{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:Z4HV5APYIYLEDVBKNR4TCYLBJI","short_pith_number":"pith:Z4HV5APY","schema_version":"1.0","canonical_sha256":"cf0f5e81f8461641d42a6c793161614a07d8952de24fdac7c9bae967dd989624","source":{"kind":"arxiv","id":"2106.09675","version":2},"attestation_state":"computed","paper":{"title":"Gone Fishing: Neural Active Learning with Fisher Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Akshay Krishnamurthy, Jordan T. Ash, Sham Kakade, Surbhi Goel","submitted_at":"2021-06-17T17:26:31Z","abstract_excerpt":"There is an increasing need for effective active learning algorithms that are compatible with deep neural networks. This paper motivates and revisits a classic, Fisher-based active selection objective, and proposes BAIT, a practical, tractable, and high-performing algorithm that makes it viable for use with neural models. BAIT draws inspiration from the theoretical analysis of maximum likelihood estimators (MLE) for parametric models. It selects batches of samples by optimizing a bound on the MLE error in terms of the Fisher information, which we show can be implemented efficiently at scale by"},"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":"2106.09675","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-17T17:26:31Z","cross_cats_sorted":[],"title_canon_sha256":"59ad52fce24e35bbd553a2ed2ad6817ebb83a3855620906c86d4a3ab22224c25","abstract_canon_sha256":"45d29f77d2893bfc10e0085dcdf2e5fd8742a73d892fd10847b6d531585015a5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:40:38.487920Z","signature_b64":"hw5AEIGSc4TkXtkH6YAcdaVE2O6qRVoQ0WzZsKQDmFCCtMzLRJduqdT5mibOhkbgf0Zp7rV3i/GpdT0QByCkDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf0f5e81f8461641d42a6c793161614a07d8952de24fdac7c9bae967dd989624","last_reissued_at":"2026-07-05T03:40:38.487420Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:40:38.487420Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gone Fishing: Neural Active Learning with Fisher Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Akshay Krishnamurthy, Jordan T. Ash, Sham Kakade, Surbhi Goel","submitted_at":"2021-06-17T17:26:31Z","abstract_excerpt":"There is an increasing need for effective active learning algorithms that are compatible with deep neural networks. This paper motivates and revisits a classic, Fisher-based active selection objective, and proposes BAIT, a practical, tractable, and high-performing algorithm that makes it viable for use with neural models. BAIT draws inspiration from the theoretical analysis of maximum likelihood estimators (MLE) for parametric models. It selects batches of samples by optimizing a bound on the MLE error in terms of the Fisher information, which we show can be implemented efficiently at scale by"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.09675","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/2106.09675/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":"2106.09675","created_at":"2026-07-05T03:40:38.487489+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.09675v2","created_at":"2026-07-05T03:40:38.487489+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.09675","created_at":"2026-07-05T03:40:38.487489+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z4HV5APYIYLE","created_at":"2026-07-05T03:40:38.487489+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z4HV5APYIYLEDVBK","created_at":"2026-07-05T03:40:38.487489+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z4HV5APY","created_at":"2026-07-05T03:40:38.487489+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z4HV5APYIYLEDVBKNR4TCYLBJI","json":"https://pith.science/pith/Z4HV5APYIYLEDVBKNR4TCYLBJI.json","graph_json":"https://pith.science/api/pith-number/Z4HV5APYIYLEDVBKNR4TCYLBJI/graph.json","events_json":"https://pith.science/api/pith-number/Z4HV5APYIYLEDVBKNR4TCYLBJI/events.json","paper":"https://pith.science/paper/Z4HV5APY"},"agent_actions":{"view_html":"https://pith.science/pith/Z4HV5APYIYLEDVBKNR4TCYLBJI","download_json":"https://pith.science/pith/Z4HV5APYIYLEDVBKNR4TCYLBJI.json","view_paper":"https://pith.science/paper/Z4HV5APY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.09675&json=true","fetch_graph":"https://pith.science/api/pith-number/Z4HV5APYIYLEDVBKNR4TCYLBJI/graph.json","fetch_events":"https://pith.science/api/pith-number/Z4HV5APYIYLEDVBKNR4TCYLBJI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z4HV5APYIYLEDVBKNR4TCYLBJI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z4HV5APYIYLEDVBKNR4TCYLBJI/action/storage_attestation","attest_author":"https://pith.science/pith/Z4HV5APYIYLEDVBKNR4TCYLBJI/action/author_attestation","sign_citation":"https://pith.science/pith/Z4HV5APYIYLEDVBKNR4TCYLBJI/action/citation_signature","submit_replication":"https://pith.science/pith/Z4HV5APYIYLEDVBKNR4TCYLBJI/action/replication_record"}},"created_at":"2026-07-05T03:40:38.487489+00:00","updated_at":"2026-07-05T03:40:38.487489+00:00"}