63516caa799499df2e69e8d5b0db232d4b2b195e6fef3859794b443ce","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":"384aa1e63516caa799499df2e69e8d5b0db232d4b2b195e6fef3859794b443ce","observed_at":"2026-05-07T04:43:30.601849Z","parent_run_hash":"b20b3beeadde500bb99eda3b869d50b00c5259b2c78c650d83e786ac81b85801","published":"Thu, 07 May 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:2603.04601v2 Announce Type: replace-cross \nAbstract: Code generation has emerged as one of AI's highest-impact use cases, yet existing benchmarks measure isolated tasks rather than the complete \"zero-to-one\" process of building a working application from scratch. We introduce Vibe Code Bench, a benchmark of 100 web application specifications (50 public validation, 50 held-out test) with 964 browser-based workflows comprising 10,131 substeps, evaluated against deployed applications by an autonomous browser agent. Across 16 frontier models, the best achieves 61.8% accuracy on the test split, revealing that reliable end-to-end application development remains a frontier challenge. We identify self-testing during generation as a strong performance predictor (Pearson r=0.72), and show through a completed human alignment study that evaluator selection materially affects outcomes (31.8-93.6% pairwise step-level agreement). Our contributions include (1) a novel benchmark dataset and brows","title":"Vibe Code Bench: Evaluating AI Models on End-to-End Web Application Development","url":"https://arxiv.org/abs/2603.04601","vendor":"arxiv_cs_ai"},"summary":"arXiv:2603.04601v2 Announce Type: replace-cross \nAbstract: Code generation has emerged as one of AI's highest-impact use cases, yet existing benchmarks measure isolated tasks rather than the complete \"zero-to-one\" process of building a working application from scratch. We introduce Vibe Code Bench, a benchmark of 100 web application specifications (50 public validation, 50 held-out test) with 964 browser-based workflows comprising 10,131 substeps, evaluated against deployed applications by an autonomous browser agent. Across 16 frontier models, the best achieves 61.8% accuracy on the test split, revealing that reliable end-to-end application development remains a frontier challenge. We identify self-testing during generation as a strong performance predictor (Pearson r=0.72), and show through a completed human alignment study that evaluator selection materially affects outcomes (31.8-93.6% pairwise step-level agreement). Our contributions include (1) a novel benchmark dataset and brows","title":"Vibe Code Bench: Evaluating AI Models on End-to-End Web Application Development","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-05-07T04:43:30Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2603.04601"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:a24905a4a134278cd71b8f9525881034b0e33f80ff7f50b9449efa0cc42fd6594694845375a5b56e502ec9c877933c80b7193e95959cbb7e6835595a35d3fd04","signer":"crovia.substrate","subject":{"observed_at":"2026-05-07T04:43:30Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2603.04601"},"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":"c96fa5db746776c90500e8f9997c51a5dfacb02c63e4a2954f3160143ba47fbf","leaf_index":118411,"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":"e6eac8703cb081e9e07032360a469c95c760b2345cfbf7fbbd6898b656c04108","side":"left"},{"sibling":"b64e604e34b6ddef449099ac63d40c165a90864c0351f08db0ec4d85db74cd19","side":"left"},{"sibling":"d67787a9e796b95c5cad1631f398c9952fa5a8a295c1ff6f3c35c89c7b806577","side":"right"},{"sibling":"84fd4a46ec209af50c7cf043376f034a3bd302f0d35b092d417c459f0ce1ce01","side":"left"},{"sibling":"8bf2d3079a7d2d1910fe27dc145a9975d0a57d364e898a83521c31ee442110e2","side":"right"},{"sibling":"a4b6da5f02e3305d0c1284c479cd6ddabeb3a94354a776b3726c69be66303f02","side":"right"},{"sibling":"5af39df3c9035d13ceb80709e514dc55846b6a733cea60cd870ff94e52fa2781","side":"right"},{"sibling":"2a0f4af441a1e3c0e9aaa2f84181fde452bc4d86f670959c83aab5c6d154671f","side":"left"},{"sibling":"943780ddf0bc6538ed8b19cdb0e84ad78f5880f72d472b378c67229ade3fd90d","side":"right"},{"sibling":"9e688ad7df5f10379f7d9b9d109c3ea84968c044c36d5562f359706d012cf15b","side":"left"},{"sibling":"8e758a4477dfc0838d2e8ea2bdbd583bc3192683e75fd9cde217ee6a3b2f3ac8","side":"left"},{"sibling":"4219f746e463e594ccd6447debdf736a57e77319b12bcb74d8ece2b5860064c6","side":"left"},{"sibling":"05f89b32c00462e60adf95c1fe4579cdc2791b36e8b17573d8f3b5fd5da95a0b","side":"right"},{"sibling":"8ccd9937a2c0d5c04044d07d1557791b7d07bb31eac41a39a675608d44b38f23","side":"right"},{"sibling":"3a5e69cf0803f4c91f3895ed7c9a95748fef240bec4422e167c05300f79f06c0","side":"left"},{"sibling":"f2817ab288b5324fe49770372c7a10f33f7cd11005f8d4c0a730316f5229dc98","side":"left"},{"sibling":"725fac972e772ca0dc598810ea1abc70df472f72d2d6ab8a0baee2b80e5d2f4c","side":"left"},{"sibling":"98fc57dfef8873b512edc8340f7181df57302bb96777625e072235c62d7c5895","side":"right"}]},"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":134292,"merkle_root":"77fc9c28fae777b81da5b495b3115474df6592dfac590333213d3bdf8b94a9b3","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260515T023701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-05-15T02:37:25Z","sig_algorithm":"ed25519","signature":"68107a834b00b24f5d4501e5ec727445311f132a486567ecc4c72a4e6dff24c8c21f2de3105293353ba5fdbe370d032819af6aa70f694e2e39b6af6737507009","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_f389412215f585cc6111c2bc93b5faa519abf68fcd6f732c05816712fd2edc19"}}