{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:IIHFIAMATP4YRI3OJYUUTISOZL","short_pith_number":"pith:IIHFIAMA","canonical_record":{"source":{"id":"2606.07591","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T16:27:40Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"8a4e3fab1967b63af1077b52b23aed0108c6b71e492d325853acdbd96f37e2ac","abstract_canon_sha256":"188fc7755712288a240c05efd562bf6adaa01f71ef453ccb28a1cf5384300504"},"schema_version":"1.0"},"canonical_sha256":"420e5401809bf988a36e4e2949a24ecadb6e7f84ee7b7247d33705e2522e2cd0","source":{"kind":"arxiv","id":"2606.07591","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.07591","created_at":"2026-06-09T00:04:44Z"},{"alias_kind":"arxiv_version","alias_value":"2606.07591v1","created_at":"2026-06-09T00:04:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07591","created_at":"2026-06-09T00:04:44Z"},{"alias_kind":"pith_short_12","alias_value":"IIHFIAMATP4Y","created_at":"2026-06-09T00:04:44Z"},{"alias_kind":"pith_short_16","alias_value":"IIHFIAMATP4YRI3O","created_at":"2026-06-09T00:04:44Z"},{"alias_kind":"pith_short_8","alias_value":"IIHFIAMA","created_at":"2026-06-09T00:04:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:IIHFIAMATP4YRI3OJYUUTISOZL","target":"record","payload":{"canonical_record":{"source":{"id":"2606.07591","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T16:27:40Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"8a4e3fab1967b63af1077b52b23aed0108c6b71e492d325853acdbd96f37e2ac","abstract_canon_sha256":"188fc7755712288a240c05efd562bf6adaa01f71ef453ccb28a1cf5384300504"},"schema_version":"1.0"},"canonical_sha256":"420e5401809bf988a36e4e2949a24ecadb6e7f84ee7b7247d33705e2522e2cd0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T00:04:44.196755Z","signature_b64":"SsJzCHich36+Zhin/aA7hC+hh078FgaShuaIDx+xIjMOJ+7PsRKw5HooovplEVAAMl3yEA/GPlCcHVardBFpDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"420e5401809bf988a36e4e2949a24ecadb6e7f84ee7b7247d33705e2522e2cd0","last_reissued_at":"2026-06-09T00:04:44.196013Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T00:04:44.196013Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.07591","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-09T00:04:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iwsthxp0rYbaIcsg/YWzLV2bX2gv99URTg4TH7vidTklt0HV/iXLSRiZRhe++J/RsKfr0KVyB+8A4PHuh5FLBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T18:08:59.882254Z"},"content_sha256":"90bdf0c486d75fb9e78d8c76a5b71d4d40e3e1c70743f15a7b75427c1fedd41e","schema_version":"1.0","event_id":"sha256:90bdf0c486d75fb9e78d8c76a5b71d4d40e3e1c70743f15a7b75427c1fedd41e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:IIHFIAMATP4YRI3OJYUUTISOZL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Bin Wang, Bo Zhang, Chaofan Hu, Chunfeng Song, Dongzhan Zhou, Fangchen Yu, Fenghua Ling, Guangtao Zhai, Haoxiang Yin, Haoxuan Li, Haoyu Zhou, Hengjian Gao, Jiamin Wu, Kun Li, Lei Bai, Lixue Cheng, Lu Mi, Mao Su, Mianxin Liu, Peng Ye, Qi Li, Qinglong Cao, Ruizhe Chen, Shengdu Chai, Sheng Xu, Shengyuan Xu, Shixiang Tang, Shuo Li, Siqi Sun, Tianfan Fu, Tianlin Ye, Wanghan Xu, Wanli Ouyang, Weijie Ma, Wenlong Zhang, Xiangyu Zhao, Xingjian Guo, Xinyu Gu, Xue Yang, Xuming He, Xuxuan Xie, Yifan Zhou, Yiheng Wang, Yixin Chen, Yuhao Zhou, Yuqiang Li, Zhangrui Zhao, Zhenfei Yin, Zhiwang Zhou, Zijie Guo","submitted_at":"2026-05-28T16:27:40Z","abstract_excerpt":"AI coding agents are increasingly used for scientific work, but their end-to-end autonomous research capability remains difficult to verify. We present ResearchClawBench, a benchmark for evaluating autonomous scientific research across 40 tasks from 10 scientific domains. Each task is grounded in a real published paper, provides related literature and raw data, and hides the target paper during evaluation. Expert-curated multimodal rubrics decompose the target scientific artifacts into weighted criteria, enabling evaluation of target-paper-level re-discovery while leaving room for new discover"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07591","kind":"arxiv","version":1},"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/2606.07591/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":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-09T00:04:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qDhP7MkvCSc/UsSjMNHKkucm0hs2IDRmXo8hcDOI+UzP06QRCqwDjcPWeU1rRaTz5SB6bcGbXBfUZ65dpRu9AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T18:08:59.882999Z"},"content_sha256":"11d4d183d90f96b5acec35f7aeba07880203c59ee6994778645dd0fc0e73261d","schema_version":"1.0","event_id":"sha256:11d4d183d90f96b5acec35f7aeba07880203c59ee6994778645dd0fc0e73261d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IIHFIAMATP4YRI3OJYUUTISOZL/bundle.json","state_url":"https://pith.science/pith/IIHFIAMATP4YRI3OJYUUTISOZL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IIHFIAMATP4YRI3OJYUUTISOZL/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":"2026-06-09T18:08:59Z","links":{"resolver":"https://pith.science/pith/IIHFIAMATP4YRI3OJYUUTISOZL","bundle":"https://pith.science/pith/IIHFIAMATP4YRI3OJYUUTISOZL/bundle.json","state":"https://pith.science/pith/IIHFIAMATP4YRI3OJYUUTISOZL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IIHFIAMATP4YRI3OJYUUTISOZL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:IIHFIAMATP4YRI3OJYUUTISOZL","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":"188fc7755712288a240c05efd562bf6adaa01f71ef453ccb28a1cf5384300504","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T16:27:40Z","title_canon_sha256":"8a4e3fab1967b63af1077b52b23aed0108c6b71e492d325853acdbd96f37e2ac"},"schema_version":"1.0","source":{"id":"2606.07591","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.07591","created_at":"2026-06-09T00:04:44Z"},{"alias_kind":"arxiv_version","alias_value":"2606.07591v1","created_at":"2026-06-09T00:04:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07591","created_at":"2026-06-09T00:04:44Z"},{"alias_kind":"pith_short_12","alias_value":"IIHFIAMATP4Y","created_at":"2026-06-09T00:04:44Z"},{"alias_kind":"pith_short_16","alias_value":"IIHFIAMATP4YRI3O","created_at":"2026-06-09T00:04:44Z"},{"alias_kind":"pith_short_8","alias_value":"IIHFIAMA","created_at":"2026-06-09T00:04:44Z"}],"graph_snapshots":[{"event_id":"sha256:11d4d183d90f96b5acec35f7aeba07880203c59ee6994778645dd0fc0e73261d","target":"graph","created_at":"2026-06-09T00:04:44Z","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/2606.07591/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"AI coding agents are increasingly used for scientific work, but their end-to-end autonomous research capability remains difficult to verify. We present ResearchClawBench, a benchmark for evaluating autonomous scientific research across 40 tasks from 10 scientific domains. Each task is grounded in a real published paper, provides related literature and raw data, and hides the target paper during evaluation. Expert-curated multimodal rubrics decompose the target scientific artifacts into weighted criteria, enabling evaluation of target-paper-level re-discovery while leaving room for new discover","authors_text":"Bin Wang, Bo Zhang, Chaofan Hu, Chunfeng Song, Dongzhan Zhou, Fangchen Yu, Fenghua Ling, Guangtao Zhai, Haoxiang Yin, Haoxuan Li, Haoyu Zhou, Hengjian Gao, Jiamin Wu, Kun Li, Lei Bai, Lixue Cheng, Lu Mi, Mao Su, Mianxin Liu, Peng Ye, Qi Li, Qinglong Cao, Ruizhe Chen, Shengdu Chai, Sheng Xu, Shengyuan Xu, Shixiang Tang, Shuo Li, Siqi Sun, Tianfan Fu, Tianlin Ye, Wanghan Xu, Wanli Ouyang, Weijie Ma, Wenlong Zhang, Xiangyu Zhao, Xingjian Guo, Xinyu Gu, Xue Yang, Xuming He, Xuxuan Xie, Yifan Zhou, Yiheng Wang, Yixin Chen, Yuhao Zhou, Yuqiang Li, Zhangrui Zhao, Zhenfei Yin, Zhiwang Zhou, Zijie Guo","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T16:27:40Z","title":"ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07591","kind":"arxiv","version":1},"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":"sha256:90bdf0c486d75fb9e78d8c76a5b71d4d40e3e1c70743f15a7b75427c1fedd41e","target":"record","created_at":"2026-06-09T00:04:44Z","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":"188fc7755712288a240c05efd562bf6adaa01f71ef453ccb28a1cf5384300504","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T16:27:40Z","title_canon_sha256":"8a4e3fab1967b63af1077b52b23aed0108c6b71e492d325853acdbd96f37e2ac"},"schema_version":"1.0","source":{"id":"2606.07591","kind":"arxiv","version":1}},"canonical_sha256":"420e5401809bf988a36e4e2949a24ecadb6e7f84ee7b7247d33705e2522e2cd0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"420e5401809bf988a36e4e2949a24ecadb6e7f84ee7b7247d33705e2522e2cd0","first_computed_at":"2026-06-09T00:04:44.196013Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T00:04:44.196013Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SsJzCHich36+Zhin/aA7hC+hh078FgaShuaIDx+xIjMOJ+7PsRKw5HooovplEVAAMl3yEA/GPlCcHVardBFpDw==","signature_status":"signed_v1","signed_at":"2026-06-09T00:04:44.196755Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.07591","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:90bdf0c486d75fb9e78d8c76a5b71d4d40e3e1c70743f15a7b75427c1fedd41e","sha256:11d4d183d90f96b5acec35f7aeba07880203c59ee6994778645dd0fc0e73261d"],"state_sha256":"126575f09a98ff50ed78861a9061ee34ff64c639e7f79473b70db12c0b4d311a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Bn3p42mArvcX/ghj3o2TLpGeLZojkd+3lasRmwQjsjtqsMWU+sQ8eADldiS8NNGjJUiMkiVuaK1v4EeDJiZ6Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T18:08:59.887189Z","bundle_sha256":"c1424439e9bcb2fc58ec0606399642dafa3ae98870d342fdd4108d416797fd23"}}