{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JJ6A6DLN7B5BXROUPBB7SOEBY5","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":"9f63309d8c95261f7f7362c7b764071103da72af2e5dc898bebafd2beb12af41","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-07-26T02:49:56Z","title_canon_sha256":"ba914f30c7ab29e497cb412f8bf809de05b7c1d1e99fbf8b9c208cd3c93ed165"},"schema_version":"1.0","source":{"id":"2607.23425","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.23425","created_at":"2026-07-28T01:22:52Z"},{"alias_kind":"arxiv_version","alias_value":"2607.23425v1","created_at":"2026-07-28T01:22:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.23425","created_at":"2026-07-28T01:22:52Z"},{"alias_kind":"pith_short_12","alias_value":"JJ6A6DLN7B5B","created_at":"2026-07-28T01:22:52Z"},{"alias_kind":"pith_short_16","alias_value":"JJ6A6DLN7B5BXROU","created_at":"2026-07-28T01:22:52Z"},{"alias_kind":"pith_short_8","alias_value":"JJ6A6DLN","created_at":"2026-07-28T01:22:52Z"}],"graph_snapshots":[{"event_id":"sha256:baa35d0925dc849a9097e2556d6601d4fe79068aeb4620706f4c09cb6081ae5b","target":"graph","created_at":"2026-07-28T01:22:52Z","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/2607.23425/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models increasingly write TLA$^{+}$ formal specifications from natural-language descriptions, but progress is hard to measure: existing resources grade by resemblance to a reference or by whether the output parses, neither of which shows correctness. We present TLA$^{+}$-Bench, a dataset and benchmark that grades by execution. Every gold specification ships a configuration the TLA$^{+}$ model checker runs over the full reachable state space, deciding exactly whether the specification holds the properties that configuration names. The dataset holds 403 model-checked gold and 897 ","authors_text":"Anisa Ramos, Arslan Bisharat, Beatriz Santos, Brian Ortiz, Eric Spencer, George K. Thiruvathukal, Khushboo Bhadauria, Konstantin L\\\"aufer, Mohammed Abuhamad, Mujtaba Nazari, TaiNing Wang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-07-26T02:49:56Z","title":"TLA$^{+}$-Bench: An Execution-Grounded Benchmark and Dataset for Natural-Language to TLA+ Specification Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.23425","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":"sha256:9a268c61f91710b988ad5b7893b48928e5eb8c2fed051bca700866ba689c5f49","target":"record","created_at":"2026-07-28T01:22:52Z","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":"9f63309d8c95261f7f7362c7b764071103da72af2e5dc898bebafd2beb12af41","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-07-26T02:49:56Z","title_canon_sha256":"ba914f30c7ab29e497cb412f8bf809de05b7c1d1e99fbf8b9c208cd3c93ed165"},"schema_version":"1.0","source":{"id":"2607.23425","kind":"arxiv","version":1}},"canonical_sha256":"4a7c0f0d6df87a1bc5d47843f93881c75ced2843a324c4c3dc5e8a9f96c16d15","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4a7c0f0d6df87a1bc5d47843f93881c75ced2843a324c4c3dc5e8a9f96c16d15","first_computed_at":"2026-07-28T01:22:52.310362Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-28T01:22:52.310362Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"phANiarCAKihBf+27XMdTjYGw9ml8ECdakr8bH3c0Zd+Yd+Axi7DExJ1VjVEenghNCVpDhw5BZLFkQL50dycBw==","signature_status":"signed_v1","signed_at":"2026-07-28T01:22:52.311143Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.23425","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9a268c61f91710b988ad5b7893b48928e5eb8c2fed051bca700866ba689c5f49","sha256:baa35d0925dc849a9097e2556d6601d4fe79068aeb4620706f4c09cb6081ae5b"],"state_sha256":"6dadf63deb3dc4d3cd4581b310061b2c7f6699775af3fd357688646de7ba7c0d"}