{"_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_647dc72332ce181c6ff117fea77d57565c0160015664a019b05e817b0e96cc26","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_647dc72332ce181c6ff117fea77d57565c0160015664a019b05e817b0e96cc26","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"962fff6e946fce2b2b0a08db137cde1fac4b3554524287f1c1639bf41ea28a69","published":"Fri, 17 Jul 2026 00:00:00 -0400","receipt_hash":"962fff6e946fce2b2b0a08db137cde1fac4b3554524287f1c1639bf41ea28a69","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":"962fff6e946fce2b2b0a08db137cde1fac4b3554524287f1c1639bf41ea28a69","observed_at":"2026-07-17T04:43:38.280949Z","parent_run_hash":"113193614a8af99887180226d4e28a8b71d957da5fe3694f0e7a56807c145504","published":"Fri, 17 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:2607.01211v2 Announce Type: replace-cross \nAbstract: Repository-level performance-optimization benchmarks such as GSO, SWE-Perf and SWE-fficiency evaluate coding agents by applying patches to real repositories and comparing runtime against unoptimized baselines and official reference patches. Their leaderboard scores are increasingly used as evidence of coding-agent progress, but those scores can conflate runtime instability, benchmark-specific scoring rules, and how many tasks are already solved by at least one public submission. We audit these issues across the three benchmarks. First, we replay the official reference patches for 740 code optimization tasks across four common types of Google Cloud machines. Most benchmark tasks can be replayed, but their reference patches satisfy the original benchmark validity rules in every cross-machine replay for only 39/102 GSO tasks, 11/140 SWE-Perf tasks, and 411/498 SWE-fficiency tasks; SWE-Perf is especially fragile because many refere","title":"Are Performance-Optimization Benchmarks Reliably Measuring Coding Agents?","url":"https://arxiv.org/abs/2607.01211","vendor":"arxiv_cs_ai"},"summary":"arXiv:2607.01211v2 Announce Type: replace-cross \nAbstract: Repository-level performance-optimization benchmarks such as GSO, SWE-Perf and SWE-fficiency evaluate coding agents by applying patches to real repositories and comparing runtime against unoptimized baselines and official reference patches. Their leaderboard scores are increasingly used as evidence of coding-agent progress, but those scores can conflate runtime instability, benchmark-specific scoring rules, and how many tasks are already solved by at least one public submission. We audit these issues across the three benchmarks. First, we replay the official reference patches for 740 code optimization tasks across four common types of Google Cloud machines. Most benchmark tasks can be replayed, but their reference patches satisfy the original benchmark validity rules in every cross-machine replay for only 39/102 GSO tasks, 11/140 SWE-Perf tasks, and 411/498 SWE-fficiency tasks; SWE-Perf is especially fragile because many refere","title":"Are Performance-Optimization Benchmarks Reliably Measuring Coding Agents?","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-07-17T04:43:38Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2607.01211"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:c5176eebd2b40cd48c6207bcae738e0e83ca4b35ad8977324d34f3b4bc6fc48c31f1a6ecfbb9e9cad79c8d38554232e6fbe5415778d512b0a214ededc5e6ab04","signer":"crovia.substrate","subject":{"observed_at":"2026-07-17T04:43:38Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2607.01211"},"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":"bce75ec0608127eae2b12b777fab0d2426ff1ccd3bb60bff9703a830b34651df","leaf_index":323258,"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":"70000b079b0714ee047595a6704ef995c419a96cd68c9fb87aaff98e419249d8","side":"right"},{"sibling":"c20c4caf28e235015c3e265958f1761df0395298c84dae0f63045a1b7913d973","side":"left"},{"sibling":"b198d1a26dda13463b8bbba19b6eb0bd7a2fbd00c27597bda804e47f41a8b21d","side":"right"},{"sibling":"824d712ad73efb0978a426e8ae30a9de6bf70c0db3aa26870e810aca2e168ae8","side":"left"},{"sibling":"b49ba42fddd47fd0f5bce2d53d7522666aae90b791a17d1a997d9ed31094d0c7","side":"left"},{"sibling":"e598d86f6dc3df9796230f34c4de8648b46e542e1c7872d2ce6d2f940933cc08","side":"left"},{"sibling":"aebfde2196fc7fd2178375305cab7b77eaaa1ebf74063760b1eb4e14f8814e82","side":"right"},{"sibling":"b5089ad323e3a111201fbe7e6c412f67ceaa2ae3f4a343adb22b037ec4c30755","side":"left"},{"sibling":"4242cc570ec8c36a37f3f6f20dcae20b49fccc17c7b53ba47d8715e465bec585","side":"right"},{"sibling":"be025f48721bfc0ca7107f0454bda3ab460e50539f0caeb1bf839a8dabcf036c","side":"left"},{"sibling":"05a09763743cdc09fc45cf454e4e3ea4a0d1cd74f9c8162b2a57e2c873160908","side":"left"},{"sibling":"de3120ef2488b8a791a686b47257da4e612256abdfcdda7519265e7edd47d041","side":"left"},{"sibling":"e86f56a4883492da5b5e7b0201324c52946e865e69b99ebb532f41fe3c658ee4","side":"right"},{"sibling":"34d85f6ad6cc7dfa79d90e2b9ff99a561bcdc75b0301bbbd3e83861f54535c1e","side":"left"},{"sibling":"f302542c38ba7c3aab7c9280dd60259ecec777dca6e6f71b6f0729b0b8791b72","side":"left"},{"sibling":"d8b9143917b539c543cf4448cec00131f8b807bd8004979c54ebe09798748c66","side":"left"},{"sibling":"9b11714124b9b951ff9450b0ee9d625a0b70b6da2cf388bd3df1475eec0b17ba","side":"right"},{"sibling":"a4523a9014d45df43e006e9210a73428c380d771f2c650a1b986910759b0cdf7","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":323382,"merkle_root":"2f4d32419c80a9600aba5a480fc3fb7012ec0a695c91a1b055048e78760b65ca","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260717T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-07-17T05:38:31Z","sig_algorithm":"ed25519","signature":"495308c7bf004117807331d3f71d0b079f6bd7ed7737faa58c773b1b3e80ee84928d2d8519cc7d2b809506501aada1be6546f72c7ecda3dad5445cbb44502209","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_647dc72332ce181c6ff117fea77d57565c0160015664a019b05e817b0e96cc26"}}