{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:M7CSXQDF3QSSVPYLUUCT2PQPCS","short_pith_number":"pith:M7CSXQDF","schema_version":"1.0","canonical_sha256":"67c52bc065dc252abf0ba5053d3e0f14b013b3407200fa5b33f75fc321195fa1","source":{"kind":"arxiv","id":"1810.02126","version":1},"attestation_state":"computed","paper":{"title":"Learning Finer-class Networks for Universal Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"C\\'eline Hudelot, Herv\\'e Le Borgne, Julien Girard, Youssef Tamaazousti","submitted_at":"2018-10-04T09:58:34Z","abstract_excerpt":"Many real-world visual recognition use-cases can not directly benefit from state-of-the-art CNN-based approaches because of the lack of many annotated data. The usual approach to deal with this is to transfer a representation pre-learned on a large annotated source-task onto a target-task of interest. This raises the question of how well the original representation is \"universal\", that is to say directly adapted to many different target-tasks. To improve such universality, the state-of-the-art consists in training networks on a diversified source problem, that is modified either by adding gene"},"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":"1810.02126","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-10-04T09:58:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7c0046c9cd9385e8bd9f7122f189cd05f2d42d4a40bfb67920140977506e63b5","abstract_canon_sha256":"f0e824b729d1c8d2fc553e9ab0016a1e95e888a0c4f8d0c2f478b071d673b7d8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:04:06.167627Z","signature_b64":"5BGXILMVlqRAHs6zypnAIQT7gIySCrm9bzLV8FlqkOkHnmF5AIN0wjWVdVvHrL9HhGQWu8Ja0TbFNM2TRA9QBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67c52bc065dc252abf0ba5053d3e0f14b013b3407200fa5b33f75fc321195fa1","last_reissued_at":"2026-05-18T00:04:06.166962Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:04:06.166962Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Finer-class Networks for Universal Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"C\\'eline Hudelot, Herv\\'e Le Borgne, Julien Girard, Youssef Tamaazousti","submitted_at":"2018-10-04T09:58:34Z","abstract_excerpt":"Many real-world visual recognition use-cases can not directly benefit from state-of-the-art CNN-based approaches because of the lack of many annotated data. The usual approach to deal with this is to transfer a representation pre-learned on a large annotated source-task onto a target-task of interest. This raises the question of how well the original representation is \"universal\", that is to say directly adapted to many different target-tasks. To improve such universality, the state-of-the-art consists in training networks on a diversified source problem, that is modified either by adding gene"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.02126","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":"1810.02126","created_at":"2026-05-18T00:04:06.167067+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.02126v1","created_at":"2026-05-18T00:04:06.167067+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.02126","created_at":"2026-05-18T00:04:06.167067+00:00"},{"alias_kind":"pith_short_12","alias_value":"M7CSXQDF3QSS","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_16","alias_value":"M7CSXQDF3QSSVPYL","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_8","alias_value":"M7CSXQDF","created_at":"2026-05-18T12:32:37.024351+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/M7CSXQDF3QSSVPYLUUCT2PQPCS","json":"https://pith.science/pith/M7CSXQDF3QSSVPYLUUCT2PQPCS.json","graph_json":"https://pith.science/api/pith-number/M7CSXQDF3QSSVPYLUUCT2PQPCS/graph.json","events_json":"https://pith.science/api/pith-number/M7CSXQDF3QSSVPYLUUCT2PQPCS/events.json","paper":"https://pith.science/paper/M7CSXQDF"},"agent_actions":{"view_html":"https://pith.science/pith/M7CSXQDF3QSSVPYLUUCT2PQPCS","download_json":"https://pith.science/pith/M7CSXQDF3QSSVPYLUUCT2PQPCS.json","view_paper":"https://pith.science/paper/M7CSXQDF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.02126&json=true","fetch_graph":"https://pith.science/api/pith-number/M7CSXQDF3QSSVPYLUUCT2PQPCS/graph.json","fetch_events":"https://pith.science/api/pith-number/M7CSXQDF3QSSVPYLUUCT2PQPCS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M7CSXQDF3QSSVPYLUUCT2PQPCS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M7CSXQDF3QSSVPYLUUCT2PQPCS/action/storage_attestation","attest_author":"https://pith.science/pith/M7CSXQDF3QSSVPYLUUCT2PQPCS/action/author_attestation","sign_citation":"https://pith.science/pith/M7CSXQDF3QSSVPYLUUCT2PQPCS/action/citation_signature","submit_replication":"https://pith.science/pith/M7CSXQDF3QSSVPYLUUCT2PQPCS/action/replication_record"}},"created_at":"2026-05-18T00:04:06.167067+00:00","updated_at":"2026-05-18T00:04:06.167067+00:00"}