{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:4CVALDIMKWF7KFNGGP564DE73Q","short_pith_number":"pith:4CVALDIM","schema_version":"1.0","canonical_sha256":"e0aa058d0c558bf515a633fbee0c9fdc17c11a48cedf0593051381a4cfa2f76d","source":{"kind":"arxiv","id":"2211.05417","version":1},"attestation_state":"computed","paper":{"title":"Can Transformers Reason in Fragments of Natural Language?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ian Pratt-Hartmann, Kamen V. Pavlov, Viktor Schlegel","submitted_at":"2022-11-10T08:46:53Z","abstract_excerpt":"State-of-the-art deep-learning-based approaches to Natural Language Processing (NLP) are credited with various capabilities that involve reasoning with natural language texts. In this paper we carry out a large-scale empirical study investigating the detection of formally valid inferences in controlled fragments of natural language for which the satisfiability problem becomes increasingly complex. We find that, while transformer-based language models perform surprisingly well in these scenarios, a deeper analysis re-veals that they appear to overfit to superficial patterns in the data rather t"},"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":"2211.05417","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-10T08:46:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"dde0757f84dcad8538c49f1d4686455b351fbfbd1d7df66c5195c5ca8faee195","abstract_canon_sha256":"c6f1fee39c6418dd789b6a5c157765310d8802d7993d26a6f67ea362e963cf8d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:15:04.118989Z","signature_b64":"hNCFC1qwT8qLW/f2IN59VAckAQctcoXeXolVVBAx64jzCTM8CtcphzFiJkfA/pfVVcQ8CNjTG9f4rxRjJ+rNCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e0aa058d0c558bf515a633fbee0c9fdc17c11a48cedf0593051381a4cfa2f76d","last_reissued_at":"2026-07-05T05:15:04.118665Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:15:04.118665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can Transformers Reason in Fragments of Natural Language?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ian Pratt-Hartmann, Kamen V. Pavlov, Viktor Schlegel","submitted_at":"2022-11-10T08:46:53Z","abstract_excerpt":"State-of-the-art deep-learning-based approaches to Natural Language Processing (NLP) are credited with various capabilities that involve reasoning with natural language texts. In this paper we carry out a large-scale empirical study investigating the detection of formally valid inferences in controlled fragments of natural language for which the satisfiability problem becomes increasingly complex. We find that, while transformer-based language models perform surprisingly well in these scenarios, a deeper analysis re-veals that they appear to overfit to superficial patterns in the data rather t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.05417","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/2211.05417/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":"2211.05417","created_at":"2026-07-05T05:15:04.118718+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.05417v1","created_at":"2026-07-05T05:15:04.118718+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.05417","created_at":"2026-07-05T05:15:04.118718+00:00"},{"alias_kind":"pith_short_12","alias_value":"4CVALDIMKWF7","created_at":"2026-07-05T05:15:04.118718+00:00"},{"alias_kind":"pith_short_16","alias_value":"4CVALDIMKWF7KFNG","created_at":"2026-07-05T05:15:04.118718+00:00"},{"alias_kind":"pith_short_8","alias_value":"4CVALDIM","created_at":"2026-07-05T05:15:04.118718+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/4CVALDIMKWF7KFNGGP564DE73Q","json":"https://pith.science/pith/4CVALDIMKWF7KFNGGP564DE73Q.json","graph_json":"https://pith.science/api/pith-number/4CVALDIMKWF7KFNGGP564DE73Q/graph.json","events_json":"https://pith.science/api/pith-number/4CVALDIMKWF7KFNGGP564DE73Q/events.json","paper":"https://pith.science/paper/4CVALDIM"},"agent_actions":{"view_html":"https://pith.science/pith/4CVALDIMKWF7KFNGGP564DE73Q","download_json":"https://pith.science/pith/4CVALDIMKWF7KFNGGP564DE73Q.json","view_paper":"https://pith.science/paper/4CVALDIM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.05417&json=true","fetch_graph":"https://pith.science/api/pith-number/4CVALDIMKWF7KFNGGP564DE73Q/graph.json","fetch_events":"https://pith.science/api/pith-number/4CVALDIMKWF7KFNGGP564DE73Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4CVALDIMKWF7KFNGGP564DE73Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4CVALDIMKWF7KFNGGP564DE73Q/action/storage_attestation","attest_author":"https://pith.science/pith/4CVALDIMKWF7KFNGGP564DE73Q/action/author_attestation","sign_citation":"https://pith.science/pith/4CVALDIMKWF7KFNGGP564DE73Q/action/citation_signature","submit_replication":"https://pith.science/pith/4CVALDIMKWF7KFNGGP564DE73Q/action/replication_record"}},"created_at":"2026-07-05T05:15:04.118718+00:00","updated_at":"2026-07-05T05:15:04.118718+00:00"}