{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:474OF7OJGDEYBUPH6Z7HJHZDUW","short_pith_number":"pith:474OF7OJ","schema_version":"1.0","canonical_sha256":"e7f8e2fdc930c980d1e7f67e749f23a5a594411b314f889839663588cb8554cf","source":{"kind":"arxiv","id":"2605.01489","version":2},"attestation_state":"computed","paper":{"title":"SciResearcher: Scaling Deep Research Agents for Frontier Scientific Reasoning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"Automated synthesis of conceptual and computational tasks trains an 8B model to set new records on frontier biology and chemistry reasoning benchmarks.","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Kelvin Kiu Wai Tam, Newt Nguyen Kim Hue Nam, Rui Wang, Tianqing Fang, Tianshi Zheng, Wei Fan, Xiyun Li, Yangqiu Song","submitted_at":"2026-05-02T15:26:45Z","abstract_excerpt":"Frontier scientific reasoning is rapidly emerging as a key foundation for advancing AI agents in automated scientific discovery. Deep research agents offer a promising approach to this challenge. These models develop robust problem-solving capabilities through post-training on information-seeking tasks, which are typically curated via knowledge graph construction or iterative web browsing. However, these strategies face inherent limitations in frontier science, where domain-specific knowledge is scattered across sparse and heterogeneous academic sources, and problem solving requires sophistica"},"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":"2605.01489","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-02T15:26:45Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"7ceb00cfd966388e770212fbb394a4642b787e096360daca5bfea7ab18ec741d","abstract_canon_sha256":"3b47ba40dd0e0666a765efc80157afb6b97d519cfd9d13d598ae51c9eec8202c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:05:55.656005Z","signature_b64":"nDBUmB6rFU2hwbgylwflrH/kgCcO/2q0cbpulbC/yVb9QBP5iceqqVC0dRXfhB8J99+IpOjJY34nfm37LLukAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7f8e2fdc930c980d1e7f67e749f23a5a594411b314f889839663588cb8554cf","last_reissued_at":"2026-05-27T01:05:55.655135Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:05:55.655135Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SciResearcher: Scaling Deep Research Agents for Frontier Scientific Reasoning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"Automated synthesis of conceptual and computational tasks trains an 8B model to set new records on frontier biology and chemistry reasoning benchmarks.","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Kelvin Kiu Wai Tam, Newt Nguyen Kim Hue Nam, Rui Wang, Tianqing Fang, Tianshi Zheng, Wei Fan, Xiyun Li, Yangqiu Song","submitted_at":"2026-05-02T15:26:45Z","abstract_excerpt":"Frontier scientific reasoning is rapidly emerging as a key foundation for advancing AI agents in automated scientific discovery. Deep research agents offer a promising approach to this challenge. These models develop robust problem-solving capabilities through post-training on information-seeking tasks, which are typically curated via knowledge graph construction or iterative web browsing. However, these strategies face inherent limitations in frontier science, where domain-specific knowledge is scattered across sparse and heterogeneous academic sources, and problem solving requires sophistica"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"SciResearcher-8B achieves 19.46% on the HLE-Bio/Chem-Gold benchmark, establishing a new state of the art at its parameter scale and surpassing several larger proprietary agents. It further achieves 13-15% absolute gains on SuperGPQA-Hard-Biology and TRQA-Literature benchmarks.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That tasks synthesized by the agentic framework accurately reflect the computational and reasoning demands of actual frontier scientific problems rather than simplified or proxy versions.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"SciResearcher automates creation of diverse scientific reasoning tasks from academic evidence to train an 8B model that sets new SOTA at 19.46% on HLE-Bio/Chem-Gold and gains 13-15% on SuperGPQA-Hard-Biology and TRQA-Literature.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Automated synthesis of conceptual and computational tasks trains an 8B model to set new records on frontier biology and chemistry reasoning benchmarks.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"9a738753c9f2398ed340feb06f96acd02965d24f57e23cab512eaa68a7072ac8"},"source":{"id":"2605.01489","kind":"arxiv","version":2},"verdict":{"id":"b0632074-89ac-46f4-82d8-5c9660c72ff8","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-09T14:14:38.432631Z","strongest_claim":"SciResearcher-8B achieves 19.46% on the HLE-Bio/Chem-Gold benchmark, establishing a new state of the art at its parameter scale and surpassing several larger proprietary agents. It further achieves 13-15% absolute gains on SuperGPQA-Hard-Biology and TRQA-Literature benchmarks.","one_line_summary":"SciResearcher automates creation of diverse scientific reasoning tasks from academic evidence to train an 8B model that sets new SOTA at 19.46% on HLE-Bio/Chem-Gold and gains 13-15% on SuperGPQA-Hard-Biology and TRQA-Literature.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That tasks synthesized by the agentic framework accurately reflect the computational and reasoning demands of actual frontier scientific problems rather than simplified or proxy versions.","pith_extraction_headline":"Automated synthesis of conceptual and computational tasks trains an 8B model to set new records on frontier biology and chemistry reasoning benchmarks."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.01489/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-20T17:41:04.058433Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T17:13:33.807168Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"68abf098f1144e9428abf2bf1bf488b5638eb76e9dda3d6b9a6fa19ddb4d447e"},"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":"2605.01489","created_at":"2026-05-27T01:05:55.655274+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.01489v2","created_at":"2026-05-27T01:05:55.655274+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.01489","created_at":"2026-05-27T01:05:55.655274+00:00"},{"alias_kind":"pith_short_12","alias_value":"474OF7OJGDEY","created_at":"2026-05-27T01:05:55.655274+00:00"},{"alias_kind":"pith_short_16","alias_value":"474OF7OJGDEYBUPH","created_at":"2026-05-27T01:05:55.655274+00:00"},{"alias_kind":"pith_short_8","alias_value":"474OF7OJ","created_at":"2026-05-27T01:05:55.655274+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/474OF7OJGDEYBUPH6Z7HJHZDUW","json":"https://pith.science/pith/474OF7OJGDEYBUPH6Z7HJHZDUW.json","graph_json":"https://pith.science/api/pith-number/474OF7OJGDEYBUPH6Z7HJHZDUW/graph.json","events_json":"https://pith.science/api/pith-number/474OF7OJGDEYBUPH6Z7HJHZDUW/events.json","paper":"https://pith.science/paper/474OF7OJ"},"agent_actions":{"view_html":"https://pith.science/pith/474OF7OJGDEYBUPH6Z7HJHZDUW","download_json":"https://pith.science/pith/474OF7OJGDEYBUPH6Z7HJHZDUW.json","view_paper":"https://pith.science/paper/474OF7OJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.01489&json=true","fetch_graph":"https://pith.science/api/pith-number/474OF7OJGDEYBUPH6Z7HJHZDUW/graph.json","fetch_events":"https://pith.science/api/pith-number/474OF7OJGDEYBUPH6Z7HJHZDUW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/474OF7OJGDEYBUPH6Z7HJHZDUW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/474OF7OJGDEYBUPH6Z7HJHZDUW/action/storage_attestation","attest_author":"https://pith.science/pith/474OF7OJGDEYBUPH6Z7HJHZDUW/action/author_attestation","sign_citation":"https://pith.science/pith/474OF7OJGDEYBUPH6Z7HJHZDUW/action/citation_signature","submit_replication":"https://pith.science/pith/474OF7OJGDEYBUPH6Z7HJHZDUW/action/replication_record"}},"created_at":"2026-05-27T01:05:55.655274+00:00","updated_at":"2026-05-27T01:05:55.655274+00:00"}