{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:I56VINPQTSDKWNMFJPHN263NNB","short_pith_number":"pith:I56VINPQ","schema_version":"1.0","canonical_sha256":"477d5435f09c86ab35854bcedd7b6d684a2bc2d49f57106244b79b53814e3a57","source":{"kind":"arxiv","id":"2411.07464","version":2},"attestation_state":"computed","paper":{"title":"BudgetMLAgent: A Cost-Effective LLM Multi-Agent system for Automating Machine Learning Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.MA","authors_text":"Gautam Shroff, Lovekesh Vig, Manasi Patwardhan, Shubham Gandhi","submitted_at":"2024-11-12T00:57:30Z","abstract_excerpt":"Large Language Models (LLMs) excel in diverse applications including generation of code snippets, but often struggle with generating code for complex Machine Learning (ML) tasks. Although existing LLM single-agent based systems give varying performance depending on the task complexity, they purely rely on larger and expensive models such as GPT-4. Our investigation reveals that no-cost and low-cost models such as Gemini-Pro, Mixtral and CodeLlama perform far worse than GPT-4 in a single-agent setting. With the motivation of developing a cost-efficient LLM based solution for solving ML tasks, w"},"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":"2411.07464","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2024-11-12T00:57:30Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"7df0db8e867f02786957734f173a5fd45e7fc849526cd7c8c45cbb7c4a3d846b","abstract_canon_sha256":"b2c351ea28a4f8cd59511020088780f9629031265919848d2cf8d9c16b515e04"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:58:26.070950Z","signature_b64":"A20f4Wm+mrZbSYnasb0xj8gVEanrNIVBig678txunZojgsCFvPXieymyJ3GLEHGujntLLJ0LBwB0YjDyN2pRDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"477d5435f09c86ab35854bcedd7b6d684a2bc2d49f57106244b79b53814e3a57","last_reissued_at":"2026-07-05T09:58:26.070527Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:58:26.070527Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BudgetMLAgent: A Cost-Effective LLM Multi-Agent system for Automating Machine Learning Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.MA","authors_text":"Gautam Shroff, Lovekesh Vig, Manasi Patwardhan, Shubham Gandhi","submitted_at":"2024-11-12T00:57:30Z","abstract_excerpt":"Large Language Models (LLMs) excel in diverse applications including generation of code snippets, but often struggle with generating code for complex Machine Learning (ML) tasks. Although existing LLM single-agent based systems give varying performance depending on the task complexity, they purely rely on larger and expensive models such as GPT-4. Our investigation reveals that no-cost and low-cost models such as Gemini-Pro, Mixtral and CodeLlama perform far worse than GPT-4 in a single-agent setting. With the motivation of developing a cost-efficient LLM based solution for solving ML tasks, w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.07464","kind":"arxiv","version":2},"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/2411.07464/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":"2411.07464","created_at":"2026-07-05T09:58:26.070580+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.07464v2","created_at":"2026-07-05T09:58:26.070580+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.07464","created_at":"2026-07-05T09:58:26.070580+00:00"},{"alias_kind":"pith_short_12","alias_value":"I56VINPQTSDK","created_at":"2026-07-05T09:58:26.070580+00:00"},{"alias_kind":"pith_short_16","alias_value":"I56VINPQTSDKWNMF","created_at":"2026-07-05T09:58:26.070580+00:00"},{"alias_kind":"pith_short_8","alias_value":"I56VINPQ","created_at":"2026-07-05T09:58:26.070580+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17915","citing_title":"Trustworthy Self-Composable Big-Data-as-a-Service: An LLM-Orchestrated Multi-Agent Framework for Automated Data Engineering, AutoML, MLOps Deployment, and Drift-Aware Lifecycle Optimization","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I56VINPQTSDKWNMFJPHN263NNB","json":"https://pith.science/pith/I56VINPQTSDKWNMFJPHN263NNB.json","graph_json":"https://pith.science/api/pith-number/I56VINPQTSDKWNMFJPHN263NNB/graph.json","events_json":"https://pith.science/api/pith-number/I56VINPQTSDKWNMFJPHN263NNB/events.json","paper":"https://pith.science/paper/I56VINPQ"},"agent_actions":{"view_html":"https://pith.science/pith/I56VINPQTSDKWNMFJPHN263NNB","download_json":"https://pith.science/pith/I56VINPQTSDKWNMFJPHN263NNB.json","view_paper":"https://pith.science/paper/I56VINPQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.07464&json=true","fetch_graph":"https://pith.science/api/pith-number/I56VINPQTSDKWNMFJPHN263NNB/graph.json","fetch_events":"https://pith.science/api/pith-number/I56VINPQTSDKWNMFJPHN263NNB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I56VINPQTSDKWNMFJPHN263NNB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I56VINPQTSDKWNMFJPHN263NNB/action/storage_attestation","attest_author":"https://pith.science/pith/I56VINPQTSDKWNMFJPHN263NNB/action/author_attestation","sign_citation":"https://pith.science/pith/I56VINPQTSDKWNMFJPHN263NNB/action/citation_signature","submit_replication":"https://pith.science/pith/I56VINPQTSDKWNMFJPHN263NNB/action/replication_record"}},"created_at":"2026-07-05T09:58:26.070580+00:00","updated_at":"2026-07-05T09:58:26.070580+00:00"}