{"_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_639f454cddb7d00f9c8809ac31ba813be496d4e3be2fc199ef2f6104c5829d85","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_639f454cddb7d00f9c8809ac31ba813be496d4e3be2fc199ef2f6104c5829d85","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"0ec2a438181cafcdc9f743f274f4c572134f1c7049435ab990968a93f24a268b","published":"Fri, 29 May 2026 00:00:00 -0400","receipt_hash":"0ec2a438181cafcdc9f743f274f4c572134f1c7049435ab990968a93f24a268b","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":"0ec2a438181cafcdc9f743f274f4c572134f1c7049435ab990968a93f24a268b","observed_at":"2026-05-29T04:43:58.478092Z","parent_run_hash":"0fcd87efcfe67ccb9952f747541debc16793919a4d20fd71ca0ad5516a0a13ee","published":"Fri, 29 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:2601.08654v2 Announce Type: replace-cross \nAbstract: Rubric-based text evaluation increasingly uses large language models (LLMs) as scalable judges, but aligning frozen black-box models with human scoring standards remains challenging. We formulate this challenge as a criteria-transfer problem: the goal is not merely to prompt an LLM to assign a score, but to transfer human rubric intent into a stable, auditable, and human-aligned scoring protocol. We identify three recurring failure modes in LLM-based rubric scoring: rubric execution drift, unverifiable score attribution, and human-scale misalignment. To address these failure modes, we introduce Rulers, a three-stage inference-time framework for reliable, evidence-grounded rubric-based text evaluation. Rulers first converts a human rubric into a locked task-level specification, then executes the specification with structured checklist decisions, typed evidence grounding, and extractive quote verification when applicable, and fin","title":"From Rubrics to Reliable Scores: Evidence-Grounded Text Evaluation with LLM Judges","url":"https://arxiv.org/abs/2601.08654","vendor":"arxiv_cs_ai"},"summary":"arXiv:2601.08654v2 Announce Type: replace-cross \nAbstract: Rubric-based text evaluation increasingly uses large language models (LLMs) as scalable judges, but aligning frozen black-box models with human scoring standards remains challenging. We formulate this challenge as a criteria-transfer problem: the goal is not merely to prompt an LLM to assign a score, but to transfer human rubric intent into a stable, auditable, and human-aligned scoring protocol. We identify three recurring failure modes in LLM-based rubric scoring: rubric execution drift, unverifiable score attribution, and human-scale misalignment. To address these failure modes, we introduce Rulers, a three-stage inference-time framework for reliable, evidence-grounded rubric-based text evaluation. Rulers first converts a human rubric into a locked task-level specification, then executes the specification with structured checklist decisions, typed evidence grounding, and extractive quote verification when applicable, and fin","title":"From Rubrics to Reliable Scores: Evidence-Grounded Text Evaluation with LLM Judges","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-05-29T04:43:58Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2601.08654"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:69b1f000a32ce0ef3e795cc3303f6dadb0a5747e3479fd7fcef4b0fb95ee882c3ebb6dcf047416674498898e5f910058f7475d0323d836025fda0e215ffc320f","signer":"crovia.substrate","subject":{"observed_at":"2026-05-29T04:43:58Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2601.08654"},"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":"1fc607d897f7d8778e7403e54333a0ba8bb1aa590a8a280fac42ad87aab879fb","leaf_index":158110,"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":"4ec484a6101950743322c32b160c6eaf7b7f91693530f9aeb0a043eb9397c3a5","side":"right"},{"sibling":"f5fc1d0191604e9f28f01dbe0164a1133eadbc4d24486a5529b31e1f53e0debd","side":"left"},{"sibling":"b058d700279bbfa4a1e9dc08b9e1868967639b9dfb7aeb6a26b5f837e178b0b9","side":"left"},{"sibling":"ec79b47e4c788e1459e0d3dcc1d7f705087f3478d39bd22d2849f1f0e9348fdd","side":"left"},{"sibling":"e3130a3704881a2c1557e04fe5240e3ad958c2e712d62e0529e6f3284341b946","side":"left"},{"sibling":"796de9dd6ef901ab3e49311279a21042b8f2cfbb09b2fbb767544159218def9b","side":"right"},{"sibling":"62988561fabfe452383ec872bd31f27e80fe019c13c67e0ef3aed8f206215007","side":"right"},{"sibling":"463d4726f68bda2bbf724c72553fd53d88ea99a3d4a713f9b8a1b2d9fde12933","side":"left"},{"sibling":"002471ff5893cd2a2890119cbfe4a9456bfb46cf31fa6aee377650afe6ae0c92","side":"left"},{"sibling":"1dcc44e23fbb0218b13591e4b584eca3600dcf365769cb741e0ecd33b25b8c56","side":"right"},{"sibling":"fcf16a6f44025801f5b83e928acce764352ddbc06ae3043d8cde9a409933e6d8","side":"right"},{"sibling":"78982294dee68f9db9288c64d7e507c7865fda96e1b6f7ccff5c8bb152e93c49","side":"left"},{"sibling":"995b421824624a8282c7f44e64c64ee35344800f477ae1845b41be14d3fab94c","side":"right"},{"sibling":"66331bac84ca0f8983eb09fac7eaf95af234f1b82680b793eabff4ee25caac40","side":"left"},{"sibling":"35ca36cee447f0ef7064a25d55f59357c66901e31427729c4c1d8b14aa8adb6c","side":"left"},{"sibling":"eef0e8906a749d3470f89beeedc723f37a5737010bbb0dcc7cf91515338e5a3e","side":"right"},{"sibling":"1a07e481a9407d71aad078ce854cdeee362163c887fe10f889b0ecf0b5e749ad","side":"right"},{"sibling":"d841ad93efda0869e5eb97678f348f03f5caab4353e05ff4bf18f47fb945b822","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":158251,"merkle_root":"485e6b31fe60c8beba5b394808c7e4c32448b2ff65c2482c480ca0e2a2eda718","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260529T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-05-29T05:37:37Z","sig_algorithm":"ed25519","signature":"bbf9f005201182fce4f9d94c7a9d01a508b56daf7d9611bd73514f5f616bc059d0e5e1f2edfc95716e6fe08ef5fae38b558cbf7f2fd8f9d5dfe4c34a54c83005","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_639f454cddb7d00f9c8809ac31ba813be496d4e3be2fc199ef2f6104c5829d85"}}