{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:RRWWNZLMPYYKEZSN6CHAUZVX4W","short_pith_number":"pith:RRWWNZLM","schema_version":"1.0","canonical_sha256":"8c6d66e56c7e30a2664df08e0a66b7e5a574e9d4593310b5488333e8f4d2e797","source":{"kind":"arxiv","id":"1802.01483","version":2},"attestation_state":"computed","paper":{"title":"Explicit Inductive Bias for Transfer Learning with Convolutional Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Franck Davoine, Xuhong Li, Yves Grandvalet","submitted_at":"2018-02-05T15:58:40Z","abstract_excerpt":"In inductive transfer learning, fine-tuning pre-trained convolutional networks substantially outperforms training from scratch. When using fine-tuning, the underlying assumption is that the pre-trained model extracts generic features, which are at least partially relevant for solving the target task, but would be difficult to extract from the limited amount of data available on the target task. However, besides the initialization with the pre-trained model and the early stopping, there is no mechanism in fine-tuning for retaining the features learned on the source task. In this paper, we inves"},"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":"1802.01483","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-02-05T15:58:40Z","cross_cats_sorted":[],"title_canon_sha256":"2de709077a87b75b085997a994c2f167cb71ee7ad5d8d32f7dfcfcfd76289ebc","abstract_canon_sha256":"9565216b309318e750818e4faf0a909429e5368bda14252cca0866cd283a5381"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:06.352136Z","signature_b64":"WtpcNf6UWNhBp1zxVQzzj8AP2P/Q0VXjjdtHUH7VEGajmQBzr92rWBbraj0zmQjyLV/anuZfbHxqcfxu4pdjBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c6d66e56c7e30a2664df08e0a66b7e5a574e9d4593310b5488333e8f4d2e797","last_reissued_at":"2026-05-18T00:14:06.351651Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:06.351651Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Explicit Inductive Bias for Transfer Learning with Convolutional Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Franck Davoine, Xuhong Li, Yves Grandvalet","submitted_at":"2018-02-05T15:58:40Z","abstract_excerpt":"In inductive transfer learning, fine-tuning pre-trained convolutional networks substantially outperforms training from scratch. When using fine-tuning, the underlying assumption is that the pre-trained model extracts generic features, which are at least partially relevant for solving the target task, but would be difficult to extract from the limited amount of data available on the target task. However, besides the initialization with the pre-trained model and the early stopping, there is no mechanism in fine-tuning for retaining the features learned on the source task. In this paper, we inves"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.01483","kind":"arxiv","version":2},"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":"1802.01483","created_at":"2026-05-18T00:14:06.351730+00:00"},{"alias_kind":"arxiv_version","alias_value":"1802.01483v2","created_at":"2026-05-18T00:14:06.351730+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.01483","created_at":"2026-05-18T00:14:06.351730+00:00"},{"alias_kind":"pith_short_12","alias_value":"RRWWNZLMPYYK","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_16","alias_value":"RRWWNZLMPYYKEZSN","created_at":"2026-05-18T12:32:50.500415+00:00"},{"alias_kind":"pith_short_8","alias_value":"RRWWNZLM","created_at":"2026-05-18T12:32:50.500415+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/RRWWNZLMPYYKEZSN6CHAUZVX4W","json":"https://pith.science/pith/RRWWNZLMPYYKEZSN6CHAUZVX4W.json","graph_json":"https://pith.science/api/pith-number/RRWWNZLMPYYKEZSN6CHAUZVX4W/graph.json","events_json":"https://pith.science/api/pith-number/RRWWNZLMPYYKEZSN6CHAUZVX4W/events.json","paper":"https://pith.science/paper/RRWWNZLM"},"agent_actions":{"view_html":"https://pith.science/pith/RRWWNZLMPYYKEZSN6CHAUZVX4W","download_json":"https://pith.science/pith/RRWWNZLMPYYKEZSN6CHAUZVX4W.json","view_paper":"https://pith.science/paper/RRWWNZLM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1802.01483&json=true","fetch_graph":"https://pith.science/api/pith-number/RRWWNZLMPYYKEZSN6CHAUZVX4W/graph.json","fetch_events":"https://pith.science/api/pith-number/RRWWNZLMPYYKEZSN6CHAUZVX4W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RRWWNZLMPYYKEZSN6CHAUZVX4W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RRWWNZLMPYYKEZSN6CHAUZVX4W/action/storage_attestation","attest_author":"https://pith.science/pith/RRWWNZLMPYYKEZSN6CHAUZVX4W/action/author_attestation","sign_citation":"https://pith.science/pith/RRWWNZLMPYYKEZSN6CHAUZVX4W/action/citation_signature","submit_replication":"https://pith.science/pith/RRWWNZLMPYYKEZSN6CHAUZVX4W/action/replication_record"}},"created_at":"2026-05-18T00:14:06.351730+00:00","updated_at":"2026-05-18T00:14:06.351730+00:00"}