{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CPKCD4J464PNSOSTIQ5CIA5GXH","short_pith_number":"pith:CPKCD4J4","schema_version":"1.0","canonical_sha256":"13d421f13cf71ed93a53443a2403a6b9da45beeaf524bf383e1e6d311c4c8cd0","source":{"kind":"arxiv","id":"2507.03175","version":1},"attestation_state":"computed","paper":{"title":"Understanding Knowledge Transferability for Transfer Learning: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Enming Zhang, Hanbing Liu, Haohua Wang, Jingge Wang, Jingyun Yang, Shanxin Guo, Xiangyu Chen, Yang Li, Yang Tan, Yanru Wu, Zhengze Rong, Zijie Zhao","submitted_at":"2025-07-03T21:06:30Z","abstract_excerpt":"Transfer learning has become an essential paradigm in artificial intelligence, enabling the transfer of knowledge from a source task to improve performance on a target task. This approach, particularly through techniques such as pretraining and fine-tuning, has seen significant success in fields like computer vision and natural language processing. However, despite its widespread use, how to reliably assess the transferability of knowledge remains a challenge. Understanding the theoretical underpinnings of each transferability metric is critical for ensuring the success of transfer learning. I"},"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":"2507.03175","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-03T21:06:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a6418db1352f407aa089d6ff9b06aad648ffdc4d3e7b414b7ce147708bc48698","abstract_canon_sha256":"ad28729cb7bb09f0e7eaddecf9c40d54dc638421a870e37c99d706fbebd949c8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:31:54.083241Z","signature_b64":"z8hO6qScsR08qQMSeGEr8TMjfjG3XltdwfpIjs/Xfr3LSIOeo19y/T0Ox482PkANOfBeOwMTvB1dIgigK8awDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13d421f13cf71ed93a53443a2403a6b9da45beeaf524bf383e1e6d311c4c8cd0","last_reissued_at":"2026-07-05T11:31:54.082757Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:31:54.082757Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding Knowledge Transferability for Transfer Learning: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Enming Zhang, Hanbing Liu, Haohua Wang, Jingge Wang, Jingyun Yang, Shanxin Guo, Xiangyu Chen, Yang Li, Yang Tan, Yanru Wu, Zhengze Rong, Zijie Zhao","submitted_at":"2025-07-03T21:06:30Z","abstract_excerpt":"Transfer learning has become an essential paradigm in artificial intelligence, enabling the transfer of knowledge from a source task to improve performance on a target task. This approach, particularly through techniques such as pretraining and fine-tuning, has seen significant success in fields like computer vision and natural language processing. However, despite its widespread use, how to reliably assess the transferability of knowledge remains a challenge. Understanding the theoretical underpinnings of each transferability metric is critical for ensuring the success of transfer learning. I"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.03175","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/2507.03175/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":"2507.03175","created_at":"2026-07-05T11:31:54.082813+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.03175v1","created_at":"2026-07-05T11:31:54.082813+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.03175","created_at":"2026-07-05T11:31:54.082813+00:00"},{"alias_kind":"pith_short_12","alias_value":"CPKCD4J464PN","created_at":"2026-07-05T11:31:54.082813+00:00"},{"alias_kind":"pith_short_16","alias_value":"CPKCD4J464PNSOST","created_at":"2026-07-05T11:31:54.082813+00:00"},{"alias_kind":"pith_short_8","alias_value":"CPKCD4J4","created_at":"2026-07-05T11:31:54.082813+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23028","citing_title":"RADAR: Relative Angular Divergence Across Representations","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19101","citing_title":"Heterogeneity-Aware Dataset Scheduling for Efficient Audio Large Language Model Training","ref_index":56,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CPKCD4J464PNSOSTIQ5CIA5GXH","json":"https://pith.science/pith/CPKCD4J464PNSOSTIQ5CIA5GXH.json","graph_json":"https://pith.science/api/pith-number/CPKCD4J464PNSOSTIQ5CIA5GXH/graph.json","events_json":"https://pith.science/api/pith-number/CPKCD4J464PNSOSTIQ5CIA5GXH/events.json","paper":"https://pith.science/paper/CPKCD4J4"},"agent_actions":{"view_html":"https://pith.science/pith/CPKCD4J464PNSOSTIQ5CIA5GXH","download_json":"https://pith.science/pith/CPKCD4J464PNSOSTIQ5CIA5GXH.json","view_paper":"https://pith.science/paper/CPKCD4J4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.03175&json=true","fetch_graph":"https://pith.science/api/pith-number/CPKCD4J464PNSOSTIQ5CIA5GXH/graph.json","fetch_events":"https://pith.science/api/pith-number/CPKCD4J464PNSOSTIQ5CIA5GXH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CPKCD4J464PNSOSTIQ5CIA5GXH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CPKCD4J464PNSOSTIQ5CIA5GXH/action/storage_attestation","attest_author":"https://pith.science/pith/CPKCD4J464PNSOSTIQ5CIA5GXH/action/author_attestation","sign_citation":"https://pith.science/pith/CPKCD4J464PNSOSTIQ5CIA5GXH/action/citation_signature","submit_replication":"https://pith.science/pith/CPKCD4J464PNSOSTIQ5CIA5GXH/action/replication_record"}},"created_at":"2026-07-05T11:31:54.082813+00:00","updated_at":"2026-07-05T11:31:54.082813+00:00"}