{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:ZUALWONYSBKNVUQLQCL72YDU2B","short_pith_number":"pith:ZUALWONY","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"},"canonical_sha256":"cd00bb39b89054dad20b8097fd6074d0615f2fa78728c783273ad7ec23d8df99","source":{"kind":"arxiv","id":"2604.13018","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.13018","created_at":"2026-05-27T01:05:54Z"},{"alias_kind":"arxiv_version","alias_value":"2604.13018v2","created_at":"2026-05-27T01:05:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.13018","created_at":"2026-05-27T01:05:54Z"},{"alias_kind":"pith_short_12","alias_value":"ZUALWONYSBKN","created_at":"2026-05-27T01:05:54Z"},{"alias_kind":"pith_short_16","alias_value":"ZUALWONYSBKNVUQL","created_at":"2026-05-27T01:05:54Z"},{"alias_kind":"pith_short_8","alias_value":"ZUALWONY","created_at":"2026-05-27T01:05:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:ZUALWONYSBKNVUQLQCL72YDU2B","target":"record","payload":{"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"},"canonical_sha256":"cd00bb39b89054dad20b8097fd6074d0615f2fa78728c783273ad7ec23d8df99","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"},"source_kind":"arxiv","source_id":"2604.13018","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":"2026-05-27T01:05:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E8tPAsIkG5BbpniQeAT6Z8YUW6QREr9BfGUFdqK+JjgBed+rvuB2uSeVQqXRmChFqN4OmAApra+xmQhs+6K0Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T00:34:47.895836Z"},"content_sha256":"be4592b7c1a4c594784c09f4e4001232ab2bac1882a82b845050e7d4e60dae55","schema_version":"1.0","event_id":"sha256:be4592b7c1a4c594784c09f4e4001232ab2bac1882a82b845050e7d4e60dae55"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:ZUALWONYSBKNVUQLQCL72YDU2B","target":"graph","payload":{"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"},"verdict_id":"937606f7-c438-4d2e-b510-61a6625585f5"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-27T01:05:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p2XSgdbQNzVIDoNAWE3DbajQGuGt5WIXyQT1FoEB1Onb5c4pYlgO/yg3Yy5gdEVkqPx2dffiu3Vybyh4gKSfBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T00:34:47.896336Z"},"content_sha256":"bcfcc55c888bb45a8435ebe9ba11d883c0768cbd3ddef8cb9de4d490649c2308","schema_version":"1.0","event_id":"sha256:bcfcc55c888bb45a8435ebe9ba11d883c0768cbd3ddef8cb9de4d490649c2308"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZUALWONYSBKNVUQLQCL72YDU2B/bundle.json","state_url":"https://pith.science/pith/ZUALWONYSBKNVUQLQCL72YDU2B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZUALWONYSBKNVUQLQCL72YDU2B/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":"2026-06-03T00:34:47Z","links":{"resolver":"https://pith.science/pith/ZUALWONYSBKNVUQLQCL72YDU2B","bundle":"https://pith.science/pith/ZUALWONYSBKNVUQLQCL72YDU2B/bundle.json","state":"https://pith.science/pith/ZUALWONYSBKNVUQLQCL72YDU2B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZUALWONYSBKNVUQLQCL72YDU2B/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZUALWONYSBKNVUQLQCL72YDU2B","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":"99df1d90f1a022d32d8037f6224c8375d0ee7e19af4a719db1a76f71656c821f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-14T17:55:16Z","title_canon_sha256":"eda5ff3025ceba1aad9cca7f65e63e4adb969b5d4c5d1deff099ab1f62b8d9ae"},"schema_version":"1.0","source":{"id":"2604.13018","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.13018","created_at":"2026-05-27T01:05:54Z"},{"alias_kind":"arxiv_version","alias_value":"2604.13018v2","created_at":"2026-05-27T01:05:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.13018","created_at":"2026-05-27T01:05:54Z"},{"alias_kind":"pith_short_12","alias_value":"ZUALWONYSBKN","created_at":"2026-05-27T01:05:54Z"},{"alias_kind":"pith_short_16","alias_value":"ZUALWONYSBKNVUQL","created_at":"2026-05-27T01:05:54Z"},{"alias_kind":"pith_short_8","alias_value":"ZUALWONY","created_at":"2026-05-27T01:05:54Z"}],"graph_snapshots":[{"event_id":"sha256:bcfcc55c888bb45a8435ebe9ba11d883c0768cbd3ddef8cb9de4d490649c2308","target":"graph","created_at":"2026-05-27T01:05:54Z","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":"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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"AiScientist achieves higher performance on long-horizon ML research benchmarks by using hierarchical orchestration and a File-as-Bus workspace."}],"snapshot_sha256":"55774e1c0ae4bdfc0eb6b15246c9d281f0c6014f2be0d8c89ebe2267b02461ac"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.13018/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Cheng Chen, Fanzhe Meng, Guoxin Chen, Jiale Zhao, Jie Chen, Ji-Rong Wen, Kai Jia, Lei Chen, Ruihua Song, Wayne Xin Zhao","cross_cats":[],"headline":"AiScientist achieves higher performance on long-horizon ML research benchmarks by using hierarchical orchestration and a File-as-Bus workspace.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-14T17:55:16Z","title":"Toward Autonomous Long-Horizon Engineering for ML Research"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.13018","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-10T15:46:53.395337Z","id":"937606f7-c438-4d2e-b510-61a6625585f5","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"AiScientist achieves higher performance on long-horizon ML research benchmarks by using hierarchical orchestration and a File-as-Bus workspace.","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.","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."}},"verdict_id":"937606f7-c438-4d2e-b510-61a6625585f5"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:be4592b7c1a4c594784c09f4e4001232ab2bac1882a82b845050e7d4e60dae55","target":"record","created_at":"2026-05-27T01:05:54Z","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":"99df1d90f1a022d32d8037f6224c8375d0ee7e19af4a719db1a76f71656c821f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-14T17:55:16Z","title_canon_sha256":"eda5ff3025ceba1aad9cca7f65e63e4adb969b5d4c5d1deff099ab1f62b8d9ae"},"schema_version":"1.0","source":{"id":"2604.13018","kind":"arxiv","version":2}},"canonical_sha256":"cd00bb39b89054dad20b8097fd6074d0615f2fa78728c783273ad7ec23d8df99","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cd00bb39b89054dad20b8097fd6074d0615f2fa78728c783273ad7ec23d8df99","first_computed_at":"2026-05-27T01:05:54.535357Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T01:05:54.535357Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1c9GCTO4vWRfuT8NIB2q+fKnQ8LILMFzwRHEdReWG6dxOwGgwTxKWKaRVRTaFs2vdbwqCvGDbIP1EFNTcojmAQ==","signature_status":"signed_v1","signed_at":"2026-05-27T01:05:54.536075Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.13018","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:be4592b7c1a4c594784c09f4e4001232ab2bac1882a82b845050e7d4e60dae55","sha256:bcfcc55c888bb45a8435ebe9ba11d883c0768cbd3ddef8cb9de4d490649c2308"],"state_sha256":"c3378a9d3cfaae062579b634957b29962387614dc24c907082b77411854cf8f5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qR8IdLpsyj40G9AQnLO+AoaaUL0xifveSGWdlu6x/NLsMzCIjlU7fg+s6kk0Rna4RGff0BUTrH7yZJ/ubXKWBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T00:34:47.898749Z","bundle_sha256":"9b7a04d69fbb538fded6d178bcfcce10eaa55f50875cebb6a891e0fff96fbd82"}}