{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:INJYUQJTVMXV6QDXD6YCPKYPPQ","short_pith_number":"pith:INJYUQJT","canonical_record":{"source":{"id":"2505.08463","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-13T11:47:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6846243965a3bc925104a46d26740f5eb7298fe592a8990fe033ce708f7af0f3","abstract_canon_sha256":"83562e54d86dc463927f73b6d6a0fb925f1152c79901801594c091b66c385df5"},"schema_version":"1.0"},"canonical_sha256":"43538a4133ab2f5f40771fb027ab0f7c0907e38ee5fabf0da6ec231fe723b058","source":{"kind":"arxiv","id":"2505.08463","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.08463","created_at":"2026-07-05T11:11:44Z"},{"alias_kind":"arxiv_version","alias_value":"2505.08463v2","created_at":"2026-07-05T11:11:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.08463","created_at":"2026-07-05T11:11:44Z"},{"alias_kind":"pith_short_12","alias_value":"INJYUQJTVMXV","created_at":"2026-07-05T11:11:44Z"},{"alias_kind":"pith_short_16","alias_value":"INJYUQJTVMXV6QDX","created_at":"2026-07-05T11:11:44Z"},{"alias_kind":"pith_short_8","alias_value":"INJYUQJT","created_at":"2026-07-05T11:11:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:INJYUQJTVMXV6QDXD6YCPKYPPQ","target":"record","payload":{"canonical_record":{"source":{"id":"2505.08463","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-13T11:47:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6846243965a3bc925104a46d26740f5eb7298fe592a8990fe033ce708f7af0f3","abstract_canon_sha256":"83562e54d86dc463927f73b6d6a0fb925f1152c79901801594c091b66c385df5"},"schema_version":"1.0"},"canonical_sha256":"43538a4133ab2f5f40771fb027ab0f7c0907e38ee5fabf0da6ec231fe723b058","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:44.846328Z","signature_b64":"nku8SpS3C3JNSHOH+VyOUyA8TNgeEh/o8kx8tZd1FdOhNBDe2GhHHyterbvR2dsKNEFWOg7fd7f0vQh0pTQgDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"43538a4133ab2f5f40771fb027ab0f7c0907e38ee5fabf0da6ec231fe723b058","last_reissued_at":"2026-07-05T11:11:44.845845Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:44.845845Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.08463","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":"2026-07-05T11:11:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vhC7me6x0RqfTUFjAHbfu1LC/Q7NYgFXLhiRP2tESL3QDZ7RtREx9b4a+ZT9cVnGHZ7lycovWAJgQa8mGn1TBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T12:36:26.629231Z"},"content_sha256":"ea3d55f576646434794309dc24b60ee0fe51c7731396333c87565c4d3d8d0716","schema_version":"1.0","event_id":"sha256:ea3d55f576646434794309dc24b60ee0fe51c7731396333c87565c4d3d8d0716"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:INJYUQJTVMXV6QDXD6YCPKYPPQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RepCali: High Efficient Fine-tuning Via Representation Calibration in Latent Space for Pre-trained Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Fujun Zhang, Guanglai Gao, Xiangdong Su, Xiaoying Fan","submitted_at":"2025-05-13T11:47:00Z","abstract_excerpt":"Fine-tuning pre-trained language models (PLMs) has become a dominant paradigm in applying PLMs to downstream tasks. However, with limited fine-tuning, PLMs still struggle with the discrepancies between the representation obtained from the PLMs' encoder and the optimal input to the PLMs' decoder. This paper tackles this challenge by learning to calibrate the representation of PLMs in the latent space. In the proposed representation calibration method (RepCali), we integrate a specific calibration block to the latent space after the encoder and use the calibrated output as the decoder input. The"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.08463","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/2505.08463/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":"2026-07-05T11:11:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6prC8F5ceQaY1qzrE6dqJ3bCjBnQyJOHqdzXVZVUCXNbqpCNSA4rCwOBDEO9uL3gUkmXsmkHe0BIvK9JBQfODA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T12:36:26.629733Z"},"content_sha256":"76a431c5eb7b8886d0eef3f16cd691030a382f6dd6bdcd2188272954a1bd478c","schema_version":"1.0","event_id":"sha256:76a431c5eb7b8886d0eef3f16cd691030a382f6dd6bdcd2188272954a1bd478c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/INJYUQJTVMXV6QDXD6YCPKYPPQ/bundle.json","state_url":"https://pith.science/pith/INJYUQJTVMXV6QDXD6YCPKYPPQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/INJYUQJTVMXV6QDXD6YCPKYPPQ/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":"2026-08-18T12:36:26Z","links":{"resolver":"https://pith.science/pith/INJYUQJTVMXV6QDXD6YCPKYPPQ","bundle":"https://pith.science/pith/INJYUQJTVMXV6QDXD6YCPKYPPQ/bundle.json","state":"https://pith.science/pith/INJYUQJTVMXV6QDXD6YCPKYPPQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/INJYUQJTVMXV6QDXD6YCPKYPPQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:INJYUQJTVMXV6QDXD6YCPKYPPQ","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":"83562e54d86dc463927f73b6d6a0fb925f1152c79901801594c091b66c385df5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-13T11:47:00Z","title_canon_sha256":"6846243965a3bc925104a46d26740f5eb7298fe592a8990fe033ce708f7af0f3"},"schema_version":"1.0","source":{"id":"2505.08463","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.08463","created_at":"2026-07-05T11:11:44Z"},{"alias_kind":"arxiv_version","alias_value":"2505.08463v2","created_at":"2026-07-05T11:11:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.08463","created_at":"2026-07-05T11:11:44Z"},{"alias_kind":"pith_short_12","alias_value":"INJYUQJTVMXV","created_at":"2026-07-05T11:11:44Z"},{"alias_kind":"pith_short_16","alias_value":"INJYUQJTVMXV6QDX","created_at":"2026-07-05T11:11:44Z"},{"alias_kind":"pith_short_8","alias_value":"INJYUQJT","created_at":"2026-07-05T11:11:44Z"}],"graph_snapshots":[{"event_id":"sha256:76a431c5eb7b8886d0eef3f16cd691030a382f6dd6bdcd2188272954a1bd478c","target":"graph","created_at":"2026-07-05T11:11:44Z","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/2505.08463/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fine-tuning pre-trained language models (PLMs) has become a dominant paradigm in applying PLMs to downstream tasks. However, with limited fine-tuning, PLMs still struggle with the discrepancies between the representation obtained from the PLMs' encoder and the optimal input to the PLMs' decoder. This paper tackles this challenge by learning to calibrate the representation of PLMs in the latent space. In the proposed representation calibration method (RepCali), we integrate a specific calibration block to the latent space after the encoder and use the calibrated output as the decoder input. The","authors_text":"Fujun Zhang, Guanglai Gao, Xiangdong Su, Xiaoying Fan","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-13T11:47:00Z","title":"RepCali: High Efficient Fine-tuning Via Representation Calibration in Latent Space for Pre-trained Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.08463","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:ea3d55f576646434794309dc24b60ee0fe51c7731396333c87565c4d3d8d0716","target":"record","created_at":"2026-07-05T11:11:44Z","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":"83562e54d86dc463927f73b6d6a0fb925f1152c79901801594c091b66c385df5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-13T11:47:00Z","title_canon_sha256":"6846243965a3bc925104a46d26740f5eb7298fe592a8990fe033ce708f7af0f3"},"schema_version":"1.0","source":{"id":"2505.08463","kind":"arxiv","version":2}},"canonical_sha256":"43538a4133ab2f5f40771fb027ab0f7c0907e38ee5fabf0da6ec231fe723b058","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"43538a4133ab2f5f40771fb027ab0f7c0907e38ee5fabf0da6ec231fe723b058","first_computed_at":"2026-07-05T11:11:44.845845Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:11:44.845845Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nku8SpS3C3JNSHOH+VyOUyA8TNgeEh/o8kx8tZd1FdOhNBDe2GhHHyterbvR2dsKNEFWOg7fd7f0vQh0pTQgDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:11:44.846328Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.08463","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ea3d55f576646434794309dc24b60ee0fe51c7731396333c87565c4d3d8d0716","sha256:76a431c5eb7b8886d0eef3f16cd691030a382f6dd6bdcd2188272954a1bd478c"],"state_sha256":"bff8a913b69f96fa9fe15214329191021e55e7b258bb98733d6547c39b737228"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gZ/hxkEX31SEUl/xxVNY37Y2M3LUXHX/iGb/wdBX32x1AXceO1E2M3BApWySIcFf+yRlM/riRgKJwJsdkJapDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T12:36:26.634795Z","bundle_sha256":"47f5b16ad0817eb22a7e05fd044ab3d1e8617f83ca84afb2c5c340f5b8936fcd"}}