{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:HJK7R5VCVBUGNOVJXV25BLGYVW","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":"9345c2d1101a80ba696c58b9bc3a52345b1fd7b8fad136ba60840939156b4d7f","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-12T17:16:27Z","title_canon_sha256":"e954c48726f9539c93edeadb6a868978846af88ed2bdecda9f200611b878233b"},"schema_version":"1.0","source":{"id":"2210.06423","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.06423","created_at":"2026-07-05T05:08:18Z"},{"alias_kind":"arxiv_version","alias_value":"2210.06423v2","created_at":"2026-07-05T05:08:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.06423","created_at":"2026-07-05T05:08:18Z"},{"alias_kind":"pith_short_12","alias_value":"HJK7R5VCVBUG","created_at":"2026-07-05T05:08:18Z"},{"alias_kind":"pith_short_16","alias_value":"HJK7R5VCVBUGNOVJ","created_at":"2026-07-05T05:08:18Z"},{"alias_kind":"pith_short_8","alias_value":"HJK7R5VC","created_at":"2026-07-05T05:08:18Z"}],"graph_snapshots":[{"event_id":"sha256:39f28c89cd1f9618971101c488c1d8d06691662322f1ba1a601f7a60f7fe70f7","target":"graph","created_at":"2026-07-05T05:08:18Z","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/2210.06423/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A big convergence of model architectures across language, vision, speech, and multimodal is emerging. However, under the same name \"Transformers\", the above areas use different implementations for better performance, e.g., Post-LayerNorm for BERT, and Pre-LayerNorm for GPT and vision Transformers. We call for the development of Foundation Transformer for true general-purpose modeling, which serves as a go-to architecture for various tasks and modalities with guaranteed training stability. In this work, we introduce a Transformer variant, named Magneto, to fulfill the goal. Specifically, we pro","authors_text":"Alon Benhaim, Barun Patra, Furu Wei, Hongyu Wang, Li Dong, Payal Bajaj, Saksham Singhal, Shaohan Huang, Shuming Ma, Vishrav Chaudhary, Wenhui Wang, Xia Song, Yu Wu, Zhiliang Peng, Zhun Liu","cross_cats":["cs.CL","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-12T17:16:27Z","title":"Foundation Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.06423","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":"sha256:1c96c36d9956d664b436d4c44ff8721f554c48cb52518e0ab3cc9281656ed330","target":"record","created_at":"2026-07-05T05:08:18Z","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":"9345c2d1101a80ba696c58b9bc3a52345b1fd7b8fad136ba60840939156b4d7f","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-12T17:16:27Z","title_canon_sha256":"e954c48726f9539c93edeadb6a868978846af88ed2bdecda9f200611b878233b"},"schema_version":"1.0","source":{"id":"2210.06423","kind":"arxiv","version":2}},"canonical_sha256":"3a55f8f6a2a86866baa9bd75d0acd8ad909fcabd73a517ffc4b6855a98a49a0a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3a55f8f6a2a86866baa9bd75d0acd8ad909fcabd73a517ffc4b6855a98a49a0a","first_computed_at":"2026-07-05T05:08:18.391618Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:08:18.391618Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EeXfYxTGd3KckLS4DlSkCwgNJppikC9CFIQJiZeJm8yIqg85ZOXTrPyFOv+2ccspCItnYjqqQ2oW75ZyvhuBBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:08:18.392124Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.06423","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1c96c36d9956d664b436d4c44ff8721f554c48cb52518e0ab3cc9281656ed330","sha256:39f28c89cd1f9618971101c488c1d8d06691662322f1ba1a601f7a60f7fe70f7"],"state_sha256":"91f39f20d5f70e625cd93c3d10881a1f723bc7c22031da12c6eb97ba644aa963"}