{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:EAIHDIULBZI4N7XSOYIUKYDE3R","short_pith_number":"pith:EAIHDIUL","canonical_record":{"source":{"id":"2312.11875","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-19T06:06:30Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"63412c1e21be7cd313794a444918f24dc022d6af5364c9994b98a3f33115c37d","abstract_canon_sha256":"08a8180adb3287ccb8ae55176a0c01d592a1fd98cbe70ee9cec6adde172737c0"},"schema_version":"1.0"},"canonical_sha256":"201071a28b0e51c6fef27611456064dc41cc4550d937099f6cc5fd9f5b22d137","source":{"kind":"arxiv","id":"2312.11875","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.11875","created_at":"2026-07-05T08:28:58Z"},{"alias_kind":"arxiv_version","alias_value":"2312.11875v3","created_at":"2026-07-05T08:28:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.11875","created_at":"2026-07-05T08:28:58Z"},{"alias_kind":"pith_short_12","alias_value":"EAIHDIULBZI4","created_at":"2026-07-05T08:28:58Z"},{"alias_kind":"pith_short_16","alias_value":"EAIHDIULBZI4N7XS","created_at":"2026-07-05T08:28:58Z"},{"alias_kind":"pith_short_8","alias_value":"EAIHDIUL","created_at":"2026-07-05T08:28:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:EAIHDIULBZI4N7XSOYIUKYDE3R","target":"record","payload":{"canonical_record":{"source":{"id":"2312.11875","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-19T06:06:30Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"63412c1e21be7cd313794a444918f24dc022d6af5364c9994b98a3f33115c37d","abstract_canon_sha256":"08a8180adb3287ccb8ae55176a0c01d592a1fd98cbe70ee9cec6adde172737c0"},"schema_version":"1.0"},"canonical_sha256":"201071a28b0e51c6fef27611456064dc41cc4550d937099f6cc5fd9f5b22d137","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:58.146811Z","signature_b64":"d11XiXe2+77L9PGKgXbapkCjfjjO07ihBaHQ198mxaZhnbuao+TcWjgPb6wVqFGl7RZG1hnAj0//d26eeyxAAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"201071a28b0e51c6fef27611456064dc41cc4550d937099f6cc5fd9f5b22d137","last_reissued_at":"2026-07-05T08:28:58.146308Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:58.146308Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.11875","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":"2026-07-05T08:28:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BOAKPD+6TmkN1U2FVvbt9dK/RMS/npGEYuYHGfMJYuobp8vaExJeau0LDFxVjn6t6fLmyESruNWRgxLT59AmDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T18:58:58.793583Z"},"content_sha256":"2b0ec39bfc083edadaed6ee150471fd6a2a9970e37e82aba8119f7009de9d067","schema_version":"1.0","event_id":"sha256:2b0ec39bfc083edadaed6ee150471fd6a2a9970e37e82aba8119f7009de9d067"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:EAIHDIULBZI4N7XSOYIUKYDE3R","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sparse is Enough in Fine-tuning Pre-trained Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Bo Du, Hai Zhao, Lefei Zhang, Weixi Song, Zuchao Li","submitted_at":"2023-12-19T06:06:30Z","abstract_excerpt":"With the prevalence of pre-training-fine-tuning paradigm, how to efficiently adapt the pre-trained model to the downstream tasks has been an intriguing issue. Parameter-Efficient Fine-Tuning (PEFT) methods have been proposed for low-cost adaptation. Although PEFT has demonstrated effectiveness and been widely applied, the underlying principles are still unclear. In this paper, we adopt the PAC-Bayesian generalization error bound, viewing pre-training as a shift of prior distribution which leads to a tighter bound for generalization error. We validate this shift from the perspectives of oscilla"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.11875","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/2312.11875/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":"2026-07-05T08:28:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7BqWm/SGXvIf3tL9BZa159aM/uscAB0q2Ld1WDHweYJ0MSUfZT9p5fw8puuY4hiMfgO2xuXZBOYp82WEDooKCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T18:58:58.794079Z"},"content_sha256":"50bcaad92d57e967d9187f717f3adbc2b01ff41e75adb6a39f3f172e034994fa","schema_version":"1.0","event_id":"sha256:50bcaad92d57e967d9187f717f3adbc2b01ff41e75adb6a39f3f172e034994fa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EAIHDIULBZI4N7XSOYIUKYDE3R/bundle.json","state_url":"https://pith.science/pith/EAIHDIULBZI4N7XSOYIUKYDE3R/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EAIHDIULBZI4N7XSOYIUKYDE3R/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":"2026-08-15T18:58:58Z","links":{"resolver":"https://pith.science/pith/EAIHDIULBZI4N7XSOYIUKYDE3R","bundle":"https://pith.science/pith/EAIHDIULBZI4N7XSOYIUKYDE3R/bundle.json","state":"https://pith.science/pith/EAIHDIULBZI4N7XSOYIUKYDE3R/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EAIHDIULBZI4N7XSOYIUKYDE3R/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:EAIHDIULBZI4N7XSOYIUKYDE3R","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":"08a8180adb3287ccb8ae55176a0c01d592a1fd98cbe70ee9cec6adde172737c0","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-19T06:06:30Z","title_canon_sha256":"63412c1e21be7cd313794a444918f24dc022d6af5364c9994b98a3f33115c37d"},"schema_version":"1.0","source":{"id":"2312.11875","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.11875","created_at":"2026-07-05T08:28:58Z"},{"alias_kind":"arxiv_version","alias_value":"2312.11875v3","created_at":"2026-07-05T08:28:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.11875","created_at":"2026-07-05T08:28:58Z"},{"alias_kind":"pith_short_12","alias_value":"EAIHDIULBZI4","created_at":"2026-07-05T08:28:58Z"},{"alias_kind":"pith_short_16","alias_value":"EAIHDIULBZI4N7XS","created_at":"2026-07-05T08:28:58Z"},{"alias_kind":"pith_short_8","alias_value":"EAIHDIUL","created_at":"2026-07-05T08:28:58Z"}],"graph_snapshots":[{"event_id":"sha256:50bcaad92d57e967d9187f717f3adbc2b01ff41e75adb6a39f3f172e034994fa","target":"graph","created_at":"2026-07-05T08:28:58Z","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/2312.11875/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the prevalence of pre-training-fine-tuning paradigm, how to efficiently adapt the pre-trained model to the downstream tasks has been an intriguing issue. Parameter-Efficient Fine-Tuning (PEFT) methods have been proposed for low-cost adaptation. Although PEFT has demonstrated effectiveness and been widely applied, the underlying principles are still unclear. In this paper, we adopt the PAC-Bayesian generalization error bound, viewing pre-training as a shift of prior distribution which leads to a tighter bound for generalization error. We validate this shift from the perspectives of oscilla","authors_text":"Bo Du, Hai Zhao, Lefei Zhang, Weixi Song, Zuchao Li","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-19T06:06:30Z","title":"Sparse is Enough in Fine-tuning Pre-trained Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.11875","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":"sha256:2b0ec39bfc083edadaed6ee150471fd6a2a9970e37e82aba8119f7009de9d067","target":"record","created_at":"2026-07-05T08:28:58Z","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":"08a8180adb3287ccb8ae55176a0c01d592a1fd98cbe70ee9cec6adde172737c0","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-19T06:06:30Z","title_canon_sha256":"63412c1e21be7cd313794a444918f24dc022d6af5364c9994b98a3f33115c37d"},"schema_version":"1.0","source":{"id":"2312.11875","kind":"arxiv","version":3}},"canonical_sha256":"201071a28b0e51c6fef27611456064dc41cc4550d937099f6cc5fd9f5b22d137","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"201071a28b0e51c6fef27611456064dc41cc4550d937099f6cc5fd9f5b22d137","first_computed_at":"2026-07-05T08:28:58.146308Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:28:58.146308Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"d11XiXe2+77L9PGKgXbapkCjfjjO07ihBaHQ198mxaZhnbuao+TcWjgPb6wVqFGl7RZG1hnAj0//d26eeyxAAw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:28:58.146811Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.11875","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2b0ec39bfc083edadaed6ee150471fd6a2a9970e37e82aba8119f7009de9d067","sha256:50bcaad92d57e967d9187f717f3adbc2b01ff41e75adb6a39f3f172e034994fa"],"state_sha256":"2b526f672855f7c1c01753eb203d92666868ce0e51e62fa141ebc9ee438a783b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KAXDWx1y0A9MfqUL5L/N05WsY2BWFWQKEKDgo69rnMwLdU3ep4o6ZbnNdhySNAqEKJPDOpy0YxCVb8J9e+VaAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T18:58:58.797926Z","bundle_sha256":"d69b2627aa351dbfee78c67a4733cc697ba50c3603661a23a246adcdf12e55a2"}}