{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:EPXTSJMHMSXNIHQ7GN57R3E72M","short_pith_number":"pith:EPXTSJMH","canonical_record":{"source":{"id":"2403.10097","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-15T08:26:59Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"e1e0a8c5475ee9df4a7ba4fc542ddaa730dd932f4255adeed5e26c9faaff0f81","abstract_canon_sha256":"a5546f39fa5142c64d3121f82ab8af9172c9c2e383a4e48ef0220ab9dd8377c8"},"schema_version":"1.0"},"canonical_sha256":"23ef39258764aed41e1f337bf8ec9fd31bd99e6b0cc5ef77876f476dd1866a7c","source":{"kind":"arxiv","id":"2403.10097","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.10097","created_at":"2026-07-05T07:56:30Z"},{"alias_kind":"arxiv_version","alias_value":"2403.10097v1","created_at":"2026-07-05T07:56:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.10097","created_at":"2026-07-05T07:56:30Z"},{"alias_kind":"pith_short_12","alias_value":"EPXTSJMHMSXN","created_at":"2026-07-05T07:56:30Z"},{"alias_kind":"pith_short_16","alias_value":"EPXTSJMHMSXNIHQ7","created_at":"2026-07-05T07:56:30Z"},{"alias_kind":"pith_short_8","alias_value":"EPXTSJMH","created_at":"2026-07-05T07:56:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:EPXTSJMHMSXNIHQ7GN57R3E72M","target":"record","payload":{"canonical_record":{"source":{"id":"2403.10097","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-15T08:26:59Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"e1e0a8c5475ee9df4a7ba4fc542ddaa730dd932f4255adeed5e26c9faaff0f81","abstract_canon_sha256":"a5546f39fa5142c64d3121f82ab8af9172c9c2e383a4e48ef0220ab9dd8377c8"},"schema_version":"1.0"},"canonical_sha256":"23ef39258764aed41e1f337bf8ec9fd31bd99e6b0cc5ef77876f476dd1866a7c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:56:30.225110Z","signature_b64":"daaSe85fDAxe/gWN+ygUrolk6B2VvI7kIIh8CCJ4GCBFcmNVs18+jlfn8HdsrhnPA9avJ7k42JqmOb6KxOM8BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23ef39258764aed41e1f337bf8ec9fd31bd99e6b0cc5ef77876f476dd1866a7c","last_reissued_at":"2026-07-05T07:56:30.224711Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:56:30.224711Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.10097","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":"2026-07-05T07:56:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fKm4NSyPeBCfI6LEiem+Yjcs40C+NHkl+FfGlJFHbKHqlBuzL9GtQqI54DMhT/jX1WxKaRLsh711rp3J3tGRBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T20:57:44.605533Z"},"content_sha256":"c5b47d5aff25d61a8a84de22d17af13b27423ee683b17a54d7905b82ed8d5575","schema_version":"1.0","event_id":"sha256:c5b47d5aff25d61a8a84de22d17af13b27423ee683b17a54d7905b82ed8d5575"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:EPXTSJMHMSXNIHQ7GN57R3E72M","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adaptive Random Feature Regularization on Fine-tuning Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Daiki Chijiwa, Kazuki Adachi, Sekitoshi Kanai, Shin'ya Yamaguchi","submitted_at":"2024-03-15T08:26:59Z","abstract_excerpt":"While fine-tuning is a de facto standard method for training deep neural networks, it still suffers from overfitting when using small target datasets. Previous methods improve fine-tuning performance by maintaining knowledge of the source datasets or introducing regularization terms such as contrastive loss. However, these methods require auxiliary source information (e.g., source labels or datasets) or heavy additional computations. In this paper, we propose a simple method called adaptive random feature regularization (AdaRand). AdaRand helps the feature extractors of training models to adap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.10097","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/2403.10097/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":"2026-07-05T07:56:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GVwlRxY4BaYRCqmWHs6f4uNRixovqZp4rCzPnPPWptojtvynfm8qbqHzOAkPv1sRFlvQMFuNkHOj60I6FjWXCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T20:57:44.605932Z"},"content_sha256":"a0b3f2591511427f1623b727a023897c2bfa9a1698eb78c1546dee5c5dc9b928","schema_version":"1.0","event_id":"sha256:a0b3f2591511427f1623b727a023897c2bfa9a1698eb78c1546dee5c5dc9b928"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EPXTSJMHMSXNIHQ7GN57R3E72M/bundle.json","state_url":"https://pith.science/pith/EPXTSJMHMSXNIHQ7GN57R3E72M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EPXTSJMHMSXNIHQ7GN57R3E72M/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":"2026-08-03T20:57:44Z","links":{"resolver":"https://pith.science/pith/EPXTSJMHMSXNIHQ7GN57R3E72M","bundle":"https://pith.science/pith/EPXTSJMHMSXNIHQ7GN57R3E72M/bundle.json","state":"https://pith.science/pith/EPXTSJMHMSXNIHQ7GN57R3E72M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EPXTSJMHMSXNIHQ7GN57R3E72M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:EPXTSJMHMSXNIHQ7GN57R3E72M","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":"a5546f39fa5142c64d3121f82ab8af9172c9c2e383a4e48ef0220ab9dd8377c8","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-15T08:26:59Z","title_canon_sha256":"e1e0a8c5475ee9df4a7ba4fc542ddaa730dd932f4255adeed5e26c9faaff0f81"},"schema_version":"1.0","source":{"id":"2403.10097","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.10097","created_at":"2026-07-05T07:56:30Z"},{"alias_kind":"arxiv_version","alias_value":"2403.10097v1","created_at":"2026-07-05T07:56:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.10097","created_at":"2026-07-05T07:56:30Z"},{"alias_kind":"pith_short_12","alias_value":"EPXTSJMHMSXN","created_at":"2026-07-05T07:56:30Z"},{"alias_kind":"pith_short_16","alias_value":"EPXTSJMHMSXNIHQ7","created_at":"2026-07-05T07:56:30Z"},{"alias_kind":"pith_short_8","alias_value":"EPXTSJMH","created_at":"2026-07-05T07:56:30Z"}],"graph_snapshots":[{"event_id":"sha256:a0b3f2591511427f1623b727a023897c2bfa9a1698eb78c1546dee5c5dc9b928","target":"graph","created_at":"2026-07-05T07:56:30Z","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/2403.10097/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While fine-tuning is a de facto standard method for training deep neural networks, it still suffers from overfitting when using small target datasets. Previous methods improve fine-tuning performance by maintaining knowledge of the source datasets or introducing regularization terms such as contrastive loss. However, these methods require auxiliary source information (e.g., source labels or datasets) or heavy additional computations. In this paper, we propose a simple method called adaptive random feature regularization (AdaRand). AdaRand helps the feature extractors of training models to adap","authors_text":"Daiki Chijiwa, Kazuki Adachi, Sekitoshi Kanai, Shin'ya Yamaguchi","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-15T08:26:59Z","title":"Adaptive Random Feature Regularization on Fine-tuning Deep Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.10097","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:c5b47d5aff25d61a8a84de22d17af13b27423ee683b17a54d7905b82ed8d5575","target":"record","created_at":"2026-07-05T07:56:30Z","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":"a5546f39fa5142c64d3121f82ab8af9172c9c2e383a4e48ef0220ab9dd8377c8","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-03-15T08:26:59Z","title_canon_sha256":"e1e0a8c5475ee9df4a7ba4fc542ddaa730dd932f4255adeed5e26c9faaff0f81"},"schema_version":"1.0","source":{"id":"2403.10097","kind":"arxiv","version":1}},"canonical_sha256":"23ef39258764aed41e1f337bf8ec9fd31bd99e6b0cc5ef77876f476dd1866a7c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"23ef39258764aed41e1f337bf8ec9fd31bd99e6b0cc5ef77876f476dd1866a7c","first_computed_at":"2026-07-05T07:56:30.224711Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:56:30.224711Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"daaSe85fDAxe/gWN+ygUrolk6B2VvI7kIIh8CCJ4GCBFcmNVs18+jlfn8HdsrhnPA9avJ7k42JqmOb6KxOM8BA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:56:30.225110Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.10097","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c5b47d5aff25d61a8a84de22d17af13b27423ee683b17a54d7905b82ed8d5575","sha256:a0b3f2591511427f1623b727a023897c2bfa9a1698eb78c1546dee5c5dc9b928"],"state_sha256":"22e52bb0aba33c499010ed0c2741321a1dbdc2bc025c8021e3be6d301b36ba9a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vCdftGnFlSPYsp9+U0nxeJG1LyMrL1qOOY8KRljHJCxtkalCpSOCGfglRkRmHf8J3T5PbQ4cI3S5aDqopZUsDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T20:57:44.608851Z","bundle_sha256":"dab1f3c888042076ebc8d0fd45b119739ec08fb6f872de67dc388c3a60ad34d6"}}