{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2MSWBSYKMOO6POI7I455O4UNOH","short_pith_number":"pith:2MSWBSYK","schema_version":"1.0","canonical_sha256":"d32560cb0a639de7b91f473bd7728d71ecc23741c553b119fb6869fa89531d4a","source":{"kind":"arxiv","id":"2606.02837","version":1},"attestation_state":"computed","paper":{"title":"Fixing FOLIO and MALLS: Verified Annotations and an LLM-assisted Framework to Focus Human Relabeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Andrea Brunello, Angelo Montanari, Cristian Curaba, Luca Geatti, Michele Mignani, Nicola Saccomanno","submitted_at":"2026-06-01T20:00:35Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2606.02837","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-01T20:00:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7af07bc5f1b2ad092381f81c28256f8483bf1003611e4b7f6666abfd857d97ff","abstract_canon_sha256":"161daddd1bfff62f0cfb72c8c99dcab51d24013d215f60f01f0020affd448254"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:24.252765Z","signature_b64":"A9jHPbfXS72bCTHr/NI3EkzBsM1MIG+22qX8emVrNz+I/cdEhA71mJgE6Lb2AEI1s6qz/nxxHzopRZiFnNlkAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d32560cb0a639de7b91f473bd7728d71ecc23741c553b119fb6869fa89531d4a","last_reissued_at":"2026-06-03T01:05:24.252375Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:24.252375Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fixing FOLIO and MALLS: Verified Annotations and an LLM-assisted Framework to Focus Human Relabeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Andrea Brunello, Angelo Montanari, Cristian Curaba, Luca Geatti, Michele Mignani, Nicola Saccomanno","submitted_at":"2026-06-01T20:00:35Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.02837","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.02837/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.02837","created_at":"2026-06-03T01:05:24.252442+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.02837v1","created_at":"2026-06-03T01:05:24.252442+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.02837","created_at":"2026-06-03T01:05:24.252442+00:00"},{"alias_kind":"pith_short_12","alias_value":"2MSWBSYKMOO6","created_at":"2026-06-03T01:05:24.252442+00:00"},{"alias_kind":"pith_short_16","alias_value":"2MSWBSYKMOO6POI7","created_at":"2026-06-03T01:05:24.252442+00:00"},{"alias_kind":"pith_short_8","alias_value":"2MSWBSYK","created_at":"2026-06-03T01:05:24.252442+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2MSWBSYKMOO6POI7I455O4UNOH","json":"https://pith.science/pith/2MSWBSYKMOO6POI7I455O4UNOH.json","graph_json":"https://pith.science/api/pith-number/2MSWBSYKMOO6POI7I455O4UNOH/graph.json","events_json":"https://pith.science/api/pith-number/2MSWBSYKMOO6POI7I455O4UNOH/events.json","paper":"https://pith.science/paper/2MSWBSYK"},"agent_actions":{"view_html":"https://pith.science/pith/2MSWBSYKMOO6POI7I455O4UNOH","download_json":"https://pith.science/pith/2MSWBSYKMOO6POI7I455O4UNOH.json","view_paper":"https://pith.science/paper/2MSWBSYK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.02837&json=true","fetch_graph":"https://pith.science/api/pith-number/2MSWBSYKMOO6POI7I455O4UNOH/graph.json","fetch_events":"https://pith.science/api/pith-number/2MSWBSYKMOO6POI7I455O4UNOH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2MSWBSYKMOO6POI7I455O4UNOH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2MSWBSYKMOO6POI7I455O4UNOH/action/storage_attestation","attest_author":"https://pith.science/pith/2MSWBSYKMOO6POI7I455O4UNOH/action/author_attestation","sign_citation":"https://pith.science/pith/2MSWBSYKMOO6POI7I455O4UNOH/action/citation_signature","submit_replication":"https://pith.science/pith/2MSWBSYKMOO6POI7I455O4UNOH/action/replication_record"}},"created_at":"2026-06-03T01:05:24.252442+00:00","updated_at":"2026-06-03T01:05:24.252442+00:00"}