{"_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_4db99a89a31f3af9a868d756a808b3561b31657f9af60a751ac1b834f0dc933d","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_4db99a89a31f3af9a868d756a808b3561b31657f9af60a751ac1b834f0dc933d","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"9a2b43a46a77bad0369b12f1fbf669090a433734978b165daf07663d807dd458","published":"Fri, 12 Jun 2026 00:00:00 -0400","receipt_hash":"9a2b43a46a77bad0369b12f1fbf669090a433734978b165daf07663d807dd458","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":"9a2b43a46a77bad0369b12f1fbf669090a433734978b165daf07663d807dd458","observed_at":"2026-06-12T04:43:44.933383Z","parent_run_hash":"a8b304a31db3809a528f5a45e58597f7bb9f23028e53b4f9ed2f5599dd731b5e","published":"Fri, 12 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:2606.12618v1 Announce Type: new \nAbstract: Robust lie detectors for language models could enable powerful techniques for auditing, monitoring, and post-hoc investigation of model behaviour, but evaluating them requires testbeds where models verifiably believe the opposite of what they say. We show that existing trained model organisms often fail this requirement, leaving prior positive and negative detection results difficult to interpret. We address this with 13 reasoning model organisms whose hidden beliefs are verified in chain-of-thought and shown to generalise to held-out tasks, alongside Varied Deception, a prompted-lying testbed covering a broad range of lie-inducing motivations. On these testbeds we evaluate four detectors: a chain-of-thought judge, a logprob classifier, and two activation probes, including Did-You-Lie (DYL), a new method for training follow-up probes. On prompted lying, across 31 open-weight models spanning 2B to 1T parameters, all four detectors show po","title":"\"Did you lie?\" Evaluating Lie Detectors across Model Scale and Belief-Verified Model Organisms","url":"https://arxiv.org/abs/2606.12618","vendor":"arxiv_cs_ai"},"summary":"arXiv:2606.12618v1 Announce Type: new \nAbstract: Robust lie detectors for language models could enable powerful techniques for auditing, monitoring, and post-hoc investigation of model behaviour, but evaluating them requires testbeds where models verifiably believe the opposite of what they say. We show that existing trained model organisms often fail this requirement, leaving prior positive and negative detection results difficult to interpret. We address this with 13 reasoning model organisms whose hidden beliefs are verified in chain-of-thought and shown to generalise to held-out tasks, alongside Varied Deception, a prompted-lying testbed covering a broad range of lie-inducing motivations. On these testbeds we evaluate four detectors: a chain-of-thought judge, a logprob classifier, and two activation probes, including Did-You-Lie (DYL), a new method for training follow-up probes. On prompted lying, across 31 open-weight models spanning 2B to 1T parameters, all four detectors show po","title":"\"Did you lie?\" Evaluating Lie Detectors across Model Scale and Belief-Verified Model Organisms","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-06-12T04:43:44Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2606.12618"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:4d4fa59d4f872a4ddc8de305e63da2cc1e86a786d6c78dce6326d1021031b6c3b2f46daa82f9efddb5fe605dee5de4c3aba34353db52f900e12c757187b6ec0d","signer":"crovia.substrate","subject":{"observed_at":"2026-06-12T04:43:44Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2606.12618"},"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":"b03a68eddd7ae840e842a5553c35b9c23820053ac9a482d612edeae3222c61a9","leaf_index":229590,"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":"ccc400023742c0d9b9c441401f155eda1cc9d21dedf5fca064b2f49946430f55","side":"right"},{"sibling":"5bdffb60fe298901a3fdd024a584153e9d826a0f74c7a57e032d649827393c6d","side":"left"},{"sibling":"94701f7fff7f1cd01fe2c4a064391e12ad90d9abff5b6bf249987f185cd2a0eb","side":"left"},{"sibling":"3fd0dad2c755466865b274bdb5fbbd98aeaa1d86af55ff9d2a579544c590d2f6","side":"right"},{"sibling":"633626ccfc2bc89577dbb6f4c7bdc05be3e0c9feb36257c62aad54467840d2d7","side":"left"},{"sibling":"b7145c6b010b215b0c5002acb7ee3a025a5773e60677d3e7a894c7b648f0381f","side":"right"},{"sibling":"3ecde8d5b1aef7d87f45b824944efb9ddcb925547ba1b0df184a80b65e3628b2","side":"left"},{"sibling":"036b81c8003605ba78b7f79e8751093f80731187bf2970c7e3a612d0738c622b","side":"left"},{"sibling":"fd035c47cab5aa276f339e8f999b8537ea3a4fa7d9e74ec4c8ff95f5e10a223c","side":"right"},{"sibling":"d385017d38a86f6abc492026a7cd60ceb3b3ff2486142dc49e5acb179f4b7d11","side":"right"},{"sibling":"bde25d7e94e64717e426a97f6fcb4907e92b5c61fc89d92d7e0947a2249c3f6b","side":"right"},{"sibling":"d10d772a4984cae00e65ab24af21d1d260e475bbaae3f17871859eb705bd3999","side":"right"},{"sibling":"e79159853f2f35ddae8e3247d515e433c534277b287d65bbd77ae989aa4992fa","side":"right"},{"sibling":"3054319f1840cce0eaaf0bc4b1ae38e5bf8b6210927d924a750775cc7d77cca6","side":"right"},{"sibling":"0fd8b5059f279c4a4a6688de2472fdbc25543fee183df19b21dacca880354cff","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":232015,"merkle_root":"62bfb7809bb55667ad7eeebdb48267b9b2c1ee89bb808ea1e6d3a814a15aa402","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260617T133701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-06-17T13:39:59Z","sig_algorithm":"ed25519","signature":"930a3563c643cc7518d048b12a1f5392a96a5edce49533ba0a56f11b6cc69319bb1c800aacc46b52a6941c4d05dae255a45cac757d6093c971b96852c24f140e","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_4db99a89a31f3af9a868d756a808b3561b31657f9af60a751ac1b834f0dc933d"}}