{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:J4L6NJX376ALXBVAQLYLJHDKZO","short_pith_number":"pith:J4L6NJX3","canonical_record":{"source":{"id":"2403.00812","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-25T07:09:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a0f84e7cdd528abfdc730ecfe12dc7286ca767157fc9549a2dc89a24fd9720b4","abstract_canon_sha256":"0fe3f85a4e06ef076cbdba606a37aaa6a2401e21b062ed210f364335d4d610e2"},"schema_version":"1.0"},"canonical_sha256":"4f17e6a6fbff80bb86a082f0b49c6acbb3e8c3f9710698c6a8017305a1b5957c","source":{"kind":"arxiv","id":"2403.00812","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.00812","created_at":"2026-07-05T08:23:19Z"},{"alias_kind":"arxiv_version","alias_value":"2403.00812v2","created_at":"2026-07-05T08:23:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.00812","created_at":"2026-07-05T08:23:19Z"},{"alias_kind":"pith_short_12","alias_value":"J4L6NJX376AL","created_at":"2026-07-05T08:23:19Z"},{"alias_kind":"pith_short_16","alias_value":"J4L6NJX376ALXBVA","created_at":"2026-07-05T08:23:19Z"},{"alias_kind":"pith_short_8","alias_value":"J4L6NJX3","created_at":"2026-07-05T08:23:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:J4L6NJX376ALXBVAQLYLJHDKZO","target":"record","payload":{"canonical_record":{"source":{"id":"2403.00812","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-25T07:09:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a0f84e7cdd528abfdc730ecfe12dc7286ca767157fc9549a2dc89a24fd9720b4","abstract_canon_sha256":"0fe3f85a4e06ef076cbdba606a37aaa6a2401e21b062ed210f364335d4d610e2"},"schema_version":"1.0"},"canonical_sha256":"4f17e6a6fbff80bb86a082f0b49c6acbb3e8c3f9710698c6a8017305a1b5957c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:23:19.227095Z","signature_b64":"nRvztlP6hN/j0R/OAMsJKNTkBiiwWkyu/rCTN6OH/4sN9lfcN+YsiJzK35bMm/i8JN75Ncfn/tA33D5hDiG4Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f17e6a6fbff80bb86a082f0b49c6acbb3e8c3f9710698c6a8017305a1b5957c","last_reissued_at":"2026-07-05T08:23:19.226620Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:23:19.226620Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.00812","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":"2026-07-05T08:23:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m3C3BRCewbpXG2cfxQNy8XszDAYGHR1Omc3OPE28zMDDifzvgZqW1znE3I3Ja8ebpKSeMTD43xlIKgSJvL+ZCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T17:44:07.328915Z"},"content_sha256":"d774c7e6dcd210df32329bf457dd6f690b1444c386df9b8c12446e4c9d51c465","schema_version":"1.0","event_id":"sha256:d774c7e6dcd210df32329bf457dd6f690b1444c386df9b8c12446e4c9d51c465"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:J4L6NJX376ALXBVAQLYLJHDKZO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LoRA Meets Dropout under a Unified Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Boyang Xue, Chuan Wu, Jiyue Jiang, Liheng Chen, Lingpeng Kong, Sheng Wang","submitted_at":"2024-02-25T07:09:10Z","abstract_excerpt":"With the remarkable capabilities, large language models (LLMs) have emerged as essential elements in numerous NLP applications, while parameter-efficient finetuning, especially LoRA, has gained popularity as a lightweight approach for model customization. Meanwhile, various dropout methods, initially designed for full finetuning with all the parameters updated, alleviates overfitting associated with excessive parameter redundancy. Hence, a possible contradiction arises from negligible trainable parameters of LoRA and the effectiveness of previous dropout methods, which has been largely overloo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.00812","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/2403.00812/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":"2026-07-05T08:23:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KwD8jlKrAghojeuk2m243TQo7/oMuxzh/TJDkEPMcuUVpCIRk0fGTQ0+pggGGIQjL6oedWoyGYLS6rts6berCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T17:44:07.329758Z"},"content_sha256":"432d076b1f60b64be9c4407e038cf9348d35bdac97c29615026d672c3ffd8468","schema_version":"1.0","event_id":"sha256:432d076b1f60b64be9c4407e038cf9348d35bdac97c29615026d672c3ffd8468"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/J4L6NJX376ALXBVAQLYLJHDKZO/bundle.json","state_url":"https://pith.science/pith/J4L6NJX376ALXBVAQLYLJHDKZO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/J4L6NJX376ALXBVAQLYLJHDKZO/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":"2026-08-05T17:44:07Z","links":{"resolver":"https://pith.science/pith/J4L6NJX376ALXBVAQLYLJHDKZO","bundle":"https://pith.science/pith/J4L6NJX376ALXBVAQLYLJHDKZO/bundle.json","state":"https://pith.science/pith/J4L6NJX376ALXBVAQLYLJHDKZO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/J4L6NJX376ALXBVAQLYLJHDKZO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:J4L6NJX376ALXBVAQLYLJHDKZO","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":"0fe3f85a4e06ef076cbdba606a37aaa6a2401e21b062ed210f364335d4d610e2","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-25T07:09:10Z","title_canon_sha256":"a0f84e7cdd528abfdc730ecfe12dc7286ca767157fc9549a2dc89a24fd9720b4"},"schema_version":"1.0","source":{"id":"2403.00812","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.00812","created_at":"2026-07-05T08:23:19Z"},{"alias_kind":"arxiv_version","alias_value":"2403.00812v2","created_at":"2026-07-05T08:23:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.00812","created_at":"2026-07-05T08:23:19Z"},{"alias_kind":"pith_short_12","alias_value":"J4L6NJX376AL","created_at":"2026-07-05T08:23:19Z"},{"alias_kind":"pith_short_16","alias_value":"J4L6NJX376ALXBVA","created_at":"2026-07-05T08:23:19Z"},{"alias_kind":"pith_short_8","alias_value":"J4L6NJX3","created_at":"2026-07-05T08:23:19Z"}],"graph_snapshots":[{"event_id":"sha256:432d076b1f60b64be9c4407e038cf9348d35bdac97c29615026d672c3ffd8468","target":"graph","created_at":"2026-07-05T08:23:19Z","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/2403.00812/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the remarkable capabilities, large language models (LLMs) have emerged as essential elements in numerous NLP applications, while parameter-efficient finetuning, especially LoRA, has gained popularity as a lightweight approach for model customization. Meanwhile, various dropout methods, initially designed for full finetuning with all the parameters updated, alleviates overfitting associated with excessive parameter redundancy. Hence, a possible contradiction arises from negligible trainable parameters of LoRA and the effectiveness of previous dropout methods, which has been largely overloo","authors_text":"Boyang Xue, Chuan Wu, Jiyue Jiang, Liheng Chen, Lingpeng Kong, Sheng Wang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-25T07:09:10Z","title":"LoRA Meets Dropout under a Unified Framework"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.00812","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:d774c7e6dcd210df32329bf457dd6f690b1444c386df9b8c12446e4c9d51c465","target":"record","created_at":"2026-07-05T08:23:19Z","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":"0fe3f85a4e06ef076cbdba606a37aaa6a2401e21b062ed210f364335d4d610e2","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-25T07:09:10Z","title_canon_sha256":"a0f84e7cdd528abfdc730ecfe12dc7286ca767157fc9549a2dc89a24fd9720b4"},"schema_version":"1.0","source":{"id":"2403.00812","kind":"arxiv","version":2}},"canonical_sha256":"4f17e6a6fbff80bb86a082f0b49c6acbb3e8c3f9710698c6a8017305a1b5957c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4f17e6a6fbff80bb86a082f0b49c6acbb3e8c3f9710698c6a8017305a1b5957c","first_computed_at":"2026-07-05T08:23:19.226620Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:23:19.226620Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nRvztlP6hN/j0R/OAMsJKNTkBiiwWkyu/rCTN6OH/4sN9lfcN+YsiJzK35bMm/i8JN75Ncfn/tA33D5hDiG4Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:23:19.227095Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.00812","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d774c7e6dcd210df32329bf457dd6f690b1444c386df9b8c12446e4c9d51c465","sha256:432d076b1f60b64be9c4407e038cf9348d35bdac97c29615026d672c3ffd8468"],"state_sha256":"66fdf3b4224d40e985f4cfceb435c10ef123a3f2d96d127c3c3508e32d4e69a6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SXT6WuFTL/nHovlD0OFvIiMSya4QKoSbrAhnlDiZbItqoo/QmvovfnEQBeV6Vdg4SZAIrdiWAryiHtwWbWIkDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T17:44:07.336252Z","bundle_sha256":"fb48ab73bc945fca57dc7598cb4dfa023662f4ff4d7a8ffd413b6066a3ec6a74"}}