{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4IZJPCFPCUXD5QWLTLTM7HUDQU","short_pith_number":"pith:4IZJPCFP","schema_version":"1.0","canonical_sha256":"e2329788af152e3ec2cb9ae6cf9e8385039d4c9b3c53cfbbbf12eb2279e0eb0f","source":{"kind":"arxiv","id":"2606.11337","version":1},"attestation_state":"computed","paper":{"title":"Can AI Agents Synthesize Scientific Conclusions?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CY"],"primary_cat":"cs.AI","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","submitted_at":"2026-06-09T18:16:04Z","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"},"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":"2606.11337","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-09T18:16:04Z","cross_cats_sorted":["cs.CL","cs.CY"],"title_canon_sha256":"3403e25fb83cb39edf1dfeed139d00286638034c6265d88701cf1ee0ab3eddae","abstract_canon_sha256":"00c4edce3e049f35a8602c442784e40282f636cfda72861a67fa9e62729c4346"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T00:08:20.335709Z","signature_b64":"Lo1q4a/fU8RB3fbZyGfmpsaninnaosqhU0qOsDENVx1YrK8VRf1k62/EYTrITOsfu75doUcaGhAQIvlzBDzyBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e2329788af152e3ec2cb9ae6cf9e8385039d4c9b3c53cfbbbf12eb2279e0eb0f","last_reissued_at":"2026-06-11T00:08:20.334988Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T00:08:20.334988Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can AI Agents Synthesize Scientific Conclusions?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.CY"],"primary_cat":"cs.AI","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","submitted_at":"2026-06-09T18:16:04Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.11337","kind":"arxiv","version":1},"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/2606.11337/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":"2606.11337","created_at":"2026-06-11T00:08:20.335095+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.11337v1","created_at":"2026-06-11T00:08:20.335095+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.11337","created_at":"2026-06-11T00:08:20.335095+00:00"},{"alias_kind":"pith_short_12","alias_value":"4IZJPCFPCUXD","created_at":"2026-06-11T00:08:20.335095+00:00"},{"alias_kind":"pith_short_16","alias_value":"4IZJPCFPCUXD5QWL","created_at":"2026-06-11T00:08:20.335095+00:00"},{"alias_kind":"pith_short_8","alias_value":"4IZJPCFP","created_at":"2026-06-11T00:08:20.335095+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/4IZJPCFPCUXD5QWLTLTM7HUDQU","json":"https://pith.science/pith/4IZJPCFPCUXD5QWLTLTM7HUDQU.json","graph_json":"https://pith.science/api/pith-number/4IZJPCFPCUXD5QWLTLTM7HUDQU/graph.json","events_json":"https://pith.science/api/pith-number/4IZJPCFPCUXD5QWLTLTM7HUDQU/events.json","paper":"https://pith.science/paper/4IZJPCFP"},"agent_actions":{"view_html":"https://pith.science/pith/4IZJPCFPCUXD5QWLTLTM7HUDQU","download_json":"https://pith.science/pith/4IZJPCFPCUXD5QWLTLTM7HUDQU.json","view_paper":"https://pith.science/paper/4IZJPCFP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.11337&json=true","fetch_graph":"https://pith.science/api/pith-number/4IZJPCFPCUXD5QWLTLTM7HUDQU/graph.json","fetch_events":"https://pith.science/api/pith-number/4IZJPCFPCUXD5QWLTLTM7HUDQU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4IZJPCFPCUXD5QWLTLTM7HUDQU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4IZJPCFPCUXD5QWLTLTM7HUDQU/action/storage_attestation","attest_author":"https://pith.science/pith/4IZJPCFPCUXD5QWLTLTM7HUDQU/action/author_attestation","sign_citation":"https://pith.science/pith/4IZJPCFPCUXD5QWLTLTM7HUDQU/action/citation_signature","submit_replication":"https://pith.science/pith/4IZJPCFPCUXD5QWLTLTM7HUDQU/action/replication_record"}},"created_at":"2026-06-11T00:08:20.335095+00:00","updated_at":"2026-06-11T00:08:20.335095+00:00"}