{"_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_77401e7687625d7e77c0750288ca85375b2d335a153fd4d8465b839b8940cbba","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_77401e7687625d7e77c0750288ca85375b2d335a153fd4d8465b839b8940cbba","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"74474bfb46212d1c73e71da02ddc0139c37e1890b651781952b6050a54fa673a","published":"Thu, 23 Jul 2026 00:00:00 -0400","receipt_hash":"74474bfb46212d1c73e71da02ddc0139c37e1890b651781952b6050a54fa673a","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":"74474bfb46212d1c73e71da02ddc0139c37e1890b651781952b6050a54fa673a","observed_at":"2026-07-23T04:43:18.446221Z","parent_run_hash":"b3f5e4095688e31d15c25de2607bca42111343bdfdac967d48e47905415ddea0","published":"Thu, 23 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:2607.16195v2 Announce Type: replace \nAbstract: We identify a structured confound in Reinforcement Learning from Human Feedback (RLHF). Pairwise preference labels are intended to reflect the compared outputs, but they may also reflect the rater's state during annotation. Under sustained stressful or distressing conditions, raters' preferences may shift over time, so that preference data encode rater state alongside judgments about response quality. We argue that, if present, such shifts would differ from ordinary disagreement or random label noise. They would be state dependent, could be shared across annotators under similar conditions, and would not necessarily cancel during aggregation, reward modeling, and policy optimization. We propose rater state shift as a plausible and testable source of structured bias in RLHF preference data. This paper develops a hypothesis and an audit framework for studying this source of bias. We define rater state shift, rater state confound, and c","title":"Rater State Bias in RLHF Preference Data: An Audit Framework","url":"https://arxiv.org/abs/2607.16195","vendor":"arxiv_cs_ai"},"summary":"arXiv:2607.16195v2 Announce Type: replace \nAbstract: We identify a structured confound in Reinforcement Learning from Human Feedback (RLHF). Pairwise preference labels are intended to reflect the compared outputs, but they may also reflect the rater's state during annotation. Under sustained stressful or distressing conditions, raters' preferences may shift over time, so that preference data encode rater state alongside judgments about response quality. We argue that, if present, such shifts would differ from ordinary disagreement or random label noise. They would be state dependent, could be shared across annotators under similar conditions, and would not necessarily cancel during aggregation, reward modeling, and policy optimization. We propose rater state shift as a plausible and testable source of structured bias in RLHF preference data. This paper develops a hypothesis and an audit framework for studying this source of bias. We define rater state shift, rater state confound, and c","title":"Rater State Bias in RLHF Preference Data: An Audit Framework","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-07-23T04:43:18Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2607.16195"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:fe3a12c21e3699b72290ec1bd6bd27d76df42ab8f11be26a73351e1dfba355884bc02cfcc43d52021f002ccdb22339c81bd656c45ef0fba7a842fcdc1a52af0f","signer":"crovia.substrate","subject":{"observed_at":"2026-07-23T04:43:18Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2607.16195"},"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":"ec7ee3a3c20aee15e891c46ad904d16d67c6483958cdb51b363ed9acc36d9024","leaf_index":343764,"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":"6ba88a8a164eaf42eb8503bda1e6a94551b7bfb35d6836500337d74061fdf2f1","side":"right"},{"sibling":"f129ba9037604c6a59fb4cb874646a2268f600510e3a861da9cc0044a0a307f0","side":"right"},{"sibling":"b9adde91015b7900cc4ebf6451bbc6f67d8995510714a1cab0026b228f6d7529","side":"left"},{"sibling":"0f0010a0cb3bbb624ad3911bddd6fecb33845f8418cb5307b3b561b07848cc64","side":"right"},{"sibling":"60ac0a360039328a953cf84192a9ca0785104fe8331eea7cef380e56648d0478","side":"left"},{"sibling":"bd62965e883f30b5727471e8ff54a8dd65e32e4f4987b1fd326fdacea35f9b59","side":"right"},{"sibling":"84e2bd69f70ff0e814f453c01a295fde8d94bdb3824a1424ab4fd97be4fa4cba","side":"left"},{"sibling":"fbe8bc0f33cd1a297ce2f845b101ed1107ebb67f2c2577c28ed032c1046d3b97","side":"left"},{"sibling":"6ecdcc1e2fb6ab44777fffbb7c8297d723018c63aac9d90c7a1bbebe728d84cf","side":"right"},{"sibling":"93d7d8e0e882d05b2a15bb707a824979a0427907eb47e687c712906674a0d345","side":"left"},{"sibling":"92219a3ef58cd145d94f071b0b9396cec3707812b02a8c7c63f2d0e22340552b","side":"left"},{"sibling":"4eb402d67bd4bf583b0434363061166fe259c34cc6c42adb32dcfbff0a9f5767","side":"left"},{"sibling":"2dd9cb2521044ee7c6b74f2315e0a0253b8df0d04a7b810bbbbe7da5a9788769","side":"left"},{"sibling":"21d66dd41003813f710b7617944f1bfba3258658a5d3370c21cad8f9e945bc99","side":"left"},{"sibling":"941f71d7ce3990a507b8f485de3f872a51d0e9a8c59405d76c2ae6f4a6af494a","side":"right"},{"sibling":"6281b6f7a93c44e3c4895bc65cfcb6f2be24dd725f4f46540ec022a6e215f4e8","side":"right"},{"sibling":"77025bcb374a7ad74f520643e20a8ae1205a7ee78507b0beb93117760f1c29d3","side":"left"},{"sibling":"6baede22892163664bb2e4d92cf75e6b290761533a6c39491c3afd89bb3a0252","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":343944,"merkle_root":"afab58f71597d393a7a61b857dac2eacb72fd1c04cd1432c2622d7b19309dffd","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260723T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-07-23T05:38:39Z","sig_algorithm":"ed25519","signature":"1a58fdc6367d0c86f83d2385be748e0800a64bcf9987c92fadca53deda009cd390d2070302c2b6e44841febfd864637c323ba12c7a1e9ae58fdf2a0cf546ac01","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_77401e7687625d7e77c0750288ca85375b2d335a153fd4d8465b839b8940cbba"}}