{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:T7AAUEZM25MNPMURX7VG3S5QV6","short_pith_number":"pith:T7AAUEZM","schema_version":"1.0","canonical_sha256":"9fc00a132cd758d7b291bfea6dcbb0af9f60e86ca7ea7b8fb37d0201b6e5aef6","source":{"kind":"arxiv","id":"2203.06404","version":1},"attestation_state":"computed","paper":{"title":"A Proposal to Study \"Is High Quality Data All We Need?\"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Anjana Arunkumar, Swaroop Mishra","submitted_at":"2022-03-12T10:50:13Z","abstract_excerpt":"Even though deep neural models have achieved superhuman performance on many popular benchmarks, they have failed to generalize to OOD or adversarial datasets. Conventional approaches aimed at increasing robustness include developing increasingly large models and augmentation with large scale datasets. However, orthogonal to these trends, we hypothesize that a smaller, high quality dataset is what we need. Our hypothesis is based on the fact that deep neural networks are data driven models, and data is what leads/misleads models. In this work, we propose an empirical study that examines how to "},"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":"2203.06404","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-12T10:50:13Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"d1993e044c0484430b39f844b484c996d6e66881a6297877f54713e735c75d01","abstract_canon_sha256":"1c5fd55930d5183f8c637f992d084b36cadeed7ad3576cedee92f9a79053a3e3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:04:50.351897Z","signature_b64":"y9TxmK5cMcYTRE9okVaDqVeNuGVs63rreM6EwCr93H9vqNztcNLLr6kj3WfMhhtwh/TwXdaYEhFFNqIL84X/Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9fc00a132cd758d7b291bfea6dcbb0af9f60e86ca7ea7b8fb37d0201b6e5aef6","last_reissued_at":"2026-07-05T04:04:50.351476Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:04:50.351476Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Proposal to Study \"Is High Quality Data All We Need?\"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Anjana Arunkumar, Swaroop Mishra","submitted_at":"2022-03-12T10:50:13Z","abstract_excerpt":"Even though deep neural models have achieved superhuman performance on many popular benchmarks, they have failed to generalize to OOD or adversarial datasets. Conventional approaches aimed at increasing robustness include developing increasingly large models and augmentation with large scale datasets. However, orthogonal to these trends, we hypothesize that a smaller, high quality dataset is what we need. Our hypothesis is based on the fact that deep neural networks are data driven models, and data is what leads/misleads models. In this work, we propose an empirical study that examines how to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.06404","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2203.06404/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":"2203.06404","created_at":"2026-07-05T04:04:50.351535+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.06404v1","created_at":"2026-07-05T04:04:50.351535+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.06404","created_at":"2026-07-05T04:04:50.351535+00:00"},{"alias_kind":"pith_short_12","alias_value":"T7AAUEZM25MN","created_at":"2026-07-05T04:04:50.351535+00:00"},{"alias_kind":"pith_short_16","alias_value":"T7AAUEZM25MNPMUR","created_at":"2026-07-05T04:04:50.351535+00:00"},{"alias_kind":"pith_short_8","alias_value":"T7AAUEZM","created_at":"2026-07-05T04:04:50.351535+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.20564","citing_title":"The NaijaVoices Dataset: Cultivating Large-Scale, High-Quality, Culturally-Rich Speech Data for African Languages","ref_index":2022,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T7AAUEZM25MNPMURX7VG3S5QV6","json":"https://pith.science/pith/T7AAUEZM25MNPMURX7VG3S5QV6.json","graph_json":"https://pith.science/api/pith-number/T7AAUEZM25MNPMURX7VG3S5QV6/graph.json","events_json":"https://pith.science/api/pith-number/T7AAUEZM25MNPMURX7VG3S5QV6/events.json","paper":"https://pith.science/paper/T7AAUEZM"},"agent_actions":{"view_html":"https://pith.science/pith/T7AAUEZM25MNPMURX7VG3S5QV6","download_json":"https://pith.science/pith/T7AAUEZM25MNPMURX7VG3S5QV6.json","view_paper":"https://pith.science/paper/T7AAUEZM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.06404&json=true","fetch_graph":"https://pith.science/api/pith-number/T7AAUEZM25MNPMURX7VG3S5QV6/graph.json","fetch_events":"https://pith.science/api/pith-number/T7AAUEZM25MNPMURX7VG3S5QV6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T7AAUEZM25MNPMURX7VG3S5QV6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T7AAUEZM25MNPMURX7VG3S5QV6/action/storage_attestation","attest_author":"https://pith.science/pith/T7AAUEZM25MNPMURX7VG3S5QV6/action/author_attestation","sign_citation":"https://pith.science/pith/T7AAUEZM25MNPMURX7VG3S5QV6/action/citation_signature","submit_replication":"https://pith.science/pith/T7AAUEZM25MNPMURX7VG3S5QV6/action/replication_record"}},"created_at":"2026-07-05T04:04:50.351535+00:00","updated_at":"2026-07-05T04:04:50.351535+00:00"}