{"_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_e80f3ac180286a5349531b9e1bb823d85662c38f44664549f15614d46bcb5fcf","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_e80f3ac180286a5349531b9e1bb823d85662c38f44664549f15614d46bcb5fcf","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"00f5484157fc399a2fe437c4e2385aabdac2c4f9e8e305631caf5cc6b4c6419a","published":"Tue, 28 Jul 2026 00:00:00 -0400","receipt_hash":"00f5484157fc399a2fe437c4e2385aabdac2c4f9e8e305631caf5cc6b4c6419a","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":"00f5484157fc399a2fe437c4e2385aabdac2c4f9e8e305631caf5cc6b4c6419a","observed_at":"2026-07-28T04:43:08.282317Z","parent_run_hash":"23a1ef85134515049ced29518443d084afc46fd7c967741e6c6acdbdbbf29939","published":"Tue, 28 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:2607.22585v1 Announce Type: new \nAbstract: Public leaderboards for coding agents typically rank systems by model name and pass rate, while the surrounding harness (the scaffold that issues tools, manages context, and decides when to stop) is often under-specified. Model-to-model comparison is valid when the harness is fixed; when it varies, performance and efficiency conflate model and scaffold effects. We evaluate Qwen 3.6 Plus and MiniMax M2.5 across three open-source harnesses (Goose, OpenCode, OpenHands-SDK) on a stratified 50-task subset of Terminal-Bench Pro. Harness choice induces up to a 40x difference in tokens per solved task, while paired within-model pass-rate differences remain 0-8 percentage points (95% paired-task bootstrap CIs include zero except for the largest gap). Failure fingerprints replicate across models (REASON for Goose, VERIFY/MAX_TURNS for OpenHands-SDK, idle-loop/TIME for OpenCode), indicating harness-level biases that are largely model-independent. F","title":"The Scaffold Effect in Coding Agents: Harness Choice as a Hidden Variable in Coding-Agent Evaluation","url":"https://arxiv.org/abs/2607.22585","vendor":"arxiv_cs_ai"},"summary":"arXiv:2607.22585v1 Announce Type: new \nAbstract: Public leaderboards for coding agents typically rank systems by model name and pass rate, while the surrounding harness (the scaffold that issues tools, manages context, and decides when to stop) is often under-specified. Model-to-model comparison is valid when the harness is fixed; when it varies, performance and efficiency conflate model and scaffold effects. We evaluate Qwen 3.6 Plus and MiniMax M2.5 across three open-source harnesses (Goose, OpenCode, OpenHands-SDK) on a stratified 50-task subset of Terminal-Bench Pro. Harness choice induces up to a 40x difference in tokens per solved task, while paired within-model pass-rate differences remain 0-8 percentage points (95% paired-task bootstrap CIs include zero except for the largest gap). Failure fingerprints replicate across models (REASON for Goose, VERIFY/MAX_TURNS for OpenHands-SDK, idle-loop/TIME for OpenCode), indicating harness-level biases that are largely model-independent. F","title":"The Scaffold Effect in Coding Agents: Harness Choice as a Hidden Variable in Coding-Agent Evaluation","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-07-28T04:43:08Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2607.22585"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:443e58716febb433f13c22561c36ce903ea7b77178ebf37e44b5fb98d5036f120879ce19d5b740694684d4feda4cc63fd8da81e1ae77492a9202bbcdd5d50907","signer":"crovia.substrate","subject":{"observed_at":"2026-07-28T04:43:08Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2607.22585"},"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":"c3cfa7f2a8c1bd5b22a9dcb9ca29979cfb618ea56aa93c69c2626fdf58a2b094","leaf_index":360331,"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":"29bbec115a6943872e033deb3314651053c47f63aa5d889505199e12ee3c9952","side":"left"},{"sibling":"a19fce68e40f9773d9ac1f3b1c36165a381f7e9e0ca66749911fee760d458f4f","side":"left"},{"sibling":"3b7ac4922d9d4aa6eec9162aafba69376730a6df01bbcb09add2fabc30966cc9","side":"right"},{"sibling":"a05aa3b330c26bb6238872266f0f92e27d396861097976b232ed4673a177179d","side":"left"},{"sibling":"abad7bb98b8ed03c8ac90e1cb738b6cea860e4eb9925715cb54360f99561ce70","side":"right"},{"sibling":"d37ffa11305d6d9fceec26104df82aea607e4a2930cc769267c77453f7e47b9e","side":"right"},{"sibling":"48dace931609a55569e4aa242be3eefac99c722b35aa9345c111116089b4e976","side":"right"},{"sibling":"ce393210d8cb9e0705a24ff80bd76d7becf22bfce1258f4a57fd2dbdca17218b","side":"left"},{"sibling":"8fe957ea378915d410087f8b2c41171bdfdac25ba34c42d93c5aaa835f32246c","side":"left"},{"sibling":"f57ebea8749a327b4323e9ad9c906a9400f5a5d8c83084dfc7d80be83bd44007","side":"left"},{"sibling":"4424ff61f20c9cef2251672611ec86369d87b1608ab089738930fd3d52e0dd54","side":"left"},{"sibling":"8db22b6d8b4004df8ccd40f648d9fd8a62f564821c80fbfd9c743849f4102e1b","side":"left"},{"sibling":"cff500acb83b14a8a7195a72d90dd4b7a6b8a28fc1069f8300b1191728718f90","side":"left"},{"sibling":"51ee2566d84aba54b9d07233fb460f9fab044b4edfa3fbe376fa1df0727acfa5","side":"left"},{"sibling":"f3e45bceed774d2402fa45d41ff5190f295823bd2f216eb90157884150034693","side":"left"},{"sibling":"2096cd69b54e283ddc45b26b63564a5e4c02f303ffd855b3b3533bcf26bc284d","side":"right"},{"sibling":"77025bcb374a7ad74f520643e20a8ae1205a7ee78507b0beb93117760f1c29d3","side":"left"},{"sibling":"3b50864499c874394ea0928567747666eaf59b01380e46cd52164ec5acec0f71","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":361008,"merkle_root":"3065e8369ea437c06beba806dc4e4bb159979adeb21fe632242c1906a7204647","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260728T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-07-28T05:38:48Z","sig_algorithm":"ed25519","signature":"9141644407577a82611c1579110f667de2d46dc6b93c6322edf26f4c3056ea99f0e56502853908e30d87c38bcf95eb6e0ab5130525aa51505bd6f61938120609","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_e80f3ac180286a5349531b9e1bb823d85662c38f44664549f15614d46bcb5fcf"}}