{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:2GB75OA7A6ATDAEEV63PIS5JCB","short_pith_number":"pith:2GB75OA7","canonical_record":{"source":{"id":"2501.04227","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2025-01-08T01:58:42Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"2eea69674a838fac30e8504e6339ed62c38737ea128b881f59b4deb534b50845","abstract_canon_sha256":"60134504e062ed509777419fbe85f761cfbfe5d36590d086ae3fb354f16fa935"},"schema_version":"1.0"},"canonical_sha256":"d183feb81f0781318084afb6f44ba9105750a156f2ea9504bd3b7b2c132f5642","source":{"kind":"arxiv","id":"2501.04227","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.04227","created_at":"2026-05-17T23:38:15Z"},{"alias_kind":"arxiv_version","alias_value":"2501.04227v2","created_at":"2026-05-17T23:38:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.04227","created_at":"2026-05-17T23:38:15Z"},{"alias_kind":"pith_short_12","alias_value":"2GB75OA7A6AT","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"2GB75OA7A6ATDAEE","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"2GB75OA7","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:2GB75OA7A6ATDAEEV63PIS5JCB","target":"record","payload":{"canonical_record":{"source":{"id":"2501.04227","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2025-01-08T01:58:42Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"2eea69674a838fac30e8504e6339ed62c38737ea128b881f59b4deb534b50845","abstract_canon_sha256":"60134504e062ed509777419fbe85f761cfbfe5d36590d086ae3fb354f16fa935"},"schema_version":"1.0"},"canonical_sha256":"d183feb81f0781318084afb6f44ba9105750a156f2ea9504bd3b7b2c132f5642","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:15.178207Z","signature_b64":"Vl4hFhsidrBvrrOAjdIdf6+Aw5QzlZxZQ6ePxNxoCQqnbjcx+siorcwgiacGE3ZsTw032MLAOiZ3w/tDQBWMBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d183feb81f0781318084afb6f44ba9105750a156f2ea9504bd3b7b2c132f5642","last_reissued_at":"2026-05-17T23:38:15.177657Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:15.177657Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.04227","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":"2026-05-17T23:38:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Cr4S55dpYj+FtbjE0RZQShltJa/QSTSK9w1ho/0kiuE2rEaaKb6DeiGWCpD+jrnML5op7ADImE9d0KfvApZoDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T22:50:28.259083Z"},"content_sha256":"2efee8d9f2ef616be6c98810cc9329b2662f1c61cebabd07ec3e80e1c48f2794","schema_version":"1.0","event_id":"sha256:2efee8d9f2ef616be6c98810cc9329b2662f1c61cebabd07ec3e80e1c48f2794"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:2GB75OA7A6ATDAEEV63PIS5JCB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Agent Laboratory: Using LLM Agents as Research Assistants","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Agent Laboratory lets LLM agents carry out the full research process from idea to code repository and report.","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.HC","authors_text":"Emad Barsoum, Jialian Wu, Jiang Liu, Michael Moor, Samuel Schmidgall, Xiaodong Yu, Ximeng Sun, Yusheng Su, Ze Wang, Zicheng Liu","submitted_at":"2025-01-08T01:58:42Z","abstract_excerpt":"Historically, scientific discovery has been a lengthy and costly process, demanding substantial time and resources from initial conception to final results. To accelerate scientific discovery, reduce research costs, and improve research quality, we introduce Agent Laboratory, an autonomous LLM-based framework capable of completing the entire research process. This framework accepts a human-provided research idea and progresses through three stages--literature review, experimentation, and report writing to produce comprehensive research outputs, including a code repository and a research report"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Agent Laboratory driven by o1-preview generates the best research outcomes; the generated machine learning code is able to achieve state-of-the-art performance compared to existing methods; human involvement significantly improves overall quality; and it achieves an 84% decrease in research expenses compared to previous autonomous research methods.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the human evaluators invited to assess the outputs provide unbiased, reproducible judgments and that the SOTA comparisons use current, fairly matched baselines without post-hoc selection of tasks or metrics.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Agent Laboratory is an autonomous LLM framework that completes end-to-end research from idea to report and code, with human feedback improving quality and cutting expenses by 84% while reaching competitive ML performance.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Agent Laboratory lets LLM agents carry out the full research process from idea to code repository and report.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"f741f1c1c64402d0ccfad8a34c0307e0d3cd5cb7121634fe6c6308abffad8c5c"},"source":{"id":"2501.04227","kind":"arxiv","version":2},"verdict":{"id":"7ae86f5b-3942-4b95-8577-59240bbe2a77","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-17T04:00:55.190729Z","strongest_claim":"Agent Laboratory driven by o1-preview generates the best research outcomes; the generated machine learning code is able to achieve state-of-the-art performance compared to existing methods; human involvement significantly improves overall quality; and it achieves an 84% decrease in research expenses compared to previous autonomous research methods.","one_line_summary":"Agent Laboratory is an autonomous LLM framework that completes end-to-end research from idea to report and code, with human feedback improving quality and cutting expenses by 84% while reaching competitive ML performance.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the human evaluators invited to assess the outputs provide unbiased, reproducible judgments and that the SOTA comparisons use current, fairly matched baselines without post-hoc selection of tasks or metrics.","pith_extraction_headline":"Agent Laboratory lets LLM agents carry out the full research process from idea to code repository and report."},"references":{"count":16,"sample":[{"doi":"","year":2024,"title":"Agentclinic: A multimodal agent benchmark to evaluate ai in simulated clinical environments","work_id":"418a0992-6f06-45f9-958d-cfdfc51c72af","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Results, and 8. Discussion. Just create the scaffolding as compilable latex. Your title should start with Research Report: (title here) where title here is a title you choose. For author write Agent L","work_id":"aba8cca0-24cc-4bf5-9d01-4cb1c9ac1a9e","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"This is not the place to critique the paper; the authors should generally agree with a well-written summary","work_id":"973affa8-48ee-42c5-8aed-54ee3b29f3d0","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Think of the things where a response from the author can change your opinion, clarify a confusion or address a limitation","work_id":"ec0635cf-b5d6-4eee-bea2-5b6afc0ba770","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Limitations: Have the authors adequately addressed the limitations and potential negative societal impact of their work? If not, please include constructive suggestions for improvement. In general, au","work_id":"5af2c341-8b04-4d89-9c0a-a6a77d543ef1","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":16,"snapshot_sha256":"5cb5ef159b48654057dfd418c42fd081cef5102f5accd9c214de6df2230a61cd","internal_anchors":0},"formal_canon":{"evidence_count":3,"snapshot_sha256":"10f192cd2985e917a0a2472b95c5759eaf34540ad65df0cf8e34766a71742e98"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"7ae86f5b-3942-4b95-8577-59240bbe2a77"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IgmRSzHP6uWPOFysGrWjGSlPvp4gG83/n74YN1+MApX/Gv7kUSrNfntoNA/T0zG+EtgleC0CNeRagjJxZNtFCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T22:50:28.259638Z"},"content_sha256":"c6f0502a34b062c47b4ff5025cf613db5ca82a557d864b10b733094f4e887388","schema_version":"1.0","event_id":"sha256:c6f0502a34b062c47b4ff5025cf613db5ca82a557d864b10b733094f4e887388"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2GB75OA7A6ATDAEEV63PIS5JCB/bundle.json","state_url":"https://pith.science/pith/2GB75OA7A6ATDAEEV63PIS5JCB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2GB75OA7A6ATDAEEV63PIS5JCB/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":"2026-05-19T22:50:28Z","links":{"resolver":"https://pith.science/pith/2GB75OA7A6ATDAEEV63PIS5JCB","bundle":"https://pith.science/pith/2GB75OA7A6ATDAEEV63PIS5JCB/bundle.json","state":"https://pith.science/pith/2GB75OA7A6ATDAEEV63PIS5JCB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2GB75OA7A6ATDAEEV63PIS5JCB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2GB75OA7A6ATDAEEV63PIS5JCB","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":"60134504e062ed509777419fbe85f761cfbfe5d36590d086ae3fb354f16fa935","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2025-01-08T01:58:42Z","title_canon_sha256":"2eea69674a838fac30e8504e6339ed62c38737ea128b881f59b4deb534b50845"},"schema_version":"1.0","source":{"id":"2501.04227","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.04227","created_at":"2026-05-17T23:38:15Z"},{"alias_kind":"arxiv_version","alias_value":"2501.04227v2","created_at":"2026-05-17T23:38:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.04227","created_at":"2026-05-17T23:38:15Z"},{"alias_kind":"pith_short_12","alias_value":"2GB75OA7A6AT","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"2GB75OA7A6ATDAEE","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"2GB75OA7","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:c6f0502a34b062c47b4ff5025cf613db5ca82a557d864b10b733094f4e887388","target":"graph","created_at":"2026-05-17T23:38:15Z","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":"Agent Laboratory driven by o1-preview generates the best research outcomes; the generated machine learning code is able to achieve state-of-the-art performance compared to existing methods; human involvement significantly improves overall quality; and it achieves an 84% decrease in research expenses compared to previous autonomous research methods."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the human evaluators invited to assess the outputs provide unbiased, reproducible judgments and that the SOTA comparisons use current, fairly matched baselines without post-hoc selection of tasks or metrics."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Agent Laboratory is an autonomous LLM framework that completes end-to-end research from idea to report and code, with human feedback improving quality and cutting expenses by 84% while reaching competitive ML performance."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Agent Laboratory lets LLM agents carry out the full research process from idea to code repository and report."}],"snapshot_sha256":"f741f1c1c64402d0ccfad8a34c0307e0d3cd5cb7121634fe6c6308abffad8c5c"},"formal_canon":{"evidence_count":3,"snapshot_sha256":"10f192cd2985e917a0a2472b95c5759eaf34540ad65df0cf8e34766a71742e98"},"paper":{"abstract_excerpt":"Historically, scientific discovery has been a lengthy and costly process, demanding substantial time and resources from initial conception to final results. To accelerate scientific discovery, reduce research costs, and improve research quality, we introduce Agent Laboratory, an autonomous LLM-based framework capable of completing the entire research process. This framework accepts a human-provided research idea and progresses through three stages--literature review, experimentation, and report writing to produce comprehensive research outputs, including a code repository and a research report","authors_text":"Emad Barsoum, Jialian Wu, Jiang Liu, Michael Moor, Samuel Schmidgall, Xiaodong Yu, Ximeng Sun, Yusheng Su, Ze Wang, Zicheng Liu","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"Agent Laboratory lets LLM agents carry out the full research process from idea to code repository and report.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2025-01-08T01:58:42Z","title":"Agent Laboratory: Using LLM Agents as Research Assistants"},"references":{"count":16,"internal_anchors":0,"resolved_work":16,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Agentclinic: A multimodal agent benchmark to evaluate ai in simulated clinical environments","work_id":"418a0992-6f06-45f9-958d-cfdfc51c72af","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Results, and 8. Discussion. Just create the scaffolding as compilable latex. Your title should start with Research Report: (title here) where title here is a title you choose. For author write Agent L","work_id":"aba8cca0-24cc-4bf5-9d01-4cb1c9ac1a9e","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"This is not the place to critique the paper; the authors should generally agree with a well-written summary","work_id":"973affa8-48ee-42c5-8aed-54ee3b29f3d0","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Think of the things where a response from the author can change your opinion, clarify a confusion or address a limitation","work_id":"ec0635cf-b5d6-4eee-bea2-5b6afc0ba770","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Limitations: Have the authors adequately addressed the limitations and potential negative societal impact of their work? If not, please include constructive suggestions for improvement. In general, au","work_id":"5af2c341-8b04-4d89-9c0a-a6a77d543ef1","year":null}],"snapshot_sha256":"5cb5ef159b48654057dfd418c42fd081cef5102f5accd9c214de6df2230a61cd"},"source":{"id":"2501.04227","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-17T04:00:55.190729Z","id":"7ae86f5b-3942-4b95-8577-59240bbe2a77","model_set":{"reader":"grok-4.3"},"one_line_summary":"Agent Laboratory is an autonomous LLM framework that completes end-to-end research from idea to report and code, with human feedback improving quality and cutting expenses by 84% while reaching competitive ML performance.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Agent Laboratory lets LLM agents carry out the full research process from idea to code repository and report.","strongest_claim":"Agent Laboratory driven by o1-preview generates the best research outcomes; the generated machine learning code is able to achieve state-of-the-art performance compared to existing methods; human involvement significantly improves overall quality; and it achieves an 84% decrease in research expenses compared to previous autonomous research methods.","weakest_assumption":"That the human evaluators invited to assess the outputs provide unbiased, reproducible judgments and that the SOTA comparisons use current, fairly matched baselines without post-hoc selection of tasks or metrics."}},"verdict_id":"7ae86f5b-3942-4b95-8577-59240bbe2a77"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:2efee8d9f2ef616be6c98810cc9329b2662f1c61cebabd07ec3e80e1c48f2794","target":"record","created_at":"2026-05-17T23:38:15Z","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":"60134504e062ed509777419fbe85f761cfbfe5d36590d086ae3fb354f16fa935","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2025-01-08T01:58:42Z","title_canon_sha256":"2eea69674a838fac30e8504e6339ed62c38737ea128b881f59b4deb534b50845"},"schema_version":"1.0","source":{"id":"2501.04227","kind":"arxiv","version":2}},"canonical_sha256":"d183feb81f0781318084afb6f44ba9105750a156f2ea9504bd3b7b2c132f5642","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d183feb81f0781318084afb6f44ba9105750a156f2ea9504bd3b7b2c132f5642","first_computed_at":"2026-05-17T23:38:15.177657Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:15.177657Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Vl4hFhsidrBvrrOAjdIdf6+Aw5QzlZxZQ6ePxNxoCQqnbjcx+siorcwgiacGE3ZsTw032MLAOiZ3w/tDQBWMBg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:15.178207Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.04227","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2efee8d9f2ef616be6c98810cc9329b2662f1c61cebabd07ec3e80e1c48f2794","sha256:c6f0502a34b062c47b4ff5025cf613db5ca82a557d864b10b733094f4e887388"],"state_sha256":"be49569f4807308cd5c353da980e19e60d3e90aff93d7f0d27415293e9ea5f2f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+NcJ5ZXsFeYTjP6POlJ2x4vawt5NGPiiAWV/+926UIMtFCaJ4c8eDtAf5yUkdxij7cWGXH+A64SxmbAJe2cfCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-19T22:50:28.262063Z","bundle_sha256":"0d033d05c8df5f52925309cbb37a7f106cffd0838b5a15d76119e3d364deec92"}}