{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:HIIJLFWSHULCB3HAADOEBOXQJE","short_pith_number":"pith:HIIJLFWS","schema_version":"1.0","canonical_sha256":"3a109596d23d1620ece000dc40baf0490bf710b0955547e64f5ee91031fdcee5","source":{"kind":"arxiv","id":"1905.09272","version":3},"attestation_state":"computed","paper":{"title":"Data-Efficient Image Recognition with Contrastive Predictive Coding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Aaron van den Oord, Ali Razavi, Aravind Srinivas, Carl Doersch, Jeffrey De Fauw, Olivier J. H\\'enaff, S. M. Ali Eslami","submitted_at":"2019-05-22T17:57:49Z","abstract_excerpt":"Human observers can learn to recognize new categories of images from a handful of examples, yet doing so with artificial ones remains an open challenge. We hypothesize that data-efficient recognition is enabled by representations which make the variability in natural signals more predictable. We therefore revisit and improve Contrastive Predictive Coding, an unsupervised objective for learning such representations. This new implementation produces features which support state-of-the-art linear classification accuracy on the ImageNet dataset. When used as input for non-linear classification wit"},"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":"1905.09272","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-05-22T17:57:49Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3443e5ccf2fa1838276e824c91ec79699b850197b9cc4b297b9f0662ce3c28d3","abstract_canon_sha256":"963dd3173cbf7ec64fc4c3b86efdceee455ed47c2fecf11a0222265fb4a96135"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:15:22.129270Z","signature_b64":"taB/CZ2XLlCPAWe1W9ONM33wt0ZGGNpXxZE5Ore72918zqTW6P/eqG7yZgsHthMsuOEmWnzLIKMSnY3jMAZHDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a109596d23d1620ece000dc40baf0490bf710b0955547e64f5ee91031fdcee5","last_reissued_at":"2026-07-05T01:15:22.128764Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:15:22.128764Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data-Efficient Image Recognition with Contrastive Predictive Coding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Aaron van den Oord, Ali Razavi, Aravind Srinivas, Carl Doersch, Jeffrey De Fauw, Olivier J. H\\'enaff, S. M. Ali Eslami","submitted_at":"2019-05-22T17:57:49Z","abstract_excerpt":"Human observers can learn to recognize new categories of images from a handful of examples, yet doing so with artificial ones remains an open challenge. We hypothesize that data-efficient recognition is enabled by representations which make the variability in natural signals more predictable. We therefore revisit and improve Contrastive Predictive Coding, an unsupervised objective for learning such representations. This new implementation produces features which support state-of-the-art linear classification accuracy on the ImageNet dataset. When used as input for non-linear classification wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.09272","kind":"arxiv","version":3},"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/1905.09272/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":"1905.09272","created_at":"2026-07-05T01:15:22.128815+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.09272v3","created_at":"2026-07-05T01:15:22.128815+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.09272","created_at":"2026-07-05T01:15:22.128815+00:00"},{"alias_kind":"pith_short_12","alias_value":"HIIJLFWSHULC","created_at":"2026-07-05T01:15:22.128815+00:00"},{"alias_kind":"pith_short_16","alias_value":"HIIJLFWSHULCB3HA","created_at":"2026-07-05T01:15:22.128815+00:00"},{"alias_kind":"pith_short_8","alias_value":"HIIJLFWS","created_at":"2026-07-05T01:15:22.128815+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"1910.04867","citing_title":"A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2002.05709","citing_title":"A Simple Framework for Contrastive Learning of Visual Representations","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2003.04297","citing_title":"Improved Baselines with Momentum Contrastive Learning","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HIIJLFWSHULCB3HAADOEBOXQJE","json":"https://pith.science/pith/HIIJLFWSHULCB3HAADOEBOXQJE.json","graph_json":"https://pith.science/api/pith-number/HIIJLFWSHULCB3HAADOEBOXQJE/graph.json","events_json":"https://pith.science/api/pith-number/HIIJLFWSHULCB3HAADOEBOXQJE/events.json","paper":"https://pith.science/paper/HIIJLFWS"},"agent_actions":{"view_html":"https://pith.science/pith/HIIJLFWSHULCB3HAADOEBOXQJE","download_json":"https://pith.science/pith/HIIJLFWSHULCB3HAADOEBOXQJE.json","view_paper":"https://pith.science/paper/HIIJLFWS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.09272&json=true","fetch_graph":"https://pith.science/api/pith-number/HIIJLFWSHULCB3HAADOEBOXQJE/graph.json","fetch_events":"https://pith.science/api/pith-number/HIIJLFWSHULCB3HAADOEBOXQJE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HIIJLFWSHULCB3HAADOEBOXQJE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HIIJLFWSHULCB3HAADOEBOXQJE/action/storage_attestation","attest_author":"https://pith.science/pith/HIIJLFWSHULCB3HAADOEBOXQJE/action/author_attestation","sign_citation":"https://pith.science/pith/HIIJLFWSHULCB3HAADOEBOXQJE/action/citation_signature","submit_replication":"https://pith.science/pith/HIIJLFWSHULCB3HAADOEBOXQJE/action/replication_record"}},"created_at":"2026-07-05T01:15:22.128815+00:00","updated_at":"2026-07-05T01:15:22.128815+00:00"}