{"_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_d41d4c4566c3d707ae8a42cb0032eb28fa376818ecc1eac07343f725f70b85a9","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_d41d4c4566c3d707ae8a42cb0032eb28fa376818ecc1eac07343f725f70b85a9","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"9fc2cf845cc6e6d1035bb009663f6be6bed10bb8fb41b8cfb5c4834c84ad0938","published":"Wed, 24 Jun 2026 00:00:00 -0400","receipt_hash":"9fc2cf845cc6e6d1035bb009663f6be6bed10bb8fb41b8cfb5c4834c84ad0938","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":"9fc2cf845cc6e6d1035bb009663f6be6bed10bb8fb41b8cfb5c4834c84ad0938","observed_at":"2026-06-24T04:43:17.877668Z","parent_run_hash":"ca17d06d44ba7db934e6f913874699efc608b8f87453f1ac67f52060e620b57c","published":"Wed, 24 Jun 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:2606.24381v1 Announce Type: cross \nAbstract: Prompt-based interaction has become a dominant paradigm for using large language models (LLMs), where multiple candidate prompts are evaluated and the top-ranked one is selected for downstream use. This workflow implicitly assumes that prompt rankings are stable under minor variations in evaluation conditions. In this paper, we systematically study prompt ranking stability under common sources of variability, including random seeds and limited evaluation subsets. Across three open-weight LLMs and two benchmark tasks, we find that while overall rank correlations are often moderate to high, the identity of the top-performing prompt frequently changes, leading to unreliable selection decisions. To address this issue, we propose a simple stability-aware selection strategy based on a lower confidence bound, which accounts for both performance and variance. Our results show that this approach improves robustness in unstable settings while re","title":"On the Stability of Prompt Ranking in Large Language Model Evaluation","url":"https://arxiv.org/abs/2606.24381","vendor":"arxiv_cs_ai"},"summary":"arXiv:2606.24381v1 Announce Type: cross \nAbstract: Prompt-based interaction has become a dominant paradigm for using large language models (LLMs), where multiple candidate prompts are evaluated and the top-ranked one is selected for downstream use. This workflow implicitly assumes that prompt rankings are stable under minor variations in evaluation conditions. In this paper, we systematically study prompt ranking stability under common sources of variability, including random seeds and limited evaluation subsets. Across three open-weight LLMs and two benchmark tasks, we find that while overall rank correlations are often moderate to high, the identity of the top-performing prompt frequently changes, leading to unreliable selection decisions. To address this issue, we propose a simple stability-aware selection strategy based on a lower confidence bound, which accounts for both performance and variance. Our results show that this approach improves robustness in unstable settings while re","title":"On the Stability of Prompt Ranking in Large Language Model Evaluation","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-06-24T04:43:17Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2606.24381"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:b32d10fdebfdaa71efb28b0190839396261ef6bd0bf19094c4c25743bf4c5b9a12efb79e0ce1afd739a6711f8675367753fa24fcd54afbe7a13a18307aa4880a","signer":"crovia.substrate","subject":{"observed_at":"2026-06-24T04:43:17Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2606.24381"},"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":"ff70e15e7e03d00412955ccaa88df58497920f261f32eb68fcc4570b9db2fd3e","leaf_index":244572,"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":"ca86edb152cd2369ae279a3543deaf0cc05c2278c21e0e16f7d8f8155dba2f64","side":"right"},{"sibling":"909ce0c540be858c7ab821ea3c206568cf1b717ec9eaf10fdeaef8f5430f3464","side":"right"},{"sibling":"fead3793e42008b1bbf01b49a7cfc4fd53a3b68d90802477d2c7d5ca54638d01","side":"left"},{"sibling":"1794eb07172a8e36089e11983be3a84b2b450a87e4bbc39204ea24a6d8137533","side":"left"},{"sibling":"92703a887e7f1bf8322f8d44ac0cb59c1842671e6697413180532d2dd09d35d1","side":"left"},{"sibling":"b067534616bb7d7c6554b89a9447081f53dff0fccf744257ad56cf669f711947","side":"right"},{"sibling":"2fb6532259e6852414e5b4ef4dd8ffec5a8a48bee3324303be4c62aabee72329","side":"left"},{"sibling":"d4fcf6bcc7f1fe78997b28df74b23bba21f5b2585d6fe8efb802f0d067291d5c","side":"right"},{"sibling":"0fa23771b702ff726ed1fc5a44f9b416b2a7861c2f957fcac2d95392276d4784","side":"left"},{"sibling":"bc74ebb08462da8a50fc65ea75f8a8a3418d10ebd471d830f1c67f33dd54dfd1","side":"left"},{"sibling":"6dafd355e5d54c60e61c6c02d3842984e234b1f5bca1623fcdd3def7b8931973","side":"right"},{"sibling":"3107b9d4dbf9456a39f99de694a4dd4da2c0600f9f8855f125161335fe8810af","side":"left"},{"sibling":"86118ab4500c3055a2af70062751a960423c464405b18ca1c37411bf0ce3f52e","side":"left"},{"sibling":"3a42039065acac6d3e4088ec61d9c116ecf7a26c7b7163d23da8fd0b3362e038","side":"left"},{"sibling":"c044f2bd864a0e8e8af5a7f6e3124def7fc4b4511b2b166ea8f9de321e8d385e","side":"right"},{"sibling":"a04392fb9f2a3a620840e3b3fecd93d12e6d224e481c162389d8ae64e7194599","side":"left"},{"sibling":"c300cf0154c136afc09b1702a0be98f4ba5b6dc5cf57e8cc714ec1eaf4196eff","side":"left"},{"sibling":"d841ad93efda0869e5eb97678f348f03f5caab4353e05ff4bf18f47fb945b822","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":244827,"merkle_root":"274e133c6dfa2781a9cfb85337d01cc6b72688ce5e810149f3183e400ffab136","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260624T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-06-24T05:37:55Z","sig_algorithm":"ed25519","signature":"22ca3cee4de2447b3d281e30e09fe566461996bb7be4d4465f08a3f4cf59cea58f22683a4aa10ef4d5d17a19b03f4212392bfd26f2b51f289f0cdf1042a03800","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_d41d4c4566c3d707ae8a42cb0032eb28fa376818ecc1eac07343f725f70b85a9"}}