{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EF4RPSA7JWEBX7SBVY4MGDA3VR","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":"98ddbe5e17fe35ad6f5f2e90ea9840e93b5326f30c7a3287ec68e7172c891980","cross_cats_sorted":["cond-mat.dis-nn","cond-mat.stat-mech","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-24T20:34:18Z","title_canon_sha256":"e1fd643378b4c362886b0e72f513381309e7ef68c780bbb32cc7ccbb0a3b9f1f"},"schema_version":"1.0","source":{"id":"2405.15926","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.15926","created_at":"2026-07-05T09:45:49Z"},{"alias_kind":"arxiv_version","alias_value":"2405.15926v2","created_at":"2026-07-05T09:45:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.15926","created_at":"2026-07-05T09:45:49Z"},{"alias_kind":"pith_short_12","alias_value":"EF4RPSA7JWEB","created_at":"2026-07-05T09:45:49Z"},{"alias_kind":"pith_short_16","alias_value":"EF4RPSA7JWEBX7SB","created_at":"2026-07-05T09:45:49Z"},{"alias_kind":"pith_short_8","alias_value":"EF4RPSA7","created_at":"2026-07-05T09:45:49Z"}],"graph_snapshots":[{"event_id":"sha256:23b8af1ce506e2c0f60b43b1b59f5ccd13a3199de547053a67317ee9d992f61d","target":"graph","created_at":"2026-07-05T09:45:49Z","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/2405.15926/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the remarkable empirical performance of Transformers, their theoretical understanding remains elusive. Here, we consider a deep multi-head self-attention network, that is closely related to Transformers yet analytically tractable. We develop a statistical mechanics theory of Bayesian learning in this model, deriving exact equations for the network's predictor statistics under the finite-width thermodynamic limit, i.e., $N,P\\rightarrow\\infty$, $P/N=\\mathcal{O}(1)$, where $N$ is the network width and $P$ is the number of training examples. Our theory shows that the predictor statistics a","authors_text":"Francesca Mignacco, Haim Sompolinsky, Kazuki Irie, Lorenzo Tiberi","cross_cats":["cond-mat.dis-nn","cond-mat.stat-mech","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-24T20:34:18Z","title":"Dissecting the Interplay of Attention Paths in a Statistical Mechanics Theory of Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.15926","kind":"arxiv","version":2},"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:f47e2151e044acd42b4424d47fc33f1eb8488cab339289ff1470029184e94fb7","target":"record","created_at":"2026-07-05T09:45:49Z","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":"98ddbe5e17fe35ad6f5f2e90ea9840e93b5326f30c7a3287ec68e7172c891980","cross_cats_sorted":["cond-mat.dis-nn","cond-mat.stat-mech","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-24T20:34:18Z","title_canon_sha256":"e1fd643378b4c362886b0e72f513381309e7ef68c780bbb32cc7ccbb0a3b9f1f"},"schema_version":"1.0","source":{"id":"2405.15926","kind":"arxiv","version":2}},"canonical_sha256":"217917c81f4d881bfe41ae38c30c1bac4409db4f12ee88b0bd102f50620d204e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"217917c81f4d881bfe41ae38c30c1bac4409db4f12ee88b0bd102f50620d204e","first_computed_at":"2026-07-05T09:45:49.306111Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:45:49.306111Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"u1oJNWHKd0r2JjDiweLvOZ4Wnu1dX+9we/P1KkPGHS5Qpsih8oZDZ5rAK88t+zC8q+ECASlgIoxnWIWfef9eBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:45:49.306622Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.15926","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f47e2151e044acd42b4424d47fc33f1eb8488cab339289ff1470029184e94fb7","sha256:23b8af1ce506e2c0f60b43b1b59f5ccd13a3199de547053a67317ee9d992f61d"],"state_sha256":"d7e58249d10ba57b62b33befa867f35d3f5069822d225bf3e9ad50f7cb50ede6"}