{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:JKMLG6SDQYX3KO7HRIIAUKKS6G","short_pith_number":"pith:JKMLG6SD","schema_version":"1.0","canonical_sha256":"4a98b37a43862fb53be78a100a2952f1a895c7f9cccd8e819c00afe49a905d67","source":{"kind":"arxiv","id":"2109.08580","version":2},"attestation_state":"computed","paper":{"title":"Self-Supervised Neural Architecture Search for Imbalanced Datasets","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Aleksandr Timofeev, Grigorios G. Chrysos, Volkan Cevher","submitted_at":"2021-09-17T14:56:36Z","abstract_excerpt":"Neural Architecture Search (NAS) provides state-of-the-art results when trained on well-curated datasets with annotated labels. However, annotating data or even having balanced number of samples can be a luxury for practitioners from different scientific fields, e.g., in the medical domain. To that end, we propose a NAS-based framework that bears the threefold contributions: (a) we focus on the self-supervised scenario, i.e., where no labels are required to determine the architecture, and (b) we assume the datasets are imbalanced, (c) we design each component to be able to run on a resource co"},"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":"2109.08580","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-09-17T14:56:36Z","cross_cats_sorted":["cs.LG","eess.IV"],"title_canon_sha256":"57b20a6b856a534ffddc1775b8a48f90f3556d7c14c252853a9b48e2bc907d0f","abstract_canon_sha256":"6e06aa6a441115a2c31d28de30737f8358cc702445147a4fb6f60e0289f7aff8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:15:37.753996Z","signature_b64":"LuJyKj0ChLNTQJodU6O29uAgZYU0GpLmkIQ7BZETQ3pXJ8N5Z7x9L7gxfh0xtmE1y9qmeIWt6hc39I8VMpmdCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4a98b37a43862fb53be78a100a2952f1a895c7f9cccd8e819c00afe49a905d67","last_reissued_at":"2026-07-05T03:15:37.753598Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:15:37.753598Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Supervised Neural Architecture Search for Imbalanced Datasets","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Aleksandr Timofeev, Grigorios G. Chrysos, Volkan Cevher","submitted_at":"2021-09-17T14:56:36Z","abstract_excerpt":"Neural Architecture Search (NAS) provides state-of-the-art results when trained on well-curated datasets with annotated labels. However, annotating data or even having balanced number of samples can be a luxury for practitioners from different scientific fields, e.g., in the medical domain. To that end, we propose a NAS-based framework that bears the threefold contributions: (a) we focus on the self-supervised scenario, i.e., where no labels are required to determine the architecture, and (b) we assume the datasets are imbalanced, (c) we design each component to be able to run on a resource co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.08580","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/2109.08580/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":"2109.08580","created_at":"2026-07-05T03:15:37.753652+00:00"},{"alias_kind":"arxiv_version","alias_value":"2109.08580v2","created_at":"2026-07-05T03:15:37.753652+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.08580","created_at":"2026-07-05T03:15:37.753652+00:00"},{"alias_kind":"pith_short_12","alias_value":"JKMLG6SDQYX3","created_at":"2026-07-05T03:15:37.753652+00:00"},{"alias_kind":"pith_short_16","alias_value":"JKMLG6SDQYX3KO7H","created_at":"2026-07-05T03:15:37.753652+00:00"},{"alias_kind":"pith_short_8","alias_value":"JKMLG6SD","created_at":"2026-07-05T03:15:37.753652+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22991","citing_title":"Neural Architecture Search of Sample Reweighting Networks for Complex Distribution Shift","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2402.13228","citing_title":"Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive","ref_index":184,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JKMLG6SDQYX3KO7HRIIAUKKS6G","json":"https://pith.science/pith/JKMLG6SDQYX3KO7HRIIAUKKS6G.json","graph_json":"https://pith.science/api/pith-number/JKMLG6SDQYX3KO7HRIIAUKKS6G/graph.json","events_json":"https://pith.science/api/pith-number/JKMLG6SDQYX3KO7HRIIAUKKS6G/events.json","paper":"https://pith.science/paper/JKMLG6SD"},"agent_actions":{"view_html":"https://pith.science/pith/JKMLG6SDQYX3KO7HRIIAUKKS6G","download_json":"https://pith.science/pith/JKMLG6SDQYX3KO7HRIIAUKKS6G.json","view_paper":"https://pith.science/paper/JKMLG6SD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2109.08580&json=true","fetch_graph":"https://pith.science/api/pith-number/JKMLG6SDQYX3KO7HRIIAUKKS6G/graph.json","fetch_events":"https://pith.science/api/pith-number/JKMLG6SDQYX3KO7HRIIAUKKS6G/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JKMLG6SDQYX3KO7HRIIAUKKS6G/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JKMLG6SDQYX3KO7HRIIAUKKS6G/action/storage_attestation","attest_author":"https://pith.science/pith/JKMLG6SDQYX3KO7HRIIAUKKS6G/action/author_attestation","sign_citation":"https://pith.science/pith/JKMLG6SDQYX3KO7HRIIAUKKS6G/action/citation_signature","submit_replication":"https://pith.science/pith/JKMLG6SDQYX3KO7HRIIAUKKS6G/action/replication_record"}},"created_at":"2026-07-05T03:15:37.753652+00:00","updated_at":"2026-07-05T03:15:37.753652+00:00"}