{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:VW3EH4XKFKLH2OICE3S6UD7SOI","short_pith_number":"pith:VW3EH4XK","canonical_record":{"source":{"id":"2507.00016","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-14T14:41:03Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"25f0785499901c9c47ce7effa315ec49d900134330a2ffd9b1635365d06e8594","abstract_canon_sha256":"b6b119c6722bcedc9433e33cdcfff5343f640472194fed68ec3ece6e37375d7b"},"schema_version":"1.0"},"canonical_sha256":"adb643f2ea2a967d390226e5ea0ff2723658700d0278babf5edb2de75dabbd53","source":{"kind":"arxiv","id":"2507.00016","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.00016","created_at":"2026-07-05T11:29:35Z"},{"alias_kind":"arxiv_version","alias_value":"2507.00016v1","created_at":"2026-07-05T11:29:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00016","created_at":"2026-07-05T11:29:35Z"},{"alias_kind":"pith_short_12","alias_value":"VW3EH4XKFKLH","created_at":"2026-07-05T11:29:35Z"},{"alias_kind":"pith_short_16","alias_value":"VW3EH4XKFKLH2OIC","created_at":"2026-07-05T11:29:35Z"},{"alias_kind":"pith_short_8","alias_value":"VW3EH4XK","created_at":"2026-07-05T11:29:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:VW3EH4XKFKLH2OICE3S6UD7SOI","target":"record","payload":{"canonical_record":{"source":{"id":"2507.00016","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-14T14:41:03Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"25f0785499901c9c47ce7effa315ec49d900134330a2ffd9b1635365d06e8594","abstract_canon_sha256":"b6b119c6722bcedc9433e33cdcfff5343f640472194fed68ec3ece6e37375d7b"},"schema_version":"1.0"},"canonical_sha256":"adb643f2ea2a967d390226e5ea0ff2723658700d0278babf5edb2de75dabbd53","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:35.156913Z","signature_b64":"HlLicD24MK/hl6Os/d+ESZpRIgmboamqmGpuzz0m5UAw5t2qgJbY3KL+nQvKeD5TiiNAiM8QOnj4KiYIpS+ODA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"adb643f2ea2a967d390226e5ea0ff2723658700d0278babf5edb2de75dabbd53","last_reissued_at":"2026-07-05T11:29:35.156410Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:35.156410Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.00016","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":"2026-07-05T11:29:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wb5KPOcXnp74OIveK8Q8jUKFkeCTuC/vCe5pijuzVcrtfbg5RKSgp2uRBpGiGa7O4i78yBicbnwttRBgWCnLDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T15:27:00.422131Z"},"content_sha256":"d4cc25ec75222ff714f7d2c8e648bea366e864100d9dfa6270a9eee1dc4aa298","schema_version":"1.0","event_id":"sha256:d4cc25ec75222ff714f7d2c8e648bea366e864100d9dfa6270a9eee1dc4aa298"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:VW3EH4XKFKLH2OICE3S6UD7SOI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Gradient-based Fine-Tuning through Pre-trained Model Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Fusheng Hao, Fuxiang Wu, Liu Liu, Xianglong Liu, Xuanbo Liu","submitted_at":"2025-06-14T14:41:03Z","abstract_excerpt":"Large pre-trained models have demonstrated extensive applications across various fields. However, fine-tuning these models for specific downstream tasks demands significant computational resources and storage. One fine-tuning method, gradient-based parameter selection (GPS), focuses on fine-tuning only the parameters with high gradients in each neuron, thereby reducing the number of training parameters. Nevertheless, this approach increases computational resource requirements and storage demands. In this paper, we propose an efficient gradient-based and regularized fine-tuning method (GRFT) th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00016","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/2507.00016/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":"2026-07-05T11:29:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BuamwK89JsPg8GoVmqP4BCD7qFNsHoHudve6isGHtdJ1uUTWv41ohzAGRiIAVeG6Oh92zV9o1VCZVcRPtS0UAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T15:27:00.423039Z"},"content_sha256":"edd6e8c6947f202d35d853f62f4800a6f5d67b3be7caef6c77e881d5919f720c","schema_version":"1.0","event_id":"sha256:edd6e8c6947f202d35d853f62f4800a6f5d67b3be7caef6c77e881d5919f720c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VW3EH4XKFKLH2OICE3S6UD7SOI/bundle.json","state_url":"https://pith.science/pith/VW3EH4XKFKLH2OICE3S6UD7SOI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VW3EH4XKFKLH2OICE3S6UD7SOI/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":"2026-08-09T15:27:00Z","links":{"resolver":"https://pith.science/pith/VW3EH4XKFKLH2OICE3S6UD7SOI","bundle":"https://pith.science/pith/VW3EH4XKFKLH2OICE3S6UD7SOI/bundle.json","state":"https://pith.science/pith/VW3EH4XKFKLH2OICE3S6UD7SOI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VW3EH4XKFKLH2OICE3S6UD7SOI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VW3EH4XKFKLH2OICE3S6UD7SOI","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":"b6b119c6722bcedc9433e33cdcfff5343f640472194fed68ec3ece6e37375d7b","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-14T14:41:03Z","title_canon_sha256":"25f0785499901c9c47ce7effa315ec49d900134330a2ffd9b1635365d06e8594"},"schema_version":"1.0","source":{"id":"2507.00016","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.00016","created_at":"2026-07-05T11:29:35Z"},{"alias_kind":"arxiv_version","alias_value":"2507.00016v1","created_at":"2026-07-05T11:29:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.00016","created_at":"2026-07-05T11:29:35Z"},{"alias_kind":"pith_short_12","alias_value":"VW3EH4XKFKLH","created_at":"2026-07-05T11:29:35Z"},{"alias_kind":"pith_short_16","alias_value":"VW3EH4XKFKLH2OIC","created_at":"2026-07-05T11:29:35Z"},{"alias_kind":"pith_short_8","alias_value":"VW3EH4XK","created_at":"2026-07-05T11:29:35Z"}],"graph_snapshots":[{"event_id":"sha256:edd6e8c6947f202d35d853f62f4800a6f5d67b3be7caef6c77e881d5919f720c","target":"graph","created_at":"2026-07-05T11:29:35Z","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/2507.00016/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large pre-trained models have demonstrated extensive applications across various fields. However, fine-tuning these models for specific downstream tasks demands significant computational resources and storage. One fine-tuning method, gradient-based parameter selection (GPS), focuses on fine-tuning only the parameters with high gradients in each neuron, thereby reducing the number of training parameters. Nevertheless, this approach increases computational resource requirements and storage demands. In this paper, we propose an efficient gradient-based and regularized fine-tuning method (GRFT) th","authors_text":"Fusheng Hao, Fuxiang Wu, Liu Liu, Xianglong Liu, Xuanbo Liu","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-14T14:41:03Z","title":"Gradient-based Fine-Tuning through Pre-trained Model Regularization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.00016","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:d4cc25ec75222ff714f7d2c8e648bea366e864100d9dfa6270a9eee1dc4aa298","target":"record","created_at":"2026-07-05T11:29:35Z","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":"b6b119c6722bcedc9433e33cdcfff5343f640472194fed68ec3ece6e37375d7b","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-14T14:41:03Z","title_canon_sha256":"25f0785499901c9c47ce7effa315ec49d900134330a2ffd9b1635365d06e8594"},"schema_version":"1.0","source":{"id":"2507.00016","kind":"arxiv","version":1}},"canonical_sha256":"adb643f2ea2a967d390226e5ea0ff2723658700d0278babf5edb2de75dabbd53","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"adb643f2ea2a967d390226e5ea0ff2723658700d0278babf5edb2de75dabbd53","first_computed_at":"2026-07-05T11:29:35.156410Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:29:35.156410Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HlLicD24MK/hl6Os/d+ESZpRIgmboamqmGpuzz0m5UAw5t2qgJbY3KL+nQvKeD5TiiNAiM8QOnj4KiYIpS+ODA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:29:35.156913Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.00016","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d4cc25ec75222ff714f7d2c8e648bea366e864100d9dfa6270a9eee1dc4aa298","sha256:edd6e8c6947f202d35d853f62f4800a6f5d67b3be7caef6c77e881d5919f720c"],"state_sha256":"4e8275fad75ee02744e3a4f7bf0874eedbc058dd4d82d2be40e8a431452543c2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LqYg2d0wmOiHSv7R2eS6Yo2LjGcM0JbhI52HGJzZ0MG6VSxwKk4gMxd3ZjkUjklliizJnf4A+uhlKxMw7Nh8Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T15:27:00.427925Z","bundle_sha256":"218c9a5498a44ee00e6d955d7b72521cd225fcfe8ff207234891e3c5fc67397e"}}