{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:LGCWLPR3QQRYFRE25G2ZVR5LQS","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":"bc67c2b0c223f13dcc81b8cb68d7f958abda6c476208543e09c72843bc9e35ee","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-02T00:16:09Z","title_canon_sha256":"ac55db1972766ce0b283b55be4fc080c572162be483eb11c4f6f7c8c2fa1f0e0"},"schema_version":"1.0","source":{"id":"2005.00663","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.00663","created_at":"2026-07-05T00:59:44Z"},{"alias_kind":"arxiv_version","alias_value":"2005.00663v1","created_at":"2026-07-05T00:59:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.00663","created_at":"2026-07-05T00:59:44Z"},{"alias_kind":"pith_short_12","alias_value":"LGCWLPR3QQRY","created_at":"2026-07-05T00:59:44Z"},{"alias_kind":"pith_short_16","alias_value":"LGCWLPR3QQRYFRE2","created_at":"2026-07-05T00:59:44Z"},{"alias_kind":"pith_short_8","alias_value":"LGCWLPR3","created_at":"2026-07-05T00:59:44Z"}],"graph_snapshots":[{"event_id":"sha256:fe7603a7b23f19e643d735d2e1140756d0eabaabb2da1e411ae2db3d77fafc56","target":"graph","created_at":"2026-07-05T00:59:44Z","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/2005.00663/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing datasets for regular expression (regex) generation from natural language are limited in complexity; compared to regex tasks that users post on StackOverflow, the regexes in these datasets are simple, and the language used to describe them is not diverse. We introduce StructuredRegex, a new regex synthesis dataset differing from prior ones in three aspects. First, to obtain structurally complex and realistic regexes, we generate the regexes using a probabilistic grammar with pre-defined macros observed from real-world StackOverflow posts. Second, to obtain linguistically diverse natura","authors_text":"Greg Durrett, Isil Dillig, Qiaochu Chen, Xi Ye","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-02T00:16:09Z","title":"Benchmarking Multimodal Regex Synthesis with Complex Structures"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.00663","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":"sha256:6cf9f7bbf0ee504de5a1773b5743898e0ecefb68c430e5b4e937c4536781f2e1","target":"record","created_at":"2026-07-05T00:59:44Z","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":"bc67c2b0c223f13dcc81b8cb68d7f958abda6c476208543e09c72843bc9e35ee","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-02T00:16:09Z","title_canon_sha256":"ac55db1972766ce0b283b55be4fc080c572162be483eb11c4f6f7c8c2fa1f0e0"},"schema_version":"1.0","source":{"id":"2005.00663","kind":"arxiv","version":1}},"canonical_sha256":"598565be3b842382c49ae9b59ac7ab8485581a56fc4ceba1525798de21cf8cea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"598565be3b842382c49ae9b59ac7ab8485581a56fc4ceba1525798de21cf8cea","first_computed_at":"2026-07-05T00:59:44.935354Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:59:44.935354Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YXkjTiOr1ZfvhLKYWRAlm2v60sAER3L7cX171ncbp5FfZLrFP5CmyrCF5GVOb0zbHiEsA0zR6QTa7GQbgOP/Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:59:44.935788Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.00663","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6cf9f7bbf0ee504de5a1773b5743898e0ecefb68c430e5b4e937c4536781f2e1","sha256:fe7603a7b23f19e643d735d2e1140756d0eabaabb2da1e411ae2db3d77fafc56"],"state_sha256":"f38d75f5961c84205a0487e937a0725443458630d60d9e91182d8225f59afd41"}