{"_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_f205213a71dbd06ad7992e841c4c1a8779494e13044070c6bbb25946d14846ac","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_f205213a71dbd06ad7992e841c4c1a8779494e13044070c6bbb25946d14846ac","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"102ab9fc68f4dc372d235a9506d0e4f1b49248797e8fd404bc81e29b63147cd8","published":"Thu, 23 Jul 2026 00:00:00 -0400","receipt_hash":"102ab9fc68f4dc372d235a9506d0e4f1b49248797e8fd404bc81e29b63147cd8","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":"102ab9fc68f4dc372d235a9506d0e4f1b49248797e8fd404bc81e29b63147cd8","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:2604.06996v2 Announce Type: replace-cross \nAbstract: LLM-as-a-judge has become the de facto approach for evaluating LLM outputs. However, judges are known to exhibit self-preference bias (SPB): they tend to favor outputs produced by themselves or by models from their own family. This skews evaluations and, thus, hinders model development, especially in settings of recursive self-improvement. We present the first study of SPB in rubric-based evaluation, an increasingly popular benchmarking paradigm where judges issue binary verdicts on individual evaluation criteria, instead of assigning holistic scores or rankings. Using IFEval and LiveCodeBench, benchmarks with programmatically verifiable rubrics, we show that SPB persists even when evaluation criteria are entirely objective: among rubrics where generators fail, judges can be more than 50% more likely to incorrectly mark them as satisfied when the output is their own. We also find that, similarly to other evaluation paradigms, e","title":"Self-Preference Bias in Rubric-Based Evaluation of Large Language Models","url":"https://arxiv.org/abs/2604.06996","vendor":"arxiv_cs_ai"},"summary":"arXiv:2604.06996v2 Announce Type: replace-cross \nAbstract: LLM-as-a-judge has become the de facto approach for evaluating LLM outputs. However, judges are known to exhibit self-preference bias (SPB): they tend to favor outputs produced by themselves or by models from their own family. This skews evaluations and, thus, hinders model development, especially in settings of recursive self-improvement. We present the first study of SPB in rubric-based evaluation, an increasingly popular benchmarking paradigm where judges issue binary verdicts on individual evaluation criteria, instead of assigning holistic scores or rankings. Using IFEval and LiveCodeBench, benchmarks with programmatically verifiable rubrics, we show that SPB persists even when evaluation criteria are entirely objective: among rubrics where generators fail, judges can be more than 50% more likely to incorrectly mark them as satisfied when the output is their own. We also find that, similarly to other evaluation paradigms, e","title":"Self-Preference Bias in Rubric-Based Evaluation of Large Language Models","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/2604.06996"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:083100fda1ef008f30f4cad992f82f394046523e60ea0f2a1073d2f75fec340e96a3bec3c406aa3b56504cebc5e229870a640fa0b7a6cf4aa9209113071c650f","signer":"crovia.substrate","subject":{"observed_at":"2026-07-23T04:43:18Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2604.06996"},"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":"0b9c07a6efc3395db21b1b9606d396defb681b3c77fd8cff5f64e65258361aae","leaf_index":343801,"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":"0b95cfe149e16868b8094b1cfc4291bbcb9886e5251e04d4cea8934a08e6744d","side":"left"},{"sibling":"ac9fae5fadab0eecbb932a912f2f1319ba039c5430bf918988855cadbdf2b96e","side":"right"},{"sibling":"58b7f6058770a791b13d51edb21b4b03574a023f6aa12a3b7b776ed10288a286","side":"right"},{"sibling":"e3d67f858869217b6bb995e6b1f0458f3f34abb4e494d42966f4a978f9df10a4","side":"left"},{"sibling":"3a71d7f46b406fcfbdfbc11a7325edc08bc6a524909b33541b5d4f9893ac1298","side":"left"},{"sibling":"8c4abba7f73d017263c7cfa7cf00e7dad2248eccd24b930d64f9284ce5a8897d","side":"left"},{"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_f205213a71dbd06ad7992e841c4c1a8779494e13044070c6bbb25946d14846ac"}}