{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4FPHHL7RE7DZMPQNPOQU2NFOVA","short_pith_number":"pith:4FPHHL7R","schema_version":"1.0","canonical_sha256":"e15e73aff127c7963e0d7ba14d34aea8336bfe9f4144df51e63d10f96e3c9c2e","source":{"kind":"arxiv","id":"2605.14917","version":1},"attestation_state":"computed","paper":{"title":"A Mutual Information Lower Bound for Multimodal Regression Active Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CE","cs.IT","math.IT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Akshat Kaushal, Leonardo Ferreira Guilhoto, Paris Perdikaris","submitted_at":"2026-05-14T14:50:47Z","abstract_excerpt":"Active learning for continuous regression has lacked an acquisition function that targets epistemic uncertainty when the predictive distribution is multimodal: variance misses modal disagreement, and information-theoretic targets like BALD are designed for discrete outputs. We introduce a Two-Index framework that makes this separation explicit: one stochastic index selects among competing model hypotheses (epistemic source), while a second governs within-hypothesis randomness (aleatoric source). An entropy decomposition within the framework identifies the mutual information between the output "},"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":"2605.14917","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T14:50:47Z","cross_cats_sorted":["cs.CE","cs.IT","math.IT","stat.ML"],"title_canon_sha256":"936df367aee20d3f71cc73354d6f98c3b087088c8da86dfbb58e56e6229fb369","abstract_canon_sha256":"2aae69250184a341d9be06f07d5027a143184dff2f53172901f81b63c9ce95e7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:55.697138Z","signature_b64":"LPS1QxHb06AICBeZJeDfYTqKL6Nttgnu1upxUt6fVAPxFRgPeLM9WMTpb0tS6OoRLj9etncZIxc/RUJXcwveCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e15e73aff127c7963e0d7ba14d34aea8336bfe9f4144df51e63d10f96e3c9c2e","last_reissued_at":"2026-05-17T23:38:55.696472Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:55.696472Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Mutual Information Lower Bound for Multimodal Regression Active Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CE","cs.IT","math.IT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Akshat Kaushal, Leonardo Ferreira Guilhoto, Paris Perdikaris","submitted_at":"2026-05-14T14:50:47Z","abstract_excerpt":"Active learning for continuous regression has lacked an acquisition function that targets epistemic uncertainty when the predictive distribution is multimodal: variance misses modal disagreement, and information-theoretic targets like BALD are designed for discrete outputs. We introduce a Two-Index framework that makes this separation explicit: one stochastic index selects among competing model hypotheses (epistemic source), while a second governs within-hypothesis randomness (aleatoric source). An entropy decomposition within the framework identifies the mutual information between the output "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.14917","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":""},"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":"2605.14917","created_at":"2026-05-17T23:38:55.696583+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.14917v1","created_at":"2026-05-17T23:38:55.696583+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14917","created_at":"2026-05-17T23:38:55.696583+00:00"},{"alias_kind":"pith_short_12","alias_value":"4FPHHL7RE7DZ","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"4FPHHL7RE7DZMPQN","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"4FPHHL7R","created_at":"2026-05-18T12:33:37.589309+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/4FPHHL7RE7DZMPQNPOQU2NFOVA","json":"https://pith.science/pith/4FPHHL7RE7DZMPQNPOQU2NFOVA.json","graph_json":"https://pith.science/api/pith-number/4FPHHL7RE7DZMPQNPOQU2NFOVA/graph.json","events_json":"https://pith.science/api/pith-number/4FPHHL7RE7DZMPQNPOQU2NFOVA/events.json","paper":"https://pith.science/paper/4FPHHL7R"},"agent_actions":{"view_html":"https://pith.science/pith/4FPHHL7RE7DZMPQNPOQU2NFOVA","download_json":"https://pith.science/pith/4FPHHL7RE7DZMPQNPOQU2NFOVA.json","view_paper":"https://pith.science/paper/4FPHHL7R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.14917&json=true","fetch_graph":"https://pith.science/api/pith-number/4FPHHL7RE7DZMPQNPOQU2NFOVA/graph.json","fetch_events":"https://pith.science/api/pith-number/4FPHHL7RE7DZMPQNPOQU2NFOVA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4FPHHL7RE7DZMPQNPOQU2NFOVA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4FPHHL7RE7DZMPQNPOQU2NFOVA/action/storage_attestation","attest_author":"https://pith.science/pith/4FPHHL7RE7DZMPQNPOQU2NFOVA/action/author_attestation","sign_citation":"https://pith.science/pith/4FPHHL7RE7DZMPQNPOQU2NFOVA/action/citation_signature","submit_replication":"https://pith.science/pith/4FPHHL7RE7DZMPQNPOQU2NFOVA/action/replication_record"}},"created_at":"2026-05-17T23:38:55.696583+00:00","updated_at":"2026-05-17T23:38:55.696583+00:00"}