{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RXRJ7RYU5RPIN77N53WXC3C6DO","short_pith_number":"pith:RXRJ7RYU","schema_version":"1.0","canonical_sha256":"8de29fc714ec5e86ffedeeed716c5e1b9f7254140237fc42f5b6b8e6664e4996","source":{"kind":"arxiv","id":"2606.27226","version":1},"attestation_state":"computed","paper":{"title":"Ask, Don't Judge: Binary Questions for Interpretable LLM Evaluation and Self-Improvement","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Chenyang Zhu, Kushal Chawla, Pengshan Cai, Sambit Sahu, Sangwoo Cho, Shi-Xiong Zhang, Zefang Liu","submitted_at":"2026-06-25T16:14:50Z","abstract_excerpt":"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-"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.27226","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-25T16:14:50Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"14661cbfb9a779c3ce19be32f014ae8028ac0af43448c3ea9e1347396a88745d","abstract_canon_sha256":"6fb1544a6a6c3a23ea3eeb81cbc89ce4d8870adcbe499db55b4c72ea02b1d8fc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-26T01:16:15.673917Z","signature_b64":"c3dCtHC3XD6lV2CMn6t0hjwCP0M/cw8TmyUZqPAw79q0yFiVHlmDXXC0CXRpgxGHqGopkiwinQPZVbZwhpZpDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8de29fc714ec5e86ffedeeed716c5e1b9f7254140237fc42f5b6b8e6664e4996","last_reissued_at":"2026-06-26T01:16:15.673524Z","signature_status":"signed_v1","first_computed_at":"2026-06-26T01:16:15.673524Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ask, Don't Judge: Binary Questions for Interpretable LLM Evaluation and Self-Improvement","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Chenyang Zhu, Kushal Chawla, Pengshan Cai, Sambit Sahu, Sangwoo Cho, Shi-Xiong Zhang, Zefang Liu","submitted_at":"2026-06-25T16:14:50Z","abstract_excerpt":"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-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.27226","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.27226/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.27226","created_at":"2026-06-26T01:16:15.673580+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.27226v1","created_at":"2026-06-26T01:16:15.673580+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.27226","created_at":"2026-06-26T01:16:15.673580+00:00"},{"alias_kind":"pith_short_12","alias_value":"RXRJ7RYU5RPI","created_at":"2026-06-26T01:16:15.673580+00:00"},{"alias_kind":"pith_short_16","alias_value":"RXRJ7RYU5RPIN77N","created_at":"2026-06-26T01:16:15.673580+00:00"},{"alias_kind":"pith_short_8","alias_value":"RXRJ7RYU","created_at":"2026-06-26T01:16:15.673580+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RXRJ7RYU5RPIN77N53WXC3C6DO","json":"https://pith.science/pith/RXRJ7RYU5RPIN77N53WXC3C6DO.json","graph_json":"https://pith.science/api/pith-number/RXRJ7RYU5RPIN77N53WXC3C6DO/graph.json","events_json":"https://pith.science/api/pith-number/RXRJ7RYU5RPIN77N53WXC3C6DO/events.json","paper":"https://pith.science/paper/RXRJ7RYU"},"agent_actions":{"view_html":"https://pith.science/pith/RXRJ7RYU5RPIN77N53WXC3C6DO","download_json":"https://pith.science/pith/RXRJ7RYU5RPIN77N53WXC3C6DO.json","view_paper":"https://pith.science/paper/RXRJ7RYU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.27226&json=true","fetch_graph":"https://pith.science/api/pith-number/RXRJ7RYU5RPIN77N53WXC3C6DO/graph.json","fetch_events":"https://pith.science/api/pith-number/RXRJ7RYU5RPIN77N53WXC3C6DO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RXRJ7RYU5RPIN77N53WXC3C6DO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RXRJ7RYU5RPIN77N53WXC3C6DO/action/storage_attestation","attest_author":"https://pith.science/pith/RXRJ7RYU5RPIN77N53WXC3C6DO/action/author_attestation","sign_citation":"https://pith.science/pith/RXRJ7RYU5RPIN77N53WXC3C6DO/action/citation_signature","submit_replication":"https://pith.science/pith/RXRJ7RYU5RPIN77N53WXC3C6DO/action/replication_record"}},"created_at":"2026-06-26T01:16:15.673580+00:00","updated_at":"2026-06-26T01:16:15.673580+00:00"}