{"_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_bbb60e3284bec78fc22b973ec11330a58048946871618b5ef01526469c1f31a0","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_bbb60e3284bec78fc22b973ec11330a58048946871618b5ef01526469c1f31a0","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"f33e9a70dc060bbb7aeba91adf3272b9ed708998a23d59c5b0fb9cfe4abda21e","published":"Fri, 26 Jun 2026 00:00:00 -0400","receipt_hash":"f33e9a70dc060bbb7aeba91adf3272b9ed708998a23d59c5b0fb9cfe4abda21e","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":"f33e9a70dc060bbb7aeba91adf3272b9ed708998a23d59c5b0fb9cfe4abda21e","observed_at":"2026-06-26T04:43:58.168958Z","parent_run_hash":"9459505a803125e4b968df08c74ed0054a2aafd44e4e1a036e3b0709a8a65cb4","published":"Fri, 26 Jun 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:2606.27226v1 Announce Type: new \nAbstract: Evaluating LLM outputs remains a major bottleneck in NLP: human evaluation is expensive and slow, lexical metrics correlate poorly with human judgments on open-ended generation, and holistic LLM judges often produce opaque scores that are hard to debug. We propose BINEVAL, a framework that decomposes evaluation criteria into atomic binary questions and aggregates the resulting verdicts into interpretable, multi-dimensional scores. Given a task prompt, a meta-prompt generates fine-grained evaluation questions, and an LLM answers them independently for each output, yielding transparent question-level feedback together with calibrated overall scores. This decomposition makes evaluation easier to inspect, easier to diagnose, and directly usable for prompt improvement. Across SummEval, Topical-Chat, and QAGS, BINEVAL matches or outperforms strong baselines including UniEval and G-Eval, with especially strong results on factual consistency ben","title":"Ask, Don't Judge: Binary Questions for Interpretable LLM Evaluation and Self-Improvement","url":"https://arxiv.org/abs/2606.27226","vendor":"arxiv_cs_ai"},"summary":"arXiv:2606.27226v1 Announce Type: new \nAbstract: Evaluating LLM outputs remains a major bottleneck in NLP: human evaluation is expensive and slow, lexical metrics correlate poorly with human judgments on open-ended generation, and holistic LLM judges often produce opaque scores that are hard to debug. We propose BINEVAL, a framework that decomposes evaluation criteria into atomic binary questions and aggregates the resulting verdicts into interpretable, multi-dimensional scores. Given a task prompt, a meta-prompt generates fine-grained evaluation questions, and an LLM answers them independently for each output, yielding transparent question-level feedback together with calibrated overall scores. This decomposition makes evaluation easier to inspect, easier to diagnose, and directly usable for prompt improvement. Across SummEval, Topical-Chat, and QAGS, BINEVAL matches or outperforms strong baselines including UniEval and G-Eval, with especially strong results on factual consistency ben","title":"Ask, Don't Judge: Binary Questions for Interpretable LLM Evaluation and Self-Improvement","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-06-26T04:43:58Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2606.27226"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:ed4fa52247c845c0e10869adcf4c4903a1f345b5c136bac450c00079d56eec0643bb8df14a4d148fedf8e334f07ee4d54d991a6e5fc9dc6e42ed0db5c7311b0a","signer":"crovia.substrate","subject":{"observed_at":"2026-06-26T04:43:58Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2606.27226"},"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":"25afc0319ba7fdb3b9f4330896f515beac8d84c624c2a0478010c489650046fb","leaf_index":251056,"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":"97e16bc2626425b739b1520c8c342573d4148080cf54b9c036aad2861b06252b","side":"right"},{"sibling":"23f097ef9e54efd872bd94900d45bc6cc9aa584e42c631c0d1061ddf6d2f103e","side":"right"},{"sibling":"358d02313c5ef2659b25b5cfe3f4233b4a7c45b2ad70bd9555d54149812c01a2","side":"right"},{"sibling":"170569eaded236021d6c02d463c5c17f4379fcdf13f10e090ee2a599ab4c1fab","side":"right"},{"sibling":"ed68287d1915ab292e39acf04af5a28ed8f162b77ec2d989b76a53b85aa53d20","side":"left"},{"sibling":"78203b2e2864794a122eaedd882440e0ed445673a2d3d6166066180ea87f64dc","side":"left"},{"sibling":"b31fd8919314f43e5528d32d692e1d0c9345f86173f69bd11bcf95d27af3147a","side":"right"},{"sibling":"762a50202e5bb846bfb5afec2f3cc80d9313546598c6c53f53acc51c6325b763","side":"left"},{"sibling":"e276c2896e885a069398e8350a2d9aae49ed0ab34771e352045341312283b40a","side":"right"},{"sibling":"b6709caadc8510310ee2ec0b66d1058fcad31c91c65cc2bad6f46a693d553580","side":"right"},{"sibling":"a72c3b8804a37d1a9d18e02e6fdb048bc8ea6b0746909cd2de10bdbabc793737","side":"left"},{"sibling":"803703dc2c50a646fa77b57c0056e9a5126611ba4bcde0d6013ccd6b2d44bdbf","side":"right"},{"sibling":"e78f244b1b8df6d5e3fdc6dd76b5c27d4e6fe3b93b8cd61355497b63d7e4cfe8","side":"left"},{"sibling":"6167cb552ed6871fbf0afcf3db01d1017af7d472b136fcbe5404d1df09f41cc1","side":"right"},{"sibling":"f29798d8bb6aa9900eab878992d9ff0c53266debd87472f31ab26a6a3fb55880","side":"left"},{"sibling":"a04392fb9f2a3a620840e3b3fecd93d12e6d224e481c162389d8ae64e7194599","side":"left"},{"sibling":"c300cf0154c136afc09b1702a0be98f4ba5b6dc5cf57e8cc714ec1eaf4196eff","side":"left"},{"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":251380,"merkle_root":"e042805d07cd8dc777d49695ad78b8d4ec9721df271ff0245d7706773c30b4a5","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260626T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-06-26T05:37:59Z","sig_algorithm":"ed25519","signature":"c68a6e827804771acd244208495c5e35c6f417307db3c76192f038dedaa5b5f86e019074a3bea353357ff7457924c4f7907832638bb9a4d3d18e7a7f50c6a10b","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_bbb60e3284bec78fc22b973ec11330a58048946871618b5ef01526469c1f31a0"}}