{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3FERRCFBIL46SERMHQ3246IPHW","short_pith_number":"pith:3FERRCFB","schema_version":"1.0","canonical_sha256":"d9491888a142f9e9122c3c37ae790f3d9f62048dcca7e3c9b11c1ab3aabf3678","source":{"kind":"arxiv","id":"2606.01185","version":1},"attestation_state":"computed","paper":{"title":"\"Skill issues'': data-centric optimization of lakehouse agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Davide Ghilardi, Giacomo Piccinini, Jacopo Tagliabue, Nicole Rose Schneider","submitted_at":"2026-05-31T11:58:04Z","abstract_excerpt":"Coding agents are becoming users of data infrastructure, but their success depends not only on model quality: it also depends on the skills and environment files that teach agents how to use a system. We study how to optimize these artifacts for agents operating on a branching lakehouse, Bauplan. In our setting, headless APIs and Git-like data primitives expose data workflows through code, branches, commits, and merges. Our central observation is that a branching lakehouse turns data-agent evaluation from an output-matching problem into a state-verification problem: agent-generated pipeline co"},"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":"2606.01185","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-31T11:58:04Z","cross_cats_sorted":[],"title_canon_sha256":"e4cc9b55bd3182a8390fd06f205615994fafc39e4d5e0a8a12f44e0f094d4a78","abstract_canon_sha256":"a075e66cb464979aa146463553d31c59c844bccba08097604df09f9bc21dda8c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:26.053025Z","signature_b64":"GNDesWx05gKCNfWyyPFigjDHHjF4jvkubl4hg28oWxu8NAHYzl4exc/YeAeGAeoS2Y0/Ko6Z6kkn3X/glidWAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9491888a142f9e9122c3c37ae790f3d9f62048dcca7e3c9b11c1ab3aabf3678","last_reissued_at":"2026-06-02T02:04:26.052614Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:26.052614Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"\"Skill issues'': data-centric optimization of lakehouse agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Davide Ghilardi, Giacomo Piccinini, Jacopo Tagliabue, Nicole Rose Schneider","submitted_at":"2026-05-31T11:58:04Z","abstract_excerpt":"Coding agents are becoming users of data infrastructure, but their success depends not only on model quality: it also depends on the skills and environment files that teach agents how to use a system. We study how to optimize these artifacts for agents operating on a branching lakehouse, Bauplan. In our setting, headless APIs and Git-like data primitives expose data workflows through code, branches, commits, and merges. Our central observation is that a branching lakehouse turns data-agent evaluation from an output-matching problem into a state-verification problem: agent-generated pipeline co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01185","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/2606.01185/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":"2606.01185","created_at":"2026-06-02T02:04:26.052674+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.01185v1","created_at":"2026-06-02T02:04:26.052674+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01185","created_at":"2026-06-02T02:04:26.052674+00:00"},{"alias_kind":"pith_short_12","alias_value":"3FERRCFBIL46","created_at":"2026-06-02T02:04:26.052674+00:00"},{"alias_kind":"pith_short_16","alias_value":"3FERRCFBIL46SERM","created_at":"2026-06-02T02:04:26.052674+00:00"},{"alias_kind":"pith_short_8","alias_value":"3FERRCFB","created_at":"2026-06-02T02:04:26.052674+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/3FERRCFBIL46SERMHQ3246IPHW","json":"https://pith.science/pith/3FERRCFBIL46SERMHQ3246IPHW.json","graph_json":"https://pith.science/api/pith-number/3FERRCFBIL46SERMHQ3246IPHW/graph.json","events_json":"https://pith.science/api/pith-number/3FERRCFBIL46SERMHQ3246IPHW/events.json","paper":"https://pith.science/paper/3FERRCFB"},"agent_actions":{"view_html":"https://pith.science/pith/3FERRCFBIL46SERMHQ3246IPHW","download_json":"https://pith.science/pith/3FERRCFBIL46SERMHQ3246IPHW.json","view_paper":"https://pith.science/paper/3FERRCFB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.01185&json=true","fetch_graph":"https://pith.science/api/pith-number/3FERRCFBIL46SERMHQ3246IPHW/graph.json","fetch_events":"https://pith.science/api/pith-number/3FERRCFBIL46SERMHQ3246IPHW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3FERRCFBIL46SERMHQ3246IPHW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3FERRCFBIL46SERMHQ3246IPHW/action/storage_attestation","attest_author":"https://pith.science/pith/3FERRCFBIL46SERMHQ3246IPHW/action/author_attestation","sign_citation":"https://pith.science/pith/3FERRCFBIL46SERMHQ3246IPHW/action/citation_signature","submit_replication":"https://pith.science/pith/3FERRCFBIL46SERMHQ3246IPHW/action/replication_record"}},"created_at":"2026-06-02T02:04:26.052674+00:00","updated_at":"2026-06-02T02:04:26.052674+00:00"}