{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SM44NDPAAFEASKTMQIMF3HVCLT","short_pith_number":"pith:SM44NDPA","schema_version":"1.0","canonical_sha256":"9339c68de00148092a6c82185d9ea25cf24ff6b30fb402e08aaf691c9d39335d","source":{"kind":"arxiv","id":"2507.13413","version":1},"attestation_state":"computed","paper":{"title":"LightAutoDS-Tab: Multi-AutoML Agentic System for Tabular Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aleksey Lapin, Andrey V. Savchenko, Dmitry Simakov, Igor Hromov, Mile Mitrovic, Nikolay O. Nikitin, Stanislav Chumakov","submitted_at":"2025-07-17T09:33:24Z","abstract_excerpt":"AutoML has advanced in handling complex tasks using the integration of LLMs, yet its efficiency remains limited by dependence on specific underlying tools. In this paper, we introduce LightAutoDS-Tab, a multi-AutoML agentic system for tasks with tabular data, which combines an LLM-based code generation with several AutoML tools. Our approach improves the flexibility and robustness of pipeline design, outperforming state-of-the-art open-source solutions on several data science tasks from Kaggle. The code of LightAutoDS-Tab is available in the open repository https://github.com/sb-ai-lab/LADS"},"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":"2507.13413","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-17T09:33:24Z","cross_cats_sorted":[],"title_canon_sha256":"84955190fca14dc797bef112b884c317b4405217f19b9048155ec112d7fad42a","abstract_canon_sha256":"803ba1c8f63bc551cf53b9576a07dc83203c483a27e707c2749e231354c29272"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:39:17.212548Z","signature_b64":"4Rkz39WbjD8nmD9rHpbZ6l9JPHPaCOlNnB7DBLa2SAQpF9B6AZVyUFa/CwBQUYn70AtoLpOhI3zaAasn6OZVDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9339c68de00148092a6c82185d9ea25cf24ff6b30fb402e08aaf691c9d39335d","last_reissued_at":"2026-07-05T11:39:17.211539Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:39:17.211539Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LightAutoDS-Tab: Multi-AutoML Agentic System for Tabular Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aleksey Lapin, Andrey V. Savchenko, Dmitry Simakov, Igor Hromov, Mile Mitrovic, Nikolay O. Nikitin, Stanislav Chumakov","submitted_at":"2025-07-17T09:33:24Z","abstract_excerpt":"AutoML has advanced in handling complex tasks using the integration of LLMs, yet its efficiency remains limited by dependence on specific underlying tools. In this paper, we introduce LightAutoDS-Tab, a multi-AutoML agentic system for tasks with tabular data, which combines an LLM-based code generation with several AutoML tools. Our approach improves the flexibility and robustness of pipeline design, outperforming state-of-the-art open-source solutions on several data science tasks from Kaggle. The code of LightAutoDS-Tab is available in the open repository https://github.com/sb-ai-lab/LADS"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.13413","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/2507.13413/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":"2507.13413","created_at":"2026-07-05T11:39:17.212057+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.13413v1","created_at":"2026-07-05T11:39:17.212057+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.13413","created_at":"2026-07-05T11:39:17.212057+00:00"},{"alias_kind":"pith_short_12","alias_value":"SM44NDPAAFEA","created_at":"2026-07-05T11:39:17.212057+00:00"},{"alias_kind":"pith_short_16","alias_value":"SM44NDPAAFEASKTM","created_at":"2026-07-05T11:39:17.212057+00:00"},{"alias_kind":"pith_short_8","alias_value":"SM44NDPA","created_at":"2026-07-05T11:39:17.212057+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SM44NDPAAFEASKTMQIMF3HVCLT","json":"https://pith.science/pith/SM44NDPAAFEASKTMQIMF3HVCLT.json","graph_json":"https://pith.science/api/pith-number/SM44NDPAAFEASKTMQIMF3HVCLT/graph.json","events_json":"https://pith.science/api/pith-number/SM44NDPAAFEASKTMQIMF3HVCLT/events.json","paper":"https://pith.science/paper/SM44NDPA"},"agent_actions":{"view_html":"https://pith.science/pith/SM44NDPAAFEASKTMQIMF3HVCLT","download_json":"https://pith.science/pith/SM44NDPAAFEASKTMQIMF3HVCLT.json","view_paper":"https://pith.science/paper/SM44NDPA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.13413&json=true","fetch_graph":"https://pith.science/api/pith-number/SM44NDPAAFEASKTMQIMF3HVCLT/graph.json","fetch_events":"https://pith.science/api/pith-number/SM44NDPAAFEASKTMQIMF3HVCLT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SM44NDPAAFEASKTMQIMF3HVCLT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SM44NDPAAFEASKTMQIMF3HVCLT/action/storage_attestation","attest_author":"https://pith.science/pith/SM44NDPAAFEASKTMQIMF3HVCLT/action/author_attestation","sign_citation":"https://pith.science/pith/SM44NDPAAFEASKTMQIMF3HVCLT/action/citation_signature","submit_replication":"https://pith.science/pith/SM44NDPAAFEASKTMQIMF3HVCLT/action/replication_record"}},"created_at":"2026-07-05T11:39:17.212057+00:00","updated_at":"2026-07-05T11:39:17.212057+00:00"}