{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:CW2SWSL5XCHS6MFBX2ILUXJUIC","short_pith_number":"pith:CW2SWSL5","schema_version":"1.0","canonical_sha256":"15b52b497db88f2f30a1be90ba5d3440a0e73dbedb3800d5379d667b686850ea","source":{"kind":"arxiv","id":"2103.16483","version":2},"attestation_state":"computed","paper":{"title":"Benchmarking Representation Learning for Natural World Image Collections","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Elijah Cole, Grant Van Horn, Kimberly Wilber, Oisin Mac Aodha, Sara Beery, Serge Belongie","submitted_at":"2021-03-30T16:41:49Z","abstract_excerpt":"Recent progress in self-supervised learning has resulted in models that are capable of extracting rich representations from image collections without requiring any explicit label supervision. However, to date the vast majority of these approaches have restricted themselves to training on standard benchmark datasets such as ImageNet. We argue that fine-grained visual categorization problems, such as plant and animal species classification, provide an informative testbed for self-supervised learning. In order to facilitate progress in this area we present two new natural world visual classificat"},"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":"2103.16483","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-30T16:41:49Z","cross_cats_sorted":[],"title_canon_sha256":"192c3b618d532bcc1d1f650767627e5096735e8780ca6f2c531b740eeea42d02","abstract_canon_sha256":"bc04e222eb3dc5265dfb1691968a6c5ba8e0c185def650959801a756f9ad0d03"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:47:43.641612Z","signature_b64":"QXgbxm8smIZuBvCuQn0zQiqKXv7X4kWvm+O23xJiJjVhjHhYxGjHkkKh8xMSFgvMDia19ziYej66EQnkEBOcDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15b52b497db88f2f30a1be90ba5d3440a0e73dbedb3800d5379d667b686850ea","last_reissued_at":"2026-07-05T02:47:43.641197Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:47:43.641197Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmarking Representation Learning for Natural World Image Collections","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Elijah Cole, Grant Van Horn, Kimberly Wilber, Oisin Mac Aodha, Sara Beery, Serge Belongie","submitted_at":"2021-03-30T16:41:49Z","abstract_excerpt":"Recent progress in self-supervised learning has resulted in models that are capable of extracting rich representations from image collections without requiring any explicit label supervision. However, to date the vast majority of these approaches have restricted themselves to training on standard benchmark datasets such as ImageNet. We argue that fine-grained visual categorization problems, such as plant and animal species classification, provide an informative testbed for self-supervised learning. In order to facilitate progress in this area we present two new natural world visual classificat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.16483","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2103.16483/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":"2103.16483","created_at":"2026-07-05T02:47:43.641249+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.16483v2","created_at":"2026-07-05T02:47:43.641249+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.16483","created_at":"2026-07-05T02:47:43.641249+00:00"},{"alias_kind":"pith_short_12","alias_value":"CW2SWSL5XCHS","created_at":"2026-07-05T02:47:43.641249+00:00"},{"alias_kind":"pith_short_16","alias_value":"CW2SWSL5XCHS6MFB","created_at":"2026-07-05T02:47:43.641249+00:00"},{"alias_kind":"pith_short_8","alias_value":"CW2SWSL5","created_at":"2026-07-05T02:47:43.641249+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.22764","citing_title":"Test-time augmentation improves efficiency in conformal prediction","ref_index":2021,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CW2SWSL5XCHS6MFBX2ILUXJUIC","json":"https://pith.science/pith/CW2SWSL5XCHS6MFBX2ILUXJUIC.json","graph_json":"https://pith.science/api/pith-number/CW2SWSL5XCHS6MFBX2ILUXJUIC/graph.json","events_json":"https://pith.science/api/pith-number/CW2SWSL5XCHS6MFBX2ILUXJUIC/events.json","paper":"https://pith.science/paper/CW2SWSL5"},"agent_actions":{"view_html":"https://pith.science/pith/CW2SWSL5XCHS6MFBX2ILUXJUIC","download_json":"https://pith.science/pith/CW2SWSL5XCHS6MFBX2ILUXJUIC.json","view_paper":"https://pith.science/paper/CW2SWSL5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.16483&json=true","fetch_graph":"https://pith.science/api/pith-number/CW2SWSL5XCHS6MFBX2ILUXJUIC/graph.json","fetch_events":"https://pith.science/api/pith-number/CW2SWSL5XCHS6MFBX2ILUXJUIC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CW2SWSL5XCHS6MFBX2ILUXJUIC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CW2SWSL5XCHS6MFBX2ILUXJUIC/action/storage_attestation","attest_author":"https://pith.science/pith/CW2SWSL5XCHS6MFBX2ILUXJUIC/action/author_attestation","sign_citation":"https://pith.science/pith/CW2SWSL5XCHS6MFBX2ILUXJUIC/action/citation_signature","submit_replication":"https://pith.science/pith/CW2SWSL5XCHS6MFBX2ILUXJUIC/action/replication_record"}},"created_at":"2026-07-05T02:47:43.641249+00:00","updated_at":"2026-07-05T02:47:43.641249+00:00"}