{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:EIDGZ4PJJ3TWMOB2XWBCDFV75B","short_pith_number":"pith:EIDGZ4PJ","schema_version":"1.0","canonical_sha256":"22066cf1e94ee766383abd822196bfe8681289578e9bfd8437ead08b7221e9f2","source":{"kind":"arxiv","id":"2011.06182","version":1},"attestation_state":"computed","paper":{"title":"Bi-tuning of Pre-trained Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Jianmin Wang, Jincheng Zhong, Mingsheng Long, Ximei Wang, Zhi Kou","submitted_at":"2020-11-12T03:32:25Z","abstract_excerpt":"It is common within the deep learning community to first pre-train a deep neural network from a large-scale dataset and then fine-tune the pre-trained model to a specific downstream task. Recently, both supervised and unsupervised pre-training approaches to learning representations have achieved remarkable advances, which exploit the discriminative knowledge of labels and the intrinsic structure of data, respectively. It follows natural intuition that both discriminative knowledge and intrinsic structure of the downstream task can be useful for fine-tuning, however, existing fine-tuning method"},"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":"2011.06182","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2020-11-12T03:32:25Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"5ffcc5e69ee4dce7fe05ba77ddbe1aad32025e70e05c77e4ee88dc44cac09ccc","abstract_canon_sha256":"fc9d1547cbd3a095a202c1d94fb1b5832e6962f3c5aaddec733ff61406eab63f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:51:12.744482Z","signature_b64":"xuYzObBy+hWQoNB6XzoSzzvGvna//7LUUioowx/CL6mMNTEz9YmPSVg7qao4hjYmkar9yFAuOM/eYR+6QasmAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"22066cf1e94ee766383abd822196bfe8681289578e9bfd8437ead08b7221e9f2","last_reissued_at":"2026-07-05T01:51:12.744106Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:51:12.744106Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bi-tuning of Pre-trained Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Jianmin Wang, Jincheng Zhong, Mingsheng Long, Ximei Wang, Zhi Kou","submitted_at":"2020-11-12T03:32:25Z","abstract_excerpt":"It is common within the deep learning community to first pre-train a deep neural network from a large-scale dataset and then fine-tune the pre-trained model to a specific downstream task. Recently, both supervised and unsupervised pre-training approaches to learning representations have achieved remarkable advances, which exploit the discriminative knowledge of labels and the intrinsic structure of data, respectively. It follows natural intuition that both discriminative knowledge and intrinsic structure of the downstream task can be useful for fine-tuning, however, existing fine-tuning method"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.06182","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/2011.06182/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":"2011.06182","created_at":"2026-07-05T01:51:12.744159+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.06182v1","created_at":"2026-07-05T01:51:12.744159+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.06182","created_at":"2026-07-05T01:51:12.744159+00:00"},{"alias_kind":"pith_short_12","alias_value":"EIDGZ4PJJ3TW","created_at":"2026-07-05T01:51:12.744159+00:00"},{"alias_kind":"pith_short_16","alias_value":"EIDGZ4PJJ3TWMOB2","created_at":"2026-07-05T01:51:12.744159+00:00"},{"alias_kind":"pith_short_8","alias_value":"EIDGZ4PJ","created_at":"2026-07-05T01:51:12.744159+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/EIDGZ4PJJ3TWMOB2XWBCDFV75B","json":"https://pith.science/pith/EIDGZ4PJJ3TWMOB2XWBCDFV75B.json","graph_json":"https://pith.science/api/pith-number/EIDGZ4PJJ3TWMOB2XWBCDFV75B/graph.json","events_json":"https://pith.science/api/pith-number/EIDGZ4PJJ3TWMOB2XWBCDFV75B/events.json","paper":"https://pith.science/paper/EIDGZ4PJ"},"agent_actions":{"view_html":"https://pith.science/pith/EIDGZ4PJJ3TWMOB2XWBCDFV75B","download_json":"https://pith.science/pith/EIDGZ4PJJ3TWMOB2XWBCDFV75B.json","view_paper":"https://pith.science/paper/EIDGZ4PJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.06182&json=true","fetch_graph":"https://pith.science/api/pith-number/EIDGZ4PJJ3TWMOB2XWBCDFV75B/graph.json","fetch_events":"https://pith.science/api/pith-number/EIDGZ4PJJ3TWMOB2XWBCDFV75B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EIDGZ4PJJ3TWMOB2XWBCDFV75B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EIDGZ4PJJ3TWMOB2XWBCDFV75B/action/storage_attestation","attest_author":"https://pith.science/pith/EIDGZ4PJJ3TWMOB2XWBCDFV75B/action/author_attestation","sign_citation":"https://pith.science/pith/EIDGZ4PJJ3TWMOB2XWBCDFV75B/action/citation_signature","submit_replication":"https://pith.science/pith/EIDGZ4PJJ3TWMOB2XWBCDFV75B/action/replication_record"}},"created_at":"2026-07-05T01:51:12.744159+00:00","updated_at":"2026-07-05T01:51:12.744159+00:00"}