{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:T7FE43FOOKB4W5KLUXB3I7TVNT","short_pith_number":"pith:T7FE43FO","canonical_record":{"source":{"id":"2211.08682","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-11-16T05:31:49Z","cross_cats_sorted":[],"title_canon_sha256":"ddb7233df7271c5df944f2f29cbadfa22fd577fa9ca5a0c3ba7e87e0a97e7305","abstract_canon_sha256":"ed183e3c1f78d021f22a54151f52edafc5a353c010bf3bd19ebfa7b81450dfef"},"schema_version":"1.0"},"canonical_sha256":"9fca4e6cae7283cb754ba5c3b47e756cf5e9d8d7e628f664fd0fda37ad8b990d","source":{"kind":"arxiv","id":"2211.08682","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.08682","created_at":"2026-07-05T05:23:47Z"},{"alias_kind":"arxiv_version","alias_value":"2211.08682v3","created_at":"2026-07-05T05:23:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.08682","created_at":"2026-07-05T05:23:47Z"},{"alias_kind":"pith_short_12","alias_value":"T7FE43FOOKB4","created_at":"2026-07-05T05:23:47Z"},{"alias_kind":"pith_short_16","alias_value":"T7FE43FOOKB4W5KL","created_at":"2026-07-05T05:23:47Z"},{"alias_kind":"pith_short_8","alias_value":"T7FE43FO","created_at":"2026-07-05T05:23:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:T7FE43FOOKB4W5KLUXB3I7TVNT","target":"record","payload":{"canonical_record":{"source":{"id":"2211.08682","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-11-16T05:31:49Z","cross_cats_sorted":[],"title_canon_sha256":"ddb7233df7271c5df944f2f29cbadfa22fd577fa9ca5a0c3ba7e87e0a97e7305","abstract_canon_sha256":"ed183e3c1f78d021f22a54151f52edafc5a353c010bf3bd19ebfa7b81450dfef"},"schema_version":"1.0"},"canonical_sha256":"9fca4e6cae7283cb754ba5c3b47e756cf5e9d8d7e628f664fd0fda37ad8b990d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:23:47.569412Z","signature_b64":"bk7P11wCDOQfRrC2K1LykGiup48unXyRYG8MEQ0p8Tp/Zextk43iNQ6LQ4IGookrqt5PaOe5zCduKGKAZH9PDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9fca4e6cae7283cb754ba5c3b47e756cf5e9d8d7e628f664fd0fda37ad8b990d","last_reissued_at":"2026-07-05T05:23:47.568906Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:23:47.568906Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2211.08682","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":"2026-07-05T05:23:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SVvAr9pvAzYK+mSKC61tkkRqTByVpMYUYksyUZrM4wzLJDA1SU3djSX321y5+NXyNAMeMxseWfyOEkRm3he9Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T13:42:33.591240Z"},"content_sha256":"7fc6b2dae5139d5901836fa3ea87954f4ace179b4a59be9c266da990ac4103ba","schema_version":"1.0","event_id":"sha256:7fc6b2dae5139d5901836fa3ea87954f4ace179b4a59be9c266da990ac4103ba"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:T7FE43FOOKB4W5KLUXB3I7TVNT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Parameter-Efficient Tuning on Layer Normalization for Pre-trained Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Taihao Li, Wang Qi, Yuan Zuo, Yu-Ping Ruan","submitted_at":"2022-11-16T05:31:49Z","abstract_excerpt":"Conventional fine-tuning encounters increasing difficulties given the size of current Pre-trained Language Models, which makes parameter-efficient tuning become the focal point of frontier research. Previous methods in this field add tunable adapters into MHA or/and FFN of Transformer blocks to enable PLMs achieve transferability. However, as an important part of Transformer architecture, the power of layer normalization for parameter-efficent tuning is ignored. In this paper, we first propose LN-tuning, by tuning the gain and bias term of Layer Normalization module with only 0.03\\% parameters"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.08682","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/2211.08682/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":"2026-07-05T05:23:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IU1sCFsnQ9Mb909TIujGhtjSosOenuKsh2NhWbelHKLCxinmcMK/HE+TUpLZSG3weMQlXX2S85ILu4yuMKRkBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T13:42:33.592037Z"},"content_sha256":"e0c3a46739c881e0784843df133c7ed723a5f437b3d7e96faf69861a935487d3","schema_version":"1.0","event_id":"sha256:e0c3a46739c881e0784843df133c7ed723a5f437b3d7e96faf69861a935487d3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/T7FE43FOOKB4W5KLUXB3I7TVNT/bundle.json","state_url":"https://pith.science/pith/T7FE43FOOKB4W5KLUXB3I7TVNT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/T7FE43FOOKB4W5KLUXB3I7TVNT/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":"2026-08-04T13:42:33Z","links":{"resolver":"https://pith.science/pith/T7FE43FOOKB4W5KLUXB3I7TVNT","bundle":"https://pith.science/pith/T7FE43FOOKB4W5KLUXB3I7TVNT/bundle.json","state":"https://pith.science/pith/T7FE43FOOKB4W5KLUXB3I7TVNT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/T7FE43FOOKB4W5KLUXB3I7TVNT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:T7FE43FOOKB4W5KLUXB3I7TVNT","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":"ed183e3c1f78d021f22a54151f52edafc5a353c010bf3bd19ebfa7b81450dfef","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-11-16T05:31:49Z","title_canon_sha256":"ddb7233df7271c5df944f2f29cbadfa22fd577fa9ca5a0c3ba7e87e0a97e7305"},"schema_version":"1.0","source":{"id":"2211.08682","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.08682","created_at":"2026-07-05T05:23:47Z"},{"alias_kind":"arxiv_version","alias_value":"2211.08682v3","created_at":"2026-07-05T05:23:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.08682","created_at":"2026-07-05T05:23:47Z"},{"alias_kind":"pith_short_12","alias_value":"T7FE43FOOKB4","created_at":"2026-07-05T05:23:47Z"},{"alias_kind":"pith_short_16","alias_value":"T7FE43FOOKB4W5KL","created_at":"2026-07-05T05:23:47Z"},{"alias_kind":"pith_short_8","alias_value":"T7FE43FO","created_at":"2026-07-05T05:23:47Z"}],"graph_snapshots":[{"event_id":"sha256:e0c3a46739c881e0784843df133c7ed723a5f437b3d7e96faf69861a935487d3","target":"graph","created_at":"2026-07-05T05:23:47Z","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/2211.08682/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Conventional fine-tuning encounters increasing difficulties given the size of current Pre-trained Language Models, which makes parameter-efficient tuning become the focal point of frontier research. Previous methods in this field add tunable adapters into MHA or/and FFN of Transformer blocks to enable PLMs achieve transferability. However, as an important part of Transformer architecture, the power of layer normalization for parameter-efficent tuning is ignored. In this paper, we first propose LN-tuning, by tuning the gain and bias term of Layer Normalization module with only 0.03\\% parameters","authors_text":"Taihao Li, Wang Qi, Yuan Zuo, Yu-Ping Ruan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-11-16T05:31:49Z","title":"Parameter-Efficient Tuning on Layer Normalization for Pre-trained Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.08682","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":"sha256:7fc6b2dae5139d5901836fa3ea87954f4ace179b4a59be9c266da990ac4103ba","target":"record","created_at":"2026-07-05T05:23:47Z","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":"ed183e3c1f78d021f22a54151f52edafc5a353c010bf3bd19ebfa7b81450dfef","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-11-16T05:31:49Z","title_canon_sha256":"ddb7233df7271c5df944f2f29cbadfa22fd577fa9ca5a0c3ba7e87e0a97e7305"},"schema_version":"1.0","source":{"id":"2211.08682","kind":"arxiv","version":3}},"canonical_sha256":"9fca4e6cae7283cb754ba5c3b47e756cf5e9d8d7e628f664fd0fda37ad8b990d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9fca4e6cae7283cb754ba5c3b47e756cf5e9d8d7e628f664fd0fda37ad8b990d","first_computed_at":"2026-07-05T05:23:47.568906Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:23:47.568906Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bk7P11wCDOQfRrC2K1LykGiup48unXyRYG8MEQ0p8Tp/Zextk43iNQ6LQ4IGookrqt5PaOe5zCduKGKAZH9PDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:23:47.569412Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.08682","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7fc6b2dae5139d5901836fa3ea87954f4ace179b4a59be9c266da990ac4103ba","sha256:e0c3a46739c881e0784843df133c7ed723a5f437b3d7e96faf69861a935487d3"],"state_sha256":"1cd30a5b7f22297cdb1bf723b6f63b6e979d65b607deb62455d27b1335af0baf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EpvQmkZ18XkOVeiyrIoLQdgqW4sEVn8Fn18t2JgAfGHSmdK86ALHPIGiapZ2dJ201MFGhRxXjNdfr0LTBdqgCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T13:42:33.597717Z","bundle_sha256":"2e6c865f84e6c057d20c59b09cd901772f4d70477ad7049ce837627dbd1f7077"}}