{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:HAXJKXGJB6J5MJ6PRVTU2T3P4R","short_pith_number":"pith:HAXJKXGJ","schema_version":"1.0","canonical_sha256":"382e955cc90f93d627cf8d674d4f6fe475c194b478c700a751461918a3136941","source":{"kind":"arxiv","id":"2311.04157","version":3},"attestation_state":"computed","paper":{"title":"A Simple Interpretable Transformer for Fine-Grained Image Classification and Analysis","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Anuj Karpatne, Arpita Chowdhury, Bryan Carstens, Charles Stewart, Daniel Rubenstein, David Carlyn, Dipanjyoti Paul, Feng-Ju Chang, Kaiya L. Provost, Samuel Stevens, Tanya Berger-Wolf, Wei-Lun Chao, Xinqi Xiong, Yu Su","submitted_at":"2023-11-07T17:32:55Z","abstract_excerpt":"We present a novel usage of Transformers to make image classification interpretable. Unlike mainstream classifiers that wait until the last fully connected layer to incorporate class information to make predictions, we investigate a proactive approach, asking each class to search for itself in an image. We realize this idea via a Transformer encoder-decoder inspired by DEtection TRansformer (DETR). We learn \"class-specific\" queries (one for each class) as input to the decoder, enabling each class to localize its patterns in an image via cross-attention. We name our approach INterpretable TRans"},"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":"2311.04157","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-07T17:32:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5a3c3d211d0a02e90db4f0f0156d8a6217c34e5d9b64ae014bcf593b446b4fff","abstract_canon_sha256":"b037dff18e44bbfbf66f7ed9eb63bd6bf762a80f19063c7de20719e1a21e047d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:31:44.324872Z","signature_b64":"8GZLxOcyo+b+6CXfTkrSTO2VxaN2tz6NiQtP/ROyCLf7SPGu/k35M3rgp0LQO46WAljGe4daMLz9DnNAargRDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"382e955cc90f93d627cf8d674d4f6fe475c194b478c700a751461918a3136941","last_reissued_at":"2026-07-05T08:31:44.324370Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:31:44.324370Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Simple Interpretable Transformer for Fine-Grained Image Classification and Analysis","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Anuj Karpatne, Arpita Chowdhury, Bryan Carstens, Charles Stewart, Daniel Rubenstein, David Carlyn, Dipanjyoti Paul, Feng-Ju Chang, Kaiya L. Provost, Samuel Stevens, Tanya Berger-Wolf, Wei-Lun Chao, Xinqi Xiong, Yu Su","submitted_at":"2023-11-07T17:32:55Z","abstract_excerpt":"We present a novel usage of Transformers to make image classification interpretable. Unlike mainstream classifiers that wait until the last fully connected layer to incorporate class information to make predictions, we investigate a proactive approach, asking each class to search for itself in an image. We realize this idea via a Transformer encoder-decoder inspired by DEtection TRansformer (DETR). We learn \"class-specific\" queries (one for each class) as input to the decoder, enabling each class to localize its patterns in an image via cross-attention. We name our approach INterpretable TRans"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.04157","kind":"arxiv","version":3},"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/2311.04157/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":"2311.04157","created_at":"2026-07-05T08:31:44.324433+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.04157v3","created_at":"2026-07-05T08:31:44.324433+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.04157","created_at":"2026-07-05T08:31:44.324433+00:00"},{"alias_kind":"pith_short_12","alias_value":"HAXJKXGJB6J5","created_at":"2026-07-05T08:31:44.324433+00:00"},{"alias_kind":"pith_short_16","alias_value":"HAXJKXGJB6J5MJ6P","created_at":"2026-07-05T08:31:44.324433+00:00"},{"alias_kind":"pith_short_8","alias_value":"HAXJKXGJ","created_at":"2026-07-05T08:31:44.324433+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2507.14787","citing_title":"FOCUS: Fused Observation of Channels for Unveiling Spectra","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HAXJKXGJB6J5MJ6PRVTU2T3P4R","json":"https://pith.science/pith/HAXJKXGJB6J5MJ6PRVTU2T3P4R.json","graph_json":"https://pith.science/api/pith-number/HAXJKXGJB6J5MJ6PRVTU2T3P4R/graph.json","events_json":"https://pith.science/api/pith-number/HAXJKXGJB6J5MJ6PRVTU2T3P4R/events.json","paper":"https://pith.science/paper/HAXJKXGJ"},"agent_actions":{"view_html":"https://pith.science/pith/HAXJKXGJB6J5MJ6PRVTU2T3P4R","download_json":"https://pith.science/pith/HAXJKXGJB6J5MJ6PRVTU2T3P4R.json","view_paper":"https://pith.science/paper/HAXJKXGJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.04157&json=true","fetch_graph":"https://pith.science/api/pith-number/HAXJKXGJB6J5MJ6PRVTU2T3P4R/graph.json","fetch_events":"https://pith.science/api/pith-number/HAXJKXGJB6J5MJ6PRVTU2T3P4R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HAXJKXGJB6J5MJ6PRVTU2T3P4R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HAXJKXGJB6J5MJ6PRVTU2T3P4R/action/storage_attestation","attest_author":"https://pith.science/pith/HAXJKXGJB6J5MJ6PRVTU2T3P4R/action/author_attestation","sign_citation":"https://pith.science/pith/HAXJKXGJB6J5MJ6PRVTU2T3P4R/action/citation_signature","submit_replication":"https://pith.science/pith/HAXJKXGJB6J5MJ6PRVTU2T3P4R/action/replication_record"}},"created_at":"2026-07-05T08:31:44.324433+00:00","updated_at":"2026-07-05T08:31:44.324433+00:00"}