{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MH3QB3GRCFNKILJKU275LVHAF5","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":"6761a18b59bf1091b3d68627aba624e0575279e6c2a9c3d3c54e0ad06651bddc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-31T17:58:25Z","title_canon_sha256":"1b311c295b22dda9e0041cf21019f85e0060371a6c4cefbd8405561cec502d57"},"schema_version":"1.0","source":{"id":"2507.23776","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.23776","created_at":"2026-07-05T11:46:30Z"},{"alias_kind":"arxiv_version","alias_value":"2507.23776v1","created_at":"2026-07-05T11:46:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.23776","created_at":"2026-07-05T11:46:30Z"},{"alias_kind":"pith_short_12","alias_value":"MH3QB3GRCFNK","created_at":"2026-07-05T11:46:30Z"},{"alias_kind":"pith_short_16","alias_value":"MH3QB3GRCFNKILJK","created_at":"2026-07-05T11:46:30Z"},{"alias_kind":"pith_short_8","alias_value":"MH3QB3GR","created_at":"2026-07-05T11:46:30Z"}],"graph_snapshots":[{"event_id":"sha256:c64de4c6d645240cc794d8bb2be7535017dfb454299302d959be1db55d9cdb62","target":"graph","created_at":"2026-07-05T11:46:30Z","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/2507.23776/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While question-answering~(QA) benchmark performance is an automatic and scalable method to compare LLMs, it is an indirect method of evaluating their underlying problem-solving capabilities. Therefore, we propose a holistic and generalizable framework based on \\emph{cascaded question disclosure} that provides a more accurate estimate of the models' problem-solving capabilities while maintaining the scalability and automation. This approach collects model responses in a stagewise manner with each stage revealing partial information about the question designed to elicit generalized reasoning in ","authors_text":"Kartik Goyal, Tomohiro Sawada, Yunxiang Yan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-31T17:58:25Z","title":"Cascaded Information Disclosure for Generalized Evaluation of Problem Solving Capabilities"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.23776","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":"sha256:782d7b9e0ac4f41239beb9a40274ca852e6faa824461dba30fc74f7c3c02cd18","target":"record","created_at":"2026-07-05T11:46:30Z","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":"6761a18b59bf1091b3d68627aba624e0575279e6c2a9c3d3c54e0ad06651bddc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-31T17:58:25Z","title_canon_sha256":"1b311c295b22dda9e0041cf21019f85e0060371a6c4cefbd8405561cec502d57"},"schema_version":"1.0","source":{"id":"2507.23776","kind":"arxiv","version":1}},"canonical_sha256":"61f700ecd1115aa42d2aa6bfd5d4e02f5d4a18836e4f56f2281e23440f2cf46a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"61f700ecd1115aa42d2aa6bfd5d4e02f5d4a18836e4f56f2281e23440f2cf46a","first_computed_at":"2026-07-05T11:46:30.743475Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:46:30.743475Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qFT06y5VJ0lJLKbgTCbjgbsFfUcjdqBHfiV8xK4S5uZQRmQTk2W7Z8S42I+ldQSqhG4ZrnOfn4UlrVsaUV8IDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:46:30.743936Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.23776","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:782d7b9e0ac4f41239beb9a40274ca852e6faa824461dba30fc74f7c3c02cd18","sha256:c64de4c6d645240cc794d8bb2be7535017dfb454299302d959be1db55d9cdb62"],"state_sha256":"6576ce9d148fc489bdd82c721c68ad333d2a02e10d915e9eb89df23b5a868436"}