{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:7IUGSMZEXTPYH3CL4UU4KOJ5GD","short_pith_number":"pith:7IUGSMZE","canonical_record":{"source":{"id":"2302.06354","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-13T13:38:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"22aeecaf1fe2f7c2952b23622ba8a08a6da669ba321417a2e89dfbe4e8be498c","abstract_canon_sha256":"77937fcc4a2983d05b2abf62b1e9dc7c3d881341dd6780d1485ffe1a687cb4e2"},"schema_version":"1.0"},"canonical_sha256":"fa28693324bcdf83ec4be529c5393d30da2098091c80c97f821f995642126f76","source":{"kind":"arxiv","id":"2302.06354","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.06354","created_at":"2026-07-05T06:26:45Z"},{"alias_kind":"arxiv_version","alias_value":"2302.06354v3","created_at":"2026-07-05T06:26:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.06354","created_at":"2026-07-05T06:26:45Z"},{"alias_kind":"pith_short_12","alias_value":"7IUGSMZEXTPY","created_at":"2026-07-05T06:26:45Z"},{"alias_kind":"pith_short_16","alias_value":"7IUGSMZEXTPYH3CL","created_at":"2026-07-05T06:26:45Z"},{"alias_kind":"pith_short_8","alias_value":"7IUGSMZE","created_at":"2026-07-05T06:26:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:7IUGSMZEXTPYH3CL4UU4KOJ5GD","target":"record","payload":{"canonical_record":{"source":{"id":"2302.06354","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-13T13:38:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"22aeecaf1fe2f7c2952b23622ba8a08a6da669ba321417a2e89dfbe4e8be498c","abstract_canon_sha256":"77937fcc4a2983d05b2abf62b1e9dc7c3d881341dd6780d1485ffe1a687cb4e2"},"schema_version":"1.0"},"canonical_sha256":"fa28693324bcdf83ec4be529c5393d30da2098091c80c97f821f995642126f76","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:26:45.730847Z","signature_b64":"fKxo+VCnskagb/y7ysRQ77V+WoLPFuCv2S9aP8xtO2dSSA9jIGf10n+6BOyup1I2TDJyQogOO027fCBezUECAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa28693324bcdf83ec4be529c5393d30da2098091c80c97f821f995642126f76","last_reissued_at":"2026-07-05T06:26:45.730356Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:26:45.730356Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.06354","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":"2026-07-05T06:26:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Il2uEEIHycBtmS1Ptz+RkOAFOzrrOBTcrdrnvgOvZDAtmIn3Hcq1y2mVQK1lQdv7P8FKoku3pkCWKJqXre8cBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T15:02:29.574398Z"},"content_sha256":"e1f13470e4f3d2f9cc9e24b0ff111406f05f47da82bef400be67316d82f228ab","schema_version":"1.0","event_id":"sha256:e1f13470e4f3d2f9cc9e24b0ff111406f05f47da82bef400be67316d82f228ab"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:7IUGSMZEXTPYH3CL4UU4KOJ5GD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Less is More: Selective Layer Finetuning with SubTuning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Andrey Gurevich, Eran Malach, Gal Kaplun, Mazor David, Shai Shalev-Shwartz, Tal Swisa","submitted_at":"2023-02-13T13:38:46Z","abstract_excerpt":"Finetuning a pretrained model has become a standard approach for training neural networks on novel tasks, resulting in fast convergence and improved performance. In this work, we study an alternative finetuning method, where instead of finetuning all the weights of the network, we only train a carefully chosen subset of layers, keeping the rest of the weights frozen at their initial (pretrained) values. We demonstrate that \\emph{subset finetuning} (or SubTuning) often achieves accuracy comparable to full finetuning of the model, and even surpasses the performance of full finetuning when traini"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.06354","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/2302.06354/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":"2026-07-05T06:26:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FKJA491/cGLAb0NIWDJyCdPan8CtvnG0lsPGdmkWx/JqLLDlAdVrjLylYXZ8ZcEKCHaDphGBZ8GuICu6QMbHAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T15:02:29.575031Z"},"content_sha256":"69664796ed6e8587ebc17b0ba9905ecba16062dfa45f3cf808fce440568c5563","schema_version":"1.0","event_id":"sha256:69664796ed6e8587ebc17b0ba9905ecba16062dfa45f3cf808fce440568c5563"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7IUGSMZEXTPYH3CL4UU4KOJ5GD/bundle.json","state_url":"https://pith.science/pith/7IUGSMZEXTPYH3CL4UU4KOJ5GD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7IUGSMZEXTPYH3CL4UU4KOJ5GD/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":"2026-08-06T15:02:29Z","links":{"resolver":"https://pith.science/pith/7IUGSMZEXTPYH3CL4UU4KOJ5GD","bundle":"https://pith.science/pith/7IUGSMZEXTPYH3CL4UU4KOJ5GD/bundle.json","state":"https://pith.science/pith/7IUGSMZEXTPYH3CL4UU4KOJ5GD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7IUGSMZEXTPYH3CL4UU4KOJ5GD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:7IUGSMZEXTPYH3CL4UU4KOJ5GD","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":"77937fcc4a2983d05b2abf62b1e9dc7c3d881341dd6780d1485ffe1a687cb4e2","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-13T13:38:46Z","title_canon_sha256":"22aeecaf1fe2f7c2952b23622ba8a08a6da669ba321417a2e89dfbe4e8be498c"},"schema_version":"1.0","source":{"id":"2302.06354","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.06354","created_at":"2026-07-05T06:26:45Z"},{"alias_kind":"arxiv_version","alias_value":"2302.06354v3","created_at":"2026-07-05T06:26:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.06354","created_at":"2026-07-05T06:26:45Z"},{"alias_kind":"pith_short_12","alias_value":"7IUGSMZEXTPY","created_at":"2026-07-05T06:26:45Z"},{"alias_kind":"pith_short_16","alias_value":"7IUGSMZEXTPYH3CL","created_at":"2026-07-05T06:26:45Z"},{"alias_kind":"pith_short_8","alias_value":"7IUGSMZE","created_at":"2026-07-05T06:26:45Z"}],"graph_snapshots":[{"event_id":"sha256:69664796ed6e8587ebc17b0ba9905ecba16062dfa45f3cf808fce440568c5563","target":"graph","created_at":"2026-07-05T06:26:45Z","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/2302.06354/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Finetuning a pretrained model has become a standard approach for training neural networks on novel tasks, resulting in fast convergence and improved performance. In this work, we study an alternative finetuning method, where instead of finetuning all the weights of the network, we only train a carefully chosen subset of layers, keeping the rest of the weights frozen at their initial (pretrained) values. We demonstrate that \\emph{subset finetuning} (or SubTuning) often achieves accuracy comparable to full finetuning of the model, and even surpasses the performance of full finetuning when traini","authors_text":"Andrey Gurevich, Eran Malach, Gal Kaplun, Mazor David, Shai Shalev-Shwartz, Tal Swisa","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-13T13:38:46Z","title":"Less is More: Selective Layer Finetuning with SubTuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.06354","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:e1f13470e4f3d2f9cc9e24b0ff111406f05f47da82bef400be67316d82f228ab","target":"record","created_at":"2026-07-05T06:26:45Z","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":"77937fcc4a2983d05b2abf62b1e9dc7c3d881341dd6780d1485ffe1a687cb4e2","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-13T13:38:46Z","title_canon_sha256":"22aeecaf1fe2f7c2952b23622ba8a08a6da669ba321417a2e89dfbe4e8be498c"},"schema_version":"1.0","source":{"id":"2302.06354","kind":"arxiv","version":3}},"canonical_sha256":"fa28693324bcdf83ec4be529c5393d30da2098091c80c97f821f995642126f76","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fa28693324bcdf83ec4be529c5393d30da2098091c80c97f821f995642126f76","first_computed_at":"2026-07-05T06:26:45.730356Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:26:45.730356Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fKxo+VCnskagb/y7ysRQ77V+WoLPFuCv2S9aP8xtO2dSSA9jIGf10n+6BOyup1I2TDJyQogOO027fCBezUECAg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:26:45.730847Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.06354","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e1f13470e4f3d2f9cc9e24b0ff111406f05f47da82bef400be67316d82f228ab","sha256:69664796ed6e8587ebc17b0ba9905ecba16062dfa45f3cf808fce440568c5563"],"state_sha256":"1636acc17d7262b0e8f604c54e076c1a70df8642df4f26829aa39c1b2bf5f4a5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j8cxNMeLoBI8JCysSbKcBfKz/ptspJoUqNbnch/UPaA6Rr4yGtSOVdJ2c+N/jWqxMsVbr/ejGRbvCsjyIzDACA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T15:02:29.581058Z","bundle_sha256":"8dec1356e0bc014db2c3865af9d44199dd89045519cd82fdf8cdbb509ffb3bf2"}}