{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4IZJPCFPCUXD5QWLTLTM7HUDQU","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":"00c4edce3e049f35a8602c442784e40282f636cfda72861a67fa9e62729c4346","cross_cats_sorted":["cs.CL","cs.CY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-09T18:16:04Z","title_canon_sha256":"3403e25fb83cb39edf1dfeed139d00286638034c6265d88701cf1ee0ab3eddae"},"schema_version":"1.0","source":{"id":"2606.11337","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.11337","created_at":"2026-06-11T00:08:20Z"},{"alias_kind":"arxiv_version","alias_value":"2606.11337v1","created_at":"2026-06-11T00:08:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11337","created_at":"2026-06-11T00:08:20Z"},{"alias_kind":"pith_short_12","alias_value":"4IZJPCFPCUXD","created_at":"2026-06-11T00:08:20Z"},{"alias_kind":"pith_short_16","alias_value":"4IZJPCFPCUXD5QWL","created_at":"2026-06-11T00:08:20Z"},{"alias_kind":"pith_short_8","alias_value":"4IZJPCFP","created_at":"2026-06-11T00:08:20Z"}],"graph_snapshots":[{"event_id":"sha256:88db76b0bed7319d25cfcf2d80531b266009ebc0ace1d71dd6f933c5f5850e76","target":"graph","created_at":"2026-06-11T00:08:20Z","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/2606.11337/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Scientific AI agents increasingly retrieve evidence, reason across sources, and synthesize conclusions used in consequential decisions. Yet, their ability to do so in high-stakes domains such as health remains unclear. We introduce SciConBench, a large-scale live benchmark of 9.11K questions and expert-written conclusions from systematic reviews to evaluate open-domain scientific conclusion synthesis. The benchmark draws on an expert-validated automated evaluation pipeline that decomposes conclusions into atomic facts and measures correctness and comprehensiveness via factual precision and rec","authors_text":"Abner Fernandes da Silva, Aleksandra Korolova, Enoch Tsai, Haeun Jung, Hayoung Jung, Jos\\'e Reinaldo Corr\\^ea Roveda, Manoel Horta Ribeiro, Pedro Viana Diniz","cross_cats":["cs.CL","cs.CY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-09T18:16:04Z","title":"Can AI Agents Synthesize Scientific Conclusions?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11337","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":"sha256:77e2d118d71eff2b5498acdb5fb3cab8d3a67bf97f051c5730679fb6742c4766","target":"record","created_at":"2026-06-11T00:08:20Z","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":"00c4edce3e049f35a8602c442784e40282f636cfda72861a67fa9e62729c4346","cross_cats_sorted":["cs.CL","cs.CY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-09T18:16:04Z","title_canon_sha256":"3403e25fb83cb39edf1dfeed139d00286638034c6265d88701cf1ee0ab3eddae"},"schema_version":"1.0","source":{"id":"2606.11337","kind":"arxiv","version":1}},"canonical_sha256":"e2329788af152e3ec2cb9ae6cf9e8385039d4c9b3c53cfbbbf12eb2279e0eb0f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e2329788af152e3ec2cb9ae6cf9e8385039d4c9b3c53cfbbbf12eb2279e0eb0f","first_computed_at":"2026-06-11T00:08:20.334988Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-11T00:08:20.334988Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Lo1q4a/fU8RB3fbZyGfmpsaninnaosqhU0qOsDENVx1YrK8VRf1k62/EYTrITOsfu75doUcaGhAQIvlzBDzyBA==","signature_status":"signed_v1","signed_at":"2026-06-11T00:08:20.335709Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.11337","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:77e2d118d71eff2b5498acdb5fb3cab8d3a67bf97f051c5730679fb6742c4766","sha256:88db76b0bed7319d25cfcf2d80531b266009ebc0ace1d71dd6f933c5f5850e76"],"state_sha256":"9c027dd9d9e8528e33ff58046b1e33c40662496e8e63eb891828c45e774ab996"}