{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:2MUJTHHCLJSX73I34KSBRMV3WU","short_pith_number":"pith:2MUJTHHC","schema_version":"1.0","canonical_sha256":"d328999ce25a657fed1be2a418b2bbb52f4d1fabb57dc356dbc440e030d523cb","source":{"kind":"arxiv","id":"2211.16299","version":3},"attestation_state":"computed","paper":{"title":"Transferability Estimation Based On Principal Gradient Expectation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Huiyan Qi, Jingjing Chen, Lechao Cheng, Xue Song, Yue Yu, Yu-Gang Jiang, Zunlei Feng","submitted_at":"2022-11-29T15:33:02Z","abstract_excerpt":"Transfer learning aims to improve the performance of target tasks by transferring knowledge acquired in source tasks. The standard approach is pre-training followed by fine-tuning or linear probing. Especially, selecting a proper source domain for a specific target domain under predefined tasks is crucial for improving efficiency and effectiveness. It is conventional to solve this problem via estimating transferability. However, existing methods can not reach a trade-off between performance and cost. To comprehensively evaluate estimation methods, we summarize three properties: stability, reli"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2211.16299","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-29T15:33:02Z","cross_cats_sorted":[],"title_canon_sha256":"4cad1c8e565a79235fce60eb9110dbd6fa778fa9afee60f6cd3adb596afe5f42","abstract_canon_sha256":"90baa0515f0e6713227c61f5cf903154d327f6de7c73b3d891fa264b51a0ae09"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:51:28.515407Z","signature_b64":"mnBa88jzPfJhIrvSYnD45oWFBG2DYjEcQSvfIAcFb8ElgB97KtTRMosAbhN3bwC2NBekvkH4rxiXqUeGZwFNAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d328999ce25a657fed1be2a418b2bbb52f4d1fabb57dc356dbc440e030d523cb","last_reissued_at":"2026-07-05T05:51:28.514923Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:51:28.514923Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transferability Estimation Based On Principal Gradient Expectation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Huiyan Qi, Jingjing Chen, Lechao Cheng, Xue Song, Yue Yu, Yu-Gang Jiang, Zunlei Feng","submitted_at":"2022-11-29T15:33:02Z","abstract_excerpt":"Transfer learning aims to improve the performance of target tasks by transferring knowledge acquired in source tasks. The standard approach is pre-training followed by fine-tuning or linear probing. Especially, selecting a proper source domain for a specific target domain under predefined tasks is crucial for improving efficiency and effectiveness. It is conventional to solve this problem via estimating transferability. However, existing methods can not reach a trade-off between performance and cost. To comprehensively evaluate estimation methods, we summarize three properties: stability, reli"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.16299","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/2211.16299/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2211.16299","created_at":"2026-07-05T05:51:28.514985+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.16299v3","created_at":"2026-07-05T05:51:28.514985+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.16299","created_at":"2026-07-05T05:51:28.514985+00:00"},{"alias_kind":"pith_short_12","alias_value":"2MUJTHHCLJSX","created_at":"2026-07-05T05:51:28.514985+00:00"},{"alias_kind":"pith_short_16","alias_value":"2MUJTHHCLJSX73I3","created_at":"2026-07-05T05:51:28.514985+00:00"},{"alias_kind":"pith_short_8","alias_value":"2MUJTHHC","created_at":"2026-07-05T05:51:28.514985+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.03175","citing_title":"Understanding Knowledge Transferability for Transfer Learning: A Survey","ref_index":67,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2MUJTHHCLJSX73I34KSBRMV3WU","json":"https://pith.science/pith/2MUJTHHCLJSX73I34KSBRMV3WU.json","graph_json":"https://pith.science/api/pith-number/2MUJTHHCLJSX73I34KSBRMV3WU/graph.json","events_json":"https://pith.science/api/pith-number/2MUJTHHCLJSX73I34KSBRMV3WU/events.json","paper":"https://pith.science/paper/2MUJTHHC"},"agent_actions":{"view_html":"https://pith.science/pith/2MUJTHHCLJSX73I34KSBRMV3WU","download_json":"https://pith.science/pith/2MUJTHHCLJSX73I34KSBRMV3WU.json","view_paper":"https://pith.science/paper/2MUJTHHC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.16299&json=true","fetch_graph":"https://pith.science/api/pith-number/2MUJTHHCLJSX73I34KSBRMV3WU/graph.json","fetch_events":"https://pith.science/api/pith-number/2MUJTHHCLJSX73I34KSBRMV3WU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2MUJTHHCLJSX73I34KSBRMV3WU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2MUJTHHCLJSX73I34KSBRMV3WU/action/storage_attestation","attest_author":"https://pith.science/pith/2MUJTHHCLJSX73I34KSBRMV3WU/action/author_attestation","sign_citation":"https://pith.science/pith/2MUJTHHCLJSX73I34KSBRMV3WU/action/citation_signature","submit_replication":"https://pith.science/pith/2MUJTHHCLJSX73I34KSBRMV3WU/action/replication_record"}},"created_at":"2026-07-05T05:51:28.514985+00:00","updated_at":"2026-07-05T05:51:28.514985+00:00"}