{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:RXRJ7RYU5RPIN77N53WXC3C6DO","short_pith_number":"pith:RXRJ7RYU","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"},"canonical_sha256":"8de29fc714ec5e86ffedeeed716c5e1b9f7254140237fc42f5b6b8e6664e4996","source":{"kind":"arxiv","id":"2606.27226","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.27226","created_at":"2026-06-26T01:16:15Z"},{"alias_kind":"arxiv_version","alias_value":"2606.27226v1","created_at":"2026-06-26T01:16:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.27226","created_at":"2026-06-26T01:16:15Z"},{"alias_kind":"pith_short_12","alias_value":"RXRJ7RYU5RPI","created_at":"2026-06-26T01:16:15Z"},{"alias_kind":"pith_short_16","alias_value":"RXRJ7RYU5RPIN77N","created_at":"2026-06-26T01:16:15Z"},{"alias_kind":"pith_short_8","alias_value":"RXRJ7RYU","created_at":"2026-06-26T01:16:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:RXRJ7RYU5RPIN77N53WXC3C6DO","target":"record","payload":{"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"},"canonical_sha256":"8de29fc714ec5e86ffedeeed716c5e1b9f7254140237fc42f5b6b8e6664e4996","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"},"source_kind":"arxiv","source_id":"2606.27226","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-26T01:16:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S7aV9pWmVnVbwFG8BAgJgy3O4yDVWyr/ir1EMfvaZHOtCa9GcYuNu77GtUXVGzts1fAKMc3DDaqSFxWc3xQ3Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T19:28:13.080075Z"},"content_sha256":"861020b21c7d6b17d9f1af4537b540fe4d32b98f5f4cd907cea50f3f27f0e8ef","schema_version":"1.0","event_id":"sha256:861020b21c7d6b17d9f1af4537b540fe4d32b98f5f4cd907cea50f3f27f0e8ef"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:RXRJ7RYU5RPIN77N53WXC3C6DO","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-26T01:16:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8r7IJ/6f7g949qXY/XLtyNImCB1KmM3L/uf6/Kn3pgCvAcYWJekceE6zMziUykMtuQsfOmFAdgjwriHDlzBjCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T19:28:13.080471Z"},"content_sha256":"79b8644add2bd3a35debc19f26dfea24ce09fdd8a4149739e5e9892af262b98a","schema_version":"1.0","event_id":"sha256:79b8644add2bd3a35debc19f26dfea24ce09fdd8a4149739e5e9892af262b98a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RXRJ7RYU5RPIN77N53WXC3C6DO/bundle.json","state_url":"https://pith.science/pith/RXRJ7RYU5RPIN77N53WXC3C6DO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RXRJ7RYU5RPIN77N53WXC3C6DO/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-29T19:28:13Z","links":{"resolver":"https://pith.science/pith/RXRJ7RYU5RPIN77N53WXC3C6DO","bundle":"https://pith.science/pith/RXRJ7RYU5RPIN77N53WXC3C6DO/bundle.json","state":"https://pith.science/pith/RXRJ7RYU5RPIN77N53WXC3C6DO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RXRJ7RYU5RPIN77N53WXC3C6DO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:RXRJ7RYU5RPIN77N53WXC3C6DO","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"6fb1544a6a6c3a23ea3eeb81cbc89ce4d8870adcbe499db55b4c72ea02b1d8fc","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-25T16:14:50Z","title_canon_sha256":"14661cbfb9a779c3ce19be32f014ae8028ac0af43448c3ea9e1347396a88745d"},"schema_version":"1.0","source":{"id":"2606.27226","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.27226","created_at":"2026-06-26T01:16:15Z"},{"alias_kind":"arxiv_version","alias_value":"2606.27226v1","created_at":"2026-06-26T01:16:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.27226","created_at":"2026-06-26T01:16:15Z"},{"alias_kind":"pith_short_12","alias_value":"RXRJ7RYU5RPI","created_at":"2026-06-26T01:16:15Z"},{"alias_kind":"pith_short_16","alias_value":"RXRJ7RYU5RPIN77N","created_at":"2026-06-26T01:16:15Z"},{"alias_kind":"pith_short_8","alias_value":"RXRJ7RYU","created_at":"2026-06-26T01:16:15Z"}],"graph_snapshots":[{"event_id":"sha256:79b8644add2bd3a35debc19f26dfea24ce09fdd8a4149739e5e9892af262b98a","target":"graph","created_at":"2026-06-26T01:16:15Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2606.27226/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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-","authors_text":"Chenyang Zhu, Kushal Chawla, Pengshan Cai, Sambit Sahu, Sangwoo Cho, Shi-Xiong Zhang, Zefang Liu","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-25T16:14:50Z","title":"Ask, Don't Judge: Binary Questions for Interpretable LLM Evaluation and Self-Improvement"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.27226","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:861020b21c7d6b17d9f1af4537b540fe4d32b98f5f4cd907cea50f3f27f0e8ef","target":"record","created_at":"2026-06-26T01:16:15Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"6fb1544a6a6c3a23ea3eeb81cbc89ce4d8870adcbe499db55b4c72ea02b1d8fc","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-25T16:14:50Z","title_canon_sha256":"14661cbfb9a779c3ce19be32f014ae8028ac0af43448c3ea9e1347396a88745d"},"schema_version":"1.0","source":{"id":"2606.27226","kind":"arxiv","version":1}},"canonical_sha256":"8de29fc714ec5e86ffedeeed716c5e1b9f7254140237fc42f5b6b8e6664e4996","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8de29fc714ec5e86ffedeeed716c5e1b9f7254140237fc42f5b6b8e6664e4996","first_computed_at":"2026-06-26T01:16:15.673524Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-26T01:16:15.673524Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"c3dCtHC3XD6lV2CMn6t0hjwCP0M/cw8TmyUZqPAw79q0yFiVHlmDXXC0CXRpgxGHqGopkiwinQPZVbZwhpZpDA==","signature_status":"signed_v1","signed_at":"2026-06-26T01:16:15.673917Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.27226","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:861020b21c7d6b17d9f1af4537b540fe4d32b98f5f4cd907cea50f3f27f0e8ef","sha256:79b8644add2bd3a35debc19f26dfea24ce09fdd8a4149739e5e9892af262b98a"],"state_sha256":"c749e97cf849a676cd5b61859dc2ed970195a06bd92438bc8dd0c147976a9ed4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LswNqee88Chj5nFMg08KUEytOg0MG93h2B7vejoxx7qzLSgOhwcp3Xd0+rt6RuVvATbhogyFLeyBSvRa1qPnCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-29T19:28:13.082542Z","bundle_sha256":"51026e0b322629bd94476f92beb8dd6ecffbb26c700a1394b4e65c915093eb32"}}