{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6SFR6Y3LXJVZW474YML36I6PJE","short_pith_number":"pith:6SFR6Y3L","schema_version":"1.0","canonical_sha256":"f48b1f636bba6b9b73fcc317bf23cf492fe85403ea570b2b8371ce3fda6b31e1","source":{"kind":"arxiv","id":"2606.07822","version":1},"attestation_state":"computed","paper":{"title":"The ACUTE Protocol: Operationalizing Language Model Activations for Better Calibration, Utility, and Trust","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Hamid Palangi, Mani Malek, Nishant Subramani, Palash Goyal, Tomas Pfister, Yiwen Song, Yuan Xue","submitted_at":"2026-06-05T20:15:50Z","abstract_excerpt":"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 renormalize"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.07822","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-05T20:15:50Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"61485683e92c2e9f113ce10af79914ad2fbb2b9a3024408cc9d7f436734d18cc","abstract_canon_sha256":"28ce21448675bdc1988d8357591e46fc1768f039eb2f625d96e3928a4717c597"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:04:53.113583Z","signature_b64":"tYqt9LHblZCQvq3qgtlyljTCUDRtSLPC59xEvYRjNwTCTuJnoFg0+8uEgoJRtowE6z4nLTGI3kXVFzhcZOXqCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f48b1f636bba6b9b73fcc317bf23cf492fe85403ea570b2b8371ce3fda6b31e1","last_reissued_at":"2026-06-09T01:04:53.113177Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:04:53.113177Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The ACUTE Protocol: Operationalizing Language Model Activations for Better Calibration, Utility, and Trust","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Hamid Palangi, Mani Malek, Nishant Subramani, Palash Goyal, Tomas Pfister, Yiwen Song, Yuan Xue","submitted_at":"2026-06-05T20:15:50Z","abstract_excerpt":"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 renormalize"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07822","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.07822/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.07822","created_at":"2026-06-09T01:04:53.113239+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.07822v1","created_at":"2026-06-09T01:04:53.113239+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07822","created_at":"2026-06-09T01:04:53.113239+00:00"},{"alias_kind":"pith_short_12","alias_value":"6SFR6Y3LXJVZ","created_at":"2026-06-09T01:04:53.113239+00:00"},{"alias_kind":"pith_short_16","alias_value":"6SFR6Y3LXJVZW474","created_at":"2026-06-09T01:04:53.113239+00:00"},{"alias_kind":"pith_short_8","alias_value":"6SFR6Y3L","created_at":"2026-06-09T01:04:53.113239+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6SFR6Y3LXJVZW474YML36I6PJE","json":"https://pith.science/pith/6SFR6Y3LXJVZW474YML36I6PJE.json","graph_json":"https://pith.science/api/pith-number/6SFR6Y3LXJVZW474YML36I6PJE/graph.json","events_json":"https://pith.science/api/pith-number/6SFR6Y3LXJVZW474YML36I6PJE/events.json","paper":"https://pith.science/paper/6SFR6Y3L"},"agent_actions":{"view_html":"https://pith.science/pith/6SFR6Y3LXJVZW474YML36I6PJE","download_json":"https://pith.science/pith/6SFR6Y3LXJVZW474YML36I6PJE.json","view_paper":"https://pith.science/paper/6SFR6Y3L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.07822&json=true","fetch_graph":"https://pith.science/api/pith-number/6SFR6Y3LXJVZW474YML36I6PJE/graph.json","fetch_events":"https://pith.science/api/pith-number/6SFR6Y3LXJVZW474YML36I6PJE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6SFR6Y3LXJVZW474YML36I6PJE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6SFR6Y3LXJVZW474YML36I6PJE/action/storage_attestation","attest_author":"https://pith.science/pith/6SFR6Y3LXJVZW474YML36I6PJE/action/author_attestation","sign_citation":"https://pith.science/pith/6SFR6Y3LXJVZW474YML36I6PJE/action/citation_signature","submit_replication":"https://pith.science/pith/6SFR6Y3LXJVZW474YML36I6PJE/action/replication_record"}},"created_at":"2026-06-09T01:04:53.113239+00:00","updated_at":"2026-06-09T01:04:53.113239+00:00"}