{"_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_8b6ee67de9dff7a3f0348e8896f5a9bb99c0759a7e7368eac7e6190bf333f78b","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_8b6ee67de9dff7a3f0348e8896f5a9bb99c0759a7e7368eac7e6190bf333f78b","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"1c1f8b460a6fc68500e62e0aef0d4e9a2654930ae9b313016cdca533c4127ac0","published":"Mon, 29 Jun 2026 00:00:00 -0400","receipt_hash":"1c1f8b460a6fc68500e62e0aef0d4e9a2654930ae9b313016cdca533c4127ac0","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":"1c1f8b460a6fc68500e62e0aef0d4e9a2654930ae9b313016cdca533c4127ac0","observed_at":"2026-06-29T04:44:03.414425Z","parent_run_hash":"36b5ab5c57ae76dc9e1a863501c4d38f172868cfae31b4ba5baf3caffaafb2c4","published":"Mon, 29 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:2606.26071v2 Announce Type: replace-cross \nAbstract: A central goal of safety research is determining whether a model is misaligned. Prior work has largely focused on detecting concerning behavior. But behavior alone does not establish misalignment: a concerning action can arise from benign causes such as confusion. This motivates model forensics: investigating whether the action was driven by malign intent. In this paper, we propose a baseline protocol for model forensics consisting of two steps, iterated as needed. First, we read the chain of thought (CoT) to generate hypotheses about what drives model behavior. Second, we make edits to the prompt or environment to test these hypotheses. While the CoT is not always faithful, it is a rich source of unsupervised insight that can guide the collection of more rigorous evidence. To evaluate our protocol, we create a suite of six agentic environments where models exhibit concerning behavior, and apply it to each. We establish that Ki","title":"Model Forensics: Investigating Whether Concerning Behavior Reflects Misalignment","url":"https://arxiv.org/abs/2606.26071","vendor":"arxiv_cs_ai"},"summary":"arXiv:2606.26071v2 Announce Type: replace-cross \nAbstract: A central goal of safety research is determining whether a model is misaligned. Prior work has largely focused on detecting concerning behavior. But behavior alone does not establish misalignment: a concerning action can arise from benign causes such as confusion. This motivates model forensics: investigating whether the action was driven by malign intent. In this paper, we propose a baseline protocol for model forensics consisting of two steps, iterated as needed. First, we read the chain of thought (CoT) to generate hypotheses about what drives model behavior. Second, we make edits to the prompt or environment to test these hypotheses. While the CoT is not always faithful, it is a rich source of unsupervised insight that can guide the collection of more rigorous evidence. To evaluate our protocol, we create a suite of six agentic environments where models exhibit concerning behavior, and apply it to each. We establish that Ki","title":"Model Forensics: Investigating Whether Concerning Behavior Reflects Misalignment","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-06-29T04:44:03Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2606.26071"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:873108d2d851420b933d1ce8f996cf7a5f60c5fd558826304a67596b70553fb55a6e1cfd765075e6621f1dd223030389d6c64384b7346b83fc5307d2dc222c05","signer":"crovia.substrate","subject":{"observed_at":"2026-06-29T04:44:03Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2606.26071"},"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":"8f217188f6e7bd45fcf2cf31fc92c90ac9e824593e96443920f4f47959230495","leaf_index":261544,"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":"7bc09fec2016e112d25b775c9e14e7476826f32ad9e99133186fc18fcc594b1b","side":"right"},{"sibling":"b3e7866d1e9135899b48b3f9a0b673d66cdd5f00323f6bc04927e9ea0fcc5bf0","side":"right"},{"sibling":"39df260d9e67968251f04dabeb0b628d05bb2fd6418340b7627e918dc259fb42","side":"right"},{"sibling":"2b682a5aa56046638dbe82af8097be3fe39c2a202eec7947249806f95b65bc4d","side":"left"},{"sibling":"ae5fc09861f6c2f429def61fea6325e83ea51f07bb7d128d623b34ab68eb92d7","side":"right"},{"sibling":"86b7dc18bff854bbc3b571815bc2446a58496e2deb9b0519a081576729826ea7","side":"left"},{"sibling":"68a8ff8f71247734930721fd8fb46d5601c2f438645b61686958db9f099baa00","side":"right"},{"sibling":"6541e04390f40ec94bca13a445548c91511634a5ffb1a1a6cce967da56056afd","side":"left"},{"sibling":"6d1df65d14253ed3a13c03e25aa9adcd9a091d8062a82e8586bcaee74013b90e","side":"left"},{"sibling":"9f9daa9d12e65b219f34c92aec45450536b79a42b8892050d66961432ae28ed1","side":"right"},{"sibling":"b5725d7b0807dc6da32d9788f20057fa8726be38d30a9ebdabc605ae92739122","side":"left"},{"sibling":"e321b2cac14cbe28f76ccb7938249a40ff60cd5d2128b5634be046ea10e984b8","side":"left"},{"sibling":"5900dc6c7d13855af9d0385baf1691ec386df33e450c422af1cabe0a36e40ad8","side":"left"},{"sibling":"ae636ddee98c71ab7a7dc55ddfab70c7f710a2b6abfdf7a8b5d16a4017d1c0d1","side":"left"},{"sibling":"f29798d8bb6aa9900eab878992d9ff0c53266debd87472f31ab26a6a3fb55880","side":"left"},{"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":261662,"merkle_root":"aa8865c239aa2eb6c8aa7c6250f56b3cd5709854a8a07f6a29eb4ddd8802cb6f","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260629T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-06-29T05:38:02Z","sig_algorithm":"ed25519","signature":"476329233e82fb35fba2552ddc5d1d75b2bdd8513bbd281e9c40a0b8e475df374a62dcd8b456b0c5e8815984f5b4bf0983ae95d2cf4d7412ebb13a433b933c0a","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_8b6ee67de9dff7a3f0348e8896f5a9bb99c0759a7e7368eac7e6190bf333f78b"}}