{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6HKXBQXUY7FOOOMACQ53MSVMTQ","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":"39632aa4c0b72c9c50847f8a6c10ccebd99df93bf350a95804af6eee5f822c03","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-02-02T23:21:13Z","title_canon_sha256":"dd4645fe223092161ba66ecdfdbbaeb2f4b291e4f40fee94b3fbb572554e4faa"},"schema_version":"1.0","source":{"id":"2602.02905","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.02905","created_at":"2026-07-14T00:18:22Z"},{"alias_kind":"arxiv_version","alias_value":"2602.02905v2","created_at":"2026-07-14T00:18:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.02905","created_at":"2026-07-14T00:18:22Z"},{"alias_kind":"pith_short_12","alias_value":"6HKXBQXUY7FO","created_at":"2026-07-14T00:18:22Z"},{"alias_kind":"pith_short_16","alias_value":"6HKXBQXUY7FOOOMA","created_at":"2026-07-14T00:18:22Z"},{"alias_kind":"pith_short_8","alias_value":"6HKXBQXU","created_at":"2026-07-14T00:18:22Z"}],"graph_snapshots":[{"event_id":"sha256:c5ff143a3e7c0cbb3ccccaa1f3665e8785b8ab05746e26bd4ad56be5db9b87d2","target":"graph","created_at":"2026-07-14T00:18:22Z","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/2602.02905/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Autonomous agents powered by large language models (LLMs) promise to accelerate scientific discovery end-to-end, but rigorously evaluating their capacity for verifiable discovery remains a central challenge. Existing benchmarks face a trade-off: they either heavily rely on LLM-as-judge evaluations of automatically generated research outputs or optimize convenient yet isolated performance metrics that provide coarse proxies for scientific insight. To address this gap, we introduce FIRE-Bench (Full-cycle Insight Rediscovery Evaluation), a benchmark that evaluates agents through the rediscovery o","authors_text":"Claire Cardie, Eric P. Xing, Fan Bai, Jieyuan Liu, Jinyan Su, Kaiser Sun, Kun Zhou, Mark Dredze, Xinle Yu, Zhen Wang, Zhiting Hu, Zhongyan Luo","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-02-02T23:21:13Z","title":"FIRE-Bench: Evaluating AI Agents on the Rediscovery of Scientific Insights"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.02905","kind":"arxiv","version":2},"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:af9510e2a80d5edbe1c8f4ff82e7b4c87b2f0e96b7a31cefcdff2cab6d5bbead","target":"record","created_at":"2026-07-14T00:18:22Z","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":"39632aa4c0b72c9c50847f8a6c10ccebd99df93bf350a95804af6eee5f822c03","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-02-02T23:21:13Z","title_canon_sha256":"dd4645fe223092161ba66ecdfdbbaeb2f4b291e4f40fee94b3fbb572554e4faa"},"schema_version":"1.0","source":{"id":"2602.02905","kind":"arxiv","version":2}},"canonical_sha256":"f1d570c2f4c7cae73980143bb64aac9c237f08c2088d5b89e4b109b6ba739f52","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f1d570c2f4c7cae73980143bb64aac9c237f08c2088d5b89e4b109b6ba739f52","first_computed_at":"2026-07-14T00:18:22.088736Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-14T00:18:22.088736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Dkj0g77347ggN0DR78gZSW2XTeALipEzeypJkmhDJK1rc+zFhz4JOeP8KBAghXIUPtaCd7Xk1EWUGcSTxunSBg==","signature_status":"signed_v1","signed_at":"2026-07-14T00:18:22.090446Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.02905","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:af9510e2a80d5edbe1c8f4ff82e7b4c87b2f0e96b7a31cefcdff2cab6d5bbead","sha256:c5ff143a3e7c0cbb3ccccaa1f3665e8785b8ab05746e26bd4ad56be5db9b87d2"],"state_sha256":"c9c1abc58ab61da74c28af877db310844d076b937fba5436971854efd132ec0a"}