{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:Y6LDLQ7JVWYIA432FTRDSFM476","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":"872a96b3aa02938fc2b655b32a39fb2fb23216e67888c346d7809ce9f9ff2959","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-15T17:56:41Z","title_canon_sha256":"75ce56dd945b4562623bfd6a6f62e05893f17122c1d360cff589aa57a4127791"},"schema_version":"1.0","source":{"id":"2606.17041","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.17041","created_at":"2026-06-19T16:12:21Z"},{"alias_kind":"arxiv_version","alias_value":"2606.17041v3","created_at":"2026-06-19T16:12:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.17041","created_at":"2026-06-19T16:12:21Z"},{"alias_kind":"pith_short_12","alias_value":"Y6LDLQ7JVWYI","created_at":"2026-06-19T16:12:21Z"},{"alias_kind":"pith_short_16","alias_value":"Y6LDLQ7JVWYIA432","created_at":"2026-06-19T16:12:21Z"},{"alias_kind":"pith_short_8","alias_value":"Y6LDLQ7J","created_at":"2026-06-19T16:12:21Z"}],"graph_snapshots":[{"event_id":"sha256:219b0b8b11de92cb5a2d022a762db9e257b178e88a4b8a7d9eb6e5d2ed666141","target":"graph","created_at":"2026-06-19T16:12:21Z","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/2606.17041/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Meta-analysis is a demanding form of evidence synthesis that combines literature retrieval, PI/ECO-guided study selection, and statistical aggregation. Its structured, verifiable workflow makes it an ideal substrate for evaluating systematic scientific reasoning, yet existing benchmarks lack ground truth across the full retrieval-screening-synthesis pipeline. We introduce MetaSyn, a dataset of 442 expert-curated meta-analyses from Nature Portfolio journals. Each entry pairs a research question with PI/ECO criteria, a retrieval corpus of 140k PubMed articles, verified positive studies, hard neg","authors_text":"Anzhe Xie, Qingyao Ai, Weihang Su, Yiqun Liu, Yujia Zhou","cross_cats":["cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-15T17:56:41Z","title":"Benchmarking LLM Agents on Meta-Analysis Articles from Nature Portfolio"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.17041","kind":"arxiv","version":3},"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:ad676395c8bbcfd28b735025a839b9601a31a81a809786020b027c0151e271b0","target":"record","created_at":"2026-06-19T16:12:21Z","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":"872a96b3aa02938fc2b655b32a39fb2fb23216e67888c346d7809ce9f9ff2959","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-15T17:56:41Z","title_canon_sha256":"75ce56dd945b4562623bfd6a6f62e05893f17122c1d360cff589aa57a4127791"},"schema_version":"1.0","source":{"id":"2606.17041","kind":"arxiv","version":3}},"canonical_sha256":"c79635c3e9adb080737a2ce239159cffbe8dec04434fc461ab74f0c9ad9b3f82","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c79635c3e9adb080737a2ce239159cffbe8dec04434fc461ab74f0c9ad9b3f82","first_computed_at":"2026-06-19T16:12:21.878756Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:12:21.878756Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Fboin7FYsAsPsOo9m6C63puwKUySe8tEW6gVeK6jiODdY+A2JIL311dRo+3vM+fuJjIcu6zDFgE/g7Yi91YAAA==","signature_status":"signed_v1","signed_at":"2026-06-19T16:12:21.879097Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.17041","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ad676395c8bbcfd28b735025a839b9601a31a81a809786020b027c0151e271b0","sha256:219b0b8b11de92cb5a2d022a762db9e257b178e88a4b8a7d9eb6e5d2ed666141"],"state_sha256":"35853f8c0f1d90e72489b03cd1ac2e3145f2323b3a77ab70b6a631d07170f0ab"}