{"_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_b09e18f7b1f42fc420f9e21f140b604406ec9f7164d26c392058c8a2a3f27952","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_b09e18f7b1f42fc420f9e21f140b604406ec9f7164d26c392058c8a2a3f27952","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"fca9d905eae1c304635c7dba62e2f4cb0bde5392df0c2c8f9753895ae08a8bdf","published":"Wed, 22 Jul 2026 00:00:00 -0400","receipt_hash":"fca9d905eae1c304635c7dba62e2f4cb0bde5392df0c2c8f9753895ae08a8bdf","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":"fca9d905eae1c304635c7dba62e2f4cb0bde5392df0c2c8f9753895ae08a8bdf","observed_at":"2026-07-22T04:43:18.261256Z","parent_run_hash":"4765c85b8b4b27ff9a690c1ae11c3b009baa2c60297295f395ad422f5afed68c","published":"Wed, 22 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:2607.18438v1 Announce Type: cross \nAbstract: Introducing Relay-Bench, an unsaturated, holistic, text-only benchmark that measures LLMs' ability to complete an assortment of tasks from distinct domains in a single prompt. The leading model, GPT-5.5 (xHigh), scores 43.3%. The test set entirely consists of composite problems: groups of single-domain subproblems that are strung together into challenges that require reasoning across multiple domains in combination. Many of these problems then have layers of complexity added through prompt encoding and deliberate context bloat. Domains tested include visual reasoning, coding, math, information extraction (with a focus on web search), problem-solving, general knowledge, and data analysis. No restrictions are imposed outside of the model harness, and models are explicitly encouraged to leverage code-execution, web searches, and all available tools. All problems are composed of two to thirteen subproblems and do not require multi-modal in","title":"Relay-Bench: Evaluating LLMs on Multi-Domain Reasoning Chains","url":"https://arxiv.org/abs/2607.18438","vendor":"arxiv_cs_ai"},"summary":"arXiv:2607.18438v1 Announce Type: cross \nAbstract: Introducing Relay-Bench, an unsaturated, holistic, text-only benchmark that measures LLMs' ability to complete an assortment of tasks from distinct domains in a single prompt. The leading model, GPT-5.5 (xHigh), scores 43.3%. The test set entirely consists of composite problems: groups of single-domain subproblems that are strung together into challenges that require reasoning across multiple domains in combination. Many of these problems then have layers of complexity added through prompt encoding and deliberate context bloat. Domains tested include visual reasoning, coding, math, information extraction (with a focus on web search), problem-solving, general knowledge, and data analysis. No restrictions are imposed outside of the model harness, and models are explicitly encouraged to leverage code-execution, web searches, and all available tools. All problems are composed of two to thirteen subproblems and do not require multi-modal in","title":"Relay-Bench: Evaluating LLMs on Multi-Domain Reasoning Chains","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-07-22T04:43:18Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2607.18438"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:c4633c70adbab36951374864b6de6ce1ebbf27b7127c37b40e5829f82d521fd4f72975949bee53a5dd88fb8cd30821a13f04770d04ecaeb8f28368343822d603","signer":"crovia.substrate","subject":{"observed_at":"2026-07-22T04:43:18Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2607.18438"},"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":"9207f911d64c57b2712c4328dd382a4e211965c87136092bc176cba17dd6c284","leaf_index":340232,"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":"8bbb2cd21639ac1edf5d6608a2297d78ef9837e91102e6f59fe454ad99de0da7","side":"right"},{"sibling":"93d1fd2f2fe35b18fb31222042f20432aa5685b332155979fd82c7cbbe975418","side":"right"},{"sibling":"4d1bf1d320de2b084d60f587835583cab89fca07898082e2f7737bb2889c3007","side":"right"},{"sibling":"fb234bac05d88ad1a04d82aa0d7f31a495d0e76efb9a8962d1bcfe8be1031251","side":"left"},{"sibling":"ee8e89b5cb932a19da65fe7751081de773cd079333f5a85e733bcc98dd9c6f78","side":"right"},{"sibling":"2a4aa2537f893d14f07b75a55253578662d88ca7188a783d59bbffc2dcd6e695","side":"right"},{"sibling":"1ceec737648abedef5cf424287d8814c7a276b6ddf1096ff671c381f5455c7e9","side":"right"},{"sibling":"617d94b8a1da646ac45b4d986747eccb1604c294cb2a78b6cf4c70df505a76f4","side":"right"},{"sibling":"99d4b7aea5e7c917c580af0f1a9556bbd4d44f3f36cf9391892e7ef0340a8258","side":"left"},{"sibling":"c7fc9d4187cdc36f4c03b4b13daf4b880ea65536b051f71a5cc2543839d02697","side":"right"},{"sibling":"1758ec6ac206ce40e8368cb702195322fe3737d0fb03d8bd9e3b30acc4fa7d81","side":"right"},{"sibling":"0c407f0d553cf3fab8f9bd79205b8180e090cbf29fa0490ebb55155041ad5c86","side":"right"},{"sibling":"2dd9cb2521044ee7c6b74f2315e0a0253b8df0d04a7b810bbbbe7da5a9788769","side":"left"},{"sibling":"21d66dd41003813f710b7617944f1bfba3258658a5d3370c21cad8f9e945bc99","side":"left"},{"sibling":"787ee3744642ff909d610b0514cb100784f0ef1ba0ef4c70a0dc91f0ab2bb192","side":"right"},{"sibling":"9fc8a8ebbc1bff7e62b9f1e1c681c91e7196092ce9551573df6e23096df13e4d","side":"right"},{"sibling":"77025bcb374a7ad74f520643e20a8ae1205a7ee78507b0beb93117760f1c29d3","side":"left"},{"sibling":"ee6f33920899d9bdef2eb706dfff29e26eea61e29ea9824c6c8e6bcd48275d76","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":340557,"merkle_root":"7d45d94f20b5bf82263df45b87749e19e06161972f25141dd573cc138d566338","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260722T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-07-22T05:38:39Z","sig_algorithm":"ed25519","signature":"812cb61e90d3582ba508db8515c4168bbf8ee1c6762885609049d012f680f8068f15c98b9accf2042047dcfc6a6fc3885820ee34b0be350846386f64f2591309","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_b09e18f7b1f42fc420f9e21f140b604406ec9f7164d26c392058c8a2a3f27952"}}