{"_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_c01db9e25fffdbb799839f3a8148f1de9c9d4048b06534c37314a7ff0fb2829f","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_c01db9e25fffdbb799839f3a8148f1de9c9d4048b06534c37314a7ff0fb2829f","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"6f10f245646862c28d73692d05f297472d0b8da63caf6c247f29b0600cfcab7b","published":"Tue, 26 May 2026 00:00:00 -0400","receipt_hash":"6f10f245646862c28d73692d05f297472d0b8da63caf6c247f29b0600cfcab7b","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":"6f10f245646862c28d73692d05f297472d0b8da63caf6c247f29b0600cfcab7b","observed_at":"2026-05-26T04:43:39.018238Z","parent_run_hash":"dca8dedd754ad6a1772113d6b97ee4f4ab9a0afbdeb44aaace5ff2d2446b164b","published":"Tue, 26 May 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:2605.25394v1 Announce Type: new \nAbstract: Large language models often generate confident but incorrect answers rather than abstaining when uncertain. This problem is particularly acute for small language models (SLMs), where computational constraints and autonomous operation amplify the need for reliable uncertainty detection. We propose _Second Guess_, a lightweight, parameter-free prompting technique for abstention in multiple-choice question answering (MCQA) that is well-suited for SLMs. Our key empirical insight is that models which truly know an answer will select it consistently, while uncertain models exhibit unstable behavior when an ``I don't know'' option is added. Evaluated on four open models (2B-8B parameters) and four benchmarks, Second Guess achieves the highest composite risk improvement of 10.81\\%. Notably, it maintains an 8\\% composite risk improvement on fine-tuned models where entropy-based methods degrade, and improves most for lower-performing models. All c","title":"Second Guess: Detecting Uncertainty Through Abstention and Answer Stability in Small Language Models","url":"https://arxiv.org/abs/2605.25394","vendor":"arxiv_cs_ai"},"summary":"arXiv:2605.25394v1 Announce Type: new \nAbstract: Large language models often generate confident but incorrect answers rather than abstaining when uncertain. This problem is particularly acute for small language models (SLMs), where computational constraints and autonomous operation amplify the need for reliable uncertainty detection. We propose _Second Guess_, a lightweight, parameter-free prompting technique for abstention in multiple-choice question answering (MCQA) that is well-suited for SLMs. Our key empirical insight is that models which truly know an answer will select it consistently, while uncertain models exhibit unstable behavior when an ``I don't know'' option is added. Evaluated on four open models (2B-8B parameters) and four benchmarks, Second Guess achieves the highest composite risk improvement of 10.81\\%. Notably, it maintains an 8\\% composite risk improvement on fine-tuned models where entropy-based methods degrade, and improves most for lower-performing models. All c","title":"Second Guess: Detecting Uncertainty Through Abstention and Answer Stability in Small Language Models","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-05-26T04:43:39Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2605.25394"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:f97f531ee60569bbb751a5ccf8e85e0685b38472d17ed781bdd92597efc41eaa90101da940e4c6c737d7d579497bc0c30a53a54b7359bbd7ae638084ecc3c30b","signer":"crovia.substrate","subject":{"observed_at":"2026-05-26T04:43:39Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2605.25394"},"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":"08b70e68fc07408fcd16d7f0cead21a2afa88ea362859556776409a1f0fb0c24","leaf_index":151416,"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":"b75a4ed1e7e689d7c861b065dc1fddf7ad1b15ae73edbb7201d2518e49f2bf9d","side":"right"},{"sibling":"0492c975d7a6eb14ff0b37d8ff8b78c2f88395c162dc438dfb697c35cb35f325","side":"right"},{"sibling":"61431400cc9a286ca82dce27defdc5c99d9ca7f10eefd9ee94b219f4e09bdad9","side":"right"},{"sibling":"517eae67171846600d235cff79478f6961354e2c1f1314b75126d51138eeb4e4","side":"left"},{"sibling":"61b60b9ed13411c54bb7aa36d7438f81a2fa94381c764565f6c27b17e4c5ee38","side":"left"},{"sibling":"ccb0d1ce6fe03ae447d77b1a5d403df935110ea0f0cacdaa2f110858f5bf0ce1","side":"left"},{"sibling":"0a5010458437ccad9c345d7808e550a19558e3d8585ebb9302d9493157ff7a12","side":"left"},{"sibling":"8d693959d4763b28b351e1bc64d35b03213077740e93193dee0f2ab1f6459eb7","side":"right"},{"sibling":"a808644c9a09dd75253c6c0ba9275dc94a6b6451ad5184ebdafda4a2722b36a5","side":"left"},{"sibling":"fdd22ebd87e5ba37d1153e47753a63818abb25df8fe45dbf735ba5c512c3355b","side":"left"},{"sibling":"cf593c482d17d202b94914915d0c65fb8713053548db64771d0ec5dbb404a07f","side":"left"},{"sibling":"134949308b15cffd6792ee2cf678119af34d69a64764d7c89cd47573c94e1cda","side":"left"},{"sibling":"e20a7391fed5b5f3b675af68344a3f5b050d6701e127b7db010af3941e59dfdb","side":"right"},{"sibling":"e5893793e3591ed7f5e58ca94ffcfba46bb30f69fb1c25d5ba8ef49eb99f9126","side":"right"},{"sibling":"35ca36cee447f0ef7064a25d55f59357c66901e31427729c4c1d8b14aa8adb6c","side":"left"},{"sibling":"e3eecaf996dbe7229a7bb1d234c97aea97a252c5f7c89f8547b6d091db0f0e40","side":"right"},{"sibling":"55bcbd4da3e20d93931f7e58673f10232e81a5b1514d7396cb4b71e8f95788d0","side":"right"},{"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":152106,"merkle_root":"ac5182c6f3dd09931f2a689df5f4be36df7b55e55bcf106e195671f5ed55fd8f","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260526T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-05-26T05:37:34Z","sig_algorithm":"ed25519","signature":"a401243fbd2c077d29a623c6ef616c78fbd5c8ce1930afa7af7165b2386e5a8cf15d5094983a1c962e71b27b911a3f3ce09c8cfab9393be2ce5ce8ee6513da06","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_c01db9e25fffdbb799839f3a8148f1de9c9d4048b06534c37314a7ff0fb2829f"}}