{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:HRDSEMM4GHR3D2ACK2CXOSP47O","short_pith_number":"pith:HRDSEMM4","schema_version":"1.0","canonical_sha256":"3c4722319c31e3b1e80256857749fcfb8625ace75c355391b3ca31da80aa4247","source":{"kind":"arxiv","id":"2308.09971","version":1},"attestation_state":"computed","paper":{"title":"Disposable Transfer Learning for Selective Source Task Unlearning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Hyeong Gwon Hong, Hyounguk Shon, Janghyeon Lee, Junmo Kim, Seunghee Koh","submitted_at":"2023-08-19T10:13:17Z","abstract_excerpt":"Transfer learning is widely used for training deep neural networks (DNN) for building a powerful representation. Even after the pre-trained model is adapted for the target task, the representation performance of the feature extractor is retained to some extent. As the performance of the pre-trained model can be considered the private property of the owner, it is natural to seek the exclusive right of the generalized performance of the pre-trained weight. To address this issue, we suggest a new paradigm of transfer learning called disposable transfer learning (DTL), which disposes of only the s"},"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":"2308.09971","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-19T10:13:17Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"349a4ae1d7cd22b85f0e3afbbc6c273ed1cb503f0d4a941b9967c18e5208906b","abstract_canon_sha256":"2231fbd0a503716c814437eaef71576753372437d7d54e7c7401367d5422e49b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:42:49.454285Z","signature_b64":"leyl/nx7aZv0ZcxRQqRdBqLFfMs6E+9bvsavL7/1dAaC3v3ipNnm3hP1Q86vDVFxsXcFErFPH6czT8WpxtDUDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3c4722319c31e3b1e80256857749fcfb8625ace75c355391b3ca31da80aa4247","last_reissued_at":"2026-07-05T06:42:49.453818Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:42:49.453818Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Disposable Transfer Learning for Selective Source Task Unlearning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Hyeong Gwon Hong, Hyounguk Shon, Janghyeon Lee, Junmo Kim, Seunghee Koh","submitted_at":"2023-08-19T10:13:17Z","abstract_excerpt":"Transfer learning is widely used for training deep neural networks (DNN) for building a powerful representation. Even after the pre-trained model is adapted for the target task, the representation performance of the feature extractor is retained to some extent. As the performance of the pre-trained model can be considered the private property of the owner, it is natural to seek the exclusive right of the generalized performance of the pre-trained weight. To address this issue, we suggest a new paradigm of transfer learning called disposable transfer learning (DTL), which disposes of only the s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.09971","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/2308.09971/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":"2308.09971","created_at":"2026-07-05T06:42:49.453882+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.09971v1","created_at":"2026-07-05T06:42:49.453882+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.09971","created_at":"2026-07-05T06:42:49.453882+00:00"},{"alias_kind":"pith_short_12","alias_value":"HRDSEMM4GHR3","created_at":"2026-07-05T06:42:49.453882+00:00"},{"alias_kind":"pith_short_16","alias_value":"HRDSEMM4GHR3D2AC","created_at":"2026-07-05T06:42:49.453882+00:00"},{"alias_kind":"pith_short_8","alias_value":"HRDSEMM4","created_at":"2026-07-05T06:42:49.453882+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HRDSEMM4GHR3D2ACK2CXOSP47O","json":"https://pith.science/pith/HRDSEMM4GHR3D2ACK2CXOSP47O.json","graph_json":"https://pith.science/api/pith-number/HRDSEMM4GHR3D2ACK2CXOSP47O/graph.json","events_json":"https://pith.science/api/pith-number/HRDSEMM4GHR3D2ACK2CXOSP47O/events.json","paper":"https://pith.science/paper/HRDSEMM4"},"agent_actions":{"view_html":"https://pith.science/pith/HRDSEMM4GHR3D2ACK2CXOSP47O","download_json":"https://pith.science/pith/HRDSEMM4GHR3D2ACK2CXOSP47O.json","view_paper":"https://pith.science/paper/HRDSEMM4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.09971&json=true","fetch_graph":"https://pith.science/api/pith-number/HRDSEMM4GHR3D2ACK2CXOSP47O/graph.json","fetch_events":"https://pith.science/api/pith-number/HRDSEMM4GHR3D2ACK2CXOSP47O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HRDSEMM4GHR3D2ACK2CXOSP47O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HRDSEMM4GHR3D2ACK2CXOSP47O/action/storage_attestation","attest_author":"https://pith.science/pith/HRDSEMM4GHR3D2ACK2CXOSP47O/action/author_attestation","sign_citation":"https://pith.science/pith/HRDSEMM4GHR3D2ACK2CXOSP47O/action/citation_signature","submit_replication":"https://pith.science/pith/HRDSEMM4GHR3D2ACK2CXOSP47O/action/replication_record"}},"created_at":"2026-07-05T06:42:49.453882+00:00","updated_at":"2026-07-05T06:42:49.453882+00:00"}