{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZUALWONYSBKNVUQLQCL72YDU2B","short_pith_number":"pith:ZUALWONY","schema_version":"1.0","canonical_sha256":"cd00bb39b89054dad20b8097fd6074d0615f2fa78728c783273ad7ec23d8df99","source":{"kind":"arxiv","id":"2604.13018","version":2},"attestation_state":"computed","paper":{"title":"Toward Autonomous Long-Horizon Engineering for ML Research","license":"http://creativecommons.org/licenses/by/4.0/","headline":"AiScientist achieves higher performance on long-horizon ML research benchmarks by using hierarchical orchestration and a File-as-Bus workspace.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cheng Chen, Fanzhe Meng, Guoxin Chen, Jiale Zhao, Jie Chen, Ji-Rong Wen, Kai Jia, Lei Chen, Ruihua Song, Wayne Xin Zhao","submitted_at":"2026-04-14T17:55:16Z","abstract_excerpt":"Agentic systems increasingly automate pieces of AI research. Yet turning underspecified research objectives into runnable, experimentally validated ML systems remains a central bottleneck. We study this operational setting as \\emph{long-horizon ML research engineering}: converting a research specification into a runnable ML system through repeated implementation, experimentation, and refinement. The central challenge is to sustain cumulative project progress across heterogeneous stages under delayed, confounded feedback. We introduce AiScientist, a multi-agent system built around thin control "},"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":"2604.13018","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-14T17:55:16Z","cross_cats_sorted":[],"title_canon_sha256":"eda5ff3025ceba1aad9cca7f65e63e4adb969b5d4c5d1deff099ab1f62b8d9ae","abstract_canon_sha256":"99df1d90f1a022d32d8037f6224c8375d0ee7e19af4a719db1a76f71656c821f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:05:54.536075Z","signature_b64":"1c9GCTO4vWRfuT8NIB2q+fKnQ8LILMFzwRHEdReWG6dxOwGgwTxKWKaRVRTaFs2vdbwqCvGDbIP1EFNTcojmAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd00bb39b89054dad20b8097fd6074d0615f2fa78728c783273ad7ec23d8df99","last_reissued_at":"2026-05-27T01:05:54.535357Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:05:54.535357Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Toward Autonomous Long-Horizon Engineering for ML Research","license":"http://creativecommons.org/licenses/by/4.0/","headline":"AiScientist achieves higher performance on long-horizon ML research benchmarks by using hierarchical orchestration and a File-as-Bus workspace.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cheng Chen, Fanzhe Meng, Guoxin Chen, Jiale Zhao, Jie Chen, Ji-Rong Wen, Kai Jia, Lei Chen, Ruihua Song, Wayne Xin Zhao","submitted_at":"2026-04-14T17:55:16Z","abstract_excerpt":"Agentic systems increasingly automate pieces of AI research. Yet turning underspecified research objectives into runnable, experimentally validated ML systems remains a central bottleneck. We study this operational setting as \\emph{long-horizon ML research engineering}: converting a research specification into a runnable ML system through repeated implementation, experimentation, and refinement. The central challenge is to sustain cumulative project progress across heterogeneous stages under delayed, confounded feedback. We introduce AiScientist, a multi-agent system built around thin control "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"AiScientist improves PaperBench score by 10.54 points on average over the best matched baseline and achieves 81.82 Any Medal% on MLE-Bench Lite. Ablation studies further show that File-as-Bus protocol is a key driver of performance, reducing PaperBench by 6.41 points and MLE-Bench Lite by 31.82 points when removed.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the chosen benchmarks (PaperBench and MLE-Bench Lite) accurately capture real long-horizon ML research engineering capability and that the reported gains are attributable to the hierarchical orchestration plus File-as-Bus design rather than implementation details or baseline mismatches.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"AiScientist improves ML research benchmarks by 10.54 points on PaperBench and reaches 81.82% Any Medal on MLE-Bench Lite through hierarchical control plus durable file-based state instead of conversational handoffs.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"AiScientist achieves higher performance on long-horizon ML research benchmarks by using hierarchical orchestration and a File-as-Bus workspace.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"55774e1c0ae4bdfc0eb6b15246c9d281f0c6014f2be0d8c89ebe2267b02461ac"},"source":{"id":"2604.13018","kind":"arxiv","version":2},"verdict":{"id":"937606f7-c438-4d2e-b510-61a6625585f5","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T15:46:53.395337Z","strongest_claim":"AiScientist improves PaperBench score by 10.54 points on average over the best matched baseline and achieves 81.82 Any Medal% on MLE-Bench Lite. Ablation studies further show that File-as-Bus protocol is a key driver of performance, reducing PaperBench by 6.41 points and MLE-Bench Lite by 31.82 points when removed.","one_line_summary":"AiScientist improves ML research benchmarks by 10.54 points on PaperBench and reaches 81.82% Any Medal on MLE-Bench Lite through hierarchical control plus durable file-based state instead of conversational handoffs.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the chosen benchmarks (PaperBench and MLE-Bench Lite) accurately capture real long-horizon ML research engineering capability and that the reported gains are attributable to the hierarchical orchestration plus File-as-Bus design rather than implementation details or baseline mismatches.","pith_extraction_headline":"AiScientist achieves higher performance on long-horizon ML research benchmarks by using hierarchical orchestration and a File-as-Bus workspace."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.13018/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2604.13018","created_at":"2026-05-27T01:05:54.535469+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.13018v2","created_at":"2026-05-27T01:05:54.535469+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.13018","created_at":"2026-05-27T01:05:54.535469+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZUALWONYSBKN","created_at":"2026-05-27T01:05:54.535469+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZUALWONYSBKNVUQL","created_at":"2026-05-27T01:05:54.535469+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZUALWONY","created_at":"2026-05-27T01:05:54.535469+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":3,"sample":[{"citing_arxiv_id":"2605.18661","citing_title":"AI for Auto-Research: Roadmap & User Guide","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13874","citing_title":"GEAR: Genetic AutoResearch for Agentic Code Evolution","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2604.25256","citing_title":"AutoResearchBench: Benchmarking AI Agents on Complex Scientific Literature Discovery","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZUALWONYSBKNVUQLQCL72YDU2B","json":"https://pith.science/pith/ZUALWONYSBKNVUQLQCL72YDU2B.json","graph_json":"https://pith.science/api/pith-number/ZUALWONYSBKNVUQLQCL72YDU2B/graph.json","events_json":"https://pith.science/api/pith-number/ZUALWONYSBKNVUQLQCL72YDU2B/events.json","paper":"https://pith.science/paper/ZUALWONY"},"agent_actions":{"view_html":"https://pith.science/pith/ZUALWONYSBKNVUQLQCL72YDU2B","download_json":"https://pith.science/pith/ZUALWONYSBKNVUQLQCL72YDU2B.json","view_paper":"https://pith.science/paper/ZUALWONY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.13018&json=true","fetch_graph":"https://pith.science/api/pith-number/ZUALWONYSBKNVUQLQCL72YDU2B/graph.json","fetch_events":"https://pith.science/api/pith-number/ZUALWONYSBKNVUQLQCL72YDU2B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZUALWONYSBKNVUQLQCL72YDU2B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZUALWONYSBKNVUQLQCL72YDU2B/action/storage_attestation","attest_author":"https://pith.science/pith/ZUALWONYSBKNVUQLQCL72YDU2B/action/author_attestation","sign_citation":"https://pith.science/pith/ZUALWONYSBKNVUQLQCL72YDU2B/action/citation_signature","submit_replication":"https://pith.science/pith/ZUALWONYSBKNVUQLQCL72YDU2B/action/replication_record"}},"created_at":"2026-05-27T01:05:54.535469+00:00","updated_at":"2026-05-27T01:05:54.535469+00:00"}