{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:ECGIOME7FAPTGMQP2RZFQCJACF","short_pith_number":"pith:ECGIOME7","canonical_record":{"source":{"id":"2203.11431","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-22T03:11:39Z","cross_cats_sorted":[],"title_canon_sha256":"fd210b9c9331bb929b4a1dc6d59ab801efb2156d9e35afb8f25797a507282afa","abstract_canon_sha256":"e8f8f7ede239987f2aba656a47b6a0ac4298b669bdaa43d9cc9efb163ee337b8"},"schema_version":"1.0"},"canonical_sha256":"208c87309f281f33320fd4725809201171810988cb6e2414f513e83f9e70730f","source":{"kind":"arxiv","id":"2203.11431","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.11431","created_at":"2026-07-05T04:07:12Z"},{"alias_kind":"arxiv_version","alias_value":"2203.11431v1","created_at":"2026-07-05T04:07:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.11431","created_at":"2026-07-05T04:07:12Z"},{"alias_kind":"pith_short_12","alias_value":"ECGIOME7FAPT","created_at":"2026-07-05T04:07:12Z"},{"alias_kind":"pith_short_16","alias_value":"ECGIOME7FAPTGMQP","created_at":"2026-07-05T04:07:12Z"},{"alias_kind":"pith_short_8","alias_value":"ECGIOME7","created_at":"2026-07-05T04:07:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:ECGIOME7FAPTGMQP2RZFQCJACF","target":"record","payload":{"canonical_record":{"source":{"id":"2203.11431","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-22T03:11:39Z","cross_cats_sorted":[],"title_canon_sha256":"fd210b9c9331bb929b4a1dc6d59ab801efb2156d9e35afb8f25797a507282afa","abstract_canon_sha256":"e8f8f7ede239987f2aba656a47b6a0ac4298b669bdaa43d9cc9efb163ee337b8"},"schema_version":"1.0"},"canonical_sha256":"208c87309f281f33320fd4725809201171810988cb6e2414f513e83f9e70730f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:07:12.130499Z","signature_b64":"G+EFjD6VXk3gAI+CJwu/b5yIpVy2pMWm3u2P/tiGzmIQUgtuX6oIlewn6SDi7MQebbzELBfBLODPPV6qWOx6CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"208c87309f281f33320fd4725809201171810988cb6e2414f513e83f9e70730f","last_reissued_at":"2026-07-05T04:07:12.130076Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:07:12.130076Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.11431","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":"2026-07-05T04:07:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pfKUCg9R9yjLTOVaff7EIHk8/o/eMtnxx6j/mw4ofVhNaphQQbS0y/AXk/JX3l1KhMk4lMH6UCDgyKk+1xTICw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T03:05:01.619045Z"},"content_sha256":"f1ccaea481aef74b859d76d621529b4baa791627f808542b9f980cf04d029a05","schema_version":"1.0","event_id":"sha256:f1ccaea481aef74b859d76d621529b4baa791627f808542b9f980cf04d029a05"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:ECGIOME7FAPTGMQP2RZFQCJACF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Task-guided Disentangled Tuning for Pretrained Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiali Zeng, Mu Li, Shuangzhi Wu, Yongjing Yin, Yufan Jiang","submitted_at":"2022-03-22T03:11:39Z","abstract_excerpt":"Pretrained language models (PLMs) trained on large-scale unlabeled corpus are typically fine-tuned on task-specific downstream datasets, which have produced state-of-the-art results on various NLP tasks. However, the data discrepancy issue in domain and scale makes fine-tuning fail to efficiently capture task-specific patterns, especially in the low data regime. To address this issue, we propose Task-guided Disentangled Tuning (TDT) for PLMs, which enhances the generalization of representations by disentangling task-relevant signals from the entangled representations. For a given task, we intr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.11431","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/2203.11431/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":"2026-07-05T04:07:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EVDaZCFDcG01Ji7CTlSFFC1tgEnkIXZSem1ITNpvBqi9suQHwZvYmh3nYwk+qqphtMHNZATvtej7itx9jMbQDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T03:05:01.619433Z"},"content_sha256":"3776df3fe7cd5b8014dac25df94374090cffe931ea16dc0fc7be544dc8e51747","schema_version":"1.0","event_id":"sha256:3776df3fe7cd5b8014dac25df94374090cffe931ea16dc0fc7be544dc8e51747"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ECGIOME7FAPTGMQP2RZFQCJACF/bundle.json","state_url":"https://pith.science/pith/ECGIOME7FAPTGMQP2RZFQCJACF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ECGIOME7FAPTGMQP2RZFQCJACF/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":"2026-07-10T03:05:01Z","links":{"resolver":"https://pith.science/pith/ECGIOME7FAPTGMQP2RZFQCJACF","bundle":"https://pith.science/pith/ECGIOME7FAPTGMQP2RZFQCJACF/bundle.json","state":"https://pith.science/pith/ECGIOME7FAPTGMQP2RZFQCJACF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ECGIOME7FAPTGMQP2RZFQCJACF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:ECGIOME7FAPTGMQP2RZFQCJACF","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":"e8f8f7ede239987f2aba656a47b6a0ac4298b669bdaa43d9cc9efb163ee337b8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-22T03:11:39Z","title_canon_sha256":"fd210b9c9331bb929b4a1dc6d59ab801efb2156d9e35afb8f25797a507282afa"},"schema_version":"1.0","source":{"id":"2203.11431","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.11431","created_at":"2026-07-05T04:07:12Z"},{"alias_kind":"arxiv_version","alias_value":"2203.11431v1","created_at":"2026-07-05T04:07:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.11431","created_at":"2026-07-05T04:07:12Z"},{"alias_kind":"pith_short_12","alias_value":"ECGIOME7FAPT","created_at":"2026-07-05T04:07:12Z"},{"alias_kind":"pith_short_16","alias_value":"ECGIOME7FAPTGMQP","created_at":"2026-07-05T04:07:12Z"},{"alias_kind":"pith_short_8","alias_value":"ECGIOME7","created_at":"2026-07-05T04:07:12Z"}],"graph_snapshots":[{"event_id":"sha256:3776df3fe7cd5b8014dac25df94374090cffe931ea16dc0fc7be544dc8e51747","target":"graph","created_at":"2026-07-05T04:07:12Z","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/2203.11431/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pretrained language models (PLMs) trained on large-scale unlabeled corpus are typically fine-tuned on task-specific downstream datasets, which have produced state-of-the-art results on various NLP tasks. However, the data discrepancy issue in domain and scale makes fine-tuning fail to efficiently capture task-specific patterns, especially in the low data regime. To address this issue, we propose Task-guided Disentangled Tuning (TDT) for PLMs, which enhances the generalization of representations by disentangling task-relevant signals from the entangled representations. For a given task, we intr","authors_text":"Jiali Zeng, Mu Li, Shuangzhi Wu, Yongjing Yin, Yufan Jiang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-22T03:11:39Z","title":"Task-guided Disentangled Tuning for Pretrained Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.11431","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:f1ccaea481aef74b859d76d621529b4baa791627f808542b9f980cf04d029a05","target":"record","created_at":"2026-07-05T04:07:12Z","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":"e8f8f7ede239987f2aba656a47b6a0ac4298b669bdaa43d9cc9efb163ee337b8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-22T03:11:39Z","title_canon_sha256":"fd210b9c9331bb929b4a1dc6d59ab801efb2156d9e35afb8f25797a507282afa"},"schema_version":"1.0","source":{"id":"2203.11431","kind":"arxiv","version":1}},"canonical_sha256":"208c87309f281f33320fd4725809201171810988cb6e2414f513e83f9e70730f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"208c87309f281f33320fd4725809201171810988cb6e2414f513e83f9e70730f","first_computed_at":"2026-07-05T04:07:12.130076Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:07:12.130076Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"G+EFjD6VXk3gAI+CJwu/b5yIpVy2pMWm3u2P/tiGzmIQUgtuX6oIlewn6SDi7MQebbzELBfBLODPPV6qWOx6CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:07:12.130499Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.11431","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f1ccaea481aef74b859d76d621529b4baa791627f808542b9f980cf04d029a05","sha256:3776df3fe7cd5b8014dac25df94374090cffe931ea16dc0fc7be544dc8e51747"],"state_sha256":"d07dfd73a486fbca291a60535d861dbb237fdff6dc49f4b666327eb5005e77de"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QweWkx7SpBq4Y5m+ws7laO+lEPL6n61X1xYJLn9uAJywg/EOBUmSP94bDqieTVUuFjeQlabj/22dkQi98YDEAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-10T03:05:01.621343Z","bundle_sha256":"5627c81343b226a60d534587b75c244878f394cafb846479a6d5d6b59f8949ba"}}