{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VQTHEA367XW44YX7X3R2MRQJ4L","short_pith_number":"pith:VQTHEA36","schema_version":"1.0","canonical_sha256":"ac2672037efdedce62ffbee3a64609e2f7002b446613d528f0054c7640ba8477","source":{"kind":"arxiv","id":"2607.14399","version":1},"attestation_state":"computed","paper":{"title":"Instrument Effects in Language-Model Honesty Evaluation: An Auditable Single-System Demonstration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Justin Bronder (Corabo Inc.)","submitted_at":"2026-07-15T22:33:53Z","abstract_excerpt":"Evaluations of language-model honesty read the model's verdicts as evidence about the model. We test the instrument instead. We built a text-adventure world where the game engine, not any model, knows whether the quest can be completed. A language model plays under a budget and must eventually declare its quest complete, unreachable, or not yet decidable; the engine scores every verdict. Decision rules were recorded before results were read, and run artifacts bind the revisions they executed; the strength of preregistration varies by series and is disclosed. With the player held fixed, instrum"},"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":"2607.14399","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-15T22:33:53Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"4abb0f862cce1f6d76af9b30f14d72e292d1c6cbaf8990051e41d1f528bb7405","abstract_canon_sha256":"3eacf53d057ffaea5cc92e06f159d36700c10c157eb96b6eb9a890b71fba585e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-17T00:21:10.721113Z","signature_b64":"fWulyv8rTdCgxKP3s8gMsy7Um/Gvn9CqePoMDRzHfzZ5iWGvDrM+X2UifWxZStLOzDN9gZTjbAcdhc4IeVk1Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac2672037efdedce62ffbee3a64609e2f7002b446613d528f0054c7640ba8477","last_reissued_at":"2026-07-17T00:21:10.720254Z","signature_status":"signed_v1","first_computed_at":"2026-07-17T00:21:10.720254Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Instrument Effects in Language-Model Honesty Evaluation: An Auditable Single-System Demonstration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Justin Bronder (Corabo Inc.)","submitted_at":"2026-07-15T22:33:53Z","abstract_excerpt":"Evaluations of language-model honesty read the model's verdicts as evidence about the model. We test the instrument instead. We built a text-adventure world where the game engine, not any model, knows whether the quest can be completed. A language model plays under a budget and must eventually declare its quest complete, unreachable, or not yet decidable; the engine scores every verdict. Decision rules were recorded before results were read, and run artifacts bind the revisions they executed; the strength of preregistration varies by series and is disclosed. With the player held fixed, instrum"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.14399","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/2607.14399/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":"2607.14399","created_at":"2026-07-17T00:21:10.720710+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.14399v1","created_at":"2026-07-17T00:21:10.720710+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.14399","created_at":"2026-07-17T00:21:10.720710+00:00"},{"alias_kind":"pith_short_12","alias_value":"VQTHEA367XW4","created_at":"2026-07-17T00:21:10.720710+00:00"},{"alias_kind":"pith_short_16","alias_value":"VQTHEA367XW44YX7","created_at":"2026-07-17T00:21:10.720710+00:00"},{"alias_kind":"pith_short_8","alias_value":"VQTHEA36","created_at":"2026-07-17T00:21:10.720710+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/VQTHEA367XW44YX7X3R2MRQJ4L","json":"https://pith.science/pith/VQTHEA367XW44YX7X3R2MRQJ4L.json","graph_json":"https://pith.science/api/pith-number/VQTHEA367XW44YX7X3R2MRQJ4L/graph.json","events_json":"https://pith.science/api/pith-number/VQTHEA367XW44YX7X3R2MRQJ4L/events.json","paper":"https://pith.science/paper/VQTHEA36"},"agent_actions":{"view_html":"https://pith.science/pith/VQTHEA367XW44YX7X3R2MRQJ4L","download_json":"https://pith.science/pith/VQTHEA367XW44YX7X3R2MRQJ4L.json","view_paper":"https://pith.science/paper/VQTHEA36","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.14399&json=true","fetch_graph":"https://pith.science/api/pith-number/VQTHEA367XW44YX7X3R2MRQJ4L/graph.json","fetch_events":"https://pith.science/api/pith-number/VQTHEA367XW44YX7X3R2MRQJ4L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VQTHEA367XW44YX7X3R2MRQJ4L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VQTHEA367XW44YX7X3R2MRQJ4L/action/storage_attestation","attest_author":"https://pith.science/pith/VQTHEA367XW44YX7X3R2MRQJ4L/action/author_attestation","sign_citation":"https://pith.science/pith/VQTHEA367XW44YX7X3R2MRQJ4L/action/citation_signature","submit_replication":"https://pith.science/pith/VQTHEA367XW44YX7X3R2MRQJ4L/action/replication_record"}},"created_at":"2026-07-17T00:21:10.720710+00:00","updated_at":"2026-07-17T00:21:10.720710+00:00"}