{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:JUPSADALHXPAUAIAOTIRMTJX2J","short_pith_number":"pith:JUPSADAL","canonical_record":{"source":{"id":"1911.03437","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-08T18:41:31Z","cross_cats_sorted":["cs.LG","math.OC"],"title_canon_sha256":"4a34a7c97034dede9b85c7d2493740fe9fc867712c12ad32f499cbd58c38a27e","abstract_canon_sha256":"93d444a14f890b84265654f6cc9497b037c8fd768b8da9391a0177344f4b7e55"},"schema_version":"1.0"},"canonical_sha256":"4d1f200c0b3dde0a010074d1164d37d2647a42a8a0f4b91bcf6d545bec040106","source":{"kind":"arxiv","id":"1911.03437","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.03437","created_at":"2026-07-05T03:12:44Z"},{"alias_kind":"arxiv_version","alias_value":"1911.03437v5","created_at":"2026-07-05T03:12:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.03437","created_at":"2026-07-05T03:12:44Z"},{"alias_kind":"pith_short_12","alias_value":"JUPSADALHXPA","created_at":"2026-07-05T03:12:44Z"},{"alias_kind":"pith_short_16","alias_value":"JUPSADALHXPAUAIA","created_at":"2026-07-05T03:12:44Z"},{"alias_kind":"pith_short_8","alias_value":"JUPSADAL","created_at":"2026-07-05T03:12:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:JUPSADALHXPAUAIAOTIRMTJX2J","target":"record","payload":{"canonical_record":{"source":{"id":"1911.03437","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-08T18:41:31Z","cross_cats_sorted":["cs.LG","math.OC"],"title_canon_sha256":"4a34a7c97034dede9b85c7d2493740fe9fc867712c12ad32f499cbd58c38a27e","abstract_canon_sha256":"93d444a14f890b84265654f6cc9497b037c8fd768b8da9391a0177344f4b7e55"},"schema_version":"1.0"},"canonical_sha256":"4d1f200c0b3dde0a010074d1164d37d2647a42a8a0f4b91bcf6d545bec040106","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:12:44.104866Z","signature_b64":"1Ci/gz2XbPtvaN63hmLSwtDHsM0lRjVrvom7cNnhOmK0xzWyXSUUtA2iWvLkipgxLviRylh93z9+3+QfH7SXBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d1f200c0b3dde0a010074d1164d37d2647a42a8a0f4b91bcf6d545bec040106","last_reissued_at":"2026-07-05T03:12:44.104518Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:12:44.104518Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1911.03437","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:12:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sfRejG625tPvuHAb1iToGJb4+4WSTd0wST4fUMdQ+uLo5hjABo4saYSNM/kmux748drv+mCGG0MDkTjM8kToBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T14:24:50.925789Z"},"content_sha256":"48e632d1769e05c3898210a485fadf3e16471f8882787b2868b6f62e939f1007","schema_version":"1.0","event_id":"sha256:48e632d1769e05c3898210a485fadf3e16471f8882787b2868b6f62e939f1007"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:JUPSADALHXPAUAIAOTIRMTJX2J","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"cs.CL","authors_text":"Haoming Jiang, Jianfeng Gao, Pengcheng He, Tuo Zhao, Weizhu Chen, XiaoDong Liu","submitted_at":"2019-11-08T18:41:31Z","abstract_excerpt":"Transfer learning has fundamentally changed the landscape of natural language processing (NLP) research. Many existing state-of-the-art models are first pre-trained on a large text corpus and then fine-tuned on downstream tasks. However, due to limited data resources from downstream tasks and the extremely large capacity of pre-trained models, aggressive fine-tuning often causes the adapted model to overfit the data of downstream tasks and forget the knowledge of the pre-trained model. To address the above issue in a more principled manner, we propose a new computational framework for robust a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.03437","kind":"arxiv","version":5},"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/1911.03437/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":"2026-07-05T03:12:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P5zvFRRnTJSuafexK458XNqePNleiTzPBCdaqie1GwPH42rRhSc+cQ5mEeJtlxpl62AcP2UTOiY2i7D4P8B0BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T14:24:50.926178Z"},"content_sha256":"70fc1b506533877c4a7414566837715e36bb46fdbd7d5380bc32664caf224a14","schema_version":"1.0","event_id":"sha256:70fc1b506533877c4a7414566837715e36bb46fdbd7d5380bc32664caf224a14"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JUPSADALHXPAUAIAOTIRMTJX2J/bundle.json","state_url":"https://pith.science/pith/JUPSADALHXPAUAIAOTIRMTJX2J/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JUPSADALHXPAUAIAOTIRMTJX2J/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":"2026-07-07T14:24:50Z","links":{"resolver":"https://pith.science/pith/JUPSADALHXPAUAIAOTIRMTJX2J","bundle":"https://pith.science/pith/JUPSADALHXPAUAIAOTIRMTJX2J/bundle.json","state":"https://pith.science/pith/JUPSADALHXPAUAIAOTIRMTJX2J/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JUPSADALHXPAUAIAOTIRMTJX2J/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:JUPSADALHXPAUAIAOTIRMTJX2J","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":"93d444a14f890b84265654f6cc9497b037c8fd768b8da9391a0177344f4b7e55","cross_cats_sorted":["cs.LG","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-08T18:41:31Z","title_canon_sha256":"4a34a7c97034dede9b85c7d2493740fe9fc867712c12ad32f499cbd58c38a27e"},"schema_version":"1.0","source":{"id":"1911.03437","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.03437","created_at":"2026-07-05T03:12:44Z"},{"alias_kind":"arxiv_version","alias_value":"1911.03437v5","created_at":"2026-07-05T03:12:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.03437","created_at":"2026-07-05T03:12:44Z"},{"alias_kind":"pith_short_12","alias_value":"JUPSADALHXPA","created_at":"2026-07-05T03:12:44Z"},{"alias_kind":"pith_short_16","alias_value":"JUPSADALHXPAUAIA","created_at":"2026-07-05T03:12:44Z"},{"alias_kind":"pith_short_8","alias_value":"JUPSADAL","created_at":"2026-07-05T03:12:44Z"}],"graph_snapshots":[{"event_id":"sha256:70fc1b506533877c4a7414566837715e36bb46fdbd7d5380bc32664caf224a14","target":"graph","created_at":"2026-07-05T03:12:44Z","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/1911.03437/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transfer learning has fundamentally changed the landscape of natural language processing (NLP) research. Many existing state-of-the-art models are first pre-trained on a large text corpus and then fine-tuned on downstream tasks. However, due to limited data resources from downstream tasks and the extremely large capacity of pre-trained models, aggressive fine-tuning often causes the adapted model to overfit the data of downstream tasks and forget the knowledge of the pre-trained model. To address the above issue in a more principled manner, we propose a new computational framework for robust a","authors_text":"Haoming Jiang, Jianfeng Gao, Pengcheng He, Tuo Zhao, Weizhu Chen, XiaoDong Liu","cross_cats":["cs.LG","math.OC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-08T18:41:31Z","title":"SMART: Robust and Efficient Fine-Tuning for Pre-trained Natural Language Models through Principled Regularized Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.03437","kind":"arxiv","version":5},"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":"sha256:48e632d1769e05c3898210a485fadf3e16471f8882787b2868b6f62e939f1007","target":"record","created_at":"2026-07-05T03:12:44Z","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":"93d444a14f890b84265654f6cc9497b037c8fd768b8da9391a0177344f4b7e55","cross_cats_sorted":["cs.LG","math.OC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-08T18:41:31Z","title_canon_sha256":"4a34a7c97034dede9b85c7d2493740fe9fc867712c12ad32f499cbd58c38a27e"},"schema_version":"1.0","source":{"id":"1911.03437","kind":"arxiv","version":5}},"canonical_sha256":"4d1f200c0b3dde0a010074d1164d37d2647a42a8a0f4b91bcf6d545bec040106","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4d1f200c0b3dde0a010074d1164d37d2647a42a8a0f4b91bcf6d545bec040106","first_computed_at":"2026-07-05T03:12:44.104518Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:12:44.104518Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1Ci/gz2XbPtvaN63hmLSwtDHsM0lRjVrvom7cNnhOmK0xzWyXSUUtA2iWvLkipgxLviRylh93z9+3+QfH7SXBw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:12:44.104866Z","signed_message":"canonical_sha256_bytes"},"source_id":"1911.03437","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:48e632d1769e05c3898210a485fadf3e16471f8882787b2868b6f62e939f1007","sha256:70fc1b506533877c4a7414566837715e36bb46fdbd7d5380bc32664caf224a14"],"state_sha256":"a47e2c26d9900a2fd5f08dcb873c17dd454d2cef17a59196075fe1030fb1ee36"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZVc+ZmWIemWQ4kxBqFZUpaey8vN9myOG1qXE3fkAiMBPeM2HBKuWdh3gL1+l8/1TxBICmG87TcpqT+VYjdY/Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T14:24:50.928234Z","bundle_sha256":"531f50982d5c5ea2d81d7c33c2bdb7a59e0cbbb1ed9c4889ec0726e5fd020428"}}