{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:MLRPM4YIFRVCES4D2ZVBWTPLCG","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"7fe7e1c9113f996df9b04999579eacd44c18a7c47530bd070a369fe373889828","cross_cats_sorted":["cs.AI","cs.CL","math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-31T17:57:50Z","title_canon_sha256":"53f2e48176bb69dfff20c02461b5027e2c4f6196a900eb4a0fe41b351e735d90"},"schema_version":"1.0","source":{"id":"2308.16898","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.16898","created_at":"2026-07-05T07:47:58Z"},{"alias_kind":"arxiv_version","alias_value":"2308.16898v3","created_at":"2026-07-05T07:47:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.16898","created_at":"2026-07-05T07:47:58Z"},{"alias_kind":"pith_short_12","alias_value":"MLRPM4YIFRVC","created_at":"2026-07-05T07:47:58Z"},{"alias_kind":"pith_short_16","alias_value":"MLRPM4YIFRVCES4D","created_at":"2026-07-05T07:47:58Z"},{"alias_kind":"pith_short_8","alias_value":"MLRPM4YI","created_at":"2026-07-05T07:47:58Z"}],"graph_snapshots":[{"event_id":"sha256:4250b7bcbd136a3c35bef8c5ca9b8f6f5c49908cb9835be10b50536251e48541","target":"graph","created_at":"2026-07-05T07:47:58Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2308.16898/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Since its inception in \"Attention Is All You Need\", transformer architecture has led to revolutionary advancements in NLP. The attention layer within the transformer admits a sequence of input tokens $X$ and makes them interact through pairwise similarities computed as softmax$(XQK^\\top X^\\top)$, where $(K,Q)$ are the trainable key-query parameters. In this work, we establish a formal equivalence between the optimization geometry of self-attention and a hard-margin SVM problem that separates optimal input tokens from non-optimal tokens using linear constraints on the outer-products of token pa","authors_text":"Christos Thrampoulidis, Davoud Ataee Tarzanagh, Samet Oymak, Yingcong Li","cross_cats":["cs.AI","cs.CL","math.OC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-31T17:57:50Z","title":"Transformers as Support Vector Machines"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.16898","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:bf19af83bb4871aca82e5b9773357f018a44173b51fd7a2f33f5631c997be5e5","target":"record","created_at":"2026-07-05T07:47:58Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"7fe7e1c9113f996df9b04999579eacd44c18a7c47530bd070a369fe373889828","cross_cats_sorted":["cs.AI","cs.CL","math.OC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-31T17:57:50Z","title_canon_sha256":"53f2e48176bb69dfff20c02461b5027e2c4f6196a900eb4a0fe41b351e735d90"},"schema_version":"1.0","source":{"id":"2308.16898","kind":"arxiv","version":3}},"canonical_sha256":"62e2f673082c6a224b83d66a1b4deb119b86423808ec51625f95f01db78f7c43","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"62e2f673082c6a224b83d66a1b4deb119b86423808ec51625f95f01db78f7c43","first_computed_at":"2026-07-05T07:47:58.812894Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:47:58.812894Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"azeYachpuXiwmPRaeYdL8cU/3awa2qm1VavsmYBkrUM6Hit8GCv7xfjURbjlT+SEHs3ib9T8w70urvgyRiN8Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:47:58.813401Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.16898","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bf19af83bb4871aca82e5b9773357f018a44173b51fd7a2f33f5631c997be5e5","sha256:4250b7bcbd136a3c35bef8c5ca9b8f6f5c49908cb9835be10b50536251e48541"],"state_sha256":"f5678a19a534b4a8a28b7a9fd3af7a07db164e5a8a6f14ad5115c1f9ac8fe8c0"}