{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VS23ZKI7I5LGNNYVPWWSYFHFC2","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":"9e182a2d6995d7e1fbb821933ee888f6cfeb8ca1be3c25cb54fbcf6d549e0747","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2026-04-27T16:23:09Z","title_canon_sha256":"3e33912c22e8b3dbb00486be2278d65ead8393599fd3ecba3bd7df914af4a187"},"schema_version":"1.0","source":{"id":"2604.24658","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.24658","created_at":"2026-05-20T02:05:43Z"},{"alias_kind":"arxiv_version","alias_value":"2604.24658v3","created_at":"2026-05-20T02:05:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.24658","created_at":"2026-05-20T02:05:43Z"},{"alias_kind":"pith_short_12","alias_value":"VS23ZKI7I5LG","created_at":"2026-05-20T02:05:43Z"},{"alias_kind":"pith_short_16","alias_value":"VS23ZKI7I5LGNNYV","created_at":"2026-05-20T02:05:43Z"},{"alias_kind":"pith_short_8","alias_value":"VS23ZKI7","created_at":"2026-05-20T02:05:43Z"}],"graph_snapshots":[{"event_id":"sha256:a599c4b9d073827fa171aca97a850f253bd64abf56b3e946b67e27fbb46da075","target":"graph","created_at":"2026-05-20T02:05:43Z","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":"On PaperBench and RE-Bench, ARA raises question-answering accuracy from 72.4% to 93.7% and reproduction success from 57.4% to 64.4%. On RE-Bench's five open-ended extension tasks, preserved failure traces in ARA accelerate progress, but can also constrain a capable agent from stepping outside the prior-run box depending on the agent's capabilities."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the specific benchmarks (PaperBench and RE-Bench) and the way ARA was applied to them accurately reflect the general challenges AI agents face when trying to understand, reproduce, and extend real published research."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"The authors introduce Agent-Native Research Artifacts (ARA) as executable research packages with four layers to reduce information loss in papers for AI agents, showing benchmark gains in question-answering and reproduction."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Machine-executable research packages replace narrative papers so AI agents can reproduce and extend work more reliably."}],"snapshot_sha256":"e2b6dbb9a959c4a7e8a83369d0cea5096aa80f6047d4871ba459fab066f3bf3f"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T21:52:50.917235Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2604.24658/integrity.json","findings":[],"snapshot_sha256":"8e3f8ebe564e5859aa03ffcdc6658452b299b98112efeecad5de33c42d62c4a1","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Scientific publication compresses a branching, iterative research process into a linear narrative, discarding the majority of what was discovered along the way. This compilation imposes two structural costs: a Storytelling Tax, where failed experiments, rejected hypotheses, and the branching exploration process are discarded to fit a linear narrative; and an Engineering Tax, where the gap between reviewer-sufficient prose and agent-sufficient specification leaves critical implementation details unwritten. Tolerable for human readers, these costs become critical when AI agents must understand, ","authors_text":"Alex Pentland, Ang Chen, Ao Qu, Baoyu Zhou, Beidi Chen, Carl Chen, Chenglei Si, Chenyu You, Fan Lai, Haizhong Zheng, Haojie Ye, Jiachen Liu, Jiachen Sun, Jianqiao Zeng, Jiaxin Pei, Jintao Huang, John Dianzhuo Wang, Junyuan Hong, Lichang Chen, Maestro Harmon, Mingyuan Wu, Mosharaf Chowdhury, Ruihao Zhu, Runyu Lu, Shangquan Sun, Shijian Lu, Xiangru Tang, Xiaoyan Bai, Yao Li, Yiming Qiu, Yuan Yuan, Yujuan Fu, Zechen Zhang, Zexue He, Zhenyu Zhang, Zhiyang Chen, Zijian Jin","cross_cats":[],"headline":"Machine-executable research packages replace narrative papers so AI agents can reproduce and extend work more reliably.","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2026-04-27T16:23:09Z","title":"The Last Human-Written Paper: Agent-Native Research Artifacts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.24658","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-08T03:53:42.590982Z","id":"0e6495cd-1cd5-4dcc-9483-84e2c2727401","model_set":{"reader":"grok-4.3"},"one_line_summary":"The authors introduce Agent-Native Research Artifacts (ARA) as executable research packages with four layers to reduce information loss in papers for AI agents, showing benchmark gains in question-answering and reproduction.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Machine-executable research packages replace narrative papers so AI agents can reproduce and extend work more reliably.","strongest_claim":"On PaperBench and RE-Bench, ARA raises question-answering accuracy from 72.4% to 93.7% and reproduction success from 57.4% to 64.4%. On RE-Bench's five open-ended extension tasks, preserved failure traces in ARA accelerate progress, but can also constrain a capable agent from stepping outside the prior-run box depending on the agent's capabilities.","weakest_assumption":"That the specific benchmarks (PaperBench and RE-Bench) and the way ARA was applied to them accurately reflect the general challenges AI agents face when trying to understand, reproduce, and extend real published research."}},"verdict_id":"0e6495cd-1cd5-4dcc-9483-84e2c2727401"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:144727f8cf094d74cdc9610598d536105a1076a4a0441a9c0e6493fdb6f7ad34","target":"record","created_at":"2026-05-20T02:05:43Z","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":"9e182a2d6995d7e1fbb821933ee888f6cfeb8ca1be3c25cb54fbcf6d549e0747","cross_cats_sorted":[],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2026-04-27T16:23:09Z","title_canon_sha256":"3e33912c22e8b3dbb00486be2278d65ead8393599fd3ecba3bd7df914af4a187"},"schema_version":"1.0","source":{"id":"2604.24658","kind":"arxiv","version":3}},"canonical_sha256":"acb5bca91f475666b7157dad2c14e516b3efeb7a63e87452f6a9b8f35f9ea221","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"acb5bca91f475666b7157dad2c14e516b3efeb7a63e87452f6a9b8f35f9ea221","first_computed_at":"2026-05-20T02:05:43.796735Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T02:05:43.796735Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6n2pfgKomB6ROXev+8I2XPCGjnBqqiucwtWmyW70L75aRoFn+JU57AbKSaWPElL2Ymhyed2Pt1AE/ZCliGWcCw==","signature_status":"signed_v1","signed_at":"2026-05-20T02:05:43.797553Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.24658","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:144727f8cf094d74cdc9610598d536105a1076a4a0441a9c0e6493fdb6f7ad34","sha256:a599c4b9d073827fa171aca97a850f253bd64abf56b3e946b67e27fbb46da075"],"state_sha256":"d5042477c6a3619b874f473eed276cd11507f37fd9c3505a75d18509757484fe"}