{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:RLRSZFAQLU3M2B6PDGP55LX7B5","short_pith_number":"pith:RLRSZFAQ","schema_version":"1.0","canonical_sha256":"8ae32c94105d36cd07cf199fdeaeff0f543115fc69df42f223a793bd3628c948","source":{"kind":"arxiv","id":"1712.09708","version":5},"attestation_state":"computed","paper":{"title":"Learning More Universal Representations for Transfer-Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"C\\'eline Hudelot, Herv\\'e Le Borgne, Mohamed El Amine Seddik, Mohamed Tamaazousti, Youssef Tamaazousti","submitted_at":"2017-12-27T23:14:46Z","abstract_excerpt":"A representation is supposed universal if it encodes any element of the visual world (e.g., objects, scenes) in any configuration (e.g., scale, context). While not expecting pure universal representations, the goal in the literature is to improve the universality level, starting from a representation with a certain level. To do so, the state-of-the-art consists in learning CNN-based representations on a diversified training problem (e.g., ImageNet modified by adding annotated data). While it effectively increases universality, such approach still requires a large amount of efforts to satisfy t"},"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":"1712.09708","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-12-27T23:14:46Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"527f85c6e4e00212f6b34e90e6ae407ff433c60aad17cf78d195cfe701a3dce5","abstract_canon_sha256":"cdf984d7fd5615c4d315a236090953fe075eaa0d2723e6a524627cc21ee80f14"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:06:40.880796Z","signature_b64":"tSn0skyOGkMb87UtS4hwdWOk47jY1BByfoTQ53pon46iehcJZNEly+dD3uVfYzd3EHhCokfpPRxF8A69zcsyBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ae32c94105d36cd07cf199fdeaeff0f543115fc69df42f223a793bd3628c948","last_reissued_at":"2026-05-18T00:06:40.880202Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:06:40.880202Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning More Universal Representations for Transfer-Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"C\\'eline Hudelot, Herv\\'e Le Borgne, Mohamed El Amine Seddik, Mohamed Tamaazousti, Youssef Tamaazousti","submitted_at":"2017-12-27T23:14:46Z","abstract_excerpt":"A representation is supposed universal if it encodes any element of the visual world (e.g., objects, scenes) in any configuration (e.g., scale, context). While not expecting pure universal representations, the goal in the literature is to improve the universality level, starting from a representation with a certain level. To do so, the state-of-the-art consists in learning CNN-based representations on a diversified training problem (e.g., ImageNet modified by adding annotated data). While it effectively increases universality, such approach still requires a large amount of efforts to satisfy t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.09708","kind":"arxiv","version":5},"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":"1712.09708","created_at":"2026-05-18T00:06:40.880286+00:00"},{"alias_kind":"arxiv_version","alias_value":"1712.09708v5","created_at":"2026-05-18T00:06:40.880286+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.09708","created_at":"2026-05-18T00:06:40.880286+00:00"},{"alias_kind":"pith_short_12","alias_value":"RLRSZFAQLU3M","created_at":"2026-05-18T12:31:39.905425+00:00"},{"alias_kind":"pith_short_16","alias_value":"RLRSZFAQLU3M2B6P","created_at":"2026-05-18T12:31:39.905425+00:00"},{"alias_kind":"pith_short_8","alias_value":"RLRSZFAQ","created_at":"2026-05-18T12:31:39.905425+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/RLRSZFAQLU3M2B6PDGP55LX7B5","json":"https://pith.science/pith/RLRSZFAQLU3M2B6PDGP55LX7B5.json","graph_json":"https://pith.science/api/pith-number/RLRSZFAQLU3M2B6PDGP55LX7B5/graph.json","events_json":"https://pith.science/api/pith-number/RLRSZFAQLU3M2B6PDGP55LX7B5/events.json","paper":"https://pith.science/paper/RLRSZFAQ"},"agent_actions":{"view_html":"https://pith.science/pith/RLRSZFAQLU3M2B6PDGP55LX7B5","download_json":"https://pith.science/pith/RLRSZFAQLU3M2B6PDGP55LX7B5.json","view_paper":"https://pith.science/paper/RLRSZFAQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1712.09708&json=true","fetch_graph":"https://pith.science/api/pith-number/RLRSZFAQLU3M2B6PDGP55LX7B5/graph.json","fetch_events":"https://pith.science/api/pith-number/RLRSZFAQLU3M2B6PDGP55LX7B5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RLRSZFAQLU3M2B6PDGP55LX7B5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RLRSZFAQLU3M2B6PDGP55LX7B5/action/storage_attestation","attest_author":"https://pith.science/pith/RLRSZFAQLU3M2B6PDGP55LX7B5/action/author_attestation","sign_citation":"https://pith.science/pith/RLRSZFAQLU3M2B6PDGP55LX7B5/action/citation_signature","submit_replication":"https://pith.science/pith/RLRSZFAQLU3M2B6PDGP55LX7B5/action/replication_record"}},"created_at":"2026-05-18T00:06:40.880286+00:00","updated_at":"2026-05-18T00:06:40.880286+00:00"}