{"_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_8512879902174aec6d2d205fe82aa9c21c811751c86ea0593c54e1a1268ccf30","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_8512879902174aec6d2d205fe82aa9c21c811751c86ea0593c54e1a1268ccf30","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"f7d77cec3c6d17641449b40be560ecb09d54a2d0107dc0f7833c1abd2a00dc0d","published":"Fri, 19 Jun 2026 00:00:00 -0400","receipt_hash":"f7d77cec3c6d17641449b40be560ecb09d54a2d0107dc0f7833c1abd2a00dc0d","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":"f7d77cec3c6d17641449b40be560ecb09d54a2d0107dc0f7833c1abd2a00dc0d","observed_at":"2026-06-19T04:43:39.497162Z","parent_run_hash":"942f204649bd8fb7e5f3ac68f64dc64a5a02624b49ac200c0f629f6ff3a211f3","published":"Fri, 19 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:2606.07822v2 Announce Type: replace-cross \nAbstract: As language models improve and become increasingly deployed to solve a variety of tasks, trustworthiness becomes essential. Calibration is a good proxy for trust: well-calibrated confidence estimates help inform the risk versus reward tradeoff when trusting a specific model output. Unfortunately, even as models improve, they remain poorly calibrated, often biasing towards overconfidence. Additionally, calibration can be gamed: a policy that always predicts the base rate is perfectly calibrated, but completely uninformative. To resolve this, we develop a new metric, expected utility renormalized by the oracle (EURO), that balances calibration and informativeness. We also propose a general-purpose activation-based confidence, utility, and trust estimation protocol (ACUTE) to appropriately adjudicate uncertainty. The ACUTE protocol provides flexible, sample-efficient, and compute-efficient confidence estimators for 3 tasks includi","title":"The ACUTE Protocol: Operationalizing Language Model Activations for Better Calibration, Utility, and Trust","url":"https://arxiv.org/abs/2606.07822","vendor":"arxiv_cs_ai"},"summary":"arXiv:2606.07822v2 Announce Type: replace-cross \nAbstract: As language models improve and become increasingly deployed to solve a variety of tasks, trustworthiness becomes essential. Calibration is a good proxy for trust: well-calibrated confidence estimates help inform the risk versus reward tradeoff when trusting a specific model output. Unfortunately, even as models improve, they remain poorly calibrated, often biasing towards overconfidence. Additionally, calibration can be gamed: a policy that always predicts the base rate is perfectly calibrated, but completely uninformative. To resolve this, we develop a new metric, expected utility renormalized by the oracle (EURO), that balances calibration and informativeness. We also propose a general-purpose activation-based confidence, utility, and trust estimation protocol (ACUTE) to appropriately adjudicate uncertainty. The ACUTE protocol provides flexible, sample-efficient, and compute-efficient confidence estimators for 3 tasks includi","title":"The ACUTE Protocol: Operationalizing Language Model Activations for Better Calibration, Utility, and Trust","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-06-19T04:43:39Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2606.07822"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:031c8cbcbde8bbbf794e5130bbd8a12c98eab96dfa954e786be59f73792eae84bedb17c6e8d20001fdef32fc93eb15c9e5a54ecf200856855dd71ac858793801","signer":"crovia.substrate","subject":{"observed_at":"2026-06-19T04:43:39Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2606.07822"},"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":"465bf3e3c250c11ef6fe1f45f05c280a249d60d7279e76f5d7a8bc37b17c62be","leaf_index":235752,"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":"0e863edb8ed302e89974c774cdcd27d0c3e691ad66ba5b58a224abe006ca73ff","side":"right"},{"sibling":"8f7a3495115b3ff828ac7979d989cdc65e2b905f4b575ef48e81be32deb532d8","side":"right"},{"sibling":"ce5c9b2dcc9147da1c73434e9ac9a3aa3f2530134acfdeb98575c1d47e24c8f2","side":"right"},{"sibling":"0f458bab130547bb0b4d830c28f615186b9e4c9bf5328b4c2b44502398172c56","side":"left"},{"sibling":"f5847bcafaf5669734e710d72989e1cda283f6d6063cbf5aa691579795d24d89","side":"right"},{"sibling":"496049c530193449be89dc65e224c2525d1095c081021f8539debc555271ff98","side":"left"},{"sibling":"cff664a6462d639aed9e14805d8bb57d59dd159a92997aa1da18b50dd5d6c34f","side":"left"},{"sibling":"9af7ea2b04101a414ff44ef903d5d381777f0286b489347e7e959b64158ff697","side":"left"},{"sibling":"aa68ebe8f5e8e96388fc8d1af3aa08be7ccd27ab4cebcf5913560c48d877bc27","side":"right"},{"sibling":"8253d44cf1ed30d3ab19c2b339fb4000a1fa173182c65390e9e8dabf8173b9e9","side":"right"},{"sibling":"e2bf9b60400244c698c0196109f54323457abc5b64dee08ec33ab14cc4faaef7","side":"right"},{"sibling":"86664e7f68ba08b8dfcf77dda51a4dfa7fcfc986d4ad7c704ffb71b669202da7","side":"left"},{"sibling":"410c633928fea11c5b4bdddb431956b1d7c320db9cda00d2fe32e0fcf888d7b7","side":"left"},{"sibling":"b52a771530dd1686bca49e42088898b86da94879579cd6a995c6ab0598a665fe","side":"right"},{"sibling":"a116bb92f9b0350491155b470acc86d006c33ec558759e49e56614a54c39f242","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":241122,"merkle_root":"7a906c6a26ff6c6feabc2feaba6a1a70c515e6fd72a38c779293b0f78ff291c4","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260622T183701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-06-23T06:25:25Z","sig_algorithm":"ed25519","signature":"5576b1d56d5dbb0d96c780fa3ca0940d805c8de95c6251bc87297f0be058aa5e37eb53a6aa1b601381f489f093842cf674b28737ed8e46ce3a49814b5e57290c","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_8512879902174aec6d2d205fe82aa9c21c811751c86ea0593c54e1a1268ccf30"}}