{"_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_c6dd847fb72da76c035182cae6d65084bfb687075d0eeb3d2c8239aaaed51271","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_c6dd847fb72da76c035182cae6d65084bfb687075d0eeb3d2c8239aaaed51271","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"e2f2aa0860b38abb9d3798286c38f044c222dd5b56d08b25f624aa66494829ae","published":"Fri, 29 May 2026 00:00:00 -0400","receipt_hash":"e2f2aa0860b38abb9d3798286c38f044c222dd5b56d08b25f624aa66494829ae","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":"e2f2aa0860b38abb9d3798286c38f044c222dd5b56d08b25f624aa66494829ae","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:2605.29025v1 Announce Type: new \nAbstract: Federal agencies are deploying large language models (LLMs) to categorize public comment corpora, where the model's organization of the record shapes what policymakers see and which arguments register. Standard evaluation, anchored on stance accuracy against a small validated set, cannot detect when different models produce materially different categorizations of the same public input. We propose an Interpretive Audit Pipeline that treats multi-model disagreement as diagnostic of interpretive complexity and directs human review toward genuinely ambiguous public input. Analyzing 1,260 public comments on a federal USDA docket across four LLMs, we find that inter-model thematic divergence exceeds within-model prompt variation, and that an expert rubric suppresses deep interpretive disagreement without resolving it. In a two-stage labeling study on a stratified 40-comment subsample, four LLMs and a human annotator labeled independently and t","title":"When Models Disagree: Rethinking LLM Evaluation for Public Comment Analysis","url":"https://arxiv.org/abs/2605.29025","vendor":"arxiv_cs_ai"},"summary":"arXiv:2605.29025v1 Announce Type: new \nAbstract: Federal agencies are deploying large language models (LLMs) to categorize public comment corpora, where the model's organization of the record shapes what policymakers see and which arguments register. Standard evaluation, anchored on stance accuracy against a small validated set, cannot detect when different models produce materially different categorizations of the same public input. We propose an Interpretive Audit Pipeline that treats multi-model disagreement as diagnostic of interpretive complexity and directs human review toward genuinely ambiguous public input. Analyzing 1,260 public comments on a federal USDA docket across four LLMs, we find that inter-model thematic divergence exceeds within-model prompt variation, and that an expert rubric suppresses deep interpretive disagreement without resolving it. In a two-stage labeling study on a stratified 40-comment subsample, four LLMs and a human annotator labeled independently and t","title":"When Models Disagree: Rethinking LLM Evaluation for Public Comment Analysis","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/2605.29025"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:ea4bb6cdc7800d0a240a041ef4c97ee0f6cbd156799a40e86ebca5627b023cf80905fd376c2275842cb5bfe55a8a068aa25f946143d4b2ae7c5d61925d0a520a","signer":"crovia.substrate","subject":{"observed_at":"2026-05-29T04:43:58Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2605.29025"},"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":"0dd5a6a47c6b5968ddd2bb104802d2fcc190a016ee6626bb2e1b72d27719dc04","leaf_index":157654,"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":"a757035fb097760c1952606c4fc8170b7c1c6be60dcd7ab4dc57b195381f3e45","side":"right"},{"sibling":"68aea7294c1151b8db42f3bc5bbd3aa91853f95edb7a15c3e48ff8b256ccbf56","side":"left"},{"sibling":"dc47d7bc60756368bb6ff20a3399c83adb9f51059a8120eb0d73727a57c50c21","side":"left"},{"sibling":"5d5db581b90d223c2cc94102e6ab6383e4d97f9eb4c3e6899f42a6d610c64a57","side":"right"},{"sibling":"bb9691a4bac0bf4ae76e52675fbd3b05bc40d48fca7c797c7f066a157c7f880a","side":"left"},{"sibling":"043b0b93db31688bb506b27c0bb88b9838dd4a0b5e0340f6fa82e708ed75922b","side":"right"},{"sibling":"f65c4257e1e3e5a8d1432a336a21d8e806501313e0c2888ff215dba80f4c4cfe","side":"left"},{"sibling":"27e5f392a568b11659ecd5aed52502b5e6d88eea7862dffac806a2d7b5a9ef78","side":"left"},{"sibling":"ece7b043912367e6be374d77e09128de032af83a2b87e39b397350dd279ebe83","side":"left"},{"sibling":"39ec45a73732c5ed1abe96972bd3bc32a517083704467dde1c8117578609124d","side":"left"},{"sibling":"68b4895a8015cdde1c1baeaf63a8382cf574ce4d2ad88d596d4217ce2238245e","side":"left"},{"sibling":"0bc831354843fa27f7ba6a4b3080a72fd440b9a76d1bac63429adfbfe6549bca","side":"right"},{"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_c6dd847fb72da76c035182cae6d65084bfb687075d0eeb3d2c8239aaaed51271"}}