{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:QDV3F3LIRECFDJXZNH5SVUM47H","short_pith_number":"pith:QDV3F3LI","schema_version":"1.0","canonical_sha256":"80ebb2ed68890451a6f969fb2ad19cf9eb5d1c1c4f5e44310c8609406dcefe36","source":{"kind":"arxiv","id":"1702.02052","version":1},"attestation_state":"computed","paper":{"title":"Knowledge Adaptation: Teaching to Adapt","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"John G. Breslin, Parsa Ghaffari, Sebastian Ruder","submitted_at":"2017-02-07T14:59:45Z","abstract_excerpt":"Domain adaptation is crucial in many real-world applications where the distribution of the training data differs from the distribution of the test data. Previous Deep Learning-based approaches to domain adaptation need to be trained jointly on source and target domain data and are therefore unappealing in scenarios where models need to be adapted to a large number of domains or where a domain is evolving, e.g. spam detection where attackers continuously change their tactics.\n  To fill this gap, we propose Knowledge Adaptation, an extension of Knowledge Distillation (Bucilua et al., 2006; Hinto"},"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":"1702.02052","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-02-07T14:59:45Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0ae26aee689eddf855cdb8c71827bed793f6654368575d43392c1cf68335891c","abstract_canon_sha256":"f90fcee53b574824832125f0b84f8b82f1556a9d3b66231674cad88f1fd558da"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:51:10.455700Z","signature_b64":"YAf0CREuJHnKb4XyN3hBVFSFGKLw8pwkEBwagtzYlEOamVZa/sHZdweM7j4C2hySSXiG62qpdqBzSbZRVFJFCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80ebb2ed68890451a6f969fb2ad19cf9eb5d1c1c4f5e44310c8609406dcefe36","last_reissued_at":"2026-05-18T00:51:10.454922Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:51:10.454922Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Knowledge Adaptation: Teaching to Adapt","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"John G. Breslin, Parsa Ghaffari, Sebastian Ruder","submitted_at":"2017-02-07T14:59:45Z","abstract_excerpt":"Domain adaptation is crucial in many real-world applications where the distribution of the training data differs from the distribution of the test data. Previous Deep Learning-based approaches to domain adaptation need to be trained jointly on source and target domain data and are therefore unappealing in scenarios where models need to be adapted to a large number of domains or where a domain is evolving, e.g. spam detection where attackers continuously change their tactics.\n  To fill this gap, we propose Knowledge Adaptation, an extension of Knowledge Distillation (Bucilua et al., 2006; Hinto"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.02052","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":""},"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":"1702.02052","created_at":"2026-05-18T00:51:10.455053+00:00"},{"alias_kind":"arxiv_version","alias_value":"1702.02052v1","created_at":"2026-05-18T00:51:10.455053+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.02052","created_at":"2026-05-18T00:51:10.455053+00:00"},{"alias_kind":"pith_short_12","alias_value":"QDV3F3LIRECF","created_at":"2026-05-18T12:31:37.085036+00:00"},{"alias_kind":"pith_short_16","alias_value":"QDV3F3LIRECFDJXZ","created_at":"2026-05-18T12:31:37.085036+00:00"},{"alias_kind":"pith_short_8","alias_value":"QDV3F3LI","created_at":"2026-05-18T12:31:37.085036+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.07006","citing_title":"CARoL: Context-aware Adaptation for Robot Learning","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QDV3F3LIRECFDJXZNH5SVUM47H","json":"https://pith.science/pith/QDV3F3LIRECFDJXZNH5SVUM47H.json","graph_json":"https://pith.science/api/pith-number/QDV3F3LIRECFDJXZNH5SVUM47H/graph.json","events_json":"https://pith.science/api/pith-number/QDV3F3LIRECFDJXZNH5SVUM47H/events.json","paper":"https://pith.science/paper/QDV3F3LI"},"agent_actions":{"view_html":"https://pith.science/pith/QDV3F3LIRECFDJXZNH5SVUM47H","download_json":"https://pith.science/pith/QDV3F3LIRECFDJXZNH5SVUM47H.json","view_paper":"https://pith.science/paper/QDV3F3LI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1702.02052&json=true","fetch_graph":"https://pith.science/api/pith-number/QDV3F3LIRECFDJXZNH5SVUM47H/graph.json","fetch_events":"https://pith.science/api/pith-number/QDV3F3LIRECFDJXZNH5SVUM47H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QDV3F3LIRECFDJXZNH5SVUM47H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QDV3F3LIRECFDJXZNH5SVUM47H/action/storage_attestation","attest_author":"https://pith.science/pith/QDV3F3LIRECFDJXZNH5SVUM47H/action/author_attestation","sign_citation":"https://pith.science/pith/QDV3F3LIRECFDJXZNH5SVUM47H/action/citation_signature","submit_replication":"https://pith.science/pith/QDV3F3LIRECFDJXZNH5SVUM47H/action/replication_record"}},"created_at":"2026-05-18T00:51:10.455053+00:00","updated_at":"2026-05-18T00:51:10.455053+00:00"}