{"_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_a4c7f1bc37853f78e1fad75a37016b181f59301e49fec00622b3c9dbde8ce552","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_a4c7f1bc37853f78e1fad75a37016b181f59301e49fec00622b3c9dbde8ce552","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"900fe41c618bd06b264a3139b389a39fa54ea03c1f8961573d1035c7c86131fc","published":"Tue, 28 Jul 2026 00:00:00 -0400","receipt_hash":"900fe41c618bd06b264a3139b389a39fa54ea03c1f8961573d1035c7c86131fc","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":"900fe41c618bd06b264a3139b389a39fa54ea03c1f8961573d1035c7c86131fc","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:2607.24573v1 Announce Type: new \nAbstract: Large language models (LLMs) increasingly support decisions about uncertain future events, yet evaluating their ability to forecast real-world outcomes remains difficult. In particular, existing benchmarks are typically static and retrospective, and therefore cannot test how information is synthesized by LLMs to predict future events under uncertainty. We introduce LLM-SoccerArena (https://llm-soccerarena.com), a prospective live benchmark that evaluates how well LLMs forecast real-world sports events before the outcomes are known. LLM-SoccerArena provides (1) a prospective live benchmark protocol, (2) a public open-source platform, and (3) a factorial benchmark design together with tournament-related questions (e.g., which team will win). LLM-SoccerArena automatically records timestamped, schema-validated forecasts of unresolved events, together with prompts, model versions, tool traces, and costs. The factorial design varies along four","title":"LLM-SoccerArena: Benchmarking LLMs on Real-World Predictions in Sports","url":"https://arxiv.org/abs/2607.24573","vendor":"arxiv_cs_ai"},"summary":"arXiv:2607.24573v1 Announce Type: new \nAbstract: Large language models (LLMs) increasingly support decisions about uncertain future events, yet evaluating their ability to forecast real-world outcomes remains difficult. In particular, existing benchmarks are typically static and retrospective, and therefore cannot test how information is synthesized by LLMs to predict future events under uncertainty. We introduce LLM-SoccerArena (https://llm-soccerarena.com), a prospective live benchmark that evaluates how well LLMs forecast real-world sports events before the outcomes are known. LLM-SoccerArena provides (1) a prospective live benchmark protocol, (2) a public open-source platform, and (3) a factorial benchmark design together with tournament-related questions (e.g., which team will win). LLM-SoccerArena automatically records timestamped, schema-validated forecasts of unresolved events, together with prompts, model versions, tool traces, and costs. The factorial design varies along four","title":"LLM-SoccerArena: Benchmarking LLMs on Real-World Predictions in Sports","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/2607.24573"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:60ec70514bea0ee1b55e816438ef130f4fac9688fe358ff9a90786e712bf470e1df7f15ee0843c2bacdb8311016df3f5da2bd9099bfe05fef4930cbbc77d410c","signer":"crovia.substrate","subject":{"observed_at":"2026-07-28T04:43:08Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2607.24573"},"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":"9929657a8c675fd6d86cfd6e9673ec2b6cac7d047d1b97eb09645dd3d2c1f45b","leaf_index":360485,"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":"e4817f075778621ae77050c1c8195d364c9ab90e1d910ff3ecafd2c3c61c56b7","side":"left"},{"sibling":"9f86383a242a3082467cb739f9be7635d0505e1c0c0c5d251c126d6e131c2f0d","side":"right"},{"sibling":"634f53002ef127169e6b1a0da2bd148c156be51a54bd3419ee97d7b3083d3171","side":"left"},{"sibling":"680a6af777a0b8fab96620537ccd693715ae8af5bbceb7a7ade52fdb78e06bda","side":"right"},{"sibling":"a1c76048aeec2248236838a703e4ac14a61f82ef51d1c13eb066a5d267c78b1a","side":"right"},{"sibling":"9a45174405abad8c6238b5cea175009c5728635224ac72d0182f5d73903f2e17","side":"left"},{"sibling":"af35a1d32b2197ab764f9882c8ba5ae653d1e5419b2df50a1daf88021ca8b2bd","side":"right"},{"sibling":"7da15787b28ee42d6f6ffa689ccb25f3c7958b4ad112266a2a4acad4347e0386","side":"right"},{"sibling":"eb79f1d599c07786d2268140481af8b617999ecc5688c6283fe58e5e6f3a2640","side":"right"},{"sibling":"fe03c6d0b083c4097049d7fc6d7d08dfdb05d9c198b2786336689712d66eabf0","side":"right"},{"sibling":"590ea76fdfc1b9e8072055c378be3182f916709e8d06bd955232e650a7188b86","side":"right"},{"sibling":"d92781c59301ffd5bfb0bad75d9fdf6d73879f715518149d383f7362213e0daf","side":"right"},{"sibling":"f315303d4402b57497416d48eb4c4bb50405b40862d41c7caf318cb3d29c5237","side":"right"},{"sibling":"36973eb5f586cd67e0c0dc055dd87e734aa544c35d4400d2c9f932f8ef8fb27f","side":"right"},{"sibling":"e39f7900355489c4718b21cc2d3d06382e1d2f22b864d10be9ebc9d498b279a1","side":"right"},{"sibling":"1f9a970b25dd938c98cabc9e0a55c5a6f46292b9fa37cc89d90ef0cbb1e05a8c","side":"left"},{"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_a4c7f1bc37853f78e1fad75a37016b181f59301e49fec00622b3c9dbde8ce552"}}