{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BMPDYASTODREJNYCJYQC3FBTKC","short_pith_number":"pith:BMPDYAST","schema_version":"1.0","canonical_sha256":"0b1e3c025370e244b7024e202d943350ae30e0e37f1daa884acf12eef55bdff7","source":{"kind":"arxiv","id":"2606.03841","version":1},"attestation_state":"computed","paper":{"title":"EvoDS: Self-Evolving Autonomous Data Science Agent with Skill Learning and Context Management","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Fan Liu, Hao Liu, Yansong Ning, Zherui Yang","submitted_at":"2026-06-02T16:20:58Z","abstract_excerpt":"Recent progress in Large Language Model (LLM) agents has enabled promising advances in automated data science. However, existing approaches remain fundamentally limited by their static action sets and lack of principled long-horizon context management, hindering their ability to accumulate reusable experience across tasks and operate reliably in multi-stage, iterative data science pipelines. To address these challenges, we introduce EvoDS, a self-evolving autonomous data science agent that learns to expand its skills and adaptively managing long-term context through agentic reinforcement learn"},"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":"2606.03841","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-02T16:20:58Z","cross_cats_sorted":[],"title_canon_sha256":"115fc5625507eba052d4ef1c53dc19b9c3f06e3b4ac2583cf7c0d6c00c1b0a39","abstract_canon_sha256":"d4645f195c1ae4d9f495aced752fe6c6625f2ee999a062fe759181922d03186b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T02:06:03.872288Z","signature_b64":"Pr2n2t4vegvXmFZ4CrzE1FKgFQAx2FzEyr6SpcBTZKMupWzjEoGiqPMy/MNBuzRlwhc27N7NVxbeue1dRalmAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0b1e3c025370e244b7024e202d943350ae30e0e37f1daa884acf12eef55bdff7","last_reissued_at":"2026-06-03T02:06:03.871910Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T02:06:03.871910Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EvoDS: Self-Evolving Autonomous Data Science Agent with Skill Learning and Context Management","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Fan Liu, Hao Liu, Yansong Ning, Zherui Yang","submitted_at":"2026-06-02T16:20:58Z","abstract_excerpt":"Recent progress in Large Language Model (LLM) agents has enabled promising advances in automated data science. However, existing approaches remain fundamentally limited by their static action sets and lack of principled long-horizon context management, hindering their ability to accumulate reusable experience across tasks and operate reliably in multi-stage, iterative data science pipelines. To address these challenges, we introduce EvoDS, a self-evolving autonomous data science agent that learns to expand its skills and adaptively managing long-term context through agentic reinforcement learn"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03841","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/2606.03841/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":"2606.03841","created_at":"2026-06-03T02:06:03.871966+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.03841v1","created_at":"2026-06-03T02:06:03.871966+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03841","created_at":"2026-06-03T02:06:03.871966+00:00"},{"alias_kind":"pith_short_12","alias_value":"BMPDYASTODRE","created_at":"2026-06-03T02:06:03.871966+00:00"},{"alias_kind":"pith_short_16","alias_value":"BMPDYASTODREJNYC","created_at":"2026-06-03T02:06:03.871966+00:00"},{"alias_kind":"pith_short_8","alias_value":"BMPDYAST","created_at":"2026-06-03T02:06:03.871966+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/BMPDYASTODREJNYCJYQC3FBTKC","json":"https://pith.science/pith/BMPDYASTODREJNYCJYQC3FBTKC.json","graph_json":"https://pith.science/api/pith-number/BMPDYASTODREJNYCJYQC3FBTKC/graph.json","events_json":"https://pith.science/api/pith-number/BMPDYASTODREJNYCJYQC3FBTKC/events.json","paper":"https://pith.science/paper/BMPDYAST"},"agent_actions":{"view_html":"https://pith.science/pith/BMPDYASTODREJNYCJYQC3FBTKC","download_json":"https://pith.science/pith/BMPDYASTODREJNYCJYQC3FBTKC.json","view_paper":"https://pith.science/paper/BMPDYAST","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.03841&json=true","fetch_graph":"https://pith.science/api/pith-number/BMPDYASTODREJNYCJYQC3FBTKC/graph.json","fetch_events":"https://pith.science/api/pith-number/BMPDYASTODREJNYCJYQC3FBTKC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BMPDYASTODREJNYCJYQC3FBTKC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BMPDYASTODREJNYCJYQC3FBTKC/action/storage_attestation","attest_author":"https://pith.science/pith/BMPDYASTODREJNYCJYQC3FBTKC/action/author_attestation","sign_citation":"https://pith.science/pith/BMPDYASTODREJNYCJYQC3FBTKC/action/citation_signature","submit_replication":"https://pith.science/pith/BMPDYASTODREJNYCJYQC3FBTKC/action/replication_record"}},"created_at":"2026-06-03T02:06:03.871966+00:00","updated_at":"2026-06-03T02:06:03.871966+00:00"}