{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:74W3EDCGZOZNH7TM6PIDUXXQFJ","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":"2bc8f9a84ee86770cc9049847372546bc563549a71fa6fadf56418f3559a5efb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-25T03:29:53Z","title_canon_sha256":"e4ec158f2588e9caecb87c4ac3c007e39a21a4eedd1fe88348232b4d26be3235"},"schema_version":"1.0","source":{"id":"2502.17807","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.17807","created_at":"2026-07-05T10:19:44Z"},{"alias_kind":"arxiv_version","alias_value":"2502.17807v1","created_at":"2026-07-05T10:19:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.17807","created_at":"2026-07-05T10:19:44Z"},{"alias_kind":"pith_short_12","alias_value":"74W3EDCGZOZN","created_at":"2026-07-05T10:19:44Z"},{"alias_kind":"pith_short_16","alias_value":"74W3EDCGZOZNH7TM","created_at":"2026-07-05T10:19:44Z"},{"alias_kind":"pith_short_8","alias_value":"74W3EDCG","created_at":"2026-07-05T10:19:44Z"}],"graph_snapshots":[{"event_id":"sha256:adbf8d38ccb2b1d44ac85210ad24bd15c9a349f620ef58c9b873cf7744c6c603","target":"graph","created_at":"2026-07-05T10:19:44Z","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/2502.17807/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present DocPuzzle, a rigorously constructed benchmark for evaluating long-context reasoning capabilities in large language models (LLMs). This benchmark comprises 100 expert-level QA problems requiring multi-step reasoning over long real-world documents. To ensure the task quality and complexity, we implement a human-AI collaborative annotation-validation pipeline. DocPuzzle introduces an innovative evaluation framework that mitigates guessing bias through checklist-guided process analysis, establishing new standards for assessing reasoning capacities in LLMs. Our evaluation results show th","authors_text":"Chuqiao Kuang, Jihao Wu, Lifeng Shang, Tianyi Zhuang, Xiaoguang Li, Yasheng Wang, Yihua Teng","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-25T03:29:53Z","title":"DocPuzzle: A Process-Aware Benchmark for Evaluating Realistic Long-Context Reasoning Capabilities"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.17807","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:a0f6303338ca639b5fd8cc22d717e12cbc370bd49da904272d820eb2cb1d5053","target":"record","created_at":"2026-07-05T10:19:44Z","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":"2bc8f9a84ee86770cc9049847372546bc563549a71fa6fadf56418f3559a5efb","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-25T03:29:53Z","title_canon_sha256":"e4ec158f2588e9caecb87c4ac3c007e39a21a4eedd1fe88348232b4d26be3235"},"schema_version":"1.0","source":{"id":"2502.17807","kind":"arxiv","version":1}},"canonical_sha256":"ff2db20c46cbb2d3fe6cf3d03a5ef02a5429c9c46abc3fb114c3800feabe6c53","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ff2db20c46cbb2d3fe6cf3d03a5ef02a5429c9c46abc3fb114c3800feabe6c53","first_computed_at":"2026-07-05T10:19:44.479442Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:19:44.479442Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2Qr54fb10c8x92EInE804oj3bIYQqeg1tsRnQcny+e8PbCJATSX3PigUUYfwUo+Eq4PYTR2ZadNOYopYEVuSAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:19:44.479863Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.17807","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a0f6303338ca639b5fd8cc22d717e12cbc370bd49da904272d820eb2cb1d5053","sha256:adbf8d38ccb2b1d44ac85210ad24bd15c9a349f620ef58c9b873cf7744c6c603"],"state_sha256":"73600f110808a67acc2a2c72d9d14b1ee8c2fc51aff0a0b6eafdfc410cf15142"}