{"_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_65702430450749b6ccdaef6596003f10a1b6e40f54ef159a6cabe26f9cf59a3f","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_65702430450749b6ccdaef6596003f10a1b6e40f54ef159a6cabe26f9cf59a3f","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"5380acc092832a5934ac7af5b276c214e197fdd5ab087257954d3174b224f2dc","published":"Fri, 24 Jul 2026 00:00:00 -0400","receipt_hash":"5380acc092832a5934ac7af5b276c214e197fdd5ab087257954d3174b224f2dc","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":"5380acc092832a5934ac7af5b276c214e197fdd5ab087257954d3174b224f2dc","observed_at":"2026-07-24T04:43:08.456021Z","parent_run_hash":"b018378f86139a28e6209ec008b31c1282cd1b5c1632dbd43b054c17aa88ab96","published":"Fri, 24 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:2607.21217v1 Announce Type: new \nAbstract: The recent emergence of vibe-coding workflows is changing what coding agents are expected to do. Instead of merely completing code under fully specified instructions, agents are increasingly expected to transform incomplete product intent into working software by combining various abilities including planning, requirement clarification, tool use, debugging, and repository-level construction. Yet existing benchmarks have not fully caught up with this shift, evaluating agents on static, fully specified tasks.\n  In this paper, we introduce ICAE-Bench, a benchmark for evaluating coding agents under interactive project-building settings. The basic idea is to start from a fuzzy product requirement, simulating the dynamic paradigm with an automated User Agent. To make this setting both realistic and evaluable, ICAE-Bench introduces three key designs. First, to avoid the ambiguity of unconstrained fuzzy requirements, each task derives ambiguity ","title":"ICAE-Bench: Evaluating Coding Agents as Interactive Project Builders","url":"https://arxiv.org/abs/2607.21217","vendor":"arxiv_cs_ai"},"summary":"arXiv:2607.21217v1 Announce Type: new \nAbstract: The recent emergence of vibe-coding workflows is changing what coding agents are expected to do. Instead of merely completing code under fully specified instructions, agents are increasingly expected to transform incomplete product intent into working software by combining various abilities including planning, requirement clarification, tool use, debugging, and repository-level construction. Yet existing benchmarks have not fully caught up with this shift, evaluating agents on static, fully specified tasks.\n  In this paper, we introduce ICAE-Bench, a benchmark for evaluating coding agents under interactive project-building settings. The basic idea is to start from a fuzzy product requirement, simulating the dynamic paradigm with an automated User Agent. To make this setting both realistic and evaluable, ICAE-Bench introduces three key designs. First, to avoid the ambiguity of unconstrained fuzzy requirements, each task derives ambiguity ","title":"ICAE-Bench: Evaluating Coding Agents as Interactive Project Builders","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-07-24T04:43:08Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2607.21217"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:f1bb255a3a2a7037650615431717fae6b0769e371564b6db5bacb2ec9a2f73e5153646f7a1198bc8c59bb4c88ffcef7d914a636e3fcc629ac6234ac6afbfe403","signer":"crovia.substrate","subject":{"observed_at":"2026-07-24T04:43:08Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2607.21217"},"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":"9d68a9dc93e3290a2620cc45a8a68b07562379ebef00dba7b601ea09889556f8","leaf_index":347042,"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":"deb9a9ed247d14183192e0671c8861f95a1556e4f051d738399f26f19a1d0ffa","side":"right"},{"sibling":"a98e82acf83d3bb4b8f6af0e61d2a955f06e423101fe9a4a47ede8c55acdeef9","side":"left"},{"sibling":"50a6d0afcc9c5af1b50c6f0209b34d7a7c9e198b2cc817cea9efddc9d9ff8582","side":"right"},{"sibling":"7510bb7fcb210416846421fe8aedf8053b6c5d3e388cf9fb6248a102e5654115","side":"right"},{"sibling":"9bc1243164793a5595fdf94a9704736aedef1110100e57802bd8272a119b8c37","side":"right"},{"sibling":"35324677b23e55f1ffa43dd5b4dd9dc3c11e5ce4d8e088d669a002edfb294b27","side":"left"},{"sibling":"09a4759d227421c77e1462a3c333b1907095af488295f5ae40a2926b1ac32eed","side":"right"},{"sibling":"735b40cd86add2eb12982a84f45647b35267af61e771b38192432357dac71eb1","side":"left"},{"sibling":"c212fcc83c532c0321804b72fe72b546946bb055d3d482aab19c43f5bebfbf3f","side":"left"},{"sibling":"da189c159d0789c2229cf3731890cc753832dab1aa83e4bbf0fac01955c22cd8","side":"left"},{"sibling":"3a02ed8ea41a09957282e4e27db74ed88cd675156461abb02acb28e2cd257e63","side":"right"},{"sibling":"d3139af8c5ce235438e1c69e4b7afa44ba09129fd86674968434f23e546f423e","side":"left"},{"sibling":"cb89775a838ee16d10fc8da3213420c2012b4d96e8d55cd49939b0887a4b92d3","side":"right"},{"sibling":"252d30ea8052c3bb6b40bc5cc29fc9b9725343d212f84c08fbbae4215a125b00","side":"right"},{"sibling":"f3e45bceed774d2402fa45d41ff5190f295823bd2f216eb90157884150034693","side":"left"},{"sibling":"3cfa2102c0224815c6f3bf73e6710e24103f43f7bf5da1ca2abad1416d9c0890","side":"right"},{"sibling":"77025bcb374a7ad74f520643e20a8ae1205a7ee78507b0beb93117760f1c29d3","side":"left"},{"sibling":"e871fd7edf9b2ad89bce1609a028f5225eea4d14372169bac242420830f86530","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":347413,"merkle_root":"9efe042c5dd6583dfd3b6a58fbfc289807f60bcf2bd2927f10488a54a8ba11fc","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260724T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-07-24T05:38:42Z","sig_algorithm":"ed25519","signature":"8633c55f558d42994850505218b2862c6134bad2b1c80d4b80736c2fd3ea7a19690ca3498727a8adbdc47791176128a8d64bef0883b888db809f0477355bd00c","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_65702430450749b6ccdaef6596003f10a1b6e40f54ef159a6cabe26f9cf59a3f"}}