{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KBDGQHZVTGSIXJCL3PH3IPLRTE","short_pith_number":"pith:KBDGQHZV","schema_version":"1.0","canonical_sha256":"5046681f3599a48ba44bdbcfb43d71993c748701fd4647d2680ce673732b2ebf","source":{"kind":"arxiv","id":"2311.00208","version":3},"attestation_state":"computed","paper":{"title":"What Formal Languages Can Transformers Express? A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.FL","cs.LO"],"primary_cat":"cs.LG","authors_text":"Dana Angluin, David Chiang, Gail Weiss, Lena Strobl, William Merrill","submitted_at":"2023-11-01T00:38:26Z","abstract_excerpt":"As transformers have gained prominence in natural language processing, some researchers have investigated theoretically what problems they can and cannot solve, by treating problems as formal languages. Exploring such questions can help clarify the power of transformers relative to other models of computation, their fundamental capabilities and limits, and the impact of architectural choices. Work in this subarea has made considerable progress in recent years. Here, we undertake a comprehensive survey of this work, documenting the diverse assumptions that underlie different results and providi"},"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":"2311.00208","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-01T00:38:26Z","cross_cats_sorted":["cs.CL","cs.FL","cs.LO"],"title_canon_sha256":"04085a49d341b684021158644c74a0e597d6aa8a1e1eddfb734b51cb0c6eeb5b","abstract_canon_sha256":"086a2f0bf8fbd3162307506f09af3d1393c2e365670a3be64efc3b4f56b794c0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:02:54.794974Z","signature_b64":"1ArOFQKoB4VMdNs0h0NJ4gNE9RsjIXsIwvuJVfKkprqxRdw7XJfhCjBULZvfHW6FQOacXYpfAl1vErs7Z7jEDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5046681f3599a48ba44bdbcfb43d71993c748701fd4647d2680ce673732b2ebf","last_reissued_at":"2026-07-05T09:02:54.794564Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:02:54.794564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"What Formal Languages Can Transformers Express? A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.FL","cs.LO"],"primary_cat":"cs.LG","authors_text":"Dana Angluin, David Chiang, Gail Weiss, Lena Strobl, William Merrill","submitted_at":"2023-11-01T00:38:26Z","abstract_excerpt":"As transformers have gained prominence in natural language processing, some researchers have investigated theoretically what problems they can and cannot solve, by treating problems as formal languages. Exploring such questions can help clarify the power of transformers relative to other models of computation, their fundamental capabilities and limits, and the impact of architectural choices. Work in this subarea has made considerable progress in recent years. Here, we undertake a comprehensive survey of this work, documenting the diverse assumptions that underlie different results and providi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.00208","kind":"arxiv","version":3},"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/2311.00208/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":"2311.00208","created_at":"2026-07-05T09:02:54.794618+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.00208v3","created_at":"2026-07-05T09:02:54.794618+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.00208","created_at":"2026-07-05T09:02:54.794618+00:00"},{"alias_kind":"pith_short_12","alias_value":"KBDGQHZVTGSI","created_at":"2026-07-05T09:02:54.794618+00:00"},{"alias_kind":"pith_short_16","alias_value":"KBDGQHZVTGSIXJCL","created_at":"2026-07-05T09:02:54.794618+00:00"},{"alias_kind":"pith_short_8","alias_value":"KBDGQHZV","created_at":"2026-07-05T09:02:54.794618+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09822","citing_title":"Causally Evaluating the Learnability of Formal Language Tasks","ref_index":95,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20988","citing_title":"A Sharper Picture of Generalization in Transformers","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20988","citing_title":"A Sharper Picture of Generalization in Transformers","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23267","citing_title":"Fine-tuning vs. In-context Learning in Large Language Models: A Formal Language Learning Perspective","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2507.12549","citing_title":"The Serial Scaling Hypothesis","ref_index":110,"is_internal_anchor":false},{"citing_arxiv_id":"2508.16745","citing_title":"Beyond Memorization: Extending Reasoning Depth with Recurrence, Memory and Test-Time Compute Scaling","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23267","citing_title":"Fine-tuning vs. In-context Learning in Large Language Models: A Formal Language Learning Perspective","ref_index":64,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KBDGQHZVTGSIXJCL3PH3IPLRTE","json":"https://pith.science/pith/KBDGQHZVTGSIXJCL3PH3IPLRTE.json","graph_json":"https://pith.science/api/pith-number/KBDGQHZVTGSIXJCL3PH3IPLRTE/graph.json","events_json":"https://pith.science/api/pith-number/KBDGQHZVTGSIXJCL3PH3IPLRTE/events.json","paper":"https://pith.science/paper/KBDGQHZV"},"agent_actions":{"view_html":"https://pith.science/pith/KBDGQHZVTGSIXJCL3PH3IPLRTE","download_json":"https://pith.science/pith/KBDGQHZVTGSIXJCL3PH3IPLRTE.json","view_paper":"https://pith.science/paper/KBDGQHZV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.00208&json=true","fetch_graph":"https://pith.science/api/pith-number/KBDGQHZVTGSIXJCL3PH3IPLRTE/graph.json","fetch_events":"https://pith.science/api/pith-number/KBDGQHZVTGSIXJCL3PH3IPLRTE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KBDGQHZVTGSIXJCL3PH3IPLRTE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KBDGQHZVTGSIXJCL3PH3IPLRTE/action/storage_attestation","attest_author":"https://pith.science/pith/KBDGQHZVTGSIXJCL3PH3IPLRTE/action/author_attestation","sign_citation":"https://pith.science/pith/KBDGQHZVTGSIXJCL3PH3IPLRTE/action/citation_signature","submit_replication":"https://pith.science/pith/KBDGQHZVTGSIXJCL3PH3IPLRTE/action/replication_record"}},"created_at":"2026-07-05T09:02:54.794618+00:00","updated_at":"2026-07-05T09:02:54.794618+00:00"}