{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:63KKEEZNQPPQHXGICC52RWPVGO","short_pith_number":"pith:63KKEEZN","schema_version":"1.0","canonical_sha256":"f6d4a2132d83df03dcc810bba8d9f5338a95c739c9fedec4a490e3f8dbacd6b1","source":{"kind":"arxiv","id":"2306.15058","version":1},"attestation_state":"computed","paper":{"title":"BatchGFN: Generative Flow Networks for Batch Active Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrew Jesson, Moksh Jain, Nikolay Malkin, Salem Lahlou, Shreshth A. Malik, Tristan Deleu, Yarin Gal, Yoshua Bengio","submitted_at":"2023-06-26T20:41:36Z","abstract_excerpt":"We introduce BatchGFN -- a novel approach for pool-based active learning that uses generative flow networks to sample sets of data points proportional to a batch reward. With an appropriate reward function to quantify the utility of acquiring a batch, such as the joint mutual information between the batch and the model parameters, BatchGFN is able to construct highly informative batches for active learning in a principled way. We show our approach enables sampling near-optimal utility batches at inference time with a single forward pass per point in the batch in toy regression problems. This a"},"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":"2306.15058","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-26T20:41:36Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"642b7626372f298912be276da486857209c4a19bab50cb801bd6809a311715fb","abstract_canon_sha256":"1bf9ed4fb75b01cfc895b0af892bd346b06d726345cef709ca01a1544c0183cf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:24:53.361079Z","signature_b64":"epJVKJmHM8yPw9FdaUe9nnpJ+wo76u/M6Rc1WJEm09CCpeUI3jgPh1WOEZOakMV/kQKT2MNCNlnakuiK0ox9Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f6d4a2132d83df03dcc810bba8d9f5338a95c739c9fedec4a490e3f8dbacd6b1","last_reissued_at":"2026-07-05T06:24:53.360628Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:24:53.360628Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BatchGFN: Generative Flow Networks for Batch Active Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrew Jesson, Moksh Jain, Nikolay Malkin, Salem Lahlou, Shreshth A. Malik, Tristan Deleu, Yarin Gal, Yoshua Bengio","submitted_at":"2023-06-26T20:41:36Z","abstract_excerpt":"We introduce BatchGFN -- a novel approach for pool-based active learning that uses generative flow networks to sample sets of data points proportional to a batch reward. With an appropriate reward function to quantify the utility of acquiring a batch, such as the joint mutual information between the batch and the model parameters, BatchGFN is able to construct highly informative batches for active learning in a principled way. We show our approach enables sampling near-optimal utility batches at inference time with a single forward pass per point in the batch in toy regression problems. This a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.15058","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/2306.15058/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":"2306.15058","created_at":"2026-07-05T06:24:53.360693+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.15058v1","created_at":"2026-07-05T06:24:53.360693+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.15058","created_at":"2026-07-05T06:24:53.360693+00:00"},{"alias_kind":"pith_short_12","alias_value":"63KKEEZNQPPQ","created_at":"2026-07-05T06:24:53.360693+00:00"},{"alias_kind":"pith_short_16","alias_value":"63KKEEZNQPPQHXGI","created_at":"2026-07-05T06:24:53.360693+00:00"},{"alias_kind":"pith_short_8","alias_value":"63KKEEZN","created_at":"2026-07-05T06:24:53.360693+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.00704","citing_title":"Why Pool When You Can Flow? Active Learning with GFlowNets","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/63KKEEZNQPPQHXGICC52RWPVGO","json":"https://pith.science/pith/63KKEEZNQPPQHXGICC52RWPVGO.json","graph_json":"https://pith.science/api/pith-number/63KKEEZNQPPQHXGICC52RWPVGO/graph.json","events_json":"https://pith.science/api/pith-number/63KKEEZNQPPQHXGICC52RWPVGO/events.json","paper":"https://pith.science/paper/63KKEEZN"},"agent_actions":{"view_html":"https://pith.science/pith/63KKEEZNQPPQHXGICC52RWPVGO","download_json":"https://pith.science/pith/63KKEEZNQPPQHXGICC52RWPVGO.json","view_paper":"https://pith.science/paper/63KKEEZN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.15058&json=true","fetch_graph":"https://pith.science/api/pith-number/63KKEEZNQPPQHXGICC52RWPVGO/graph.json","fetch_events":"https://pith.science/api/pith-number/63KKEEZNQPPQHXGICC52RWPVGO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/63KKEEZNQPPQHXGICC52RWPVGO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/63KKEEZNQPPQHXGICC52RWPVGO/action/storage_attestation","attest_author":"https://pith.science/pith/63KKEEZNQPPQHXGICC52RWPVGO/action/author_attestation","sign_citation":"https://pith.science/pith/63KKEEZNQPPQHXGICC52RWPVGO/action/citation_signature","submit_replication":"https://pith.science/pith/63KKEEZNQPPQHXGICC52RWPVGO/action/replication_record"}},"created_at":"2026-07-05T06:24:53.360693+00:00","updated_at":"2026-07-05T06:24:53.360693+00:00"}