{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:2E5KNOPTQZGG5VM5PXWLKX3KBZ","short_pith_number":"pith:2E5KNOPT","schema_version":"1.0","canonical_sha256":"d13aa6b9f3864c6ed59d7decb55f6a0e47f016389ebb543e7089145f5d18503c","source":{"kind":"arxiv","id":"2112.15278","version":1},"attestation_state":"computed","paper":{"title":"Data-Free Knowledge Transfer: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Jianyong Wang, Jun Wang, Wei Zhang, Yuang Liu","submitted_at":"2021-12-31T03:39:42Z","abstract_excerpt":"In the last decade, many deep learning models have been well trained and made a great success in various fields of machine intelligence, especially for computer vision and natural language processing. To better leverage the potential of these well-trained models in intra-domain or cross-domain transfer learning situations, knowledge distillation (KD) and domain adaptation (DA) are proposed and become research highlights. They both aim to transfer useful information from a well-trained model with original training data. However, the original data is not always available in many cases due to pri"},"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":"2112.15278","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-12-31T03:39:42Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"2acaeadad41c7f3ff24d3300830a9ee555fa026f523503b40602cb0cf5552f6f","abstract_canon_sha256":"86a3dfaf6efa6803d8b13d9157dd6e5d7e41ff91a28f7b8e676f79c909169a23"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:44:38.227827Z","signature_b64":"RBHcvg5o6uAPgply9vWVbAGf1BgG4M/qnAk1dkI7RakfEAft0HBUGWvza8KYyNd1MC1EHpnjbmZ2mUyBBbNABQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d13aa6b9f3864c6ed59d7decb55f6a0e47f016389ebb543e7089145f5d18503c","last_reissued_at":"2026-07-05T03:44:38.227437Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:44:38.227437Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data-Free Knowledge Transfer: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Jianyong Wang, Jun Wang, Wei Zhang, Yuang Liu","submitted_at":"2021-12-31T03:39:42Z","abstract_excerpt":"In the last decade, many deep learning models have been well trained and made a great success in various fields of machine intelligence, especially for computer vision and natural language processing. To better leverage the potential of these well-trained models in intra-domain or cross-domain transfer learning situations, knowledge distillation (KD) and domain adaptation (DA) are proposed and become research highlights. They both aim to transfer useful information from a well-trained model with original training data. However, the original data is not always available in many cases due to pri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.15278","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/2112.15278/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":"2112.15278","created_at":"2026-07-05T03:44:38.227497+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.15278v1","created_at":"2026-07-05T03:44:38.227497+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.15278","created_at":"2026-07-05T03:44:38.227497+00:00"},{"alias_kind":"pith_short_12","alias_value":"2E5KNOPTQZGG","created_at":"2026-07-05T03:44:38.227497+00:00"},{"alias_kind":"pith_short_16","alias_value":"2E5KNOPTQZGG5VM5","created_at":"2026-07-05T03:44:38.227497+00:00"},{"alias_kind":"pith_short_8","alias_value":"2E5KNOPT","created_at":"2026-07-05T03:44:38.227497+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.20089","citing_title":"Bridging Domain Gaps for Fine-Grained Moth Classification Through Expert-Informed Adaptation and Foundation Model Priors","ref_index":16,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2E5KNOPTQZGG5VM5PXWLKX3KBZ","json":"https://pith.science/pith/2E5KNOPTQZGG5VM5PXWLKX3KBZ.json","graph_json":"https://pith.science/api/pith-number/2E5KNOPTQZGG5VM5PXWLKX3KBZ/graph.json","events_json":"https://pith.science/api/pith-number/2E5KNOPTQZGG5VM5PXWLKX3KBZ/events.json","paper":"https://pith.science/paper/2E5KNOPT"},"agent_actions":{"view_html":"https://pith.science/pith/2E5KNOPTQZGG5VM5PXWLKX3KBZ","download_json":"https://pith.science/pith/2E5KNOPTQZGG5VM5PXWLKX3KBZ.json","view_paper":"https://pith.science/paper/2E5KNOPT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.15278&json=true","fetch_graph":"https://pith.science/api/pith-number/2E5KNOPTQZGG5VM5PXWLKX3KBZ/graph.json","fetch_events":"https://pith.science/api/pith-number/2E5KNOPTQZGG5VM5PXWLKX3KBZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2E5KNOPTQZGG5VM5PXWLKX3KBZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2E5KNOPTQZGG5VM5PXWLKX3KBZ/action/storage_attestation","attest_author":"https://pith.science/pith/2E5KNOPTQZGG5VM5PXWLKX3KBZ/action/author_attestation","sign_citation":"https://pith.science/pith/2E5KNOPTQZGG5VM5PXWLKX3KBZ/action/citation_signature","submit_replication":"https://pith.science/pith/2E5KNOPTQZGG5VM5PXWLKX3KBZ/action/replication_record"}},"created_at":"2026-07-05T03:44:38.227497+00:00","updated_at":"2026-07-05T03:44:38.227497+00:00"}