{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UM4W6O4TDRTXDE3TH4NVIVR5ST","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":"15d3be0b28f45a6274799356934c59efb51e01854dceeff35afc2c991eb8cb3f","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-13T17:59:06Z","title_canon_sha256":"0182d715e05b39ff90e899151729b037c086a1824f8303d147153ae0e388b6ed"},"schema_version":"1.0","source":{"id":"2503.10622","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.10622","created_at":"2026-07-05T11:21:44Z"},{"alias_kind":"arxiv_version","alias_value":"2503.10622v2","created_at":"2026-07-05T11:21:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.10622","created_at":"2026-07-05T11:21:44Z"},{"alias_kind":"pith_short_12","alias_value":"UM4W6O4TDRTX","created_at":"2026-07-05T11:21:44Z"},{"alias_kind":"pith_short_16","alias_value":"UM4W6O4TDRTXDE3T","created_at":"2026-07-05T11:21:44Z"},{"alias_kind":"pith_short_8","alias_value":"UM4W6O4T","created_at":"2026-07-05T11:21:44Z"}],"graph_snapshots":[{"event_id":"sha256:9fc484468ca28bf54e693b81f8f5427f029b202ed182782f6b9ddfcbfa39f85a","target":"graph","created_at":"2026-07-05T11:21:44Z","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/2503.10622/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Normalization layers are ubiquitous in modern neural networks and have long been considered essential. This work demonstrates that Transformers without normalization can achieve the same or better performance using a remarkably simple technique. We introduce Dynamic Tanh (DyT), an element-wise operation $DyT($x$) = \\tanh(\\alpha $x$)$, as a drop-in replacement for normalization layers in Transformers. DyT is inspired by the observation that layer normalization in Transformers often produces tanh-like, $S$-shaped input-output mappings. By incorporating DyT, Transformers without normalization can","authors_text":"Jiachen Zhu, Kaiming He, Xinlei Chen, Yann LeCun, Zhuang Liu","cross_cats":["cs.AI","cs.CL","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-13T17:59:06Z","title":"Transformers without Normalization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.10622","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":"sha256:1cf50a6a37cdc58b225dfdba0d5f642b1883bc48743eb7cd53ec58e790742d37","target":"record","created_at":"2026-07-05T11:21:44Z","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":"15d3be0b28f45a6274799356934c59efb51e01854dceeff35afc2c991eb8cb3f","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-13T17:59:06Z","title_canon_sha256":"0182d715e05b39ff90e899151729b037c086a1824f8303d147153ae0e388b6ed"},"schema_version":"1.0","source":{"id":"2503.10622","kind":"arxiv","version":2}},"canonical_sha256":"a3396f3b931c677193733f1b54563d94f5606ab5f57f38bb66c0fcaebfde4f15","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a3396f3b931c677193733f1b54563d94f5606ab5f57f38bb66c0fcaebfde4f15","first_computed_at":"2026-07-05T11:21:44.177298Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:21:44.177298Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NuU82yegajq/VhHJ4CiXbO5xvap9udLFZI6QqFXyBk/0MG8kKJ45dw3jItCG6WudNu7CNyMKZoEAoMwnpP56BA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:21:44.177755Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.10622","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1cf50a6a37cdc58b225dfdba0d5f642b1883bc48743eb7cd53ec58e790742d37","sha256:9fc484468ca28bf54e693b81f8f5427f029b202ed182782f6b9ddfcbfa39f85a"],"state_sha256":"aad1d9affbc36e2c07bb05cddc706477750a6e3354d17baddd7faa9092f27b7b"}