{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:53LB4EDHW3KWVDDKPFCBUFR4XI","short_pith_number":"pith:53LB4EDH","schema_version":"1.0","canonical_sha256":"eed61e1067b6d56a8c6a79441a163cba2eb0aedea8c96409f9a79fd3eb572bbc","source":{"kind":"arxiv","id":"2210.03822","version":1},"attestation_state":"computed","paper":{"title":"Is margin all you need? An extensive empirical study of active learning on tabular data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Afshin Rostamizadeh, Dara Bahri, Heinrich Jiang, Tal Schuster","submitted_at":"2022-10-07T21:18:24Z","abstract_excerpt":"Given a labeled training set and a collection of unlabeled data, the goal of active learning (AL) is to identify the best unlabeled points to label. In this comprehensive study, we analyze the performance of a variety of AL algorithms on deep neural networks trained on 69 real-world tabular classification datasets from the OpenML-CC18 benchmark. We consider different data regimes and the effect of self-supervised model pre-training. Surprisingly, we find that the classical margin sampling technique matches or outperforms all others, including current state-of-art, in a wide range of experiment"},"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":"2210.03822","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-07T21:18:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"02c2b13f440a800d607b1c6387f5984349bb3855e3f2ab11f7956c4435161f7d","abstract_canon_sha256":"116f396073ee223d24793b688168996bdd65838ff72fd7dff4a3ed7c691cc16b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:04:32.629744Z","signature_b64":"O/KQgyW8VZWsfU/Wp3TMo/oNLw4KjPVQGytC32qIWNI4RP+5KoG4XmGoPx0O70zOnMo5QY5fQ7B1fU3MFFMhAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eed61e1067b6d56a8c6a79441a163cba2eb0aedea8c96409f9a79fd3eb572bbc","last_reissued_at":"2026-07-05T05:04:32.629357Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:04:32.629357Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Is margin all you need? An extensive empirical study of active learning on tabular data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Afshin Rostamizadeh, Dara Bahri, Heinrich Jiang, Tal Schuster","submitted_at":"2022-10-07T21:18:24Z","abstract_excerpt":"Given a labeled training set and a collection of unlabeled data, the goal of active learning (AL) is to identify the best unlabeled points to label. In this comprehensive study, we analyze the performance of a variety of AL algorithms on deep neural networks trained on 69 real-world tabular classification datasets from the OpenML-CC18 benchmark. We consider different data regimes and the effect of self-supervised model pre-training. Surprisingly, we find that the classical margin sampling technique matches or outperforms all others, including current state-of-art, in a wide range of experiment"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.03822","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/2210.03822/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":"2210.03822","created_at":"2026-07-05T05:04:32.629414+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.03822v1","created_at":"2026-07-05T05:04:32.629414+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.03822","created_at":"2026-07-05T05:04:32.629414+00:00"},{"alias_kind":"pith_short_12","alias_value":"53LB4EDHW3KW","created_at":"2026-07-05T05:04:32.629414+00:00"},{"alias_kind":"pith_short_16","alias_value":"53LB4EDHW3KWVDDK","created_at":"2026-07-05T05:04:32.629414+00:00"},{"alias_kind":"pith_short_8","alias_value":"53LB4EDH","created_at":"2026-07-05T05:04:32.629414+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.01992","citing_title":"No Free Lunch in Active Learning: LLM Embedding Quality Dictates Query Strategy Success","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/53LB4EDHW3KWVDDKPFCBUFR4XI","json":"https://pith.science/pith/53LB4EDHW3KWVDDKPFCBUFR4XI.json","graph_json":"https://pith.science/api/pith-number/53LB4EDHW3KWVDDKPFCBUFR4XI/graph.json","events_json":"https://pith.science/api/pith-number/53LB4EDHW3KWVDDKPFCBUFR4XI/events.json","paper":"https://pith.science/paper/53LB4EDH"},"agent_actions":{"view_html":"https://pith.science/pith/53LB4EDHW3KWVDDKPFCBUFR4XI","download_json":"https://pith.science/pith/53LB4EDHW3KWVDDKPFCBUFR4XI.json","view_paper":"https://pith.science/paper/53LB4EDH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.03822&json=true","fetch_graph":"https://pith.science/api/pith-number/53LB4EDHW3KWVDDKPFCBUFR4XI/graph.json","fetch_events":"https://pith.science/api/pith-number/53LB4EDHW3KWVDDKPFCBUFR4XI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/53LB4EDHW3KWVDDKPFCBUFR4XI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/53LB4EDHW3KWVDDKPFCBUFR4XI/action/storage_attestation","attest_author":"https://pith.science/pith/53LB4EDHW3KWVDDKPFCBUFR4XI/action/author_attestation","sign_citation":"https://pith.science/pith/53LB4EDHW3KWVDDKPFCBUFR4XI/action/citation_signature","submit_replication":"https://pith.science/pith/53LB4EDHW3KWVDDKPFCBUFR4XI/action/replication_record"}},"created_at":"2026-07-05T05:04:32.629414+00:00","updated_at":"2026-07-05T05:04:32.629414+00:00"}