{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:6QS3OIBMID4YM746F42RZYUPGR","short_pith_number":"pith:6QS3OIBM","canonical_record":{"source":{"id":"2604.17406","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-04-19T12:26:05Z","cross_cats_sorted":[],"title_canon_sha256":"f1fa16a77866ce189a142a3a36acde5c71251fdefe26346b88e28e37fed3c793","abstract_canon_sha256":"4ea9375219fde31525eaa7b9ba7235c33ccdda4ced060a0d76b766234db661aa"},"schema_version":"1.0"},"canonical_sha256":"f425b7202c40f9867f9e2f351ce28f345a0b7a7ecafd1bec4dc9796ab9cf83b5","source":{"kind":"arxiv","id":"2604.17406","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.17406","created_at":"2026-06-09T01:05:17Z"},{"alias_kind":"arxiv_version","alias_value":"2604.17406v3","created_at":"2026-06-09T01:05:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.17406","created_at":"2026-06-09T01:05:17Z"},{"alias_kind":"pith_short_12","alias_value":"6QS3OIBMID4Y","created_at":"2026-06-09T01:05:17Z"},{"alias_kind":"pith_short_16","alias_value":"6QS3OIBMID4YM746","created_at":"2026-06-09T01:05:17Z"},{"alias_kind":"pith_short_8","alias_value":"6QS3OIBM","created_at":"2026-06-09T01:05:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:6QS3OIBMID4YM746F42RZYUPGR","target":"record","payload":{"canonical_record":{"source":{"id":"2604.17406","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-04-19T12:26:05Z","cross_cats_sorted":[],"title_canon_sha256":"f1fa16a77866ce189a142a3a36acde5c71251fdefe26346b88e28e37fed3c793","abstract_canon_sha256":"4ea9375219fde31525eaa7b9ba7235c33ccdda4ced060a0d76b766234db661aa"},"schema_version":"1.0"},"canonical_sha256":"f425b7202c40f9867f9e2f351ce28f345a0b7a7ecafd1bec4dc9796ab9cf83b5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T01:05:17.509874Z","signature_b64":"Qtu7JyoX1glaaTC5zF9lSl66kDcq/xkepueHwQF3tpZKqwmm7XUoEufIVlji6m1a/8PnMJcVktAjO/3TV6KECQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f425b7202c40f9867f9e2f351ce28f345a0b7a7ecafd1bec4dc9796ab9cf83b5","last_reissued_at":"2026-06-09T01:05:17.509458Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T01:05:17.509458Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2604.17406","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-09T01:05:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PxjN8qbJUzNpujj0jAdHnxB1mp7tIGB9j0EelwOexs6RtR7rzWcBQ5V/BJbDBH1JIypDVJi1Nonw8Q82gFuZBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T05:03:31.501933Z"},"content_sha256":"57c8d48ea83d3c8657a6f17b56ac3337817f3bbeae0f8feda005b0ff89788838","schema_version":"1.0","event_id":"sha256:57c8d48ea83d3c8657a6f17b56ac3337817f3bbeae0f8feda005b0ff89788838"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:6QS3OIBMID4YM746F42RZYUPGR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"EvoMaster: A Foundational Evolving Agent Framework for Agentic Science at Scale","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"EvoMaster is a foundational framework that lets scientific agents continuously evolve through self-critique and knowledge accumulation.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bingyang Zheng, Cheng Wang, Fengyang Li, Jingyi Chai, Linfeng Zhang, Rui Ye, Ruoxue Liao, Shuo Tang, Siheng Chen, Tingjia Miao, Wanxu Liu, Weinan E, Wenkai Jin, Xianghe Pang, Xinyu Zhu, Yanfeng Wang, Yaxin Du, Yuwen Du, Yuzhi Zhang, Yuzhu Cai, Zehao Bing, Zexi Liu, Zhaohan Ding","submitted_at":"2026-04-19T12:26:05Z","abstract_excerpt":"The convergence of large language models and agents is catalyzing a new era of scientific discovery: Agentic Science. While the scientific method is inherently iterative, existing agent frameworks are predominantly static, narrowly scoped, and lack the capacity to learn from trial and error. To bridge this gap, we present EvoMaster, a foundational evolving agent framework engineered specifically for Agentic Science at Scale. Driven by the core principle of continuous self-evolution, EvoMaster empowers agents to iteratively refine hypotheses, self-critique, and progressively accumulate knowledg"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"EvoMaster achieves state-of-the-art scores of 41.1%, 75.8%, 73.3%, and 53.3% on Humanity's Last Exam, MLE-Bench Lite, BrowseComp, and FrontierScience respectively, comprehensively outperforming the general-purpose baseline OpenClaw with relative improvements ranging from +159% to +316%.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the described continuous self-evolution process produces genuine improvements in scientific reasoning and discovery capability rather than benchmark-specific optimizations or superficial gains.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"EvoMaster is a self-evolving agent framework that achieves state-of-the-art results on scientific benchmarks by enabling iterative hypothesis refinement and knowledge accumulation across domains.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"EvoMaster is a foundational framework that lets scientific agents continuously evolve through self-critique and knowledge accumulation.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"b86ff658d4aa8427bceb45ef9d6f5ca5f9e26b1ec228ec3526497c383f0f8103"},"source":{"id":"2604.17406","kind":"arxiv","version":3},"verdict":{"id":"266cdb8a-a93f-43ae-ae9f-f3091a9d6031","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T05:55:16.555100Z","strongest_claim":"EvoMaster achieves state-of-the-art scores of 41.1%, 75.8%, 73.3%, and 53.3% on Humanity's Last Exam, MLE-Bench Lite, BrowseComp, and FrontierScience respectively, comprehensively outperforming the general-purpose baseline OpenClaw with relative improvements ranging from +159% to +316%.","one_line_summary":"EvoMaster is a self-evolving agent framework that achieves state-of-the-art results on scientific benchmarks by enabling iterative hypothesis refinement and knowledge accumulation across domains.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the described continuous self-evolution process produces genuine improvements in scientific reasoning and discovery capability rather than benchmark-specific optimizations or superficial gains.","pith_extraction_headline":"EvoMaster is a foundational framework that lets scientific agents continuously evolve through self-critique and knowledge accumulation."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.17406/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"},"verdict_id":"266cdb8a-a93f-43ae-ae9f-f3091a9d6031"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-09T01:05:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ePFmZFlZd4ZmD7zQ8UQcn2npkiWE8spDedVFSevdFYph9jFQaeL+gQSG9vG3ZI5zZJkRuRjPd1vJs3ZdyiteBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T05:03:31.503011Z"},"content_sha256":"28176d6b26866e74fe1e33d721b4fb393ad3849e49eceec0e6f5ebd9f4e5e0e6","schema_version":"1.0","event_id":"sha256:28176d6b26866e74fe1e33d721b4fb393ad3849e49eceec0e6f5ebd9f4e5e0e6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6QS3OIBMID4YM746F42RZYUPGR/bundle.json","state_url":"https://pith.science/pith/6QS3OIBMID4YM746F42RZYUPGR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6QS3OIBMID4YM746F42RZYUPGR/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":"2026-06-11T05:03:31Z","links":{"resolver":"https://pith.science/pith/6QS3OIBMID4YM746F42RZYUPGR","bundle":"https://pith.science/pith/6QS3OIBMID4YM746F42RZYUPGR/bundle.json","state":"https://pith.science/pith/6QS3OIBMID4YM746F42RZYUPGR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6QS3OIBMID4YM746F42RZYUPGR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6QS3OIBMID4YM746F42RZYUPGR","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":"4ea9375219fde31525eaa7b9ba7235c33ccdda4ced060a0d76b766234db661aa","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-04-19T12:26:05Z","title_canon_sha256":"f1fa16a77866ce189a142a3a36acde5c71251fdefe26346b88e28e37fed3c793"},"schema_version":"1.0","source":{"id":"2604.17406","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.17406","created_at":"2026-06-09T01:05:17Z"},{"alias_kind":"arxiv_version","alias_value":"2604.17406v3","created_at":"2026-06-09T01:05:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.17406","created_at":"2026-06-09T01:05:17Z"},{"alias_kind":"pith_short_12","alias_value":"6QS3OIBMID4Y","created_at":"2026-06-09T01:05:17Z"},{"alias_kind":"pith_short_16","alias_value":"6QS3OIBMID4YM746","created_at":"2026-06-09T01:05:17Z"},{"alias_kind":"pith_short_8","alias_value":"6QS3OIBM","created_at":"2026-06-09T01:05:17Z"}],"graph_snapshots":[{"event_id":"sha256:28176d6b26866e74fe1e33d721b4fb393ad3849e49eceec0e6f5ebd9f4e5e0e6","target":"graph","created_at":"2026-06-09T01:05:17Z","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":"EvoMaster achieves state-of-the-art scores of 41.1%, 75.8%, 73.3%, and 53.3% on Humanity's Last Exam, MLE-Bench Lite, BrowseComp, and FrontierScience respectively, comprehensively outperforming the general-purpose baseline OpenClaw with relative improvements ranging from +159% to +316%."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the described continuous self-evolution process produces genuine improvements in scientific reasoning and discovery capability rather than benchmark-specific optimizations or superficial gains."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"EvoMaster is a self-evolving agent framework that achieves state-of-the-art results on scientific benchmarks by enabling iterative hypothesis refinement and knowledge accumulation across domains."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"EvoMaster is a foundational framework that lets scientific agents continuously evolve through self-critique and knowledge accumulation."}],"snapshot_sha256":"b86ff658d4aa8427bceb45ef9d6f5ca5f9e26b1ec228ec3526497c383f0f8103"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.17406/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The convergence of large language models and agents is catalyzing a new era of scientific discovery: Agentic Science. While the scientific method is inherently iterative, existing agent frameworks are predominantly static, narrowly scoped, and lack the capacity to learn from trial and error. To bridge this gap, we present EvoMaster, a foundational evolving agent framework engineered specifically for Agentic Science at Scale. Driven by the core principle of continuous self-evolution, EvoMaster empowers agents to iteratively refine hypotheses, self-critique, and progressively accumulate knowledg","authors_text":"Bingyang Zheng, Cheng Wang, Fengyang Li, Jingyi Chai, Linfeng Zhang, Rui Ye, Ruoxue Liao, Shuo Tang, Siheng Chen, Tingjia Miao, Wanxu Liu, Weinan E, Wenkai Jin, Xianghe Pang, Xinyu Zhu, Yanfeng Wang, Yaxin Du, Yuwen Du, Yuzhi Zhang, Yuzhu Cai, Zehao Bing, Zexi Liu, Zhaohan Ding","cross_cats":[],"headline":"EvoMaster is a foundational framework that lets scientific agents continuously evolve through self-critique and knowledge accumulation.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-04-19T12:26:05Z","title":"EvoMaster: A Foundational Evolving Agent Framework for Agentic Science at Scale"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.17406","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-10T05:55:16.555100Z","id":"266cdb8a-a93f-43ae-ae9f-f3091a9d6031","model_set":{"reader":"grok-4.3"},"one_line_summary":"EvoMaster is a self-evolving agent framework that achieves state-of-the-art results on scientific benchmarks by enabling iterative hypothesis refinement and knowledge accumulation across domains.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"EvoMaster is a foundational framework that lets scientific agents continuously evolve through self-critique and knowledge accumulation.","strongest_claim":"EvoMaster achieves state-of-the-art scores of 41.1%, 75.8%, 73.3%, and 53.3% on Humanity's Last Exam, MLE-Bench Lite, BrowseComp, and FrontierScience respectively, comprehensively outperforming the general-purpose baseline OpenClaw with relative improvements ranging from +159% to +316%.","weakest_assumption":"That the described continuous self-evolution process produces genuine improvements in scientific reasoning and discovery capability rather than benchmark-specific optimizations or superficial gains."}},"verdict_id":"266cdb8a-a93f-43ae-ae9f-f3091a9d6031"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:57c8d48ea83d3c8657a6f17b56ac3337817f3bbeae0f8feda005b0ff89788838","target":"record","created_at":"2026-06-09T01:05:17Z","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":"4ea9375219fde31525eaa7b9ba7235c33ccdda4ced060a0d76b766234db661aa","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-04-19T12:26:05Z","title_canon_sha256":"f1fa16a77866ce189a142a3a36acde5c71251fdefe26346b88e28e37fed3c793"},"schema_version":"1.0","source":{"id":"2604.17406","kind":"arxiv","version":3}},"canonical_sha256":"f425b7202c40f9867f9e2f351ce28f345a0b7a7ecafd1bec4dc9796ab9cf83b5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f425b7202c40f9867f9e2f351ce28f345a0b7a7ecafd1bec4dc9796ab9cf83b5","first_computed_at":"2026-06-09T01:05:17.509458Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T01:05:17.509458Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Qtu7JyoX1glaaTC5zF9lSl66kDcq/xkepueHwQF3tpZKqwmm7XUoEufIVlji6m1a/8PnMJcVktAjO/3TV6KECQ==","signature_status":"signed_v1","signed_at":"2026-06-09T01:05:17.509874Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.17406","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:57c8d48ea83d3c8657a6f17b56ac3337817f3bbeae0f8feda005b0ff89788838","sha256:28176d6b26866e74fe1e33d721b4fb393ad3849e49eceec0e6f5ebd9f4e5e0e6"],"state_sha256":"42e74bd2d234b0ff6db99d5901062872f7e52b94104192f9d5aa13017ba88814"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YIfgVBJkNQFqkRrXE5mkKUGV/K8a75WpfkwHDHqQVpDr15E1y6F13iG5Ngr5xvqVp8Dk4YkQQ3YwvOOjtIX0Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T05:03:31.507272Z","bundle_sha256":"e17853feebca6b0cf6caaef5eb729e5b989958d4aa434f390bb5bf8311ee12ab"}}