{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4JBEBJELMMACG6WTFFFEP3OVZ2","short_pith_number":"pith:4JBEBJEL","schema_version":"1.0","canonical_sha256":"e24240a48b6300237ad3294a47edd5ce9f818d9e4c2b250e02bc5156a180243e","source":{"kind":"arxiv","id":"2505.13941","version":1},"attestation_state":"computed","paper":{"title":"MLZero: A Multi-Agent System for End-to-end Machine Learning Automation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.MA","authors_text":"Ali Caner Turkmen, Anirudh Dagar, Bernie Wang, Boran Han, Cuixiong Hu, George Karypis, Haoyang Fang, Huzefa Rangwala, Jiani Zhang, Nick Erickson, Su Zhou, Xiyuan Zhang, Ying Nian Wu","submitted_at":"2025-05-20T05:20:53Z","abstract_excerpt":"Existing AutoML systems have advanced the automation of machine learning (ML); however, they still require substantial manual configuration and expert input, particularly when handling multimodal data. We introduce MLZero, a novel multi-agent framework powered by Large Language Models (LLMs) that enables end-to-end ML automation across diverse data modalities with minimal human intervention. A cognitive perception module is first employed, transforming raw multimodal inputs into perceptual context that effectively guides the subsequent workflow. To address key limitations of LLMs, such as hall"},"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":"2505.13941","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2025-05-20T05:20:53Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"58fcd95b69ceff550d30f49dbe154da75e1851ee380475457d0a5e748d860e23","abstract_canon_sha256":"9a7b54d69f05ce3bdab2616b3a77f0176d37009fceac88dd24decf32869b449e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:53.419999Z","signature_b64":"helzMLmdwMkN5WGH+2omt1Sp+t5vKOC8vm1ro59/SJ+LFz6z5LhxVbL8zynYjlziJiDJYfBKrz/5nMuuCpF5Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e24240a48b6300237ad3294a47edd5ce9f818d9e4c2b250e02bc5156a180243e","last_reissued_at":"2026-07-05T11:05:53.419517Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:53.419517Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MLZero: A Multi-Agent System for End-to-end Machine Learning Automation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.MA","authors_text":"Ali Caner Turkmen, Anirudh Dagar, Bernie Wang, Boran Han, Cuixiong Hu, George Karypis, Haoyang Fang, Huzefa Rangwala, Jiani Zhang, Nick Erickson, Su Zhou, Xiyuan Zhang, Ying Nian Wu","submitted_at":"2025-05-20T05:20:53Z","abstract_excerpt":"Existing AutoML systems have advanced the automation of machine learning (ML); however, they still require substantial manual configuration and expert input, particularly when handling multimodal data. We introduce MLZero, a novel multi-agent framework powered by Large Language Models (LLMs) that enables end-to-end ML automation across diverse data modalities with minimal human intervention. A cognitive perception module is first employed, transforming raw multimodal inputs into perceptual context that effectively guides the subsequent workflow. To address key limitations of LLMs, such as hall"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13941","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/2505.13941/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":"2505.13941","created_at":"2026-07-05T11:05:53.419572+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.13941v1","created_at":"2026-07-05T11:05:53.419572+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13941","created_at":"2026-07-05T11:05:53.419572+00:00"},{"alias_kind":"pith_short_12","alias_value":"4JBEBJELMMAC","created_at":"2026-07-05T11:05:53.419572+00:00"},{"alias_kind":"pith_short_16","alias_value":"4JBEBJELMMACG6WT","created_at":"2026-07-05T11:05:53.419572+00:00"},{"alias_kind":"pith_short_8","alias_value":"4JBEBJEL","created_at":"2026-07-05T11:05:53.419572+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06473","citing_title":"MLEvolve: A Self-Evolving Framework for Automated Machine Learning Algorithm Discovery","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2509.21465","citing_title":"Talking Trees: Reasoning-Assisted Induction of Decision Trees for Tabular Data","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10906","citing_title":"DataMaster: Data-Centric Autonomous AI Research","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10906","citing_title":"DataMaster: Data-Centric Autonomous AI Research","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14655","citing_title":"AgentGA: Evolving Code Solutions in Agent-Seed Space","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14655","citing_title":"AgentGA: Evolving Code Solutions in Agent-Seed Space","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4JBEBJELMMACG6WTFFFEP3OVZ2","json":"https://pith.science/pith/4JBEBJELMMACG6WTFFFEP3OVZ2.json","graph_json":"https://pith.science/api/pith-number/4JBEBJELMMACG6WTFFFEP3OVZ2/graph.json","events_json":"https://pith.science/api/pith-number/4JBEBJELMMACG6WTFFFEP3OVZ2/events.json","paper":"https://pith.science/paper/4JBEBJEL"},"agent_actions":{"view_html":"https://pith.science/pith/4JBEBJELMMACG6WTFFFEP3OVZ2","download_json":"https://pith.science/pith/4JBEBJELMMACG6WTFFFEP3OVZ2.json","view_paper":"https://pith.science/paper/4JBEBJEL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.13941&json=true","fetch_graph":"https://pith.science/api/pith-number/4JBEBJELMMACG6WTFFFEP3OVZ2/graph.json","fetch_events":"https://pith.science/api/pith-number/4JBEBJELMMACG6WTFFFEP3OVZ2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4JBEBJELMMACG6WTFFFEP3OVZ2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4JBEBJELMMACG6WTFFFEP3OVZ2/action/storage_attestation","attest_author":"https://pith.science/pith/4JBEBJELMMACG6WTFFFEP3OVZ2/action/author_attestation","sign_citation":"https://pith.science/pith/4JBEBJELMMACG6WTFFFEP3OVZ2/action/citation_signature","submit_replication":"https://pith.science/pith/4JBEBJELMMACG6WTFFFEP3OVZ2/action/replication_record"}},"created_at":"2026-07-05T11:05:53.419572+00:00","updated_at":"2026-07-05T11:05:53.419572+00:00"}