{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2MSWBSYKMOO6POI7I455O4UNOH","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":"161daddd1bfff62f0cfb72c8c99dcab51d24013d215f60f01f0020affd448254","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-01T20:00:35Z","title_canon_sha256":"7af07bc5f1b2ad092381f81c28256f8483bf1003611e4b7f6666abfd857d97ff"},"schema_version":"1.0","source":{"id":"2606.02837","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.02837","created_at":"2026-06-03T01:05:24Z"},{"alias_kind":"arxiv_version","alias_value":"2606.02837v1","created_at":"2026-06-03T01:05:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.02837","created_at":"2026-06-03T01:05:24Z"},{"alias_kind":"pith_short_12","alias_value":"2MSWBSYKMOO6","created_at":"2026-06-03T01:05:24Z"},{"alias_kind":"pith_short_16","alias_value":"2MSWBSYKMOO6POI7","created_at":"2026-06-03T01:05:24Z"},{"alias_kind":"pith_short_8","alias_value":"2MSWBSYK","created_at":"2026-06-03T01:05:24Z"}],"graph_snapshots":[{"event_id":"sha256:d1ef2c9c8eea167800eace66ec0170908d4cc0b5146e8e8e9d38cbab295d8d3b","target":"graph","created_at":"2026-06-03T01:05:24Z","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/2606.02837/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Accurate translation from Natural Language to First-Order Logic (NL-to-FOL) underpins neurosymbolic AI systems and Natural Language Inference (NLI), making the quality of NL-to-FOL benchmarks essential -- yet these datasets have never been rigorously audited. Our first contribution is to present a systematic human inspection of the validation split of \\textsf{FOLIO} and a subset of \\textsf{MALLS} test instances, finding that approximately 39% and 36% of entries, respectively, contain incorrect FOL formalizations (i.e., ground truth labels), with additional rates of ambiguous NL sentences (16.4","authors_text":"Andrea Brunello, Angelo Montanari, Cristian Curaba, Luca Geatti, Michele Mignani, Nicola Saccomanno","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-01T20:00:35Z","title":"Fixing FOLIO and MALLS: Verified Annotations and an LLM-assisted Framework to Focus Human Relabeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.02837","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":"sha256:5fc19e6dbd46d48f00a971457733dab6c5cad8f245ed1b44014181afaa770850","target":"record","created_at":"2026-06-03T01:05:24Z","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":"161daddd1bfff62f0cfb72c8c99dcab51d24013d215f60f01f0020affd448254","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-01T20:00:35Z","title_canon_sha256":"7af07bc5f1b2ad092381f81c28256f8483bf1003611e4b7f6666abfd857d97ff"},"schema_version":"1.0","source":{"id":"2606.02837","kind":"arxiv","version":1}},"canonical_sha256":"d32560cb0a639de7b91f473bd7728d71ecc23741c553b119fb6869fa89531d4a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d32560cb0a639de7b91f473bd7728d71ecc23741c553b119fb6869fa89531d4a","first_computed_at":"2026-06-03T01:05:24.252375Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-03T01:05:24.252375Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"A9jHPbfXS72bCTHr/NI3EkzBsM1MIG+22qX8emVrNz+I/cdEhA71mJgE6Lb2AEI1s6qz/nxxHzopRZiFnNlkAg==","signature_status":"signed_v1","signed_at":"2026-06-03T01:05:24.252765Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.02837","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5fc19e6dbd46d48f00a971457733dab6c5cad8f245ed1b44014181afaa770850","sha256:d1ef2c9c8eea167800eace66ec0170908d4cc0b5146e8e8e9d38cbab295d8d3b"],"state_sha256":"93590b780191c85b3dc8b6e6c419e118db9ddd7503f2d0ab9dc3b2557598721e"}