{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Y6LDLQ7JVWYIA432FTRDSFM476","short_pith_number":"pith:Y6LDLQ7J","schema_version":"1.0","canonical_sha256":"c79635c3e9adb080737a2ce239159cffbe8dec04434fc461ab74f0c9ad9b3f82","source":{"kind":"arxiv","id":"2606.17041","version":3},"attestation_state":"computed","paper":{"title":"Benchmarking LLM Agents on Meta-Analysis Articles from Nature Portfolio","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Anzhe Xie, Qingyao Ai, Weihang Su, Yiqun Liu, Yujia Zhou","submitted_at":"2026-06-15T17:56:41Z","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"},"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":"2606.17041","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-15T17:56:41Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"75ce56dd945b4562623bfd6a6f62e05893f17122c1d360cff589aa57a4127791","abstract_canon_sha256":"872a96b3aa02938fc2b655b32a39fb2fb23216e67888c346d7809ce9f9ff2959"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:12:21.879097Z","signature_b64":"Fboin7FYsAsPsOo9m6C63puwKUySe8tEW6gVeK6jiODdY+A2JIL311dRo+3vM+fuJjIcu6zDFgE/g7Yi91YAAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c79635c3e9adb080737a2ce239159cffbe8dec04434fc461ab74f0c9ad9b3f82","last_reissued_at":"2026-06-19T16:12:21.878756Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:12:21.878756Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmarking LLM Agents on Meta-Analysis Articles from Nature Portfolio","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Anzhe Xie, Qingyao Ai, Weihang Su, Yiqun Liu, Yujia Zhou","submitted_at":"2026-06-15T17:56:41Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.17041","kind":"arxiv","version":3},"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/2606.17041/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":"2606.17041","created_at":"2026-06-19T16:12:21.878813+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.17041v3","created_at":"2026-06-19T16:12:21.878813+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.17041","created_at":"2026-06-19T16:12:21.878813+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y6LDLQ7JVWYI","created_at":"2026-06-19T16:12:21.878813+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y6LDLQ7JVWYIA432","created_at":"2026-06-19T16:12:21.878813+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y6LDLQ7J","created_at":"2026-06-19T16:12:21.878813+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/Y6LDLQ7JVWYIA432FTRDSFM476","json":"https://pith.science/pith/Y6LDLQ7JVWYIA432FTRDSFM476.json","graph_json":"https://pith.science/api/pith-number/Y6LDLQ7JVWYIA432FTRDSFM476/graph.json","events_json":"https://pith.science/api/pith-number/Y6LDLQ7JVWYIA432FTRDSFM476/events.json","paper":"https://pith.science/paper/Y6LDLQ7J"},"agent_actions":{"view_html":"https://pith.science/pith/Y6LDLQ7JVWYIA432FTRDSFM476","download_json":"https://pith.science/pith/Y6LDLQ7JVWYIA432FTRDSFM476.json","view_paper":"https://pith.science/paper/Y6LDLQ7J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.17041&json=true","fetch_graph":"https://pith.science/api/pith-number/Y6LDLQ7JVWYIA432FTRDSFM476/graph.json","fetch_events":"https://pith.science/api/pith-number/Y6LDLQ7JVWYIA432FTRDSFM476/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y6LDLQ7JVWYIA432FTRDSFM476/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y6LDLQ7JVWYIA432FTRDSFM476/action/storage_attestation","attest_author":"https://pith.science/pith/Y6LDLQ7JVWYIA432FTRDSFM476/action/author_attestation","sign_citation":"https://pith.science/pith/Y6LDLQ7JVWYIA432FTRDSFM476/action/citation_signature","submit_replication":"https://pith.science/pith/Y6LDLQ7JVWYIA432FTRDSFM476/action/replication_record"}},"created_at":"2026-06-19T16:12:21.878813+00:00","updated_at":"2026-06-19T16:12:21.878813+00:00"}