{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:U6KBUO6ZMR3CH3KRB3X5QJA6CQ","short_pith_number":"pith:U6KBUO6Z","schema_version":"1.0","canonical_sha256":"a7941a3bd9647623ed510eefd8241e14121825d9b745a4a3b7c838fb3acaa1a7","source":{"kind":"arxiv","id":"2607.16617","version":1},"attestation_state":"computed","paper":{"title":"DataFlow-Harness: A Grounded Code-Agent Platform for Constructing Editable LLM Data Pipelines","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Chengyu Shen, Hao Liang, Runming He, Wentao Zhang, Xiaochen Ma, Zhen Hao Wong, Zimo Meng","submitted_at":"2026-07-18T03:30:19Z","abstract_excerpt":"Large language models (LLMs) are increasingly used to automate data-processing workflows, yet coding agents typically produce scripts that are not automatically materialized as persistent, editable platform artifacts. We call this disconnect the \\textit{NL2Pipeline gap}. To bridge it, we introduce \\textsc{DataFlow-Harness}, a platform that guides an LLM agent to construct platform-native directed acyclic graphs (DAGs) through typed, incremental mutations rather than free-form scripts. The platform combines \\textsc{DataFlow-Skills} for procedural guidance, a Model Context Protocol (MCP) layer t"},"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":"2607.16617","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-07-18T03:30:19Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a8a61769c59684d6690f252178927a5c062e660feed464dca7a6393074b2bb6c","abstract_canon_sha256":"cd7c4d8413fd1ea6230093450804197d56d506a06dd7de16c90b5b1073ac8a1f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T00:20:28.572471Z","signature_b64":"BpcKw28mo6V+k5BMSGkdJhsuzMe7yXNrH3jJtmem15rdmAPLsGzPqJcvMg0Y9dAJ5Wr+MEhsNBhpfxvFMb0hDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7941a3bd9647623ed510eefd8241e14121825d9b745a4a3b7c838fb3acaa1a7","last_reissued_at":"2026-07-21T00:20:28.571610Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T00:20:28.571610Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DataFlow-Harness: A Grounded Code-Agent Platform for Constructing Editable LLM Data Pipelines","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Chengyu Shen, Hao Liang, Runming He, Wentao Zhang, Xiaochen Ma, Zhen Hao Wong, Zimo Meng","submitted_at":"2026-07-18T03:30:19Z","abstract_excerpt":"Large language models (LLMs) are increasingly used to automate data-processing workflows, yet coding agents typically produce scripts that are not automatically materialized as persistent, editable platform artifacts. We call this disconnect the \\textit{NL2Pipeline gap}. To bridge it, we introduce \\textsc{DataFlow-Harness}, a platform that guides an LLM agent to construct platform-native directed acyclic graphs (DAGs) through typed, incremental mutations rather than free-form scripts. The platform combines \\textsc{DataFlow-Skills} for procedural guidance, a Model Context Protocol (MCP) layer t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.16617","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/2607.16617/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":"2607.16617","created_at":"2026-07-21T00:20:28.572051+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.16617v1","created_at":"2026-07-21T00:20:28.572051+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.16617","created_at":"2026-07-21T00:20:28.572051+00:00"},{"alias_kind":"pith_short_12","alias_value":"U6KBUO6ZMR3C","created_at":"2026-07-21T00:20:28.572051+00:00"},{"alias_kind":"pith_short_16","alias_value":"U6KBUO6ZMR3CH3KR","created_at":"2026-07-21T00:20:28.572051+00:00"},{"alias_kind":"pith_short_8","alias_value":"U6KBUO6Z","created_at":"2026-07-21T00:20:28.572051+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/U6KBUO6ZMR3CH3KRB3X5QJA6CQ","json":"https://pith.science/pith/U6KBUO6ZMR3CH3KRB3X5QJA6CQ.json","graph_json":"https://pith.science/api/pith-number/U6KBUO6ZMR3CH3KRB3X5QJA6CQ/graph.json","events_json":"https://pith.science/api/pith-number/U6KBUO6ZMR3CH3KRB3X5QJA6CQ/events.json","paper":"https://pith.science/paper/U6KBUO6Z"},"agent_actions":{"view_html":"https://pith.science/pith/U6KBUO6ZMR3CH3KRB3X5QJA6CQ","download_json":"https://pith.science/pith/U6KBUO6ZMR3CH3KRB3X5QJA6CQ.json","view_paper":"https://pith.science/paper/U6KBUO6Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.16617&json=true","fetch_graph":"https://pith.science/api/pith-number/U6KBUO6ZMR3CH3KRB3X5QJA6CQ/graph.json","fetch_events":"https://pith.science/api/pith-number/U6KBUO6ZMR3CH3KRB3X5QJA6CQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U6KBUO6ZMR3CH3KRB3X5QJA6CQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U6KBUO6ZMR3CH3KRB3X5QJA6CQ/action/storage_attestation","attest_author":"https://pith.science/pith/U6KBUO6ZMR3CH3KRB3X5QJA6CQ/action/author_attestation","sign_citation":"https://pith.science/pith/U6KBUO6ZMR3CH3KRB3X5QJA6CQ/action/citation_signature","submit_replication":"https://pith.science/pith/U6KBUO6ZMR3CH3KRB3X5QJA6CQ/action/replication_record"}},"created_at":"2026-07-21T00:20:28.572051+00:00","updated_at":"2026-07-21T00:20:28.572051+00:00"}