{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:2YE4ZXKGPZUHTAA7M2B3DCH3DZ","short_pith_number":"pith:2YE4ZXKG","canonical_record":{"source":{"id":"2507.02559","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-03T12:09:04Z","cross_cats_sorted":[],"title_canon_sha256":"b1d197f169531850ca65199f15257dab8595f442fbaa03b06fa88516146c503f","abstract_canon_sha256":"5c5a03a6047b363ff56e3aa92c13d9128bbd449b27d361b095644215be75d66d"},"schema_version":"1.0"},"canonical_sha256":"d609ccdd467e6879801f6683b188fb1e6dd985781bcdfc3acde9b133e6e3bc4f","source":{"kind":"arxiv","id":"2507.02559","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.02559","created_at":"2026-07-05T11:31:30Z"},{"alias_kind":"arxiv_version","alias_value":"2507.02559v1","created_at":"2026-07-05T11:31:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.02559","created_at":"2026-07-05T11:31:30Z"},{"alias_kind":"pith_short_12","alias_value":"2YE4ZXKGPZUH","created_at":"2026-07-05T11:31:30Z"},{"alias_kind":"pith_short_16","alias_value":"2YE4ZXKGPZUHTAA7","created_at":"2026-07-05T11:31:30Z"},{"alias_kind":"pith_short_8","alias_value":"2YE4ZXKG","created_at":"2026-07-05T11:31:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:2YE4ZXKGPZUHTAA7M2B3DCH3DZ","target":"record","payload":{"canonical_record":{"source":{"id":"2507.02559","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-03T12:09:04Z","cross_cats_sorted":[],"title_canon_sha256":"b1d197f169531850ca65199f15257dab8595f442fbaa03b06fa88516146c503f","abstract_canon_sha256":"5c5a03a6047b363ff56e3aa92c13d9128bbd449b27d361b095644215be75d66d"},"schema_version":"1.0"},"canonical_sha256":"d609ccdd467e6879801f6683b188fb1e6dd985781bcdfc3acde9b133e6e3bc4f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:31:30.864914Z","signature_b64":"yhRaxS6d9Trn45OeaN29X4tKSkEmP7WnBDgvpaDtpDBNsEkX0xnxtHGm8iXUGNAJQUN+lpP9TV/nVkWr0v5gDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d609ccdd467e6879801f6683b188fb1e6dd985781bcdfc3acde9b133e6e3bc4f","last_reissued_at":"2026-07-05T11:31:30.864554Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:31:30.864554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.02559","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:31:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YzLgOp8acdFWpHh02QiA62sMSOIPkKC9M6uWrPSpbtrXH5KzgXyrIOsejm0qVkYHPSHkGZYvY3TJVSgn+C6lCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T04:43:53.036914Z"},"content_sha256":"885fb8fd9b645cdeb9b798e0eeab794f1a5f630485a4481899d247a6f0dbbf7b","schema_version":"1.0","event_id":"sha256:885fb8fd9b645cdeb9b798e0eeab794f1a5f630485a4481899d247a6f0dbbf7b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:2YE4ZXKGPZUHTAA7M2B3DCH3DZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Transformers Don't Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and the Implications for Mechanistic Interpretability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Galvin Khara, Joachim Schaeffer, Luca Baroni, Marat Subkhankulov, Stefan Heimersheim","submitted_at":"2025-07-03T12:09:04Z","abstract_excerpt":"Layer-wise normalization (LN) is an essential component of virtually all transformer-based large language models. While its effects on training stability are well documented, its role at inference time is poorly understood. Additionally, LN layers hinder mechanistic interpretability by introducing additional nonlinearities and increasing the interconnectedness of individual model components. Here, we show that all LN layers can be removed from every GPT-2 model with only a small increase in validation loss (e.g. +0.03 cross-entropy loss for GPT-2 XL). Thus, LN cannot play a substantial role in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.02559","kind":"arxiv","version":1},"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/2507.02559/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":"2026-07-05T11:31:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dZyxVlrVpJcGSdoCWrichs3Z0i9SfrNNW2EiIZYqnXraVVcexFmWgoMxKeGEVX0TB0Z5uzInuCat9uZ1fzuGBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T04:43:53.037405Z"},"content_sha256":"ac2332981878e42acb57c15f6b1ac1b5bb6cc920ff9f4520425eecf37fb4092a","schema_version":"1.0","event_id":"sha256:ac2332981878e42acb57c15f6b1ac1b5bb6cc920ff9f4520425eecf37fb4092a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2YE4ZXKGPZUHTAA7M2B3DCH3DZ/bundle.json","state_url":"https://pith.science/pith/2YE4ZXKGPZUHTAA7M2B3DCH3DZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2YE4ZXKGPZUHTAA7M2B3DCH3DZ/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":"2026-08-08T04:43:53Z","links":{"resolver":"https://pith.science/pith/2YE4ZXKGPZUHTAA7M2B3DCH3DZ","bundle":"https://pith.science/pith/2YE4ZXKGPZUHTAA7M2B3DCH3DZ/bundle.json","state":"https://pith.science/pith/2YE4ZXKGPZUHTAA7M2B3DCH3DZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2YE4ZXKGPZUHTAA7M2B3DCH3DZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2YE4ZXKGPZUHTAA7M2B3DCH3DZ","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":"5c5a03a6047b363ff56e3aa92c13d9128bbd449b27d361b095644215be75d66d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-03T12:09:04Z","title_canon_sha256":"b1d197f169531850ca65199f15257dab8595f442fbaa03b06fa88516146c503f"},"schema_version":"1.0","source":{"id":"2507.02559","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.02559","created_at":"2026-07-05T11:31:30Z"},{"alias_kind":"arxiv_version","alias_value":"2507.02559v1","created_at":"2026-07-05T11:31:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.02559","created_at":"2026-07-05T11:31:30Z"},{"alias_kind":"pith_short_12","alias_value":"2YE4ZXKGPZUH","created_at":"2026-07-05T11:31:30Z"},{"alias_kind":"pith_short_16","alias_value":"2YE4ZXKGPZUHTAA7","created_at":"2026-07-05T11:31:30Z"},{"alias_kind":"pith_short_8","alias_value":"2YE4ZXKG","created_at":"2026-07-05T11:31:30Z"}],"graph_snapshots":[{"event_id":"sha256:ac2332981878e42acb57c15f6b1ac1b5bb6cc920ff9f4520425eecf37fb4092a","target":"graph","created_at":"2026-07-05T11:31:30Z","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/2507.02559/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Layer-wise normalization (LN) is an essential component of virtually all transformer-based large language models. While its effects on training stability are well documented, its role at inference time is poorly understood. Additionally, LN layers hinder mechanistic interpretability by introducing additional nonlinearities and increasing the interconnectedness of individual model components. Here, we show that all LN layers can be removed from every GPT-2 model with only a small increase in validation loss (e.g. +0.03 cross-entropy loss for GPT-2 XL). Thus, LN cannot play a substantial role in","authors_text":"Galvin Khara, Joachim Schaeffer, Luca Baroni, Marat Subkhankulov, Stefan Heimersheim","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-03T12:09:04Z","title":"Transformers Don't Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and the Implications for Mechanistic Interpretability"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.02559","kind":"arxiv","version":1},"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":"sha256:885fb8fd9b645cdeb9b798e0eeab794f1a5f630485a4481899d247a6f0dbbf7b","target":"record","created_at":"2026-07-05T11:31:30Z","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":"5c5a03a6047b363ff56e3aa92c13d9128bbd449b27d361b095644215be75d66d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-03T12:09:04Z","title_canon_sha256":"b1d197f169531850ca65199f15257dab8595f442fbaa03b06fa88516146c503f"},"schema_version":"1.0","source":{"id":"2507.02559","kind":"arxiv","version":1}},"canonical_sha256":"d609ccdd467e6879801f6683b188fb1e6dd985781bcdfc3acde9b133e6e3bc4f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d609ccdd467e6879801f6683b188fb1e6dd985781bcdfc3acde9b133e6e3bc4f","first_computed_at":"2026-07-05T11:31:30.864554Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:31:30.864554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yhRaxS6d9Trn45OeaN29X4tKSkEmP7WnBDgvpaDtpDBNsEkX0xnxtHGm8iXUGNAJQUN+lpP9TV/nVkWr0v5gDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:31:30.864914Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.02559","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:885fb8fd9b645cdeb9b798e0eeab794f1a5f630485a4481899d247a6f0dbbf7b","sha256:ac2332981878e42acb57c15f6b1ac1b5bb6cc920ff9f4520425eecf37fb4092a"],"state_sha256":"72f06337f26faa1d565808fc16e7026e6fdd7bd9e24dfee28e5e89822d743829"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VatXzQU1WjWIFF8o8G3AVc1BqyWOc5WAlEN/Xb0y58MBGRcek1VlV7FcxKZCHzmh5Nk0Rdzqt5YB565ObYfOCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T04:43:53.040768Z","bundle_sha256":"a44c58f01ff18cad643022dca6200f9809f52641988781ced42b8a6f6c2e0a31"}}