{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:55YUHH3ADN5UIIM2IL5NKL7ES7","short_pith_number":"pith:55YUHH3A","schema_version":"1.0","canonical_sha256":"ef71439f601b7b44219a42fad52fe497f0fa61db398e7fa1ffed1de812f8de7a","source":{"kind":"arxiv","id":"2308.12562","version":1},"attestation_state":"computed","paper":{"title":"Variational Information Pursuit with Large Language and Multimodal Models for Interpretable Predictions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aditya Chattopadhyay, Benjamin David Haeffele, Kwan Ho Ryan Chan, Rene Vidal","submitted_at":"2023-08-24T05:04:10Z","abstract_excerpt":"Variational Information Pursuit (V-IP) is a framework for making interpretable predictions by design by sequentially selecting a short chain of task-relevant, user-defined and interpretable queries about the data that are most informative for the task. While this allows for built-in interpretability in predictive models, applying V-IP to any task requires data samples with dense concept-labeling by domain experts, limiting the application of V-IP to small-scale tasks where manual data annotation is feasible. In this work, we extend the V-IP framework with Foundational Models (FMs) to address t"},"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":"2308.12562","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-24T05:04:10Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"c2cdb74c128efdf50f4b0a719093742c1e6502e9257bf9cc3eb9e7a641b924e7","abstract_canon_sha256":"44148059fd0b3625b2609ec3e0fd47d7b6a0cc7223f03767c549bc0e69d3aa8a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:44:14.444858Z","signature_b64":"txXxiD/gti5TPmznqLPl9JtUNVo/TpB2GLGKs70VXzGH0iMNpuTYEEtUJg7XmUbkXT7slgVueuuFfu+xPnO1BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef71439f601b7b44219a42fad52fe497f0fa61db398e7fa1ffed1de812f8de7a","last_reissued_at":"2026-07-05T06:44:14.444445Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:44:14.444445Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Variational Information Pursuit with Large Language and Multimodal Models for Interpretable Predictions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aditya Chattopadhyay, Benjamin David Haeffele, Kwan Ho Ryan Chan, Rene Vidal","submitted_at":"2023-08-24T05:04:10Z","abstract_excerpt":"Variational Information Pursuit (V-IP) is a framework for making interpretable predictions by design by sequentially selecting a short chain of task-relevant, user-defined and interpretable queries about the data that are most informative for the task. While this allows for built-in interpretability in predictive models, applying V-IP to any task requires data samples with dense concept-labeling by domain experts, limiting the application of V-IP to small-scale tasks where manual data annotation is feasible. In this work, we extend the V-IP framework with Foundational Models (FMs) to address t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.12562","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/2308.12562/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":"2308.12562","created_at":"2026-07-05T06:44:14.444502+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.12562v1","created_at":"2026-07-05T06:44:14.444502+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.12562","created_at":"2026-07-05T06:44:14.444502+00:00"},{"alias_kind":"pith_short_12","alias_value":"55YUHH3ADN5U","created_at":"2026-07-05T06:44:14.444502+00:00"},{"alias_kind":"pith_short_16","alias_value":"55YUHH3ADN5UIIM2","created_at":"2026-07-05T06:44:14.444502+00:00"},{"alias_kind":"pith_short_8","alias_value":"55YUHH3A","created_at":"2026-07-05T06:44:14.444502+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/55YUHH3ADN5UIIM2IL5NKL7ES7","json":"https://pith.science/pith/55YUHH3ADN5UIIM2IL5NKL7ES7.json","graph_json":"https://pith.science/api/pith-number/55YUHH3ADN5UIIM2IL5NKL7ES7/graph.json","events_json":"https://pith.science/api/pith-number/55YUHH3ADN5UIIM2IL5NKL7ES7/events.json","paper":"https://pith.science/paper/55YUHH3A"},"agent_actions":{"view_html":"https://pith.science/pith/55YUHH3ADN5UIIM2IL5NKL7ES7","download_json":"https://pith.science/pith/55YUHH3ADN5UIIM2IL5NKL7ES7.json","view_paper":"https://pith.science/paper/55YUHH3A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.12562&json=true","fetch_graph":"https://pith.science/api/pith-number/55YUHH3ADN5UIIM2IL5NKL7ES7/graph.json","fetch_events":"https://pith.science/api/pith-number/55YUHH3ADN5UIIM2IL5NKL7ES7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/55YUHH3ADN5UIIM2IL5NKL7ES7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/55YUHH3ADN5UIIM2IL5NKL7ES7/action/storage_attestation","attest_author":"https://pith.science/pith/55YUHH3ADN5UIIM2IL5NKL7ES7/action/author_attestation","sign_citation":"https://pith.science/pith/55YUHH3ADN5UIIM2IL5NKL7ES7/action/citation_signature","submit_replication":"https://pith.science/pith/55YUHH3ADN5UIIM2IL5NKL7ES7/action/replication_record"}},"created_at":"2026-07-05T06:44:14.444502+00:00","updated_at":"2026-07-05T06:44:14.444502+00:00"}