{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RLXTRHVSDKWGOPMDC6MC2FYZLL","short_pith_number":"pith:RLXTRHVS","schema_version":"1.0","canonical_sha256":"8aef389eb21aac673d8317982d17195aee40083913f19013332c1b47a332aeb2","source":{"kind":"arxiv","id":"2312.11548","version":2},"attestation_state":"computed","paper":{"title":"Learning Interpretable Queries for Explainable Image Classification with Information Pursuit","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aditya Chattopadhyay, Gitta Kutyniok, Hector Andrade-Loarca, Kwan Ho Ryan Chan, R\\'ene Vidal, Stefan Kolek","submitted_at":"2023-12-16T21:43:07Z","abstract_excerpt":"Information Pursuit (IP) is an explainable prediction algorithm that greedily selects a sequence of interpretable queries about the data in order of information gain, updating its posterior at each step based on observed query-answer pairs. The standard paradigm uses hand-crafted dictionaries of potential data queries curated by a domain expert or a large language model after a human prompt. However, in practice, hand-crafted dictionaries are limited by the expertise of the curator and the heuristics of prompt engineering. This paper introduces a novel approach: learning a dictionary of interp"},"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":"2312.11548","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-16T21:43:07Z","cross_cats_sorted":[],"title_canon_sha256":"01d7a0839bfcfaad97ba205269497ffa919bdfd04522e22146570df74883b079","abstract_canon_sha256":"c7b05d02f13841e5b02a89c07e0a4426ae3dfc246240510d1209e9e83db827ec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:48:19.781893Z","signature_b64":"/vRaFr/dYobtqIuMK0TXVmcg/lPTegnmzmqydDLbuObZ8Sp/v5xcxXrHpSJxfDbbrjLI4jR/b7OcfFoRBIMTCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8aef389eb21aac673d8317982d17195aee40083913f19013332c1b47a332aeb2","last_reissued_at":"2026-07-05T11:48:19.781469Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:48:19.781469Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Interpretable Queries for Explainable Image Classification with Information Pursuit","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aditya Chattopadhyay, Gitta Kutyniok, Hector Andrade-Loarca, Kwan Ho Ryan Chan, R\\'ene Vidal, Stefan Kolek","submitted_at":"2023-12-16T21:43:07Z","abstract_excerpt":"Information Pursuit (IP) is an explainable prediction algorithm that greedily selects a sequence of interpretable queries about the data in order of information gain, updating its posterior at each step based on observed query-answer pairs. The standard paradigm uses hand-crafted dictionaries of potential data queries curated by a domain expert or a large language model after a human prompt. However, in practice, hand-crafted dictionaries are limited by the expertise of the curator and the heuristics of prompt engineering. This paper introduces a novel approach: learning a dictionary of interp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.11548","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/2312.11548/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":"2312.11548","created_at":"2026-07-05T11:48:19.781526+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.11548v2","created_at":"2026-07-05T11:48:19.781526+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.11548","created_at":"2026-07-05T11:48:19.781526+00:00"},{"alias_kind":"pith_short_12","alias_value":"RLXTRHVSDKWG","created_at":"2026-07-05T11:48:19.781526+00:00"},{"alias_kind":"pith_short_16","alias_value":"RLXTRHVSDKWGOPMD","created_at":"2026-07-05T11:48:19.781526+00:00"},{"alias_kind":"pith_short_8","alias_value":"RLXTRHVS","created_at":"2026-07-05T11:48:19.781526+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/RLXTRHVSDKWGOPMDC6MC2FYZLL","json":"https://pith.science/pith/RLXTRHVSDKWGOPMDC6MC2FYZLL.json","graph_json":"https://pith.science/api/pith-number/RLXTRHVSDKWGOPMDC6MC2FYZLL/graph.json","events_json":"https://pith.science/api/pith-number/RLXTRHVSDKWGOPMDC6MC2FYZLL/events.json","paper":"https://pith.science/paper/RLXTRHVS"},"agent_actions":{"view_html":"https://pith.science/pith/RLXTRHVSDKWGOPMDC6MC2FYZLL","download_json":"https://pith.science/pith/RLXTRHVSDKWGOPMDC6MC2FYZLL.json","view_paper":"https://pith.science/paper/RLXTRHVS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.11548&json=true","fetch_graph":"https://pith.science/api/pith-number/RLXTRHVSDKWGOPMDC6MC2FYZLL/graph.json","fetch_events":"https://pith.science/api/pith-number/RLXTRHVSDKWGOPMDC6MC2FYZLL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RLXTRHVSDKWGOPMDC6MC2FYZLL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RLXTRHVSDKWGOPMDC6MC2FYZLL/action/storage_attestation","attest_author":"https://pith.science/pith/RLXTRHVSDKWGOPMDC6MC2FYZLL/action/author_attestation","sign_citation":"https://pith.science/pith/RLXTRHVSDKWGOPMDC6MC2FYZLL/action/citation_signature","submit_replication":"https://pith.science/pith/RLXTRHVSDKWGOPMDC6MC2FYZLL/action/replication_record"}},"created_at":"2026-07-05T11:48:19.781526+00:00","updated_at":"2026-07-05T11:48:19.781526+00:00"}