{"_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_8098b2fe568ef0df21443c1e494cd708c77dc4dcc337ba3ed0d69a3f2867ecc9","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_8098b2fe568ef0df21443c1e494cd708c77dc4dcc337ba3ed0d69a3f2867ecc9","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"857727d5f16ba37e75ae49d07d5733fe411540b21bd4dab46bc0624bcfd9baba","published":"Tue, 21 Jul 2026 00:00:00 -0400","receipt_hash":"857727d5f16ba37e75ae49d07d5733fe411540b21bd4dab46bc0624bcfd9baba","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":"857727d5f16ba37e75ae49d07d5733fe411540b21bd4dab46bc0624bcfd9baba","observed_at":"2026-07-21T04:43:35.036805Z","parent_run_hash":"03e944014de2697434479833d15ea9303e014945afc230ecc7f207824493b589","published":"Tue, 21 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:2607.09306v2 Announce Type: replace-cross \nAbstract: Whether a language model behaves as it claims is a judgement on which independent human raters cannot agree (Fleiss kappa = 0.074). We show that a small, purpose-built instrument does better. A linear read-out of the frozen representation of a from-scratch 146-million-parameter auditor detects companion-induced sycophancy, dependence-fostering and confabulated memories on generator models unseen in training (AUROC 0.804, leave-one-generator-out, against ground truth fixed at generation, independent of human judgement), where a frontier zero-shot judge on the identical items reaches 0.721 and falls to chance on the most distant family. The auditor's substrate is hyperbolic, and its demonstrated benefit is hierarchical: an ablation isolates the advantage over a matched Euclidean control on multi-domain structure. On this task, behavioural faithfulness is measured not by scale but by a small, purpose-built instrument.","title":"A small language model detects behavioural faithfulness gaps that frontier judges and human raters miss","url":"https://arxiv.org/abs/2607.09306","vendor":"arxiv_cs_ai"},"summary":"arXiv:2607.09306v2 Announce Type: replace-cross \nAbstract: Whether a language model behaves as it claims is a judgement on which independent human raters cannot agree (Fleiss kappa = 0.074). We show that a small, purpose-built instrument does better. A linear read-out of the frozen representation of a from-scratch 146-million-parameter auditor detects companion-induced sycophancy, dependence-fostering and confabulated memories on generator models unseen in training (AUROC 0.804, leave-one-generator-out, against ground truth fixed at generation, independent of human judgement), where a frontier zero-shot judge on the identical items reaches 0.721 and falls to chance on the most distant family. The auditor's substrate is hyperbolic, and its demonstrated benefit is hierarchical: an ablation isolates the advantage over a matched Euclidean control on multi-domain structure. On this task, behavioural faithfulness is measured not by scale but by a small, purpose-built instrument.","title":"A small language model detects behavioural faithfulness gaps that frontier judges and human raters miss","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-07-21T04:43:35Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2607.09306"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:d4c4f2bc8d4606ed9dd50cac33dfbab74f25269b889f39aeceb46075ce7f2f8fe8ca04e913afb161f97fbe1c01796fe61c53aa5ff384ef5599afe0f3c7703701","signer":"crovia.substrate","subject":{"observed_at":"2026-07-21T04:43:35Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2607.09306"},"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":"17d717e2fc402bcff4a1e0e8568806f89d4c66d9b1cf7646313e642c79c1fa62","leaf_index":337008,"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":"45b386a5bc222e2cfc0cf4d2d309085f92c1927762275e36491345466e0e793a","side":"right"},{"sibling":"4c27a353df263bd1487327791a12860f56699bffd3b3c34162c4de9b900b3969","side":"right"},{"sibling":"b00b7c53b6ec68592a6bef163ce12a16c5cce4f50555e9c7d4b5be59756be764","side":"right"},{"sibling":"ea31fc0726388d027b61458603d17a0c3806d933bf2f948c2618ea4ec35c3566","side":"right"},{"sibling":"aeee7b559866550c2d734a696b201b0dd33399df66ed83a8f4689426fd639296","side":"left"},{"sibling":"07c87330e171a55b29b083c7c6c30454fcdfd68bb1f0238fbbe25104f4826174","side":"left"},{"sibling":"34efd454df46a7476d0bc83ac9843e7409ddde5c8ee1426de19ece35f23d2d83","side":"left"},{"sibling":"45255096c5a08e740a615b6e3c262589a170dbfc373bdeaceae175916dd2ab97","side":"right"},{"sibling":"1298242aa509bc13b92160250ead2d95a721941ca6310e33b9eb0bf0821557d0","side":"right"},{"sibling":"61d44c6d16b87de577db53cff0dba2f003c50c036d92dc335120aa70124c8788","side":"right"},{"sibling":"5d0b792dbe69fd0a7cd8d79b467aa10204d1f25be602c06190f3423bc22727b8","side":"left"},{"sibling":"9eb5077edfb3dc553857d4794b925bfce117e0f8a1d049af5d0dd9026b470eef","side":"right"},{"sibling":"414b1a70fd1dcb25489a194714b97492b066684b15d0b7a48a176c4b9b5bc713","side":"right"},{"sibling":"21d66dd41003813f710b7617944f1bfba3258658a5d3370c21cad8f9e945bc99","side":"left"},{"sibling":"613f015699131eb89bd755dee67133be95af25cf5f16c1c8ce4b99d963b8dd86","side":"right"},{"sibling":"a729b574b1135956436ded5eef1fe8f08014ff6a0729749d307ab1bca93fcdc9","side":"right"},{"sibling":"77025bcb374a7ad74f520643e20a8ae1205a7ee78507b0beb93117760f1c29d3","side":"left"},{"sibling":"4bf21052e085e8ac81f1dec1d2b310bd12bf948992de6177d12e9d2fda8d39f0","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":337144,"merkle_root":"5e969cc01afa67e4dbe5d37b712cdb10f4aa1fd74404e02eab724cf487c8d6d9","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260721T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-07-21T05:38:38Z","sig_algorithm":"ed25519","signature":"5c0c1a8dd2793d787ccd5e49e8b4d70eed136352555518589f05c74be357fc171702e42a76c3a556d90e3d51ff36cb3d292aaac83c66566de7b943f318bda50c","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_8098b2fe568ef0df21443c1e494cd708c77dc4dcc337ba3ed0d69a3f2867ecc9"}}