{"_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_c15a66162cf3875981d0870bf2f8d5a804be4e56edccd917fa8a65df2cd678b9","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_c15a66162cf3875981d0870bf2f8d5a804be4e56edccd917fa8a65df2cd678b9","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"8442bbfa684c31678e6839614b8affd918d124240abab73485559c8b36d0183a","published":"Tue, 28 Jul 2026 00:00:00 -0400","receipt_hash":"8442bbfa684c31678e6839614b8affd918d124240abab73485559c8b36d0183a","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":"8442bbfa684c31678e6839614b8affd918d124240abab73485559c8b36d0183a","observed_at":"2026-07-28T04:43:08.282317Z","parent_run_hash":"23a1ef85134515049ced29518443d084afc46fd7c967741e6c6acdbdbbf29939","published":"Tue, 28 Jul 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:2607.24539v1 Announce Type: new \nAbstract: Multimodal large language models (LLMs) can combine topology, measurements, and incident text for grid diagnosis, yet answer accuracy does not establish that task-appropriate evidence was used. This letter proposes a general framework in order to conduct task-conditional faithfulness audit. It compares self-reported reliance, intervention-derived behavioral reliance, and preregistered engineering importance. The framework first registers task-specific evidence requirements and compares them with self-reported reliance and behavioral changes under controlled modality ablations. To resolve detected discrepancies, we design an evidence-gated correction and re-audit mechanism that regenerates failed responses under evidence constraints and independently re-ablates them to verify improved grounding without performance loss. Case studies evaluate three differently scaled LLMs on IEEE 39- and 118-bus scenarios. These results validate the framew","title":"Task-Conditional Faithfulness Auditing of Multimodal LLMs for Grid Diagnosis","url":"https://arxiv.org/abs/2607.24539","vendor":"arxiv_cs_ai"},"summary":"arXiv:2607.24539v1 Announce Type: new \nAbstract: Multimodal large language models (LLMs) can combine topology, measurements, and incident text for grid diagnosis, yet answer accuracy does not establish that task-appropriate evidence was used. This letter proposes a general framework in order to conduct task-conditional faithfulness audit. It compares self-reported reliance, intervention-derived behavioral reliance, and preregistered engineering importance. The framework first registers task-specific evidence requirements and compares them with self-reported reliance and behavioral changes under controlled modality ablations. To resolve detected discrepancies, we design an evidence-gated correction and re-audit mechanism that regenerates failed responses under evidence constraints and independently re-ablates them to verify improved grounding without performance loss. Case studies evaluate three differently scaled LLMs on IEEE 39- and 118-bus scenarios. These results validate the framew","title":"Task-Conditional Faithfulness Auditing of Multimodal LLMs for Grid Diagnosis","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-07-28T04:43:08Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2607.24539"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:d3e049b438f0dcedbb9db6521afb6b0d5c66788e6c9000703cfd6d8fd844e613f296f6bf271f239b3d0dbf26759c2628598acc723547cc8ac53b73a7ed338d05","signer":"crovia.substrate","subject":{"observed_at":"2026-07-28T04:43:08Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2607.24539"},"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":"2f01f650a71becf7bef2e1555a743d745e07064b5d18fdd4d83301e6b2378eff","leaf_index":360480,"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":"e8c806beeb48a7d5687230e18baa6867a91e8cb0ef6c93f1c6a11c4631f647f2","side":"right"},{"sibling":"50896c2888b2ebaceb640434348ae090e437e94d5df70c082c097fb9900fbb95","side":"right"},{"sibling":"f0655631bdf854761ec279dffb547e4a93a0d87880a4efb5874cc7ebdcdb176c","side":"right"},{"sibling":"680a6af777a0b8fab96620537ccd693715ae8af5bbceb7a7ade52fdb78e06bda","side":"right"},{"sibling":"a1c76048aeec2248236838a703e4ac14a61f82ef51d1c13eb066a5d267c78b1a","side":"right"},{"sibling":"9a45174405abad8c6238b5cea175009c5728635224ac72d0182f5d73903f2e17","side":"left"},{"sibling":"af35a1d32b2197ab764f9882c8ba5ae653d1e5419b2df50a1daf88021ca8b2bd","side":"right"},{"sibling":"7da15787b28ee42d6f6ffa689ccb25f3c7958b4ad112266a2a4acad4347e0386","side":"right"},{"sibling":"eb79f1d599c07786d2268140481af8b617999ecc5688c6283fe58e5e6f3a2640","side":"right"},{"sibling":"fe03c6d0b083c4097049d7fc6d7d08dfdb05d9c198b2786336689712d66eabf0","side":"right"},{"sibling":"590ea76fdfc1b9e8072055c378be3182f916709e8d06bd955232e650a7188b86","side":"right"},{"sibling":"d92781c59301ffd5bfb0bad75d9fdf6d73879f715518149d383f7362213e0daf","side":"right"},{"sibling":"f315303d4402b57497416d48eb4c4bb50405b40862d41c7caf318cb3d29c5237","side":"right"},{"sibling":"36973eb5f586cd67e0c0dc055dd87e734aa544c35d4400d2c9f932f8ef8fb27f","side":"right"},{"sibling":"e39f7900355489c4718b21cc2d3d06382e1d2f22b864d10be9ebc9d498b279a1","side":"right"},{"sibling":"1f9a970b25dd938c98cabc9e0a55c5a6f46292b9fa37cc89d90ef0cbb1e05a8c","side":"left"},{"sibling":"77025bcb374a7ad74f520643e20a8ae1205a7ee78507b0beb93117760f1c29d3","side":"left"},{"sibling":"3b50864499c874394ea0928567747666eaf59b01380e46cd52164ec5acec0f71","side":"right"},{"sibling":"1cecb7f447febd025aac272837c80de218aecc6485d2395a509b2a1f1b9c746e","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":361008,"merkle_root":"3065e8369ea437c06beba806dc4e4bb159979adeb21fe632242c1906a7204647","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260728T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-07-28T05:38:48Z","sig_algorithm":"ed25519","signature":"9141644407577a82611c1579110f667de2d46dc6b93c6322edf26f4c3056ea99f0e56502853908e30d87c38bcf95eb6e0ab5130525aa51505bd6f61938120609","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_c15a66162cf3875981d0870bf2f8d5a804be4e56edccd917fa8a65df2cd678b9"}}