{"_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_a496be149e95f17ddf7015dc828f83f647a4fa4822347d09bc74283798700f19","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_a496be149e95f17ddf7015dc828f83f647a4fa4822347d09bc74283798700f19","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"927d32be66b9d79535d9d4eace73bdfbc23fb221954cebc5909510a95018b2da","published":"Fri, 15 May 2026 00:00:00 -0400","receipt_hash":"927d32be66b9d79535d9d4eace73bdfbc23fb221954cebc5909510a95018b2da","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":"927d32be66b9d79535d9d4eace73bdfbc23fb221954cebc5909510a95018b2da","observed_at":"2026-05-15T04:43:17.611638Z","parent_run_hash":"5c64f85625fabd323e9c4a1cf068c012fb88a248deda9a9ac702fb2f9799f2e5","published":"Fri, 15 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:2604.25855v2 Announce Type: replace-cross \nAbstract: Multimodal large language models (MLLMs) achieve ever-stronger performance on visual-language tasks. Even as traditional visual question answering (VQA) benchmarks approach saturation, reliable deployment requires satisfying low error tolerances in real-world, out-of-distribution (OOD) scenarios. Precisely, selective prediction aims to improve coverage, i.e. the share of inputs the system answers, while adhering to a user-defined risk level. This is typically achieved by assigning a confidence score to each answer and abstaining on those that fall below a certain threshold. Existing selective prediction methods estimate implicit confidence scores, relying on model internal signals like logits or hidden representations, which are not available for frontier closed-sourced models. To enable reliable generalization in VQA, we require reasoner models to produce localized visual evidence while answering, and design a selector that ex","title":"SIEVES: Selective Prediction Generalizes through Visual Evidence Scoring","url":"https://arxiv.org/abs/2604.25855","vendor":"arxiv_cs_ai"},"summary":"arXiv:2604.25855v2 Announce Type: replace-cross \nAbstract: Multimodal large language models (MLLMs) achieve ever-stronger performance on visual-language tasks. Even as traditional visual question answering (VQA) benchmarks approach saturation, reliable deployment requires satisfying low error tolerances in real-world, out-of-distribution (OOD) scenarios. Precisely, selective prediction aims to improve coverage, i.e. the share of inputs the system answers, while adhering to a user-defined risk level. This is typically achieved by assigning a confidence score to each answer and abstaining on those that fall below a certain threshold. Existing selective prediction methods estimate implicit confidence scores, relying on model internal signals like logits or hidden representations, which are not available for frontier closed-sourced models. To enable reliable generalization in VQA, we require reasoner models to produce localized visual evidence while answering, and design a selector that ex","title":"SIEVES: Selective Prediction Generalizes through Visual Evidence Scoring","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-05-15T04:43:17Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2604.25855"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:f59140728c738fe126af575c7d1c775387ba5ccd78a192a1be2845a18d76a40ed2596b8b1670f8e8d054b1e0fe0038190224f7b1bec8c917a9d1e34098756707","signer":"crovia.substrate","subject":{"observed_at":"2026-05-15T04:43:17Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2604.25855"},"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":"fd713c635a84307d2e738b8ada94443695f736954265f76853e52d97338f959f","leaf_index":134801,"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":"d2ebad65aa2d5c304875426be230f49a1f0d5a2026c5751aeec89d83ddd261f1","side":"left"},{"sibling":"14de18b300e806f7d0eee9263ac5f3fbffe863f59fdb27744ccbf912c1c77f48","side":"right"},{"sibling":"227889165d75ae840a32a752c9590ff7f1cf94d6fbf8cf97fd49864149575de3","side":"right"},{"sibling":"686d3031b0a2fe1016ed013e5017884927672094c4da2307f3ac7a34c05c10c1","side":"right"},{"sibling":"4bf0085792aaba9c39d4ba78c58255609bce019f21775220a541d055902f9515","side":"left"},{"sibling":"5fc2935f973135027dfec44abb4984cf3256aee30f1888041f5f4c94633bf55a","side":"right"},{"sibling":"7fb440277b43a0a448cbfa0e516ee5aa0504495adea486e423b8bbf045b1f798","side":"right"},{"sibling":"c007bf5d6c3a3a484205f30ad38ce03dff757769991af941772ae831255ede50","side":"left"},{"sibling":"a17a0eaa87574a308e2c02cf125072b9e69566b9e8d6d2e64a02880192b885d5","side":"right"},{"sibling":"6bd0475fd3a73322a4f73095c96b072de89e462ce5839161aa552e0208619bce","side":"left"},{"sibling":"36672459e5ed50c64ee1842b69cb6d2eb682c2a04844555be8d124257571994a","side":"left"},{"sibling":"727783827652adfa99c455bd80a01bfb33836228e51068b4f654ef3da468ca69","side":"left"},{"sibling":"623194cd30880ed223e306737fdb111aa0d781751bfc47553c404a6af6aad2c4","side":"right"},{"sibling":"fc8f53ed42756907fb79ee19a4ed09f72c560e5302b3d98198b96bf1da635a4a","side":"right"},{"sibling":"d6607539da7ba39ec68be2d12f27ed6768766c745e3120fd915f88c5e288e07c","side":"right"},{"sibling":"b63408a424d27cd6a75e0fb155e69a58a328f41e9cb9dba1eddef9a5289cc7fd","side":"right"},{"sibling":"356fb36a4e188f03d7a05c54cd8789bdd40eda454b9bc9560f667acc08e6c4e0","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":134886,"merkle_root":"c6c7ae28c065bced89e7f844216b073f1a7cc4b378db0d41a98bcd21b28066db","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260515T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-05-15T05:37:26Z","sig_algorithm":"ed25519","signature":"5a3978c26017daf4104adbb3e1c3099c5750157acbfc7242ece1815dc6740fe08a690291ce0afe42011e20cc565b5ebe64ec016bf658b5bab563a63337985c05","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_a496be149e95f17ddf7015dc828f83f647a4fa4822347d09bc74283798700f19"}}