{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:474OF7OJGDEYBUPH6Z7HJHZDUW","short_pith_number":"pith:474OF7OJ","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"},"canonical_sha256":"e7f8e2fdc930c980d1e7f67e749f23a5a594411b314f889839663588cb8554cf","source":{"kind":"arxiv","id":"2605.01489","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.01489","created_at":"2026-05-27T01:05:55Z"},{"alias_kind":"arxiv_version","alias_value":"2605.01489v2","created_at":"2026-05-27T01:05:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.01489","created_at":"2026-05-27T01:05:55Z"},{"alias_kind":"pith_short_12","alias_value":"474OF7OJGDEY","created_at":"2026-05-27T01:05:55Z"},{"alias_kind":"pith_short_16","alias_value":"474OF7OJGDEYBUPH","created_at":"2026-05-27T01:05:55Z"},{"alias_kind":"pith_short_8","alias_value":"474OF7OJ","created_at":"2026-05-27T01:05:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:474OF7OJGDEYBUPH6Z7HJHZDUW","target":"record","payload":{"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"},"canonical_sha256":"e7f8e2fdc930c980d1e7f67e749f23a5a594411b314f889839663588cb8554cf","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"},"source_kind":"arxiv","source_id":"2605.01489","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-27T01:05:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qL5MZNltfOf3EGFc9Y9Wj9MeL96hsVWeJ/8KRKs2YcUXWrs6bGVYn+UTTQQ7F1NvpchPRhkQ61JcyPOGZxH2CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T21:57:25.797584Z"},"content_sha256":"1af9090ec1a7a3d8c77e13a1d761f31f036f80228f1fb06953ab0ca42f2a76b0","schema_version":"1.0","event_id":"sha256:1af9090ec1a7a3d8c77e13a1d761f31f036f80228f1fb06953ab0ca42f2a76b0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:474OF7OJGDEYBUPH6Z7HJHZDUW","target":"graph","payload":{"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"},"verdict_id":"b0632074-89ac-46f4-82d8-5c9660c72ff8"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-27T01:05:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AH5fC9NJBO4+WNWofkw6Bo6HsRYPjN4EJtDlYARFJIC/+cU6Q/xUVbtxaCz2PDVUSGOvRUzRyyUMx+3mz55MCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T21:57:25.798267Z"},"content_sha256":"b20a2324af16b36ab83bb837d6146cc5b1d2846180cf76e80e7d326538b59a59","schema_version":"1.0","event_id":"sha256:b20a2324af16b36ab83bb837d6146cc5b1d2846180cf76e80e7d326538b59a59"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/474OF7OJGDEYBUPH6Z7HJHZDUW/bundle.json","state_url":"https://pith.science/pith/474OF7OJGDEYBUPH6Z7HJHZDUW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/474OF7OJGDEYBUPH6Z7HJHZDUW/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-31T21:57:25Z","links":{"resolver":"https://pith.science/pith/474OF7OJGDEYBUPH6Z7HJHZDUW","bundle":"https://pith.science/pith/474OF7OJGDEYBUPH6Z7HJHZDUW/bundle.json","state":"https://pith.science/pith/474OF7OJGDEYBUPH6Z7HJHZDUW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/474OF7OJGDEYBUPH6Z7HJHZDUW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:474OF7OJGDEYBUPH6Z7HJHZDUW","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":"3b47ba40dd0e0666a765efc80157afb6b97d519cfd9d13d598ae51c9eec8202c","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-02T15:26:45Z","title_canon_sha256":"7ceb00cfd966388e770212fbb394a4642b787e096360daca5bfea7ab18ec741d"},"schema_version":"1.0","source":{"id":"2605.01489","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.01489","created_at":"2026-05-27T01:05:55Z"},{"alias_kind":"arxiv_version","alias_value":"2605.01489v2","created_at":"2026-05-27T01:05:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.01489","created_at":"2026-05-27T01:05:55Z"},{"alias_kind":"pith_short_12","alias_value":"474OF7OJGDEY","created_at":"2026-05-27T01:05:55Z"},{"alias_kind":"pith_short_16","alias_value":"474OF7OJGDEYBUPH","created_at":"2026-05-27T01:05:55Z"},{"alias_kind":"pith_short_8","alias_value":"474OF7OJ","created_at":"2026-05-27T01:05:55Z"}],"graph_snapshots":[{"event_id":"sha256:b20a2324af16b36ab83bb837d6146cc5b1d2846180cf76e80e7d326538b59a59","target":"graph","created_at":"2026-05-27T01:05:55Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Automated synthesis of conceptual and computational tasks trains an 8B model to set new records on frontier biology and chemistry reasoning benchmarks."}],"snapshot_sha256":"9a738753c9f2398ed340feb06f96acd02965d24f57e23cab512eaa68a7072ac8"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"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"}],"endpoint":"/pith/2605.01489/integrity.json","findings":[],"snapshot_sha256":"68abf098f1144e9428abf2bf1bf488b5638eb76e9dda3d6b9a6fa19ddb4d447e","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Kelvin Kiu Wai Tam, Newt Nguyen Kim Hue Nam, Rui Wang, Tianqing Fang, Tianshi Zheng, Wei Fan, Xiyun Li, Yangqiu Song","cross_cats":["cs.CL"],"headline":"Automated synthesis of conceptual and computational tasks trains an 8B model to set new records on frontier biology and chemistry reasoning benchmarks.","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-02T15:26:45Z","title":"SciResearcher: Scaling Deep Research Agents for Frontier Scientific Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.01489","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-09T14:14:38.432631Z","id":"b0632074-89ac-46f4-82d8-5c9660c72ff8","model_set":{"reader":"grok-4.3"},"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","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.","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.","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."}},"verdict_id":"b0632074-89ac-46f4-82d8-5c9660c72ff8"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1af9090ec1a7a3d8c77e13a1d761f31f036f80228f1fb06953ab0ca42f2a76b0","target":"record","created_at":"2026-05-27T01:05:55Z","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":"3b47ba40dd0e0666a765efc80157afb6b97d519cfd9d13d598ae51c9eec8202c","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-02T15:26:45Z","title_canon_sha256":"7ceb00cfd966388e770212fbb394a4642b787e096360daca5bfea7ab18ec741d"},"schema_version":"1.0","source":{"id":"2605.01489","kind":"arxiv","version":2}},"canonical_sha256":"e7f8e2fdc930c980d1e7f67e749f23a5a594411b314f889839663588cb8554cf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e7f8e2fdc930c980d1e7f67e749f23a5a594411b314f889839663588cb8554cf","first_computed_at":"2026-05-27T01:05:55.655135Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T01:05:55.655135Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nDBUmB6rFU2hwbgylwflrH/kgCcO/2q0cbpulbC/yVb9QBP5iceqqVC0dRXfhB8J99+IpOjJY34nfm37LLukAA==","signature_status":"signed_v1","signed_at":"2026-05-27T01:05:55.656005Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.01489","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1af9090ec1a7a3d8c77e13a1d761f31f036f80228f1fb06953ab0ca42f2a76b0","sha256:b20a2324af16b36ab83bb837d6146cc5b1d2846180cf76e80e7d326538b59a59"],"state_sha256":"01d0ad5265e64fb4cb8a6858932a2d98aaa332c9166ba1ffe263d45a8a90bf97"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vtqRJtVTPiIUmpPJHUEhp5Mn0mtD6+bBv0+GUrSc6izUD78E8gasxlp84KLjqqhzZeIpNoi3P/nhUQcU2aJ7Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T21:57:25.800810Z","bundle_sha256":"6e6690537fb9ac63e8d677b3a9ad387f3093e8be43e9e33023d81e214c45fb23"}}