{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:UOE45U7ZUAZGFXGTHBN2YBLN7V","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":"89ca8480d631737d8ff93e78498117249fd22ec534b8b9ecad612c1a16bdc524","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DL","submitted_at":"2026-06-11T06:49:52Z","title_canon_sha256":"40821d5aab9077f437e61799327ed5e4997f3e27998df57574d7988aed3376f1"},"schema_version":"1.0","source":{"id":"2606.27383","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.27383","created_at":"2026-06-29T00:14:04Z"},{"alias_kind":"arxiv_version","alias_value":"2606.27383v1","created_at":"2026-06-29T00:14:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.27383","created_at":"2026-06-29T00:14:04Z"},{"alias_kind":"pith_short_12","alias_value":"UOE45U7ZUAZG","created_at":"2026-06-29T00:14:04Z"},{"alias_kind":"pith_short_16","alias_value":"UOE45U7ZUAZGFXGT","created_at":"2026-06-29T00:14:04Z"},{"alias_kind":"pith_short_8","alias_value":"UOE45U7Z","created_at":"2026-06-29T00:14:04Z"}],"graph_snapshots":[{"event_id":"sha256:96c90a7ee0bb8cd03d8dcedd99000d180d83754140e69a1a609f31e7220fc409","target":"graph","created_at":"2026-06-29T00:14:04Z","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/2606.27383/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) are increasingly used as research assistants, yet it remains unclear whether they can calibrate research takeaways to the strength and scope of the supporting evidence. We study evidence-calibrated scientific briefing: given a bounded package of related papers, a system should generate package-level takeaways with evidence strength, scope boundaries, and missing-evidence caveats. We contribute a verified pilot benchmark of 16 heterogeneous scientific evidence packages and 96 human-verified takeaways, and we use CalBrief, an auditable role/gap/strength framework, as","authors_text":"Yongqi Kang, Yong Zhao, Yu Fu","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DL","submitted_at":"2026-06-11T06:49:52Z","title":"CalBrief: A Pilot Diagnostic Benchmark for Evidence-Calibrated Scientific Briefing with Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.27383","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:d830cbe99678ff6a45710155f7afd6b4599d3bc68e644a75b75a404f5ed3cdf0","target":"record","created_at":"2026-06-29T00:14:04Z","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":"89ca8480d631737d8ff93e78498117249fd22ec534b8b9ecad612c1a16bdc524","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DL","submitted_at":"2026-06-11T06:49:52Z","title_canon_sha256":"40821d5aab9077f437e61799327ed5e4997f3e27998df57574d7988aed3376f1"},"schema_version":"1.0","source":{"id":"2606.27383","kind":"arxiv","version":1}},"canonical_sha256":"a389ced3f9a03262dcd3385bac056dfd51fada3cfcbfe78d14bfe3e0f6fe10e9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a389ced3f9a03262dcd3385bac056dfd51fada3cfcbfe78d14bfe3e0f6fe10e9","first_computed_at":"2026-06-29T00:14:04.418959Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-29T00:14:04.418959Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"915KqNk4Guf/b0G2KAhPkFGlVMBwt0L2kkaehDNOG+n/W9pNhEcO1aVqIlbb35fbztP6wmMQakZL1p8WOHZGBQ==","signature_status":"signed_v1","signed_at":"2026-06-29T00:14:04.419477Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.27383","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d830cbe99678ff6a45710155f7afd6b4599d3bc68e644a75b75a404f5ed3cdf0","sha256:96c90a7ee0bb8cd03d8dcedd99000d180d83754140e69a1a609f31e7220fc409"],"state_sha256":"ac0f8868f0c5ebb5f7acaa61b9d69c4f8057b427e2d42bc87000993e39e7ea16"}