{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HYI3S42F6RMHNT4Y44VGGMZR2Y","short_pith_number":"pith:HYI3S42F","schema_version":"1.0","canonical_sha256":"3e11b97345f45876cf98e72a633331d60261a306e8b2bf8ad80785b7f8fe125b","source":{"kind":"arxiv","id":"2406.13781","version":1},"attestation_state":"computed","paper":{"title":"A Primal-Dual Framework for Transformers and Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrea L. Bertozzi, Nhat Ho, Richard G. Baraniuk, Stanley J. Osher, Tam Nguyen, Tan M. Nguyen","submitted_at":"2024-06-19T19:11:22Z","abstract_excerpt":"Self-attention is key to the remarkable success of transformers in sequence modeling tasks including many applications in natural language processing and computer vision. Like neural network layers, these attention mechanisms are often developed by heuristics and experience. To provide a principled framework for constructing attention layers in transformers, we show that the self-attention corresponds to the support vector expansion derived from a support vector regression problem, whose primal formulation has the form of a neural network layer. Using our framework, we derive popular attention"},"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":"2406.13781","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-19T19:11:22Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV","stat.ML"],"title_canon_sha256":"fa5dc7990082acdb0140f9396518b38177980dcd79fc2a54b4e48260b98f7056","abstract_canon_sha256":"f39e42672af205906ee214c9c1bfe7eeb31f035c6a298a2a67610ccf13bf0ff2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:34:34.368759Z","signature_b64":"Axq3PYleDVkDRGCO2zdRlm4qilnQaCoqU7lppKvYpqhmFjDYGVoEOM81CUOerZtmmI5LIlLIJQ+/L5aWzo5/Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e11b97345f45876cf98e72a633331d60261a306e8b2bf8ad80785b7f8fe125b","last_reissued_at":"2026-07-05T08:34:34.368327Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:34:34.368327Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Primal-Dual Framework for Transformers and Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrea L. Bertozzi, Nhat Ho, Richard G. Baraniuk, Stanley J. Osher, Tam Nguyen, Tan M. Nguyen","submitted_at":"2024-06-19T19:11:22Z","abstract_excerpt":"Self-attention is key to the remarkable success of transformers in sequence modeling tasks including many applications in natural language processing and computer vision. Like neural network layers, these attention mechanisms are often developed by heuristics and experience. To provide a principled framework for constructing attention layers in transformers, we show that the self-attention corresponds to the support vector expansion derived from a support vector regression problem, whose primal formulation has the form of a neural network layer. Using our framework, we derive popular attention"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.13781","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/2406.13781/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":"2406.13781","created_at":"2026-07-05T08:34:34.368386+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.13781v1","created_at":"2026-07-05T08:34:34.368386+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.13781","created_at":"2026-07-05T08:34:34.368386+00:00"},{"alias_kind":"pith_short_12","alias_value":"HYI3S42F6RMH","created_at":"2026-07-05T08:34:34.368386+00:00"},{"alias_kind":"pith_short_16","alias_value":"HYI3S42F6RMHNT4Y","created_at":"2026-07-05T08:34:34.368386+00:00"},{"alias_kind":"pith_short_8","alias_value":"HYI3S42F","created_at":"2026-07-05T08:34:34.368386+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.07908","citing_title":"A Reproduction Study: The Kernel PCA Interpretation of Self-Attention Fails Under Scrutiny","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HYI3S42F6RMHNT4Y44VGGMZR2Y","json":"https://pith.science/pith/HYI3S42F6RMHNT4Y44VGGMZR2Y.json","graph_json":"https://pith.science/api/pith-number/HYI3S42F6RMHNT4Y44VGGMZR2Y/graph.json","events_json":"https://pith.science/api/pith-number/HYI3S42F6RMHNT4Y44VGGMZR2Y/events.json","paper":"https://pith.science/paper/HYI3S42F"},"agent_actions":{"view_html":"https://pith.science/pith/HYI3S42F6RMHNT4Y44VGGMZR2Y","download_json":"https://pith.science/pith/HYI3S42F6RMHNT4Y44VGGMZR2Y.json","view_paper":"https://pith.science/paper/HYI3S42F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.13781&json=true","fetch_graph":"https://pith.science/api/pith-number/HYI3S42F6RMHNT4Y44VGGMZR2Y/graph.json","fetch_events":"https://pith.science/api/pith-number/HYI3S42F6RMHNT4Y44VGGMZR2Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HYI3S42F6RMHNT4Y44VGGMZR2Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HYI3S42F6RMHNT4Y44VGGMZR2Y/action/storage_attestation","attest_author":"https://pith.science/pith/HYI3S42F6RMHNT4Y44VGGMZR2Y/action/author_attestation","sign_citation":"https://pith.science/pith/HYI3S42F6RMHNT4Y44VGGMZR2Y/action/citation_signature","submit_replication":"https://pith.science/pith/HYI3S42F6RMHNT4Y44VGGMZR2Y/action/replication_record"}},"created_at":"2026-07-05T08:34:34.368386+00:00","updated_at":"2026-07-05T08:34:34.368386+00:00"}