{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FRX2IAEFLOWHLDQXNHYDOVJHJT","short_pith_number":"pith:FRX2IAEF","schema_version":"1.0","canonical_sha256":"2c6fa400855bac758e1769f03755274ce67b5026d4fcf1230bf905db758c8e5f","source":{"kind":"arxiv","id":"2405.16837","version":3},"attestation_state":"computed","paper":{"title":"Enhancing Accuracy in Generative Models via Knowledge Transfer","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Xiaotong Shen, Xinyu Tian","submitted_at":"2024-05-27T05:10:49Z","abstract_excerpt":"This paper investigates the accuracy of generative models and the impact of knowledge transfer on their generation precision. Specifically, we examine a generative model for a target task, fine-tuned using a pre-trained model from a source task. Building on the \"Shared Embedding\" concept, which bridges the source and target tasks, we introduce a novel framework for transfer learning under distribution metrics such as the Kullback-Leibler divergence. This framework underscores the importance of leveraging inherent similarities between diverse tasks despite their distinct data distributions. Our"},"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":"2405.16837","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2024-05-27T05:10:49Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"bce0e5eec4e010f1e163515b8a15954220695a486e42cbfb1f195bd6ce4e356b","abstract_canon_sha256":"e56cc6eb781fc236c688852f2c6d4bfb113e10470a8b85e042969b7b904da7f1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:10.001184Z","signature_b64":"bQJ2ZkbbCmmmA7SDTk4ZN0owkfDxTzl3mRLGCKi7MDV4RkpJSiqzDvowXj36bK/KImSWe3QHpDcodWYcAdJsAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2c6fa400855bac758e1769f03755274ce67b5026d4fcf1230bf905db758c8e5f","last_reissued_at":"2026-07-05T11:13:10.000626Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:10.000626Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Accuracy in Generative Models via Knowledge Transfer","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Xiaotong Shen, Xinyu Tian","submitted_at":"2024-05-27T05:10:49Z","abstract_excerpt":"This paper investigates the accuracy of generative models and the impact of knowledge transfer on their generation precision. Specifically, we examine a generative model for a target task, fine-tuned using a pre-trained model from a source task. Building on the \"Shared Embedding\" concept, which bridges the source and target tasks, we introduce a novel framework for transfer learning under distribution metrics such as the Kullback-Leibler divergence. This framework underscores the importance of leveraging inherent similarities between diverse tasks despite their distinct data distributions. Our"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16837","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/2405.16837/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":"2405.16837","created_at":"2026-07-05T11:13:10.000690+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.16837v3","created_at":"2026-07-05T11:13:10.000690+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16837","created_at":"2026-07-05T11:13:10.000690+00:00"},{"alias_kind":"pith_short_12","alias_value":"FRX2IAEFLOWH","created_at":"2026-07-05T11:13:10.000690+00:00"},{"alias_kind":"pith_short_16","alias_value":"FRX2IAEFLOWHLDQX","created_at":"2026-07-05T11:13:10.000690+00:00"},{"alias_kind":"pith_short_8","alias_value":"FRX2IAEF","created_at":"2026-07-05T11:13:10.000690+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.21843","citing_title":"Causality-Encoded Diffusion Models for Interventional Sampling and Edge Inference","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FRX2IAEFLOWHLDQXNHYDOVJHJT","json":"https://pith.science/pith/FRX2IAEFLOWHLDQXNHYDOVJHJT.json","graph_json":"https://pith.science/api/pith-number/FRX2IAEFLOWHLDQXNHYDOVJHJT/graph.json","events_json":"https://pith.science/api/pith-number/FRX2IAEFLOWHLDQXNHYDOVJHJT/events.json","paper":"https://pith.science/paper/FRX2IAEF"},"agent_actions":{"view_html":"https://pith.science/pith/FRX2IAEFLOWHLDQXNHYDOVJHJT","download_json":"https://pith.science/pith/FRX2IAEFLOWHLDQXNHYDOVJHJT.json","view_paper":"https://pith.science/paper/FRX2IAEF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.16837&json=true","fetch_graph":"https://pith.science/api/pith-number/FRX2IAEFLOWHLDQXNHYDOVJHJT/graph.json","fetch_events":"https://pith.science/api/pith-number/FRX2IAEFLOWHLDQXNHYDOVJHJT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FRX2IAEFLOWHLDQXNHYDOVJHJT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FRX2IAEFLOWHLDQXNHYDOVJHJT/action/storage_attestation","attest_author":"https://pith.science/pith/FRX2IAEFLOWHLDQXNHYDOVJHJT/action/author_attestation","sign_citation":"https://pith.science/pith/FRX2IAEFLOWHLDQXNHYDOVJHJT/action/citation_signature","submit_replication":"https://pith.science/pith/FRX2IAEFLOWHLDQXNHYDOVJHJT/action/replication_record"}},"created_at":"2026-07-05T11:13:10.000690+00:00","updated_at":"2026-07-05T11:13:10.000690+00:00"}