{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:76BGFZKK5NALYB5IDX2333BACX","short_pith_number":"pith:76BGFZKK","canonical_record":{"source":{"id":"2601.09719","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-12-26T06:22:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"df7abdf6d515e2a6bdb2d584a5001bd00bc4304fe9653ea3549076733f7327ae","abstract_canon_sha256":"d742b22a8d3a19096c37bdd0cba4cd9dc11ee5d9b7a7a21db1f8271c796ef3d7"},"schema_version":"1.0"},"canonical_sha256":"ff8262e54aeb40bc07a81df5bdec2015ffb0eb237f3db1e7025f1569cdeaac85","source":{"kind":"arxiv","id":"2601.09719","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.09719","created_at":"2026-06-04T01:09:41Z"},{"alias_kind":"arxiv_version","alias_value":"2601.09719v3","created_at":"2026-06-04T01:09:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.09719","created_at":"2026-06-04T01:09:41Z"},{"alias_kind":"pith_short_12","alias_value":"76BGFZKK5NAL","created_at":"2026-06-04T01:09:41Z"},{"alias_kind":"pith_short_16","alias_value":"76BGFZKK5NALYB5I","created_at":"2026-06-04T01:09:41Z"},{"alias_kind":"pith_short_8","alias_value":"76BGFZKK","created_at":"2026-06-04T01:09:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:76BGFZKK5NALYB5IDX2333BACX","target":"record","payload":{"canonical_record":{"source":{"id":"2601.09719","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-12-26T06:22:13Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"df7abdf6d515e2a6bdb2d584a5001bd00bc4304fe9653ea3549076733f7327ae","abstract_canon_sha256":"d742b22a8d3a19096c37bdd0cba4cd9dc11ee5d9b7a7a21db1f8271c796ef3d7"},"schema_version":"1.0"},"canonical_sha256":"ff8262e54aeb40bc07a81df5bdec2015ffb0eb237f3db1e7025f1569cdeaac85","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:09:41.044351Z","signature_b64":"5yK2iciWAwOxlsHEM/YLAk0N/4/hpDigg8qEu8oJz3JiNL8+ZQJBaQISgpYcz/Yu4He/IHp3EaXJKtaH24CcCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff8262e54aeb40bc07a81df5bdec2015ffb0eb237f3db1e7025f1569cdeaac85","last_reissued_at":"2026-06-04T01:09:41.043792Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:09:41.043792Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2601.09719","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-04T01:09:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Tj8TBWajJZB/OFOJi6IHdj0rEru7UeiEixXmb8Rj8oaCTG6oXEGWzcBQuCBa5+3N8ewJ33wtK1blUufN+Mr3BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T09:00:55.267497Z"},"content_sha256":"bc8e2b870c2d7aad21dc14f4b3079c89bcb0a5e22f11eee711e9b8e7cbffbfd3","schema_version":"1.0","event_id":"sha256:bc8e2b870c2d7aad21dc14f4b3079c89bcb0a5e22f11eee711e9b8e7cbffbfd3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:76BGFZKK5NALYB5IDX2333BACX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Bounded Hyperbolic Tangent: A Stable and Efficient Alternative to Pre-Layer Normalization in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hoyoon Byun, Kyungwoo Song, Sungrae Park, Taero Kim, Youngjun Choi","submitted_at":"2025-12-26T06:22:13Z","abstract_excerpt":"Pre-Layer Normalization (Pre-LN) is the de facto choice for large language models (LLMs) and is crucial for stable pretraining and effective transfer learning. However, Pre-LN incurs repeated statistical-computation overhead and remains vulnerable to the curse of depth, where hidden-state magnitudes and variances grow as the number of layers increases, destabilizing training. Efficiency-oriented normalization-free methods such as Dynamic Tanh (DyT) improve throughput but remain fragile at depth. To jointly address stability and efficiency, we propose Bounded Hyperbolic Tanh (BHyT), a drop-in r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.09719","kind":"arxiv","version":3},"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/2601.09719/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":"2026-06-04T01:09:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+KwZaEI79VDtX7Q98yP+wRoBLc9YzbFB27U3R4f0pK491zmuJOIED4d+WAdPv4DCvhhnUIZVu4UfO4DPOho/Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T09:00:55.267876Z"},"content_sha256":"666e438e8ae5352516510d5be76c5262d5e263cdcaf88632dbf21fafea647d6d","schema_version":"1.0","event_id":"sha256:666e438e8ae5352516510d5be76c5262d5e263cdcaf88632dbf21fafea647d6d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/76BGFZKK5NALYB5IDX2333BACX/bundle.json","state_url":"https://pith.science/pith/76BGFZKK5NALYB5IDX2333BACX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/76BGFZKK5NALYB5IDX2333BACX/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":"2026-06-10T09:00:55Z","links":{"resolver":"https://pith.science/pith/76BGFZKK5NALYB5IDX2333BACX","bundle":"https://pith.science/pith/76BGFZKK5NALYB5IDX2333BACX/bundle.json","state":"https://pith.science/pith/76BGFZKK5NALYB5IDX2333BACX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/76BGFZKK5NALYB5IDX2333BACX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:76BGFZKK5NALYB5IDX2333BACX","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":"d742b22a8d3a19096c37bdd0cba4cd9dc11ee5d9b7a7a21db1f8271c796ef3d7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-12-26T06:22:13Z","title_canon_sha256":"df7abdf6d515e2a6bdb2d584a5001bd00bc4304fe9653ea3549076733f7327ae"},"schema_version":"1.0","source":{"id":"2601.09719","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.09719","created_at":"2026-06-04T01:09:41Z"},{"alias_kind":"arxiv_version","alias_value":"2601.09719v3","created_at":"2026-06-04T01:09:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.09719","created_at":"2026-06-04T01:09:41Z"},{"alias_kind":"pith_short_12","alias_value":"76BGFZKK5NAL","created_at":"2026-06-04T01:09:41Z"},{"alias_kind":"pith_short_16","alias_value":"76BGFZKK5NALYB5I","created_at":"2026-06-04T01:09:41Z"},{"alias_kind":"pith_short_8","alias_value":"76BGFZKK","created_at":"2026-06-04T01:09:41Z"}],"graph_snapshots":[{"event_id":"sha256:666e438e8ae5352516510d5be76c5262d5e263cdcaf88632dbf21fafea647d6d","target":"graph","created_at":"2026-06-04T01:09:41Z","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/2601.09719/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-Layer Normalization (Pre-LN) is the de facto choice for large language models (LLMs) and is crucial for stable pretraining and effective transfer learning. However, Pre-LN incurs repeated statistical-computation overhead and remains vulnerable to the curse of depth, where hidden-state magnitudes and variances grow as the number of layers increases, destabilizing training. Efficiency-oriented normalization-free methods such as Dynamic Tanh (DyT) improve throughput but remain fragile at depth. To jointly address stability and efficiency, we propose Bounded Hyperbolic Tanh (BHyT), a drop-in r","authors_text":"Hoyoon Byun, Kyungwoo Song, Sungrae Park, Taero Kim, Youngjun Choi","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-12-26T06:22:13Z","title":"Bounded Hyperbolic Tangent: A Stable and Efficient Alternative to Pre-Layer Normalization in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.09719","kind":"arxiv","version":3},"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:bc8e2b870c2d7aad21dc14f4b3079c89bcb0a5e22f11eee711e9b8e7cbffbfd3","target":"record","created_at":"2026-06-04T01:09:41Z","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":"d742b22a8d3a19096c37bdd0cba4cd9dc11ee5d9b7a7a21db1f8271c796ef3d7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-12-26T06:22:13Z","title_canon_sha256":"df7abdf6d515e2a6bdb2d584a5001bd00bc4304fe9653ea3549076733f7327ae"},"schema_version":"1.0","source":{"id":"2601.09719","kind":"arxiv","version":3}},"canonical_sha256":"ff8262e54aeb40bc07a81df5bdec2015ffb0eb237f3db1e7025f1569cdeaac85","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ff8262e54aeb40bc07a81df5bdec2015ffb0eb237f3db1e7025f1569cdeaac85","first_computed_at":"2026-06-04T01:09:41.043792Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-04T01:09:41.043792Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5yK2iciWAwOxlsHEM/YLAk0N/4/hpDigg8qEu8oJz3JiNL8+ZQJBaQISgpYcz/Yu4He/IHp3EaXJKtaH24CcCw==","signature_status":"signed_v1","signed_at":"2026-06-04T01:09:41.044351Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.09719","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bc8e2b870c2d7aad21dc14f4b3079c89bcb0a5e22f11eee711e9b8e7cbffbfd3","sha256:666e438e8ae5352516510d5be76c5262d5e263cdcaf88632dbf21fafea647d6d"],"state_sha256":"aa9c246fb671a2e4fb444e7483a2e3f02056dbfe2b584d882fdec9b257c1b3c8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q9YnTz6bVaLJfio/GdEHAV8eF9xtsgd8FnuHX7y5nYXxffQPrU3QUe4jC1c0HyODaXGIqU83FPI2ZaEB7c3EBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T09:00:55.271062Z","bundle_sha256":"bf491445a6e4297b456aed7bc4d3202a431e3572f9ff30078fd39aa4beed93b9"}}