{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GJA6ZL7MFRITKNETC764XBWM5T","short_pith_number":"pith:GJA6ZL7M","schema_version":"1.0","canonical_sha256":"3241ecafec2c5135349317fdcb86ccecc544c07a4a501fbb2ca3b658a1bc7fa7","source":{"kind":"arxiv","id":"2304.14979","version":2},"attestation_state":"computed","paper":{"title":"MLCopilot: Unleashing the Power of Large Language Models in Solving Machine Learning Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Dongsheng Li, Kan Ren, Lei Zhang, Yuge Zhang, Yuqing Yang","submitted_at":"2023-04-28T17:03:57Z","abstract_excerpt":"The field of machine learning (ML) has gained widespread adoption, leading to significant demand for adapting ML to specific scenarios, which is yet expensive and non-trivial. The predominant approaches towards the automation of solving ML tasks (e.g., AutoML) are often time-consuming and hard to understand for human developers. In contrast, though human engineers have the incredible ability to understand tasks and reason about solutions, their experience and knowledge are often sparse and difficult to utilize by quantitative approaches. In this paper, we aim to bridge the gap between machine "},"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":"2304.14979","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-28T17:03:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0b34be70df42bf51626d597c19f9746d7e65a73ababa93f6db2ddf0d36dd8624","abstract_canon_sha256":"9b32a9309b1e3fe8fad3a2bdc2e743327573378a77bea8f08bf29ce066133b1b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:46:17.569485Z","signature_b64":"sUEUeV2lPB/KetZm9t3jLgCiexU1cVrTrvy+Gezk3uyWr92KYSmwMd7VU/LEVMoI7fVP+CS13xwICBLdRwjtBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3241ecafec2c5135349317fdcb86ccecc544c07a4a501fbb2ca3b658a1bc7fa7","last_reissued_at":"2026-07-05T07:46:17.568979Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:46:17.568979Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MLCopilot: Unleashing the Power of Large Language Models in Solving Machine Learning Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Dongsheng Li, Kan Ren, Lei Zhang, Yuge Zhang, Yuqing Yang","submitted_at":"2023-04-28T17:03:57Z","abstract_excerpt":"The field of machine learning (ML) has gained widespread adoption, leading to significant demand for adapting ML to specific scenarios, which is yet expensive and non-trivial. The predominant approaches towards the automation of solving ML tasks (e.g., AutoML) are often time-consuming and hard to understand for human developers. In contrast, though human engineers have the incredible ability to understand tasks and reason about solutions, their experience and knowledge are often sparse and difficult to utilize by quantitative approaches. In this paper, we aim to bridge the gap between machine "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.14979","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/2304.14979/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":"2304.14979","created_at":"2026-07-05T07:46:17.569037+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.14979v2","created_at":"2026-07-05T07:46:17.569037+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.14979","created_at":"2026-07-05T07:46:17.569037+00:00"},{"alias_kind":"pith_short_12","alias_value":"GJA6ZL7MFRIT","created_at":"2026-07-05T07:46:17.569037+00:00"},{"alias_kind":"pith_short_16","alias_value":"GJA6ZL7MFRITKNET","created_at":"2026-07-05T07:46:17.569037+00:00"},{"alias_kind":"pith_short_8","alias_value":"GJA6ZL7M","created_at":"2026-07-05T07:46:17.569037+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.12376","citing_title":"ProfiliTable: Profiling-Driven Tabular Data Processing via Agentic Workflows","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12376","citing_title":"ProfiliTable: Profiling-Driven Tabular Data Processing via Agentic Workflows","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14655","citing_title":"AgentGA: Evolving Code Solutions in Agent-Seed Space","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14655","citing_title":"AgentGA: Evolving Code Solutions in Agent-Seed Space","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GJA6ZL7MFRITKNETC764XBWM5T","json":"https://pith.science/pith/GJA6ZL7MFRITKNETC764XBWM5T.json","graph_json":"https://pith.science/api/pith-number/GJA6ZL7MFRITKNETC764XBWM5T/graph.json","events_json":"https://pith.science/api/pith-number/GJA6ZL7MFRITKNETC764XBWM5T/events.json","paper":"https://pith.science/paper/GJA6ZL7M"},"agent_actions":{"view_html":"https://pith.science/pith/GJA6ZL7MFRITKNETC764XBWM5T","download_json":"https://pith.science/pith/GJA6ZL7MFRITKNETC764XBWM5T.json","view_paper":"https://pith.science/paper/GJA6ZL7M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.14979&json=true","fetch_graph":"https://pith.science/api/pith-number/GJA6ZL7MFRITKNETC764XBWM5T/graph.json","fetch_events":"https://pith.science/api/pith-number/GJA6ZL7MFRITKNETC764XBWM5T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GJA6ZL7MFRITKNETC764XBWM5T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GJA6ZL7MFRITKNETC764XBWM5T/action/storage_attestation","attest_author":"https://pith.science/pith/GJA6ZL7MFRITKNETC764XBWM5T/action/author_attestation","sign_citation":"https://pith.science/pith/GJA6ZL7MFRITKNETC764XBWM5T/action/citation_signature","submit_replication":"https://pith.science/pith/GJA6ZL7MFRITKNETC764XBWM5T/action/replication_record"}},"created_at":"2026-07-05T07:46:17.569037+00:00","updated_at":"2026-07-05T07:46:17.569037+00:00"}