{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XF7JHAWJX7Q2N77WDJRQMKMEYI","short_pith_number":"pith:XF7JHAWJ","schema_version":"1.0","canonical_sha256":"b97e9382c9bfe1a6fff61a63062984c202239db2ed2753ce2c1d84bc515d30ef","source":{"kind":"arxiv","id":"2402.15478","version":3},"attestation_state":"computed","paper":{"title":"Transformers are Expressive, But Are They Expressive Enough for Regression?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Harshad Khadilkar, Pushpak Bhattacharyya, Swaroop Nath","submitted_at":"2024-02-23T18:12:53Z","abstract_excerpt":"Transformers have become pivotal in Natural Language Processing, demonstrating remarkable success in applications like Machine Translation and Summarization. Given their widespread adoption, several works have attempted to analyze the expressivity of Transformers. Expressivity of a neural network is the class of functions it can approximate. A neural network is fully expressive if it can act as a universal function approximator. We attempt to analyze the same for Transformers. Contrary to existing claims, our findings reveal that Transformers struggle to reliably approximate smooth functions, "},"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":"2402.15478","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-23T18:12:53Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"165797d9389f1f300bb881a4139b044e4c3d11b8373cc4a4a96b088831c5837b","abstract_canon_sha256":"0525c7b143c04d63b4fccc190b23719dfaf919110f2543814afd2ff2822e199f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:00:57.702824Z","signature_b64":"a9S7A5SGvM60q54UyodklaweFKTsKmgRt9oHJfPoGhuWJepH1hKYvY7gg9u10CSJo01KhF/iurBWb3s9cfPWCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b97e9382c9bfe1a6fff61a63062984c202239db2ed2753ce2c1d84bc515d30ef","last_reissued_at":"2026-07-05T09:00:57.702364Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:00:57.702364Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transformers are Expressive, But Are They Expressive Enough for Regression?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Harshad Khadilkar, Pushpak Bhattacharyya, Swaroop Nath","submitted_at":"2024-02-23T18:12:53Z","abstract_excerpt":"Transformers have become pivotal in Natural Language Processing, demonstrating remarkable success in applications like Machine Translation and Summarization. Given their widespread adoption, several works have attempted to analyze the expressivity of Transformers. Expressivity of a neural network is the class of functions it can approximate. A neural network is fully expressive if it can act as a universal function approximator. We attempt to analyze the same for Transformers. Contrary to existing claims, our findings reveal that Transformers struggle to reliably approximate smooth functions, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.15478","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/2402.15478/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":"2402.15478","created_at":"2026-07-05T09:00:57.702424+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.15478v3","created_at":"2026-07-05T09:00:57.702424+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.15478","created_at":"2026-07-05T09:00:57.702424+00:00"},{"alias_kind":"pith_short_12","alias_value":"XF7JHAWJX7Q2","created_at":"2026-07-05T09:00:57.702424+00:00"},{"alias_kind":"pith_short_16","alias_value":"XF7JHAWJX7Q2N77W","created_at":"2026-07-05T09:00:57.702424+00:00"},{"alias_kind":"pith_short_8","alias_value":"XF7JHAWJ","created_at":"2026-07-05T09:00:57.702424+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.14727","citing_title":"Geometric Capacity of Transformers: A Tropical Geometry Perspective","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XF7JHAWJX7Q2N77WDJRQMKMEYI","json":"https://pith.science/pith/XF7JHAWJX7Q2N77WDJRQMKMEYI.json","graph_json":"https://pith.science/api/pith-number/XF7JHAWJX7Q2N77WDJRQMKMEYI/graph.json","events_json":"https://pith.science/api/pith-number/XF7JHAWJX7Q2N77WDJRQMKMEYI/events.json","paper":"https://pith.science/paper/XF7JHAWJ"},"agent_actions":{"view_html":"https://pith.science/pith/XF7JHAWJX7Q2N77WDJRQMKMEYI","download_json":"https://pith.science/pith/XF7JHAWJX7Q2N77WDJRQMKMEYI.json","view_paper":"https://pith.science/paper/XF7JHAWJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.15478&json=true","fetch_graph":"https://pith.science/api/pith-number/XF7JHAWJX7Q2N77WDJRQMKMEYI/graph.json","fetch_events":"https://pith.science/api/pith-number/XF7JHAWJX7Q2N77WDJRQMKMEYI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XF7JHAWJX7Q2N77WDJRQMKMEYI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XF7JHAWJX7Q2N77WDJRQMKMEYI/action/storage_attestation","attest_author":"https://pith.science/pith/XF7JHAWJX7Q2N77WDJRQMKMEYI/action/author_attestation","sign_citation":"https://pith.science/pith/XF7JHAWJX7Q2N77WDJRQMKMEYI/action/citation_signature","submit_replication":"https://pith.science/pith/XF7JHAWJX7Q2N77WDJRQMKMEYI/action/replication_record"}},"created_at":"2026-07-05T09:00:57.702424+00:00","updated_at":"2026-07-05T09:00:57.702424+00:00"}