{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AP3OSNVIYAKZ6B4JC7LJGKQCBN","short_pith_number":"pith:AP3OSNVI","schema_version":"1.0","canonical_sha256":"03f6e936a8c0159f078917d6932a020b7e6243094ed101ef6d09b83e5ffb0eba","source":{"kind":"arxiv","id":"2412.18604","version":1},"attestation_state":"computed","paper":{"title":"Explaining in Diffusion: Explaining a Classifier Through Hierarchical Semantics with Text-to-Image Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Pinar Yanardag, Ritika Allada, Tahira Kazimi","submitted_at":"2024-12-24T18:58:28Z","abstract_excerpt":"Classifiers are important components in many computer vision tasks, serving as the foundational backbone of a wide variety of models employed across diverse applications. However, understanding the decision-making process of classifiers remains a significant challenge. We propose DiffEx, a novel method that leverages the capabilities of text-to-image diffusion models to explain classifier decisions. Unlike traditional GAN-based explainability models, which are limited to simple, single-concept analyses and typically require training a new model for each classifier, our approach can explain cla"},"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":"2412.18604","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-24T18:58:28Z","cross_cats_sorted":[],"title_canon_sha256":"046ab97c0441a74ef0c9c276af3ac2ba185c08618f40cf86c65de0345c6738ad","abstract_canon_sha256":"a2a878d5d4135169877d98dc8ed7fb36247480395c47f83461d456054c64b39a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:58.070969Z","signature_b64":"V/QG4UcRHHGmYX5t/hkEUWVMhJN/c73QT/67QfpBcdvvwjL2lxeeaCn1lyKQpilloc9Gd1ETD94OlrHirfifDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03f6e936a8c0159f078917d6932a020b7e6243094ed101ef6d09b83e5ffb0eba","last_reissued_at":"2026-07-05T09:53:58.070523Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:58.070523Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Explaining in Diffusion: Explaining a Classifier Through Hierarchical Semantics with Text-to-Image Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Pinar Yanardag, Ritika Allada, Tahira Kazimi","submitted_at":"2024-12-24T18:58:28Z","abstract_excerpt":"Classifiers are important components in many computer vision tasks, serving as the foundational backbone of a wide variety of models employed across diverse applications. However, understanding the decision-making process of classifiers remains a significant challenge. We propose DiffEx, a novel method that leverages the capabilities of text-to-image diffusion models to explain classifier decisions. Unlike traditional GAN-based explainability models, which are limited to simple, single-concept analyses and typically require training a new model for each classifier, our approach can explain cla"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.18604","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/2412.18604/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":"2412.18604","created_at":"2026-07-05T09:53:58.070577+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.18604v1","created_at":"2026-07-05T09:53:58.070577+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.18604","created_at":"2026-07-05T09:53:58.070577+00:00"},{"alias_kind":"pith_short_12","alias_value":"AP3OSNVIYAKZ","created_at":"2026-07-05T09:53:58.070577+00:00"},{"alias_kind":"pith_short_16","alias_value":"AP3OSNVIYAKZ6B4J","created_at":"2026-07-05T09:53:58.070577+00:00"},{"alias_kind":"pith_short_8","alias_value":"AP3OSNVI","created_at":"2026-07-05T09:53:58.070577+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.23758","citing_title":"LoRAShop: Training-Free Multi-Concept Image Generation and Editing with Rectified Flow Transformers","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AP3OSNVIYAKZ6B4JC7LJGKQCBN","json":"https://pith.science/pith/AP3OSNVIYAKZ6B4JC7LJGKQCBN.json","graph_json":"https://pith.science/api/pith-number/AP3OSNVIYAKZ6B4JC7LJGKQCBN/graph.json","events_json":"https://pith.science/api/pith-number/AP3OSNVIYAKZ6B4JC7LJGKQCBN/events.json","paper":"https://pith.science/paper/AP3OSNVI"},"agent_actions":{"view_html":"https://pith.science/pith/AP3OSNVIYAKZ6B4JC7LJGKQCBN","download_json":"https://pith.science/pith/AP3OSNVIYAKZ6B4JC7LJGKQCBN.json","view_paper":"https://pith.science/paper/AP3OSNVI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.18604&json=true","fetch_graph":"https://pith.science/api/pith-number/AP3OSNVIYAKZ6B4JC7LJGKQCBN/graph.json","fetch_events":"https://pith.science/api/pith-number/AP3OSNVIYAKZ6B4JC7LJGKQCBN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AP3OSNVIYAKZ6B4JC7LJGKQCBN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AP3OSNVIYAKZ6B4JC7LJGKQCBN/action/storage_attestation","attest_author":"https://pith.science/pith/AP3OSNVIYAKZ6B4JC7LJGKQCBN/action/author_attestation","sign_citation":"https://pith.science/pith/AP3OSNVIYAKZ6B4JC7LJGKQCBN/action/citation_signature","submit_replication":"https://pith.science/pith/AP3OSNVIYAKZ6B4JC7LJGKQCBN/action/replication_record"}},"created_at":"2026-07-05T09:53:58.070577+00:00","updated_at":"2026-07-05T09:53:58.070577+00:00"}