{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LXZXW7IK5PQUU5XHOP677Y7U7U","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"bf704f769a03a9e8d17398317b3e5f615cddd16299c31e26dbe963302123c224","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-31T10:21:36Z","title_canon_sha256":"ae89b51bf2fc690944cf41bba60cdbea10bc1ae89002144571b5297af72d8895"},"schema_version":"1.0","source":{"id":"2607.29250","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.29250","created_at":"2026-08-03T01:22:27Z"},{"alias_kind":"arxiv_version","alias_value":"2607.29250v1","created_at":"2026-08-03T01:22:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.29250","created_at":"2026-08-03T01:22:27Z"},{"alias_kind":"pith_short_12","alias_value":"LXZXW7IK5PQU","created_at":"2026-08-03T01:22:27Z"},{"alias_kind":"pith_short_16","alias_value":"LXZXW7IK5PQUU5XH","created_at":"2026-08-03T01:22:27Z"},{"alias_kind":"pith_short_8","alias_value":"LXZXW7IK","created_at":"2026-08-03T01:22:27Z"}],"graph_snapshots":[{"event_id":"sha256:37448d61410396f434572c1ac98c95bb06c053264e7efae3a8badab5a854b748","target":"graph","created_at":"2026-08-03T01:22:27Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2607.29250/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Goutham Ramakrishnan, Megha Sharma","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-31T10:21:36Z","title":"Data Turnstile: A Scalable Open Framework for Function-Calling Data Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.29250","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:686961761d7e1ce1a5fa7ee262a0e4c9977d2a0225354513d88db9a9ff50b340","target":"record","created_at":"2026-08-03T01:22:27Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"bf704f769a03a9e8d17398317b3e5f615cddd16299c31e26dbe963302123c224","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-31T10:21:36Z","title_canon_sha256":"ae89b51bf2fc690944cf41bba60cdbea10bc1ae89002144571b5297af72d8895"},"schema_version":"1.0","source":{"id":"2607.29250","kind":"arxiv","version":1}},"canonical_sha256":"5df37b7d0aebe14a76e773fdffe3f4fd129030d097cac8978cd1887bda10241b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5df37b7d0aebe14a76e773fdffe3f4fd129030d097cac8978cd1887bda10241b","first_computed_at":"2026-08-03T01:22:27.186004Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-03T01:22:27.186004Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tkImn8U3zkF4oy2f7ukOBH8yKeWbIlZm9KZ7uErT558jA/Hx31ZuMvdmjiYgQb0qUS8MnbCW9FiSwvBuYAQ6Cw==","signature_status":"signed_v1","signed_at":"2026-08-03T01:22:27.187550Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.29250","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:686961761d7e1ce1a5fa7ee262a0e4c9977d2a0225354513d88db9a9ff50b340","sha256:37448d61410396f434572c1ac98c95bb06c053264e7efae3a8badab5a854b748"],"state_sha256":"a0d295e61a713573dc5427819893582c17ca099a00428552be8b583057dd1f37"}