{"_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_dcad507c604269a22a06ab83e01fa73852d66805bc1593e40dbb492301fc79bb","bitcoin_anchor":{"bitcoin_attestations":["bitcoin_block_949451"],"calendar_attestations":["https://finney.calendar.eternitywall.com","https://btc.calendar.catallaxy.com","https://alice.btc.calendar.opentimestamps.org","https://bob.btc.calendar.opentimestamps.org"],"ots_url":"/registry/data/substrate/anchors/77fc9c28fae777b81da5b495b3115474df6592dfac590333213d3bdf8b94a9b3.ots","stamped_at":"2026-05-15T03:00:03Z","status":"bitcoin"},"envelope":{"anchors":[{"chain":"crovia.axiom_graph","height":0,"merkle_proof":"spider_vendor_press_v1","root_at_anchor":"spider_vendor_press_v1"}],"axiom_id":"axm_dcad507c604269a22a06ab83e01fa73852d66805bc1593e40dbb492301fc79bb","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"e22623b9e5b6c5236bb6bd15352df912f8d0a8f55d606e61e1d069b9f41ea07d","published":"Tue, 05 May 2026 00:00:00 -0400","receipt_hash":"e22623b9e5b6c5236bb6bd15352df912f8d0a8f55d606e61e1d069b9f41ea07d","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":"e22623b9e5b6c5236bb6bd15352df912f8d0a8f55d606e61e1d069b9f41ea07d","observed_at":"2026-05-05T04:43:28.458286Z","parent_run_hash":"84f40dd8e6af9caa9f2a7fd632024f0e0192177c4532d9af5caf61b409324d7a","published":"Tue, 05 May 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:2605.00123v1 Announce Type: new \nAbstract: Safety trained large language models (LLMs) can often be induced to answer harmful requests through jailbreak prompts. Because we lack a robust understanding of why LLMs are susceptible to jailbreaks, future frontier models operating more autonomously in higher-stakes settings may similarly be vulnerable to such attacks. Prior work has studied jailbreak success by examining the model's intermediate representations, identifying directions in this space that causally encode concepts like harmfulness and refusal. Then, they globally explain all jailbreak attacks as attempting to reduce or strengthen these concepts (e.g., reduce harmfulness). However, different jailbreak strategies may succeed by strengthening or suppressing different intermediate concepts, and the same jailbreak strategy may not work for different harmful request categories (e.g., violence vs. cyberattack); thus, we seek to give a local explanation -- i.e., why did this spe","title":"Minimal, Local, Causal Explanations for Jailbreak Success in Large Language Models","url":"https://arxiv.org/abs/2605.00123","vendor":"arxiv_cs_ai"},"summary":"arXiv:2605.00123v1 Announce Type: new \nAbstract: Safety trained large language models (LLMs) can often be induced to answer harmful requests through jailbreak prompts. Because we lack a robust understanding of why LLMs are susceptible to jailbreaks, future frontier models operating more autonomously in higher-stakes settings may similarly be vulnerable to such attacks. Prior work has studied jailbreak success by examining the model's intermediate representations, identifying directions in this space that causally encode concepts like harmfulness and refusal. Then, they globally explain all jailbreak attacks as attempting to reduce or strengthen these concepts (e.g., reduce harmfulness). However, different jailbreak strategies may succeed by strengthening or suppressing different intermediate concepts, and the same jailbreak strategy may not work for different harmful request categories (e.g., violence vs. cyberattack); thus, we seek to give a local explanation -- i.e., why did this spe","title":"Minimal, Local, Causal Explanations for Jailbreak Success in Large Language Models","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-05-05T04:43:28Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2605.00123"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:7e5ca6a847713d4ad8539521f35bf26b80e30a081dd7b1418a89a8672d21a8b041382ac648e58a45ae5e1fa5a90151cedf332d96034d9a4249da11ecd2c2cd0f","signer":"crovia.substrate","subject":{"observed_at":"2026-05-05T04:43:28Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2605.00123"},"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":"7e5377c02f417017e1a049af71770f84bb68fc83d4a5099815f6c267651a41bd","leaf_index":114230,"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":"70c4c6ad99e0b324c2d46abbe1f61877754d1ef240acd5a6709c6a43a4023264","side":"right"},{"sibling":"d0a12b1437de809b2c2b2ce8881f078a7b91debd80dd91b0f45aaa9978b997dd","side":"left"},{"sibling":"7557d8667672ad0292240f279edd9b9661cf1628bdd4b722514751c016901032","side":"left"},{"sibling":"eeb0279992b69447b3d2b2a337d03fe91252a242226a836b2eef532cd437a748","side":"right"},{"sibling":"8444d0a639fac8e1654e2cbdd22e776f09c6550d93fc865934fd27bc1b1d9a0b","side":"left"},{"sibling":"87b4957d049a161a9b39c490e114dc16a468e44f3b33f8d54b249a6eb3aee3c6","side":"left"},{"sibling":"79ab99f7ecb15901e23d5b9cde8e96e03f496b5efce971a5e585b7d5bed96577","side":"right"},{"sibling":"46dca532ded31bba3e38a2fc1bf625ddbe113eaf158d9999dfa7f7d5674bbb32","side":"right"},{"sibling":"17e21f83c86c2a86dddad911d22393ee81f41d8e0b79ef8c0c48668ea846f2ca","side":"right"},{"sibling":"8df6c69f776fbba620634f6baf125eeaa6fdf9426e461e649028010d9a703f42","side":"left"},{"sibling":"ea40d1bd0432ad4dd90f023c692aaab8c8f54e27ce652e82f2ec8e16cacfb632","side":"left"},{"sibling":"673cd6d27b696232f7f65e7a0733c7df6bc9fac3bcb569907ebb0de1c72c4bb2","side":"left"},{"sibling":"76d7c4385d71ae8104107105be66eddb792e01ed6e493db5a9b4eec5441abb76","side":"left"},{"sibling":"b03f005860bf95148ea89c703a32ca19ab7a2ca71b58bb628ff94a9edb8703b0","side":"left"},{"sibling":"21d1e30b556f553dc939fddc23e6367f0a7755ebe3dd489dc0001cef017beb7f","side":"right"},{"sibling":"f2817ab288b5324fe49770372c7a10f33f7cd11005f8d4c0a730316f5229dc98","side":"left"},{"sibling":"725fac972e772ca0dc598810ea1abc70df472f72d2d6ab8a0baee2b80e5d2f4c","side":"left"},{"sibling":"98fc57dfef8873b512edc8340f7181df57302bb96777625e072235c62d7c5895","side":"right"}]},"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":134292,"merkle_root":"77fc9c28fae777b81da5b495b3115474df6592dfac590333213d3bdf8b94a9b3","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260515T023701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-05-15T02:37:25Z","sig_algorithm":"ed25519","signature":"68107a834b00b24f5d4501e5ec727445311f132a486567ecc4c72a4e6dff24c8c21f2de3105293353ba5fdbe370d032819af6aa70f694e2e39b6af6737507009","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_dcad507c604269a22a06ab83e01fa73852d66805bc1593e40dbb492301fc79bb"}}