{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6HKXBQXUY7FOOOMACQ53MSVMTQ","short_pith_number":"pith:6HKXBQXU","schema_version":"1.0","canonical_sha256":"f1d570c2f4c7cae73980143bb64aac9c237f08c2088d5b89e4b109b6ba739f52","source":{"kind":"arxiv","id":"2602.02905","version":2},"attestation_state":"computed","paper":{"title":"FIRE-Bench: Evaluating AI Agents on the Rediscovery of Scientific Insights","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","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","submitted_at":"2026-02-02T23:21:13Z","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"},"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":"2602.02905","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-02-02T23:21:13Z","cross_cats_sorted":[],"title_canon_sha256":"dd4645fe223092161ba66ecdfdbbaeb2f4b291e4f40fee94b3fbb572554e4faa","abstract_canon_sha256":"39632aa4c0b72c9c50847f8a6c10ccebd99df93bf350a95804af6eee5f822c03"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T00:18:22.090446Z","signature_b64":"Dkj0g77347ggN0DR78gZSW2XTeALipEzeypJkmhDJK1rc+zFhz4JOeP8KBAghXIUPtaCd7Xk1EWUGcSTxunSBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1d570c2f4c7cae73980143bb64aac9c237f08c2088d5b89e4b109b6ba739f52","last_reissued_at":"2026-07-14T00:18:22.088736Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T00:18:22.088736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FIRE-Bench: Evaluating AI Agents on the Rediscovery of Scientific Insights","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","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","submitted_at":"2026-02-02T23:21:13Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.02905","kind":"arxiv","version":2},"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/2602.02905/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":"2602.02905","created_at":"2026-07-14T00:18:22.089843+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.02905v2","created_at":"2026-07-14T00:18:22.089843+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.02905","created_at":"2026-07-14T00:18:22.089843+00:00"},{"alias_kind":"pith_short_12","alias_value":"6HKXBQXUY7FO","created_at":"2026-07-14T00:18:22.089843+00:00"},{"alias_kind":"pith_short_16","alias_value":"6HKXBQXUY7FOOOMA","created_at":"2026-07-14T00:18:22.089843+00:00"},{"alias_kind":"pith_short_8","alias_value":"6HKXBQXU","created_at":"2026-07-14T00:18:22.089843+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":8,"sample":[{"citing_arxiv_id":"2606.24530","citing_title":"NatureBench: Can Coding Agents Match the Published SOTA of Nature-Family Papers?","ref_index":84,"is_internal_anchor":true},{"citing_arxiv_id":"2606.22731","citing_title":"Closed-loop Auto Research for Molecular Property Prediction: Discovering and Certifying Generalizable Improvements","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08678","citing_title":"MLS-Bench: A Holistic and Rigorous Assessment of AI Systems on Building Better AI","ref_index":107,"is_internal_anchor":true},{"citing_arxiv_id":"2605.26340","citing_title":"ScientistOne: Towards Human-Level Autonomous Research via Chain-of-Evidence","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2606.18237","citing_title":"ReproRepo: Scaling Reproducibility Audits with GitHub Repository Issues","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2605.23204","citing_title":"AutoResearch AI: Towards AI-Powered Research Automation for Scientific Discovery","ref_index":96,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08678","citing_title":"MLS-Bench: A Holistic and Rigorous Assessment of AI Systems on Building Better AI","ref_index":105,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07335","citing_title":"CellScientist: Dual-Space Hierarchical Orchestration for Closed-Loop Refinement of Virtual Cell Models","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6HKXBQXUY7FOOOMACQ53MSVMTQ","json":"https://pith.science/pith/6HKXBQXUY7FOOOMACQ53MSVMTQ.json","graph_json":"https://pith.science/api/pith-number/6HKXBQXUY7FOOOMACQ53MSVMTQ/graph.json","events_json":"https://pith.science/api/pith-number/6HKXBQXUY7FOOOMACQ53MSVMTQ/events.json","paper":"https://pith.science/paper/6HKXBQXU"},"agent_actions":{"view_html":"https://pith.science/pith/6HKXBQXUY7FOOOMACQ53MSVMTQ","download_json":"https://pith.science/pith/6HKXBQXUY7FOOOMACQ53MSVMTQ.json","view_paper":"https://pith.science/paper/6HKXBQXU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.02905&json=true","fetch_graph":"https://pith.science/api/pith-number/6HKXBQXUY7FOOOMACQ53MSVMTQ/graph.json","fetch_events":"https://pith.science/api/pith-number/6HKXBQXUY7FOOOMACQ53MSVMTQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6HKXBQXUY7FOOOMACQ53MSVMTQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6HKXBQXUY7FOOOMACQ53MSVMTQ/action/storage_attestation","attest_author":"https://pith.science/pith/6HKXBQXUY7FOOOMACQ53MSVMTQ/action/author_attestation","sign_citation":"https://pith.science/pith/6HKXBQXUY7FOOOMACQ53MSVMTQ/action/citation_signature","submit_replication":"https://pith.science/pith/6HKXBQXUY7FOOOMACQ53MSVMTQ/action/replication_record"}},"created_at":"2026-07-14T00:18:22.089843+00:00","updated_at":"2026-07-14T00:18:22.089843+00:00"}