{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SFKGJCCNROJBF7NW2LA2HNDLPG","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":"de9c91e38b76d35ffd5999729f1eacf7a7918ee295888487b60b482cd665b58c","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-17T15:40:03Z","title_canon_sha256":"dff8a591f44d1b00f77aef9cda70de244e445e44a363d247ebf49ba8881a839d"},"schema_version":"1.0","source":{"id":"2505.12058","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.12058","created_at":"2026-07-05T11:04:57Z"},{"alias_kind":"arxiv_version","alias_value":"2505.12058v1","created_at":"2026-07-05T11:04:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12058","created_at":"2026-07-05T11:04:57Z"},{"alias_kind":"pith_short_12","alias_value":"SFKGJCCNROJB","created_at":"2026-07-05T11:04:57Z"},{"alias_kind":"pith_short_16","alias_value":"SFKGJCCNROJBF7NW","created_at":"2026-07-05T11:04:57Z"},{"alias_kind":"pith_short_8","alias_value":"SFKGJCCN","created_at":"2026-07-05T11:04:57Z"}],"graph_snapshots":[{"event_id":"sha256:f330b878a8135337e742300d178a0a7bce61fdab2ddf85b0a7cff6075fcbe56b","target":"graph","created_at":"2026-07-05T11:04:57Z","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/2505.12058/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tiny QA Benchmark++ (TQB++) presents an ultra-lightweight, multilingual smoke-test suite designed to give large-language-model (LLM) pipelines a unit-test style safety net dataset that runs in seconds with minimal cost. Born out of the tight feedback-loop demands building the Comet Opik prompt-optimization SDK, where waiting on heavyweight benchmarks breaks developer flow. TQB++ couples a 52-item English gold set (less than 20 kB) with a tiny synthetic-data generator pypi package built on provider-agnostic LiteLLM. The generator lets practitioners mint their own tiny packs in any language, dom","authors_text":"Vincent Koc","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-17T15:40:03Z","title":"Tiny QA Benchmark++: Ultra-Lightweight, Synthetic Multilingual Dataset Generation & Smoke-Tests for Continuous LLM Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12058","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":"sha256:41e3b3fc4bedfe3b83657f5ef814cb4d3ea806cb2a5b9ee5f475e7f45627baf1","target":"record","created_at":"2026-07-05T11:04:57Z","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":"de9c91e38b76d35ffd5999729f1eacf7a7918ee295888487b60b482cd665b58c","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-17T15:40:03Z","title_canon_sha256":"dff8a591f44d1b00f77aef9cda70de244e445e44a363d247ebf49ba8881a839d"},"schema_version":"1.0","source":{"id":"2505.12058","kind":"arxiv","version":1}},"canonical_sha256":"915464884d8b9212fdb6d2c1a3b46b798a74749fcb8b042b34e51ca58c069bb9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"915464884d8b9212fdb6d2c1a3b46b798a74749fcb8b042b34e51ca58c069bb9","first_computed_at":"2026-07-05T11:04:57.762803Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:04:57.762803Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"moYVTnzc1ZOTz/EzCAtnOoBxGHYwoL7IsAZrWBSusoIhrBtcZ01fD0onCOYfReMNdBso+JXaZNSPU1KqFPGiDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:04:57.763276Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.12058","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:41e3b3fc4bedfe3b83657f5ef814cb4d3ea806cb2a5b9ee5f475e7f45627baf1","sha256:f330b878a8135337e742300d178a0a7bce61fdab2ddf85b0a7cff6075fcbe56b"],"state_sha256":"3548c6edaea851c2636547b7274d583bc41475477e9df50353aa0ebf5cf56838"}