{"_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_2f594c123d618f5943d2a60f6d0277b65bbdd216308aedaff91caf3d2d445a57","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_2f594c123d618f5943d2a60f6d0277b65bbdd216308aedaff91caf3d2d445a57","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"ee8697f713f1485ee1e73a1c6a1e377a66cc7bb7e0b30d5e70e8971bbc85522f","published":"Tue, 21 Jul 2026 00:00:00 -0400","receipt_hash":"ee8697f713f1485ee1e73a1c6a1e377a66cc7bb7e0b30d5e70e8971bbc85522f","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":"ee8697f713f1485ee1e73a1c6a1e377a66cc7bb7e0b30d5e70e8971bbc85522f","observed_at":"2026-07-21T04:43:35.036805Z","parent_run_hash":"03e944014de2697434479833d15ea9303e014945afc230ecc7f207824493b589","published":"Tue, 21 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:2607.06411v2 Announce Type: replace-cross \nAbstract: Developers increasingly delegate real maintenance work to product-grade coding agents, and many state tasks in their native language, in the style of a customer request rather than a curated English issue. We introduce RuBench 1.0, a benchmark of 25 tasks mined from recent fix commits in five live open-source repositories (aiohttp, aiogram, Laravel, NestJS, Fastify), each specified natively in Russian -- written from scratch, not translated -- and judged by the upstream maintainer's regression tests, which we withhold from release. All fix commits postdate the training-data cutoffs of every evaluated model. Round 1 evaluates Claude Code with Opus 4.8, Sonnet 5, and Haiku 4.5, and Codex CLI with GPT-5.5 (3 independent runs each; pass@1 with task-level uncertainty); the best configuration resolves 78.7% of tasks. Auditing full trajectories of an hors-concours configuration (Claude Code + Fable 5), we caught the product silently s","title":"RuBench: A Repository-Level Agentic Coding Benchmark with Natively Authored Russian Task Specifications","url":"https://arxiv.org/abs/2607.06411","vendor":"arxiv_cs_ai"},"summary":"arXiv:2607.06411v2 Announce Type: replace-cross \nAbstract: Developers increasingly delegate real maintenance work to product-grade coding agents, and many state tasks in their native language, in the style of a customer request rather than a curated English issue. We introduce RuBench 1.0, a benchmark of 25 tasks mined from recent fix commits in five live open-source repositories (aiohttp, aiogram, Laravel, NestJS, Fastify), each specified natively in Russian -- written from scratch, not translated -- and judged by the upstream maintainer's regression tests, which we withhold from release. All fix commits postdate the training-data cutoffs of every evaluated model. Round 1 evaluates Claude Code with Opus 4.8, Sonnet 5, and Haiku 4.5, and Codex CLI with GPT-5.5 (3 independent runs each; pass@1 with task-level uncertainty); the best configuration resolves 78.7% of tasks. Auditing full trajectories of an hors-concours configuration (Claude Code + Fable 5), we caught the product silently s","title":"RuBench: A Repository-Level Agentic Coding Benchmark with Natively Authored Russian Task Specifications","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-07-21T04:43:35Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2607.06411"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:93b3285d61377ab2bd84e30dd0ffc5f5befae4e273b43ac1366dcca702eb5e6d5cfa7e7e65753e18f0507443ead63dd482d0d6666b4e4d2af9dc35bab1461708","signer":"crovia.substrate","subject":{"observed_at":"2026-07-21T04:43:35Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2607.06411"},"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":"394bfc233514af67ca28501d6391687e8d61e1d61fb9ea97b8d0406954a685d9","leaf_index":337003,"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":"4acf93611ada491cc252c73ef28dd26069bdd19f8f5935a1c82639378b62f26a","side":"left"},{"sibling":"5e8d0cba50b7faede54df31bd662999a4e022197859adcb28f19fa768e05736c","side":"left"},{"sibling":"4beecdf1f02f0d1d3b31bf456595d289e3ecf5d391874ed78328ee50f410c2f6","side":"right"},{"sibling":"603ffabc679fd553387d5f24f9e6b9ba5add13cf43ec14f2f008f9a3b88f715a","side":"left"},{"sibling":"3f5fd1680493526da9fd95a6360272d74f78dac673ad0801691b9c004e57c90c","side":"right"},{"sibling":"07c87330e171a55b29b083c7c6c30454fcdfd68bb1f0238fbbe25104f4826174","side":"left"},{"sibling":"34efd454df46a7476d0bc83ac9843e7409ddde5c8ee1426de19ece35f23d2d83","side":"left"},{"sibling":"45255096c5a08e740a615b6e3c262589a170dbfc373bdeaceae175916dd2ab97","side":"right"},{"sibling":"1298242aa509bc13b92160250ead2d95a721941ca6310e33b9eb0bf0821557d0","side":"right"},{"sibling":"61d44c6d16b87de577db53cff0dba2f003c50c036d92dc335120aa70124c8788","side":"right"},{"sibling":"5d0b792dbe69fd0a7cd8d79b467aa10204d1f25be602c06190f3423bc22727b8","side":"left"},{"sibling":"9eb5077edfb3dc553857d4794b925bfce117e0f8a1d049af5d0dd9026b470eef","side":"right"},{"sibling":"414b1a70fd1dcb25489a194714b97492b066684b15d0b7a48a176c4b9b5bc713","side":"right"},{"sibling":"21d66dd41003813f710b7617944f1bfba3258658a5d3370c21cad8f9e945bc99","side":"left"},{"sibling":"613f015699131eb89bd755dee67133be95af25cf5f16c1c8ce4b99d963b8dd86","side":"right"},{"sibling":"a729b574b1135956436ded5eef1fe8f08014ff6a0729749d307ab1bca93fcdc9","side":"right"},{"sibling":"77025bcb374a7ad74f520643e20a8ae1205a7ee78507b0beb93117760f1c29d3","side":"left"},{"sibling":"4bf21052e085e8ac81f1dec1d2b310bd12bf948992de6177d12e9d2fda8d39f0","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":337144,"merkle_root":"5e969cc01afa67e4dbe5d37b712cdb10f4aa1fd74404e02eab724cf487c8d6d9","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260721T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-07-21T05:38:38Z","sig_algorithm":"ed25519","signature":"5c0c1a8dd2793d787ccd5e49e8b4d70eed136352555518589f05c74be357fc171702e42a76c3a556d90e3d51ff36cb3d292aaac83c66566de7b943f318bda50c","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_2f594c123d618f5943d2a60f6d0277b65bbdd216308aedaff91caf3d2d445a57"}}