{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LXZXW7IK5PQUU5XHOP677Y7U7U","short_pith_number":"pith:LXZXW7IK","schema_version":"1.0","canonical_sha256":"5df37b7d0aebe14a76e773fdffe3f4fd129030d097cac8978cd1887bda10241b","source":{"kind":"arxiv","id":"2607.29250","version":1},"attestation_state":"computed","paper":{"title":"Data Turnstile: A Scalable Open Framework for Function-Calling Data Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Goutham Ramakrishnan, Megha Sharma","submitted_at":"2026-07-31T10:21:36Z","abstract_excerpt":"Small language models (SLMs) are attractive for agentic deployment due to low latency, reduced cost, and on-device privacy, yet they struggle with tool-use tasks where training data is scarce and noisy. Unlike larger models, SLMs cannot compensate for low-quality supervision through sheer capacity, making data quality the critical bottleneck. We present Data Turnstile, an open-source framework that takes user-defined API specifications and generates high-quality synthetic training data for function calling. Turnstile decomposes multi-turn tool-use interactions into constrained, stepwise genera"},"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":"2607.29250","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-31T10:21:36Z","cross_cats_sorted":[],"title_canon_sha256":"ae89b51bf2fc690944cf41bba60cdbea10bc1ae89002144571b5297af72d8895","abstract_canon_sha256":"bf704f769a03a9e8d17398317b3e5f615cddd16299c31e26dbe963302123c224"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-03T01:22:27.187550Z","signature_b64":"tkImn8U3zkF4oy2f7ukOBH8yKeWbIlZm9KZ7uErT558jA/Hx31ZuMvdmjiYgQb0qUS8MnbCW9FiSwvBuYAQ6Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5df37b7d0aebe14a76e773fdffe3f4fd129030d097cac8978cd1887bda10241b","last_reissued_at":"2026-08-03T01:22:27.186004Z","signature_status":"signed_v1","first_computed_at":"2026-08-03T01:22:27.186004Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data Turnstile: A Scalable Open Framework for Function-Calling Data Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Goutham Ramakrishnan, Megha Sharma","submitted_at":"2026-07-31T10:21:36Z","abstract_excerpt":"Small language models (SLMs) are attractive for agentic deployment due to low latency, reduced cost, and on-device privacy, yet they struggle with tool-use tasks where training data is scarce and noisy. Unlike larger models, SLMs cannot compensate for low-quality supervision through sheer capacity, making data quality the critical bottleneck. We present Data Turnstile, an open-source framework that takes user-defined API specifications and generates high-quality synthetic training data for function calling. Turnstile decomposes multi-turn tool-use interactions into constrained, stepwise genera"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.29250","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/2607.29250/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":"2607.29250","created_at":"2026-08-03T01:22:27.186899+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.29250v1","created_at":"2026-08-03T01:22:27.186899+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.29250","created_at":"2026-08-03T01:22:27.186899+00:00"},{"alias_kind":"pith_short_12","alias_value":"LXZXW7IK5PQU","created_at":"2026-08-03T01:22:27.186899+00:00"},{"alias_kind":"pith_short_16","alias_value":"LXZXW7IK5PQUU5XH","created_at":"2026-08-03T01:22:27.186899+00:00"},{"alias_kind":"pith_short_8","alias_value":"LXZXW7IK","created_at":"2026-08-03T01:22:27.186899+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/LXZXW7IK5PQUU5XHOP677Y7U7U","json":"https://pith.science/pith/LXZXW7IK5PQUU5XHOP677Y7U7U.json","graph_json":"https://pith.science/api/pith-number/LXZXW7IK5PQUU5XHOP677Y7U7U/graph.json","events_json":"https://pith.science/api/pith-number/LXZXW7IK5PQUU5XHOP677Y7U7U/events.json","paper":"https://pith.science/paper/LXZXW7IK"},"agent_actions":{"view_html":"https://pith.science/pith/LXZXW7IK5PQUU5XHOP677Y7U7U","download_json":"https://pith.science/pith/LXZXW7IK5PQUU5XHOP677Y7U7U.json","view_paper":"https://pith.science/paper/LXZXW7IK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.29250&json=true","fetch_graph":"https://pith.science/api/pith-number/LXZXW7IK5PQUU5XHOP677Y7U7U/graph.json","fetch_events":"https://pith.science/api/pith-number/LXZXW7IK5PQUU5XHOP677Y7U7U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LXZXW7IK5PQUU5XHOP677Y7U7U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LXZXW7IK5PQUU5XHOP677Y7U7U/action/storage_attestation","attest_author":"https://pith.science/pith/LXZXW7IK5PQUU5XHOP677Y7U7U/action/author_attestation","sign_citation":"https://pith.science/pith/LXZXW7IK5PQUU5XHOP677Y7U7U/action/citation_signature","submit_replication":"https://pith.science/pith/LXZXW7IK5PQUU5XHOP677Y7U7U/action/replication_record"}},"created_at":"2026-08-03T01:22:27.186899+00:00","updated_at":"2026-08-03T01:22:27.186899+00:00"}