{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:FEEIFRFK54XOQGA3N2SFISZPSP","short_pith_number":"pith:FEEIFRFK","canonical_record":{"source":{"id":"2311.01906","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-03T13:30:52Z","cross_cats_sorted":[],"title_canon_sha256":"b73f715e1d4b17f76fd2aa6abb6758f2f751514af4a7758caa2fae98d615dfbc","abstract_canon_sha256":"7fa5cc5b42d28afe6d23f668a57f90263e5311cfb41c22a4b6bfeffe79ef25be"},"schema_version":"1.0"},"canonical_sha256":"290882c4aaef2ee8181b6ea4544b2f93ffa9574730a16857057ca716da20ccc6","source":{"kind":"arxiv","id":"2311.01906","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.01906","created_at":"2026-07-05T08:25:29Z"},{"alias_kind":"arxiv_version","alias_value":"2311.01906v2","created_at":"2026-07-05T08:25:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.01906","created_at":"2026-07-05T08:25:29Z"},{"alias_kind":"pith_short_12","alias_value":"FEEIFRFK54XO","created_at":"2026-07-05T08:25:29Z"},{"alias_kind":"pith_short_16","alias_value":"FEEIFRFK54XOQGA3","created_at":"2026-07-05T08:25:29Z"},{"alias_kind":"pith_short_8","alias_value":"FEEIFRFK","created_at":"2026-07-05T08:25:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:FEEIFRFK54XOQGA3N2SFISZPSP","target":"record","payload":{"canonical_record":{"source":{"id":"2311.01906","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-03T13:30:52Z","cross_cats_sorted":[],"title_canon_sha256":"b73f715e1d4b17f76fd2aa6abb6758f2f751514af4a7758caa2fae98d615dfbc","abstract_canon_sha256":"7fa5cc5b42d28afe6d23f668a57f90263e5311cfb41c22a4b6bfeffe79ef25be"},"schema_version":"1.0"},"canonical_sha256":"290882c4aaef2ee8181b6ea4544b2f93ffa9574730a16857057ca716da20ccc6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:29.605098Z","signature_b64":"tPh+ijSktbSvsVRCsBOin9vsOfs4i7pPsObGurgdsOY/9/dQ3sR+8vg+OjGQTZ4KHhf4Or0+W90wpUh2kOsbDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"290882c4aaef2ee8181b6ea4544b2f93ffa9574730a16857057ca716da20ccc6","last_reissued_at":"2026-07-05T08:25:29.604641Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:29.604641Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.01906","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:25:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4v9wEPm/Ox/xInderlty4tiuvOn+HlBTfX8gDXPZLe4d837OmJGRsUH3jZWClXd14yND+aWWrBJCO6/qsJ11Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T07:50:38.455968Z"},"content_sha256":"c9989319b0d5b992335534eb14313a2ab8d9bc913ac07dbb490781582b9bc5e9","schema_version":"1.0","event_id":"sha256:c9989319b0d5b992335534eb14313a2ab8d9bc913ac07dbb490781582b9bc5e9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:FEEIFRFK54XOQGA3N2SFISZPSP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Simplifying Transformer Blocks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bobby He, Thomas Hofmann","submitted_at":"2023-11-03T13:30:52Z","abstract_excerpt":"A simple design recipe for deep Transformers is to compose identical building blocks. But standard transformer blocks are far from simple, interweaving attention and MLP sub-blocks with skip connections & normalisation layers in precise arrangements. This complexity leads to brittle architectures, where seemingly minor changes can significantly reduce training speed, or render models untrainable.\n  In this work, we ask to what extent the standard transformer block can be simplified? Combining signal propagation theory and empirical observations, we motivate modifications that allow many block "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.01906","kind":"arxiv","version":2},"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/2311.01906/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:25:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GHpTpajfGvs9L4CLPpnu/pAY7e8vgApjII5D2z3h9RE26E/f+31CBGVsJttKDY3GWWp6XLobjqw6cnAz9S2DDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T07:50:38.457719Z"},"content_sha256":"c9ea7449f67c7c17acf0f8b1c00dfd2473f366f939f2c06dc207f29d51281d39","schema_version":"1.0","event_id":"sha256:c9ea7449f67c7c17acf0f8b1c00dfd2473f366f939f2c06dc207f29d51281d39"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FEEIFRFK54XOQGA3N2SFISZPSP/bundle.json","state_url":"https://pith.science/pith/FEEIFRFK54XOQGA3N2SFISZPSP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FEEIFRFK54XOQGA3N2SFISZPSP/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-06T07:50:38Z","links":{"resolver":"https://pith.science/pith/FEEIFRFK54XOQGA3N2SFISZPSP","bundle":"https://pith.science/pith/FEEIFRFK54XOQGA3N2SFISZPSP/bundle.json","state":"https://pith.science/pith/FEEIFRFK54XOQGA3N2SFISZPSP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FEEIFRFK54XOQGA3N2SFISZPSP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:FEEIFRFK54XOQGA3N2SFISZPSP","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":"7fa5cc5b42d28afe6d23f668a57f90263e5311cfb41c22a4b6bfeffe79ef25be","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-03T13:30:52Z","title_canon_sha256":"b73f715e1d4b17f76fd2aa6abb6758f2f751514af4a7758caa2fae98d615dfbc"},"schema_version":"1.0","source":{"id":"2311.01906","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.01906","created_at":"2026-07-05T08:25:29Z"},{"alias_kind":"arxiv_version","alias_value":"2311.01906v2","created_at":"2026-07-05T08:25:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.01906","created_at":"2026-07-05T08:25:29Z"},{"alias_kind":"pith_short_12","alias_value":"FEEIFRFK54XO","created_at":"2026-07-05T08:25:29Z"},{"alias_kind":"pith_short_16","alias_value":"FEEIFRFK54XOQGA3","created_at":"2026-07-05T08:25:29Z"},{"alias_kind":"pith_short_8","alias_value":"FEEIFRFK","created_at":"2026-07-05T08:25:29Z"}],"graph_snapshots":[{"event_id":"sha256:c9ea7449f67c7c17acf0f8b1c00dfd2473f366f939f2c06dc207f29d51281d39","target":"graph","created_at":"2026-07-05T08:25:29Z","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/2311.01906/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A simple design recipe for deep Transformers is to compose identical building blocks. But standard transformer blocks are far from simple, interweaving attention and MLP sub-blocks with skip connections & normalisation layers in precise arrangements. This complexity leads to brittle architectures, where seemingly minor changes can significantly reduce training speed, or render models untrainable.\n  In this work, we ask to what extent the standard transformer block can be simplified? Combining signal propagation theory and empirical observations, we motivate modifications that allow many block ","authors_text":"Bobby He, Thomas Hofmann","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-03T13:30:52Z","title":"Simplifying Transformer Blocks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.01906","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:c9989319b0d5b992335534eb14313a2ab8d9bc913ac07dbb490781582b9bc5e9","target":"record","created_at":"2026-07-05T08:25:29Z","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":"7fa5cc5b42d28afe6d23f668a57f90263e5311cfb41c22a4b6bfeffe79ef25be","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-03T13:30:52Z","title_canon_sha256":"b73f715e1d4b17f76fd2aa6abb6758f2f751514af4a7758caa2fae98d615dfbc"},"schema_version":"1.0","source":{"id":"2311.01906","kind":"arxiv","version":2}},"canonical_sha256":"290882c4aaef2ee8181b6ea4544b2f93ffa9574730a16857057ca716da20ccc6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"290882c4aaef2ee8181b6ea4544b2f93ffa9574730a16857057ca716da20ccc6","first_computed_at":"2026-07-05T08:25:29.604641Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:25:29.604641Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tPh+ijSktbSvsVRCsBOin9vsOfs4i7pPsObGurgdsOY/9/dQ3sR+8vg+OjGQTZ4KHhf4Or0+W90wpUh2kOsbDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:25:29.605098Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.01906","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c9989319b0d5b992335534eb14313a2ab8d9bc913ac07dbb490781582b9bc5e9","sha256:c9ea7449f67c7c17acf0f8b1c00dfd2473f366f939f2c06dc207f29d51281d39"],"state_sha256":"a1420298a92bb6e0b0a062984b3a71199f39a471e2aaff09331fa84d48d30a75"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lf2amAZcW1cMYlyMBVcDgVihnwylHCruEHmKBkT5njVfHcM8Gfm5neMq3TEQEYdUiXhjhHyNc5Iya5KWBXBPCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T07:50:38.466735Z","bundle_sha256":"44286a3645c2f809c8f15d53314c085cf6d58eee7ccc29ae092f299dc635f33c"}}